2168 files changed, 54580 insertions, 29671 deletions

diff --git a/.mailmap b/.mailmap
index 14314e3c5d5e..b344067e0acb 100644
--- a/.mailmap
+++ b/.mailmap
@@ -71,6 +71,9 @@ Chao Yu <chao@kernel.org> <chao2.yu@samsung.com>
 Chao Yu <chao@kernel.org> <yuchao0@huawei.com>
 Chris Chiu <chris.chiu@canonical.com> <chiu@endlessm.com>
 Chris Chiu <chris.chiu@canonical.com> <chiu@endlessos.org>
+Christian Borntraeger <borntraeger@linux.ibm.com> <borntraeger@de.ibm.com>
+Christian Borntraeger <borntraeger@linux.ibm.com> <cborntra@de.ibm.com>
+Christian Borntraeger <borntraeger@linux.ibm.com> <borntrae@de.ibm.com>
 Christophe Ricard <christophe.ricard@gmail.com>
 Christoph Hellwig <hch@lst.de>
 Colin Ian King <colin.king@intel.com> <colin.king@canonical.com>
@@ -123,6 +126,8 @@ Greg Kroah-Hartman <gregkh@suse.de>
 Greg Kroah-Hartman <greg@kroah.com>
 Greg Kurz <groug@kaod.org> <gkurz@linux.vnet.ibm.com>
 Gregory CLEMENT <gregory.clement@bootlin.com> <gregory.clement@free-electrons.com>
+Guo Ren <guoren@kernel.org> <guoren@linux.alibaba.com>
+Guo Ren <guoren@kernel.org> <ren_guo@c-sky.com>
 Gustavo Padovan <gustavo@las.ic.unicamp.br>
 Gustavo Padovan <padovan@profusion.mobi>
 Hanjun Guo <guohanjun@huawei.com> <hanjun.guo@linaro.org>
diff --git a/Documentation/ABI/testing/sysfs-fs-f2fs b/Documentation/ABI/testing/sysfs-fs-f2fs
index f627e705e663..b268e3e18b4a 100644
--- a/Documentation/ABI/testing/sysfs-fs-f2fs
+++ b/Documentation/ABI/testing/sysfs-fs-f2fs
@@ -512,3 +512,19 @@ Date:		July 2021
 Contact:	"Daeho Jeong" <daehojeong@google.com>
 Description:	You can	control the multiplier value of	bdi device readahead window size
 		between 2 (default) and 256 for POSIX_FADV_SEQUENTIAL advise option.
+
+What:		/sys/fs/f2fs/<disk>/max_fragment_chunk
+Date:		August 2021
+Contact:	"Daeho Jeong" <daehojeong@google.com>
+Description:	With "mode=fragment:block" mount options, we can scatter block allocation.
+		f2fs will allocate 1..<max_fragment_chunk> blocks in a chunk and make a hole
+		in the length of 1..<max_fragment_hole> by turns. This value can be set
+		between 1..512 and the default value is 4.
+
+What:		/sys/fs/f2fs/<disk>/max_fragment_hole
+Date:		August 2021
+Contact:	"Daeho Jeong" <daehojeong@google.com>
+Description:	With "mode=fragment:block" mount options, we can scatter block allocation.
+		f2fs will allocate 1..<max_fragment_chunk> blocks in a chunk and make a hole
+		in the length of 1..<max_fragment_hole> by turns. This value can be set
+		between 1..512 and the default value is 4.
diff --git a/Documentation/admin-guide/blockdev/drbd/figures.rst b/Documentation/admin-guide/blockdev/drbd/figures.rst
index bd9a4901fe46..9f73253ea353 100644
--- a/Documentation/admin-guide/blockdev/drbd/figures.rst
+++ b/Documentation/admin-guide/blockdev/drbd/figures.rst
@@ -25,6 +25,6 @@ Sub graphs of DRBD's state transitions
     :alt:   disk-states-8.dot
     :align: center
 
-.. kernel-figure:: node-states-8.dot
-    :alt:   node-states-8.dot
+.. kernel-figure:: peer-states-8.dot
+    :alt:   peer-states-8.dot
     :align: center
diff --git a/Documentation/admin-guide/blockdev/drbd/node-states-8.dot b/Documentation/admin-guide/blockdev/drbd/peer-states-8.dot
index bfa54e1f8016..6dc3954954d6 100644
--- a/Documentation/admin-guide/blockdev/drbd/node-states-8.dot
+++ b/Documentation/admin-guide/blockdev/drbd/peer-states-8.dot
@@ -1,8 +1,3 @@
-digraph node_states {
-	Secondary -> Primary           [ label = "ioctl_set_state()" ]
-	Primary   -> Secondary 	       [ label = "ioctl_set_state()" ]
-}
-
 digraph peer_states {
 	Secondary -> Primary           [ label = "recv state packet" ]
 	Primary   -> Secondary 	       [ label = "recv state packet" ]
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 9725c546a0d4..2fba82431efb 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -1689,6 +1689,8 @@
 			architectures force reset to be always executed
 	i8042.unlock	[HW] Unlock (ignore) the keylock
 	i8042.kbdreset	[HW] Reset device connected to KBD port
+	i8042.probe_defer
+			[HW] Allow deferred probing upon i8042 probe errors
 
 	i810=		[HW,DRM]
 
@@ -2413,8 +2415,12 @@
 			Default is 1 (enabled)
 
 	kvm-intel.emulate_invalid_guest_state=
-			[KVM,Intel] Enable emulation of invalid guest states
-			Default is 0 (disabled)
+			[KVM,Intel] Disable emulation of invalid guest state.
+			Ignored if kvm-intel.enable_unrestricted_guest=1, as
+			guest state is never invalid for unrestricted guests.
+			This param doesn't apply to nested guests (L2), as KVM
+			never emulates invalid L2 guest state.
+			Default is 1 (enabled)
 
 	kvm-intel.flexpriority=
 			[KVM,Intel] Disable FlexPriority feature (TPR shadow).
diff --git a/Documentation/admin-guide/laptops/thinkpad-acpi.rst b/Documentation/admin-guide/laptops/thinkpad-acpi.rst
index 6721a80a2d4f..475eb0e81e4a 100644
--- a/Documentation/admin-guide/laptops/thinkpad-acpi.rst
+++ b/Documentation/admin-guide/laptops/thinkpad-acpi.rst
@@ -1520,15 +1520,15 @@ This sysfs attribute controls the keyboard "face" that will be shown on the
 Lenovo X1 Carbon 2nd gen (2014)'s adaptive keyboard. The value can be read
 and set.
 
-- 1 = Home mode
-- 2 = Web-browser mode
-- 3 = Web-conference mode
-- 4 = Function mode
-- 5 = Layflat mode
+- 0 = Home mode
+- 1 = Web-browser mode
+- 2 = Web-conference mode
+- 3 = Function mode
+- 4 = Layflat mode
 
 For more details about which buttons will appear depending on the mode, please
 review the laptop's user guide:
-http://www.lenovo.com/shop/americas/content/user_guides/x1carbon_2_ug_en.pdf
+https://download.lenovo.com/ibmdl/pub/pc/pccbbs/mobiles_pdf/x1carbon_2_ug_en.pdf
 
 Battery charge control
 ----------------------
diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst
index 426162009ce9..0e486f41185e 100644
--- a/Documentation/admin-guide/sysctl/kernel.rst
+++ b/Documentation/admin-guide/sysctl/kernel.rst
@@ -1099,7 +1099,7 @@ task_delayacct
 ===============
 
 Enables/disables task delay accounting (see
-:doc:`accounting/delay-accounting.rst`). Enabling this feature incurs
+Documentation/accounting/delay-accounting.rst. Enabling this feature incurs
 a small amount of overhead in the scheduler but is useful for debugging
 and performance tuning. It is required by some tools such as iotop.
 
diff --git a/Documentation/arm/marvell.rst b/Documentation/arm/marvell.rst
index 8323c79d321b..9485a5a2e2e9 100644
--- a/Documentation/arm/marvell.rst
+++ b/Documentation/arm/marvell.rst
@@ -104,6 +104,8 @@ Discovery family
 
                 Not supported by the Linux kernel.
 
+  Homepage:
+        https://web.archive.org/web/20110924171043/http://www.marvell.com/embedded-processors/discovery-innovation/
   Core:
 	Feroceon 88fr571-vd ARMv5 compatible
 
@@ -120,6 +122,7 @@ EBU Armada family
         - 88F6707
         - 88F6W11
 
+    - Product infos:   https://web.archive.org/web/20141002083258/http://www.marvell.com/embedded-processors/armada-370/
     - Product Brief:   https://web.archive.org/web/20121115063038/http://www.marvell.com/embedded-processors/armada-300/assets/Marvell_ARMADA_370_SoC.pdf
     - Hardware Spec:   https://web.archive.org/web/20140617183747/http://www.marvell.com/embedded-processors/armada-300/assets/ARMADA370-datasheet.pdf
     - Functional Spec: https://web.archive.org/web/20140617183701/http://www.marvell.com/embedded-processors/armada-300/assets/ARMADA370-FunctionalSpec-datasheet.pdf
@@ -127,9 +130,29 @@ EBU Armada family
   Core:
 	Sheeva ARMv7 compatible PJ4B
 
+  Armada XP Flavors:
+        - MV78230
+        - MV78260
+        - MV78460
+
+    NOTE:
+	not to be confused with the non-SMP 78xx0 SoCs
+
+    - Product infos:   https://web.archive.org/web/20150101215721/http://www.marvell.com/embedded-processors/armada-xp/
+    - Product Brief:   https://web.archive.org/web/20121021173528/http://www.marvell.com/embedded-processors/armada-xp/assets/Marvell-ArmadaXP-SoC-product%20brief.pdf
+    - Functional Spec: https://web.archive.org/web/20180829171131/http://www.marvell.com/embedded-processors/armada-xp/assets/ARMADA-XP-Functional-SpecDatasheet.pdf
+    - Hardware Specs:
+        - https://web.archive.org/web/20141127013651/http://www.marvell.com/embedded-processors/armada-xp/assets/HW_MV78230_OS.PDF
+        - https://web.archive.org/web/20141222000224/http://www.marvell.com/embedded-processors/armada-xp/assets/HW_MV78260_OS.PDF
+        - https://web.archive.org/web/20141222000230/http://www.marvell.com/embedded-processors/armada-xp/assets/HW_MV78460_OS.PDF
+
+  Core:
+	Sheeva ARMv7 compatible Dual-core or Quad-core PJ4B-MP
+
   Armada 375 Flavors:
 	- 88F6720
 
+    - Product infos: https://web.archive.org/web/20140108032402/http://www.marvell.com/embedded-processors/armada-375/
     - Product Brief: https://web.archive.org/web/20131216023516/http://www.marvell.com/embedded-processors/armada-300/assets/ARMADA_375_SoC-01_product_brief.pdf
 
   Core:
@@ -162,29 +185,6 @@ EBU Armada family
   Core:
 	ARM Cortex-A9
 
-  Armada XP Flavors:
-        - MV78230
-        - MV78260
-        - MV78460
-
-    NOTE:
-	not to be confused with the non-SMP 78xx0 SoCs
-
-    Product Brief:
-	https://web.archive.org/web/20121021173528/http://www.marvell.com/embedded-processors/armada-xp/assets/Marvell-ArmadaXP-SoC-product%20brief.pdf
-
-    Functional Spec:
-	https://web.archive.org/web/20180829171131/http://www.marvell.com/embedded-processors/armada-xp/assets/ARMADA-XP-Functional-SpecDatasheet.pdf
-
-    - Hardware Specs:
-
-        - https://web.archive.org/web/20141127013651/http://www.marvell.com/embedded-processors/armada-xp/assets/HW_MV78230_OS.PDF
-        - https://web.archive.org/web/20141222000224/http://www.marvell.com/embedded-processors/armada-xp/assets/HW_MV78260_OS.PDF
-        - https://web.archive.org/web/20141222000230/http://www.marvell.com/embedded-processors/armada-xp/assets/HW_MV78460_OS.PDF
-
-  Core:
-	Sheeva ARMv7 compatible Dual-core or Quad-core PJ4B-MP
-
   Linux kernel mach directory:
 	arch/arm/mach-mvebu
   Linux kernel plat directory:
@@ -436,7 +436,7 @@ Berlin family (Multimedia Solutions)
   - Flavors:
 	- 88DE3010, Armada 1000 (no Linux support)
 		- Core:		Marvell PJ1 (ARMv5TE), Dual-core
-		- Product Brief:	http://www.marvell.com.cn/digital-entertainment/assets/armada_1000_pb.pdf
+		- Product Brief:	https://web.archive.org/web/20131103162620/http://www.marvell.com/digital-entertainment/assets/armada_1000_pb.pdf
 	- 88DE3005, Armada 1500 Mini
 		- Design name:	BG2CD
 		- Core:		ARM Cortex-A9, PL310 L2CC
diff --git a/Documentation/arm64/pointer-authentication.rst b/Documentation/arm64/pointer-authentication.rst
index f127666ea3a8..e5dad2e40aa8 100644
--- a/Documentation/arm64/pointer-authentication.rst
+++ b/Documentation/arm64/pointer-authentication.rst
@@ -53,11 +53,10 @@ The number of bits that the PAC occupies in a pointer is 55 minus the
 virtual address size configured by the kernel. For example, with a
 virtual address size of 48, the PAC is 7 bits wide.
 
-Recent versions of GCC can compile code with APIAKey-based return
-address protection when passed the -msign-return-address option. This
-uses instructions in the HINT space (unless -march=armv8.3-a or higher
-is also passed), and such code can run on systems without the pointer
-authentication extension.
+When ARM64_PTR_AUTH_KERNEL is selected, the kernel will be compiled
+with HINT space pointer authentication instructions protecting
+function returns. Kernels built with this option will work on hardware
+with or without pointer authentication support.
 
 In addition to exec(), keys can also be reinitialized to random values
 using the PR_PAC_RESET_KEYS prctl. A bitmask of PR_PAC_APIAKEY,
diff --git a/Documentation/bpf/index.rst b/Documentation/bpf/index.rst
index 37f273a7e8b6..610450f59e05 100644
--- a/Documentation/bpf/index.rst
+++ b/Documentation/bpf/index.rst
@@ -15,7 +15,7 @@ that goes into great technical depth about the BPF Architecture.
 libbpf
 ======
 
-Documentation/bpf/libbpf/libbpf.rst is a userspace library for loading and interacting with bpf programs.
+Documentation/bpf/libbpf/index.rst is a userspace library for loading and interacting with bpf programs.
 
 BPF Type Format (BTF)
 =====================
diff --git a/Documentation/conf.py b/Documentation/conf.py
index 17f7cee56987..76e5eb5cb62b 100644
--- a/Documentation/conf.py
+++ b/Documentation/conf.py
@@ -249,11 +249,16 @@ except ImportError:
 
 html_static_path = ['sphinx-static']
 
-html_context = {
-    'css_files': [
-        '_static/theme_overrides.css',
-    ],
-}
+html_css_files = [
+    'theme_overrides.css',
+]
+
+if major <= 1 and minor < 8:
+    html_context = {
+        'css_files': [
+            '_static/theme_overrides.css',
+        ],
+    }
 
 # Add any extra paths that contain custom files (such as robots.txt or
 # .htaccess) here, relative to this directory. These files are copied
diff --git a/Documentation/cpu-freq/core.rst b/Documentation/cpu-freq/core.rst
index 33cb90bd1d8f..4ceef8e7217c 100644
--- a/Documentation/cpu-freq/core.rst
+++ b/Documentation/cpu-freq/core.rst
@@ -73,12 +73,12 @@ CPUFREQ_POSTCHANGE.
 The third argument is a struct cpufreq_freqs with the following
 values:
 
-=====	===========================
-cpu	number of the affected CPU
+======	======================================
+policy	a pointer to the struct cpufreq_policy
 old	old frequency
 new	new frequency
 flags	flags of the cpufreq driver
-=====	===========================
+======	======================================
 
 3. CPUFreq Table Generation with Operating Performance Point (OPP)
 ==================================================================
diff --git a/Documentation/devicetree/bindings/arm/sti.yaml b/Documentation/devicetree/bindings/arm/sti.yaml
index b1f28d16d3fb..a41cd8764885 100644
--- a/Documentation/devicetree/bindings/arm/sti.yaml
+++ b/Documentation/devicetree/bindings/arm/sti.yaml
@@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: ST STi Platforms Device Tree Bindings
 
 maintainers:
-  - Patrice Chotard <patrice.chotard@st.com>
+  - Patrice Chotard <patrice.chotard@foss.st.com>
 
 properties:
   $nodename:
diff --git a/Documentation/devicetree/bindings/arm/stm32/st,mlahb.yaml b/Documentation/devicetree/bindings/arm/stm32/st,mlahb.yaml
index 8e711bd202fd..ecb28e90fd11 100644
--- a/Documentation/devicetree/bindings/arm/stm32/st,mlahb.yaml
+++ b/Documentation/devicetree/bindings/arm/stm32/st,mlahb.yaml
@@ -7,8 +7,8 @@ $schema: "http://devicetree.org/meta-schemas/core.yaml#"
 title: STMicroelectronics STM32 ML-AHB interconnect bindings
 
 maintainers:
-  - Fabien Dessenne <fabien.dessenne@st.com>
-  - Arnaud Pouliquen <arnaud.pouliquen@st.com>
+  - Fabien Dessenne <fabien.dessenne@foss.st.com>
+  - Arnaud Pouliquen <arnaud.pouliquen@foss.st.com>
 
 description: |
   These bindings describe the STM32 SoCs ML-AHB interconnect bus which connects
diff --git a/Documentation/devicetree/bindings/arm/stm32/st,stm32-syscon.yaml b/Documentation/devicetree/bindings/arm/stm32/st,stm32-syscon.yaml
index 149afb5df5af..6f846d69c5e1 100644
--- a/Documentation/devicetree/bindings/arm/stm32/st,stm32-syscon.yaml
+++ b/Documentation/devicetree/bindings/arm/stm32/st,stm32-syscon.yaml
@@ -7,8 +7,8 @@ $schema: "http://devicetree.org/meta-schemas/core.yaml#"
 title: STMicroelectronics STM32 Platforms System Controller bindings
 
 maintainers:
-  - Alexandre Torgue <alexandre.torgue@st.com>
-  - Christophe Roullier <christophe.roullier@st.com>
+  - Alexandre Torgue <alexandre.torgue@foss.st.com>
+  - Christophe Roullier <christophe.roullier@foss.st.com>
 
 properties:
   compatible:
diff --git a/Documentation/devicetree/bindings/arm/stm32/stm32.yaml b/Documentation/devicetree/bindings/arm/stm32/stm32.yaml
index 9ac7da01c6c3..bcaf7be3ab37 100644
--- a/Documentation/devicetree/bindings/arm/stm32/stm32.yaml
+++ b/Documentation/devicetree/bindings/arm/stm32/stm32.yaml
@@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: STMicroelectronics STM32 Platforms Device Tree Bindings
 
 maintainers:
-  - Alexandre Torgue <alexandre.torgue@st.com>
+  - Alexandre Torgue <alexandre.torgue@foss.st.com>
 
 properties:
   $nodename:
diff --git a/Documentation/devicetree/bindings/clock/ingenic,cgu.yaml b/Documentation/devicetree/bindings/clock/ingenic,cgu.yaml
index 6e80dbc8b8b9..aa1df03ef4a6 100644
--- a/Documentation/devicetree/bindings/clock/ingenic,cgu.yaml
+++ b/Documentation/devicetree/bindings/clock/ingenic,cgu.yaml
@@ -104,7 +104,7 @@ additionalProperties: false
 
 examples:
   - |
-    #include <dt-bindings/clock/jz4770-cgu.h>
+    #include <dt-bindings/clock/ingenic,jz4770-cgu.h>
     cgu: clock-controller@10000000 {
       compatible = "ingenic,jz4770-cgu", "simple-mfd";
       reg = <0x10000000 0x100>;
diff --git a/Documentation/devicetree/bindings/clock/sifive/fu740-prci.yaml b/Documentation/devicetree/bindings/clock/sifive/fu740-prci.yaml
index e17143cac316..252085a0cf65 100644
--- a/Documentation/devicetree/bindings/clock/sifive/fu740-prci.yaml
+++ b/Documentation/devicetree/bindings/clock/sifive/fu740-prci.yaml
@@ -42,6 +42,9 @@ properties:
   "#clock-cells":
     const: 1
 
+  "#reset-cells":
+    const: 1
+
 required:
   - compatible
   - reg
@@ -57,4 +60,5 @@ examples:
       reg = <0x10000000 0x1000>;
       clocks = <&hfclk>, <&rtcclk>;
       #clock-cells = <1>;
+      #reset-cells = <1>;
     };
diff --git a/Documentation/devicetree/bindings/clock/silabs,si5351.txt b/Documentation/devicetree/bindings/clock/silabs,si5351.txt
index 8fe6f80afade..bfda6af76bee 100644
--- a/Documentation/devicetree/bindings/clock/silabs,si5351.txt
+++ b/Documentation/devicetree/bindings/clock/silabs,si5351.txt
@@ -2,7 +2,7 @@ Binding for Silicon Labs Si5351a/b/c programmable i2c clock generator.
 
 Reference
 [1] Si5351A/B/C Data Sheet
-    https://www.silabs.com/Support%20Documents/TechnicalDocs/Si5351.pdf
+    https://www.skyworksinc.com/-/media/Skyworks/SL/documents/public/data-sheets/Si5351-B.pdf
 
 The Si5351a/b/c are programmable i2c clock generators with up to 8 output
 clocks. Si5351a also has a reduced pin-count package (MSOP10) where only
diff --git a/Documentation/devicetree/bindings/clock/socionext,uniphier-clock.yaml b/Documentation/devicetree/bindings/clock/socionext,uniphier-clock.yaml
index c3930edc410f..9a0cc7341630 100644
--- a/Documentation/devicetree/bindings/clock/socionext,uniphier-clock.yaml
+++ b/Documentation/devicetree/bindings/clock/socionext,uniphier-clock.yaml
@@ -23,6 +23,7 @@ properties:
           - socionext,uniphier-ld11-clock
           - socionext,uniphier-ld20-clock
           - socionext,uniphier-pxs3-clock
+          - socionext,uniphier-nx1-clock
       - description: Media I/O (MIO) clock, SD clock
         enum:
           - socionext,uniphier-ld4-mio-clock
@@ -33,6 +34,7 @@ properties:
           - socionext,uniphier-ld11-mio-clock
           - socionext,uniphier-ld20-sd-clock
           - socionext,uniphier-pxs3-sd-clock
+          - socionext,uniphier-nx1-sd-clock
       - description: Peripheral clock
         enum:
           - socionext,uniphier-ld4-peri-clock
@@ -43,6 +45,10 @@ properties:
           - socionext,uniphier-ld11-peri-clock
           - socionext,uniphier-ld20-peri-clock
           - socionext,uniphier-pxs3-peri-clock
+          - socionext,uniphier-nx1-peri-clock
+      - description: SoC-glue clock
+        enum:
+          - socionext,uniphier-pro4-sg-clock
 
   "#clock-cells":
     const: 1
diff --git a/Documentation/devicetree/bindings/clock/st,stm32mp1-rcc.yaml b/Documentation/devicetree/bindings/clock/st,stm32mp1-rcc.yaml
index 8b1ecb2ecdd5..a0ae4867ed27 100644
--- a/Documentation/devicetree/bindings/clock/st,stm32mp1-rcc.yaml
+++ b/Documentation/devicetree/bindings/clock/st,stm32mp1-rcc.yaml
@@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Reset Clock Controller Binding
 
 maintainers:
-  - Gabriel Fernandez <gabriel.fernandez@st.com>
+  - Gabriel Fernandez <gabriel.fernandez@foss.st.com>
 
 description: |
   The RCC IP is both a reset and a clock controller.
diff --git a/Documentation/devicetree/bindings/crypto/st,stm32-crc.yaml b/Documentation/devicetree/bindings/crypto/st,stm32-crc.yaml
index cee624c14f07..b72e4858f9aa 100644
--- a/Documentation/devicetree/bindings/crypto/st,stm32-crc.yaml
+++ b/Documentation/devicetree/bindings/crypto/st,stm32-crc.yaml
@@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: STMicroelectronics STM32 CRC bindings
 
 maintainers:
-  - Lionel Debieve <lionel.debieve@st.com>
+  - Lionel Debieve <lionel.debieve@foss.st.com>
 
 properties:
   compatible:
diff --git a/Documentation/devicetree/bindings/crypto/st,stm32-cryp.yaml b/Documentation/devicetree/bindings/crypto/st,stm32-cryp.yaml
index a4574552502a..ed23bf94a8e0 100644
--- a/Documentation/devicetree/bindings/crypto/st,stm32-cryp.yaml
+++ b/Documentation/devicetree/bindings/crypto/st,stm32-cryp.yaml
@@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: STMicroelectronics STM32 CRYP bindings
 
 maintainers:
-  - Lionel Debieve <lionel.debieve@st.com>
+  - Lionel Debieve <lionel.debieve@foss.st.com>
 
 properties:
   compatible:
diff --git a/Documentation/devicetree/bindings/crypto/st,stm32-hash.yaml b/Documentation/devicetree/bindings/crypto/st,stm32-hash.yaml
index 6dd658f0912c..10ba94792d95 100644
--- a/Documentation/devicetree/bindings/crypto/st,stm32-hash.yaml
+++ b/Documentation/devicetree/bindings/crypto/st,stm32-hash.yaml
@@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: STMicroelectronics STM32 HASH bindings
 
 maintainers:
-  - Lionel Debieve <lionel.debieve@st.com>
+  - Lionel Debieve <lionel.debieve@foss.st.com>
 
 properties:
   compatible:
diff --git a/Documentation/devicetree/bindings/display/bridge/snps,dw-mipi-dsi.yaml b/Documentation/devicetree/bindings/display/bridge/snps,dw-mipi-dsi.yaml
index 3c3e51af154b..11fd68a70dca 100644
--- a/Documentation/devicetree/bindings/display/bridge/snps,dw-mipi-dsi.yaml
+++ b/Documentation/devicetree/bindings/display/bridge/snps,dw-mipi-dsi.yaml
@@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Synopsys DesignWare MIPI DSI host controller
 
 maintainers:
-  - Philippe CORNU <philippe.cornu@st.com>
+  - Philippe CORNU <philippe.cornu@foss.st.com>
 
 description: |
   This document defines device tree properties for the Synopsys DesignWare MIPI
diff --git a/Documentation/devicetree/bindings/display/bridge/toshiba,tc358767.txt b/Documentation/devicetree/bindings/display/bridge/toshiba,tc358767.txt
deleted file mode 100644
index 583c5e9dbe6b..000000000000
--- a/Documentation/devicetree/bindings/display/bridge/toshiba,tc358767.txt
+++ /dev/null
@@ -1,54 +0,0 @@
-Toshiba TC358767 eDP bridge bindings
-
-Required properties:
- - compatible: "toshiba,tc358767"
- - reg: i2c address of the bridge, 0x68 or 0x0f, depending on bootstrap pins
- - clock-names: should be "ref"
- - clocks: OF device-tree clock specification for refclk input. The reference
-   clock rate must be 13 MHz, 19.2 MHz, 26 MHz, or 38.4 MHz.
-
-Optional properties:
- - shutdown-gpios: OF device-tree gpio specification for SD pin
-                   (active high shutdown input)
- - reset-gpios: OF device-tree gpio specification for RSTX pin
-                (active low system reset)
- - toshiba,hpd-pin: TC358767 GPIO pin number to which HPD is connected to (0 or 1)
- - ports: the ports node can contain video interface port nodes to connect
-   to a DPI/DSI source and to an eDP/DP sink according to [1][2]:
-    - port@0: DSI input port
-    - port@1: DPI input port
-    - port@2: eDP/DP output port
-
-[1]: Documentation/devicetree/bindings/graph.txt
-[2]: Documentation/devicetree/bindings/media/video-interfaces.txt
-
-Example:
-	edp-bridge@68 {
-		compatible = "toshiba,tc358767";
-		reg = <0x68>;
-		shutdown-gpios = <&gpio3 23 GPIO_ACTIVE_HIGH>;
-		reset-gpios = <&gpio3 24 GPIO_ACTIVE_LOW>;
-		clock-names = "ref";
-		clocks = <&edp_refclk>;
-
-		ports {
-			#address-cells = <1>;
-			#size-cells = <0>;
-
-			port@1 {
-				reg = <1>;
-
-				bridge_in: endpoint {
-					remote-endpoint = <&dpi_out>;
-				};
-			};
-
-			port@2 {
-				reg = <2>;
-
-				bridge_out: endpoint {
-					remote-endpoint = <&panel_in>;
-				};
-			};
-		};
-	};
diff --git a/Documentation/devicetree/bindings/display/bridge/toshiba,tc358767.yaml b/Documentation/devicetree/bindings/display/bridge/toshiba,tc358767.yaml
new file mode 100644
index 000000000000..f1541cc05297
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/bridge/toshiba,tc358767.yaml
@@ -0,0 +1,158 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/display/bridge/toshiba,tc358767.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Toshiba TC358767 eDP bridge bindings
+
+maintainers:
+  - Andrey Gusakov <andrey.gusakov@cogentembedded.com>
+
+description: The TC358767 is bridge device which converts DSI/DPI to eDP/DP
+
+properties:
+  compatible:
+    const: toshiba,tc358767
+
+  reg:
+    enum:
+      - 0x68
+      - 0x0f
+    description: |
+        i2c address of the bridge, 0x68 or 0x0f, depending on bootstrap pins
+
+  clock-names:
+    const: "ref"
+
+  clocks:
+    maxItems: 1
+    description: |
+        OF device-tree clock specification for refclk input. The reference.
+        clock rate must be 13 MHz, 19.2 MHz, 26 MHz, or 38.4 MHz.
+
+  shutdown-gpios:
+    maxItems: 1
+    description: |
+        OF device-tree gpio specification for SD pin(active high shutdown input)
+
+  reset-gpios:
+    maxItems: 1
+    description: |
+        OF device-tree gpio specification for RSTX pin(active low system reset)
+
+  toshiba,hpd-pin:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    enum:
+      - 0
+      - 1
+    description: TC358767 GPIO pin number to which HPD is connected to (0 or 1)
+
+  ports:
+    $ref: /schemas/graph.yaml#/properties/ports
+
+    properties:
+      port@0:
+        $ref: /schemas/graph.yaml#/properties/port
+        description: |
+            DSI input port. The remote endpoint phandle should be a
+            reference to a valid DSI output endpoint node
+
+      port@1:
+        $ref: /schemas/graph.yaml#/properties/port
+        description: |
+            DPI input port. The remote endpoint phandle should be a
+            reference to a valid DPI output endpoint node
+
+      port@2:
+        $ref: /schemas/graph.yaml#/properties/port
+        description: |
+            eDP/DP output port. The remote endpoint phandle should be a
+            reference to a valid eDP panel input endpoint node. This port is
+            optional, treated as DP panel if not defined
+
+    oneOf:
+      - required:
+          - port@0
+      - required:
+          - port@1
+
+
+required:
+  - compatible
+  - reg
+  - clock-names
+  - clocks
+  - ports
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/gpio/gpio.h>
+
+    /* DPI input and eDP output */
+
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        edp-bridge@68 {
+            compatible = "toshiba,tc358767";
+            reg = <0x68>;
+            shutdown-gpios = <&gpio3 23 GPIO_ACTIVE_HIGH>;
+            reset-gpios = <&gpio3 24 GPIO_ACTIVE_LOW>;
+            clock-names = "ref";
+            clocks = <&edp_refclk>;
+
+            ports {
+                #address-cells = <1>;
+                #size-cells = <0>;
+
+                port@1 {
+                    reg = <1>;
+
+                    bridge_in_0: endpoint {
+                        remote-endpoint = <&dpi_out>;
+                    };
+                };
+
+                port@2 {
+                    reg = <2>;
+
+                    bridge_out: endpoint {
+                        remote-endpoint = <&panel_in>;
+                    };
+                };
+            };
+        };
+    };
+  - |
+    /* DPI input and DP output */
+
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        edp-bridge@68 {
+            compatible = "toshiba,tc358767";
+            reg = <0x68>;
+            shutdown-gpios = <&gpio3 23 GPIO_ACTIVE_HIGH>;
+            reset-gpios = <&gpio3 24 GPIO_ACTIVE_LOW>;
+            clock-names = "ref";
+            clocks = <&edp_refclk>;
+
+            ports {
+                #address-cells = <1>;
+                #size-cells = <0>;
+
+                port@1 {
+                    reg = <1>;
+
+                    bridge_in_1: endpoint {
+                        remote-endpoint = <&dpi_out>;
+                    };
+                };
+            };
+        };
+    };
diff --git a/Documentation/devicetree/bindings/display/ingenic,ipu.yaml b/Documentation/devicetree/bindings/display/ingenic,ipu.yaml
index e679f48a3886..3f93def2c5a2 100644
--- a/Documentation/devicetree/bindings/display/ingenic,ipu.yaml
+++ b/Documentation/devicetree/bindings/display/ingenic,ipu.yaml
@@ -45,7 +45,7 @@ additionalProperties: false
 
 examples:
   - |
-    #include <dt-bindings/clock/jz4770-cgu.h>
+    #include <dt-bindings/clock/ingenic,jz4770-cgu.h>
     ipu@13080000 {
       compatible = "ingenic,jz4770-ipu", "ingenic,jz4760-ipu";
       reg = <0x13080000 0x800>;
diff --git a/Documentation/devicetree/bindings/display/ingenic,lcd.yaml b/Documentation/devicetree/bindings/display/ingenic,lcd.yaml
index 50d2b0a50e8a..0049010b37ca 100644
--- a/Documentation/devicetree/bindings/display/ingenic,lcd.yaml
+++ b/Documentation/devicetree/bindings/display/ingenic,lcd.yaml
@@ -88,7 +88,7 @@ additionalProperties: false
 
 examples:
   - |
-    #include <dt-bindings/clock/jz4740-cgu.h>
+    #include <dt-bindings/clock/ingenic,jz4740-cgu.h>
     lcd-controller@13050000 {
       compatible = "ingenic,jz4740-lcd";
       reg = <0x13050000 0x1000>;
@@ -107,7 +107,7 @@ examples:
     };
 
   - |
-    #include <dt-bindings/clock/jz4725b-cgu.h>
+    #include <dt-bindings/clock/ingenic,jz4725b-cgu.h>
     lcd-controller@13050000 {
       compatible = "ingenic,jz4725b-lcd";
       reg = <0x13050000 0x1000>;
diff --git a/Documentation/devicetree/bindings/display/panel/orisetech,otm8009a.yaml b/Documentation/devicetree/bindings/display/panel/orisetech,otm8009a.yaml
index 4b6dda6dbc0f..17cbd0ad32bf 100644
--- a/Documentation/devicetree/bindings/display/panel/orisetech,otm8009a.yaml
+++ b/Documentation/devicetree/bindings/display/panel/orisetech,otm8009a.yaml
@@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Orise Tech OTM8009A 3.97" 480x800 TFT LCD panel (MIPI-DSI video mode)
 
 maintainers:
-  - Philippe CORNU <philippe.cornu@st.com>
+  - Philippe CORNU <philippe.cornu@foss.st.com>
 
 description: |
              The Orise Tech OTM8009A is a 3.97" 480x800 TFT LCD panel connected using
diff --git a/Documentation/devicetree/bindings/display/panel/raydium,rm68200.yaml b/Documentation/devicetree/bindings/display/panel/raydium,rm68200.yaml
index 39477793d289..e8ce2315631a 100644
--- a/Documentation/devicetree/bindings/display/panel/raydium,rm68200.yaml
+++ b/Documentation/devicetree/bindings/display/panel/raydium,rm68200.yaml
@@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Raydium Semiconductor Corporation RM68200 5.5" 720p MIPI-DSI TFT LCD panel
 
 maintainers:
-  - Philippe CORNU <philippe.cornu@st.com>
+  - Philippe CORNU <philippe.cornu@foss.st.com>
 
 description: |
   The Raydium Semiconductor Corporation RM68200 is a 5.5" 720x1280 TFT LCD
diff --git a/Documentation/devicetree/bindings/display/st,stm32-dsi.yaml b/Documentation/devicetree/bindings/display/st,stm32-dsi.yaml
index ed310bbe3afe..ce1ef93cce93 100644
--- a/Documentation/devicetree/bindings/display/st,stm32-dsi.yaml
+++ b/Documentation/devicetree/bindings/display/st,stm32-dsi.yaml
@@ -7,8 +7,8 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: STMicroelectronics STM32 DSI host controller
 
 maintainers:
-  - Philippe Cornu <philippe.cornu@st.com>
-  - Yannick Fertre <yannick.fertre@st.com>
+  - Philippe Cornu <philippe.cornu@foss.st.com>
+  - Yannick Fertre <yannick.fertre@foss.st.com>
 
 description:
   The STMicroelectronics STM32 DSI controller uses the Synopsys DesignWare MIPI-DSI host controller.
diff --git a/Documentation/devicetree/bindings/display/st,stm32-ltdc.yaml b/Documentation/devicetree/bindings/display/st,stm32-ltdc.yaml
index 4ae3d75492d3..01e2da23790b 100644
--- a/Documentation/devicetree/bindings/display/st,stm32-ltdc.yaml
+++ b/Documentation/devicetree/bindings/display/st,stm32-ltdc.yaml
@@ -7,8 +7,8 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: STMicroelectronics STM32 lcd-tft display controller
 
 maintainers:
-  - Philippe Cornu <philippe.cornu@st.com>
-  - Yannick Fertre <yannick.fertre@st.com>
+  - Philippe Cornu <philippe.cornu@foss.st.com>
+  - Yannick Fertre <yannick.fertre@foss.st.com>
 
 properties:
   compatible:
diff --git a/Documentation/devicetree/bindings/dma/ingenic,dma.yaml b/Documentation/devicetree/bindings/dma/ingenic,dma.yaml
index ac4d59494fc8..dc059d6fd037 100644
--- a/Documentation/devicetree/bindings/dma/ingenic,dma.yaml
+++ b/Documentation/devicetree/bindings/dma/ingenic,dma.yaml
@@ -68,7 +68,7 @@ unevaluatedProperties: false
 
 examples:
   - |
-    #include <dt-bindings/clock/jz4780-cgu.h>
+    #include <dt-bindings/clock/ingenic,jz4780-cgu.h>
     dma: dma-controller@13420000 {
       compatible = "ingenic,jz4780-dma";
       reg = <0x13420000 0x400>, <0x13421000 0x40>;
diff --git a/Documentation/devicetree/bindings/dma/st,stm32-dma.yaml b/Documentation/devicetree/bindings/dma/st,stm32-dma.yaml
index 4bf676fd25dc..55faab6a468e 100644
--- a/Documentation/devicetree/bindings/dma/st,stm32-dma.yaml
+++ b/Documentation/devicetree/bindings/dma/st,stm32-dma.yaml
@@ -50,7 +50,7 @@ description: |
 
 
 maintainers:
-  - Amelie Delaunay <amelie.delaunay@st.com>
+  - Amelie Delaunay <amelie.delaunay@foss.st.com>
 
 allOf:
   - $ref: "dma-controller.yaml#"
diff --git a/Documentation/devicetree/bindings/dma/st,stm32-dmamux.yaml b/Documentation/devicetree/bindings/dma/st,stm32-dmamux.yaml
index c8d2b51d8410..f751796531c9 100644
--- a/Documentation/devicetree/bindings/dma/st,stm32-dmamux.yaml
+++ b/Documentation/devicetree/bindings/dma/st,stm32-dmamux.yaml
@@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: STMicroelectronics STM32 DMA MUX (DMA request router) bindings
 
 maintainers:
-  - Amelie Delaunay <amelie.delaunay@st.com>
+  - Amelie Delaunay <amelie.delaunay@foss.st.com>
 
 allOf:
   - $ref: "dma-router.yaml#"
diff --git a/Documentation/devicetree/bindings/dma/st,stm32-mdma.yaml b/Documentation/devicetree/bindings/dma/st,stm32-mdma.yaml
index c30be840be1c..87b4afd2cf62 100644
--- a/Documentation/devicetree/bindings/dma/st,stm32-mdma.yaml
+++ b/Documentation/devicetree/bindings/dma/st,stm32-mdma.yaml
@@ -50,7 +50,7 @@ description: |
        if no HW ack signal is used by the MDMA client
 
 maintainers:
-  - Amelie Delaunay <amelie.delaunay@st.com>
+  - Amelie Delaunay <amelie.delaunay@foss.st.com>
 
 allOf:
   - $ref: "dma-controller.yaml#"
diff --git a/Documentation/devicetree/bindings/gpio/gpio-xlp.txt b/Documentation/devicetree/bindings/gpio/gpio-xlp.txt
deleted file mode 100644
index 47fc64922fe0..000000000000
--- a/Documentation/devicetree/bindings/gpio/gpio-xlp.txt
+++ /dev/null
@@ -1,49 +0,0 @@
-Netlogic XLP Family GPIO
-========================
-
-This GPIO driver is used for following Netlogic XLP SoCs:
-	XLP832, XLP316, XLP208, XLP980, XLP532
-This GPIO driver is also compatible with GPIO controller found on
-Broadcom Vulcan ARM64.
-
-Required properties:
--------------------
-
-- compatible: Should be one of the following:
-  - "netlogic,xlp832-gpio": For Netlogic XLP832
-  - "netlogic,xlp316-gpio": For Netlogic XLP316
-  - "netlogic,xlp208-gpio": For Netlogic XLP208
-  - "netlogic,xlp980-gpio": For Netlogic XLP980
-  - "netlogic,xlp532-gpio": For Netlogic XLP532
-  - "brcm,vulcan-gpio": For Broadcom Vulcan ARM64
-- reg: Physical base address and length of the controller's registers.
-- #gpio-cells: Should be two. The first cell is the pin number and the second
-  cell is used to specify optional parameters (currently unused).
-- gpio-controller: Marks the device node as a GPIO controller.
-- nr-gpios: Number of GPIO pins supported by the controller.
-- interrupt-cells: Should be two. The first cell is the GPIO Number. The
-  second cell is used to specify flags. The following subset of flags is
-  supported:
-  - trigger type:
-	1 = low to high edge triggered.
-	2 = high to low edge triggered.
-	4 = active high level-sensitive.
-	8 = active low level-sensitive.
-- interrupts: Interrupt number for this device.
-- interrupt-controller: Identifies the node as an interrupt controller.
-
-Example:
-
-	gpio: xlp_gpio@34000 {
-		compatible = "netlogic,xlp316-gpio";
-		reg = <0 0x34100 0x1000
-		       0 0x35100 0x1000>;
-		#gpio-cells = <2>;
-		gpio-controller;
-		nr-gpios = <57>;
-
-		#interrupt-cells = <2>;
-		interrupt-parent = <&pic>;
-		interrupts = <39>;
-		interrupt-controller;
-	};
diff --git a/Documentation/devicetree/bindings/hwlock/st,stm32-hwspinlock.yaml b/Documentation/devicetree/bindings/hwlock/st,stm32-hwspinlock.yaml
index 47cf9c8d97e9..b18c616035a8 100644
--- a/Documentation/devicetree/bindings/hwlock/st,stm32-hwspinlock.yaml
+++ b/Documentation/devicetree/bindings/hwlock/st,stm32-hwspinlock.yaml
@@ -7,8 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: STMicroelectronics STM32 Hardware Spinlock bindings
 
 maintainers:
-  - Benjamin Gaignard <benjamin.gaignard@st.com>
-  - Fabien Dessenne <fabien.dessenne@st.com>
+  - Fabien Dessenne <fabien.dessenne@foss.st.com>
 
 properties:
   "#hwlock-cells":
diff --git a/Documentation/devicetree/bindings/i2c/apple,i2c.yaml b/Documentation/devicetree/bindings/i2c/apple,i2c.yaml
index 22fc8483256f..82b953181a52 100644
--- a/Documentation/devicetree/bindings/i2c/apple,i2c.yaml
+++ b/Documentation/devicetree/bindings/i2c/apple,i2c.yaml
@@ -20,9 +20,9 @@ allOf:
 
 properties:
   compatible:
-    enum:
-      - apple,t8103-i2c
-      - apple,i2c
+    items:
+      - const: apple,t8103-i2c
+      - const: apple,i2c
 
   reg:
     maxItems: 1
@@ -51,7 +51,7 @@ unevaluatedProperties: false
 examples:
   - |
     i2c@35010000 {
-      compatible = "apple,t8103-i2c";
+      compatible = "apple,t8103-i2c", "apple,i2c";
       reg = <0x35010000 0x4000>;
       interrupt-parent = <&aic>;
       interrupts = <0 627 4>;
diff --git a/Documentation/devicetree/bindings/i2c/i2c-imx-lpi2c.yaml b/Documentation/devicetree/bindings/i2c/i2c-imx-lpi2c.yaml
index 29b9447f3b84..fe0c89edf7c1 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-imx-lpi2c.yaml
+++ b/Documentation/devicetree/bindings/i2c/i2c-imx-lpi2c.yaml
@@ -17,9 +17,10 @@ properties:
     oneOf:
       - enum:
           - fsl,imx7ulp-lpi2c
-          - fsl,imx8qm-lpi2c
       - items:
-          - const: fsl,imx8qxp-lpi2c
+          - enum:
+              - fsl,imx8qxp-lpi2c
+              - fsl,imx8qm-lpi2c
           - const: fsl,imx7ulp-lpi2c
 
   reg:
diff --git a/Documentation/devicetree/bindings/i2c/i2c-imx.yaml b/Documentation/devicetree/bindings/i2c/i2c-imx.yaml
index 3592d49235e0..c167958ae2a9 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-imx.yaml
+++ b/Documentation/devicetree/bindings/i2c/i2c-imx.yaml
@@ -57,7 +57,9 @@ properties:
     const: ipg
 
   clock-frequency:
-    enum: [ 100000, 400000 ]
+    minimum: 1
+    default: 100000
+    maximum: 400000
 
   dmas:
     items:
diff --git a/Documentation/devicetree/bindings/i2c/i2c-xlp9xx.txt b/Documentation/devicetree/bindings/i2c/i2c-xlp9xx.txt
deleted file mode 100644
index f818ef507ab7..000000000000
--- a/Documentation/devicetree/bindings/i2c/i2c-xlp9xx.txt
+++ /dev/null
@@ -1,22 +0,0 @@
-Device tree configuration for the I2C controller on the XLP9xx/5xx SoC
-
-Required properties:
-- compatible      : should be "netlogic,xlp980-i2c"
-- reg             : bus address start and address range size of device
-- interrupts      : interrupt number
-
-Optional properties:
-- clock-frequency : frequency of bus clock in Hz
-                    Defaults to 100 KHz when the property is not specified
-
-Example:
-
-i2c0: i2c@113100 {
-	compatible = "netlogic,xlp980-i2c";
-	#address-cells = <1>;
-	#size-cells = <0>;
-	reg = <0 0x113100 0x100>;
-	clock-frequency = <400000>;
-	interrupts = <30>;
-	interrupt-parent = <&pic>;
-};
diff --git a/Documentation/devicetree/bindings/i2c/ingenic,i2c.yaml b/Documentation/devicetree/bindings/i2c/ingenic,i2c.yaml
index e1e65eb4f795..febde6cc5f69 100644
--- a/Documentation/devicetree/bindings/i2c/ingenic,i2c.yaml
+++ b/Documentation/devicetree/bindings/i2c/ingenic,i2c.yaml
@@ -60,7 +60,7 @@ unevaluatedProperties: false
 
 examples:
   - |
-    #include <dt-bindings/clock/jz4780-cgu.h>
+    #include <dt-bindings/clock/ingenic,jz4780-cgu.h>
     #include <dt-bindings/dma/jz4780-dma.h>
     #include <dt-bindings/interrupt-controller/irq.h>
     i2c@10054000 {
diff --git a/Documentation/devicetree/bindings/i2c/st,stm32-i2c.yaml b/Documentation/devicetree/bindings/i2c/st,stm32-i2c.yaml
index d747f4990ad8..c07289a643d8 100644
--- a/Documentation/devicetree/bindings/i2c/st,stm32-i2c.yaml
+++ b/Documentation/devicetree/bindings/i2c/st,stm32-i2c.yaml
@@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: I2C controller embedded in STMicroelectronics STM32 I2C platform
 
 maintainers:
-  - Pierre-Yves MORDRET <pierre-yves.mordret@st.com>
+  - Pierre-Yves MORDRET <pierre-yves.mordret@foss.st.com>
 
 allOf:
   - $ref: /schemas/i2c/i2c-controller.yaml#
diff --git a/Documentation/devicetree/bindings/iio/adc/ingenic,adc.yaml b/Documentation/devicetree/bindings/iio/adc/ingenic,adc.yaml
index 3eb7aa8822c3..698beb896f76 100644
--- a/Documentation/devicetree/bindings/iio/adc/ingenic,adc.yaml
+++ b/Documentation/devicetree/bindings/iio/adc/ingenic,adc.yaml
@@ -74,7 +74,7 @@ additionalProperties: false
 
 examples:
   - |
-    #include <dt-bindings/clock/jz4740-cgu.h>
+    #include <dt-bindings/clock/ingenic,jz4740-cgu.h>
     #include <dt-bindings/iio/adc/ingenic,adc.h>
 
     adc@10070000 {
diff --git a/Documentation/devicetree/bindings/iio/adc/samsung,exynos-adc.yaml b/Documentation/devicetree/bindings/iio/adc/samsung,exynos-adc.yaml
index c65921e66dc1..81c87295912c 100644
--- a/Documentation/devicetree/bindings/iio/adc/samsung,exynos-adc.yaml
+++ b/Documentation/devicetree/bindings/iio/adc/samsung,exynos-adc.yaml
@@ -136,7 +136,7 @@ examples:
         samsung,syscon-phandle = <&pmu_system_controller>;
 
         /* NTC thermistor is a hwmon device */
-        ncp15wb473 {
+        thermistor {
             compatible = "murata,ncp15wb473";
             pullup-uv = <1800000>;
             pullup-ohm = <47000>;
diff --git a/Documentation/devicetree/bindings/iio/adc/sigma-delta-modulator.yaml b/Documentation/devicetree/bindings/iio/adc/sigma-delta-modulator.yaml
index a390343d0c2a..2287697f1f61 100644
--- a/Documentation/devicetree/bindings/iio/adc/sigma-delta-modulator.yaml
+++ b/Documentation/devicetree/bindings/iio/adc/sigma-delta-modulator.yaml
@@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Device-Tree bindings for sigma delta modulator
 
 maintainers:
-  - Arnaud Pouliquen <arnaud.pouliquen@st.com>
+  - Arnaud Pouliquen <arnaud.pouliquen@foss.st.com>
 
 properties:
   compatible:
diff --git a/Documentation/devicetree/bindings/iio/adc/st,stm32-adc.yaml b/Documentation/devicetree/bindings/iio/adc/st,stm32-adc.yaml
index ec0450d111a9..4d6074518b5c 100644
--- a/Documentation/devicetree/bindings/iio/adc/st,stm32-adc.yaml
+++ b/Documentation/devicetree/bindings/iio/adc/st,stm32-adc.yaml
@@ -19,7 +19,7 @@ description: |
   Each STM32 ADC block can have up to 3 ADC instances.
 
 maintainers:
-  - Fabrice Gasnier <fabrice.gasnier@st.com>
+  - Fabrice Gasnier <fabrice.gasnier@foss.st.com>
 
 properties:
   compatible:
diff --git a/Documentation/devicetree/bindings/iio/adc/st,stm32-dfsdm-adc.yaml b/Documentation/devicetree/bindings/iio/adc/st,stm32-dfsdm-adc.yaml
index 733351dee252..7c260f209687 100644
--- a/Documentation/devicetree/bindings/iio/adc/st,stm32-dfsdm-adc.yaml
+++ b/Documentation/devicetree/bindings/iio/adc/st,stm32-dfsdm-adc.yaml
@@ -7,8 +7,8 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: STMicroelectronics STM32 DFSDM ADC device driver
 
 maintainers:
-  - Fabrice Gasnier <fabrice.gasnier@st.com>
-  - Olivier Moysan <olivier.moysan@st.com>
+  - Fabrice Gasnier <fabrice.gasnier@foss.st.com>
+  - Olivier Moysan <olivier.moysan@foss.st.com>
 
 description: |
   STM32 DFSDM ADC is a sigma delta analog-to-digital converter dedicated to
diff --git a/Documentation/devicetree/bindings/iio/dac/st,stm32-dac.yaml b/Documentation/devicetree/bindings/iio/dac/st,stm32-dac.yaml
index 393f7005941a..6adeda4087fc 100644
--- a/Documentation/devicetree/bindings/iio/dac/st,stm32-dac.yaml
+++ b/Documentation/devicetree/bindings/iio/dac/st,stm32-dac.yaml
@@ -15,7 +15,7 @@ description: |
   current.
 
 maintainers:
-  - Fabrice Gasnier <fabrice.gasnier@st.com>
+  - Fabrice Gasnier <fabrice.gasnier@foss.st.com>
 
 properties:
   compatible:
diff --git a/Documentation/devicetree/bindings/input/gpio-keys.yaml b/Documentation/devicetree/bindings/input/gpio-keys.yaml
index 060a309ff8e7..dbe7ecc19ccb 100644
--- a/Documentation/devicetree/bindings/input/gpio-keys.yaml
+++ b/Documentation/devicetree/bindings/input/gpio-keys.yaml
@@ -142,7 +142,7 @@ examples:
         down {
             label = "GPIO Key DOWN";
             linux,code = <108>;
-            interrupts = <1 IRQ_TYPE_LEVEL_HIGH 7>;
+            interrupts = <1 IRQ_TYPE_EDGE_FALLING>;
         };
     };
 
diff --git a/Documentation/devicetree/bindings/interrupt-controller/st,stm32-exti.yaml b/Documentation/devicetree/bindings/interrupt-controller/st,stm32-exti.yaml
index 6d3e68eb2e8b..d19c881b4abc 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/st,stm32-exti.yaml
+++ b/Documentation/devicetree/bindings/interrupt-controller/st,stm32-exti.yaml
@@ -7,8 +7,8 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: STM32 External Interrupt Controller Device Tree Bindings
 
 maintainers:
-  - Alexandre Torgue <alexandre.torgue@st.com>
-  - Ludovic Barre <ludovic.barre@st.com>
+  - Alexandre Torgue <alexandre.torgue@foss.st.com>
+  - Ludovic Barre <ludovic.barre@foss.st.com>
 
 properties:
   compatible:
diff --git a/Documentation/devicetree/bindings/mailbox/st,stm32-ipcc.yaml b/Documentation/devicetree/bindings/mailbox/st,stm32-ipcc.yaml
index b15da9ba90b2..8eb4bf52ea27 100644
--- a/Documentation/devicetree/bindings/mailbox/st,stm32-ipcc.yaml
+++ b/Documentation/devicetree/bindings/mailbox/st,stm32-ipcc.yaml
@@ -13,8 +13,8 @@ description:
   channels (N) can be read from a dedicated register.
 
 maintainers:
-  - Fabien Dessenne <fabien.dessenne@st.com>
-  - Arnaud Pouliquen <arnaud.pouliquen@st.com>
+  - Fabien Dessenne <fabien.dessenne@foss.st.com>
+  - Arnaud Pouliquen <arnaud.pouliquen@foss.st.com>
 
 properties:
   compatible:
diff --git a/Documentation/devicetree/bindings/media/nxp,imx7-mipi-csi2.yaml b/Documentation/devicetree/bindings/media/nxp,imx7-mipi-csi2.yaml
index 877183cf4278..1ef849dc74d7 100644
--- a/Documentation/devicetree/bindings/media/nxp,imx7-mipi-csi2.yaml
+++ b/Documentation/devicetree/bindings/media/nxp,imx7-mipi-csi2.yaml
@@ -79,6 +79,8 @@ properties:
 
             properties:
               data-lanes:
+                description:
+                  Note that 'fsl,imx7-mipi-csi2' only supports up to 2 data lines.
                 items:
                   minItems: 1
                   maxItems: 4
@@ -91,18 +93,6 @@ properties:
             required:
               - data-lanes
 
-            allOf:
-              - if:
-                  properties:
-                    compatible:
-                      contains:
-                        const: fsl,imx7-mipi-csi2
-                then:
-                  properties:
-                    data-lanes:
-                      items:
-                        maxItems: 2
-
       port@1:
         $ref: /schemas/graph.yaml#/properties/port
         description:
diff --git a/Documentation/devicetree/bindings/media/qcom,sc7280-venus.yaml b/Documentation/devicetree/bindings/media/qcom,sc7280-venus.yaml
index fa54c560e0bd..e2874683b4d5 100644
--- a/Documentation/devicetree/bindings/media/qcom,sc7280-venus.yaml
+++ b/Documentation/devicetree/bindings/media/qcom,sc7280-venus.yaml
@@ -30,7 +30,6 @@ properties:
 
   power-domain-names:
     minItems: 2
-    maxItems: 3
     items:
       - const: venus
       - const: vcodec0
diff --git a/Documentation/devicetree/bindings/media/st,stm32-cec.yaml b/Documentation/devicetree/bindings/media/st,stm32-cec.yaml
index d75019c093a4..77144cc6f7db 100644
--- a/Documentation/devicetree/bindings/media/st,stm32-cec.yaml
+++ b/Documentation/devicetree/bindings/media/st,stm32-cec.yaml
@@ -7,8 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: STMicroelectronics STM32 CEC bindings
 
 maintainers:
-  - Benjamin Gaignard <benjamin.gaignard@st.com>
-  - Yannick Fertre <yannick.fertre@st.com>
+  - Yannick Fertre <yannick.fertre@foss.st.com>
 
 properties:
   compatible:
diff --git a/Documentation/devicetree/bindings/media/st,stm32-dcmi.yaml b/Documentation/devicetree/bindings/media/st,stm32-dcmi.yaml
index 41e1d0cd80e5..9c1262a276b5 100644
--- a/Documentation/devicetree/bindings/media/st,stm32-dcmi.yaml
+++ b/Documentation/devicetree/bindings/media/st,stm32-dcmi.yaml
@@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: STMicroelectronics STM32 Digital Camera Memory Interface (DCMI) binding
 
 maintainers:
-  - Hugues Fruchet <hugues.fruchet@st.com>
+  - Hugues Fruchet <hugues.fruchet@foss.st.com>
 
 properties:
   compatible:
diff --git a/Documentation/devicetree/bindings/memory-controllers/ingenic,nemc.yaml b/Documentation/devicetree/bindings/memory-controllers/ingenic,nemc.yaml
index fe0ce191a851..24f9e1982028 100644
--- a/Documentation/devicetree/bindings/memory-controllers/ingenic,nemc.yaml
+++ b/Documentation/devicetree/bindings/memory-controllers/ingenic,nemc.yaml
@@ -84,7 +84,7 @@ additionalProperties: false
 
 examples:
   - |
-    #include <dt-bindings/clock/jz4780-cgu.h>
+    #include <dt-bindings/clock/ingenic,jz4780-cgu.h>
     #include <dt-bindings/gpio/gpio.h>
     nemc: memory-controller@13410000 {
       compatible = "ingenic,jz4780-nemc";
diff --git a/Documentation/devicetree/bindings/memory-controllers/st,stm32-fmc2-ebi.yaml b/Documentation/devicetree/bindings/memory-controllers/st,stm32-fmc2-ebi.yaml
index cba74205846a..6b516d3895af 100644
--- a/Documentation/devicetree/bindings/memory-controllers/st,stm32-fmc2-ebi.yaml
+++ b/Documentation/devicetree/bindings/memory-controllers/st,stm32-fmc2-ebi.yaml
@@ -19,7 +19,7 @@ description: |
   Select. The FMC2 performs only one access at a time to an external device.
 
 maintainers:
-  - Christophe Kerello <christophe.kerello@st.com>
+  - Christophe Kerello <christophe.kerello@foss.st.com>
 
 properties:
   compatible:
diff --git a/Documentation/devicetree/bindings/mfd/st,stm32-lptimer.yaml b/Documentation/devicetree/bindings/mfd/st,stm32-lptimer.yaml
index 8bcea8dd7d90..ec7f0190f46e 100644
--- a/Documentation/devicetree/bindings/mfd/st,stm32-lptimer.yaml
+++ b/Documentation/devicetree/bindings/mfd/st,stm32-lptimer.yaml
@@ -17,7 +17,7 @@ description: |
      - simple counter from IN1 input signal.
 
 maintainers:
-  - Fabrice Gasnier <fabrice.gasnier@st.com>
+  - Fabrice Gasnier <fabrice.gasnier@foss.st.com>
 
 properties:
   compatible:
diff --git a/Documentation/devicetree/bindings/mfd/st,stm32-timers.yaml b/Documentation/devicetree/bindings/mfd/st,stm32-timers.yaml
index dace35362a7a..10b330d42901 100644
--- a/Documentation/devicetree/bindings/mfd/st,stm32-timers.yaml
+++ b/Documentation/devicetree/bindings/mfd/st,stm32-timers.yaml
@@ -17,8 +17,7 @@ description: |
       programmable prescaler.
 
 maintainers:
-  - Benjamin Gaignard <benjamin.gaignard@st.com>
-  - Fabrice Gasnier <fabrice.gasnier@st.com>
+  - Fabrice Gasnier <fabrice.gasnier@foss.st.com>
 
 properties:
   compatible:
diff --git a/Documentation/devicetree/bindings/mfd/st,stmfx.yaml b/Documentation/devicetree/bindings/mfd/st,stmfx.yaml
index 19e9afb385ac..b2a4e4aa7ff6 100644
--- a/Documentation/devicetree/bindings/mfd/st,stmfx.yaml
+++ b/Documentation/devicetree/bindings/mfd/st,stmfx.yaml
@@ -12,7 +12,7 @@ description: ST Multi-Function eXpander (STMFX) is a slave controller using I2C
                through VDD) and resistive touchscreen controller.
 
 maintainers:
-  - Amelie Delaunay <amelie.delaunay@st.com>
+  - Amelie Delaunay <amelie.delaunay@foss.st.com>
 
 properties:
   compatible:
diff --git a/Documentation/devicetree/bindings/mfd/st,stpmic1.yaml b/Documentation/devicetree/bindings/mfd/st,stpmic1.yaml
index 305123e74a58..426658ad81d4 100644
--- a/Documentation/devicetree/bindings/mfd/st,stpmic1.yaml
+++ b/Documentation/devicetree/bindings/mfd/st,stpmic1.yaml
@@ -9,7 +9,7 @@ title: STMicroelectonics STPMIC1 Power Management IC bindings
 description: STMicroelectronics STPMIC1 Power Management IC
 
 maintainers:
-  - pascal Paillet <p.paillet@st.com>
+  - pascal Paillet <p.paillet@foss.st.com>
 
 properties:
   compatible:
diff --git a/Documentation/devicetree/bindings/mips/ingenic/ingenic,cpu.yaml b/Documentation/devicetree/bindings/mips/ingenic/ingenic,cpu.yaml
index 6df1a9470d8f..b7e7fa715437 100644
--- a/Documentation/devicetree/bindings/mips/ingenic/ingenic,cpu.yaml
+++ b/Documentation/devicetree/bindings/mips/ingenic/ingenic,cpu.yaml
@@ -44,7 +44,7 @@ additionalProperties: false
 
 examples:
   - |
-    #include <dt-bindings/clock/jz4780-cgu.h>
+    #include <dt-bindings/clock/ingenic,jz4780-cgu.h>
 
     cpus {
         #address-cells = <1>;
diff --git a/Documentation/devicetree/bindings/mmc/ingenic,mmc.yaml b/Documentation/devicetree/bindings/mmc/ingenic,mmc.yaml
index 546480f41141..01d5c6da0eeb 100644
--- a/Documentation/devicetree/bindings/mmc/ingenic,mmc.yaml
+++ b/Documentation/devicetree/bindings/mmc/ingenic,mmc.yaml
@@ -61,7 +61,7 @@ unevaluatedProperties: false
 
 examples:
   - |
-    #include <dt-bindings/clock/jz4780-cgu.h>
+    #include <dt-bindings/clock/ingenic,jz4780-cgu.h>
     #include <dt-bindings/dma/jz4780-dma.h>
     mmc0: mmc@13450000 {
       compatible = "ingenic,jz4780-mmc";
diff --git a/Documentation/devicetree/bindings/mtd/ingenic,nand.yaml b/Documentation/devicetree/bindings/mtd/ingenic,nand.yaml
index 89aa3ceda592..9de8ef6e59ca 100644
--- a/Documentation/devicetree/bindings/mtd/ingenic,nand.yaml
+++ b/Documentation/devicetree/bindings/mtd/ingenic,nand.yaml
@@ -55,7 +55,7 @@ unevaluatedProperties: false
 
 examples:
   - |
-    #include <dt-bindings/clock/jz4780-cgu.h>
+    #include <dt-bindings/clock/ingenic,jz4780-cgu.h>
     memory-controller@13410000 {
       compatible = "ingenic,jz4780-nemc";
       reg = <0x13410000 0x10000>;
diff --git a/Documentation/devicetree/bindings/mtd/st,stm32-fmc2-nand.yaml b/Documentation/devicetree/bindings/mtd/st,stm32-fmc2-nand.yaml
index 29c5ef24ac6a..eab8ea3da1fa 100644
--- a/Documentation/devicetree/bindings/mtd/st,stm32-fmc2-nand.yaml
+++ b/Documentation/devicetree/bindings/mtd/st,stm32-fmc2-nand.yaml
@@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: STMicroelectronics Flexible Memory Controller 2 (FMC2) Bindings
 
 maintainers:
-  - Christophe Kerello <christophe.kerello@st.com>
+  - Christophe Kerello <christophe.kerello@foss.st.com>
 
 properties:
   compatible:
diff --git a/Documentation/devicetree/bindings/net/ethernet-phy.yaml b/Documentation/devicetree/bindings/net/ethernet-phy.yaml
index 2766fe45bb98..ee42328a109d 100644
--- a/Documentation/devicetree/bindings/net/ethernet-phy.yaml
+++ b/Documentation/devicetree/bindings/net/ethernet-phy.yaml
@@ -91,6 +91,14 @@ properties:
       compensate for the board being designed with the lanes
       swapped.
 
+  enet-phy-lane-no-swap:
+    $ref: /schemas/types.yaml#/definitions/flag
+    description:
+      If set, indicates that PHY will disable swap of the
+      TX/RX lanes. This property allows the PHY to work correcly after
+      e.g. wrong bootstrap configuration caused by issues in PCB
+      layout design.
+
   eee-broken-100tx:
     $ref: /schemas/types.yaml#/definitions/flag
     description:
diff --git a/Documentation/devicetree/bindings/net/ingenic,mac.yaml b/Documentation/devicetree/bindings/net/ingenic,mac.yaml
index d08a88125a5c..8e52b2e683b8 100644
--- a/Documentation/devicetree/bindings/net/ingenic,mac.yaml
+++ b/Documentation/devicetree/bindings/net/ingenic,mac.yaml
@@ -58,7 +58,7 @@ additionalProperties: false
 
 examples:
   - |
-    #include <dt-bindings/clock/x1000-cgu.h>
+    #include <dt-bindings/clock/ingenic,x1000-cgu.h>
 
     mac: ethernet@134b0000 {
         compatible = "ingenic,x1000-mac";
diff --git a/Documentation/devicetree/bindings/net/snps,dwmac.yaml b/Documentation/devicetree/bindings/net/snps,dwmac.yaml
index 282d7744f27f..7ae70dc27f78 100644
--- a/Documentation/devicetree/bindings/net/snps,dwmac.yaml
+++ b/Documentation/devicetree/bindings/net/snps,dwmac.yaml
@@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Synopsys DesignWare MAC Device Tree Bindings
 
 maintainers:
-  - Alexandre Torgue <alexandre.torgue@st.com>
+  - Alexandre Torgue <alexandre.torgue@foss.st.com>
   - Giuseppe Cavallaro <peppe.cavallaro@st.com>
   - Jose Abreu <joabreu@synopsys.com>
 
diff --git a/Documentation/devicetree/bindings/net/stm32-dwmac.yaml b/Documentation/devicetree/bindings/net/stm32-dwmac.yaml
index d3f05d5934d5..577f4e284425 100644
--- a/Documentation/devicetree/bindings/net/stm32-dwmac.yaml
+++ b/Documentation/devicetree/bindings/net/stm32-dwmac.yaml
@@ -8,8 +8,8 @@ $schema: "http://devicetree.org/meta-schemas/core.yaml#"
 title: STMicroelectronics STM32 / MCU DWMAC glue layer controller
 
 maintainers:
-  - Alexandre Torgue <alexandre.torgue@st.com>
-  - Christophe Roullier <christophe.roullier@st.com>
+  - Alexandre Torgue <alexandre.torgue@foss.st.com>
+  - Christophe Roullier <christophe.roullier@foss.st.com>
 
 description:
   This file documents platform glue layer for stmmac.
diff --git a/Documentation/devicetree/bindings/nvmem/ingenic,jz4780-efuse.yaml b/Documentation/devicetree/bindings/nvmem/ingenic,jz4780-efuse.yaml
index 1485d3fbabfd..bf84768228f5 100644
--- a/Documentation/devicetree/bindings/nvmem/ingenic,jz4780-efuse.yaml
+++ b/Documentation/devicetree/bindings/nvmem/ingenic,jz4780-efuse.yaml
@@ -33,7 +33,7 @@ unevaluatedProperties: false
 
 examples:
   - |
-    #include <dt-bindings/clock/jz4780-cgu.h>
+    #include <dt-bindings/clock/ingenic,jz4780-cgu.h>
 
     efuse@134100d0 {
         compatible = "ingenic,jz4780-efuse";
diff --git a/Documentation/devicetree/bindings/nvmem/st,stm32-romem.yaml b/Documentation/devicetree/bindings/nvmem/st,stm32-romem.yaml
index 0b80ce22a2f8..a48c8fa56bce 100644
--- a/Documentation/devicetree/bindings/nvmem/st,stm32-romem.yaml
+++ b/Documentation/devicetree/bindings/nvmem/st,stm32-romem.yaml
@@ -13,7 +13,7 @@ description: |
   internal vref (VREFIN_CAL), unique device ID...
 
 maintainers:
-  - Fabrice Gasnier <fabrice.gasnier@st.com>
+  - Fabrice Gasnier <fabrice.gasnier@foss.st.com>
 
 allOf:
   - $ref: "nvmem.yaml#"
diff --git a/Documentation/devicetree/bindings/phy/ingenic,phy-usb.yaml b/Documentation/devicetree/bindings/phy/ingenic,phy-usb.yaml
index 0fd93d71fe5a..5cab21648632 100644
--- a/Documentation/devicetree/bindings/phy/ingenic,phy-usb.yaml
+++ b/Documentation/devicetree/bindings/phy/ingenic,phy-usb.yaml
@@ -46,7 +46,7 @@ additionalProperties: false
 
 examples:
   - |
-    #include <dt-bindings/clock/jz4770-cgu.h>
+    #include <dt-bindings/clock/ingenic,jz4770-cgu.h>
     otg_phy: usb-phy@3c {
       compatible = "ingenic,jz4770-phy";
       reg = <0x3c 0x10>;
diff --git a/Documentation/devicetree/bindings/phy/phy-stm32-usbphyc.yaml b/Documentation/devicetree/bindings/phy/phy-stm32-usbphyc.yaml
index 225128364a63..267b695215b6 100644
--- a/Documentation/devicetree/bindings/phy/phy-stm32-usbphyc.yaml
+++ b/Documentation/devicetree/bindings/phy/phy-stm32-usbphyc.yaml
@@ -24,7 +24,7 @@ description:
   |_ UTMI switch_______|          OTG controller
 
 maintainers:
-  - Amelie Delaunay <amelie.delaunay@st.com>
+  - Amelie Delaunay <amelie.delaunay@foss.st.com>
 
 properties:
   compatible:
diff --git a/Documentation/devicetree/bindings/phy/xlnx,zynqmp-psgtr.yaml b/Documentation/devicetree/bindings/phy/xlnx,zynqmp-psgtr.yaml
index 04d5654efb38..79906519c652 100644
--- a/Documentation/devicetree/bindings/phy/xlnx,zynqmp-psgtr.yaml
+++ b/Documentation/devicetree/bindings/phy/xlnx,zynqmp-psgtr.yaml
@@ -29,7 +29,7 @@ properties:
           - PHY_TYPE_PCIE
           - PHY_TYPE_SATA
           - PHY_TYPE_SGMII
-          - PHY_TYPE_USB
+          - PHY_TYPE_USB3
       - description: The PHY instance
         minimum: 0
         maximum: 1 # for DP, SATA or USB
diff --git a/Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.yaml
index dfee6d38a701..ac88e01ec430 100644
--- a/Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.yaml
@@ -8,7 +8,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: STM32 GPIO and Pin Mux/Config controller
 
 maintainers:
-  - Alexandre TORGUE <alexandre.torgue@st.com>
+  - Alexandre TORGUE <alexandre.torgue@foss.st.com>
 
 description: |
   STMicroelectronics's STM32 MCUs intregrate a GPIO and Pin mux/config hardware
diff --git a/Documentation/devicetree/bindings/power/supply/bq25980.yaml b/Documentation/devicetree/bindings/power/supply/bq25980.yaml
index 06eca6667f67..8367a1fd4057 100644
--- a/Documentation/devicetree/bindings/power/supply/bq25980.yaml
+++ b/Documentation/devicetree/bindings/power/supply/bq25980.yaml
@@ -105,7 +105,7 @@ examples:
           reg = <0x65>;
           interrupt-parent = <&gpio1>;
           interrupts = <16 IRQ_TYPE_EDGE_FALLING>;
-          ti,watchdog-timer = <0>;
+          ti,watchdog-timeout-ms = <0>;
           ti,sc-ocp-limit-microamp = <2000000>;
           ti,sc-ovp-limit-microvolt = <17800000>;
           monitored-battery = <&bat>;
diff --git a/Documentation/devicetree/bindings/regulator/samsung,s5m8767.yaml b/Documentation/devicetree/bindings/regulator/samsung,s5m8767.yaml
index 80a63d47790a..c98929a213e9 100644
--- a/Documentation/devicetree/bindings/regulator/samsung,s5m8767.yaml
+++ b/Documentation/devicetree/bindings/regulator/samsung,s5m8767.yaml
@@ -51,6 +51,19 @@ patternProperties:
     description:
       Properties for single BUCK regulator.
 
+    properties:
+      op_mode:
+        $ref: /schemas/types.yaml#/definitions/uint32
+        enum: [0, 1, 2, 3]
+        default: 1
+        description: |
+          Describes the different operating modes of the regulator with power
+          mode change in SOC. The different possible values are:
+            0 - always off mode
+            1 - on in normal mode
+            2 - low power mode
+            3 - suspend mode
+
     required:
       - regulator-name
 
@@ -63,6 +76,18 @@ patternProperties:
       Properties for single BUCK regulator.
 
     properties:
+      op_mode:
+        $ref: /schemas/types.yaml#/definitions/uint32
+        enum: [0, 1, 2, 3]
+        default: 1
+        description: |
+          Describes the different operating modes of the regulator with power
+          mode change in SOC. The different possible values are:
+            0 - always off mode
+            1 - on in normal mode
+            2 - low power mode
+            3 - suspend mode
+
       s5m8767,pmic-ext-control-gpios:
         maxItems: 1
         description: |
diff --git a/Documentation/devicetree/bindings/regulator/st,stm32-booster.yaml b/Documentation/devicetree/bindings/regulator/st,stm32-booster.yaml
index 9f1c70381b82..df0191b1ceba 100644
--- a/Documentation/devicetree/bindings/regulator/st,stm32-booster.yaml
+++ b/Documentation/devicetree/bindings/regulator/st,stm32-booster.yaml
@@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: STMicroelectronics STM32 booster for ADC analog input switches bindings
 
 maintainers:
-  - Fabrice Gasnier <fabrice.gasnier@st.com>
+  - Fabrice Gasnier <fabrice.gasnier@foss.st.com>
 
 description: |
   Some STM32 devices embed a 3.3V booster supplied by Vdda, that can be used
diff --git a/Documentation/devicetree/bindings/regulator/st,stm32-vrefbuf.yaml b/Documentation/devicetree/bindings/regulator/st,stm32-vrefbuf.yaml
index 3cd4a254e4cb..836d4156d54c 100644
--- a/Documentation/devicetree/bindings/regulator/st,stm32-vrefbuf.yaml
+++ b/Documentation/devicetree/bindings/regulator/st,stm32-vrefbuf.yaml
@@ -12,7 +12,7 @@ description: |
   components through the dedicated VREF+ pin.
 
 maintainers:
-  - Fabrice Gasnier <fabrice.gasnier@st.com>
+  - Fabrice Gasnier <fabrice.gasnier@foss.st.com>
 
 allOf:
   - $ref: "regulator.yaml#"
diff --git a/Documentation/devicetree/bindings/regulator/st,stm32mp1-pwr-reg.yaml b/Documentation/devicetree/bindings/regulator/st,stm32mp1-pwr-reg.yaml
index e6322bc3e447..bd07b9c81570 100644
--- a/Documentation/devicetree/bindings/regulator/st,stm32mp1-pwr-reg.yaml
+++ b/Documentation/devicetree/bindings/regulator/st,stm32mp1-pwr-reg.yaml
@@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: STM32MP1 PWR voltage regulators
 
 maintainers:
-  - Pascal Paillet <p.paillet@st.com>
+  - Pascal Paillet <p.paillet@foss.st.com>
 
 properties:
   compatible:
diff --git a/Documentation/devicetree/bindings/remoteproc/ingenic,vpu.yaml b/Documentation/devicetree/bindings/remoteproc/ingenic,vpu.yaml
index d0aa91bbf5e5..aaaaabad46ea 100644
--- a/Documentation/devicetree/bindings/remoteproc/ingenic,vpu.yaml
+++ b/Documentation/devicetree/bindings/remoteproc/ingenic,vpu.yaml
@@ -58,7 +58,7 @@ additionalProperties: false
 
 examples:
   - |
-    #include <dt-bindings/clock/jz4770-cgu.h>
+    #include <dt-bindings/clock/ingenic,jz4770-cgu.h>
 
     vpu: video-decoder@132a0000 {
       compatible = "ingenic,jz4770-vpu-rproc";
diff --git a/Documentation/devicetree/bindings/remoteproc/st,stm32-rproc.yaml b/Documentation/devicetree/bindings/remoteproc/st,stm32-rproc.yaml
index 1e6225677e00..b587c97c282b 100644
--- a/Documentation/devicetree/bindings/remoteproc/st,stm32-rproc.yaml
+++ b/Documentation/devicetree/bindings/remoteproc/st,stm32-rproc.yaml
@@ -11,8 +11,8 @@ description:
   boots firmwares on the ST32MP family chipset.
 
 maintainers:
-  - Fabien Dessenne <fabien.dessenne@st.com>
-  - Arnaud Pouliquen <arnaud.pouliquen@st.com>
+  - Fabien Dessenne <fabien.dessenne@foss.st.com>
+  - Arnaud Pouliquen <arnaud.pouliquen@foss.st.com>
 
 properties:
   compatible:
diff --git a/Documentation/devicetree/bindings/rng/ingenic,trng.yaml b/Documentation/devicetree/bindings/rng/ingenic,trng.yaml
index 808f247c8421..044d9a065650 100644
--- a/Documentation/devicetree/bindings/rng/ingenic,trng.yaml
+++ b/Documentation/devicetree/bindings/rng/ingenic,trng.yaml
@@ -32,7 +32,7 @@ additionalProperties: false
 
 examples:
   - |
-    #include <dt-bindings/clock/x1830-cgu.h>
+    #include <dt-bindings/clock/ingenic,x1830-cgu.h>
 
     dtrng: trng@10072000 {
         compatible = "ingenic,x1830-dtrng";
diff --git a/Documentation/devicetree/bindings/rng/st,stm32-rng.yaml b/Documentation/devicetree/bindings/rng/st,stm32-rng.yaml
index 82bb2e97e889..9a6e4eaf4d3c 100644
--- a/Documentation/devicetree/bindings/rng/st,stm32-rng.yaml
+++ b/Documentation/devicetree/bindings/rng/st,stm32-rng.yaml
@@ -11,7 +11,7 @@ description: |
   IP and is fully separated from other crypto functions.
 
 maintainers:
-  - Lionel Debieve <lionel.debieve@st.com>
+  - Lionel Debieve <lionel.debieve@foss.st.com>
 
 properties:
   compatible:
diff --git a/Documentation/devicetree/bindings/rtc/ingenic,rtc.yaml b/Documentation/devicetree/bindings/rtc/ingenic,rtc.yaml
index 60e93e86ad9d..b235b2441997 100644
--- a/Documentation/devicetree/bindings/rtc/ingenic,rtc.yaml
+++ b/Documentation/devicetree/bindings/rtc/ingenic,rtc.yaml
@@ -72,7 +72,7 @@ unevaluatedProperties: false
 
 examples:
   - |
-    #include <dt-bindings/clock/jz4740-cgu.h>
+    #include <dt-bindings/clock/ingenic,jz4740-cgu.h>
     rtc_dev: rtc@10003000 {
       compatible = "ingenic,jz4740-rtc";
       reg = <0x10003000 0x40>;
diff --git a/Documentation/devicetree/bindings/rtc/st,stm32-rtc.yaml b/Documentation/devicetree/bindings/rtc/st,stm32-rtc.yaml
index 5456604b1c14..2359f541b770 100644
--- a/Documentation/devicetree/bindings/rtc/st,stm32-rtc.yaml
+++ b/Documentation/devicetree/bindings/rtc/st,stm32-rtc.yaml
@@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: STMicroelectronics STM32 Real Time Clock Bindings
 
 maintainers:
-  - Gabriel Fernandez <gabriel.fernandez@st.com>
+  - Gabriel Fernandez <gabriel.fernandez@foss.st.com>
 
 properties:
   compatible:
diff --git a/Documentation/devicetree/bindings/serial/ingenic,uart.yaml b/Documentation/devicetree/bindings/serial/ingenic,uart.yaml
index b432d4dff730..9ca7a18ecd8b 100644
--- a/Documentation/devicetree/bindings/serial/ingenic,uart.yaml
+++ b/Documentation/devicetree/bindings/serial/ingenic,uart.yaml
@@ -71,7 +71,7 @@ unevaluatedProperties: false
 
 examples:
   - |
-    #include <dt-bindings/clock/jz4780-cgu.h>
+    #include <dt-bindings/clock/ingenic,jz4780-cgu.h>
     #include <dt-bindings/dma/jz4780-dma.h>
     #include <dt-bindings/gpio/gpio.h>
     serial@10032000 {
diff --git a/Documentation/devicetree/bindings/serial/st,stm32-uart.yaml b/Documentation/devicetree/bindings/serial/st,stm32-uart.yaml
index f50f4ca893a0..333dc42722d2 100644
--- a/Documentation/devicetree/bindings/serial/st,stm32-uart.yaml
+++ b/Documentation/devicetree/bindings/serial/st,stm32-uart.yaml
@@ -5,7 +5,7 @@ $id: http://devicetree.org/schemas/serial/st,stm32-uart.yaml#
 $schema: http://devicetree.org/meta-schemas/core.yaml#
 
 maintainers:
-  - Erwan Le Ray <erwan.leray@st.com>
+  - Erwan Le Ray <erwan.leray@foss.st.com>
 
 title: STMicroelectronics STM32 USART bindings
 
diff --git a/Documentation/devicetree/bindings/sound/cirrus,cs42l51.yaml b/Documentation/devicetree/bindings/sound/cirrus,cs42l51.yaml
index 0d87e2c86a42..963a871e74da 100644
--- a/Documentation/devicetree/bindings/sound/cirrus,cs42l51.yaml
+++ b/Documentation/devicetree/bindings/sound/cirrus,cs42l51.yaml
@@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: CS42L51 audio codec DT bindings
 
 maintainers:
-  - Olivier Moysan <olivier.moysan@st.com>
+  - Olivier Moysan <olivier.moysan@foss.st.com>
 
 properties:
   compatible:
diff --git a/Documentation/devicetree/bindings/sound/ingenic,aic.yaml b/Documentation/devicetree/bindings/sound/ingenic,aic.yaml
index cdc0fdaab30a..d607325f2f15 100644
--- a/Documentation/devicetree/bindings/sound/ingenic,aic.yaml
+++ b/Documentation/devicetree/bindings/sound/ingenic,aic.yaml
@@ -71,7 +71,7 @@ required:
 
 examples:
   - |
-    #include <dt-bindings/clock/jz4740-cgu.h>
+    #include <dt-bindings/clock/ingenic,jz4740-cgu.h>
     aic: audio-controller@10020000 {
       compatible = "ingenic,jz4740-i2s";
       reg = <0x10020000 0x38>;
diff --git a/Documentation/devicetree/bindings/sound/ingenic,codec.yaml b/Documentation/devicetree/bindings/sound/ingenic,codec.yaml
index 97d5f3819b27..48aae54dd643 100644
--- a/Documentation/devicetree/bindings/sound/ingenic,codec.yaml
+++ b/Documentation/devicetree/bindings/sound/ingenic,codec.yaml
@@ -48,7 +48,7 @@ required:
 
 examples:
   - |
-    #include <dt-bindings/clock/jz4740-cgu.h>
+    #include <dt-bindings/clock/ingenic,jz4740-cgu.h>
     codec: audio-codec@10020080 {
       compatible = "ingenic,jz4740-codec";
       reg = <0x10020080 0x8>;
diff --git a/Documentation/devicetree/bindings/sound/st,stm32-i2s.yaml b/Documentation/devicetree/bindings/sound/st,stm32-i2s.yaml
index 6feb5a09c184..d3966ae04ad0 100644
--- a/Documentation/devicetree/bindings/sound/st,stm32-i2s.yaml
+++ b/Documentation/devicetree/bindings/sound/st,stm32-i2s.yaml
@@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: STMicroelectronics STM32 SPI/I2S Controller
 
 maintainers:
-  - Olivier Moysan <olivier.moysan@st.com>
+  - Olivier Moysan <olivier.moysan@foss.st.com>
 
 description:
   The SPI/I2S block supports I2S/PCM protocols when configured on I2S mode.
diff --git a/Documentation/devicetree/bindings/sound/st,stm32-sai.yaml b/Documentation/devicetree/bindings/sound/st,stm32-sai.yaml
index f97132400bb6..1538d11ce9a8 100644
--- a/Documentation/devicetree/bindings/sound/st,stm32-sai.yaml
+++ b/Documentation/devicetree/bindings/sound/st,stm32-sai.yaml
@@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: STMicroelectronics STM32 Serial Audio Interface (SAI)
 
 maintainers:
-  - Olivier Moysan <olivier.moysan@st.com>
+  - Olivier Moysan <olivier.moysan@foss.st.com>
 
 description:
   The SAI interface (Serial Audio Interface) offers a wide set of audio
diff --git a/Documentation/devicetree/bindings/sound/st,stm32-spdifrx.yaml b/Documentation/devicetree/bindings/sound/st,stm32-spdifrx.yaml
index b7f7dc452231..837e830c47ac 100644
--- a/Documentation/devicetree/bindings/sound/st,stm32-spdifrx.yaml
+++ b/Documentation/devicetree/bindings/sound/st,stm32-spdifrx.yaml
@@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: STMicroelectronics STM32 S/PDIF receiver (SPDIFRX)
 
 maintainers:
-  - Olivier Moysan <olivier.moysan@st.com>
+  - Olivier Moysan <olivier.moysan@foss.st.com>
 
 description: |
   The SPDIFRX peripheral, is designed to receive an S/PDIF flow compliant with
diff --git a/Documentation/devicetree/bindings/sound/wlf,wm8962.yaml b/Documentation/devicetree/bindings/sound/wlf,wm8962.yaml
index 0e6249d7c133..5e172e9462b9 100644
--- a/Documentation/devicetree/bindings/sound/wlf,wm8962.yaml
+++ b/Documentation/devicetree/bindings/sound/wlf,wm8962.yaml
@@ -19,6 +19,9 @@ properties:
   clocks:
     maxItems: 1
 
+  interrupts:
+    maxItems: 1
+
   "#sound-dai-cells":
     const: 0
 
diff --git a/Documentation/devicetree/bindings/spi/ingenic,spi.yaml b/Documentation/devicetree/bindings/spi/ingenic,spi.yaml
index cf56cc484b19..5b1c7a2a6a31 100644
--- a/Documentation/devicetree/bindings/spi/ingenic,spi.yaml
+++ b/Documentation/devicetree/bindings/spi/ingenic,spi.yaml
@@ -55,7 +55,7 @@ unevaluatedProperties: false
 
 examples:
   - |
-    #include <dt-bindings/clock/jz4770-cgu.h>
+    #include <dt-bindings/clock/ingenic,jz4770-cgu.h>
     spi@10043000 {
       compatible = "ingenic,jz4770-spi", "ingenic,jz4750-spi";
       reg = <0x10043000 0x1c>;
diff --git a/Documentation/devicetree/bindings/spi/spi-rockchip.yaml b/Documentation/devicetree/bindings/spi/spi-rockchip.yaml
index 7f987e79337c..52a78a2e362e 100644
--- a/Documentation/devicetree/bindings/spi/spi-rockchip.yaml
+++ b/Documentation/devicetree/bindings/spi/spi-rockchip.yaml
@@ -33,6 +33,7 @@ properties:
               - rockchip,rk3328-spi
               - rockchip,rk3368-spi
               - rockchip,rk3399-spi
+              - rockchip,rk3568-spi
               - rockchip,rv1126-spi
           - const: rockchip,rk3066-spi
 
diff --git a/Documentation/devicetree/bindings/spi/spi-xlp.txt b/Documentation/devicetree/bindings/spi/spi-xlp.txt
deleted file mode 100644
index f4925ec0ed33..000000000000
--- a/Documentation/devicetree/bindings/spi/spi-xlp.txt
+++ /dev/null
@@ -1,38 +0,0 @@
-SPI Master controller for Netlogic XLP MIPS64 SOCs
-==================================================
-
-Currently this SPI controller driver is supported for the following
-Netlogic XLP SoCs:
-	XLP832, XLP316, XLP208, XLP980, XLP532
-
-Required properties:
-- compatible		: Should be "netlogic,xlp832-spi".
-- #address-cells	: Number of cells required to define a chip select address
-			  on the SPI bus.
-- #size-cells		: Should be zero.
-- reg			: Should contain register location and length.
-- clocks		: Phandle of the spi clock
-- interrupts		: Interrupt number used by this controller.
-
-SPI slave nodes must be children of the SPI master node and can contain
-properties described in Documentation/devicetree/bindings/spi/spi-bus.txt.
-
-Example:
-
-	spi: xlp_spi@3a100 {
-		compatible = "netlogic,xlp832-spi";
-		#address-cells = <1>;
-		#size-cells = <0>;
-		reg = <0 0x3a100 0x100>;
-		clocks = <&spi_clk>;
-		interrupts = <34>;
-		interrupt-parent = <&pic>;
-
-		spi_nor@1 {
-			compatible = "spansion,s25sl12801";
-			#address-cells = <1>;
-			#size-cells = <1>;
-			reg = <1>;	/* Chip Select */
-			spi-max-frequency = <40000000>;
-		};
-};
diff --git a/Documentation/devicetree/bindings/spi/st,stm32-qspi.yaml b/Documentation/devicetree/bindings/spi/st,stm32-qspi.yaml
index 983c4e54c0be..6ec6f556182f 100644
--- a/Documentation/devicetree/bindings/spi/st,stm32-qspi.yaml
+++ b/Documentation/devicetree/bindings/spi/st,stm32-qspi.yaml
@@ -7,8 +7,8 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: STMicroelectronics STM32 Quad Serial Peripheral Interface (QSPI) bindings
 
 maintainers:
-  - Christophe Kerello <christophe.kerello@st.com>
-  - Patrice Chotard <patrice.chotard@st.com>
+  - Christophe Kerello <christophe.kerello@foss.st.com>
+  - Patrice Chotard <patrice.chotard@foss.st.com>
 
 allOf:
   - $ref: "spi-controller.yaml#"
diff --git a/Documentation/devicetree/bindings/spi/st,stm32-spi.yaml b/Documentation/devicetree/bindings/spi/st,stm32-spi.yaml
index 2d9af4c506bb..3d64bed266ac 100644
--- a/Documentation/devicetree/bindings/spi/st,stm32-spi.yaml
+++ b/Documentation/devicetree/bindings/spi/st,stm32-spi.yaml
@@ -13,8 +13,8 @@ description: |
   from 4 to 32-bit data size.
 
 maintainers:
-  - Erwan Leray <erwan.leray@st.com>
-  - Fabrice Gasnier <fabrice.gasnier@st.com>
+  - Erwan Leray <erwan.leray@foss.st.com>
+  - Fabrice Gasnier <fabrice.gasnier@foss.st.com>
 
 allOf:
   - $ref: "spi-controller.yaml#"
diff --git a/Documentation/devicetree/bindings/thermal/st,stm32-thermal.yaml b/Documentation/devicetree/bindings/thermal/st,stm32-thermal.yaml
index c0f59c56003d..bee41cff5142 100644
--- a/Documentation/devicetree/bindings/thermal/st,stm32-thermal.yaml
+++ b/Documentation/devicetree/bindings/thermal/st,stm32-thermal.yaml
@@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: STMicroelectronics STM32 digital thermal sensor (DTS) binding
 
 maintainers:
-  - David Hernandez Sanchez <david.hernandezsanchez@st.com>
+  - Pascal Paillet <p.paillet@foss.st.com>
 
 properties:
   compatible:
diff --git a/Documentation/devicetree/bindings/timer/ingenic,sysost.yaml b/Documentation/devicetree/bindings/timer/ingenic,sysost.yaml
index df3eb76045e0..98648bf9e151 100644
--- a/Documentation/devicetree/bindings/timer/ingenic,sysost.yaml
+++ b/Documentation/devicetree/bindings/timer/ingenic,sysost.yaml
@@ -46,7 +46,7 @@ additionalProperties: false
 
 examples:
   - |
-    #include <dt-bindings/clock/x1000-cgu.h>
+    #include <dt-bindings/clock/ingenic,x1000-cgu.h>
 
     ost: timer@12000000 {
         compatible = "ingenic,x1000-ost";
diff --git a/Documentation/devicetree/bindings/timer/ingenic,tcu.yaml b/Documentation/devicetree/bindings/timer/ingenic,tcu.yaml
index 8165df4599cf..7fb37eae9da7 100644
--- a/Documentation/devicetree/bindings/timer/ingenic,tcu.yaml
+++ b/Documentation/devicetree/bindings/timer/ingenic,tcu.yaml
@@ -237,7 +237,7 @@ additionalProperties: false
 
 examples:
   - |
-    #include <dt-bindings/clock/jz4770-cgu.h>
+    #include <dt-bindings/clock/ingenic,jz4770-cgu.h>
     #include <dt-bindings/clock/ingenic,tcu.h>
     tcu: timer@10002000 {
       compatible = "ingenic,jz4770-tcu", "ingenic,jz4760-tcu", "simple-mfd";
diff --git a/Documentation/devicetree/bindings/timer/st,stm32-timer.yaml b/Documentation/devicetree/bindings/timer/st,stm32-timer.yaml
index 176aa3c9baf8..937aa8a56366 100644
--- a/Documentation/devicetree/bindings/timer/st,stm32-timer.yaml
+++ b/Documentation/devicetree/bindings/timer/st,stm32-timer.yaml
@@ -7,7 +7,8 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: STMicroelectronics STM32 general-purpose 16 and 32 bits timers bindings
 
 maintainers:
-  - Benjamin Gaignard <benjamin.gaignard@st.com>
+  - Fabrice Gasnier <fabrice.gasnier@foss.st.com>
+  - Patrice Chotard <patrice.chotard@foss.st.com>
 
 properties:
   compatible:
diff --git a/Documentation/devicetree/bindings/usb/ingenic,musb.yaml b/Documentation/devicetree/bindings/usb/ingenic,musb.yaml
index f506225a4d57..59212358fcce 100644
--- a/Documentation/devicetree/bindings/usb/ingenic,musb.yaml
+++ b/Documentation/devicetree/bindings/usb/ingenic,musb.yaml
@@ -58,7 +58,7 @@ additionalProperties: false
 
 examples:
   - |
-    #include <dt-bindings/clock/jz4740-cgu.h>
+    #include <dt-bindings/clock/ingenic,jz4740-cgu.h>
     usb_phy: usb-phy {
       compatible = "usb-nop-xceiv";
       #phy-cells = <0>;
diff --git a/Documentation/devicetree/bindings/usb/st,stusb160x.yaml b/Documentation/devicetree/bindings/usb/st,stusb160x.yaml
index 9a51efa9d101..ead1571e0e43 100644
--- a/Documentation/devicetree/bindings/usb/st,stusb160x.yaml
+++ b/Documentation/devicetree/bindings/usb/st,stusb160x.yaml
@@ -7,7 +7,7 @@ $schema: "http://devicetree.org/meta-schemas/core.yaml#"
 title: STMicroelectronics STUSB160x Type-C controller bindings
 
 maintainers:
-  - Amelie Delaunay <amelie.delaunay@st.com>
+  - Amelie Delaunay <amelie.delaunay@foss.st.com>
 
 properties:
   compatible:
diff --git a/Documentation/devicetree/bindings/watchdog/allwinner,sun4i-a10-wdt.yaml b/Documentation/devicetree/bindings/watchdog/allwinner,sun4i-a10-wdt.yaml
index 44cad9427ae6..43afa24513b9 100644
--- a/Documentation/devicetree/bindings/watchdog/allwinner,sun4i-a10-wdt.yaml
+++ b/Documentation/devicetree/bindings/watchdog/allwinner,sun4i-a10-wdt.yaml
@@ -40,14 +40,12 @@ properties:
 
   clocks:
     minItems: 1
-    maxItems: 2
     items:
       - description: High-frequency oscillator input, divided internally
       - description: Low-frequency oscillator input, only found on some variants
 
   clock-names:
     minItems: 1
-    maxItems: 2
     items:
       - const: hosc
       - const: losc
diff --git a/Documentation/devicetree/bindings/watchdog/st,stm32-iwdg.yaml b/Documentation/devicetree/bindings/watchdog/st,stm32-iwdg.yaml
index 481bf91f988a..39736449ba64 100644
--- a/Documentation/devicetree/bindings/watchdog/st,stm32-iwdg.yaml
+++ b/Documentation/devicetree/bindings/watchdog/st,stm32-iwdg.yaml
@@ -7,8 +7,8 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: STMicroelectronics STM32 Independent WatchDoG (IWDG) bindings
 
 maintainers:
-  - Yannick Fertre <yannick.fertre@st.com>
-  - Christophe Roullier <christophe.roullier@st.com>
+  - Yannick Fertre <yannick.fertre@foss.st.com>
+  - Christophe Roullier <christophe.roullier@foss.st.com>
 
 allOf:
   - $ref: "watchdog.yaml#"
diff --git a/Documentation/doc-guide/sphinx.rst b/Documentation/doc-guide/sphinx.rst
index ec3e71f56009..e445cb146efe 100644
--- a/Documentation/doc-guide/sphinx.rst
+++ b/Documentation/doc-guide/sphinx.rst
@@ -27,7 +27,7 @@ Sphinx Install
 ==============
 
 The ReST markups currently used by the Documentation/ files are meant to be
-built with ``Sphinx`` version 1.3 or higher.
+built with ``Sphinx`` version 1.7 or higher.
 
 There's a script that checks for the Sphinx requirements. Please see
 :ref:`sphinx-pre-install` for further details.
@@ -43,10 +43,6 @@ or ``virtualenv``, depending on how your distribution packaged Python 3.
 
 .. note::
 
-   #) Sphinx versions below 1.5 don't work properly with Python's
-      docutils version 0.13.1 or higher. So, if you're willing to use
-      those versions, you should run ``pip install 'docutils==0.12'``.
-
    #) It is recommended to use the RTD theme for html output. Depending
       on the Sphinx version, it should be installed separately,
       with ``pip install sphinx_rtd_theme``.
@@ -55,13 +51,13 @@ or ``virtualenv``, depending on how your distribution packaged Python 3.
       those expressions are written using LaTeX notation. It needs texlive
       installed with amsfonts and amsmath in order to evaluate them.
 
-In summary, if you want to install Sphinx version 1.7.9, you should do::
+In summary, if you want to install Sphinx version 2.4.4, you should do::
 
-       $ virtualenv sphinx_1.7.9
-       $ . sphinx_1.7.9/bin/activate
-       (sphinx_1.7.9) $ pip install -r Documentation/sphinx/requirements.txt
+       $ virtualenv sphinx_2.4.4
+       $ . sphinx_2.4.4/bin/activate
+       (sphinx_2.4.4) $ pip install -r Documentation/sphinx/requirements.txt
 
-After running ``. sphinx_1.7.9/bin/activate``, the prompt will change,
+After running ``. sphinx_2.4.4/bin/activate``, the prompt will change,
 in order to indicate that you're using the new environment. If you
 open a new shell, you need to rerun this command to enter again at
 the virtual environment before building the documentation.
@@ -81,7 +77,7 @@ output.
 PDF and LaTeX builds
 --------------------
 
-Such builds are currently supported only with Sphinx versions 1.4 and higher.
+Such builds are currently supported only with Sphinx versions 2.4 and higher.
 
 For PDF and LaTeX output, you'll also need ``XeLaTeX`` version 3.14159265.
 
@@ -104,8 +100,8 @@ command line options for your distro::
 	You should run:
 
 		sudo dnf install -y texlive-luatex85
-		/usr/bin/virtualenv sphinx_1.7.9
-		. sphinx_1.7.9/bin/activate
+		/usr/bin/virtualenv sphinx_2.4.4
+		. sphinx_2.4.4/bin/activate
 		pip install -r Documentation/sphinx/requirements.txt
 
 	Can't build as 1 mandatory dependency is missing at ./scripts/sphinx-pre-install line 468.
diff --git a/Documentation/filesystems/autofs.rst b/Documentation/filesystems/autofs.rst
index 681c6a492bc0..4f490278d22f 100644
--- a/Documentation/filesystems/autofs.rst
+++ b/Documentation/filesystems/autofs.rst
@@ -35,7 +35,7 @@ This document describes only the kernel module and the interactions
 required with any user-space program.  Subsequent text refers to this
 as the "automount daemon" or simply "the daemon".
 
-"autofs" is a Linux kernel module with provides the "autofs"
+"autofs" is a Linux kernel module which provides the "autofs"
 filesystem type.  Several "autofs" filesystems can be mounted and they
 can each be managed separately, or all managed by the same daemon.
 
diff --git a/Documentation/filesystems/cifs/ksmbd.rst b/Documentation/filesystems/cifs/ksmbd.rst
index a1326157d53f..b0d354fd8066 100644
--- a/Documentation/filesystems/cifs/ksmbd.rst
+++ b/Documentation/filesystems/cifs/ksmbd.rst
@@ -50,11 +50,11 @@ ksmbd.mountd (user space daemon)
 --------------------------------
 
 ksmbd.mountd is userspace process to, transfer user account and password that
-are registered using ksmbd.adduser(part of utils for user space). Further it
+are registered using ksmbd.adduser (part of utils for user space). Further it
 allows sharing information parameters that parsed from smb.conf to ksmbd in
 kernel. For the execution part it has a daemon which is continuously running
 and connected to the kernel interface using netlink socket, it waits for the
-requests(dcerpc and share/user info). It handles RPC calls (at a minimum few
+requests (dcerpc and share/user info). It handles RPC calls (at a minimum few
 dozen) that are most important for file server from NetShareEnum and
 NetServerGetInfo. Complete DCE/RPC response is prepared from the user space
 and passed over to the associated kernel thread for the client.
@@ -154,11 +154,11 @@ Each layer
 1. Enable all component prints
 	# sudo ksmbd.control -d "all"
 
-2. Enable one of components(smb, auth, vfs, oplock, ipc, conn, rdma)
+2. Enable one of components (smb, auth, vfs, oplock, ipc, conn, rdma)
 	# sudo ksmbd.control -d "smb"
 
-3. Show what prints are enable.
-	# cat/sys/class/ksmbd-control/debug
+3. Show what prints are enabled.
+	# cat /sys/class/ksmbd-control/debug
 	  [smb] auth vfs oplock ipc conn [rdma]
 
 4. Disable prints:
diff --git a/Documentation/filesystems/f2fs.rst b/Documentation/filesystems/f2fs.rst
index 6f3c6e91346d..d7b84695f56a 100644
--- a/Documentation/filesystems/f2fs.rst
+++ b/Documentation/filesystems/f2fs.rst
@@ -197,10 +197,29 @@ fault_type=%d		 Support configuring fault injection type, should be
 			 FAULT_DISCARD		  0x000002000
 			 FAULT_WRITE_IO		  0x000004000
 			 FAULT_SLAB_ALLOC	  0x000008000
+			 FAULT_DQUOT_INIT	  0x000010000
 			 ===================	  ===========
 mode=%s			 Control block allocation mode which supports "adaptive"
 			 and "lfs". In "lfs" mode, there should be no random
 			 writes towards main area.
+			 "fragment:segment" and "fragment:block" are newly added here.
+			 These are developer options for experiments to simulate filesystem
+			 fragmentation/after-GC situation itself. The developers use these
+			 modes to understand filesystem fragmentation/after-GC condition well,
+			 and eventually get some insights to handle them better.
+			 In "fragment:segment", f2fs allocates a new segment in ramdom
+			 position. With this, we can simulate the after-GC condition.
+			 In "fragment:block", we can scatter block allocation with
+			 "max_fragment_chunk" and "max_fragment_hole" sysfs nodes.
+			 We added some randomness to both chunk and hole size to make
+			 it close to realistic IO pattern. So, in this mode, f2fs will allocate
+			 1..<max_fragment_chunk> blocks in a chunk and make a hole in the
+			 length of 1..<max_fragment_hole> by turns. With this, the newly
+			 allocated blocks will be scattered throughout the whole partition.
+			 Note that "fragment:block" implicitly enables "fragment:segment"
+			 option for more randomness.
+			 Please, use these options for your experiments and we strongly
+			 recommend to re-format the filesystem after using these options.
 io_bits=%u		 Set the bit size of write IO requests. It should be set
 			 with "mode=lfs".
 usrquota		 Enable plain user disk quota accounting.
diff --git a/Documentation/filesystems/netfs_library.rst b/Documentation/filesystems/netfs_library.rst
index bb68d39f03b7..375baca7edcd 100644
--- a/Documentation/filesystems/netfs_library.rst
+++ b/Documentation/filesystems/netfs_library.rst
@@ -1,7 +1,7 @@
 .. SPDX-License-Identifier: GPL-2.0
 
 =================================
-NETWORK FILESYSTEM HELPER LIBRARY
+Network Filesystem Helper Library
 =================================
 
 .. Contents:
@@ -37,22 +37,22 @@ into a common call framework.
 
 The following services are provided:
 
- * Handles transparent huge pages (THPs).
+ * Handle folios that span multiple pages.
 
- * Insulates the netfs from VM interface changes.
+ * Insulate the netfs from VM interface changes.
 
- * Allows the netfs to arbitrarily split reads up into pieces, even ones that
-   don't match page sizes or page alignments and that may cross pages.
+ * Allow the netfs to arbitrarily split reads up into pieces, even ones that
+   don't match folio sizes or folio alignments and that may cross folios.
 
- * Allows the netfs to expand a readahead request in both directions to meet
-   its needs.
+ * Allow the netfs to expand a readahead request in both directions to meet its
+   needs.
 
- * Allows the netfs to partially fulfil a read, which will then be resubmitted.
+ * Allow the netfs to partially fulfil a read, which will then be resubmitted.
 
- * Handles local caching, allowing cached data and server-read data to be
+ * Handle local caching, allowing cached data and server-read data to be
    interleaved for a single request.
 
- * Handles clearing of bufferage that aren't on the server.
+ * Handle clearing of bufferage that aren't on the server.
 
  * Handle retrying of reads that failed, switching reads from the cache to the
    server as necessary.
@@ -70,22 +70,22 @@ Read Helper Functions
 
 Three read helpers are provided::
 
- * void netfs_readahead(struct readahead_control *ractl,
-			const struct netfs_read_request_ops *ops,
-			void *netfs_priv);``
- * int netfs_readpage(struct file *file,
-		      struct page *page,
-		      const struct netfs_read_request_ops *ops,
-		      void *netfs_priv);
- * int netfs_write_begin(struct file *file,
-			 struct address_space *mapping,
-			 loff_t pos,
-			 unsigned int len,
-			 unsigned int flags,
-			 struct page **_page,
-			 void **_fsdata,
-			 const struct netfs_read_request_ops *ops,
-			 void *netfs_priv);
+	void netfs_readahead(struct readahead_control *ractl,
+			     const struct netfs_read_request_ops *ops,
+			     void *netfs_priv);
+	int netfs_readpage(struct file *file,
+			   struct folio *folio,
+			   const struct netfs_read_request_ops *ops,
+			   void *netfs_priv);
+	int netfs_write_begin(struct file *file,
+			      struct address_space *mapping,
+			      loff_t pos,
+			      unsigned int len,
+			      unsigned int flags,
+			      struct folio **_folio,
+			      void **_fsdata,
+			      const struct netfs_read_request_ops *ops,
+			      void *netfs_priv);
 
 Each corresponds to a VM operation, with the addition of a couple of parameters
 for the use of the read helpers:
@@ -103,8 +103,8 @@ Both of these values will be stored into the read request structure.
 For ->readahead() and ->readpage(), the network filesystem should just jump
 into the corresponding read helper; whereas for ->write_begin(), it may be a
 little more complicated as the network filesystem might want to flush
-conflicting writes or track dirty data and needs to put the acquired page if an
-error occurs after calling the helper.
+conflicting writes or track dirty data and needs to put the acquired folio if
+an error occurs after calling the helper.
 
 The helpers manage the read request, calling back into the network filesystem
 through the suppplied table of operations.  Waits will be performed as
@@ -253,7 +253,7 @@ through which it can issue requests and negotiate::
 		void (*issue_op)(struct netfs_read_subrequest *subreq);
 		bool (*is_still_valid)(struct netfs_read_request *rreq);
 		int (*check_write_begin)(struct file *file, loff_t pos, unsigned len,
-					 struct page *page, void **_fsdata);
+					 struct folio *folio, void **_fsdata);
 		void (*done)(struct netfs_read_request *rreq);
 		void (*cleanup)(struct address_space *mapping, void *netfs_priv);
 	};
@@ -313,13 +313,14 @@ The operations are as follows:
 
    There is no return value; the netfs_subreq_terminated() function should be
    called to indicate whether or not the operation succeeded and how much data
-   it transferred.  The filesystem also should not deal with setting pages
+   it transferred.  The filesystem also should not deal with setting folios
    uptodate, unlocking them or dropping their refs - the helpers need to deal
    with this as they have to coordinate with copying to the local cache.
 
-   Note that the helpers have the pages locked, but not pinned.  It is possible
-   to use the ITER_XARRAY iov iterator to refer to the range of the inode that
-   is being operated upon without the need to allocate large bvec tables.
+   Note that the helpers have the folios locked, but not pinned.  It is
+   possible to use the ITER_XARRAY iov iterator to refer to the range of the
+   inode that is being operated upon without the need to allocate large bvec
+   tables.
 
  * ``is_still_valid()``
 
@@ -330,15 +331,15 @@ The operations are as follows:
  * ``check_write_begin()``
 
    [Optional] This is called from the netfs_write_begin() helper once it has
-   allocated/grabbed the page to be modified to allow the filesystem to flush
+   allocated/grabbed the folio to be modified to allow the filesystem to flush
    conflicting state before allowing it to be modified.
 
-   It should return 0 if everything is now fine, -EAGAIN if the page should be
+   It should return 0 if everything is now fine, -EAGAIN if the folio should be
    regrabbed and any other error code to abort the operation.
 
  * ``done``
 
-   [Optional] This is called after the pages in the request have all been
+   [Optional] This is called after the folios in the request have all been
    unlocked (and marked uptodate if applicable).
 
  * ``cleanup``
@@ -390,7 +391,7 @@ The read helpers work by the following general procedure:
      * If NETFS_SREQ_CLEAR_TAIL was set, a short read will be cleared to the
        end of the slice instead of reissuing.
 
- * Once the data is read, the pages that have been fully read/cleared:
+ * Once the data is read, the folios that have been fully read/cleared:
 
    * Will be marked uptodate.
 
@@ -398,11 +399,11 @@ The read helpers work by the following general procedure:
 
    * Unlocked
 
- * Any pages that need writing to the cache will then have DIO writes issued.
+ * Any folios that need writing to the cache will then have DIO writes issued.
 
  * Synchronous operations will wait for reading to be complete.
 
- * Writes to the cache will proceed asynchronously and the pages will have the
+ * Writes to the cache will proceed asynchronously and the folios will have the
    PG_fscache mark removed when that completes.
 
  * The request structures will be cleaned up when everything has completed.
@@ -452,6 +453,9 @@ operation table looks like the following::
 			    netfs_io_terminated_t term_func,
 			    void *term_func_priv);
 
+		int (*prepare_write)(struct netfs_cache_resources *cres,
+				     loff_t *_start, size_t *_len, loff_t i_size);
+
 		int (*write)(struct netfs_cache_resources *cres,
 			     loff_t start_pos,
 			     struct iov_iter *iter,
@@ -509,6 +513,14 @@ The methods defined in the table are:
    indicating whether the termination is definitely happening in the caller's
    context.
 
+ * ``prepare_write()``
+
+   [Required] Called to adjust a write to the cache and check that there is
+   sufficient space in the cache.  The start and length values indicate the
+   size of the write that netfslib is proposing, and this can be adjusted by
+   the cache to respect DIO boundaries.  The file size is passed for
+   information.
+
  * ``write()``
 
    [Required] Called to write to the cache.  The start file offset is given
@@ -525,4 +537,9 @@ not the read request structure as they could be used in other situations where
 there isn't a read request structure as well, such as writing dirty data to the
 cache.
 
+
+API Function Reference
+======================
+
 .. kernel-doc:: include/linux/netfs.h
+.. kernel-doc:: fs/netfs/read_helper.c
diff --git a/Documentation/i2c/smbus-protocol.rst b/Documentation/i2c/smbus-protocol.rst
index 9e07e6bbe6a3..00d8e17d0aca 100644
--- a/Documentation/i2c/smbus-protocol.rst
+++ b/Documentation/i2c/smbus-protocol.rst
@@ -36,6 +36,8 @@ Key to symbols
 
 =============== =============================================================
 S               Start condition
+Sr              Repeated start condition, used to switch from write to
+                read mode.
 P               Stop condition
 Rd/Wr (1 bit)   Read/Write bit. Rd equals 1, Wr equals 0.
 A, NA (1 bit)   Acknowledge (ACK) and Not Acknowledge (NACK) bit
@@ -100,7 +102,7 @@ Implemented by i2c_smbus_read_byte_data()
 This reads a single byte from a device, from a designated register.
 The register is specified through the Comm byte::
 
-  S Addr Wr [A] Comm [A] S Addr Rd [A] [Data] NA P
+  S Addr Wr [A] Comm [A] Sr Addr Rd [A] [Data] NA P
 
 Functionality flag: I2C_FUNC_SMBUS_READ_BYTE_DATA
 
@@ -114,7 +116,7 @@ This operation is very like Read Byte; again, data is read from a
 device, from a designated register that is specified through the Comm
 byte. But this time, the data is a complete word (16 bits)::
 
-  S Addr Wr [A] Comm [A] S Addr Rd [A] [DataLow] A [DataHigh] NA P
+  S Addr Wr [A] Comm [A] Sr Addr Rd [A] [DataLow] A [DataHigh] NA P
 
 Functionality flag: I2C_FUNC_SMBUS_READ_WORD_DATA
 
@@ -164,7 +166,7 @@ This command selects a device register (through the Comm byte), sends
 16 bits of data to it, and reads 16 bits of data in return::
 
   S Addr Wr [A] Comm [A] DataLow [A] DataHigh [A]
-                               S Addr Rd [A] [DataLow] A [DataHigh] NA P
+                              Sr Addr Rd [A] [DataLow] A [DataHigh] NA P
 
 Functionality flag: I2C_FUNC_SMBUS_PROC_CALL
 
@@ -181,7 +183,7 @@ of data is specified by the device in the Count byte.
 ::
 
   S Addr Wr [A] Comm [A]
-             S Addr Rd [A] [Count] A [Data] A [Data] A ... A [Data] NA P
+            Sr Addr Rd [A] [Count] A [Data] A [Data] A ... A [Data] NA P
 
 Functionality flag: I2C_FUNC_SMBUS_READ_BLOCK_DATA
 
@@ -212,7 +214,7 @@ This command selects a device register (through the Comm byte), sends
 1 to 31 bytes of data to it, and reads 1 to 31 bytes of data in return::
 
   S Addr Wr [A] Comm [A] Count [A] Data [A] ...
-                               S Addr Rd [A] [Count] A [Data] ... A P
+                              Sr Addr Rd [A] [Count] A [Data] ... A P
 
 Functionality flag: I2C_FUNC_SMBUS_BLOCK_PROC_CALL
 
@@ -300,7 +302,7 @@ This command reads a block of bytes from a device, from a
 designated register that is specified through the Comm byte::
 
   S Addr Wr [A] Comm [A]
-             S Addr Rd [A] [Data] A [Data] A ... A [Data] NA P
+            Sr Addr Rd [A] [Data] A [Data] A ... A [Data] NA P
 
 Functionality flag: I2C_FUNC_SMBUS_READ_I2C_BLOCK
 
diff --git a/Documentation/locking/locktypes.rst b/Documentation/locking/locktypes.rst
index ddada4a53749..4fd7b70fcde1 100644
--- a/Documentation/locking/locktypes.rst
+++ b/Documentation/locking/locktypes.rst
@@ -439,11 +439,9 @@ preemption. The following substitution works on both kernels::
   spin_lock(&p->lock);
   p->count += this_cpu_read(var2);
 
-On a non-PREEMPT_RT kernel migrate_disable() maps to preempt_disable()
-which makes the above code fully equivalent. On a PREEMPT_RT kernel
 migrate_disable() ensures that the task is pinned on the current CPU which
 in turn guarantees that the per-CPU access to var1 and var2 are staying on
-the same CPU.
+the same CPU while the task remains preemptible.
 
 The migrate_disable() substitution is not valid for the following
 scenario::
@@ -456,9 +454,8 @@ scenario::
     p = this_cpu_ptr(&var1);
     p->val = func2();
 
-While correct on a non-PREEMPT_RT kernel, this breaks on PREEMPT_RT because
-here migrate_disable() does not protect against reentrancy from a
-preempting task. A correct substitution for this case is::
+This breaks because migrate_disable() does not protect against reentrancy from
+a preempting task. A correct substitution for this case is::
 
   func()
   {
diff --git a/Documentation/networking/bonding.rst b/Documentation/networking/bonding.rst
index 31cfd7d674a6..c0a789b00806 100644
--- a/Documentation/networking/bonding.rst
+++ b/Documentation/networking/bonding.rst
@@ -196,11 +196,12 @@ ad_actor_sys_prio
 ad_actor_system
 
 	In an AD system, this specifies the mac-address for the actor in
-	protocol packet exchanges (LACPDUs). The value cannot be NULL or
-	multicast. It is preferred to have the local-admin bit set for this
-	mac but driver does not enforce it. If the value is not given then
-	system defaults to using the masters' mac address as actors' system
-	address.
+	protocol packet exchanges (LACPDUs). The value cannot be a multicast
+	address. If the all-zeroes MAC is specified, bonding will internally
+	use the MAC of the bond itself. It is preferred to have the
+	local-admin bit set for this mac but driver does not enforce it. If
+	the value is not given then system defaults to using the masters'
+	mac address as actors' system address.
 
 	This parameter has effect only in 802.3ad mode and is available through
 	SysFs interface.
diff --git a/Documentation/networking/device_drivers/ethernet/freescale/dpaa2/overview.rst b/Documentation/networking/device_drivers/ethernet/freescale/dpaa2/overview.rst
index d638b5a8aadd..199647729251 100644
--- a/Documentation/networking/device_drivers/ethernet/freescale/dpaa2/overview.rst
+++ b/Documentation/networking/device_drivers/ethernet/freescale/dpaa2/overview.rst
@@ -183,6 +183,7 @@ PHY and allows physical transmission and reception of Ethernet frames.
   IRQ config, enable, reset
 
 DPNI (Datapath Network Interface)
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 Contains TX/RX queues, network interface configuration, and RX buffer pool
 configuration mechanisms.  The TX/RX queues are in memory and are identified
 by queue number.
diff --git a/Documentation/networking/device_drivers/ethernet/intel/ixgbe.rst b/Documentation/networking/device_drivers/ethernet/intel/ixgbe.rst
index f1d5233e5e51..0a233b17c664 100644
--- a/Documentation/networking/device_drivers/ethernet/intel/ixgbe.rst
+++ b/Documentation/networking/device_drivers/ethernet/intel/ixgbe.rst
@@ -440,6 +440,22 @@ NOTE: For 82599-based network connections, if you are enabling jumbo frames in
 a virtual function (VF), jumbo frames must first be enabled in the physical
 function (PF). The VF MTU setting cannot be larger than the PF MTU.
 
+NBASE-T Support
+---------------
+The ixgbe driver supports NBASE-T on some devices. However, the advertisement
+of NBASE-T speeds is suppressed by default, to accommodate broken network
+switches which cannot cope with advertised NBASE-T speeds. Use the ethtool
+command to enable advertising NBASE-T speeds on devices which support it::
+
+  ethtool -s eth? advertise 0x1800000001028
+
+On Linux systems with INTERFACES(5), this can be specified as a pre-up command
+in /etc/network/interfaces so that the interface is always brought up with
+NBASE-T support, e.g.::
+
+  iface eth? inet dhcp
+       pre-up ethtool -s eth? advertise 0x1800000001028 || true
+
 Generic Receive Offload, aka GRO
 --------------------------------
 The driver supports the in-kernel software implementation of GRO. GRO has
diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst
index c04431144f7a..2572eecc3e86 100644
--- a/Documentation/networking/ip-sysctl.rst
+++ b/Documentation/networking/ip-sysctl.rst
@@ -25,7 +25,8 @@ ip_default_ttl - INTEGER
 ip_no_pmtu_disc - INTEGER
 	Disable Path MTU Discovery. If enabled in mode 1 and a
 	fragmentation-required ICMP is received, the PMTU to this
-	destination will be set to min_pmtu (see below). You will need
+	destination will be set to the smallest of the old MTU to
+	this destination and min_pmtu (see below). You will need
 	to raise min_pmtu to the smallest interface MTU on your system
 	manually if you want to avoid locally generated fragments.
 
@@ -49,7 +50,8 @@ ip_no_pmtu_disc - INTEGER
 	Default: FALSE
 
 min_pmtu - INTEGER
-	default 552 - minimum discovered Path MTU
+	default 552 - minimum Path MTU. Unless this is changed mannually,
+	each cached pmtu will never be lower than this setting.
 
 ip_forward_use_pmtu - BOOLEAN
 	By default we don't trust protocol path MTUs while forwarding
diff --git a/Documentation/networking/ipvs-sysctl.rst b/Documentation/networking/ipvs-sysctl.rst
index 95ef56d62077..387fda80f05f 100644
--- a/Documentation/networking/ipvs-sysctl.rst
+++ b/Documentation/networking/ipvs-sysctl.rst
@@ -37,8 +37,7 @@ conn_reuse_mode - INTEGER
 
 	0: disable any special handling on port reuse. The new
 	connection will be delivered to the same real server that was
-	servicing the previous connection. This will effectively
-	disable expire_nodest_conn.
+	servicing the previous connection.
 
 	bit 1: enable rescheduling of new connections when it is safe.
 	That is, whenever expire_nodest_conn and for TCP sockets, when
diff --git a/Documentation/networking/timestamping.rst b/Documentation/networking/timestamping.rst
index a722eb30e014..f5809206eb93 100644
--- a/Documentation/networking/timestamping.rst
+++ b/Documentation/networking/timestamping.rst
@@ -486,8 +486,8 @@ of packets.
 Drivers are free to use a more permissive configuration than the requested
 configuration. It is expected that drivers should only implement directly the
 most generic mode that can be supported. For example if the hardware can
-support HWTSTAMP_FILTER_V2_EVENT, then it should generally always upscale
-HWTSTAMP_FILTER_V2_L2_SYNC_MESSAGE, and so forth, as HWTSTAMP_FILTER_V2_EVENT
+support HWTSTAMP_FILTER_PTP_V2_EVENT, then it should generally always upscale
+HWTSTAMP_FILTER_PTP_V2_L2_SYNC, and so forth, as HWTSTAMP_FILTER_PTP_V2_EVENT
 is more generic (and more useful to applications).
 
 A driver which supports hardware time stamping shall update the struct
@@ -582,8 +582,8 @@ Time stamps for outgoing packets are to be generated as follows:
   and hardware timestamping is not possible (SKBTX_IN_PROGRESS not set).
 - As soon as the driver has sent the packet and/or obtained a
   hardware time stamp for it, it passes the time stamp back by
-  calling skb_hwtstamp_tx() with the original skb, the raw
-  hardware time stamp. skb_hwtstamp_tx() clones the original skb and
+  calling skb_tstamp_tx() with the original skb, the raw
+  hardware time stamp. skb_tstamp_tx() clones the original skb and
   adds the timestamps, therefore the original skb has to be freed now.
   If obtaining the hardware time stamp somehow fails, then the driver
   should not fall back to software time stamping. The rationale is that
diff --git a/Documentation/power/energy-model.rst b/Documentation/power/energy-model.rst
index 8a2788afe89b..5ac62a7b4b7c 100644
--- a/Documentation/power/energy-model.rst
+++ b/Documentation/power/energy-model.rst
@@ -84,6 +84,16 @@ CONFIG_ENERGY_MODEL must be enabled to use the EM framework.
 2.2 Registration of performance domains
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
+Registration of 'advanced' EM
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The 'advanced' EM gets it's name due to the fact that the driver is allowed
+to provide more precised power model. It's not limited to some implemented math
+formula in the framework (like it's in 'simple' EM case). It can better reflect
+the real power measurements performed for each performance state. Thus, this
+registration method should be preferred in case considering EM static power
+(leakage) is important.
+
 Drivers are expected to register performance domains into the EM framework by
 calling the following API::
 
@@ -103,6 +113,18 @@ to: return warning/error, stop working or panic.
 See Section 3. for an example of driver implementing this
 callback, or Section 2.4 for further documentation on this API
 
+Registration of 'simple' EM
+~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The 'simple' EM is registered using the framework helper function
+cpufreq_register_em_with_opp(). It implements a power model which is tight to
+math formula::
+
+	Power = C * V^2 * f
+
+The EM which is registered using this method might not reflect correctly the
+physics of a real device, e.g. when static power (leakage) is important.
+
 
 2.3 Accessing performance domains
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
@@ -138,6 +160,10 @@ or in Section 2.4
 3. Example driver
 -----------------
 
+The CPUFreq framework supports dedicated callback for registering
+the EM for a given CPU(s) 'policy' object: cpufreq_driver::register_em().
+That callback has to be implemented properly for a given driver,
+because the framework would call it at the right time during setup.
 This section provides a simple example of a CPUFreq driver registering a
 performance domain in the Energy Model framework using the (fake) 'foo'
 protocol. The driver implements an est_power() function to be provided to the
@@ -167,25 +193,22 @@ EM framework::
   20		return 0;
   21	}
   22
-  23	static int foo_cpufreq_init(struct cpufreq_policy *policy)
+  23	static void foo_cpufreq_register_em(struct cpufreq_policy *policy)
   24	{
   25		struct em_data_callback em_cb = EM_DATA_CB(est_power);
   26		struct device *cpu_dev;
-  27		int nr_opp, ret;
+  27		int nr_opp;
   28
   29		cpu_dev = get_cpu_device(cpumask_first(policy->cpus));
   30
-  31     	/* Do the actual CPUFreq init work ... */
-  32     	ret = do_foo_cpufreq_init(policy);
-  33     	if (ret)
-  34     		return ret;
-  35
-  36     	/* Find the number of OPPs for this policy */
-  37     	nr_opp = foo_get_nr_opp(policy);
+  31     	/* Find the number of OPPs for this policy */
+  32     	nr_opp = foo_get_nr_opp(policy);
+  33
+  34     	/* And register the new performance domain */
+  35     	em_dev_register_perf_domain(cpu_dev, nr_opp, &em_cb, policy->cpus,
+  36					    true);
+  37	}
   38
-  39     	/* And register the new performance domain */
-  40     	em_dev_register_perf_domain(cpu_dev, nr_opp, &em_cb, policy->cpus,
-  41					    true);
-  42
-  43	        return 0;
-  44	}
+  39	static struct cpufreq_driver foo_cpufreq_driver = {
+  40		.register_em = foo_cpufreq_register_em,
+  41	};
diff --git a/Documentation/process/changes.rst b/Documentation/process/changes.rst
index e35ab74a0f80..cf908d79666e 100644
--- a/Documentation/process/changes.rst
+++ b/Documentation/process/changes.rst
@@ -35,6 +35,7 @@ GNU make               3.81             make --version
 binutils               2.23             ld -v
 flex                   2.5.35           flex --version
 bison                  2.0              bison --version
+pahole                 1.16             pahole --version
 util-linux             2.10o            fdformat --version
 kmod                   13               depmod -V
 e2fsprogs              1.41.4           e2fsck -V
@@ -54,7 +55,7 @@ mcelog                 0.6              mcelog --version
 iptables               1.4.2            iptables -V
 openssl & libcrypto    1.0.0            openssl version
 bc                     1.06.95          bc --version
-Sphinx\ [#f1]_	       1.3		sphinx-build --version
+Sphinx\ [#f1]_         1.7              sphinx-build --version
 ====================== ===============  ========================================
 
 .. [#f1] Sphinx is needed only to build the Kernel documentation
@@ -108,6 +109,16 @@ Bison
 Since Linux 4.16, the build system generates parsers
 during build.  This requires bison 2.0 or later.
 
+pahole:
+-------
+
+Since Linux 5.2, if CONFIG_DEBUG_INFO_BTF is selected, the build system
+generates BTF (BPF Type Format) from DWARF in vmlinux, a bit later from kernel
+modules as well.  This requires pahole v1.16 or later.
+
+It is found in the 'dwarves' or 'pahole' distro packages or from
+https://fedorapeople.org/~acme/dwarves/.
+
 Perl
 ----
 
diff --git a/Documentation/process/submitting-patches.rst b/Documentation/process/submitting-patches.rst
index a0cc96923ea7..6b3aaed66fba 100644
--- a/Documentation/process/submitting-patches.rst
+++ b/Documentation/process/submitting-patches.rst
@@ -14,7 +14,8 @@ works, see Documentation/process/development-process.rst. Also, read
 Documentation/process/submit-checklist.rst
 for a list of items to check before submitting code.  If you are submitting
 a driver, also read Documentation/process/submitting-drivers.rst; for device
-tree binding patches, read Documentation/process/submitting-patches.rst.
+tree binding patches, read
+Documentation/devicetree/bindings/submitting-patches.rst.
 
 This documentation assumes that you're using ``git`` to prepare your patches.
 If you're unfamiliar with ``git``, you would be well-advised to learn how to
@@ -22,8 +23,8 @@ use it, it will make your life as a kernel developer and in general much
 easier.
 
 Some subsystems and maintainer trees have additional information about
-their workflow and expectations, see :ref:`Documentation/process/maintainer
-handbooks <maintainer_handbooks_main>`.
+their workflow and expectations, see
+:ref:`Documentation/process/maintainer-handbooks.rst <maintainer_handbooks_main>`.
 
 Obtain a current source tree
 ----------------------------
diff --git a/Documentation/security/SCTP.rst b/Documentation/security/SCTP.rst
index 406cc68b8808..d5fd6ccc3dcb 100644
--- a/Documentation/security/SCTP.rst
+++ b/Documentation/security/SCTP.rst
@@ -15,7 +15,10 @@ For security module support, three SCTP specific hooks have been implemented::
     security_sctp_assoc_request()
     security_sctp_bind_connect()
     security_sctp_sk_clone()
-    security_sctp_assoc_established()
+
+Also the following security hook has been utilised::
+
+    security_inet_conn_established()
 
 The usage of these hooks are described below with the SELinux implementation
 described in the `SCTP SELinux Support`_ chapter.
@@ -119,12 +122,11 @@ calls **sctp_peeloff**\(3).
     @newsk - pointer to new sock structure.
 
 
-security_sctp_assoc_established()
+security_inet_conn_established()
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-Called when a COOKIE ACK is received, and the peer secid will be
-saved into ``@asoc->peer_secid`` for client::
+Called when a COOKIE ACK is received::
 
-    @asoc - pointer to sctp association structure.
+    @sk  - pointer to sock structure.
     @skb - pointer to skbuff of the COOKIE ACK packet.
 
 
@@ -132,7 +134,7 @@ Security Hooks used for Association Establishment
 -------------------------------------------------
 
 The following diagram shows the use of ``security_sctp_bind_connect()``,
-``security_sctp_assoc_request()``, ``security_sctp_assoc_established()`` when
+``security_sctp_assoc_request()``, ``security_inet_conn_established()`` when
 establishing an association.
 ::
 
@@ -170,7 +172,7 @@ establishing an association.
           <------------------------------------------- COOKIE ACK
           |                                               |
     sctp_sf_do_5_1E_ca                                    |
- Call security_sctp_assoc_established()                   |
+ Call security_inet_conn_established()                    |
  to set the peer label.                                   |
           |                                               |
           |                               If SCTP_SOCKET_TCP or peeled off
@@ -196,7 +198,7 @@ hooks with the SELinux specifics expanded below::
     security_sctp_assoc_request()
     security_sctp_bind_connect()
     security_sctp_sk_clone()
-    security_sctp_assoc_established()
+    security_inet_conn_established()
 
 
 security_sctp_assoc_request()
@@ -269,12 +271,12 @@ sockets sid and peer sid to that contained in the ``@asoc sid`` and
     @newsk - pointer to new sock structure.
 
 
-security_sctp_assoc_established()
+security_inet_conn_established()
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 Called when a COOKIE ACK is received where it sets the connection's peer sid
 to that in ``@skb``::
 
-    @asoc - pointer to sctp association structure.
+    @sk  - pointer to sock structure.
     @skb - pointer to skbuff of the COOKIE ACK packet.
 
 
diff --git a/Documentation/sound/hd-audio/models.rst b/Documentation/sound/hd-audio/models.rst
index 0ea967d34583..d25335993e55 100644
--- a/Documentation/sound/hd-audio/models.rst
+++ b/Documentation/sound/hd-audio/models.rst
@@ -326,6 +326,8 @@ usi-headset
     Headset support on USI machines
 dual-codecs
     Lenovo laptops with dual codecs
+alc285-hp-amp-init
+    HP laptops which require speaker amplifier initialization (ALC285)
 
 ALC680
 ======
diff --git a/Documentation/trace/ftrace.rst b/Documentation/trace/ftrace.rst
index 4e5b26f03d5b..b3166c4a7867 100644
--- a/Documentation/trace/ftrace.rst
+++ b/Documentation/trace/ftrace.rst
@@ -2442,11 +2442,10 @@ Or this simple script!
   #!/bin/bash
 
   tracefs=`sed -ne 's/^tracefs \(.*\) tracefs.*/\1/p' /proc/mounts`
-  echo nop > $tracefs/tracing/current_tracer
-  echo 0 > $tracefs/tracing/tracing_on
-  echo $$ > $tracefs/tracing/set_ftrace_pid
-  echo function > $tracefs/tracing/current_tracer
-  echo 1 > $tracefs/tracing/tracing_on
+  echo 0 > $tracefs/tracing_on
+  echo $$ > $tracefs/set_ftrace_pid
+  echo function > $tracefs/current_tracer
+  echo 1 > $tracefs/tracing_on
   exec "$@"
 
 
diff --git a/Documentation/translations/it_IT/doc-guide/sphinx.rst b/Documentation/translations/it_IT/doc-guide/sphinx.rst
index 0046d75d9a70..9762452c584c 100644
--- a/Documentation/translations/it_IT/doc-guide/sphinx.rst
+++ b/Documentation/translations/it_IT/doc-guide/sphinx.rst
@@ -35,7 +35,7 @@ Installazione Sphinx
 ====================
 
 I marcatori ReST utilizzati nei file in Documentation/ sono pensati per essere
-processati da ``Sphinx`` nella versione 1.3 o superiore.
+processati da ``Sphinx`` nella versione 1.7 o superiore.
 
 Esiste uno script che verifica i requisiti Sphinx. Per ulteriori dettagli
 consultate :ref:`it_sphinx-pre-install`.
@@ -53,11 +53,6 @@ pacchettizzato dalla vostra distribuzione.
 
 .. note::
 
-   #) Le versioni di Sphinx inferiori alla 1.5 non funzionano bene
-      con il pacchetto Python docutils versione 0.13.1 o superiore.
-      Se volete usare queste versioni, allora dovere eseguire
-      ``pip install 'docutils==0.12'``.
-
    #) Viene raccomandato l'uso del tema RTD per la documentazione in HTML.
       A seconda della versione di Sphinx, potrebbe essere necessaria
       l'installazione tramite il comando ``pip install sphinx_rtd_theme``.
@@ -67,13 +62,13 @@ pacchettizzato dalla vostra distribuzione.
       utilizzando LaTeX. Per una corretta interpretazione, è necessario aver
       installato texlive con i pacchetti amdfonts e amsmath.
 
-Riassumendo, se volete installare la versione 1.7.9 di Sphinx dovete eseguire::
+Riassumendo, se volete installare la versione 2.4.4 di Sphinx dovete eseguire::
 
-       $ virtualenv sphinx_1.7.9
-       $ . sphinx_1.7.9/bin/activate
-       (sphinx_1.7.9) $ pip install -r Documentation/sphinx/requirements.txt
+       $ virtualenv sphinx_2.4.4
+       $ . sphinx_2.4.4/bin/activate
+       (sphinx_2.4.4) $ pip install -r Documentation/sphinx/requirements.txt
 
-Dopo aver eseguito ``. sphinx_1.7.9/bin/activate``, il prompt cambierà per
+Dopo aver eseguito ``. sphinx_2.4.4/bin/activate``, il prompt cambierà per
 indicare che state usando il nuovo ambiente. Se aprite un nuova sessione,
 prima di generare la documentazione, dovrete rieseguire questo comando per
 rientrare nell'ambiente virtuale.
@@ -94,7 +89,7 @@ Generazione in PDF e LaTeX
 --------------------------
 
 Al momento, la generazione di questi documenti è supportata solo dalle
-versioni di Sphinx superiori alla 1.4.
+versioni di Sphinx superiori alla 2.4.
 
 Per la generazione di PDF e LaTeX, avrete bisogno anche del pacchetto
 ``XeLaTeX`` nella versione 3.14159265
@@ -119,8 +114,8 @@ l'installazione::
 	You should run:
 
 		sudo dnf install -y texlive-luatex85
-		/usr/bin/virtualenv sphinx_1.7.9
-		. sphinx_1.7.9/bin/activate
+		/usr/bin/virtualenv sphinx_2.4.4
+		. sphinx_2.4.4/bin/activate
 		pip install -r Documentation/sphinx/requirements.txt
 
 	Can't build as 1 mandatory dependency is missing at ./scripts/sphinx-pre-install line 468.
diff --git a/Documentation/translations/it_IT/process/changes.rst b/Documentation/translations/it_IT/process/changes.rst
index 87d081889bfc..dc7193377b7f 100644
--- a/Documentation/translations/it_IT/process/changes.rst
+++ b/Documentation/translations/it_IT/process/changes.rst
@@ -57,7 +57,7 @@ mcelog                 0.6                mcelog --version
 iptables               1.4.2              iptables -V
 openssl & libcrypto    1.0.0              openssl version
 bc                     1.06.95            bc --version
-Sphinx\ [#f1]_         1.3                sphinx-build --version
+Sphinx\ [#f1]_         1.7                sphinx-build --version
 ====================== =================  ========================================
 
 .. [#f1] Sphinx è necessario solo per produrre la documentazione del Kernel
diff --git a/Documentation/translations/zh_CN/doc-guide/sphinx.rst b/Documentation/translations/zh_CN/doc-guide/sphinx.rst
index 951595c7d599..23eac67fbc30 100644
--- a/Documentation/translations/zh_CN/doc-guide/sphinx.rst
+++ b/Documentation/translations/zh_CN/doc-guide/sphinx.rst
@@ -26,7 +26,7 @@ reStructuredText文件å�¯èƒ½åŒ…å�«åŒ…å�«æ�¥è‡ªæº�文件的结构化文档注释æ
 安装Sphinx
 ==========
 
-Documentation/ 下的ReST文件现在使用sphinx1.3或更高版本构建。
+Documentation/ 下的ReST文件现在使用sphinx1.7或更高版本构建。
 
 这有一个脚本�以检查Sphinx的�赖项。更多详细信��
 :ref:`sphinx-pre-install_zh` 。
@@ -40,22 +40,19 @@ Documentation/ 下的ReST文件现在使用sphinx1.3或更高版本构建。
 
 .. note::
 
-   #) 低于1.5版本的Sphinx无法与Python的0.13.1或更高版本docutils一起正常工作。
-      如果您想使用这些版本，那么应该�行 ``pip install 'docutils==0.12'`` 。
-
    #) html输出建议使用RTD主题。根�Sphinx版本的��，它应该用
       ``pip install sphinx_rtd_theme`` �独安装。
 
    #) 一些ReST页�包�数学表达�。由于Sphinx的工作方�，这些表达�是使用 LaTeX
       编写的。它需�安装amsfonts和amsmath�包，以便显示。
 
-总之，如您�安装Sphinx 1.7.9版本，应执行::
+总之，如您�安装Sphinx 2.4.4版本，应执行::
 
-       $ virtualenv sphinx_1.7.9
-       $ . sphinx_1.7.9/bin/activate
-       (sphinx_1.7.9) $ pip install -r Documentation/sphinx/requirements.txt
+       $ virtualenv sphinx_2.4.4
+       $ . sphinx_2.4.4/bin/activate
+       (sphinx_2.4.4) $ pip install -r Documentation/sphinx/requirements.txt
 
-在�行 ``. sphinx_1.7.9/bin/activate`` 之�，�示符将�化，以指示您正在使用新
+在�行 ``. sphinx_2.4.4/bin/activate`` 之�，�示符将�化，以指示您正在使用新
 环境。如果您打开了一个新的shell，那么在构建文档之�，您需��新�行此命令以�
 次进入虚拟环境中。
 
@@ -71,7 +68,7 @@ Documentation/ 下的ReST文件现在使用sphinx1.3或更高版本构建。
 PDF和LaTeX构建
 --------------
 
-目��有Sphinx 1.4�更高版本�支�这�构建。
+目��有Sphinx 2.4�更高版本�支�这�构建。
 
 对于PDF和LaTeX输出，还需� ``XeLaTeX`` 3.14159265版本。（译注：此版本�真实
 存在）
@@ -93,8 +90,8 @@ PDF和LaTeX构建
 	You should run:
 
 		sudo dnf install -y texlive-luatex85
-		/usr/bin/virtualenv sphinx_1.7.9
-		. sphinx_1.7.9/bin/activate
+		/usr/bin/virtualenv sphinx_2.4.4
+		. sphinx_2.4.4/bin/activate
 		pip install -r Documentation/sphinx/requirements.txt
 
 	Can't build as 1 mandatory dependency is missing at ./scripts/sphinx-pre-install line 468.
diff --git a/Documentation/translations/zh_CN/process/management-style.rst b/Documentation/translations/zh_CN/process/management-style.rst
index c6a5bb285797..8053ae474328 100644
--- a/Documentation/translations/zh_CN/process/management-style.rst
+++ b/Documentation/translations/zh_CN/process/management-style.rst
@@ -36,14 +36,14 @@ Linux内核管�风格
 �个人都认为管�者�决定，而且决策很��。决定越大越痛苦，管�者就必须越高级。
 这很明显，但事实并�如此。
 
-游�的�字是 **��** �出决定。尤其是，如果有人告诉你“选择（a）或（b），
+最��的是 **��** �出决定。尤其是，如果有人告诉你“选择（a）或（b），
 我们真的需�你��决定�，你就是陷入麻烦的管�者。你管�的人比你更了解细节，
 所以如果他们�找你�技术决策，你完蛋了。你显然没有能力为他们�这个决定。
 
 （推论：如果你管�的人�比你更了解细节，你也会被�砸，尽管原因完全��。
 也就是说，你的工作是错的，他们应该管�你的�智）
 
-所以游�的�字是 **��** �出决定，至少是那些大而痛苦的决定。�一些�的
+所以最��的是 **��** �出决定，至少是那些大而痛苦的决定。�一些�的
 和�结果性的决定是很好的，并且使您看起�好�知�自己在�什么，所以内核管�者
 需��的是将那些大的和痛苦的决定��那些没有人真正关心的�事情。
 
diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 3b093d6dbe22..aeeb071c7688 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -6911,6 +6911,20 @@ MAP_SHARED mmap will result in an -EINVAL return.
 When enabled the VMM may make use of the ``KVM_ARM_MTE_COPY_TAGS`` ioctl to
 perform a bulk copy of tags to/from the guest.
 
+7.29 KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM
+-------------------------------------
+
+Architectures: x86 SEV enabled
+Type: vm
+Parameters: args[0] is the fd of the source vm
+Returns: 0 on success
+
+This capability enables userspace to migrate the encryption context from the VM
+indicated by the fd to the VM this is called on.
+
+This is intended to support intra-host migration of VMs between userspace VMMs,
+upgrading the VMM process without interrupting the guest.
+
 8. Other capabilities.
 ======================
 
diff --git a/Documentation/x86/xstate.rst b/Documentation/x86/xstate.rst
index 65de3f054ba5..5cec7fb558d6 100644
--- a/Documentation/x86/xstate.rst
+++ b/Documentation/x86/xstate.rst
@@ -63,3 +63,12 @@ kernel sends SIGILL to the application. If the process has permission then
 the handler allocates a larger xstate buffer for the task so the large
 state can be context switched. In the unlikely cases that the allocation
 fails, the kernel sends SIGSEGV.
+
+Dynamic features in signal frames
+---------------------------------
+
+Dynamcally enabled features are not written to the signal frame upon signal
+entry if the feature is in its initial configuration.  This differs from
+non-dynamic features which are always written regardless of their
+configuration.  Signal handlers can examine the XSAVE buffer's XSTATE_BV
+field to determine if a features was written.
diff --git a/MAINTAINERS b/MAINTAINERS
index 4c74516e4353..fb18ce7168aa 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2263,6 +2263,15 @@ L:	linux-iio@vger.kernel.org
 S:	Maintained
 F:	drivers/counter/microchip-tcb-capture.c
 
+ARM/MILBEAUT ARCHITECTURE
+M:	Taichi Sugaya <sugaya.taichi@socionext.com>
+M:	Takao Orito <orito.takao@socionext.com>
+L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+S:	Maintained
+F:	arch/arm/boot/dts/milbeaut*
+F:	arch/arm/mach-milbeaut/
+N:	milbeaut
+
 ARM/MIOA701 MACHINE SUPPORT
 M:	Robert Jarzmik <robert.jarzmik@free.fr>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
@@ -2729,10 +2738,11 @@ S:	Maintained
 F:	drivers/memory/*emif*
 
 ARM/TEXAS INSTRUMENT KEYSTONE ARCHITECTURE
+M:	Nishanth Menon <nm@ti.com>
 M:	Santosh Shilimkar <ssantosh@kernel.org>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/ssantosh/linux-keystone.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/ti/linux.git
 F:	arch/arm/boot/dts/keystone-*
 F:	arch/arm/mach-keystone/
 
@@ -3056,7 +3066,7 @@ F:	Documentation/devicetree/bindings/phy/phy-ath79-usb.txt
 F:	drivers/phy/qualcomm/phy-ath79-usb.c
 
 ATHEROS ATH GENERIC UTILITIES
-M:	Kalle Valo <kvalo@codeaurora.org>
+M:	Kalle Valo <kvalo@kernel.org>
 L:	linux-wireless@vger.kernel.org
 S:	Supported
 F:	drivers/net/wireless/ath/*
@@ -3071,7 +3081,7 @@ W:	https://wireless.wiki.kernel.org/en/users/Drivers/ath5k
 F:	drivers/net/wireless/ath/ath5k/
 
 ATHEROS ATH6KL WIRELESS DRIVER
-M:	Kalle Valo <kvalo@codeaurora.org>
+M:	Kalle Valo <kvalo@kernel.org>
 L:	linux-wireless@vger.kernel.org
 S:	Supported
 W:	https://wireless.wiki.kernel.org/en/users/Drivers/ath6kl
@@ -3570,13 +3580,14 @@ L:	netdev@vger.kernel.org
 S:	Supported
 F:	drivers/net/ethernet/broadcom/b44.*
 
-BROADCOM B53 ETHERNET SWITCH DRIVER
+BROADCOM B53/SF2 ETHERNET SWITCH DRIVER
 M:	Florian Fainelli <f.fainelli@gmail.com>
 L:	netdev@vger.kernel.org
 L:	openwrt-devel@lists.openwrt.org (subscribers-only)
 S:	Supported
 F:	Documentation/devicetree/bindings/net/dsa/brcm,b53.yaml
 F:	drivers/net/dsa/b53/*
+F:	drivers/net/dsa/bcm_sf2*
 F:	include/linux/dsa/brcm.h
 F:	include/linux/platform_data/b53.h
 
@@ -3733,7 +3744,7 @@ F:	drivers/scsi/bnx2i/
 BROADCOM BNX2X 10 GIGABIT ETHERNET DRIVER
 M:	Ariel Elior <aelior@marvell.com>
 M:	Sudarsana Kalluru <skalluru@marvell.com>
-M:	GR-everest-linux-l2@marvell.com
+M:	Manish Chopra <manishc@marvell.com>
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	drivers/net/ethernet/broadcom/bnx2x/
@@ -4676,11 +4687,10 @@ COCCINELLE/Semantic Patches (SmPL)
 M:	Julia Lawall <Julia.Lawall@inria.fr>
 M:	Gilles Muller <Gilles.Muller@inria.fr>
 M:	Nicolas Palix <nicolas.palix@imag.fr>
-M:	Michal Marek <michal.lkml@markovi.net>
-L:	cocci@systeme.lip6.fr (moderated for non-subscribers)
+L:	cocci@inria.fr (moderated for non-subscribers)
 S:	Supported
-W:	http://coccinelle.lip6.fr/
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mmarek/kbuild.git misc
+W:	https://coccinelle.gitlabpages.inria.fr/website/
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jlawall/linux.git
 F:	Documentation/dev-tools/coccinelle.rst
 F:	scripts/coccicheck
 F:	scripts/coccinelle/
@@ -9319,7 +9329,6 @@ S:	Maintained
 F:	drivers/iio/pressure/dps310.c
 
 INFINIBAND SUBSYSTEM
-M:	Doug Ledford <dledford@redhat.com>
 M:	Jason Gunthorpe <jgg@nvidia.com>
 L:	linux-rdma@vger.kernel.org
 S:	Supported
@@ -10270,9 +10279,9 @@ F:	lib/Kconfig.kcsan
 F:	scripts/Makefile.kcsan
 
 KDUMP
-M:	Dave Young <dyoung@redhat.com>
 M:	Baoquan He <bhe@redhat.com>
 R:	Vivek Goyal <vgoyal@redhat.com>
+R:	Dave Young <dyoung@redhat.com>
 L:	kexec@lists.infradead.org
 S:	Maintained
 W:	http://lse.sourceforge.net/kdump/
@@ -10446,7 +10455,7 @@ F:	arch/riscv/include/uapi/asm/kvm*
 F:	arch/riscv/kvm/
 
 KERNEL VIRTUAL MACHINE for s390 (KVM/s390)
-M:	Christian Borntraeger <borntraeger@de.ibm.com>
+M:	Christian Borntraeger <borntraeger@linux.ibm.com>
 M:	Janosch Frank <frankja@linux.ibm.com>
 R:	David Hildenbrand <david@redhat.com>
 R:	Claudio Imbrenda <imbrenda@linux.ibm.com>
@@ -12170,8 +12179,8 @@ F:	drivers/net/ethernet/mellanox/mlx5/core/fpga/*
 F:	include/linux/mlx5/mlx5_ifc_fpga.h
 
 MELLANOX ETHERNET SWITCH DRIVERS
-M:	Jiri Pirko <jiri@nvidia.com>
 M:	Ido Schimmel <idosch@nvidia.com>
+M:	Petr Machata <petrm@nvidia.com>
 L:	netdev@vger.kernel.org
 S:	Supported
 W:	http://www.mellanox.com
@@ -13239,7 +13248,7 @@ F:	include/uapi/linux/if_*
 F:	include/uapi/linux/netdevice.h
 
 NETWORKING DRIVERS (WIRELESS)
-M:	Kalle Valo <kvalo@codeaurora.org>
+M:	Kalle Valo <kvalo@kernel.org>
 L:	linux-wireless@vger.kernel.org
 S:	Maintained
 Q:	http://patchwork.kernel.org/project/linux-wireless/list/
@@ -14413,7 +14422,9 @@ M:	Juergen Gross <jgross@suse.com>
 M:	Deep Shah <sdeep@vmware.com>
 M:	"VMware, Inc." <pv-drivers@vmware.com>
 L:	virtualization@lists.linux-foundation.org
+L:	x86@kernel.org
 S:	Supported
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/core
 F:	Documentation/virt/paravirt_ops.rst
 F:	arch/*/include/asm/paravirt*.h
 F:	arch/*/kernel/paravirt*
@@ -14834,7 +14845,7 @@ PCIE DRIVER FOR MEDIATEK
 M:	Ryder Lee <ryder.lee@mediatek.com>
 M:	Jianjun Wang <jianjun.wang@mediatek.com>
 L:	linux-pci@vger.kernel.org
-L:	linux-mediatek@lists.infradead.org
+L:	linux-mediatek@lists.infradead.org (moderated for non-subscribers)
 S:	Supported
 F:	Documentation/devicetree/bindings/pci/mediatek*
 F:	drivers/pci/controller/*mediatek*
@@ -15592,7 +15603,7 @@ F:	drivers/scsi/qedi/
 
 QLOGIC QL4xxx ETHERNET DRIVER
 M:	Ariel Elior <aelior@marvell.com>
-M:	GR-everest-linux-l2@marvell.com
+M:	Manish Chopra <manishc@marvell.com>
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	drivers/net/ethernet/qlogic/qed/
@@ -15693,7 +15704,7 @@ T:	git git://linuxtv.org/anttip/media_tree.git
 F:	drivers/media/tuners/qt1010*
 
 QUALCOMM ATHEROS ATH10K WIRELESS DRIVER
-M:	Kalle Valo <kvalo@codeaurora.org>
+M:	Kalle Valo <kvalo@kernel.org>
 L:	ath10k@lists.infradead.org
 S:	Supported
 W:	https://wireless.wiki.kernel.org/en/users/Drivers/ath10k
@@ -15701,7 +15712,7 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/ath.git
 F:	drivers/net/wireless/ath/ath10k/
 
 QUALCOMM ATHEROS ATH11K WIRELESS DRIVER
-M:	Kalle Valo <kvalo@codeaurora.org>
+M:	Kalle Valo <kvalo@kernel.org>
 L:	ath11k@lists.infradead.org
 S:	Supported
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/ath.git
@@ -15759,6 +15770,15 @@ S:	Maintained
 F:	Documentation/devicetree/bindings/net/qcom,ethqos.txt
 F:	drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
 
+QUALCOMM FASTRPC DRIVER
+M:	Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
+M:	Amol Maheshwari <amahesh@qti.qualcomm.com>
+L:	linux-arm-msm@vger.kernel.org
+S:	Maintained
+F:	Documentation/devicetree/bindings/misc/qcom,fastrpc.txt
+F:	drivers/misc/fastrpc.c
+F:	include/uapi/misc/fastrpc.h
+
 QUALCOMM GENERIC INTERFACE I2C DRIVER
 M:	Akash Asthana <akashast@codeaurora.org>
 M:	Mukesh Savaliya <msavaliy@codeaurora.org>
@@ -15865,7 +15885,7 @@ F:	Documentation/devicetree/bindings/media/*venus*
 F:	drivers/media/platform/qcom/venus/
 
 QUALCOMM WCN36XX WIRELESS DRIVER
-M:	Kalle Valo <kvalo@codeaurora.org>
+M:	Kalle Valo <kvalo@kernel.org>
 L:	wcn36xx@lists.infradead.org
 S:	Supported
 W:	https://wireless.wiki.kernel.org/en/users/Drivers/wcn36xx
@@ -15967,6 +15987,7 @@ F:	arch/mips/generic/board-ranchu.c
 
 RANDOM NUMBER DRIVER
 M:	"Theodore Ts'o" <tytso@mit.edu>
+M:	Jason A. Donenfeld <Jason@zx2c4.com>
 S:	Maintained
 F:	drivers/char/random.c
 
@@ -16489,6 +16510,12 @@ T:	git git://linuxtv.org/media_tree.git
 F:	Documentation/devicetree/bindings/media/allwinner,sun8i-a83t-de2-rotate.yaml
 F:	drivers/media/platform/sunxi/sun8i-rotate/
 
+RPMSG TTY DRIVER
+M:	Arnaud Pouliquen <arnaud.pouliquen@foss.st.com>
+L:	linux-remoteproc@vger.kernel.org
+S:	Maintained
+F:	drivers/tty/rpmsg_tty.c
+
 RTL2830 MEDIA DRIVER
 M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
@@ -16572,7 +16599,7 @@ F:	drivers/video/fbdev/savage/
 S390
 M:	Heiko Carstens <hca@linux.ibm.com>
 M:	Vasily Gorbik <gor@linux.ibm.com>
-M:	Christian Borntraeger <borntraeger@de.ibm.com>
+M:	Christian Borntraeger <borntraeger@linux.ibm.com>
 R:	Alexander Gordeev <agordeev@linux.ibm.com>
 L:	linux-s390@vger.kernel.org
 S:	Supported
@@ -16610,8 +16637,8 @@ W:	http://www.ibm.com/developerworks/linux/linux390/
 F:	drivers/iommu/s390-iommu.c
 
 S390 IUCV NETWORK LAYER
-M:	Julian Wiedmann <jwi@linux.ibm.com>
-M:	Karsten Graul <kgraul@linux.ibm.com>
+M:	Alexandra Winter <wintera@linux.ibm.com>
+M:	Wenjia Zhang <wenjia@linux.ibm.com>
 L:	linux-s390@vger.kernel.org
 L:	netdev@vger.kernel.org
 S:	Supported
@@ -16621,8 +16648,8 @@ F:	include/net/iucv/
 F:	net/iucv/
 
 S390 NETWORK DRIVERS
-M:	Julian Wiedmann <jwi@linux.ibm.com>
-M:	Karsten Graul <kgraul@linux.ibm.com>
+M:	Alexandra Winter <wintera@linux.ibm.com>
+M:	Wenjia Zhang <wenjia@linux.ibm.com>
 L:	linux-s390@vger.kernel.org
 L:	netdev@vger.kernel.org
 S:	Supported
@@ -17396,7 +17423,7 @@ F:	drivers/video/fbdev/sm712*
 SILVACO I3C DUAL-ROLE MASTER
 M:	Miquel Raynal <miquel.raynal@bootlin.com>
 M:	Conor Culhane <conor.culhane@silvaco.com>
-L:	linux-i3c@lists.infradead.org
+L:	linux-i3c@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 F:	Documentation/devicetree/bindings/i3c/silvaco,i3c-master.yaml
 F:	drivers/i3c/master/svc-i3c-master.c
@@ -18482,6 +18509,7 @@ F:	include/uapi/linux/pkt_sched.h
 F:	include/uapi/linux/tc_act/
 F:	include/uapi/linux/tc_ematch/
 F:	net/sched/
+F:	tools/testing/selftests/tc-testing
 
 TC90522 MEDIA DRIVER
 M:	Akihiro Tsukada <tskd08@gmail.com>
@@ -19030,11 +19058,12 @@ F:	drivers/mmc/host/tifm_sd.c
 F:	include/linux/tifm.h
 
 TI KEYSTONE MULTICORE NAVIGATOR DRIVERS
+M:	Nishanth Menon <nm@ti.com>
 M:	Santosh Shilimkar <ssantosh@kernel.org>
 L:	linux-kernel@vger.kernel.org
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/ssantosh/linux-keystone.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/ti/linux.git
 F:	drivers/soc/ti/*
 
 TI LM49xxx FAMILY ASoC CODEC DRIVERS
@@ -20316,7 +20345,8 @@ F:	arch/x86/include/asm/vmware.h
 F:	arch/x86/kernel/cpu/vmware.c
 
 VMWARE PVRDMA DRIVER
-M:	Adit Ranadive <aditr@vmware.com>
+M:	Bryan Tan <bryantan@vmware.com>
+M:	Vishnu Dasa <vdasa@vmware.com>
 M:	VMware PV-Drivers <pv-drivers@vmware.com>
 L:	linux-rdma@vger.kernel.org
 S:	Maintained
@@ -21029,7 +21059,7 @@ S:	Maintained
 F:	arch/x86/kernel/cpu/zhaoxin.c
 
 ZONEFS FILESYSTEM
-M:	Damien Le Moal <damien.lemoal@wdc.com>
+M:	Damien Le Moal <damien.lemoal@opensource.wdc.com>
 M:	Naohiro Aota <naohiro.aota@wdc.com>
 R:	Johannes Thumshirn <jth@kernel.org>
 L:	linux-fsdevel@vger.kernel.org
@@ -21079,6 +21109,18 @@ F:	Documentation/vm/zsmalloc.rst
 F:	include/linux/zsmalloc.h
 F:	mm/zsmalloc.c
 
+ZSTD
+M:	Nick Terrell <terrelln@fb.com>
+S:	Maintained
+B:	https://github.com/facebook/zstd/issues
+T:	git git://github.com/terrelln/linux.git
+F:	include/linux/zstd*
+F:	lib/zstd/
+F:	lib/decompress_unzstd.c
+F:	crypto/zstd.c
+N:	zstd
+K:	zstd
+
 ZSWAP COMPRESSED SWAP CACHING
 M:	Seth Jennings <sjenning@redhat.com>
 M:	Dan Streetman <ddstreet@ieee.org>
diff --git a/Makefile b/Makefile
index d83d72c26aaa..17b4319ad2ff 100644
--- a/Makefile
+++ b/Makefile
@@ -1,9 +1,9 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 5
-PATCHLEVEL = 15
+PATCHLEVEL = 16
 SUBLEVEL = 0
-EXTRAVERSION =
-NAME = Trick or Treat
+EXTRAVERSION = -rc7
+NAME = Gobble Gobble
 
 # *DOCUMENTATION*
 # To see a list of typical targets execute "make help"
@@ -789,7 +789,7 @@ stackp-flags-$(CONFIG_STACKPROTECTOR_STRONG)      := -fstack-protector-strong
 KBUILD_CFLAGS += $(stackp-flags-y)
 
 KBUILD_CFLAGS-$(CONFIG_WERROR) += -Werror
-KBUILD_CFLAGS += $(KBUILD_CFLAGS-y)
+KBUILD_CFLAGS += $(KBUILD_CFLAGS-y) $(CONFIG_CC_IMPLICIT_FALLTHROUGH:"%"=%)
 
 ifdef CONFIG_CC_IS_CLANG
 KBUILD_CPPFLAGS += -Qunused-arguments
@@ -801,10 +801,6 @@ KBUILD_CFLAGS += -Wno-gnu
 KBUILD_CFLAGS += -mno-global-merge
 else
 
-# Warn about unmarked fall-throughs in switch statement.
-# Disabled for clang while comment to attribute conversion happens and
-# https://github.com/ClangBuiltLinux/linux/issues/636 is discussed.
-KBUILD_CFLAGS += $(call cc-option,-Wimplicit-fallthrough=5,)
 # gcc inanely warns about local variables called 'main'
 KBUILD_CFLAGS += -Wno-main
 endif
@@ -1378,17 +1374,17 @@ endif
 
 ifneq ($(dtstree),)
 
-%.dtb: dt_binding_check include/config/kernel.release scripts_dtc
-	$(Q)$(MAKE) $(build)=$(dtstree) $(dtstree)/$@ $(dtstree)/$*.dt.yaml
+%.dtb: include/config/kernel.release scripts_dtc
+	$(Q)$(MAKE) $(build)=$(dtstree) $(dtstree)/$@
 
-%.dtbo: dt_binding_check include/config/kernel.release scripts_dtc
-	$(Q)$(MAKE) $(build)=$(dtstree) $(dtstree)/$@ $(dtstree)/$*.dt.yaml
+%.dtbo: include/config/kernel.release scripts_dtc
+	$(Q)$(MAKE) $(build)=$(dtstree) $(dtstree)/$@
 
 PHONY += dtbs dtbs_install dtbs_check
 dtbs: include/config/kernel.release scripts_dtc
 	$(Q)$(MAKE) $(build)=$(dtstree)
 
-ifneq ($(filter dtbs_check %.dtb %.dtbo, $(MAKECMDGOALS)),)
+ifneq ($(filter dtbs_check, $(MAKECMDGOALS)),)
 export CHECK_DTBS=y
 dtbs: dt_binding_check
 endif
diff --git a/arch/Kconfig b/arch/Kconfig
index 26b8ed11639d..d3c4ab249e9c 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -991,6 +991,16 @@ config HAVE_ARCH_COMPAT_MMAP_BASES
 	  and vice-versa 32-bit applications to call 64-bit mmap().
 	  Required for applications doing different bitness syscalls.
 
+config PAGE_SIZE_LESS_THAN_64KB
+	def_bool y
+	depends on !ARM64_64K_PAGES
+	depends on !IA64_PAGE_SIZE_64KB
+	depends on !PAGE_SIZE_64KB
+	depends on !PARISC_PAGE_SIZE_64KB
+	depends on !PPC_64K_PAGES
+	depends on !PPC_256K_PAGES
+	depends on !PAGE_SIZE_256KB
+
 # This allows to use a set of generic functions to determine mmap base
 # address by giving priority to top-down scheme only if the process
 # is not in legacy mode (compat task, unlimited stack size or
diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl
index e4a041cd5715..ca5a32228cd6 100644
--- a/arch/alpha/kernel/syscalls/syscall.tbl
+++ b/arch/alpha/kernel/syscalls/syscall.tbl
@@ -488,3 +488,4 @@
 556	common	landlock_restrict_self		sys_landlock_restrict_self
 # 557 reserved for memfd_secret
 558	common	process_mrelease		sys_process_mrelease
+559	common  futex_waitv                     sys_futex_waitv
diff --git a/arch/arc/include/asm/cacheflush.h b/arch/arc/include/asm/cacheflush.h
index e8c2c7469e10..e201b4b1655a 100644
--- a/arch/arc/include/asm/cacheflush.h
+++ b/arch/arc/include/asm/cacheflush.h
@@ -36,7 +36,6 @@ void __flush_dcache_page(phys_addr_t paddr, unsigned long vaddr);
 #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
 
 void flush_dcache_page(struct page *page);
-void flush_dcache_folio(struct folio *folio);
 
 void dma_cache_wback_inv(phys_addr_t start, unsigned long sz);
 void dma_cache_inv(phys_addr_t start, unsigned long sz);
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index f0f9e8bec83a..c2724d986fa0 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1463,6 +1463,7 @@ config HIGHMEM
 	bool "High Memory Support"
 	depends on MMU
 	select KMAP_LOCAL
+	select KMAP_LOCAL_NON_LINEAR_PTE_ARRAY
 	help
 	  The address space of ARM processors is only 4 Gigabytes large
 	  and it has to accommodate user address space, kernel address
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index a522716565c6..77172d555c7e 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -60,15 +60,15 @@ KBUILD_CFLAGS	+= $(call cc-option,-fno-ipa-sra)
 # Note that GCC does not numerically define an architecture version
 # macro, but instead defines a whole series of macros which makes
 # testing for a specific architecture or later rather impossible.
-arch-$(CONFIG_CPU_32v7M)	=-D__LINUX_ARM_ARCH__=7 -march=armv7-m -Wa,-march=armv7-m
-arch-$(CONFIG_CPU_32v7)		=-D__LINUX_ARM_ARCH__=7 $(call cc-option,-march=armv7-a,-march=armv5t -Wa$(comma)-march=armv7-a)
-arch-$(CONFIG_CPU_32v6)		=-D__LINUX_ARM_ARCH__=6 $(call cc-option,-march=armv6,-march=armv5t -Wa$(comma)-march=armv6)
+arch-$(CONFIG_CPU_32v7M)	=-D__LINUX_ARM_ARCH__=7 -march=armv7-m
+arch-$(CONFIG_CPU_32v7)		=-D__LINUX_ARM_ARCH__=7 -march=armv7-a
+arch-$(CONFIG_CPU_32v6)		=-D__LINUX_ARM_ARCH__=6 -march=armv6
 # Only override the compiler option if ARMv6. The ARMv6K extensions are
 # always available in ARMv7
 ifeq ($(CONFIG_CPU_32v6),y)
-arch-$(CONFIG_CPU_32v6K)	=-D__LINUX_ARM_ARCH__=6 $(call cc-option,-march=armv6k,-march=armv5t -Wa$(comma)-march=armv6k)
+arch-$(CONFIG_CPU_32v6K)	=-D__LINUX_ARM_ARCH__=6 -march=armv6k
 endif
-arch-$(CONFIG_CPU_32v5)		=-D__LINUX_ARM_ARCH__=5 $(call cc-option,-march=armv5te,-march=armv4t)
+arch-$(CONFIG_CPU_32v5)		=-D__LINUX_ARM_ARCH__=5 -march=armv5te
 arch-$(CONFIG_CPU_32v4T)	=-D__LINUX_ARM_ARCH__=4 -march=armv4t
 arch-$(CONFIG_CPU_32v4)		=-D__LINUX_ARM_ARCH__=4 -march=armv4
 arch-$(CONFIG_CPU_32v3)		=-D__LINUX_ARM_ARCH__=3 -march=armv3m
@@ -82,7 +82,7 @@ tune-$(CONFIG_CPU_ARM720T)	=-mtune=arm7tdmi
 tune-$(CONFIG_CPU_ARM740T)	=-mtune=arm7tdmi
 tune-$(CONFIG_CPU_ARM9TDMI)	=-mtune=arm9tdmi
 tune-$(CONFIG_CPU_ARM940T)	=-mtune=arm9tdmi
-tune-$(CONFIG_CPU_ARM946E)	=$(call cc-option,-mtune=arm9e,-mtune=arm9tdmi)
+tune-$(CONFIG_CPU_ARM946E)	=-mtune=arm9e
 tune-$(CONFIG_CPU_ARM920T)	=-mtune=arm9tdmi
 tune-$(CONFIG_CPU_ARM922T)	=-mtune=arm9tdmi
 tune-$(CONFIG_CPU_ARM925T)	=-mtune=arm9tdmi
@@ -90,11 +90,11 @@ tune-$(CONFIG_CPU_ARM926T)	=-mtune=arm9tdmi
 tune-$(CONFIG_CPU_FA526)	=-mtune=arm9tdmi
 tune-$(CONFIG_CPU_SA110)	=-mtune=strongarm110
 tune-$(CONFIG_CPU_SA1100)	=-mtune=strongarm1100
-tune-$(CONFIG_CPU_XSCALE)	=$(call cc-option,-mtune=xscale,-mtune=strongarm110) -Wa,-mcpu=xscale
-tune-$(CONFIG_CPU_XSC3)		=$(call cc-option,-mtune=xscale,-mtune=strongarm110) -Wa,-mcpu=xscale
-tune-$(CONFIG_CPU_FEROCEON)	=$(call cc-option,-mtune=marvell-f,-mtune=xscale)
-tune-$(CONFIG_CPU_V6)		=$(call cc-option,-mtune=arm1136j-s,-mtune=strongarm)
-tune-$(CONFIG_CPU_V6K)		=$(call cc-option,-mtune=arm1136j-s,-mtune=strongarm)
+tune-$(CONFIG_CPU_XSCALE)	=-mtune=xscale
+tune-$(CONFIG_CPU_XSC3)		=-mtune=xscale
+tune-$(CONFIG_CPU_FEROCEON)	=-mtune=xscale
+tune-$(CONFIG_CPU_V6)		=-mtune=arm1136j-s
+tune-$(CONFIG_CPU_V6K)		=-mtune=arm1136j-s
 
 # Evaluate tune cc-option calls now
 tune-y := $(tune-y)
diff --git a/arch/arm/boot/dts/bcm2711.dtsi b/arch/arm/boot/dts/bcm2711.dtsi
index 3b60297af7f6..9e01dbca4a01 100644
--- a/arch/arm/boot/dts/bcm2711.dtsi
+++ b/arch/arm/boot/dts/bcm2711.dtsi
@@ -506,11 +506,17 @@
 			#address-cells = <3>;
 			#interrupt-cells = <1>;
 			#size-cells = <2>;
-			interrupts = <GIC_SPI 148 IRQ_TYPE_LEVEL_HIGH>,
+			interrupts = <GIC_SPI 147 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 148 IRQ_TYPE_LEVEL_HIGH>;
 			interrupt-names = "pcie", "msi";
 			interrupt-map-mask = <0x0 0x0 0x0 0x7>;
 			interrupt-map = <0 0 0 1 &gicv2 GIC_SPI 143
+							IRQ_TYPE_LEVEL_HIGH>,
+					<0 0 0 2 &gicv2 GIC_SPI 144
+							IRQ_TYPE_LEVEL_HIGH>,
+					<0 0 0 3 &gicv2 GIC_SPI 145
+							IRQ_TYPE_LEVEL_HIGH>,
+					<0 0 0 4 &gicv2 GIC_SPI 146
 							IRQ_TYPE_LEVEL_HIGH>;
 			msi-controller;
 			msi-parent = <&pcie0>;
diff --git a/arch/arm/boot/dts/bcm5301x.dtsi b/arch/arm/boot/dts/bcm5301x.dtsi
index d4f355015e3c..f69d2af3c1fa 100644
--- a/arch/arm/boot/dts/bcm5301x.dtsi
+++ b/arch/arm/boot/dts/bcm5301x.dtsi
@@ -242,6 +242,8 @@
 
 			gpio-controller;
 			#gpio-cells = <2>;
+			interrupt-controller;
+			#interrupt-cells = <2>;
 		};
 
 		pcie0: pcie@12000 {
@@ -408,7 +410,7 @@
 	i2c0: i2c@18009000 {
 		compatible = "brcm,iproc-i2c";
 		reg = <0x18009000 0x50>;
-		interrupts = <GIC_SPI 121 IRQ_TYPE_LEVEL_HIGH>;
+		interrupts = <GIC_SPI 89 IRQ_TYPE_LEVEL_HIGH>;
 		#address-cells = <1>;
 		#size-cells = <0>;
 		clock-frequency = <100000>;
diff --git a/arch/arm/boot/dts/imx6qdl-wandboard.dtsi b/arch/arm/boot/dts/imx6qdl-wandboard.dtsi
index b62a0dbb033f..ec6fba5ee8fd 100644
--- a/arch/arm/boot/dts/imx6qdl-wandboard.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-wandboard.dtsi
@@ -309,6 +309,7 @@
 
 		ethphy: ethernet-phy@1 {
 			reg = <1>;
+			qca,clk-out-frequency = <125000000>;
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/imx6qp-prtwd3.dts b/arch/arm/boot/dts/imx6qp-prtwd3.dts
index 7648e8a02000..cf6571cc4682 100644
--- a/arch/arm/boot/dts/imx6qp-prtwd3.dts
+++ b/arch/arm/boot/dts/imx6qp-prtwd3.dts
@@ -178,6 +178,8 @@
 				label = "cpu";
 				ethernet = <&fec>;
 				phy-mode = "rgmii-id";
+				rx-internal-delay-ps = <2000>;
+				tx-internal-delay-ps = <2000>;
 
 				fixed-link {
 					speed = <100>;
diff --git a/arch/arm/boot/dts/imx6ull-pinfunc.h b/arch/arm/boot/dts/imx6ull-pinfunc.h
index eb025a9d4759..7328d4ef8559 100644
--- a/arch/arm/boot/dts/imx6ull-pinfunc.h
+++ b/arch/arm/boot/dts/imx6ull-pinfunc.h
@@ -82,6 +82,6 @@
 #define MX6ULL_PAD_CSI_DATA04__ESAI_TX_FS                         0x01F4 0x0480 0x0000 0x9 0x0
 #define MX6ULL_PAD_CSI_DATA05__ESAI_TX_CLK                        0x01F8 0x0484 0x0000 0x9 0x0
 #define MX6ULL_PAD_CSI_DATA06__ESAI_TX5_RX0                       0x01FC 0x0488 0x0000 0x9 0x0
-#define MX6ULL_PAD_CSI_DATA07__ESAI_T0                            0x0200 0x048C 0x0000 0x9 0x0
+#define MX6ULL_PAD_CSI_DATA07__ESAI_TX0                           0x0200 0x048C 0x0000 0x9 0x0
 
 #endif /* __DTS_IMX6ULL_PINFUNC_H */
diff --git a/arch/arm/boot/dts/ls1021a-tsn.dts b/arch/arm/boot/dts/ls1021a-tsn.dts
index ff0ffb22768b..1ea32fff4120 100644
--- a/arch/arm/boot/dts/ls1021a-tsn.dts
+++ b/arch/arm/boot/dts/ls1021a-tsn.dts
@@ -91,6 +91,8 @@
 				/* Internal port connected to eth2 */
 				ethernet = <&enet2>;
 				phy-mode = "rgmii";
+				rx-internal-delay-ps = <0>;
+				tx-internal-delay-ps = <0>;
 				reg = <4>;
 
 				fixed-link {
diff --git a/arch/arm/boot/dts/socfpga_arria10_socdk_qspi.dts b/arch/arm/boot/dts/socfpga_arria10_socdk_qspi.dts
index 2b645642b935..2a745522404d 100644
--- a/arch/arm/boot/dts/socfpga_arria10_socdk_qspi.dts
+++ b/arch/arm/boot/dts/socfpga_arria10_socdk_qspi.dts
@@ -12,7 +12,7 @@
 	flash0: n25q00@0 {
 		#address-cells = <1>;
 		#size-cells = <1>;
-		compatible = "n25q00aa";
+		compatible = "micron,mt25qu02g", "jedec,spi-nor";
 		reg = <0>;
 		spi-max-frequency = <100000000>;
 
diff --git a/arch/arm/boot/dts/socfpga_arria5_socdk.dts b/arch/arm/boot/dts/socfpga_arria5_socdk.dts
index 90e676e7019f..1b02d46496a8 100644
--- a/arch/arm/boot/dts/socfpga_arria5_socdk.dts
+++ b/arch/arm/boot/dts/socfpga_arria5_socdk.dts
@@ -119,7 +119,7 @@
 	flash: flash@0 {
 		#address-cells = <1>;
 		#size-cells = <1>;
-		compatible = "n25q256a";
+		compatible = "micron,n25q256a", "jedec,spi-nor";
 		reg = <0>;
 		spi-max-frequency = <100000000>;
 
diff --git a/arch/arm/boot/dts/socfpga_cyclone5_socdk.dts b/arch/arm/boot/dts/socfpga_cyclone5_socdk.dts
index 6f138b2b2616..51bb436784e2 100644
--- a/arch/arm/boot/dts/socfpga_cyclone5_socdk.dts
+++ b/arch/arm/boot/dts/socfpga_cyclone5_socdk.dts
@@ -124,7 +124,7 @@
 	flash0: n25q00@0 {
 		#address-cells = <1>;
 		#size-cells = <1>;
-		compatible = "n25q00";
+		compatible = "micron,mt25qu02g", "jedec,spi-nor";
 		reg = <0>;	/* chip select */
 		spi-max-frequency = <100000000>;
 
diff --git a/arch/arm/boot/dts/socfpga_cyclone5_sockit.dts b/arch/arm/boot/dts/socfpga_cyclone5_sockit.dts
index c155ff02eb6e..cae9ddd5ed38 100644
--- a/arch/arm/boot/dts/socfpga_cyclone5_sockit.dts
+++ b/arch/arm/boot/dts/socfpga_cyclone5_sockit.dts
@@ -169,7 +169,7 @@
 	flash: flash@0 {
 		#address-cells = <1>;
 		#size-cells = <1>;
-		compatible = "n25q00";
+		compatible = "micron,mt25qu02g", "jedec,spi-nor";
 		reg = <0>;
 		spi-max-frequency = <100000000>;
 
diff --git a/arch/arm/boot/dts/socfpga_cyclone5_socrates.dts b/arch/arm/boot/dts/socfpga_cyclone5_socrates.dts
index 8d5d3996f6f2..ca18b959e655 100644
--- a/arch/arm/boot/dts/socfpga_cyclone5_socrates.dts
+++ b/arch/arm/boot/dts/socfpga_cyclone5_socrates.dts
@@ -80,7 +80,7 @@
 	flash: flash@0 {
 		#address-cells = <1>;
 		#size-cells = <1>;
-		compatible = "n25q256a";
+		compatible = "micron,n25q256a", "jedec,spi-nor";
 		reg = <0>;
 		spi-max-frequency = <100000000>;
 		m25p,fast-read;
diff --git a/arch/arm/boot/dts/socfpga_cyclone5_sodia.dts b/arch/arm/boot/dts/socfpga_cyclone5_sodia.dts
index 99a71757cdf4..3f7aa7bf0863 100644
--- a/arch/arm/boot/dts/socfpga_cyclone5_sodia.dts
+++ b/arch/arm/boot/dts/socfpga_cyclone5_sodia.dts
@@ -116,7 +116,7 @@
 	flash0: n25q512a@0 {
 		#address-cells = <1>;
 		#size-cells = <1>;
-		compatible = "n25q512a";
+		compatible = "micron,n25q512a", "jedec,spi-nor";
 		reg = <0>;
 		spi-max-frequency = <100000000>;
 
diff --git a/arch/arm/boot/dts/socfpga_cyclone5_vining_fpga.dts b/arch/arm/boot/dts/socfpga_cyclone5_vining_fpga.dts
index a060718758b6..25874e1b9c82 100644
--- a/arch/arm/boot/dts/socfpga_cyclone5_vining_fpga.dts
+++ b/arch/arm/boot/dts/socfpga_cyclone5_vining_fpga.dts
@@ -224,7 +224,7 @@
 	n25q128@0 {
 		#address-cells = <1>;
 		#size-cells = <1>;
-		compatible = "n25q128";
+		compatible = "micron,n25q128", "jedec,spi-nor";
 		reg = <0>;		/* chip select */
 		spi-max-frequency = <100000000>;
 		m25p,fast-read;
@@ -241,7 +241,7 @@
 	n25q00@1 {
 		#address-cells = <1>;
 		#size-cells = <1>;
-		compatible = "n25q00";
+		compatible = "micron,mt25qu02g", "jedec,spi-nor";
 		reg = <1>;		/* chip select */
 		spi-max-frequency = <100000000>;
 		m25p,fast-read;
diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h
index e68fb879e4f9..5e56288e343b 100644
--- a/arch/arm/include/asm/cacheflush.h
+++ b/arch/arm/include/asm/cacheflush.h
@@ -290,7 +290,6 @@ extern void flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr
  */
 #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
 extern void flush_dcache_page(struct page *);
-void flush_dcache_folio(struct folio *folio);
 
 #define ARCH_IMPLEMENTS_FLUSH_KERNEL_VMAP_RANGE 1
 static inline void flush_kernel_vmap_range(void *addr, int size)
diff --git a/arch/arm/include/asm/efi.h b/arch/arm/include/asm/efi.h
index a6f3b179e8a9..27218eabbf9a 100644
--- a/arch/arm/include/asm/efi.h
+++ b/arch/arm/include/asm/efi.h
@@ -17,7 +17,6 @@
 
 #ifdef CONFIG_EFI
 void efi_init(void);
-extern void efifb_setup_from_dmi(struct screen_info *si, const char *opt);
 
 int efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md);
 int efi_set_mapping_permissions(struct mm_struct *mm, efi_memory_desc_t *md);
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index deff286eb5ea..5cd057859fe9 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -596,11 +596,9 @@ call_fpe:
 	tstne	r0, #0x04000000			@ bit 26 set on both ARM and Thumb-2
 	reteq	lr
 	and	r8, r0, #0x00000f00		@ mask out CP number
- THUMB(	lsr	r8, r8, #8		)
 	mov	r7, #1
-	add	r6, r10, #TI_USED_CP
- ARM(	strb	r7, [r6, r8, lsr #8]	)	@ set appropriate used_cp[]
- THUMB(	strb	r7, [r6, r8]		)	@ set appropriate used_cp[]
+	add	r6, r10, r8, lsr #8		@ add used_cp[] array offset first
+	strb	r7, [r6, #TI_USED_CP]		@ set appropriate used_cp[]
 #ifdef CONFIG_IWMMXT
 	@ Test if we need to give access to iWMMXt coprocessors
 	ldr	r5, [r10, #TI_FLAGS]
@@ -609,7 +607,7 @@ call_fpe:
 	bcs	iwmmxt_task_enable
 #endif
  ARM(	add	pc, pc, r8, lsr #6	)
- THUMB(	lsl	r8, r8, #2		)
+ THUMB(	lsr	r8, r8, #6		)
  THUMB(	add	pc, r8			)
 	nop
 
diff --git a/arch/arm/kernel/head-nommu.S b/arch/arm/kernel/head-nommu.S
index fadfee9e2b45..950bef83339f 100644
--- a/arch/arm/kernel/head-nommu.S
+++ b/arch/arm/kernel/head-nommu.S
@@ -114,6 +114,7 @@ ENTRY(secondary_startup)
 	add	r12, r12, r10
 	ret	r12
 1:	bl	__after_proc_init
+	ldr	r7, __secondary_data		@ reload r7
 	ldr	sp, [r7, #12]			@ set up the stack pointer
 	ldr	r0, [r7, #16]			@ set up task pointer
 	mov	fp, #0
diff --git a/arch/arm/mach-rockchip/platsmp.c b/arch/arm/mach-rockchip/platsmp.c
index d60856898d97..5ec58d004b7d 100644
--- a/arch/arm/mach-rockchip/platsmp.c
+++ b/arch/arm/mach-rockchip/platsmp.c
@@ -189,7 +189,7 @@ static int __init rockchip_smp_prepare_sram(struct device_node *node)
 	rockchip_boot_fn = __pa_symbol(secondary_startup);
 
 	/* copy the trampoline to sram, that runs during startup of the core */
-	memcpy(sram_base_addr, &rockchip_secondary_trampoline, trampoline_sz);
+	memcpy_toio(sram_base_addr, &rockchip_secondary_trampoline, trampoline_sz);
 	flush_cache_all();
 	outer_clean_range(0, trampoline_sz);
 
diff --git a/arch/arm/mach-socfpga/core.h b/arch/arm/mach-socfpga/core.h
index fc2608b18a0d..18f01190dcfd 100644
--- a/arch/arm/mach-socfpga/core.h
+++ b/arch/arm/mach-socfpga/core.h
@@ -33,7 +33,7 @@ extern void __iomem *sdr_ctl_base_addr;
 u32 socfpga_sdram_self_refresh(u32 sdr_base);
 extern unsigned int socfpga_sdram_self_refresh_sz;
 
-extern char secondary_trampoline, secondary_trampoline_end;
+extern char secondary_trampoline[], secondary_trampoline_end[];
 
 extern unsigned long socfpga_cpu1start_addr;
 
diff --git a/arch/arm/mach-socfpga/platsmp.c b/arch/arm/mach-socfpga/platsmp.c
index fbb80b883e5d..201191cf68f3 100644
--- a/arch/arm/mach-socfpga/platsmp.c
+++ b/arch/arm/mach-socfpga/platsmp.c
@@ -20,14 +20,14 @@
 
 static int socfpga_boot_secondary(unsigned int cpu, struct task_struct *idle)
 {
-	int trampoline_size = &secondary_trampoline_end - &secondary_trampoline;
+	int trampoline_size = secondary_trampoline_end - secondary_trampoline;
 
 	if (socfpga_cpu1start_addr) {
 		/* This will put CPU #1 into reset. */
 		writel(RSTMGR_MPUMODRST_CPU1,
 		       rst_manager_base_addr + SOCFPGA_RSTMGR_MODMPURST);
 
-		memcpy(phys_to_virt(0), &secondary_trampoline, trampoline_size);
+		memcpy(phys_to_virt(0), secondary_trampoline, trampoline_size);
 
 		writel(__pa_symbol(secondary_startup),
 		       sys_manager_base_addr + (socfpga_cpu1start_addr & 0x000000ff));
@@ -45,12 +45,12 @@ static int socfpga_boot_secondary(unsigned int cpu, struct task_struct *idle)
 
 static int socfpga_a10_boot_secondary(unsigned int cpu, struct task_struct *idle)
 {
-	int trampoline_size = &secondary_trampoline_end - &secondary_trampoline;
+	int trampoline_size = secondary_trampoline_end - secondary_trampoline;
 
 	if (socfpga_cpu1start_addr) {
 		writel(RSTMGR_MPUMODRST_CPU1, rst_manager_base_addr +
 		       SOCFPGA_A10_RSTMGR_MODMPURST);
-		memcpy(phys_to_virt(0), &secondary_trampoline, trampoline_size);
+		memcpy(phys_to_virt(0), secondary_trampoline, trampoline_size);
 
 		writel(__pa_symbol(secondary_startup),
 		       sys_manager_base_addr + (socfpga_cpu1start_addr & 0x00000fff));
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index a4e006005107..274e4f73fd33 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -390,9 +390,9 @@ void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t prot)
 	BUILD_BUG_ON(__fix_to_virt(__end_of_fixed_addresses) < FIXADDR_START);
 	BUG_ON(idx >= __end_of_fixed_addresses);
 
-	/* we only support device mappings until pgprot_kernel has been set */
+	/* We support only device mappings before pgprot_kernel is set. */
 	if (WARN_ON(pgprot_val(prot) != pgprot_val(FIXMAP_PAGE_IO) &&
-		    pgprot_val(pgprot_kernel) == 0))
+		    pgprot_val(prot) && pgprot_val(pgprot_kernel) == 0))
 		return;
 
 	if (pgprot_val(prot))
diff --git a/arch/arm64/Kconfig.platforms b/arch/arm64/Kconfig.platforms
index 1aa8b7073218..54e3910e8b9b 100644
--- a/arch/arm64/Kconfig.platforms
+++ b/arch/arm64/Kconfig.platforms
@@ -161,7 +161,6 @@ config ARCH_MEDIATEK
 
 config ARCH_MESON
 	bool "Amlogic Platforms"
-	select COMMON_CLK
 	help
 	  This enables support for the arm64 based Amlogic SoCs
 	  such as the s905, S905X/D, S912, A113X/D or S905X/D2
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-zero-plus.dts b/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-zero-plus.dts
index d13980ed7a79..7ec5ac850a0d 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-zero-plus.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-zero-plus.dts
@@ -69,7 +69,7 @@
 	pinctrl-0 = <&emac_rgmii_pins>;
 	phy-supply = <&reg_gmac_3v3>;
 	phy-handle = <&ext_rgmii_phy>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 	status = "okay";
 };
 
diff --git a/arch/arm64/boot/dts/amlogic/meson-axg-jethome-jethub-j100.dts b/arch/arm64/boot/dts/amlogic/meson-axg-jethome-jethub-j100.dts
index 52ebe371df26..561eec21b4de 100644
--- a/arch/arm64/boot/dts/amlogic/meson-axg-jethome-jethub-j100.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-axg-jethome-jethub-j100.dts
@@ -134,23 +134,23 @@
 					type = "critical";
 				};
 			};
-		};
 
-		cpu_cooling_maps: cooling-maps {
-			map0 {
-				trip = <&cpu_passive>;
-				cooling-device = <&cpu0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
-						<&cpu1 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
-						<&cpu2 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
-						<&cpu3 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
-			};
+			cpu_cooling_maps: cooling-maps {
+				map0 {
+					trip = <&cpu_passive>;
+					cooling-device = <&cpu0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+							<&cpu1 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+							<&cpu2 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+							<&cpu3 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+				};
 
-			map1 {
-				trip = <&cpu_hot>;
-				cooling-device = <&cpu0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
-						<&cpu1 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
-						<&cpu2 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
-						<&cpu3 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+				map1 {
+					trip = <&cpu_hot>;
+					cooling-device = <&cpu0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+							<&cpu1 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+							<&cpu2 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+							<&cpu3 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+				};
 			};
 		};
 	};
diff --git a/arch/arm64/boot/dts/apple/t8103-j274.dts b/arch/arm64/boot/dts/apple/t8103-j274.dts
index 33a80f9501dc..02c36301e985 100644
--- a/arch/arm64/boot/dts/apple/t8103-j274.dts
+++ b/arch/arm64/boot/dts/apple/t8103-j274.dts
@@ -60,7 +60,7 @@
 
 &port02 {
 	bus-range = <3 3>;
-	ethernet0: pci@0,0 {
+	ethernet0: ethernet@0,0 {
 		reg = <0x30000 0x0 0x0 0x0 0x0>;
 		/* To be filled by the loader */
 		local-mac-address = [00 10 18 00 00 00];
diff --git a/arch/arm64/boot/dts/apple/t8103.dtsi b/arch/arm64/boot/dts/apple/t8103.dtsi
index fc8b2bb06ffe..8b61e7fd3e9c 100644
--- a/arch/arm64/boot/dts/apple/t8103.dtsi
+++ b/arch/arm64/boot/dts/apple/t8103.dtsi
@@ -7,6 +7,7 @@
  * Copyright The Asahi Linux Contributors
  */
 
+#include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/interrupt-controller/apple-aic.h>
 #include <dt-bindings/interrupt-controller/irq.h>
 #include <dt-bindings/pinctrl/apple.h>
@@ -143,6 +144,7 @@
 			apple,npins = <212>;
 
 			interrupt-controller;
+			#interrupt-cells = <2>;
 			interrupt-parent = <&aic>;
 			interrupts = <AIC_IRQ 190 IRQ_TYPE_LEVEL_HIGH>,
 				     <AIC_IRQ 191 IRQ_TYPE_LEVEL_HIGH>,
@@ -169,6 +171,7 @@
 			apple,npins = <42>;
 
 			interrupt-controller;
+			#interrupt-cells = <2>;
 			interrupt-parent = <&aic>;
 			interrupts = <AIC_IRQ 268 IRQ_TYPE_LEVEL_HIGH>,
 				     <AIC_IRQ 269 IRQ_TYPE_LEVEL_HIGH>,
@@ -189,6 +192,7 @@
 			apple,npins = <23>;
 
 			interrupt-controller;
+			#interrupt-cells = <2>;
 			interrupt-parent = <&aic>;
 			interrupts = <AIC_IRQ 330 IRQ_TYPE_LEVEL_HIGH>,
 				     <AIC_IRQ 331 IRQ_TYPE_LEVEL_HIGH>,
@@ -209,6 +213,7 @@
 			apple,npins = <16>;
 
 			interrupt-controller;
+			#interrupt-cells = <2>;
 			interrupt-parent = <&aic>;
 			interrupts = <AIC_IRQ 391 IRQ_TYPE_LEVEL_HIGH>,
 				     <AIC_IRQ 392 IRQ_TYPE_LEVEL_HIGH>,
@@ -281,7 +286,7 @@
 			port00: pci@0,0 {
 				device_type = "pci";
 				reg = <0x0 0x0 0x0 0x0 0x0>;
-				reset-gpios = <&pinctrl_ap 152 0>;
+				reset-gpios = <&pinctrl_ap 152 GPIO_ACTIVE_LOW>;
 				max-link-speed = <2>;
 
 				#address-cells = <3>;
@@ -301,7 +306,7 @@
 			port01: pci@1,0 {
 				device_type = "pci";
 				reg = <0x800 0x0 0x0 0x0 0x0>;
-				reset-gpios = <&pinctrl_ap 153 0>;
+				reset-gpios = <&pinctrl_ap 153 GPIO_ACTIVE_LOW>;
 				max-link-speed = <2>;
 
 				#address-cells = <3>;
@@ -321,7 +326,7 @@
 			port02: pci@2,0 {
 				device_type = "pci";
 				reg = <0x1000 0x0 0x0 0x0 0x0>;
-				reset-gpios = <&pinctrl_ap 33 0>;
+				reset-gpios = <&pinctrl_ap 33 GPIO_ACTIVE_LOW>;
 				max-link-speed = <1>;
 
 				#address-cells = <3>;
diff --git a/arch/arm64/boot/dts/exynos/exynosautov9.dtsi b/arch/arm64/boot/dts/exynos/exynosautov9.dtsi
index 3e4727344b4a..a960c0bc2dba 100644
--- a/arch/arm64/boot/dts/exynos/exynosautov9.dtsi
+++ b/arch/arm64/boot/dts/exynos/exynosautov9.dtsi
@@ -296,8 +296,7 @@
 			pinctrl-0 = <&ufs_rst_n &ufs_refclk_out>;
 			phys = <&ufs_0_phy>;
 			phy-names = "ufs-phy";
-			samsung,sysreg = <&syscon_fsys2>;
-			samsung,ufs-shareability-reg-offset = <0x710>;
+			samsung,sysreg = <&syscon_fsys2 0x710>;
 			status = "disabled";
 		};
 	};
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1088a-ten64.dts b/arch/arm64/boot/dts/freescale/fsl-ls1088a-ten64.dts
index 3063851c2fb9..d3f03dcbb8c3 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1088a-ten64.dts
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1088a-ten64.dts
@@ -38,7 +38,6 @@
 		powerdn {
 			label = "External Power Down";
 			gpios = <&gpio1 17 GPIO_ACTIVE_LOW>;
-			interrupts = <&gpio1 17 IRQ_TYPE_EDGE_FALLING>;
 			linux,code = <KEY_POWER>;
 		};
 
@@ -46,7 +45,6 @@
 		admin {
 			label = "ADMIN button";
 			gpios = <&gpio3 8 GPIO_ACTIVE_HIGH>;
-			interrupts = <&gpio3 8 IRQ_TYPE_EDGE_RISING>;
 			linux,code = <KEY_WPS_BUTTON>;
 		};
 	};
diff --git a/arch/arm64/boot/dts/freescale/fsl-lx2160a-bluebox3.dts b/arch/arm64/boot/dts/freescale/fsl-lx2160a-bluebox3.dts
index b21be03da0af..042c486bdda2 100644
--- a/arch/arm64/boot/dts/freescale/fsl-lx2160a-bluebox3.dts
+++ b/arch/arm64/boot/dts/freescale/fsl-lx2160a-bluebox3.dts
@@ -386,6 +386,8 @@
 				reg = <2>;
 				ethernet = <&dpmac17>;
 				phy-mode = "rgmii-id";
+				rx-internal-delay-ps = <2000>;
+				tx-internal-delay-ps = <2000>;
 
 				fixed-link {
 					speed = <1000>;
@@ -529,6 +531,8 @@
 				reg = <2>;
 				ethernet = <&dpmac18>;
 				phy-mode = "rgmii-id";
+				rx-internal-delay-ps = <2000>;
+				tx-internal-delay-ps = <2000>;
 
 				fixed-link {
 					speed = <1000>;
diff --git a/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi b/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi
index dc8661ebd1f6..2433e6f2eda8 100644
--- a/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi
@@ -719,7 +719,7 @@
 			clock-names = "i2c";
 			clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL
 					    QORIQ_CLK_PLL_DIV(16)>;
-			scl-gpio = <&gpio2 15 GPIO_ACTIVE_HIGH>;
+			scl-gpios = <&gpio2 15 GPIO_ACTIVE_HIGH>;
 			status = "disabled";
 		};
 
@@ -768,7 +768,7 @@
 			clock-names = "i2c";
 			clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL
 					    QORIQ_CLK_PLL_DIV(16)>;
-			scl-gpio = <&gpio2 16 GPIO_ACTIVE_HIGH>;
+			scl-gpios = <&gpio2 16 GPIO_ACTIVE_HIGH>;
 			status = "disabled";
 		};
 
diff --git a/arch/arm64/boot/dts/freescale/imx8mq.dtsi b/arch/arm64/boot/dts/freescale/imx8mq.dtsi
index 972766b67a15..71bf497f99c2 100644
--- a/arch/arm64/boot/dts/freescale/imx8mq.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mq.dtsi
@@ -524,8 +524,6 @@
 						  <&clk IMX8MQ_VIDEO_PLL1>,
 						  <&clk IMX8MQ_VIDEO_PLL1_OUT>;
 				assigned-clock-rates = <0>, <0>, <0>, <594000000>;
-				interconnects = <&noc IMX8MQ_ICM_LCDIF &noc IMX8MQ_ICS_DRAM>;
-				interconnect-names = "dram";
 				status = "disabled";
 
 				port@0 {
diff --git a/arch/arm64/boot/dts/rockchip/rk3308-roc-cc.dts b/arch/arm64/boot/dts/rockchip/rk3308-roc-cc.dts
index 665b2e69455d..ea6820902ede 100644
--- a/arch/arm64/boot/dts/rockchip/rk3308-roc-cc.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3308-roc-cc.dts
@@ -97,7 +97,7 @@
 		regulator-max-microvolt = <3300000>;
 		regulator-always-on;
 		regulator-boot-on;
-		vim-supply = <&vcc_io>;
+		vin-supply = <&vcc_io>;
 	};
 
 	vdd_core: vdd-core {
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-khadas-edge.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-khadas-edge.dtsi
index d5c7648c841d..f1fcc6b5b402 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-khadas-edge.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399-khadas-edge.dtsi
@@ -705,7 +705,6 @@
 &sdhci {
 	bus-width = <8>;
 	mmc-hs400-1_8v;
-	mmc-hs400-enhanced-strobe;
 	non-removable;
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-kobol-helios64.dts b/arch/arm64/boot/dts/rockchip/rk3399-kobol-helios64.dts
index 63c7681843da..b6ac00f64613 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-kobol-helios64.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3399-kobol-helios64.dts
@@ -276,6 +276,7 @@
 		clock-output-names = "xin32k", "rk808-clkout2";
 		pinctrl-names = "default";
 		pinctrl-0 = <&pmic_int_l>;
+		rockchip,system-power-controller;
 		vcc1-supply = <&vcc5v0_sys>;
 		vcc2-supply = <&vcc5v0_sys>;
 		vcc3-supply = <&vcc5v0_sys>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-leez-p710.dts b/arch/arm64/boot/dts/rockchip/rk3399-leez-p710.dts
index 7c93f840bc64..e890166e7fd4 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-leez-p710.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3399-leez-p710.dts
@@ -55,7 +55,7 @@
 		regulator-boot-on;
 		regulator-min-microvolt = <3300000>;
 		regulator-max-microvolt = <3300000>;
-		vim-supply = <&vcc3v3_sys>;
+		vin-supply = <&vcc3v3_sys>;
 	};
 
 	vcc3v3_sys: vcc3v3-sys {
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi
index 98136c88fa49..6a434be62819 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi
@@ -502,7 +502,7 @@
 	status = "okay";
 
 	bt656-supply = <&vcc_3v0>;
-	audio-supply = <&vcc_3v0>;
+	audio-supply = <&vcc1v8_codec>;
 	sdmmc-supply = <&vcc_sdio>;
 	gpio1830-supply = <&vcc_3v0>;
 };
diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h
index d3e1825337be..ad55079abe47 100644
--- a/arch/arm64/include/asm/efi.h
+++ b/arch/arm64/include/asm/efi.h
@@ -14,7 +14,6 @@
 
 #ifdef CONFIG_EFI
 extern void efi_init(void);
-extern void efifb_setup_from_dmi(struct screen_info *si, const char *opt);
 #else
 #define efi_init()
 #endif
diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index a305ce256090..d52a0b269ee8 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -68,6 +68,7 @@
 #define ESR_ELx_EC_MAX		(0x3F)
 
 #define ESR_ELx_EC_SHIFT	(26)
+#define ESR_ELx_EC_WIDTH	(6)
 #define ESR_ELx_EC_MASK		(UL(0x3F) << ESR_ELx_EC_SHIFT)
 #define ESR_ELx_EC(esr)		(((esr) & ESR_ELx_EC_MASK) >> ESR_ELx_EC_SHIFT)
 
diff --git a/arch/arm64/include/asm/ftrace.h b/arch/arm64/include/asm/ftrace.h
index 347b0cc68f07..1494cfa8639b 100644
--- a/arch/arm64/include/asm/ftrace.h
+++ b/arch/arm64/include/asm/ftrace.h
@@ -12,6 +12,17 @@
 
 #define HAVE_FUNCTION_GRAPH_FP_TEST
 
+/*
+ * HAVE_FUNCTION_GRAPH_RET_ADDR_PTR means that the architecture can provide a
+ * "return address pointer" which can be used to uniquely identify a return
+ * address which has been overwritten.
+ *
+ * On arm64 we use the address of the caller's frame record, which remains the
+ * same for the lifetime of the instrumented function, unlike the return
+ * address in the LR.
+ */
+#define HAVE_FUNCTION_GRAPH_RET_ADDR_PTR
+
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
 #define ARCH_SUPPORTS_FTRACE_OPS 1
 #else
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index a39fcf318c77..01d47c5886dc 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -91,7 +91,7 @@
 #define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H)
 
 /* TCR_EL2 Registers bits */
-#define TCR_EL2_RES1		((1 << 31) | (1 << 23))
+#define TCR_EL2_RES1		((1U << 31) | (1 << 23))
 #define TCR_EL2_TBI		(1 << 20)
 #define TCR_EL2_PS_SHIFT	16
 #define TCR_EL2_PS_MASK		(7 << TCR_EL2_PS_SHIFT)
@@ -276,7 +276,7 @@
 #define CPTR_EL2_TFP_SHIFT 10
 
 /* Hyp Coprocessor Trap Register */
-#define CPTR_EL2_TCPAC	(1 << 31)
+#define CPTR_EL2_TCPAC	(1U << 31)
 #define CPTR_EL2_TAM	(1 << 30)
 #define CPTR_EL2_TTA	(1 << 20)
 #define CPTR_EL2_TFP	(1 << CPTR_EL2_TFP_SHIFT)
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 4be8486042a7..2a5f7f38006f 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -584,7 +584,7 @@ struct kvm_vcpu_stat {
 	u64 exits;
 };
 
-int kvm_vcpu_preferred_target(struct kvm_vcpu_init *init);
+void kvm_vcpu_preferred_target(struct kvm_vcpu_init *init);
 unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu);
 int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *indices);
 int kvm_arm_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg);
diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h
index 8433a2058eb1..237224484d0f 100644
--- a/arch/arm64/include/asm/pgalloc.h
+++ b/arch/arm64/include/asm/pgalloc.h
@@ -76,7 +76,7 @@ static inline void __pmd_populate(pmd_t *pmdp, phys_addr_t ptep,
 static inline void
 pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmdp, pte_t *ptep)
 {
-	VM_BUG_ON(mm != &init_mm);
+	VM_BUG_ON(mm && mm != &init_mm);
 	__pmd_populate(pmdp, __pa(ptep), PMD_TYPE_TABLE | PMD_TABLE_UXN);
 }
 
diff --git a/arch/arm64/include/asm/stacktrace.h b/arch/arm64/include/asm/stacktrace.h
index a4e046ef4568..6564a01cc085 100644
--- a/arch/arm64/include/asm/stacktrace.h
+++ b/arch/arm64/include/asm/stacktrace.h
@@ -47,9 +47,6 @@ struct stack_info {
  * @prev_type:   The type of stack this frame record was on, or a synthetic
  *               value of STACK_TYPE_UNKNOWN. This is used to detect a
  *               transition from one stack to another.
- *
- * @graph:       When FUNCTION_GRAPH_TRACER is selected, holds the index of a
- *               replacement lr value in the ftrace graph stack.
  */
 struct stackframe {
 	unsigned long fp;
@@ -57,9 +54,6 @@ struct stackframe {
 	DECLARE_BITMAP(stacks_done, __NR_STACK_TYPES);
 	unsigned long prev_fp;
 	enum stack_type prev_type;
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	int graph;
-#endif
 #ifdef CONFIG_KRETPROBES
 	struct llist_node *kr_cur;
 #endif
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index 6e2e0b7031ab..3a5ff5e20586 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -281,12 +281,22 @@ do {									\
 	(x) = (__force __typeof__(*(ptr)))__gu_val;			\
 } while (0)
 
+/*
+ * We must not call into the scheduler between uaccess_ttbr0_enable() and
+ * uaccess_ttbr0_disable(). As `x` and `ptr` could contain blocking functions,
+ * we must evaluate these outside of the critical section.
+ */
 #define __raw_get_user(x, ptr, err)					\
 do {									\
+	__typeof__(*(ptr)) __user *__rgu_ptr = (ptr);			\
+	__typeof__(x) __rgu_val;					\
 	__chk_user_ptr(ptr);						\
+									\
 	uaccess_ttbr0_enable();						\
-	__raw_get_mem("ldtr", x, ptr, err);				\
+	__raw_get_mem("ldtr", __rgu_val, __rgu_ptr, err);		\
 	uaccess_ttbr0_disable();					\
+									\
+	(x) = __rgu_val;						\
 } while (0)
 
 #define __get_user_error(x, ptr, err)					\
@@ -310,14 +320,22 @@ do {									\
 
 #define get_user	__get_user
 
+/*
+ * We must not call into the scheduler between __uaccess_enable_tco_async() and
+ * __uaccess_disable_tco_async(). As `dst` and `src` may contain blocking
+ * functions, we must evaluate these outside of the critical section.
+ */
 #define __get_kernel_nofault(dst, src, type, err_label)			\
 do {									\
+	__typeof__(dst) __gkn_dst = (dst);				\
+	__typeof__(src) __gkn_src = (src);				\
 	int __gkn_err = 0;						\
 									\
 	__uaccess_enable_tco_async();					\
-	__raw_get_mem("ldr", *((type *)(dst)),				\
-		      (__force type *)(src), __gkn_err);		\
+	__raw_get_mem("ldr", *((type *)(__gkn_dst)),			\
+		      (__force type *)(__gkn_src), __gkn_err);		\
 	__uaccess_disable_tco_async();					\
+									\
 	if (unlikely(__gkn_err))					\
 		goto err_label;						\
 } while (0)
@@ -351,11 +369,19 @@ do {									\
 	}								\
 } while (0)
 
+/*
+ * We must not call into the scheduler between uaccess_ttbr0_enable() and
+ * uaccess_ttbr0_disable(). As `x` and `ptr` could contain blocking functions,
+ * we must evaluate these outside of the critical section.
+ */
 #define __raw_put_user(x, ptr, err)					\
 do {									\
-	__chk_user_ptr(ptr);						\
+	__typeof__(*(ptr)) __user *__rpu_ptr = (ptr);			\
+	__typeof__(*(ptr)) __rpu_val = (x);				\
+	__chk_user_ptr(__rpu_ptr);					\
+									\
 	uaccess_ttbr0_enable();						\
-	__raw_put_mem("sttr", x, ptr, err);				\
+	__raw_put_mem("sttr", __rpu_val, __rpu_ptr, err);		\
 	uaccess_ttbr0_disable();					\
 } while (0)
 
@@ -380,14 +406,22 @@ do {									\
 
 #define put_user	__put_user
 
+/*
+ * We must not call into the scheduler between __uaccess_enable_tco_async() and
+ * __uaccess_disable_tco_async(). As `dst` and `src` may contain blocking
+ * functions, we must evaluate these outside of the critical section.
+ */
 #define __put_kernel_nofault(dst, src, type, err_label)			\
 do {									\
+	__typeof__(dst) __pkn_dst = (dst);				\
+	__typeof__(src) __pkn_src = (src);				\
 	int __pkn_err = 0;						\
 									\
 	__uaccess_enable_tco_async();					\
-	__raw_put_mem("str", *((type *)(src)),				\
-		      (__force type *)(dst), __pkn_err);		\
+	__raw_put_mem("str", *((type *)(__pkn_src)),			\
+		      (__force type *)(__pkn_dst), __pkn_err);		\
 	__uaccess_disable_tco_async();					\
+									\
 	if (unlikely(__pkn_err))					\
 		goto err_label;						\
 } while(0)
diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S
index b3e4f9a088b1..8cf970d219f5 100644
--- a/arch/arm64/kernel/entry-ftrace.S
+++ b/arch/arm64/kernel/entry-ftrace.S
@@ -77,11 +77,17 @@
 	.endm
 
 SYM_CODE_START(ftrace_regs_caller)
+#ifdef BTI_C
+	BTI_C
+#endif
 	ftrace_regs_entry	1
 	b	ftrace_common
 SYM_CODE_END(ftrace_regs_caller)
 
 SYM_CODE_START(ftrace_caller)
+#ifdef BTI_C
+	BTI_C
+#endif
 	ftrace_regs_entry	0
 	b	ftrace_common
 SYM_CODE_END(ftrace_caller)
diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c
index fc62dfe73f93..4506c4a90ac1 100644
--- a/arch/arm64/kernel/ftrace.c
+++ b/arch/arm64/kernel/ftrace.c
@@ -244,8 +244,6 @@ void arch_ftrace_update_code(int command)
  * on the way back to parent. For this purpose, this function is called
  * in _mcount() or ftrace_caller() to replace return address (*parent) on
  * the call stack to return_to_handler.
- *
- * Note that @frame_pointer is used only for sanity check later.
  */
 void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent,
 			   unsigned long frame_pointer)
@@ -263,8 +261,10 @@ void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent,
 	 */
 	old = *parent;
 
-	if (!function_graph_enter(old, self_addr, frame_pointer, NULL))
+	if (!function_graph_enter(old, self_addr, frame_pointer,
+	    (void *)frame_pointer)) {
 		*parent = return_hooker;
+	}
 }
 
 #ifdef CONFIG_DYNAMIC_FTRACE
diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c
index 1038494135c8..6fb31c117ebe 100644
--- a/arch/arm64/kernel/machine_kexec.c
+++ b/arch/arm64/kernel/machine_kexec.c
@@ -147,7 +147,7 @@ int machine_kexec_post_load(struct kimage *kimage)
 	if (rc)
 		return rc;
 	kimage->arch.ttbr1 = __pa(trans_pgd);
-	kimage->arch.zero_page = __pa(empty_zero_page);
+	kimage->arch.zero_page = __pa_symbol(empty_zero_page);
 
 	reloc_size = __relocate_new_kernel_end - __relocate_new_kernel_start;
 	memcpy(reloc_code, __relocate_new_kernel_start, reloc_size);
diff --git a/arch/arm64/kernel/machine_kexec_file.c b/arch/arm64/kernel/machine_kexec_file.c
index 63634b4d72c1..59c648d51848 100644
--- a/arch/arm64/kernel/machine_kexec_file.c
+++ b/arch/arm64/kernel/machine_kexec_file.c
@@ -149,6 +149,7 @@ int load_other_segments(struct kimage *image,
 					   initrd_len, cmdline, 0);
 	if (!dtb) {
 		pr_err("Preparing for new dtb failed\n");
+		ret = -EINVAL;
 		goto out_err;
 	}
 
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index c30624fff6ac..94f83cd44e50 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -38,9 +38,6 @@ void start_backtrace(struct stackframe *frame, unsigned long fp,
 {
 	frame->fp = fp;
 	frame->pc = pc;
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	frame->graph = 0;
-#endif
 #ifdef CONFIG_KRETPROBES
 	frame->kr_cur = NULL;
 #endif
@@ -116,20 +113,23 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame)
 	frame->prev_fp = fp;
 	frame->prev_type = info.type;
 
+	frame->pc = ptrauth_strip_insn_pac(frame->pc);
+
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	if (tsk->ret_stack &&
-		(ptrauth_strip_insn_pac(frame->pc) == (unsigned long)return_to_handler)) {
-		struct ftrace_ret_stack *ret_stack;
+		(frame->pc == (unsigned long)return_to_handler)) {
+		unsigned long orig_pc;
 		/*
 		 * This is a case where function graph tracer has
 		 * modified a return address (LR) in a stack frame
 		 * to hook a function return.
 		 * So replace it to an original value.
 		 */
-		ret_stack = ftrace_graph_get_ret_stack(tsk, frame->graph++);
-		if (WARN_ON_ONCE(!ret_stack))
+		orig_pc = ftrace_graph_ret_addr(tsk, NULL, frame->pc,
+						(void *)frame->fp);
+		if (WARN_ON_ONCE(frame->pc == orig_pc))
 			return -EINVAL;
-		frame->pc = ret_stack->ret;
+		frame->pc = orig_pc;
 	}
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
 #ifdef CONFIG_KRETPROBES
@@ -137,8 +137,6 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame)
 		frame->pc = kretprobe_find_ret_addr(tsk, (void *)frame->fp, &frame->kr_cur);
 #endif
 
-	frame->pc = ptrauth_strip_insn_pac(frame->pc);
-
 	return 0;
 }
 NOKPROBE_SYMBOL(unwind_frame);
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index f5490afe1ebf..e4727dc771bf 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -223,7 +223,14 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		r = 1;
 		break;
 	case KVM_CAP_NR_VCPUS:
-		r = num_online_cpus();
+		/*
+		 * ARM64 treats KVM_CAP_NR_CPUS differently from all other
+		 * architectures, as it does not always bound it to
+		 * KVM_CAP_MAX_VCPUS. It should not matter much because
+		 * this is just an advisory value.
+		 */
+		r = min_t(unsigned int, num_online_cpus(),
+			  kvm_arm_default_max_vcpus());
 		break;
 	case KVM_CAP_MAX_VCPUS:
 	case KVM_CAP_MAX_VCPU_ID:
@@ -1389,12 +1396,9 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		return kvm_vm_ioctl_set_device_addr(kvm, &dev_addr);
 	}
 	case KVM_ARM_PREFERRED_TARGET: {
-		int err;
 		struct kvm_vcpu_init init;
 
-		err = kvm_vcpu_preferred_target(&init);
-		if (err)
-			return err;
+		kvm_vcpu_preferred_target(&init);
 
 		if (copy_to_user(argp, &init, sizeof(init)))
 			return -EFAULT;
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index 5ce26bedf23c..e116c7767730 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -869,13 +869,10 @@ u32 __attribute_const__ kvm_target_cpu(void)
 	return KVM_ARM_TARGET_GENERIC_V8;
 }
 
-int kvm_vcpu_preferred_target(struct kvm_vcpu_init *init)
+void kvm_vcpu_preferred_target(struct kvm_vcpu_init *init)
 {
 	u32 target = kvm_target_cpu();
 
-	if (target < 0)
-		return -ENODEV;
-
 	memset(init, 0, sizeof(*init));
 
 	/*
@@ -885,8 +882,6 @@ int kvm_vcpu_preferred_target(struct kvm_vcpu_init *init)
 	 * target type.
 	 */
 	init->target = (__u32)target;
-
-	return 0;
 }
 
 int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S
index 9aa9b73475c9..b6b6801d96d5 100644
--- a/arch/arm64/kvm/hyp/hyp-entry.S
+++ b/arch/arm64/kvm/hyp/hyp-entry.S
@@ -44,7 +44,7 @@
 el1_sync:				// Guest trapped into EL2
 
 	mrs	x0, esr_el2
-	lsr	x0, x0, #ESR_ELx_EC_SHIFT
+	ubfx	x0, x0, #ESR_ELx_EC_SHIFT, #ESR_ELx_EC_WIDTH
 	cmp	x0, #ESR_ELx_EC_HVC64
 	ccmp	x0, #ESR_ELx_EC_HVC32, #4, ne
 	b.ne	el1_trap
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index 7a0af1d39303..96c5f3fb7838 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -403,6 +403,8 @@ typedef bool (*exit_handler_fn)(struct kvm_vcpu *, u64 *);
 
 static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu);
 
+static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code);
+
 /*
  * Allow the hypervisor to handle the exit with an exit handler if it has one.
  *
@@ -429,6 +431,18 @@ static inline bool kvm_hyp_handle_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
  */
 static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
 {
+	/*
+	 * Save PSTATE early so that we can evaluate the vcpu mode
+	 * early on.
+	 */
+	vcpu->arch.ctxt.regs.pstate = read_sysreg_el2(SYS_SPSR);
+
+	/*
+	 * Check whether we want to repaint the state one way or
+	 * another.
+	 */
+	early_exit_filter(vcpu, exit_code);
+
 	if (ARM_EXCEPTION_CODE(*exit_code) != ARM_EXCEPTION_IRQ)
 		vcpu->arch.fault.esr_el2 = read_sysreg_el2(SYS_ESR);
 
diff --git a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
index de7e14c862e6..7ecca8b07851 100644
--- a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
+++ b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
@@ -70,7 +70,12 @@ static inline void __sysreg_save_el1_state(struct kvm_cpu_context *ctxt)
 static inline void __sysreg_save_el2_return_state(struct kvm_cpu_context *ctxt)
 {
 	ctxt->regs.pc			= read_sysreg_el2(SYS_ELR);
-	ctxt->regs.pstate		= read_sysreg_el2(SYS_SPSR);
+	/*
+	 * Guest PSTATE gets saved at guest fixup time in all
+	 * cases. We still need to handle the nVHE host side here.
+	 */
+	if (!has_vhe() && ctxt->__hyp_running_vcpu)
+		ctxt->regs.pstate	= read_sysreg_el2(SYS_SPSR);
 
 	if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN))
 		ctxt_sys_reg(ctxt, DISR_EL1) = read_sysreg_s(SYS_VDISR_EL2);
diff --git a/arch/arm64/kvm/hyp/nvhe/host.S b/arch/arm64/kvm/hyp/nvhe/host.S
index 0c6116d34e18..3d613e721a75 100644
--- a/arch/arm64/kvm/hyp/nvhe/host.S
+++ b/arch/arm64/kvm/hyp/nvhe/host.S
@@ -141,7 +141,7 @@ SYM_FUNC_END(__host_hvc)
 .L__vect_start\@:
 	stp	x0, x1, [sp, #-16]!
 	mrs	x0, esr_el2
-	lsr	x0, x0, #ESR_ELx_EC_SHIFT
+	ubfx	x0, x0, #ESR_ELx_EC_SHIFT, #ESR_ELx_EC_WIDTH
 	cmp	x0, #ESR_ELx_EC_HVC64
 	b.eq	__host_hvc
 	b	__host_exit
diff --git a/arch/arm64/kvm/hyp/nvhe/setup.c b/arch/arm64/kvm/hyp/nvhe/setup.c
index 862c7b514e20..578f71798c2e 100644
--- a/arch/arm64/kvm/hyp/nvhe/setup.c
+++ b/arch/arm64/kvm/hyp/nvhe/setup.c
@@ -178,7 +178,7 @@ static int finalize_host_mappings_walker(u64 addr, u64 end, u32 level,
 
 	phys = kvm_pte_to_phys(pte);
 	if (!addr_is_memory(phys))
-		return 0;
+		return -EINVAL;
 
 	/*
 	 * Adjust the host stage-2 mappings to match the ownership attributes
@@ -207,8 +207,18 @@ static int finalize_host_mappings(void)
 		.cb	= finalize_host_mappings_walker,
 		.flags	= KVM_PGTABLE_WALK_LEAF,
 	};
+	int i, ret;
+
+	for (i = 0; i < hyp_memblock_nr; i++) {
+		struct memblock_region *reg = &hyp_memory[i];
+		u64 start = (u64)hyp_phys_to_virt(reg->base);
+
+		ret = kvm_pgtable_walk(&pkvm_pgtable, start, reg->size, &walker);
+		if (ret)
+			return ret;
+	}
 
-	return kvm_pgtable_walk(&pkvm_pgtable, 0, BIT(pkvm_pgtable.ia_bits), &walker);
+	return 0;
 }
 
 void __noreturn __pkvm_init_finalise(void)
diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c
index c0e3fed26d93..d13115a12434 100644
--- a/arch/arm64/kvm/hyp/nvhe/switch.c
+++ b/arch/arm64/kvm/hyp/nvhe/switch.c
@@ -233,7 +233,7 @@ static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu)
  * Returns false if the guest ran in AArch32 when it shouldn't have, and
  * thus should exit to the host, or true if a the guest run loop can continue.
  */
-static bool handle_aarch32_guest(struct kvm_vcpu *vcpu, u64 *exit_code)
+static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code)
 {
 	struct kvm *kvm = kern_hyp_va(vcpu->kvm);
 
@@ -248,10 +248,7 @@ static bool handle_aarch32_guest(struct kvm_vcpu *vcpu, u64 *exit_code)
 		vcpu->arch.target = -1;
 		*exit_code &= BIT(ARM_EXIT_WITH_SERROR_BIT);
 		*exit_code |= ARM_EXCEPTION_IL;
-		return false;
 	}
-
-	return true;
 }
 
 /* Switch to the guest for legacy non-VHE systems */
@@ -316,9 +313,6 @@ int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
 		/* Jump in the fire! */
 		exit_code = __guest_enter(vcpu);
 
-		if (unlikely(!handle_aarch32_guest(vcpu, &exit_code)))
-			break;
-
 		/* And we're baaack! */
 	} while (fixup_guest_exit(vcpu, &exit_code));
 
diff --git a/arch/arm64/kvm/hyp/nvhe/sys_regs.c b/arch/arm64/kvm/hyp/nvhe/sys_regs.c
index 3787ee6fb1a2..792cf6e6ac92 100644
--- a/arch/arm64/kvm/hyp/nvhe/sys_regs.c
+++ b/arch/arm64/kvm/hyp/nvhe/sys_regs.c
@@ -474,7 +474,7 @@ bool kvm_handle_pvm_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code)
 	return true;
 }
 
-/**
+/*
  * Handler for protected VM restricted exceptions.
  *
  * Inject an undefined exception into the guest and return true to indicate that
diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
index 5a2cb5d9bc4b..fbb26b93c347 100644
--- a/arch/arm64/kvm/hyp/vhe/switch.c
+++ b/arch/arm64/kvm/hyp/vhe/switch.c
@@ -112,6 +112,10 @@ static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu)
 	return hyp_exit_handlers;
 }
 
+static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+}
+
 /* Switch to the guest for VHE systems running in EL2 */
 static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
 {
diff --git a/arch/csky/kernel/traps.c b/arch/csky/kernel/traps.c
index e5fbf8653a21..2020af88b636 100644
--- a/arch/csky/kernel/traps.c
+++ b/arch/csky/kernel/traps.c
@@ -209,7 +209,7 @@ asmlinkage void do_trap_illinsn(struct pt_regs *regs)
 
 asmlinkage void do_trap_fpe(struct pt_regs *regs)
 {
-#ifdef CONFIG_CPU_HAS_FP
+#ifdef CONFIG_CPU_HAS_FPU
 	return fpu_fpe(regs);
 #else
 	do_trap_error(regs, SIGILL, ILL_ILLOPC, regs->pc,
@@ -219,7 +219,7 @@ asmlinkage void do_trap_fpe(struct pt_regs *regs)
 
 asmlinkage void do_trap_priv(struct pt_regs *regs)
 {
-#ifdef CONFIG_CPU_HAS_FP
+#ifdef CONFIG_CPU_HAS_FPU
 	if (user_mode(regs) && fpu_libc_helper(regs))
 		return;
 #endif
diff --git a/arch/hexagon/include/asm/timer-regs.h b/arch/hexagon/include/asm/timer-regs.h
deleted file mode 100644
index ee6c61423a05..000000000000
--- a/arch/hexagon/include/asm/timer-regs.h
+++ /dev/null
@@ -1,26 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Timer support for Hexagon
- *
- * Copyright (c) 2010-2011, The Linux Foundation. All rights reserved.
- */
-
-#ifndef _ASM_TIMER_REGS_H
-#define _ASM_TIMER_REGS_H
-
-/*  This stuff should go into a platform specific file  */
-#define TCX0_CLK_RATE		19200
-#define TIMER_ENABLE		0
-#define TIMER_CLR_ON_MATCH	1
-
-/*
- * 8x50 HDD Specs 5-8.  Simulator co-sim not fixed until
- * release 1.1, and then it's "adjustable" and probably not defaulted.
- */
-#define RTOS_TIMER_INT		3
-#ifdef CONFIG_HEXAGON_COMET
-#define RTOS_TIMER_REGS_ADDR	0xAB000000UL
-#endif
-#define SLEEP_CLK_RATE		32000
-
-#endif
diff --git a/arch/hexagon/include/asm/timex.h b/arch/hexagon/include/asm/timex.h
index 8d4ec76fceb4..dfe69e118b2b 100644
--- a/arch/hexagon/include/asm/timex.h
+++ b/arch/hexagon/include/asm/timex.h
@@ -7,11 +7,10 @@
 #define _ASM_TIMEX_H
 
 #include <asm-generic/timex.h>
-#include <asm/timer-regs.h>
 #include <asm/hexagon_vm.h>
 
 /* Using TCX0 as our clock.  CLOCK_TICK_RATE scheduled to be removed. */
-#define CLOCK_TICK_RATE              TCX0_CLK_RATE
+#define CLOCK_TICK_RATE              19200
 
 #define ARCH_HAS_READ_CURRENT_TIMER
 
diff --git a/arch/hexagon/kernel/.gitignore b/arch/hexagon/kernel/.gitignore
new file mode 100644
index 000000000000..c5f676c3c224
--- /dev/null
+++ b/arch/hexagon/kernel/.gitignore
@@ -0,0 +1 @@
+vmlinux.lds
diff --git a/arch/hexagon/kernel/time.c b/arch/hexagon/kernel/time.c
index feffe527ac92..febc95714d75 100644
--- a/arch/hexagon/kernel/time.c
+++ b/arch/hexagon/kernel/time.c
@@ -17,9 +17,10 @@
 #include <linux/of_irq.h>
 #include <linux/module.h>
 
-#include <asm/timer-regs.h>
 #include <asm/hexagon_vm.h>
 
+#define TIMER_ENABLE		BIT(0)
+
 /*
  * For the clocksource we need:
  *	pcycle frequency (600MHz)
@@ -33,6 +34,13 @@ cycles_t	pcycle_freq_mhz;
 cycles_t	thread_freq_mhz;
 cycles_t	sleep_clk_freq;
 
+/*
+ * 8x50 HDD Specs 5-8.  Simulator co-sim not fixed until
+ * release 1.1, and then it's "adjustable" and probably not defaulted.
+ */
+#define RTOS_TIMER_INT		3
+#define RTOS_TIMER_REGS_ADDR	0xAB000000UL
+
 static struct resource rtos_timer_resources[] = {
 	{
 		.start	= RTOS_TIMER_REGS_ADDR,
@@ -80,7 +88,7 @@ static int set_next_event(unsigned long delta, struct clock_event_device *evt)
 	iowrite32(0, &rtos_timer->clear);
 
 	iowrite32(delta, &rtos_timer->match);
-	iowrite32(1 << TIMER_ENABLE, &rtos_timer->enable);
+	iowrite32(TIMER_ENABLE, &rtos_timer->enable);
 	return 0;
 }
 
diff --git a/arch/hexagon/lib/io.c b/arch/hexagon/lib/io.c
index d35d69d6588c..55f75392857b 100644
--- a/arch/hexagon/lib/io.c
+++ b/arch/hexagon/lib/io.c
@@ -27,6 +27,7 @@ void __raw_readsw(const void __iomem *addr, void *data, int len)
 		*dst++ = *src;
 
 }
+EXPORT_SYMBOL(__raw_readsw);
 
 /*
  * __raw_writesw - read words a short at a time
@@ -47,6 +48,7 @@ void __raw_writesw(void __iomem *addr, const void *data, int len)
 
 
 }
+EXPORT_SYMBOL(__raw_writesw);
 
 /*  Pretty sure len is pre-adjusted for the length of the access already */
 void __raw_readsl(const void __iomem *addr, void *data, int len)
@@ -62,6 +64,7 @@ void __raw_readsl(const void __iomem *addr, void *data, int len)
 
 
 }
+EXPORT_SYMBOL(__raw_readsl);
 
 void __raw_writesl(void __iomem *addr, const void *data, int len)
 {
@@ -76,3 +79,4 @@ void __raw_writesl(void __iomem *addr, const void *data, int len)
 
 
 }
+EXPORT_SYMBOL(__raw_writesl);
diff --git a/arch/ia64/kernel/syscalls/syscall.tbl b/arch/ia64/kernel/syscalls/syscall.tbl
index 6fea1844fb95..707ae121f6d3 100644
--- a/arch/ia64/kernel/syscalls/syscall.tbl
+++ b/arch/ia64/kernel/syscalls/syscall.tbl
@@ -369,3 +369,4 @@
 446	common	landlock_restrict_self		sys_landlock_restrict_self
 # 447 reserved for memfd_secret
 448	common	process_mrelease		sys_process_mrelease
+449	common  futex_waitv                     sys_futex_waitv
diff --git a/arch/m68k/include/asm/cacheflush_mm.h b/arch/m68k/include/asm/cacheflush_mm.h
index 8ab46625ddd3..1ac55e7b47f0 100644
--- a/arch/m68k/include/asm/cacheflush_mm.h
+++ b/arch/m68k/include/asm/cacheflush_mm.h
@@ -250,7 +250,6 @@ static inline void __flush_page_to_ram(void *vaddr)
 
 #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
 #define flush_dcache_page(page)		__flush_page_to_ram(page_address(page))
-void flush_dcache_folio(struct folio *folio);
 #define flush_dcache_mmap_lock(mapping)		do { } while (0)
 #define flush_dcache_mmap_unlock(mapping)	do { } while (0)
 #define flush_icache_page(vma, page)	__flush_page_to_ram(page_address(page))
diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl
index 7976dff8f879..45bc32a41b90 100644
--- a/arch/m68k/kernel/syscalls/syscall.tbl
+++ b/arch/m68k/kernel/syscalls/syscall.tbl
@@ -448,3 +448,4 @@
 446	common	landlock_restrict_self		sys_landlock_restrict_self
 # 447 reserved for memfd_secret
 448	common	process_mrelease		sys_process_mrelease
+449	common  futex_waitv                     sys_futex_waitv
diff --git a/arch/m68k/kernel/traps.c b/arch/m68k/kernel/traps.c
index 99058a6da956..34d6458340b0 100644
--- a/arch/m68k/kernel/traps.c
+++ b/arch/m68k/kernel/traps.c
@@ -1145,7 +1145,7 @@ asmlinkage void set_esp0(unsigned long ssp)
  */
 asmlinkage void fpsp040_die(void)
 {
-	force_fatal_sig(SIGSEGV);
+	force_exit_sig(SIGSEGV);
 }
 
 #ifdef CONFIG_M68KFPU_EMU
diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl
index 6b0e11362bd2..2204bde3ce4a 100644
--- a/arch/microblaze/kernel/syscalls/syscall.tbl
+++ b/arch/microblaze/kernel/syscalls/syscall.tbl
@@ -454,3 +454,4 @@
 446	common	landlock_restrict_self		sys_landlock_restrict_self
 # 447 reserved for memfd_secret
 448	common	process_mrelease		sys_process_mrelease
+449	common  futex_waitv                     sys_futex_waitv
diff --git a/arch/mips/Kbuild.platforms b/arch/mips/Kbuild.platforms
index 2c57994b5217..30193bcf9caa 100644
--- a/arch/mips/Kbuild.platforms
+++ b/arch/mips/Kbuild.platforms
@@ -37,4 +37,4 @@ platform-$(CONFIG_MACH_TX49XX)		+= txx9/
 platform-$(CONFIG_MACH_VR41XX)		+= vr41xx/
 
 # include the platform specific files
-include $(patsubst %, $(srctree)/arch/mips/%/Platform, $(platform-y))
+include $(patsubst %/, $(srctree)/arch/mips/%/Platform, $(platform-y))
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 86510741d49d..0215dc1529e9 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -292,6 +292,8 @@ config BMIPS_GENERIC
 	select USB_OHCI_BIG_ENDIAN_DESC if CPU_BIG_ENDIAN
 	select USB_OHCI_BIG_ENDIAN_MMIO if CPU_BIG_ENDIAN
 	select HARDIRQS_SW_RESEND
+	select HAVE_PCI
+	select PCI_DRIVERS_GENERIC
 	help
 	  Build a generic DT-based kernel image that boots on select
 	  BCM33xx cable modem chips, BCM63xx DSL chips, and BCM7xxx set-top
@@ -333,6 +335,9 @@ config BCM63XX
 	select SYS_SUPPORTS_32BIT_KERNEL
 	select SYS_SUPPORTS_BIG_ENDIAN
 	select SYS_HAS_EARLY_PRINTK
+	select SYS_HAS_CPU_BMIPS32_3300
+	select SYS_HAS_CPU_BMIPS4350
+	select SYS_HAS_CPU_BMIPS4380
 	select SWAP_IO_SPACE
 	select GPIOLIB
 	select MIPS_L1_CACHE_SHIFT_4
@@ -3092,7 +3097,7 @@ config STACKTRACE_SUPPORT
 config PGTABLE_LEVELS
 	int
 	default 4 if PAGE_SIZE_4KB && MIPS_VA_BITS_48
-	default 3 if 64BIT && !PAGE_SIZE_64KB
+	default 3 if 64BIT && (!PAGE_SIZE_64KB || MIPS_VA_BITS_48)
 	default 2
 
 config MIPS_AUTO_PFN_OFFSET
diff --git a/arch/mips/Makefile b/arch/mips/Makefile
index e036fc025ccc..ace7f033de07 100644
--- a/arch/mips/Makefile
+++ b/arch/mips/Makefile
@@ -253,7 +253,9 @@ endif
 #
 # Board-dependent options and extra files
 #
+ifdef need-compiler
 include $(srctree)/arch/mips/Kbuild.platforms
+endif
 
 ifdef CONFIG_PHYSICAL_START
 load-y					= $(CONFIG_PHYSICAL_START)
diff --git a/arch/mips/bcm63xx/clk.c b/arch/mips/bcm63xx/clk.c
index 5a3e325275d0..1c91064cb448 100644
--- a/arch/mips/bcm63xx/clk.c
+++ b/arch/mips/bcm63xx/clk.c
@@ -381,6 +381,12 @@ void clk_disable(struct clk *clk)
 
 EXPORT_SYMBOL(clk_disable);
 
+struct clk *clk_get_parent(struct clk *clk)
+{
+	return NULL;
+}
+EXPORT_SYMBOL(clk_get_parent);
+
 unsigned long clk_get_rate(struct clk *clk)
 {
 	if (!clk)
diff --git a/arch/mips/boot/compressed/Makefile b/arch/mips/boot/compressed/Makefile
index 3548b3b45269..f27cf31b4140 100644
--- a/arch/mips/boot/compressed/Makefile
+++ b/arch/mips/boot/compressed/Makefile
@@ -50,19 +50,9 @@ vmlinuzobjs-$(CONFIG_MIPS_ALCHEMY)		   += $(obj)/uart-alchemy.o
 vmlinuzobjs-$(CONFIG_ATH79)			   += $(obj)/uart-ath79.o
 endif
 
-extra-y += uart-ath79.c
-$(obj)/uart-ath79.c: $(srctree)/arch/mips/ath79/early_printk.c
-	$(call cmd,shipped)
-
 vmlinuzobjs-$(CONFIG_KERNEL_XZ) += $(obj)/ashldi3.o
 
-extra-y += ashldi3.c
-$(obj)/ashldi3.c: $(obj)/%.c: $(srctree)/lib/%.c FORCE
-	$(call if_changed,shipped)
-
-extra-y += bswapsi.c
-$(obj)/bswapsi.c: $(obj)/%.c: $(srctree)/arch/mips/lib/%.c FORCE
-	$(call if_changed,shipped)
+vmlinuzobjs-$(CONFIG_KERNEL_ZSTD) += $(obj)/bswapdi.o $(obj)/ashldi3.o
 
 targets := $(notdir $(vmlinuzobjs-y))
 
diff --git a/arch/mips/boot/compressed/ashldi3.c b/arch/mips/boot/compressed/ashldi3.c
new file mode 100644
index 000000000000..f7bf6a7aae31
--- /dev/null
+++ b/arch/mips/boot/compressed/ashldi3.c
@@ -0,0 +1,2 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include "../../../../lib/ashldi3.c"
diff --git a/arch/mips/boot/compressed/bswapdi.c b/arch/mips/boot/compressed/bswapdi.c
new file mode 100644
index 000000000000..acb28aebb025
--- /dev/null
+++ b/arch/mips/boot/compressed/bswapdi.c
@@ -0,0 +1,2 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include "../../lib/bswapdi.c"
diff --git a/arch/mips/boot/compressed/bswapsi.c b/arch/mips/boot/compressed/bswapsi.c
new file mode 100644
index 000000000000..fdb9c6476904
--- /dev/null
+++ b/arch/mips/boot/compressed/bswapsi.c
@@ -0,0 +1,2 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include "../../lib/bswapsi.c"
diff --git a/arch/mips/boot/compressed/uart-ath79.c b/arch/mips/boot/compressed/uart-ath79.c
new file mode 100644
index 000000000000..d686820921be
--- /dev/null
+++ b/arch/mips/boot/compressed/uart-ath79.c
@@ -0,0 +1,2 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include "../../ath79/early_printk.c"
diff --git a/arch/mips/boot/dts/ingenic/jz4725b.dtsi b/arch/mips/boot/dts/ingenic/jz4725b.dtsi
index a1f0b71c9223..0c6a5a4266f4 100644
--- a/arch/mips/boot/dts/ingenic/jz4725b.dtsi
+++ b/arch/mips/boot/dts/ingenic/jz4725b.dtsi
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <dt-bindings/clock/jz4725b-cgu.h>
+#include <dt-bindings/clock/ingenic,jz4725b-cgu.h>
 #include <dt-bindings/clock/ingenic,tcu.h>
 
 / {
diff --git a/arch/mips/boot/dts/ingenic/jz4740.dtsi b/arch/mips/boot/dts/ingenic/jz4740.dtsi
index c1afdfdaa8a3..772542e1f266 100644
--- a/arch/mips/boot/dts/ingenic/jz4740.dtsi
+++ b/arch/mips/boot/dts/ingenic/jz4740.dtsi
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <dt-bindings/clock/jz4740-cgu.h>
+#include <dt-bindings/clock/ingenic,jz4740-cgu.h>
 #include <dt-bindings/clock/ingenic,tcu.h>
 
 / {
diff --git a/arch/mips/boot/dts/ingenic/jz4770.dtsi b/arch/mips/boot/dts/ingenic/jz4770.dtsi
index 05c00b93088e..dfe74328ae5d 100644
--- a/arch/mips/boot/dts/ingenic/jz4770.dtsi
+++ b/arch/mips/boot/dts/ingenic/jz4770.dtsi
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <dt-bindings/clock/jz4770-cgu.h>
+#include <dt-bindings/clock/ingenic,jz4770-cgu.h>
 #include <dt-bindings/clock/ingenic,tcu.h>
 
 / {
diff --git a/arch/mips/boot/dts/ingenic/jz4780.dtsi b/arch/mips/boot/dts/ingenic/jz4780.dtsi
index 28adc3d93975..b0a4e2e019c3 100644
--- a/arch/mips/boot/dts/ingenic/jz4780.dtsi
+++ b/arch/mips/boot/dts/ingenic/jz4780.dtsi
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <dt-bindings/clock/jz4780-cgu.h>
+#include <dt-bindings/clock/ingenic,jz4780-cgu.h>
 #include <dt-bindings/clock/ingenic,tcu.h>
 #include <dt-bindings/dma/jz4780-dma.h>
 
diff --git a/arch/mips/boot/dts/ingenic/x1000.dtsi b/arch/mips/boot/dts/ingenic/x1000.dtsi
index dec7909d4baa..8bd27edef216 100644
--- a/arch/mips/boot/dts/ingenic/x1000.dtsi
+++ b/arch/mips/boot/dts/ingenic/x1000.dtsi
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <dt-bindings/clock/ingenic,tcu.h>
-#include <dt-bindings/clock/x1000-cgu.h>
+#include <dt-bindings/clock/ingenic,x1000-cgu.h>
 #include <dt-bindings/dma/x1000-dma.h>
 
 / {
diff --git a/arch/mips/boot/dts/ingenic/x1830.dtsi b/arch/mips/boot/dts/ingenic/x1830.dtsi
index 215257f8bb1a..2595df8671c7 100644
--- a/arch/mips/boot/dts/ingenic/x1830.dtsi
+++ b/arch/mips/boot/dts/ingenic/x1830.dtsi
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <dt-bindings/clock/ingenic,tcu.h>
-#include <dt-bindings/clock/x1830-cgu.h>
+#include <dt-bindings/clock/ingenic,x1830-cgu.h>
 #include <dt-bindings/dma/x1830-dma.h>
 
 / {
diff --git a/arch/mips/configs/bmips_stb_defconfig b/arch/mips/configs/bmips_stb_defconfig
index 625bd2d7e685..5956fb95c19f 100644
--- a/arch/mips/configs/bmips_stb_defconfig
+++ b/arch/mips/configs/bmips_stb_defconfig
@@ -1,6 +1,7 @@
 # CONFIG_LOCALVERSION_AUTO is not set
 # CONFIG_SWAP is not set
 CONFIG_NO_HZ=y
+CONFIG_HZ=1000
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_EXPERT=y
 # CONFIG_VM_EVENT_COUNTERS is not set
@@ -8,17 +9,34 @@ CONFIG_EXPERT=y
 CONFIG_BMIPS_GENERIC=y
 CONFIG_CPU_LITTLE_ENDIAN=y
 CONFIG_HIGHMEM=y
+CONFIG_HIGH_RES_TIMERS=y
 CONFIG_SMP=y
 CONFIG_NR_CPUS=4
+CONFIG_CC_STACKPROTECTOR_STRONG=y
 # CONFIG_SECCOMP is not set
 CONFIG_MIPS_O32_FP64_SUPPORT=y
+# CONFIG_RD_GZIP is not set
+# CONFIG_RD_BZIP2 is not set
+# CONFIG_RD_LZMA is not set
+CONFIG_RD_XZ=y
+# CONFIG_RD_LZO is not set
+# CONFIG_RD_LZ4 is not set
+# CONFIG_IOSCHED_DEADLINE is not set
+# CONFIG_IOSCHED_CFQ is not set
+CONFIG_PCI=y
+CONFIG_PCI_MSI=y
+CONFIG_PCIEASPM_POWERSAVE=y
+CONFIG_PCIEPORTBUS=y
+CONFIG_PCIE_BRCMSTB=y
 CONFIG_CPU_FREQ=y
 CONFIG_CPU_FREQ_STAT=y
+CONFIG_CPU_FREQ_STAT_DETAILS=y
+CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE=y
+CONFIG_CPU_FREQ_GOV_PERFORMANCE=y
 CONFIG_CPU_FREQ_GOV_POWERSAVE=y
 CONFIG_CPU_FREQ_GOV_USERSPACE=y
 CONFIG_CPU_FREQ_GOV_ONDEMAND=y
 CONFIG_CPU_FREQ_GOV_CONSERVATIVE=y
-CONFIG_CPU_FREQ_GOV_SCHEDUTIL=y
 CONFIG_BMIPS_CPUFREQ=y
 # CONFIG_BLK_DEV_BSG is not set
 CONFIG_NET=y
@@ -32,32 +50,99 @@ CONFIG_INET=y
 # CONFIG_INET_DIAG is not set
 CONFIG_CFG80211=y
 CONFIG_NL80211_TESTMODE=y
+CONFIG_WIRELESS=y
 CONFIG_MAC80211=y
+CONFIG_NL80211=y
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 # CONFIG_STANDALONE is not set
 # CONFIG_PREVENT_FIRMWARE_BUILD is not set
+CONFIG_BRCMSTB_GISB_ARB=y
+CONFIG_MODULES=y
+CONFIG_MODULE_FORCE_LOAD=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_MODVERSIONS=y
+CONFIG_IP_MULTICAST=y
+CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
+CONFIG_IP_PNP_BOOTP=y
+CONFIG_IP_PNP_RARP=y
+CONFIG_IP_MROUTE=y
+CONFIG_IP_PIMSM_V1=y
+CONFIG_IP_PIMSM_V2=y
+# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
+# CONFIG_INET_XFRM_MODE_TUNNEL is not set
+# CONFIG_INET_XFRM_MODE_BEET is not set
+# CONFIG_INET_LRO is not set
+CONFIG_INET_UDP_DIAG=y
+CONFIG_TCP_CONG_ADVANCED=y
+CONFIG_TCP_CONG_BIC=y
+# CONFIG_TCP_CONG_WESTWOOD is not set
+# CONFIG_TCP_CONG_HTCP is not set
+# CONFIG_IPV6 is not set
+CONFIG_IP_NF_IPTABLES=y
+CONFIG_IP_NF_FILTER=y
+CONFIG_NETFILTER=y
+CONFIG_NETFILTER_XTABLES=y
+CONFIG_BRIDGE=y
+CONFIG_BRIDGE_NETFILTER=m
+CONFIG_BRIDGE_NF_EBTABLES=m
+CONFIG_BRIDGE_EBT_BROUTE=m
+CONFIG_NET_DSA=y
+CONFIG_NET_SWITCHDEV=y
+CONFIG_DMA_CMA=y
+CONFIG_CMA_ALIGNMENT=12
+CONFIG_SPI=y
+CONFIG_SPI_BRCMSTB=y
 CONFIG_MTD=y
+CONFIG_MTD_CMDLINE_PARTS=y
+CONFIG_MTD_BLOCK=y
 CONFIG_MTD_CFI=y
+CONFIG_MTD_JEDECPROBE=y
 CONFIG_MTD_CFI_INTELEXT=y
 CONFIG_MTD_CFI_AMDSTD=y
-CONFIG_MTD_PHYSMAP=y
+CONFIG_MTD_CFI_STAA=y
+CONFIG_MTD_ROM=y
+CONFIG_MTD_ABSENT=y
+CONFIG_MTD_PHYSMAP_OF=y
+CONFIG_MTD_M25P80=y
+CONFIG_MTD_NAND=y
+CONFIG_MTD_NAND_BRCMNAND=y
+CONFIG_MTD_SPI_NOR=y
+# CONFIG_MTD_SPI_NOR_USE_4K_SECTORS is not set
+CONFIG_MTD_UBI=y
+CONFIG_MTD_UBI_GLUEBI=y
+CONFIG_PROC_DEVICETREE=y
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_RAM_SIZE=8192
 # CONFIG_BLK_DEV is not set
 CONFIG_SCSI=y
 CONFIG_BLK_DEV_SD=y
+CONFIG_CHR_DEV_SG=y
+CONFIG_SCSI_MULTI_LUN=y
 # CONFIG_SCSI_LOWLEVEL is not set
 CONFIG_NETDEVICES=y
+CONFIG_VLAN_8021Q=y
+CONFIG_MACVLAN=y
 CONFIG_BCMGENET=y
 CONFIG_USB_USBNET=y
-# CONFIG_INPUT is not set
+CONFIG_INPUT_EVDEV=y
+# CONFIG_INPUT_KEYBOARD is not set
+# CONFIG_INPUT_MOUSE is not set
+CONFIG_INPUT_MISC=y
+CONFIG_INPUT_UINPUT=y
 # CONFIG_SERIO is not set
-# CONFIG_VT is not set
+CONFIG_VT=y
+CONFIG_VT_HW_CONSOLE_BINDING=y
+# CONFIG_DEVKMEM is not set
 CONFIG_SERIAL_8250=y
 # CONFIG_SERIAL_8250_DEPRECATED_OPTIONS is not set
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_SERIAL_OF_PLATFORM=y
 # CONFIG_HW_RANDOM is not set
 CONFIG_POWER_RESET=y
+CONFIG_POWER_RESET_BRCMSTB=y
 CONFIG_POWER_RESET_SYSCON=y
 CONFIG_POWER_SUPPLY=y
 # CONFIG_HWMON is not set
@@ -69,22 +154,76 @@ CONFIG_USB_OHCI_HCD=y
 CONFIG_USB_OHCI_HCD_PLATFORM=y
 CONFIG_USB_STORAGE=y
 CONFIG_SOC_BRCMSTB=y
+CONFIG_MMC=y
+CONFIG_MMC_BLOCK_MINORS=16
+CONFIG_MMC_SDHCI=y
+CONFIG_MMC_SDHCI_PLTFM=y
 CONFIG_EXT4_FS=y
 CONFIG_EXT4_FS_POSIX_ACL=y
 CONFIG_EXT4_FS_SECURITY=y
 # CONFIG_DNOTIFY is not set
+CONFIG_PROC_KCORE=y
+CONFIG_CIFS=y
+CONFIG_JBD2_DEBUG=y
 CONFIG_FUSE_FS=y
+CONFIG_FHANDLE=y
+CONFIG_CGROUPS=y
+CONFIG_CUSE=y
+CONFIG_ISO9660_FS=y
+CONFIG_JOLIET=y
+CONFIG_ZISOFS=y
+CONFIG_UDF_FS=y
+CONFIG_MSDOS_FS=y
 CONFIG_VFAT_FS=y
-CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
+CONFIG_JFFS2_FS=y
+CONFIG_UBIFS_FS=y
+CONFIG_SQUASHFS=y
+CONFIG_SQUASHFS_LZO=y
+CONFIG_SQUASHFS_XZ=y
 CONFIG_NFS_FS=y
-CONFIG_CIFS=y
+CONFIG_NFS_V3_ACL=y
+CONFIG_NFS_V4=y
+CONFIG_NFS_V4_1=y
+CONFIG_NFS_V4_2=y
+CONFIG_ROOT_NFS=y
 CONFIG_NLS_CODEPAGE_437=y
-CONFIG_NLS_ASCII=y
 CONFIG_NLS_ISO8859_1=y
-# CONFIG_CRYPTO_HW is not set
 CONFIG_PRINTK_TIME=y
+CONFIG_DYNAMIC_DEBUG=y
+# CONFIG_DEBUG_INFO is not set
+# CONFIG_DEBUG_INFO_REDUCED is not set
 CONFIG_DEBUG_FS=y
 CONFIG_MAGIC_SYSRQ=y
+CONFIG_LOCKUP_DETECTOR=y
+CONFIG_DEBUG_USER=y
 CONFIG_CMDLINE_BOOL=y
 CONFIG_CMDLINE="earlycon"
+# CONFIG_MIPS_CMDLINE_FROM_DTB is not set
+CONFIG_MIPS_CMDLINE_DTB_EXTEND=y
+# CONFIG_MIPS_CMDLINE_FROM_BOOTLOADER is not set
+# CONFIG_CRYPTO_HW is not set
+CONFIG_DT_BCM974XX=y
+CONFIG_FW_CFE=y
+CONFIG_ATA=y
+CONFIG_SATA_AHCI_PLATFORM=y
+CONFIG_AHCI_BRCMSTB=y
+CONFIG_GENERIC_PHY=y
+CONFIG_GPIOLIB=y
+CONFIG_GPIO_SYSFS=y
+CONFIG_PHY_BRCM_USB=y
+CONFIG_PHY_BRCM_SATA=y
+CONFIG_PM_RUNTIME=y
+CONFIG_PM_DEBUG=y
+CONFIG_SYSVIPC=y
+CONFIG_FUNCTION_GRAPH_TRACER=y
+CONFIG_DYNAMIC_FTRACE=y
+CONFIG_FUNCTION_TRACER=y
+CONFIG_FUNCTION_PROFILER=y
+CONFIG_IRQSOFF_TRACER=y
+CONFIG_SCHED_TRACER=y
+CONFIG_BLK_DEV_IO_TRACE=y
+CONFIG_FTRACE_SYSCALLS=y
+CONFIG_TRACER_SNAPSHOT=y
+CONFIG_TRACER_SNAPSHOT_PER_CPU_SWAP=y
+CONFIG_STACK_TRACER=y
diff --git a/arch/mips/dec/setup.c b/arch/mips/dec/setup.c
index eaad0ed4b523..a8a30bb1dee8 100644
--- a/arch/mips/dec/setup.c
+++ b/arch/mips/dec/setup.c
@@ -117,21 +117,21 @@ static void __init dec_be_init(void)
 {
 	switch (mips_machtype) {
 	case MACH_DS23100:	/* DS2100/DS3100 Pmin/Pmax */
-		board_be_handler = dec_kn01_be_handler;
+		mips_set_be_handler(dec_kn01_be_handler);
 		busirq_handler = dec_kn01_be_interrupt;
 		busirq_flags |= IRQF_SHARED;
 		dec_kn01_be_init();
 		break;
 	case MACH_DS5000_1XX:	/* DS5000/1xx 3min */
 	case MACH_DS5000_XX:	/* DS5000/xx Maxine */
-		board_be_handler = dec_kn02xa_be_handler;
+		mips_set_be_handler(dec_kn02xa_be_handler);
 		busirq_handler = dec_kn02xa_be_interrupt;
 		dec_kn02xa_be_init();
 		break;
 	case MACH_DS5000_200:	/* DS5000/200 3max */
 	case MACH_DS5000_2X0:	/* DS5000/240 3max+ */
 	case MACH_DS5900:	/* DS5900 bigmax */
-		board_be_handler = dec_ecc_be_handler;
+		mips_set_be_handler(dec_ecc_be_handler);
 		busirq_handler = dec_ecc_be_interrupt;
 		dec_ecc_be_init();
 		break;
diff --git a/arch/mips/generic/yamon-dt.c b/arch/mips/generic/yamon-dt.c
index a3aa22c77cad..a07a5edbcda7 100644
--- a/arch/mips/generic/yamon-dt.c
+++ b/arch/mips/generic/yamon-dt.c
@@ -75,7 +75,7 @@ static unsigned int __init gen_fdt_mem_array(
 __init int yamon_dt_append_memory(void *fdt,
 				  const struct yamon_mem_region *regions)
 {
-	unsigned long phys_memsize, memsize;
+	unsigned long phys_memsize = 0, memsize;
 	__be32 mem_array[2 * MAX_MEM_ARRAY_ENTRIES];
 	unsigned int mem_entries;
 	int i, err, mem_off;
diff --git a/arch/mips/include/asm/cacheflush.h b/arch/mips/include/asm/cacheflush.h
index f207388541d5..b3dc9c589442 100644
--- a/arch/mips/include/asm/cacheflush.h
+++ b/arch/mips/include/asm/cacheflush.h
@@ -61,8 +61,6 @@ static inline void flush_dcache_page(struct page *page)
 		SetPageDcacheDirty(page);
 }
 
-void flush_dcache_folio(struct folio *folio);
-
 #define flush_dcache_mmap_lock(mapping)		do { } while (0)
 #define flush_dcache_mmap_unlock(mapping)	do { } while (0)
 
diff --git a/arch/mips/include/asm/mach-ralink/spaces.h b/arch/mips/include/asm/mach-ralink/spaces.h
index 05d14c21c417..f7af11ea2d61 100644
--- a/arch/mips/include/asm/mach-ralink/spaces.h
+++ b/arch/mips/include/asm/mach-ralink/spaces.h
@@ -6,5 +6,7 @@
 #define PCI_IOSIZE	SZ_64K
 #define IO_SPACE_LIMIT	(PCI_IOSIZE - 1)
 
+#define pci_remap_iospace pci_remap_iospace
+
 #include <asm/mach-generic/spaces.h>
 #endif
diff --git a/arch/mips/include/asm/pci.h b/arch/mips/include/asm/pci.h
index 421231f55935..9ffc8192adae 100644
--- a/arch/mips/include/asm/pci.h
+++ b/arch/mips/include/asm/pci.h
@@ -20,10 +20,6 @@
 #include <linux/list.h>
 #include <linux/of.h>
 
-#ifdef CONFIG_PCI_DRIVERS_GENERIC
-#define pci_remap_iospace pci_remap_iospace
-#endif
-
 #ifdef CONFIG_PCI_DRIVERS_LEGACY
 
 /*
diff --git a/arch/mips/include/asm/traps.h b/arch/mips/include/asm/traps.h
index b710e76c9c65..15cde638b407 100644
--- a/arch/mips/include/asm/traps.h
+++ b/arch/mips/include/asm/traps.h
@@ -15,7 +15,7 @@
 #define MIPS_BE_FATAL	2		/* treat as an unrecoverable error */
 
 extern void (*board_be_init)(void);
-extern int (*board_be_handler)(struct pt_regs *regs, int is_fixup);
+void mips_set_be_handler(int (*handler)(struct pt_regs *reg, int is_fixup));
 
 extern void (*board_nmi_handler_setup)(void);
 extern void (*board_ejtag_handler_setup)(void);
diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c
index ac0e2cfc6d57..24a529c6c4be 100644
--- a/arch/mips/kernel/cpu-probe.c
+++ b/arch/mips/kernel/cpu-probe.c
@@ -1734,8 +1734,6 @@ static inline void decode_cpucfg(struct cpuinfo_mips *c)
 
 static inline void cpu_probe_loongson(struct cpuinfo_mips *c, unsigned int cpu)
 {
-	decode_configs(c);
-
 	/* All Loongson processors covered here define ExcCode 16 as GSExc. */
 	c->options |= MIPS_CPU_GSEXCEX;
 
@@ -1796,6 +1794,8 @@ static inline void cpu_probe_loongson(struct cpuinfo_mips *c, unsigned int cpu)
 		panic("Unknown Loongson Processor ID!");
 		break;
 	}
+
+	decode_configs(c);
 }
 #else
 static inline void cpu_probe_loongson(struct cpuinfo_mips *c, unsigned int cpu) { }
diff --git a/arch/mips/kernel/proc.c b/arch/mips/kernel/proc.c
index 376a6e2676e9..9f47a889b047 100644
--- a/arch/mips/kernel/proc.c
+++ b/arch/mips/kernel/proc.c
@@ -185,7 +185,7 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 		seq_puts(m, " tx39_cache");
 	if (cpu_has_octeon_cache)
 		seq_puts(m, " octeon_cache");
-	if (cpu_has_fpu)
+	if (raw_cpu_has_fpu)
 		seq_puts(m, " fpu");
 	if (cpu_has_32fpr)
 		seq_puts(m, " 32fpr");
diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl
index 70e32de2bcaa..72d02d363f36 100644
--- a/arch/mips/kernel/syscalls/syscall_n32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n32.tbl
@@ -387,3 +387,4 @@
 446	n32	landlock_restrict_self		sys_landlock_restrict_self
 # 447 reserved for memfd_secret
 448	n32	process_mrelease		sys_process_mrelease
+449	n32	futex_waitv			sys_futex_waitv
diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl
index 1ca7bc337932..e2c481fcede6 100644
--- a/arch/mips/kernel/syscalls/syscall_n64.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n64.tbl
@@ -363,3 +363,4 @@
 446	n64	landlock_restrict_self		sys_landlock_restrict_self
 # 447 reserved for memfd_secret
 448	n64	process_mrelease		sys_process_mrelease
+449	n64	futex_waitv			sys_futex_waitv
diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl
index a61c35edaa74..3714c97b2643 100644
--- a/arch/mips/kernel/syscalls/syscall_o32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_o32.tbl
@@ -436,3 +436,4 @@
 446	o32	landlock_restrict_self		sys_landlock_restrict_self
 # 447 reserved for memfd_secret
 448	o32	process_mrelease		sys_process_mrelease
+449	o32	futex_waitv			sys_futex_waitv
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index 6f07362de5ce..d26b0fb8ea06 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -103,13 +103,19 @@ extern asmlinkage void handle_reserved(void);
 extern void tlb_do_page_fault_0(void);
 
 void (*board_be_init)(void);
-int (*board_be_handler)(struct pt_regs *regs, int is_fixup);
+static int (*board_be_handler)(struct pt_regs *regs, int is_fixup);
 void (*board_nmi_handler_setup)(void);
 void (*board_ejtag_handler_setup)(void);
 void (*board_bind_eic_interrupt)(int irq, int regset);
 void (*board_ebase_setup)(void);
 void(*board_cache_error_setup)(void);
 
+void mips_set_be_handler(int (*handler)(struct pt_regs *regs, int is_fixup))
+{
+	board_be_handler = handler;
+}
+EXPORT_SYMBOL_GPL(mips_set_be_handler);
+
 static void show_raw_backtrace(unsigned long reg29, const char *loglvl,
 			       bool user)
 {
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index 562aa878b266..aa20d074d388 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -1067,7 +1067,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		r = 1;
 		break;
 	case KVM_CAP_NR_VCPUS:
-		r = num_online_cpus();
+		r = min_t(unsigned int, num_online_cpus(), KVM_MAX_VCPUS);
 		break;
 	case KVM_CAP_MAX_VCPUS:
 		r = KVM_MAX_VCPUS;
diff --git a/arch/mips/lantiq/clk.c b/arch/mips/lantiq/clk.c
index dd819e31fcbb..4916cccf378f 100644
--- a/arch/mips/lantiq/clk.c
+++ b/arch/mips/lantiq/clk.c
@@ -158,6 +158,12 @@ void clk_deactivate(struct clk *clk)
 }
 EXPORT_SYMBOL(clk_deactivate);
 
+struct clk *clk_get_parent(struct clk *clk)
+{
+	return NULL;
+}
+EXPORT_SYMBOL(clk_get_parent);
+
 static inline u32 get_counter_resolution(void)
 {
 	u32 res;
diff --git a/arch/mips/net/bpf_jit_comp.h b/arch/mips/net/bpf_jit_comp.h
index 6f3a7b07294b..a37fe20818eb 100644
--- a/arch/mips/net/bpf_jit_comp.h
+++ b/arch/mips/net/bpf_jit_comp.h
@@ -98,7 +98,7 @@ do {								\
 #define emit(...) __emit(__VA_ARGS__)
 
 /* Workaround for R10000 ll/sc errata */
-#ifdef CONFIG_WAR_R10000
+#ifdef CONFIG_WAR_R10000_LLSC
 #define LLSC_beqz	beqzl
 #else
 #define LLSC_beqz	beqz
diff --git a/arch/mips/pci/pci-generic.c b/arch/mips/pci/pci-generic.c
index 18eb8a453a86..d2d68bac3d25 100644
--- a/arch/mips/pci/pci-generic.c
+++ b/arch/mips/pci/pci-generic.c
@@ -47,6 +47,7 @@ void pcibios_fixup_bus(struct pci_bus *bus)
 	pci_read_bridge_bases(bus);
 }
 
+#ifdef pci_remap_iospace
 int pci_remap_iospace(const struct resource *res, phys_addr_t phys_addr)
 {
 	unsigned long vaddr;
@@ -60,3 +61,4 @@ int pci_remap_iospace(const struct resource *res, phys_addr_t phys_addr)
 	set_io_port_base(vaddr);
 	return 0;
 }
+#endif
diff --git a/arch/mips/sgi-ip22/ip22-berr.c b/arch/mips/sgi-ip22/ip22-berr.c
index dc0110a607a5..afe8a61078e4 100644
--- a/arch/mips/sgi-ip22/ip22-berr.c
+++ b/arch/mips/sgi-ip22/ip22-berr.c
@@ -112,5 +112,5 @@ static int ip22_be_handler(struct pt_regs *regs, int is_fixup)
 
 void __init ip22_be_init(void)
 {
-	board_be_handler = ip22_be_handler;
+	mips_set_be_handler(ip22_be_handler);
 }
diff --git a/arch/mips/sgi-ip22/ip28-berr.c b/arch/mips/sgi-ip22/ip28-berr.c
index c61362d9ea95..16ca470deb80 100644
--- a/arch/mips/sgi-ip22/ip28-berr.c
+++ b/arch/mips/sgi-ip22/ip28-berr.c
@@ -468,7 +468,7 @@ static int ip28_be_handler(struct pt_regs *regs, int is_fixup)
 
 void __init ip22_be_init(void)
 {
-	board_be_handler = ip28_be_handler;
+	mips_set_be_handler(ip28_be_handler);
 }
 
 int ip28_show_be_info(struct seq_file *m)
diff --git a/arch/mips/sgi-ip27/ip27-berr.c b/arch/mips/sgi-ip27/ip27-berr.c
index 5a38ae6bdfa9..923a63a51cda 100644
--- a/arch/mips/sgi-ip27/ip27-berr.c
+++ b/arch/mips/sgi-ip27/ip27-berr.c
@@ -85,7 +85,7 @@ void __init ip27_be_init(void)
 	int cpu = LOCAL_HUB_L(PI_CPU_NUM);
 	int cpuoff = cpu << 8;
 
-	board_be_handler = ip27_be_handler;
+	mips_set_be_handler(ip27_be_handler);
 
 	LOCAL_HUB_S(PI_ERR_INT_PEND,
 		    cpu ? PI_ERR_CLEAR_ALL_B : PI_ERR_CLEAR_ALL_A);
diff --git a/arch/mips/sgi-ip32/ip32-berr.c b/arch/mips/sgi-ip32/ip32-berr.c
index c860f95ab7ed..478b63b4c808 100644
--- a/arch/mips/sgi-ip32/ip32-berr.c
+++ b/arch/mips/sgi-ip32/ip32-berr.c
@@ -34,5 +34,5 @@ static int ip32_be_handler(struct pt_regs *regs, int is_fixup)
 
 void __init ip32_be_init(void)
 {
-	board_be_handler = ip32_be_handler;
+	mips_set_be_handler(ip32_be_handler);
 }
diff --git a/arch/mips/sibyte/swarm/setup.c b/arch/mips/sibyte/swarm/setup.c
index f07b15dd1c1a..72a31eeeebba 100644
--- a/arch/mips/sibyte/swarm/setup.c
+++ b/arch/mips/sibyte/swarm/setup.c
@@ -122,7 +122,7 @@ void __init plat_mem_setup(void)
 #error invalid SiByte board configuration
 #endif
 
-	board_be_handler = swarm_be_handler;
+	mips_set_be_handler(swarm_be_handler);
 
 	if (xicor_probe())
 		swarm_rtc_type = RTC_XICOR;
diff --git a/arch/mips/txx9/generic/setup_tx4927.c b/arch/mips/txx9/generic/setup_tx4927.c
index 46e9c4101386..63f9725b2eb0 100644
--- a/arch/mips/txx9/generic/setup_tx4927.c
+++ b/arch/mips/txx9/generic/setup_tx4927.c
@@ -80,7 +80,7 @@ static int tx4927_be_handler(struct pt_regs *regs, int is_fixup)
 }
 static void __init tx4927_be_init(void)
 {
-	board_be_handler = tx4927_be_handler;
+	mips_set_be_handler(tx4927_be_handler);
 }
 
 static struct resource tx4927_sdram_resource[4];
diff --git a/arch/mips/txx9/generic/setup_tx4938.c b/arch/mips/txx9/generic/setup_tx4938.c
index 17395d5d15ca..ba646548c5f6 100644
--- a/arch/mips/txx9/generic/setup_tx4938.c
+++ b/arch/mips/txx9/generic/setup_tx4938.c
@@ -82,7 +82,7 @@ static int tx4938_be_handler(struct pt_regs *regs, int is_fixup)
 }
 static void __init tx4938_be_init(void)
 {
-	board_be_handler = tx4938_be_handler;
+	mips_set_be_handler(tx4938_be_handler);
 }
 
 static struct resource tx4938_sdram_resource[4];
diff --git a/arch/mips/txx9/generic/setup_tx4939.c b/arch/mips/txx9/generic/setup_tx4939.c
index bf8a3cdababf..f5f59b7401a3 100644
--- a/arch/mips/txx9/generic/setup_tx4939.c
+++ b/arch/mips/txx9/generic/setup_tx4939.c
@@ -86,7 +86,7 @@ static int tx4939_be_handler(struct pt_regs *regs, int is_fixup)
 }
 static void __init tx4939_be_init(void)
 {
-	board_be_handler = tx4939_be_handler;
+	mips_set_be_handler(tx4939_be_handler);
 }
 
 static struct resource tx4939_sdram_resource[4];
diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile
index 1b2ea34c3d3b..d65f55f67e19 100644
--- a/arch/mips/vdso/Makefile
+++ b/arch/mips/vdso/Makefile
@@ -57,7 +57,7 @@ endif
 
 # VDSO linker flags.
 ldflags-y := -Bsymbolic --no-undefined -soname=linux-vdso.so.1 \
-	$(filter -E%,$(KBUILD_CFLAGS)) -nostdlib -shared \
+	$(filter -E%,$(KBUILD_CFLAGS)) -shared \
 	-G 0 --eh-frame-hdr --hash-style=sysv --build-id=sha1 -T
 
 CFLAGS_REMOVE_vdso.o = $(CC_FLAGS_FTRACE)
diff --git a/arch/nds32/include/asm/cacheflush.h b/arch/nds32/include/asm/cacheflush.h
index 3fc0bb7d6487..c2a222ebfa2a 100644
--- a/arch/nds32/include/asm/cacheflush.h
+++ b/arch/nds32/include/asm/cacheflush.h
@@ -27,7 +27,6 @@ void flush_cache_vunmap(unsigned long start, unsigned long end);
 
 #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
 void flush_dcache_page(struct page *page);
-void flush_dcache_folio(struct folio *folio);
 void copy_to_user_page(struct vm_area_struct *vma, struct page *page,
 		       unsigned long vaddr, void *dst, void *src, int len);
 void copy_from_user_page(struct vm_area_struct *vma, struct page *page,
diff --git a/arch/nios2/include/asm/cacheflush.h b/arch/nios2/include/asm/cacheflush.h
index 1999561b22aa..d0b71dd71287 100644
--- a/arch/nios2/include/asm/cacheflush.h
+++ b/arch/nios2/include/asm/cacheflush.h
@@ -29,7 +29,6 @@ extern void flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr,
 	unsigned long pfn);
 #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
 void flush_dcache_page(struct page *page);
-void flush_dcache_folio(struct folio *folio);
 
 extern void flush_icache_range(unsigned long start, unsigned long end);
 extern void flush_icache_page(struct vm_area_struct *vma, struct page *page);
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index b2188da09c73..011dc32fdb4d 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -85,11 +85,6 @@ config MMU
 config STACK_GROWSUP
 	def_bool y
 
-config ARCH_DEFCONFIG
-	string
-	default "arch/parisc/configs/generic-32bit_defconfig" if !64BIT
-	default "arch/parisc/configs/generic-64bit_defconfig" if 64BIT
-
 config GENERIC_LOCKBREAK
 	bool
 	default y
diff --git a/arch/parisc/Makefile b/arch/parisc/Makefile
index 8db4af4879d0..82d77f4b0d08 100644
--- a/arch/parisc/Makefile
+++ b/arch/parisc/Makefile
@@ -15,7 +15,12 @@
 # Mike Shaver, Helge Deller and Martin K. Petersen
 #
 
+ifdef CONFIG_PARISC_SELF_EXTRACT
+boot := arch/parisc/boot
+KBUILD_IMAGE := $(boot)/bzImage
+else
 KBUILD_IMAGE := vmlinuz
+endif
 
 NM		= sh $(srctree)/arch/parisc/nm
 CHECKFLAGS	+= -D__hppa__=1
diff --git a/arch/parisc/configs/generic-32bit_defconfig b/arch/parisc/configs/generic-32bit_defconfig
index d6fd8fa7ed8c..53061cb2cf7f 100644
--- a/arch/parisc/configs/generic-32bit_defconfig
+++ b/arch/parisc/configs/generic-32bit_defconfig
@@ -231,6 +231,7 @@ CONFIG_CRYPTO_DEFLATE=y
 CONFIG_CRC_CCITT=m
 CONFIG_CRC_T10DIF=y
 CONFIG_FONTS=y
+CONFIG_PRINTK_TIME=y
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_FS=y
 CONFIG_DEBUG_MEMORY_INIT=y
diff --git a/arch/parisc/configs/generic-64bit_defconfig b/arch/parisc/configs/generic-64bit_defconfig
index d2daeac2b217..1b8fd80cbe7f 100644
--- a/arch/parisc/configs/generic-64bit_defconfig
+++ b/arch/parisc/configs/generic-64bit_defconfig
@@ -1,7 +1,9 @@
 CONFIG_LOCALVERSION="-64bit"
 # CONFIG_LOCALVERSION_AUTO is not set
+CONFIG_KERNEL_LZ4=y
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
+CONFIG_AUDIT=y
 CONFIG_BSD_PROCESS_ACCT=y
 CONFIG_BSD_PROCESS_ACCT_V3=y
 CONFIG_TASKSTATS=y
@@ -35,6 +37,7 @@ CONFIG_MODVERSIONS=y
 CONFIG_BLK_DEV_INTEGRITY=y
 CONFIG_BINFMT_MISC=m
 # CONFIG_COMPACTION is not set
+CONFIG_MEMORY_FAILURE=y
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
@@ -65,12 +68,15 @@ CONFIG_SCSI_ISCSI_ATTRS=y
 CONFIG_SCSI_SRP_ATTRS=y
 CONFIG_ISCSI_BOOT_SYSFS=y
 CONFIG_SCSI_MPT2SAS=y
-CONFIG_SCSI_LASI700=m
+CONFIG_SCSI_LASI700=y
 CONFIG_SCSI_SYM53C8XX_2=y
 CONFIG_SCSI_ZALON=y
 CONFIG_SCSI_QLA_ISCSI=m
 CONFIG_SCSI_DH=y
 CONFIG_ATA=y
+CONFIG_SATA_SIL=y
+CONFIG_SATA_SIS=y
+CONFIG_SATA_VIA=y
 CONFIG_PATA_NS87415=y
 CONFIG_PATA_SIL680=y
 CONFIG_ATA_GENERIC=y
@@ -79,6 +85,7 @@ CONFIG_MD_LINEAR=m
 CONFIG_BLK_DEV_DM=m
 CONFIG_DM_RAID=m
 CONFIG_DM_UEVENT=y
+CONFIG_DM_AUDIT=y
 CONFIG_FUSION=y
 CONFIG_FUSION_SPI=y
 CONFIG_FUSION_SAS=y
@@ -196,10 +203,15 @@ CONFIG_FB_MATROX_G=y
 CONFIG_FB_MATROX_I2C=y
 CONFIG_FB_MATROX_MAVEN=y
 CONFIG_FB_RADEON=y
+CONFIG_LOGO=y
+# CONFIG_LOGO_LINUX_CLUT224 is not set
 CONFIG_HIDRAW=y
 CONFIG_HID_PID=y
 CONFIG_USB_HIDDEV=y
 CONFIG_USB=y
+CONFIG_USB_EHCI_HCD=y
+CONFIG_USB_OHCI_HCD=y
+CONFIG_USB_OHCI_HCD_PLATFORM=y
 CONFIG_UIO=y
 CONFIG_UIO_PDRV_GENIRQ=m
 CONFIG_UIO_AEC=m
diff --git a/arch/parisc/include/asm/assembly.h b/arch/parisc/include/asm/assembly.h
index 7085df079702..6d13ae236fcb 100644
--- a/arch/parisc/include/asm/assembly.h
+++ b/arch/parisc/include/asm/assembly.h
@@ -3,38 +3,19 @@
  * Copyright (C) 1999 Hewlett-Packard (Frank Rowand)
  * Copyright (C) 1999 Philipp Rumpf <prumpf@tux.org>
  * Copyright (C) 1999 SuSE GmbH
+ * Copyright (C) 2021 Helge Deller <deller@gmx.de>
  */
 
 #ifndef _PARISC_ASSEMBLY_H
 #define _PARISC_ASSEMBLY_H
 
-#define CALLEE_FLOAT_FRAME_SIZE	80
-
 #ifdef CONFIG_64BIT
-#define LDREG	ldd
-#define STREG	std
-#define LDREGX  ldd,s
-#define LDREGM	ldd,mb
-#define STREGM	std,ma
-#define SHRREG	shrd
-#define SHLREG	shld
-#define ANDCM   andcm,*
-#define	COND(x)	* ## x
 #define RP_OFFSET	16
 #define FRAME_SIZE	128
 #define CALLEE_REG_FRAME_SIZE	144
 #define REG_SZ		8
 #define ASM_ULONG_INSN	.dword
 #else	/* CONFIG_64BIT */
-#define LDREG	ldw
-#define STREG	stw
-#define LDREGX  ldwx,s
-#define LDREGM	ldwm
-#define STREGM	stwm
-#define SHRREG	shr
-#define SHLREG	shlw
-#define ANDCM   andcm
-#define COND(x)	x
 #define RP_OFFSET	20
 #define FRAME_SIZE	64
 #define CALLEE_REG_FRAME_SIZE	128
@@ -45,6 +26,7 @@
 /* Frame alignment for 32- and 64-bit */
 #define FRAME_ALIGN     64
 
+#define CALLEE_FLOAT_FRAME_SIZE	80
 #define CALLEE_SAVE_FRAME_SIZE (CALLEE_REG_FRAME_SIZE + CALLEE_FLOAT_FRAME_SIZE)
 
 #ifdef CONFIG_PA20
@@ -68,6 +50,28 @@
 #ifdef __ASSEMBLY__
 
 #ifdef CONFIG_64BIT
+#define LDREG	ldd
+#define STREG	std
+#define LDREGX  ldd,s
+#define LDREGM	ldd,mb
+#define STREGM	std,ma
+#define SHRREG	shrd
+#define SHLREG	shld
+#define ANDCM   andcm,*
+#define	COND(x)	* ## x
+#else	/* CONFIG_64BIT */
+#define LDREG	ldw
+#define STREG	stw
+#define LDREGX  ldwx,s
+#define LDREGM	ldwm
+#define STREGM	stwm
+#define SHRREG	shr
+#define SHLREG	shlw
+#define ANDCM   andcm
+#define COND(x)	x
+#endif
+
+#ifdef CONFIG_64BIT
 /* the 64-bit pa gnu assembler unfortunately defaults to .level 1.1 or 2.0 so
  * work around that for now... */
 	.level 2.0w
@@ -143,6 +147,17 @@
 	extrd,u \r, 63-(\sa), 64-(\sa), \t
 	.endm
 
+	/* Extract unsigned for 32- and 64-bit
+	 * The extru instruction leaves the most significant 32 bits of the
+	 * target register in an undefined state on PA 2.0 systems. */
+	.macro extru_safe r, p, len, t
+#ifdef CONFIG_64BIT
+	extrd,u	\r, 32+(\p), \len, \t
+#else
+	extru	\r, \p, \len, \t
+#endif
+	.endm
+
 	/* load 32-bit 'value' into 'reg' compensating for the ldil
 	 * sign-extension when running in wide mode.
 	 * WARNING!! neither 'value' nor 'reg' can be expressions
diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h
index da0cd4b3a28f..859b8a34adcf 100644
--- a/arch/parisc/include/asm/cacheflush.h
+++ b/arch/parisc/include/asm/cacheflush.h
@@ -50,7 +50,6 @@ void invalidate_kernel_vmap_range(void *vaddr, int size);
 
 #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
 void flush_dcache_page(struct page *page);
-void flush_dcache_folio(struct folio *folio);
 
 #define flush_dcache_mmap_lock(mapping)		xa_lock_irq(&mapping->i_pages)
 #define flush_dcache_mmap_unlock(mapping)	xa_unlock_irq(&mapping->i_pages)
diff --git a/arch/parisc/include/asm/futex.h b/arch/parisc/include/asm/futex.h
index 70cf8f0a7617..9cd4dd6e63ad 100644
--- a/arch/parisc/include/asm/futex.h
+++ b/arch/parisc/include/asm/futex.h
@@ -14,7 +14,7 @@ static inline void
 _futex_spin_lock(u32 __user *uaddr)
 {
 	extern u32 lws_lock_start[];
-	long index = ((long)uaddr & 0x3f8) >> 1;
+	long index = ((long)uaddr & 0x7f8) >> 1;
 	arch_spinlock_t *s = (arch_spinlock_t *)&lws_lock_start[index];
 	preempt_disable();
 	arch_spin_lock(s);
@@ -24,7 +24,7 @@ static inline void
 _futex_spin_unlock(u32 __user *uaddr)
 {
 	extern u32 lws_lock_start[];
-	long index = ((long)uaddr & 0x3f8) >> 1;
+	long index = ((long)uaddr & 0x7f8) >> 1;
 	arch_spinlock_t *s = (arch_spinlock_t *)&lws_lock_start[index];
 	arch_spin_unlock(s);
 	preempt_enable();
diff --git a/arch/parisc/include/asm/jump_label.h b/arch/parisc/include/asm/jump_label.h
index 7efb1aa2f7f8..af2a598bc0f8 100644
--- a/arch/parisc/include/asm/jump_label.h
+++ b/arch/parisc/include/asm/jump_label.h
@@ -5,6 +5,7 @@
 #ifndef __ASSEMBLY__
 
 #include <linux/types.h>
+#include <linux/stringify.h>
 #include <asm/assembly.h>
 
 #define JUMP_LABEL_NOP_SIZE 4
diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h
index 7badd872f05a..3e7cf882639f 100644
--- a/arch/parisc/include/asm/pgtable.h
+++ b/arch/parisc/include/asm/pgtable.h
@@ -76,6 +76,8 @@ static inline void purge_tlb_entries(struct mm_struct *mm, unsigned long addr)
 	purge_tlb_end(flags);
 }
 
+extern void __update_cache(pte_t pte);
+
 /* Certain architectures need to do special things when PTEs
  * within a page table are directly modified.  Thus, the following
  * hook is made available.
@@ -83,11 +85,14 @@ static inline void purge_tlb_entries(struct mm_struct *mm, unsigned long addr)
 #define set_pte(pteptr, pteval)			\
 	do {					\
 		*(pteptr) = (pteval);		\
-		barrier();			\
+		mb();				\
 	} while(0)
 
 #define set_pte_at(mm, addr, pteptr, pteval)	\
 	do {					\
+		if (pte_present(pteval) &&	\
+		    pte_user(pteval))		\
+			__update_cache(pteval);	\
 		*(pteptr) = (pteval);		\
 		purge_tlb_entries(mm, addr);	\
 	} while (0)
@@ -303,6 +308,7 @@ extern unsigned long *empty_zero_page;
 
 #define pte_none(x)     (pte_val(x) == 0)
 #define pte_present(x)	(pte_val(x) & _PAGE_PRESENT)
+#define pte_user(x)	(pte_val(x) & _PAGE_USER)
 #define pte_clear(mm, addr, xp)  set_pte_at(mm, addr, xp, __pte(0))
 
 #define pmd_flag(x)	(pmd_val(x) & PxD_FLAG_MASK)
@@ -410,7 +416,7 @@ extern void paging_init (void);
 
 #define PG_dcache_dirty         PG_arch_1
 
-extern void update_mmu_cache(struct vm_area_struct *, unsigned long, pte_t *);
+#define update_mmu_cache(vms,addr,ptep) __update_cache(*ptep)
 
 /* Encode and de-code a swap entry */
 
diff --git a/arch/parisc/include/asm/rt_sigframe.h b/arch/parisc/include/asm/rt_sigframe.h
index 4b9e3d707571..2b3010ade00e 100644
--- a/arch/parisc/include/asm/rt_sigframe.h
+++ b/arch/parisc/include/asm/rt_sigframe.h
@@ -2,7 +2,7 @@
 #ifndef _ASM_PARISC_RT_SIGFRAME_H
 #define _ASM_PARISC_RT_SIGFRAME_H
 
-#define SIGRETURN_TRAMP 3
+#define SIGRETURN_TRAMP 4
 #define SIGRESTARTBLOCK_TRAMP 5 
 #define TRAMP_SIZE (SIGRETURN_TRAMP + SIGRESTARTBLOCK_TRAMP)
 
diff --git a/arch/parisc/install.sh b/arch/parisc/install.sh
index 056d588befdd..70d3cffb0251 100644
--- a/arch/parisc/install.sh
+++ b/arch/parisc/install.sh
@@ -39,6 +39,7 @@ verify "$3"
 if [ -n "${INSTALLKERNEL}" ]; then
   if [ -x ~/bin/${INSTALLKERNEL} ]; then exec ~/bin/${INSTALLKERNEL} "$@"; fi
   if [ -x /sbin/${INSTALLKERNEL} ]; then exec /sbin/${INSTALLKERNEL} "$@"; fi
+  if [ -x /usr/sbin/${INSTALLKERNEL} ]; then exec /usr/sbin/${INSTALLKERNEL} "$@"; fi
 fi
 
 # Default install
diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c
index c61827e4928a..94150b91c96f 100644
--- a/arch/parisc/kernel/cache.c
+++ b/arch/parisc/kernel/cache.c
@@ -83,9 +83,9 @@ EXPORT_SYMBOL(flush_cache_all_local);
 #define pfn_va(pfn)	__va(PFN_PHYS(pfn))
 
 void
-update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep)
+__update_cache(pte_t pte)
 {
-	unsigned long pfn = pte_pfn(*ptep);
+	unsigned long pfn = pte_pfn(pte);
 	struct page *page;
 
 	/* We don't have pte special.  As a result, we can be called with
diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S
index 57944d6f9ebb..6e9cdb269862 100644
--- a/arch/parisc/kernel/entry.S
+++ b/arch/parisc/kernel/entry.S
@@ -366,17 +366,9 @@
 	 */
 	.macro		L2_ptep	pmd,pte,index,va,fault
 #if CONFIG_PGTABLE_LEVELS == 3
-	extru		\va,31-ASM_PMD_SHIFT,ASM_BITS_PER_PMD,\index
+	extru_safe	\va,31-ASM_PMD_SHIFT,ASM_BITS_PER_PMD,\index
 #else
-# if defined(CONFIG_64BIT)
-	extrd,u		\va,63-ASM_PGDIR_SHIFT,ASM_BITS_PER_PGD,\index
-  #else
-  # if PAGE_SIZE > 4096
-	extru		\va,31-ASM_PGDIR_SHIFT,32-ASM_PGDIR_SHIFT,\index
-  # else
-	extru		\va,31-ASM_PGDIR_SHIFT,ASM_BITS_PER_PGD,\index
-  # endif
-# endif
+	extru_safe	\va,31-ASM_PGDIR_SHIFT,ASM_BITS_PER_PGD,\index
 #endif
 	dep             %r0,31,PAGE_SHIFT,\pmd  /* clear offset */
 #if CONFIG_PGTABLE_LEVELS < 3
@@ -386,7 +378,7 @@
 	bb,>=,n		\pmd,_PxD_PRESENT_BIT,\fault
 	dep		%r0,31,PxD_FLAG_SHIFT,\pmd /* clear flags */
 	SHLREG		\pmd,PxD_VALUE_SHIFT,\pmd
-	extru		\va,31-PAGE_SHIFT,ASM_BITS_PER_PTE,\index
+	extru_safe	\va,31-PAGE_SHIFT,ASM_BITS_PER_PTE,\index
 	dep		%r0,31,PAGE_SHIFT,\pmd  /* clear offset */
 	shladd		\index,BITS_PER_PTE_ENTRY,\pmd,\pmd /* pmd is now pte */
 	.endm
@@ -1805,7 +1797,7 @@ syscall_restore:
 
 	/* Are we being ptraced? */
 	LDREG	TASK_TI_FLAGS(%r1),%r19
-	ldi	_TIF_SYSCALL_TRACE_MASK,%r2
+	ldi	_TIF_SINGLESTEP|_TIF_BLOCKSTEP,%r2
 	and,COND(=)	%r19,%r2,%r0
 	b,n	syscall_restore_rfi
 
diff --git a/arch/parisc/kernel/signal.c b/arch/parisc/kernel/signal.c
index bbfe23c40c01..46b1050640b8 100644
--- a/arch/parisc/kernel/signal.c
+++ b/arch/parisc/kernel/signal.c
@@ -288,21 +288,22 @@ setup_rt_frame(struct ksignal *ksig, sigset_t *set, struct pt_regs *regs,
 	   already in userspace. The first words of tramp are used to
 	   save the previous sigrestartblock trampoline that might be
 	   on the stack. We start the sigreturn trampoline at 
-	   SIGRESTARTBLOCK_TRAMP. */
+	   SIGRESTARTBLOCK_TRAMP+X. */
 	err |= __put_user(in_syscall ? INSN_LDI_R25_1 : INSN_LDI_R25_0,
 			&frame->tramp[SIGRESTARTBLOCK_TRAMP+0]);
-	err |= __put_user(INSN_BLE_SR2_R0, 
+	err |= __put_user(INSN_LDI_R20, 
 			&frame->tramp[SIGRESTARTBLOCK_TRAMP+1]);
-	err |= __put_user(INSN_LDI_R20,
+	err |= __put_user(INSN_BLE_SR2_R0, 
 			&frame->tramp[SIGRESTARTBLOCK_TRAMP+2]);
+	err |= __put_user(INSN_NOP, &frame->tramp[SIGRESTARTBLOCK_TRAMP+3]);
 
-	start = (unsigned long) &frame->tramp[SIGRESTARTBLOCK_TRAMP+0];
-	end = (unsigned long) &frame->tramp[SIGRESTARTBLOCK_TRAMP+3];
+	start = (unsigned long) &frame->tramp[0];
+	end = (unsigned long) &frame->tramp[TRAMP_SIZE];
 	flush_user_dcache_range_asm(start, end);
 	flush_user_icache_range_asm(start, end);
 
 	/* TRAMP Words 0-4, Length 5 = SIGRESTARTBLOCK_TRAMP
-	 * TRAMP Words 5-7, Length 3 = SIGRETURN_TRAMP
+	 * TRAMP Words 5-9, Length 4 = SIGRETURN_TRAMP
 	 * So the SIGRETURN_TRAMP is at the end of SIGRESTARTBLOCK_TRAMP
 	 */
 	rp = (unsigned long) &frame->tramp[SIGRESTARTBLOCK_TRAMP];
diff --git a/arch/parisc/kernel/signal32.h b/arch/parisc/kernel/signal32.h
index a5bdbb5678b7..f166250f2d06 100644
--- a/arch/parisc/kernel/signal32.h
+++ b/arch/parisc/kernel/signal32.h
@@ -36,7 +36,7 @@ struct compat_regfile {
         compat_int_t rf_sar;
 };
 
-#define COMPAT_SIGRETURN_TRAMP 3
+#define COMPAT_SIGRETURN_TRAMP 4
 #define COMPAT_SIGRESTARTBLOCK_TRAMP 5
 #define COMPAT_TRAMP_SIZE (COMPAT_SIGRETURN_TRAMP + \
 				COMPAT_SIGRESTARTBLOCK_TRAMP)
diff --git a/arch/parisc/kernel/stacktrace.c b/arch/parisc/kernel/stacktrace.c
index 6b4ca91932cf..023834ef582e 100644
--- a/arch/parisc/kernel/stacktrace.c
+++ b/arch/parisc/kernel/stacktrace.c
@@ -8,6 +8,7 @@
  *
  *  TODO: Userspace stacktrace (CONFIG_USER_STACKTRACE_SUPPORT)
  */
+#include <linux/kernel.h>
 #include <linux/stacktrace.h>
 
 #include <asm/unwind.h>
diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S
index 4fb3b6a993bf..65c88ca7a7ac 100644
--- a/arch/parisc/kernel/syscall.S
+++ b/arch/parisc/kernel/syscall.S
@@ -472,7 +472,7 @@ lws_start:
 	extrd,u	%r1,PSW_W_BIT,1,%r1
 	/* sp must be aligned on 4, so deposit the W bit setting into
 	 * the bottom of sp temporarily */
-	or,ev	%r1,%r30,%r30
+	or,od	%r1,%r30,%r30
 
 	/* Clip LWS number to a 32-bit value for 32-bit processes */
 	depdi	0, 31, 32, %r20
@@ -566,7 +566,7 @@ lws_compare_and_swap:
 	ldo	R%lws_lock_start(%r20), %r28
 
 	/* Extract eight bits from r26 and hash lock (Bits 3-11) */
-	extru  %r26, 28, 8, %r20
+	extru_safe  %r26, 28, 8, %r20
 
 	/* Find lock to use, the hash is either one of 0 to
 	   15, multiplied by 16 (keep it 16-byte aligned)
@@ -751,7 +751,7 @@ cas2_lock_start:
 	ldo	R%lws_lock_start(%r20), %r28
 
 	/* Extract eight bits from r26 and hash lock (Bits 3-11) */
-	extru  %r26, 28, 8, %r20
+	extru_safe  %r26, 28, 8, %r20
 
 	/* Find lock to use, the hash is either one of 0 to
 	   15, multiplied by 16 (keep it 16-byte aligned)
diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl
index bf751e0732b7..358c00000755 100644
--- a/arch/parisc/kernel/syscalls/syscall.tbl
+++ b/arch/parisc/kernel/syscalls/syscall.tbl
@@ -446,3 +446,4 @@
 446	common	landlock_restrict_self		sys_landlock_restrict_self
 # 447 reserved for memfd_secret
 448	common	process_mrelease		sys_process_mrelease
+449	common	futex_waitv			sys_futex_waitv
diff --git a/arch/parisc/kernel/time.c b/arch/parisc/kernel/time.c
index 9fb1e794831b..061119a56fbe 100644
--- a/arch/parisc/kernel/time.c
+++ b/arch/parisc/kernel/time.c
@@ -249,30 +249,16 @@ void __init time_init(void)
 static int __init init_cr16_clocksource(void)
 {
 	/*
-	 * The cr16 interval timers are not syncronized across CPUs on
-	 * different sockets, so mark them unstable and lower rating on
-	 * multi-socket SMP systems.
+	 * The cr16 interval timers are not syncronized across CPUs, even if
+	 * they share the same socket.
 	 */
 	if (num_online_cpus() > 1 && !running_on_qemu) {
-		int cpu;
-		unsigned long cpu0_loc;
-		cpu0_loc = per_cpu(cpu_data, 0).cpu_loc;
-
-		for_each_online_cpu(cpu) {
-			if (cpu == 0)
-				continue;
-			if ((cpu0_loc != 0) &&
-			    (cpu0_loc == per_cpu(cpu_data, cpu).cpu_loc))
-				continue;
-
-			/* mark sched_clock unstable */
-			clear_sched_clock_stable();
-
-			clocksource_cr16.name = "cr16_unstable";
-			clocksource_cr16.flags = CLOCK_SOURCE_UNSTABLE;
-			clocksource_cr16.rating = 0;
-			break;
-		}
+		/* mark sched_clock unstable */
+		clear_sched_clock_stable();
+
+		clocksource_cr16.name = "cr16_unstable";
+		clocksource_cr16.flags = CLOCK_SOURCE_UNSTABLE;
+		clocksource_cr16.rating = 0;
 	}
 
 	/* register at clocksource framework */
diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c
index b11fb26ce299..892b7fc8f3c4 100644
--- a/arch/parisc/kernel/traps.c
+++ b/arch/parisc/kernel/traps.c
@@ -730,6 +730,8 @@ void notrace handle_interruption(int code, struct pt_regs *regs)
 			}
 			mmap_read_unlock(current->mm);
 		}
+		/* CPU could not fetch instruction, so clear stale IIR value. */
+		regs->iir = 0xbaadf00d;
 		fallthrough;
 	case 27: 
 		/* Data memory protection ID trap */
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 0e3640e14eb1..5fa68c2ef1f8 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -196,3 +196,6 @@ clean-files := vmlinux.lds
 # Force dependency (incbin is bad)
 $(obj)/vdso32_wrapper.o : $(obj)/vdso32/vdso32.so.dbg
 $(obj)/vdso64_wrapper.o : $(obj)/vdso64/vdso64.so.dbg
+
+# for cleaning
+subdir- += vdso32 vdso64
diff --git a/arch/powerpc/kernel/head_32.h b/arch/powerpc/kernel/head_32.h
index 6b1ec9e3541b..349c4a820231 100644
--- a/arch/powerpc/kernel/head_32.h
+++ b/arch/powerpc/kernel/head_32.h
@@ -202,11 +202,11 @@ vmap_stack_overflow:
 	mfspr	r1, SPRN_SPRG_THREAD
 	lwz	r1, TASK_CPU - THREAD(r1)
 	slwi	r1, r1, 3
-	addis	r1, r1, emergency_ctx@ha
+	addis	r1, r1, emergency_ctx-PAGE_OFFSET@ha
 #else
-	lis	r1, emergency_ctx@ha
+	lis	r1, emergency_ctx-PAGE_OFFSET@ha
 #endif
-	lwz	r1, emergency_ctx@l(r1)
+	lwz	r1, emergency_ctx-PAGE_OFFSET@l(r1)
 	addi	r1, r1, THREAD_SIZE - INT_FRAME_SIZE
 	EXCEPTION_PROLOG_2 0 vmap_stack_overflow
 	prepare_transfer_to_handler
diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index 2d596881b70e..0d073b9fd52c 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -733,6 +733,7 @@ _GLOBAL(mmu_pin_tlb)
 #ifdef CONFIG_PIN_TLB_DATA
 	LOAD_REG_IMMEDIATE(r6, PAGE_OFFSET)
 	LOAD_REG_IMMEDIATE(r7, MI_SVALID | MI_PS8MEG | _PMD_ACCESSED)
+	li	r8, 0
 #ifdef CONFIG_PIN_TLB_IMMR
 	li	r0, 3
 #else
@@ -741,26 +742,26 @@ _GLOBAL(mmu_pin_tlb)
 	mtctr	r0
 	cmpwi	r4, 0
 	beq	4f
-	LOAD_REG_IMMEDIATE(r8, 0xf0 | _PAGE_RO | _PAGE_SPS | _PAGE_SH | _PAGE_PRESENT)
 	LOAD_REG_ADDR(r9, _sinittext)
 
 2:	ori	r0, r6, MD_EVALID
+	ori	r12, r8, 0xf0 | _PAGE_RO | _PAGE_SPS | _PAGE_SH | _PAGE_PRESENT
 	mtspr	SPRN_MD_CTR, r5
 	mtspr	SPRN_MD_EPN, r0
 	mtspr	SPRN_MD_TWC, r7
-	mtspr	SPRN_MD_RPN, r8
+	mtspr	SPRN_MD_RPN, r12
 	addi	r5, r5, 0x100
 	addis	r6, r6, SZ_8M@h
 	addis	r8, r8, SZ_8M@h
 	cmplw	r6, r9
 	bdnzt	lt, 2b
-
-4:	LOAD_REG_IMMEDIATE(r8, 0xf0 | _PAGE_DIRTY | _PAGE_SPS | _PAGE_SH | _PAGE_PRESENT)
+4:
 2:	ori	r0, r6, MD_EVALID
+	ori	r12, r8, 0xf0 | _PAGE_DIRTY | _PAGE_SPS | _PAGE_SH | _PAGE_PRESENT
 	mtspr	SPRN_MD_CTR, r5
 	mtspr	SPRN_MD_EPN, r0
 	mtspr	SPRN_MD_TWC, r7
-	mtspr	SPRN_MD_RPN, r8
+	mtspr	SPRN_MD_RPN, r12
 	addi	r5, r5, 0x100
 	addis	r6, r6, SZ_8M@h
 	addis	r8, r8, SZ_8M@h
@@ -781,7 +782,7 @@ _GLOBAL(mmu_pin_tlb)
 #endif
 #if defined(CONFIG_PIN_TLB_IMMR) || defined(CONFIG_PIN_TLB_DATA)
 	lis	r0, (MD_RSV4I | MD_TWAM)@h
-	mtspr	SPRN_MI_CTR, r0
+	mtspr	SPRN_MD_CTR, r0
 #endif
 	mtspr	SPRN_SRR1, r10
 	mtspr	SPRN_SRR0, r11
diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c
index 6baa676e7cb6..5d77d3f5fbb5 100644
--- a/arch/powerpc/kernel/module_64.c
+++ b/arch/powerpc/kernel/module_64.c
@@ -422,11 +422,17 @@ static inline int create_stub(const Elf64_Shdr *sechdrs,
 			      const char *name)
 {
 	long reladdr;
+	func_desc_t desc;
+	int i;
 
 	if (is_mprofile_ftrace_call(name))
 		return create_ftrace_stub(entry, addr, me);
 
-	memcpy(entry->jump, ppc64_stub_insns, sizeof(ppc64_stub_insns));
+	for (i = 0; i < sizeof(ppc64_stub_insns) / sizeof(u32); i++) {
+		if (patch_instruction(&entry->jump[i],
+				      ppc_inst(ppc64_stub_insns[i])))
+			return 0;
+	}
 
 	/* Stub uses address relative to r2. */
 	reladdr = (unsigned long)entry - my_r2(sechdrs, me);
@@ -437,10 +443,24 @@ static inline int create_stub(const Elf64_Shdr *sechdrs,
 	}
 	pr_debug("Stub %p get data from reladdr %li\n", entry, reladdr);
 
-	entry->jump[0] |= PPC_HA(reladdr);
-	entry->jump[1] |= PPC_LO(reladdr);
-	entry->funcdata = func_desc(addr);
-	entry->magic = STUB_MAGIC;
+	if (patch_instruction(&entry->jump[0],
+			      ppc_inst(entry->jump[0] | PPC_HA(reladdr))))
+		return 0;
+
+	if (patch_instruction(&entry->jump[1],
+			  ppc_inst(entry->jump[1] | PPC_LO(reladdr))))
+		return 0;
+
+	// func_desc_t is 8 bytes if ABIv2, else 16 bytes
+	desc = func_desc(addr);
+	for (i = 0; i < sizeof(func_desc_t) / sizeof(u32); i++) {
+		if (patch_instruction(((u32 *)&entry->funcdata) + i,
+				      ppc_inst(((u32 *)(&desc))[i])))
+			return 0;
+	}
+
+	if (patch_instruction(&entry->magic, ppc_inst(STUB_MAGIC)))
+		return 0;
 
 	return 1;
 }
@@ -495,8 +515,11 @@ static int restore_r2(const char *name, u32 *instruction, struct module *me)
 			me->name, *instruction, instruction);
 		return 0;
 	}
+
 	/* ld r2,R2_STACK_OFFSET(r1) */
-	*instruction = PPC_INST_LD_TOC;
+	if (patch_instruction(instruction, ppc_inst(PPC_INST_LD_TOC)))
+		return 0;
+
 	return 1;
 }
 
@@ -636,9 +659,12 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 			}
 
 			/* Only replace bits 2 through 26 */
-			*(uint32_t *)location
-				= (*(uint32_t *)location & ~0x03fffffc)
+			value = (*(uint32_t *)location & ~0x03fffffc)
 				| (value & 0x03fffffc);
+
+			if (patch_instruction((u32 *)location, ppc_inst(value)))
+				return -EFAULT;
+
 			break;
 
 		case R_PPC64_REL64:
diff --git a/arch/powerpc/kernel/signal.h b/arch/powerpc/kernel/signal.h
index 1f07317964e4..618aeccdf691 100644
--- a/arch/powerpc/kernel/signal.h
+++ b/arch/powerpc/kernel/signal.h
@@ -25,8 +25,14 @@ static inline int __get_user_sigset(sigset_t *dst, const sigset_t __user *src)
 
 	return __get_user(dst->sig[0], (u64 __user *)&src->sig[0]);
 }
-#define unsafe_get_user_sigset(dst, src, label) \
-	unsafe_get_user((dst)->sig[0], (u64 __user *)&(src)->sig[0], label)
+#define unsafe_get_user_sigset(dst, src, label) do {			\
+	sigset_t *__dst = dst;						\
+	const sigset_t __user *__src = src;				\
+	int i;								\
+									\
+	for (i = 0; i < _NSIG_WORDS; i++)				\
+		unsafe_get_user(__dst->sig[i], &__src->sig[i], label);	\
+} while (0)
 
 #ifdef CONFIG_VSX
 extern unsigned long copy_vsx_to_user(void __user *to,
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index 00a9c9cd6d42..3e053e2fd6b6 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -1063,7 +1063,7 @@ SYSCALL_DEFINE3(swapcontext, struct ucontext __user *, old_ctx,
 	 * We kill the task with a SIGSEGV in this situation.
 	 */
 	if (do_setcontext(new_ctx, regs, 0)) {
-		force_fatal_sig(SIGSEGV);
+		force_exit_sig(SIGSEGV);
 		return -EFAULT;
 	}
 
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index ef518535d436..d1e1fc0acbea 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -704,7 +704,7 @@ SYSCALL_DEFINE3(swapcontext, struct ucontext __user *, old_ctx,
 	 */
 
 	if (__get_user_sigset(&set, &new_ctx->uc_sigmask)) {
-		force_fatal_sig(SIGSEGV);
+		force_exit_sig(SIGSEGV);
 		return -EFAULT;
 	}
 	set_current_blocked(&set);
@@ -713,7 +713,7 @@ SYSCALL_DEFINE3(swapcontext, struct ucontext __user *, old_ctx,
 		return -EFAULT;
 	if (__unsafe_restore_sigcontext(current, NULL, 0, &new_ctx->uc_mcontext)) {
 		user_read_access_end();
-		force_fatal_sig(SIGSEGV);
+		force_exit_sig(SIGSEGV);
 		return -EFAULT;
 	}
 	user_read_access_end();
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
index 7bef917cc84e..15109af9d075 100644
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -528,3 +528,4 @@
 446	common	landlock_restrict_self		sys_landlock_restrict_self
 # 447 reserved for memfd_secret
 448	common	process_mrelease		sys_process_mrelease
+449	common  futex_waitv                     sys_futex_waitv
diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c
index f9ea0e5357f9..3fa6d240bade 100644
--- a/arch/powerpc/kernel/watchdog.c
+++ b/arch/powerpc/kernel/watchdog.c
@@ -187,6 +187,12 @@ static void watchdog_smp_panic(int cpu, u64 tb)
 	if (sysctl_hardlockup_all_cpu_backtrace)
 		trigger_allbutself_cpu_backtrace();
 
+	/*
+	 * Force flush any remote buffers that might be stuck in IRQ context
+	 * and therefore could not run their irq_work.
+	 */
+	printk_trigger_flush();
+
 	if (hardlockup_panic)
 		nmi_panic(NULL, "Hard LOCKUP");
 
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index fcf4760a3a0e..70b7a8f97153 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -695,6 +695,7 @@ static void flush_guest_tlb(struct kvm *kvm)
 				       "r" (0) : "memory");
 		}
 		asm volatile("ptesync": : :"memory");
+		// POWER9 congruence-class TLBIEL leaves ERAT. Flush it now.
 		asm volatile(PPC_RADIX_INVALIDATE_ERAT_GUEST : : :"memory");
 	} else {
 		for (set = 0; set < kvm->arch.tlb_sets; ++set) {
@@ -705,7 +706,9 @@ static void flush_guest_tlb(struct kvm *kvm)
 			rb += PPC_BIT(51);	/* increment set number */
 		}
 		asm volatile("ptesync": : :"memory");
-		asm volatile(PPC_ISA_3_0_INVALIDATE_ERAT : : :"memory");
+		// POWER9 congruence-class TLBIEL leaves ERAT. Flush it now.
+		if (cpu_has_feature(CPU_FTR_ARCH_300))
+			asm volatile(PPC_ISA_3_0_INVALIDATE_ERAT : : :"memory");
 	}
 }
 
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index eb776d0c5d8e..32a4b4d412b9 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -2005,7 +2005,7 @@ hcall_real_table:
 	.globl	hcall_real_table_end
 hcall_real_table_end:
 
-_GLOBAL(kvmppc_h_set_xdabr)
+_GLOBAL_TOC(kvmppc_h_set_xdabr)
 EXPORT_SYMBOL_GPL(kvmppc_h_set_xdabr)
 	andi.	r0, r5, DABRX_USER | DABRX_KERNEL
 	beq	6f
@@ -2015,7 +2015,7 @@ EXPORT_SYMBOL_GPL(kvmppc_h_set_xdabr)
 6:	li	r3, H_PARAMETER
 	blr
 
-_GLOBAL(kvmppc_h_set_dabr)
+_GLOBAL_TOC(kvmppc_h_set_dabr)
 EXPORT_SYMBOL_GPL(kvmppc_h_set_dabr)
 	li	r5, DABRX_USER | DABRX_KERNEL
 3:
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 35e9cccdeef9..a72920f4f221 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -641,9 +641,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		 * implementations just count online CPUs.
 		 */
 		if (hv_enabled)
-			r = num_present_cpus();
+			r = min_t(unsigned int, num_present_cpus(), KVM_MAX_VCPUS);
 		else
-			r = num_online_cpus();
+			r = min_t(unsigned int, num_online_cpus(), KVM_MAX_VCPUS);
 		break;
 	case KVM_CAP_MAX_VCPUS:
 		r = KVM_MAX_VCPUS;
diff --git a/arch/powerpc/mm/nohash/kaslr_booke.c b/arch/powerpc/mm/nohash/kaslr_booke.c
index 8fc49b1b4a91..6ec978967da0 100644
--- a/arch/powerpc/mm/nohash/kaslr_booke.c
+++ b/arch/powerpc/mm/nohash/kaslr_booke.c
@@ -314,7 +314,7 @@ static unsigned long __init kaslr_choose_location(void *dt_ptr, phys_addr_t size
 		pr_warn("KASLR: No safe seed for randomizing the kernel base.\n");
 
 	ram = min_t(phys_addr_t, __max_low_memory, size);
-	ram = map_mem_in_cams(ram, CONFIG_LOWMEM_CAM_NUM, true, false);
+	ram = map_mem_in_cams(ram, CONFIG_LOWMEM_CAM_NUM, true, true);
 	linear_sz = min_t(unsigned long, ram, SZ_512M);
 
 	/* If the linear size is smaller than 64M, do not randmize */
diff --git a/arch/powerpc/mm/nohash/tlb.c b/arch/powerpc/mm/nohash/tlb.c
index 89353d4f5604..647bf454a0fa 100644
--- a/arch/powerpc/mm/nohash/tlb.c
+++ b/arch/powerpc/mm/nohash/tlb.c
@@ -645,7 +645,7 @@ static void early_init_this_mmu(void)
 
 		if (map)
 			linear_map_top = map_mem_in_cams(linear_map_top,
-							 num_cams, true, true);
+							 num_cams, false, true);
 	}
 #endif
 
@@ -766,7 +766,7 @@ void setup_initial_memory_limit(phys_addr_t first_memblock_base,
 		num_cams = (mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY) / 4;
 
 		linear_sz = map_mem_in_cams(first_memblock_size, num_cams,
-					    false, true);
+					    true, true);
 
 		ppc64_rma_size = min_t(u64, linear_sz, 0x40000000);
 	} else
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 6f14c8fb6359..59d3cfcd7887 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -376,9 +376,9 @@ static void initialize_form2_numa_distance_lookup_table(void)
 {
 	int i, j;
 	struct device_node *root;
-	const __u8 *numa_dist_table;
+	const __u8 *form2_distances;
 	const __be32 *numa_lookup_index;
-	int numa_dist_table_length;
+	int form2_distances_length;
 	int max_numa_index, distance_index;
 
 	if (firmware_has_feature(FW_FEATURE_OPAL))
@@ -392,45 +392,41 @@ static void initialize_form2_numa_distance_lookup_table(void)
 	max_numa_index = of_read_number(&numa_lookup_index[0], 1);
 
 	/* first element of the array is the size and is encode-int */
-	numa_dist_table = of_get_property(root, "ibm,numa-distance-table", NULL);
-	numa_dist_table_length = of_read_number((const __be32 *)&numa_dist_table[0], 1);
+	form2_distances = of_get_property(root, "ibm,numa-distance-table", NULL);
+	form2_distances_length = of_read_number((const __be32 *)&form2_distances[0], 1);
 	/* Skip the size which is encoded int */
-	numa_dist_table += sizeof(__be32);
+	form2_distances += sizeof(__be32);
 
-	pr_debug("numa_dist_table_len = %d, numa_dist_indexes_len = %d\n",
-		 numa_dist_table_length, max_numa_index);
+	pr_debug("form2_distances_len = %d, numa_dist_indexes_len = %d\n",
+		 form2_distances_length, max_numa_index);
 
 	for (i = 0; i < max_numa_index; i++)
 		/* +1 skip the max_numa_index in the property */
 		numa_id_index_table[i] = of_read_number(&numa_lookup_index[i + 1], 1);
 
 
-	if (numa_dist_table_length != max_numa_index * max_numa_index) {
+	if (form2_distances_length != max_numa_index * max_numa_index) {
 		WARN(1, "Wrong NUMA distance information\n");
-		/* consider everybody else just remote. */
-		for (i = 0;  i < max_numa_index; i++) {
-			for (j = 0; j < max_numa_index; j++) {
-				int nodeA = numa_id_index_table[i];
-				int nodeB = numa_id_index_table[j];
-
-				if (nodeA == nodeB)
-					numa_distance_table[nodeA][nodeB] = LOCAL_DISTANCE;
-				else
-					numa_distance_table[nodeA][nodeB] = REMOTE_DISTANCE;
-			}
-		}
+		form2_distances = NULL; // don't use it
 	}
-
 	distance_index = 0;
 	for (i = 0;  i < max_numa_index; i++) {
 		for (j = 0; j < max_numa_index; j++) {
 			int nodeA = numa_id_index_table[i];
 			int nodeB = numa_id_index_table[j];
-
-			numa_distance_table[nodeA][nodeB] = numa_dist_table[distance_index++];
-			pr_debug("dist[%d][%d]=%d ", nodeA, nodeB, numa_distance_table[nodeA][nodeB]);
+			int dist;
+
+			if (form2_distances)
+				dist = form2_distances[distance_index++];
+			else if (nodeA == nodeB)
+				dist = LOCAL_DISTANCE;
+			else
+				dist = REMOTE_DISTANCE;
+			numa_distance_table[nodeA][nodeB] = dist;
+			pr_debug("dist[%d][%d]=%d ", nodeA, nodeB, dist);
 		}
 	}
+
 	of_node_put(root);
 }
 
diff --git a/arch/powerpc/mm/ptdump/ptdump.c b/arch/powerpc/mm/ptdump/ptdump.c
index bf251191e78d..32bfb215c485 100644
--- a/arch/powerpc/mm/ptdump/ptdump.c
+++ b/arch/powerpc/mm/ptdump/ptdump.c
@@ -183,7 +183,7 @@ static void note_prot_wx(struct pg_state *st, unsigned long addr)
 {
 	pte_t pte = __pte(st->current_flags);
 
-	if (!IS_ENABLED(CONFIG_PPC_DEBUG_WX) || !st->check_wx)
+	if (!IS_ENABLED(CONFIG_DEBUG_WX) || !st->check_wx)
 		return;
 
 	if (!pte_write(pte) || !pte_exec(pte))
diff --git a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c
index bb789f33c70e..a38372f9ac12 100644
--- a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c
+++ b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c
@@ -186,7 +186,6 @@ err:
 static int mcu_remove(struct i2c_client *client)
 {
 	struct mcu *mcu = i2c_get_clientdata(client);
-	int ret;
 
 	kthread_stop(shutdown_thread);
 
diff --git a/arch/powerpc/platforms/85xx/smp.c b/arch/powerpc/platforms/85xx/smp.c
index 83f4a6389a28..d7081e9af65c 100644
--- a/arch/powerpc/platforms/85xx/smp.c
+++ b/arch/powerpc/platforms/85xx/smp.c
@@ -220,7 +220,7 @@ static int smp_85xx_start_cpu(int cpu)
 	local_irq_save(flags);
 	hard_irq_disable();
 
-	if (qoriq_pm_ops)
+	if (qoriq_pm_ops && qoriq_pm_ops->cpu_up_prepare)
 		qoriq_pm_ops->cpu_up_prepare(cpu);
 
 	/* if cpu is not spinning, reset it */
@@ -292,7 +292,7 @@ static int smp_85xx_kick_cpu(int nr)
 		booting_thread_hwid = cpu_thread_in_core(nr);
 		primary = cpu_first_thread_sibling(nr);
 
-		if (qoriq_pm_ops)
+		if (qoriq_pm_ops && qoriq_pm_ops->cpu_up_prepare)
 			qoriq_pm_ops->cpu_up_prepare(nr);
 
 		/*
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 49b401536d29..8f998e55735b 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -1094,15 +1094,6 @@ static phys_addr_t ddw_memory_hotplug_max(void)
 	phys_addr_t max_addr = memory_hotplug_max();
 	struct device_node *memory;
 
-	/*
-	 * The "ibm,pmemory" can appear anywhere in the address space.
-	 * Assuming it is still backed by page structs, set the upper limit
-	 * for the huge DMA window as MAX_PHYSMEM_BITS.
-	 */
-	if (of_find_node_by_type(NULL, "ibm,pmemory"))
-		return (sizeof(phys_addr_t) * 8 <= MAX_PHYSMEM_BITS) ?
-			(phys_addr_t) -1 : (1ULL << MAX_PHYSMEM_BITS);
-
 	for_each_node_by_type(memory, "memory") {
 		unsigned long start, size;
 		int n_mem_addr_cells, n_mem_size_cells, len;
@@ -1238,7 +1229,6 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 	u32 ddw_avail[DDW_APPLICABLE_SIZE];
 	struct dma_win *window;
 	struct property *win64;
-	bool ddw_enabled = false;
 	struct failed_ddw_pdn *fpdn;
 	bool default_win_removed = false, direct_mapping = false;
 	bool pmem_present;
@@ -1253,7 +1243,6 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 
 	if (find_existing_ddw(pdn, &dev->dev.archdata.dma_offset, &len)) {
 		direct_mapping = (len >= max_ram_len);
-		ddw_enabled = true;
 		goto out_unlock;
 	}
 
@@ -1367,8 +1356,10 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 		len = order_base_2(query.largest_available_block << page_shift);
 		win_name = DMA64_PROPNAME;
 	} else {
-		direct_mapping = true;
-		win_name = DIRECT64_PROPNAME;
+		direct_mapping = !default_win_removed ||
+			(len == MAX_PHYSMEM_BITS) ||
+			(!pmem_present && (len == max_ram_len));
+		win_name = direct_mapping ? DIRECT64_PROPNAME : DMA64_PROPNAME;
 	}
 
 	ret = create_ddw(dev, ddw_avail, &create, page_shift, len);
@@ -1406,8 +1397,8 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 			dev_info(&dev->dev, "failed to map DMA window for %pOF: %d\n",
 				 dn, ret);
 
-		/* Make sure to clean DDW if any TCE was set*/
-		clean_dma_window(pdn, win64->value);
+			/* Make sure to clean DDW if any TCE was set*/
+			clean_dma_window(pdn, win64->value);
 			goto out_del_list;
 		}
 	} else {
@@ -1454,7 +1445,6 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 	spin_unlock(&dma_win_list_lock);
 
 	dev->dev.archdata.dma_offset = win_addr;
-	ddw_enabled = true;
 	goto out_unlock;
 
 out_del_list:
@@ -1490,10 +1480,10 @@ out_unlock:
 	 * as RAM, then we failed to create a window to cover persistent
 	 * memory and need to set the DMA limit.
 	 */
-	if (pmem_present && ddw_enabled && direct_mapping && len == max_ram_len)
+	if (pmem_present && direct_mapping && len == max_ram_len)
 		dev->dev.bus_dma_limit = dev->dev.archdata.dma_offset + (1ULL << len);
 
-    return ddw_enabled && direct_mapping;
+	return direct_mapping;
 }
 
 static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
diff --git a/arch/powerpc/sysdev/xive/Kconfig b/arch/powerpc/sysdev/xive/Kconfig
index 97796c6b63f0..785c292d104b 100644
--- a/arch/powerpc/sysdev/xive/Kconfig
+++ b/arch/powerpc/sysdev/xive/Kconfig
@@ -3,7 +3,6 @@ config PPC_XIVE
 	bool
 	select PPC_SMP_MUXED_IPI
 	select HARDIRQS_SW_RESEND
-	select IRQ_DOMAIN_NOMAP
 
 config PPC_XIVE_NATIVE
 	bool
diff --git a/arch/powerpc/sysdev/xive/common.c b/arch/powerpc/sysdev/xive/common.c
index c5d75c02ad8b..7b69299c2912 100644
--- a/arch/powerpc/sysdev/xive/common.c
+++ b/arch/powerpc/sysdev/xive/common.c
@@ -1443,8 +1443,7 @@ static const struct irq_domain_ops xive_irq_domain_ops = {
 
 static void __init xive_init_host(struct device_node *np)
 {
-	xive_irq_domain = irq_domain_add_nomap(np, XIVE_MAX_IRQ,
-					       &xive_irq_domain_ops, NULL);
+	xive_irq_domain = irq_domain_add_tree(np, &xive_irq_domain_ops, NULL);
 	if (WARN_ON(xive_irq_domain == NULL))
 		return;
 	irq_set_default_host(xive_irq_domain);
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index a34c531be4e7..821252b65f89 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -62,6 +62,7 @@ config RISCV
 	select GENERIC_SCHED_CLOCK
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_TIME_VSYSCALL if MMU && 64BIT
+	select GENERIC_VDSO_TIME_NS if HAVE_GENERIC_VDSO
 	select HAVE_ARCH_AUDITSYSCALL
 	select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL
 	select HAVE_ARCH_JUMP_LABEL_RELATIVE if !XIP_KERNEL
diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile
index 7f19b784e649..8a107ed18b0d 100644
--- a/arch/riscv/Makefile
+++ b/arch/riscv/Makefile
@@ -107,11 +107,13 @@ PHONY += vdso_install
 vdso_install:
 	$(Q)$(MAKE) $(build)=arch/riscv/kernel/vdso $@
 
+ifeq ($(KBUILD_EXTMOD),)
 ifeq ($(CONFIG_MMU),y)
 prepare: vdso_prepare
 vdso_prepare: prepare0
 	$(Q)$(MAKE) $(build)=arch/riscv/kernel/vdso include/generated/vdso-offsets.h
 endif
+endif
 
 ifneq ($(CONFIG_XIP_KERNEL),y)
 ifeq ($(CONFIG_RISCV_M_MODE)$(CONFIG_SOC_CANAAN),yy)
@@ -136,3 +138,13 @@ zinstall: install-image = Image.gz
 install zinstall:
 	$(CONFIG_SHELL) $(srctree)/$(boot)/install.sh $(KERNELRELEASE) \
 	$(boot)/$(install-image) System.map "$(INSTALL_PATH)"
+
+PHONY += rv32_randconfig
+rv32_randconfig:
+	$(Q)$(MAKE) KCONFIG_ALLCONFIG=$(srctree)/arch/riscv/configs/32-bit.config \
+		-f $(srctree)/Makefile randconfig
+
+PHONY += rv64_randconfig
+rv64_randconfig:
+	$(Q)$(MAKE) KCONFIG_ALLCONFIG=$(srctree)/arch/riscv/configs/64-bit.config \
+		-f $(srctree)/Makefile randconfig
diff --git a/arch/riscv/boot/dts/microchip/microchip-mpfs-icicle-kit.dts b/arch/riscv/boot/dts/microchip/microchip-mpfs-icicle-kit.dts
index b254c60589a1..fc1e5869df1b 100644
--- a/arch/riscv/boot/dts/microchip/microchip-mpfs-icicle-kit.dts
+++ b/arch/riscv/boot/dts/microchip/microchip-mpfs-icicle-kit.dts
@@ -9,10 +9,8 @@
 #define RTCCLK_FREQ		1000000
 
 / {
-	#address-cells = <2>;
-	#size-cells = <2>;
 	model = "Microchip PolarFire-SoC Icicle Kit";
-	compatible = "microchip,mpfs-icicle-kit";
+	compatible = "microchip,mpfs-icicle-kit", "microchip,mpfs";
 
 	aliases {
 		ethernet0 = &emac1;
@@ -35,9 +33,6 @@
 		reg = <0x0 0x80000000 0x0 0x40000000>;
 		clocks = <&clkcfg 26>;
 	};
-
-	soc {
-	};
 };
 
 &serial0 {
@@ -56,8 +51,17 @@
 	status = "okay";
 };
 
-&sdcard {
+&mmc {
 	status = "okay";
+
+	bus-width = <4>;
+	disable-wp;
+	cap-sd-highspeed;
+	card-detect-delay = <200>;
+	sd-uhs-sdr12;
+	sd-uhs-sdr25;
+	sd-uhs-sdr50;
+	sd-uhs-sdr104;
 };
 
 &emac0 {
diff --git a/arch/riscv/boot/dts/microchip/microchip-mpfs.dtsi b/arch/riscv/boot/dts/microchip/microchip-mpfs.dtsi
index 9d2fbbc1f777..c9f6d205d2ba 100644
--- a/arch/riscv/boot/dts/microchip/microchip-mpfs.dtsi
+++ b/arch/riscv/boot/dts/microchip/microchip-mpfs.dtsi
@@ -6,8 +6,8 @@
 / {
 	#address-cells = <2>;
 	#size-cells = <2>;
-	model = "Microchip MPFS Icicle Kit";
-	compatible = "microchip,mpfs-icicle-kit";
+	model = "Microchip PolarFire SoC";
+	compatible = "microchip,mpfs";
 
 	chosen {
 	};
@@ -161,7 +161,7 @@
 		};
 
 		clint@2000000 {
-			compatible = "sifive,clint0";
+			compatible = "sifive,fu540-c000-clint", "sifive,clint0";
 			reg = <0x0 0x2000000 0x0 0xC000>;
 			interrupts-extended = <&cpu0_intc 3 &cpu0_intc 7
 						&cpu1_intc 3 &cpu1_intc 7
@@ -172,7 +172,7 @@
 
 		plic: interrupt-controller@c000000 {
 			#interrupt-cells = <1>;
-			compatible = "sifive,plic-1.0.0";
+			compatible = "sifive,fu540-c000-plic", "sifive,plic-1.0.0";
 			reg = <0x0 0xc000000 0x0 0x4000000>;
 			riscv,ndev = <186>;
 			interrupt-controller;
@@ -262,39 +262,13 @@
 			status = "disabled";
 		};
 
-		emmc: mmc@20008000 {
-			compatible = "cdns,sd4hc";
+		/* Common node entry for emmc/sd */
+		mmc: mmc@20008000 {
+			compatible = "microchip,mpfs-sd4hc", "cdns,sd4hc";
 			reg = <0x0 0x20008000 0x0 0x1000>;
 			interrupt-parent = <&plic>;
 			interrupts = <88 89>;
-			pinctrl-names = "default";
 			clocks = <&clkcfg 6>;
-			bus-width = <4>;
-			cap-mmc-highspeed;
-			mmc-ddr-3_3v;
-			max-frequency = <200000000>;
-			non-removable;
-			no-sd;
-			no-sdio;
-			voltage-ranges = <3300 3300>;
-			status = "disabled";
-		};
-
-		sdcard: sdhc@20008000 {
-			compatible = "cdns,sd4hc";
-			reg = <0x0 0x20008000 0x0 0x1000>;
-			interrupt-parent = <&plic>;
-			interrupts = <88>;
-			pinctrl-names = "default";
-			clocks = <&clkcfg 6>;
-			bus-width = <4>;
-			disable-wp;
-			cap-sd-highspeed;
-			card-detect-delay = <200>;
-			sd-uhs-sdr12;
-			sd-uhs-sdr25;
-			sd-uhs-sdr50;
-			sd-uhs-sdr104;
 			max-frequency = <200000000>;
 			status = "disabled";
 		};
diff --git a/arch/riscv/boot/dts/sifive/fu540-c000.dtsi b/arch/riscv/boot/dts/sifive/fu540-c000.dtsi
index 7db861053483..0655b5c4201d 100644
--- a/arch/riscv/boot/dts/sifive/fu540-c000.dtsi
+++ b/arch/riscv/boot/dts/sifive/fu540-c000.dtsi
@@ -141,7 +141,7 @@
 		ranges;
 		plic0: interrupt-controller@c000000 {
 			#interrupt-cells = <1>;
-			compatible = "sifive,plic-1.0.0";
+			compatible = "sifive,fu540-c000-plic", "sifive,plic-1.0.0";
 			reg = <0x0 0xc000000 0x0 0x4000000>;
 			riscv,ndev = <53>;
 			interrupt-controller;
diff --git a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts
index 60846e88ae4b..ced0d4e47938 100644
--- a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts
+++ b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts
@@ -8,10 +8,9 @@
 #define RTCCLK_FREQ		1000000
 
 / {
-	#address-cells = <2>;
-	#size-cells = <2>;
 	model = "SiFive HiFive Unleashed A00";
-	compatible = "sifive,hifive-unleashed-a00", "sifive,fu540-c000";
+	compatible = "sifive,hifive-unleashed-a00", "sifive,fu540-c000",
+		     "sifive,fu540";
 
 	chosen {
 		stdout-path = "serial0";
@@ -26,9 +25,6 @@
 		reg = <0x0 0x80000000 0x2 0x00000000>;
 	};
 
-	soc {
-	};
-
 	hfclk: hfclk {
 		#clock-cells = <0>;
 		compatible = "fixed-clock";
@@ -63,7 +59,7 @@
 &qspi0 {
 	status = "okay";
 	flash@0 {
-		compatible = "issi,is25wp256", "jedec,spi-nor";
+		compatible = "jedec,spi-nor";
 		reg = <0>;
 		spi-max-frequency = <50000000>;
 		m25p,fast-read;
@@ -80,6 +76,7 @@
 		spi-max-frequency = <20000000>;
 		voltage-ranges = <3300 3300>;
 		disable-wp;
+		gpios = <&gpio 11 GPIO_ACTIVE_LOW>;
 	};
 };
 
diff --git a/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts b/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts
index 2e4ea84f27e7..6bfa1f24d3de 100644
--- a/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts
+++ b/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts
@@ -2,14 +2,13 @@
 /* Copyright (c) 2020 SiFive, Inc */
 
 #include "fu740-c000.dtsi"
+#include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/interrupt-controller/irq.h>
 
 /* Clock frequency (in Hz) of the PCB crystal for rtcclk */
 #define RTCCLK_FREQ		1000000
 
 / {
-	#address-cells = <2>;
-	#size-cells = <2>;
 	model = "SiFive HiFive Unmatched A00";
 	compatible = "sifive,hifive-unmatched-a00", "sifive,fu740-c000",
 		     "sifive,fu740";
@@ -27,9 +26,6 @@
 		reg = <0x0 0x80000000 0x4 0x00000000>;
 	};
 
-	soc {
-	};
-
 	hfclk: hfclk {
 		#clock-cells = <0>;
 		compatible = "fixed-clock";
@@ -59,10 +55,21 @@
 	temperature-sensor@4c {
 		compatible = "ti,tmp451";
 		reg = <0x4c>;
+		vcc-supply = <&vdd_bpro>;
 		interrupt-parent = <&gpio>;
 		interrupts = <6 IRQ_TYPE_LEVEL_LOW>;
 	};
 
+	eeprom@54 {
+		compatible = "microchip,24c02", "atmel,24c02";
+		reg = <0x54>;
+		vcc-supply = <&vdd_bpro>;
+		label = "board-id";
+		pagesize = <16>;
+		read-only;
+		size = <256>;
+	};
+
 	pmic@58 {
 		compatible = "dlg,da9063";
 		reg = <0x58>;
@@ -70,48 +77,44 @@
 		interrupts = <1 IRQ_TYPE_LEVEL_LOW>;
 		interrupt-controller;
 
-		regulators {
-			vdd_bcore1: bcore1 {
-				regulator-min-microvolt = <900000>;
-				regulator-max-microvolt = <900000>;
-				regulator-min-microamp = <5000000>;
-				regulator-max-microamp = <5000000>;
-				regulator-always-on;
-			};
+		onkey {
+			compatible = "dlg,da9063-onkey";
+		};
+
+		rtc {
+			compatible = "dlg,da9063-rtc";
+		};
 
-			vdd_bcore2: bcore2 {
-				regulator-min-microvolt = <900000>;
-				regulator-max-microvolt = <900000>;
-				regulator-min-microamp = <5000000>;
-				regulator-max-microamp = <5000000>;
+		wdt {
+			compatible = "dlg,da9063-watchdog";
+		};
+
+		regulators {
+			vdd_bcore: bcores-merged {
+				regulator-min-microvolt = <1050000>;
+				regulator-max-microvolt = <1050000>;
+				regulator-min-microamp = <4800000>;
+				regulator-max-microamp = <4800000>;
 				regulator-always-on;
 			};
 
 			vdd_bpro: bpro {
 				regulator-min-microvolt = <1800000>;
 				regulator-max-microvolt = <1800000>;
-				regulator-min-microamp = <2500000>;
-				regulator-max-microamp = <2500000>;
+				regulator-min-microamp = <2400000>;
+				regulator-max-microamp = <2400000>;
 				regulator-always-on;
 			};
 
 			vdd_bperi: bperi {
-				regulator-min-microvolt = <1050000>;
-				regulator-max-microvolt = <1050000>;
+				regulator-min-microvolt = <1060000>;
+				regulator-max-microvolt = <1060000>;
 				regulator-min-microamp = <1500000>;
 				regulator-max-microamp = <1500000>;
 				regulator-always-on;
 			};
 
-			vdd_bmem: bmem {
-				regulator-min-microvolt = <1200000>;
-				regulator-max-microvolt = <1200000>;
-				regulator-min-microamp = <3000000>;
-				regulator-max-microamp = <3000000>;
-				regulator-always-on;
-			};
-
-			vdd_bio: bio {
+			vdd_bmem_bio: bmem-bio-merged {
 				regulator-min-microvolt = <1200000>;
 				regulator-max-microvolt = <1200000>;
 				regulator-min-microamp = <3000000>;
@@ -122,86 +125,66 @@
 			vdd_ldo1: ldo1 {
 				regulator-min-microvolt = <1800000>;
 				regulator-max-microvolt = <1800000>;
-				regulator-min-microamp = <100000>;
-				regulator-max-microamp = <100000>;
 				regulator-always-on;
 			};
 
 			vdd_ldo2: ldo2 {
 				regulator-min-microvolt = <1800000>;
 				regulator-max-microvolt = <1800000>;
-				regulator-min-microamp = <200000>;
-				regulator-max-microamp = <200000>;
 				regulator-always-on;
 			};
 
 			vdd_ldo3: ldo3 {
-				regulator-min-microvolt = <1800000>;
-				regulator-max-microvolt = <1800000>;
-				regulator-min-microamp = <200000>;
-				regulator-max-microamp = <200000>;
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
 				regulator-always-on;
 			};
 
 			vdd_ldo4: ldo4 {
-				regulator-min-microvolt = <1800000>;
-				regulator-max-microvolt = <1800000>;
-				regulator-min-microamp = <200000>;
-				regulator-max-microamp = <200000>;
+				regulator-min-microvolt = <2500000>;
+				regulator-max-microvolt = <2500000>;
 				regulator-always-on;
 			};
 
 			vdd_ldo5: ldo5 {
-				regulator-min-microvolt = <1800000>;
-				regulator-max-microvolt = <1800000>;
-				regulator-min-microamp = <100000>;
-				regulator-max-microamp = <100000>;
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
 				regulator-always-on;
 			};
 
 			vdd_ldo6: ldo6 {
-				regulator-min-microvolt = <3300000>;
-				regulator-max-microvolt = <3300000>;
-				regulator-min-microamp = <200000>;
-				regulator-max-microamp = <200000>;
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <1800000>;
 				regulator-always-on;
 			};
 
 			vdd_ldo7: ldo7 {
-				regulator-min-microvolt = <1800000>;
-				regulator-max-microvolt = <1800000>;
-				regulator-min-microamp = <200000>;
-				regulator-max-microamp = <200000>;
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
 				regulator-always-on;
 			};
 
 			vdd_ldo8: ldo8 {
-				regulator-min-microvolt = <1800000>;
-				regulator-max-microvolt = <1800000>;
-				regulator-min-microamp = <200000>;
-				regulator-max-microamp = <200000>;
+				regulator-min-microvolt = <3300000>;
+				regulator-max-microvolt = <3300000>;
 				regulator-always-on;
 			};
 
 			vdd_ld09: ldo9 {
 				regulator-min-microvolt = <1050000>;
 				regulator-max-microvolt = <1050000>;
-				regulator-min-microamp = <200000>;
-				regulator-max-microamp = <200000>;
+				regulator-always-on;
 			};
 
 			vdd_ldo10: ldo10 {
 				regulator-min-microvolt = <1000000>;
 				regulator-max-microvolt = <1000000>;
-				regulator-min-microamp = <300000>;
-				regulator-max-microamp = <300000>;
+				regulator-always-on;
 			};
 
 			vdd_ldo11: ldo11 {
 				regulator-min-microvolt = <2500000>;
 				regulator-max-microvolt = <2500000>;
-				regulator-min-microamp = <300000>;
-				regulator-max-microamp = <300000>;
 				regulator-always-on;
 			};
 		};
@@ -211,7 +194,7 @@
 &qspi0 {
 	status = "okay";
 	flash@0 {
-		compatible = "issi,is25wp256", "jedec,spi-nor";
+		compatible = "jedec,spi-nor";
 		reg = <0>;
 		spi-max-frequency = <50000000>;
 		m25p,fast-read;
@@ -228,6 +211,7 @@
 		spi-max-frequency = <20000000>;
 		voltage-ranges = <3300 3300>;
 		disable-wp;
+		gpios = <&gpio 15 GPIO_ACTIVE_LOW>;
 	};
 };
 
@@ -250,4 +234,8 @@
 
 &gpio {
 	status = "okay";
+	gpio-line-names = "J29.1", "PMICNTB", "PMICSHDN", "J8.1", "J8.3",
+		"PCIe_PWREN", "THERM", "UBRDG_RSTN", "PCIe_PERSTN",
+		"ULPI_RSTN", "J8.2", "UHUB_RSTN", "GEMGXL_RST", "J8.4",
+		"EN_VDD_SD", "SD_CD";
 };
diff --git a/arch/riscv/configs/32-bit.config b/arch/riscv/configs/32-bit.config
new file mode 100644
index 000000000000..43f41323b67e
--- /dev/null
+++ b/arch/riscv/configs/32-bit.config
@@ -0,0 +1,2 @@
+CONFIG_ARCH_RV32I=y
+CONFIG_32BIT=y
diff --git a/arch/riscv/configs/64-bit.config b/arch/riscv/configs/64-bit.config
new file mode 100644
index 000000000000..313edc554d84
--- /dev/null
+++ b/arch/riscv/configs/64-bit.config
@@ -0,0 +1,2 @@
+CONFIG_ARCH_RV64I=y
+CONFIG_64BIT=y
diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig
index 4ebc80315f01..ef473e2f503b 100644
--- a/arch/riscv/configs/defconfig
+++ b/arch/riscv/configs/defconfig
@@ -19,6 +19,8 @@ CONFIG_SOC_VIRT=y
 CONFIG_SOC_MICROCHIP_POLARFIRE=y
 CONFIG_SMP=y
 CONFIG_HOTPLUG_CPU=y
+CONFIG_VIRTUALIZATION=y
+CONFIG_KVM=m
 CONFIG_JUMP_LABEL=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
@@ -72,9 +74,10 @@ CONFIG_GPIOLIB=y
 CONFIG_GPIO_SIFIVE=y
 # CONFIG_PTP_1588_CLOCK is not set
 CONFIG_POWER_RESET=y
-CONFIG_DRM=y
-CONFIG_DRM_RADEON=y
-CONFIG_DRM_VIRTIO_GPU=y
+CONFIG_DRM=m
+CONFIG_DRM_RADEON=m
+CONFIG_DRM_NOUVEAU=m
+CONFIG_DRM_VIRTIO_GPU=m
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_USB=y
 CONFIG_USB_XHCI_HCD=y
diff --git a/arch/riscv/configs/rv32_defconfig b/arch/riscv/configs/rv32_defconfig
index 434ef5b64599..6e9f12ff968a 100644
--- a/arch/riscv/configs/rv32_defconfig
+++ b/arch/riscv/configs/rv32_defconfig
@@ -19,6 +19,8 @@ CONFIG_SOC_VIRT=y
 CONFIG_ARCH_RV32I=y
 CONFIG_SMP=y
 CONFIG_HOTPLUG_CPU=y
+CONFIG_VIRTUALIZATION=y
+CONFIG_KVM=m
 CONFIG_JUMP_LABEL=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
diff --git a/arch/riscv/include/asm/efi.h b/arch/riscv/include/asm/efi.h
index 49b398fe99f1..cc4f6787f937 100644
--- a/arch/riscv/include/asm/efi.h
+++ b/arch/riscv/include/asm/efi.h
@@ -13,7 +13,6 @@
 
 #ifdef CONFIG_EFI
 extern void efi_init(void);
-extern void efifb_setup_from_dmi(struct screen_info *si, const char *opt);
 #else
 #define efi_init()
 #endif
diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h
index 25ba21f98504..2639b9ee48f9 100644
--- a/arch/riscv/include/asm/kvm_host.h
+++ b/arch/riscv/include/asm/kvm_host.h
@@ -12,14 +12,12 @@
 #include <linux/types.h>
 #include <linux/kvm.h>
 #include <linux/kvm_types.h>
+#include <asm/csr.h>
 #include <asm/kvm_vcpu_fp.h>
 #include <asm/kvm_vcpu_timer.h>
 
-#ifdef CONFIG_64BIT
-#define KVM_MAX_VCPUS			(1U << 16)
-#else
-#define KVM_MAX_VCPUS			(1U << 9)
-#endif
+#define KVM_MAX_VCPUS			\
+	((HGATP_VMID_MASK >> HGATP_VMID_SHIFT) + 1)
 
 #define KVM_HALT_POLL_NS_DEFAULT	500000
 
diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h
index 109c97e991a6..b3e5ff0125fe 100644
--- a/arch/riscv/include/asm/page.h
+++ b/arch/riscv/include/asm/page.h
@@ -157,6 +157,8 @@ extern phys_addr_t __phys_addr_symbol(unsigned long x);
 #define page_to_bus(page)	(page_to_phys(page))
 #define phys_to_page(paddr)	(pfn_to_page(phys_to_pfn(paddr)))
 
+#define sym_to_pfn(x)           __phys_to_pfn(__pa_symbol(x))
+
 #ifdef CONFIG_FLATMEM
 #define pfn_valid(pfn) \
 	(((pfn) >= ARCH_PFN_OFFSET) && (((pfn) - ARCH_PFN_OFFSET) < max_mapnr))
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index 39b550310ec6..bf204e7c1f74 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -75,7 +75,8 @@
 #endif
 
 #ifdef CONFIG_XIP_KERNEL
-#define XIP_OFFSET		SZ_8M
+#define XIP_OFFSET		SZ_32M
+#define XIP_OFFSET_MASK		(SZ_32M - 1)
 #else
 #define XIP_OFFSET		0
 #endif
@@ -97,7 +98,8 @@
 #ifdef CONFIG_XIP_KERNEL
 #define XIP_FIXUP(addr) ({							\
 	uintptr_t __a = (uintptr_t)(addr);					\
-	(__a >= CONFIG_XIP_PHYS_ADDR && __a < CONFIG_XIP_PHYS_ADDR + SZ_16M) ?	\
+	(__a >= CONFIG_XIP_PHYS_ADDR && \
+	 __a < CONFIG_XIP_PHYS_ADDR + XIP_OFFSET * 2) ?	\
 		__a - CONFIG_XIP_PHYS_ADDR + CONFIG_PHYS_RAM_BASE - XIP_OFFSET :\
 		__a;								\
 	})
diff --git a/arch/riscv/include/asm/vdso.h b/arch/riscv/include/asm/vdso.h
index 208e31bc5d1c..bc6f75f3a199 100644
--- a/arch/riscv/include/asm/vdso.h
+++ b/arch/riscv/include/asm/vdso.h
@@ -8,30 +8,19 @@
 #ifndef _ASM_RISCV_VDSO_H
 #define _ASM_RISCV_VDSO_H
 
-
-/*
- * All systems with an MMU have a VDSO, but systems without an MMU don't
- * support shared libraries and therefor don't have one.
- */
-#ifdef CONFIG_MMU
-
-#include <linux/types.h>
 /*
  * All systems with an MMU have a VDSO, but systems without an MMU don't
  * support shared libraries and therefor don't have one.
  */
 #ifdef CONFIG_MMU
 
-#define __VVAR_PAGES    1
+#define __VVAR_PAGES    2
 
 #ifndef __ASSEMBLY__
 #include <generated/vdso-offsets.h>
 
 #define VDSO_SYMBOL(base, name)							\
 	(void __user *)((unsigned long)(base) + __vdso_##name##_offset)
-
-#endif /* CONFIG_MMU */
-
 #endif /* !__ASSEMBLY__ */
 
 #endif /* CONFIG_MMU */
diff --git a/arch/riscv/include/asm/vdso/gettimeofday.h b/arch/riscv/include/asm/vdso/gettimeofday.h
index f839f16e0d2a..77d9c2f721c4 100644
--- a/arch/riscv/include/asm/vdso/gettimeofday.h
+++ b/arch/riscv/include/asm/vdso/gettimeofday.h
@@ -76,6 +76,13 @@ static __always_inline const struct vdso_data *__arch_get_vdso_data(void)
 	return _vdso_data;
 }
 
+#ifdef CONFIG_TIME_NS
+static __always_inline
+const struct vdso_data *__arch_get_timens_vdso_data(const struct vdso_data *vd)
+{
+	return _timens_data;
+}
+#endif
 #endif /* !__ASSEMBLY__ */
 
 #endif /* __ASM_VDSO_GETTIMEOFDAY_H */
diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S
index 25ec50573957..f52f01ecbeea 100644
--- a/arch/riscv/kernel/head.S
+++ b/arch/riscv/kernel/head.S
@@ -20,10 +20,20 @@
 	REG_L t0, _xip_fixup
 	add \reg, \reg, t0
 .endm
+.macro XIP_FIXUP_FLASH_OFFSET reg
+	la t1, __data_loc
+	li t0, XIP_OFFSET_MASK
+	and t1, t1, t0
+	li t1, XIP_OFFSET
+	sub t0, t0, t1
+	sub \reg, \reg, t0
+.endm
 _xip_fixup: .dword CONFIG_PHYS_RAM_BASE - CONFIG_XIP_PHYS_ADDR - XIP_OFFSET
 #else
 .macro XIP_FIXUP_OFFSET reg
 .endm
+.macro XIP_FIXUP_FLASH_OFFSET reg
+.endm
 #endif /* CONFIG_XIP_KERNEL */
 
 __HEAD
@@ -267,6 +277,7 @@ pmp_done:
 	la a3, hart_lottery
 	mv a2, a3
 	XIP_FIXUP_OFFSET a2
+	XIP_FIXUP_FLASH_OFFSET a3
 	lw t1, (a3)
 	amoswap.w t0, t1, (a2)
 	/* first time here if hart_lottery in RAM is not set */
@@ -305,6 +316,7 @@ clear_bss_done:
 	XIP_FIXUP_OFFSET sp
 #ifdef CONFIG_BUILTIN_DTB
 	la a0, __dtb_start
+	XIP_FIXUP_OFFSET a0
 #else
 	mv a0, s1
 #endif /* CONFIG_BUILTIN_DTB */
diff --git a/arch/riscv/kernel/reset.c b/arch/riscv/kernel/reset.c
index ee5878d968cc..9c842c41684a 100644
--- a/arch/riscv/kernel/reset.c
+++ b/arch/riscv/kernel/reset.c
@@ -12,7 +12,7 @@ static void default_power_off(void)
 		wait_for_interrupt();
 }
 
-void (*pm_power_off)(void) = default_power_off;
+void (*pm_power_off)(void) = NULL;
 EXPORT_SYMBOL(pm_power_off);
 
 void machine_restart(char *cmd)
@@ -23,10 +23,16 @@ void machine_restart(char *cmd)
 
 void machine_halt(void)
 {
-	pm_power_off();
+	if (pm_power_off != NULL)
+		pm_power_off();
+	else
+		default_power_off();
 }
 
 void machine_power_off(void)
 {
-	pm_power_off();
+	if (pm_power_off != NULL)
+		pm_power_off();
+	else
+		default_power_off();
 }
diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c
index b70956d80408..a9436a65161a 100644
--- a/arch/riscv/kernel/vdso.c
+++ b/arch/riscv/kernel/vdso.c
@@ -13,6 +13,7 @@
 #include <linux/err.h>
 #include <asm/page.h>
 #include <asm/vdso.h>
+#include <linux/time_namespace.h>
 
 #ifdef CONFIG_GENERIC_TIME_VSYSCALL
 #include <vdso/datapage.h>
@@ -25,14 +26,12 @@ extern char vdso_start[], vdso_end[];
 
 enum vvar_pages {
 	VVAR_DATA_PAGE_OFFSET,
+	VVAR_TIMENS_PAGE_OFFSET,
 	VVAR_NR_PAGES,
 };
 
 #define VVAR_SIZE  (VVAR_NR_PAGES << PAGE_SHIFT)
 
-static unsigned int vdso_pages __ro_after_init;
-static struct page **vdso_pagelist __ro_after_init;
-
 /*
  * The vDSO data page.
  */
@@ -42,83 +41,228 @@ static union {
 } vdso_data_store __page_aligned_data;
 struct vdso_data *vdso_data = &vdso_data_store.data;
 
-static int __init vdso_init(void)
+struct __vdso_info {
+	const char *name;
+	const char *vdso_code_start;
+	const char *vdso_code_end;
+	unsigned long vdso_pages;
+	/* Data Mapping */
+	struct vm_special_mapping *dm;
+	/* Code Mapping */
+	struct vm_special_mapping *cm;
+};
+
+static struct __vdso_info vdso_info __ro_after_init = {
+	.name = "vdso",
+	.vdso_code_start = vdso_start,
+	.vdso_code_end = vdso_end,
+};
+
+static int vdso_mremap(const struct vm_special_mapping *sm,
+		       struct vm_area_struct *new_vma)
+{
+	current->mm->context.vdso = (void *)new_vma->vm_start;
+
+	return 0;
+}
+
+static int __init __vdso_init(void)
 {
 	unsigned int i;
+	struct page **vdso_pagelist;
+	unsigned long pfn;
 
-	vdso_pages = (vdso_end - vdso_start) >> PAGE_SHIFT;
-	vdso_pagelist =
-		kcalloc(vdso_pages + VVAR_NR_PAGES, sizeof(struct page *), GFP_KERNEL);
-	if (unlikely(vdso_pagelist == NULL)) {
-		pr_err("vdso: pagelist allocation failed\n");
-		return -ENOMEM;
+	if (memcmp(vdso_info.vdso_code_start, "\177ELF", 4)) {
+		pr_err("vDSO is not a valid ELF object!\n");
+		return -EINVAL;
 	}
 
-	for (i = 0; i < vdso_pages; i++) {
-		struct page *pg;
+	vdso_info.vdso_pages = (
+		vdso_info.vdso_code_end -
+		vdso_info.vdso_code_start) >>
+		PAGE_SHIFT;
+
+	vdso_pagelist = kcalloc(vdso_info.vdso_pages,
+				sizeof(struct page *),
+				GFP_KERNEL);
+	if (vdso_pagelist == NULL)
+		return -ENOMEM;
+
+	/* Grab the vDSO code pages. */
+	pfn = sym_to_pfn(vdso_info.vdso_code_start);
+
+	for (i = 0; i < vdso_info.vdso_pages; i++)
+		vdso_pagelist[i] = pfn_to_page(pfn + i);
+
+	vdso_info.cm->pages = vdso_pagelist;
+
+	return 0;
+}
+
+#ifdef CONFIG_TIME_NS
+struct vdso_data *arch_get_vdso_data(void *vvar_page)
+{
+	return (struct vdso_data *)(vvar_page);
+}
+
+/*
+ * The vvar mapping contains data for a specific time namespace, so when a task
+ * changes namespace we must unmap its vvar data for the old namespace.
+ * Subsequent faults will map in data for the new namespace.
+ *
+ * For more details see timens_setup_vdso_data().
+ */
+int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
+{
+	struct mm_struct *mm = task->mm;
+	struct vm_area_struct *vma;
+
+	mmap_read_lock(mm);
 
-		pg = virt_to_page(vdso_start + (i << PAGE_SHIFT));
-		vdso_pagelist[i] = pg;
+	for (vma = mm->mmap; vma; vma = vma->vm_next) {
+		unsigned long size = vma->vm_end - vma->vm_start;
+
+		if (vma_is_special_mapping(vma, vdso_info.dm))
+			zap_page_range(vma, vma->vm_start, size);
 	}
-	vdso_pagelist[i] = virt_to_page(vdso_data);
 
+	mmap_read_unlock(mm);
 	return 0;
 }
+
+static struct page *find_timens_vvar_page(struct vm_area_struct *vma)
+{
+	if (likely(vma->vm_mm == current->mm))
+		return current->nsproxy->time_ns->vvar_page;
+
+	/*
+	 * VM_PFNMAP | VM_IO protect .fault() handler from being called
+	 * through interfaces like /proc/$pid/mem or
+	 * process_vm_{readv,writev}() as long as there's no .access()
+	 * in special_mapping_vmops.
+	 * For more details check_vma_flags() and __access_remote_vm()
+	 */
+	WARN(1, "vvar_page accessed remotely");
+
+	return NULL;
+}
+#else
+static struct page *find_timens_vvar_page(struct vm_area_struct *vma)
+{
+	return NULL;
+}
+#endif
+
+static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
+			     struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	struct page *timens_page = find_timens_vvar_page(vma);
+	unsigned long pfn;
+
+	switch (vmf->pgoff) {
+	case VVAR_DATA_PAGE_OFFSET:
+		if (timens_page)
+			pfn = page_to_pfn(timens_page);
+		else
+			pfn = sym_to_pfn(vdso_data);
+		break;
+#ifdef CONFIG_TIME_NS
+	case VVAR_TIMENS_PAGE_OFFSET:
+		/*
+		 * If a task belongs to a time namespace then a namespace
+		 * specific VVAR is mapped with the VVAR_DATA_PAGE_OFFSET and
+		 * the real VVAR page is mapped with the VVAR_TIMENS_PAGE_OFFSET
+		 * offset.
+		 * See also the comment near timens_setup_vdso_data().
+		 */
+		if (!timens_page)
+			return VM_FAULT_SIGBUS;
+		pfn = sym_to_pfn(vdso_data);
+		break;
+#endif /* CONFIG_TIME_NS */
+	default:
+		return VM_FAULT_SIGBUS;
+	}
+
+	return vmf_insert_pfn(vma, vmf->address, pfn);
+}
+
+enum rv_vdso_map {
+	RV_VDSO_MAP_VVAR,
+	RV_VDSO_MAP_VDSO,
+};
+
+static struct vm_special_mapping rv_vdso_maps[] __ro_after_init = {
+	[RV_VDSO_MAP_VVAR] = {
+		.name   = "[vvar]",
+		.fault = vvar_fault,
+	},
+	[RV_VDSO_MAP_VDSO] = {
+		.name   = "[vdso]",
+		.mremap = vdso_mremap,
+	},
+};
+
+static int __init vdso_init(void)
+{
+	vdso_info.dm = &rv_vdso_maps[RV_VDSO_MAP_VVAR];
+	vdso_info.cm = &rv_vdso_maps[RV_VDSO_MAP_VDSO];
+
+	return __vdso_init();
+}
 arch_initcall(vdso_init);
 
-int arch_setup_additional_pages(struct linux_binprm *bprm,
-	int uses_interp)
+static int __setup_additional_pages(struct mm_struct *mm,
+				    struct linux_binprm *bprm,
+				    int uses_interp)
 {
-	struct mm_struct *mm = current->mm;
-	unsigned long vdso_base, vdso_len;
-	int ret;
+	unsigned long vdso_base, vdso_text_len, vdso_mapping_len;
+	void *ret;
 
 	BUILD_BUG_ON(VVAR_NR_PAGES != __VVAR_PAGES);
 
-	vdso_len = (vdso_pages + VVAR_NR_PAGES) << PAGE_SHIFT;
+	vdso_text_len = vdso_info.vdso_pages << PAGE_SHIFT;
+	/* Be sure to map the data page */
+	vdso_mapping_len = vdso_text_len + VVAR_SIZE;
 
-	if (mmap_write_lock_killable(mm))
-		return -EINTR;
-
-	vdso_base = get_unmapped_area(NULL, 0, vdso_len, 0, 0);
+	vdso_base = get_unmapped_area(NULL, 0, vdso_mapping_len, 0, 0);
 	if (IS_ERR_VALUE(vdso_base)) {
-		ret = vdso_base;
-		goto end;
+		ret = ERR_PTR(vdso_base);
+		goto up_fail;
 	}
 
-	mm->context.vdso = NULL;
-	ret = install_special_mapping(mm, vdso_base, VVAR_SIZE,
-		(VM_READ | VM_MAYREAD), &vdso_pagelist[vdso_pages]);
-	if (unlikely(ret))
-		goto end;
+	ret = _install_special_mapping(mm, vdso_base, VVAR_SIZE,
+		(VM_READ | VM_MAYREAD | VM_PFNMAP), vdso_info.dm);
+	if (IS_ERR(ret))
+		goto up_fail;
 
+	vdso_base += VVAR_SIZE;
+	mm->context.vdso = (void *)vdso_base;
 	ret =
-	   install_special_mapping(mm, vdso_base + VVAR_SIZE,
-		vdso_pages << PAGE_SHIFT,
+	   _install_special_mapping(mm, vdso_base, vdso_text_len,
 		(VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC),
-		vdso_pagelist);
+		vdso_info.cm);
 
-	if (unlikely(ret))
-		goto end;
+	if (IS_ERR(ret))
+		goto up_fail;
 
-	/*
-	 * Put vDSO base into mm struct. We need to do this before calling
-	 * install_special_mapping or the perf counter mmap tracking code
-	 * will fail to recognise it as a vDSO (since arch_vma_name fails).
-	 */
-	mm->context.vdso = (void *)vdso_base + VVAR_SIZE;
+	return 0;
 
-end:
-	mmap_write_unlock(mm);
-	return ret;
+up_fail:
+	mm->context.vdso = NULL;
+	return PTR_ERR(ret);
 }
 
-const char *arch_vma_name(struct vm_area_struct *vma)
+int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 {
-	if (vma->vm_mm && (vma->vm_start == (long)vma->vm_mm->context.vdso))
-		return "[vdso]";
-	if (vma->vm_mm && (vma->vm_start ==
-			   (long)vma->vm_mm->context.vdso - VVAR_SIZE))
-		return "[vdso_data]";
-	return NULL;
+	struct mm_struct *mm = current->mm;
+	int ret;
+
+	if (mmap_write_lock_killable(mm))
+		return -EINTR;
+
+	ret = __setup_additional_pages(mm, bprm, uses_interp);
+	mmap_write_unlock(mm);
+
+	return ret;
 }
diff --git a/arch/riscv/kernel/vdso/vdso.lds.S b/arch/riscv/kernel/vdso/vdso.lds.S
index e9111f700af0..01d94aae5bf5 100644
--- a/arch/riscv/kernel/vdso/vdso.lds.S
+++ b/arch/riscv/kernel/vdso/vdso.lds.S
@@ -10,6 +10,9 @@ OUTPUT_ARCH(riscv)
 SECTIONS
 {
 	PROVIDE(_vdso_data = . - __VVAR_PAGES * PAGE_SIZE);
+#ifdef CONFIG_TIME_NS
+	PROVIDE(_timens_data = _vdso_data + PAGE_SIZE);
+#endif
 	. = SIZEOF_HEADERS;
 
 	.hash		: { *(.hash) }			:text
diff --git a/arch/riscv/kernel/vmlinux-xip.lds.S b/arch/riscv/kernel/vmlinux-xip.lds.S
index 9c9f35091ef0..f5ed08262139 100644
--- a/arch/riscv/kernel/vmlinux-xip.lds.S
+++ b/arch/riscv/kernel/vmlinux-xip.lds.S
@@ -64,8 +64,11 @@ SECTIONS
 /*
  * From this point, stuff is considered writable and will be copied to RAM
  */
-	__data_loc = ALIGN(16);		/* location in file */
-	. = LOAD_OFFSET + XIP_OFFSET;	/* location in memory */
+	__data_loc = ALIGN(PAGE_SIZE);		/* location in file */
+	. = KERNEL_LINK_ADDR + XIP_OFFSET;	/* location in memory */
+
+#undef LOAD_OFFSET
+#define LOAD_OFFSET (KERNEL_LINK_ADDR + XIP_OFFSET - (__data_loc & XIP_OFFSET_MASK))
 
 	_sdata = .;			/* Start of data section */
 	_data = .;
@@ -96,7 +99,6 @@ SECTIONS
 		KEEP(*(__soc_builtin_dtb_table))
 		__soc_builtin_dtb_table_end = .;
 	}
-	PERCPU_SECTION(L1_CACHE_BYTES)
 
 	. = ALIGN(8);
 	.alternative : {
@@ -122,6 +124,8 @@ SECTIONS
 
 	BSS_SECTION(PAGE_SIZE, PAGE_SIZE, 0)
 
+	PERCPU_SECTION(L1_CACHE_BYTES)
+
 	.rel.dyn : AT(ADDR(.rel.dyn) - LOAD_OFFSET) {
 		*(.rel.dyn*)
 	}
diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c
index d81bae8eb55e..fc058ff5f4b6 100644
--- a/arch/riscv/kvm/mmu.c
+++ b/arch/riscv/kvm/mmu.c
@@ -453,6 +453,12 @@ void kvm_arch_flush_shadow_all(struct kvm *kvm)
 void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
 				   struct kvm_memory_slot *slot)
 {
+	gpa_t gpa = slot->base_gfn << PAGE_SHIFT;
+	phys_addr_t size = slot->npages << PAGE_SHIFT;
+
+	spin_lock(&kvm->mmu_lock);
+	stage2_unmap_range(kvm, gpa, size, false);
+	spin_unlock(&kvm->mmu_lock);
 }
 
 void kvm_arch_commit_memory_region(struct kvm *kvm,
diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c
index e3d3aed46184..fb84619df012 100644
--- a/arch/riscv/kvm/vcpu.c
+++ b/arch/riscv/kvm/vcpu.c
@@ -740,7 +740,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		 * Ensure we set mode to IN_GUEST_MODE after we disable
 		 * interrupts and before the final VCPU requests check.
 		 * See the comment in kvm_vcpu_exiting_guest_mode() and
-		 * Documentation/virtual/kvm/vcpu-requests.rst
+		 * Documentation/virt/kvm/vcpu-requests.rst
 		 */
 		vcpu->mode = IN_GUEST_MODE;
 
diff --git a/arch/riscv/kvm/vcpu_sbi.c b/arch/riscv/kvm/vcpu_sbi.c
index eb3c045edf11..3b0e703d22cf 100644
--- a/arch/riscv/kvm/vcpu_sbi.c
+++ b/arch/riscv/kvm/vcpu_sbi.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/**
+/*
  * Copyright (c) 2019 Western Digital Corporation or its affiliates.
  *
  * Authors:
diff --git a/arch/riscv/kvm/vm.c b/arch/riscv/kvm/vm.c
index 26399df15b63..fb18af34a4b5 100644
--- a/arch/riscv/kvm/vm.c
+++ b/arch/riscv/kvm/vm.c
@@ -74,7 +74,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		r = 1;
 		break;
 	case KVM_CAP_NR_VCPUS:
-		r = num_online_cpus();
+		r = min_t(unsigned int, num_online_cpus(), KVM_MAX_VCPUS);
 		break;
 	case KVM_CAP_MAX_VCPUS:
 		r = KVM_MAX_VCPUS;
diff --git a/arch/riscv/mm/context.c b/arch/riscv/mm/context.c
index ee3459cb6750..ea54cc0c9106 100644
--- a/arch/riscv/mm/context.c
+++ b/arch/riscv/mm/context.c
@@ -233,8 +233,10 @@ static int __init asids_init(void)
 	local_flush_tlb_all();
 
 	/* Pre-compute ASID details */
-	num_asids = 1 << asid_bits;
-	asid_mask = num_asids - 1;
+	if (asid_bits) {
+		num_asids = 1 << asid_bits;
+		asid_mask = num_asids - 1;
+	}
 
 	/*
 	 * Use ASID allocator only if number of HW ASIDs are
@@ -255,7 +257,7 @@ static int __init asids_init(void)
 		pr_info("ASID allocator using %lu bits (%lu entries)\n",
 			asid_bits, num_asids);
 	} else {
-		pr_info("ASID allocator disabled\n");
+		pr_info("ASID allocator disabled (%lu bits)\n", asid_bits);
 	}
 
 	return 0;
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index c0cddf0fc22d..24b2b8044602 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -41,7 +41,7 @@ phys_addr_t phys_ram_base __ro_after_init;
 EXPORT_SYMBOL(phys_ram_base);
 
 #ifdef CONFIG_XIP_KERNEL
-extern char _xiprom[], _exiprom[];
+extern char _xiprom[], _exiprom[], __data_loc;
 #endif
 
 unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]
@@ -454,10 +454,9 @@ static uintptr_t __init best_map_size(phys_addr_t base, phys_addr_t size)
 /* called from head.S with MMU off */
 asmlinkage void __init __copy_data(void)
 {
-	void *from = (void *)(&_sdata);
-	void *end = (void *)(&_end);
+	void *from = (void *)(&__data_loc);
 	void *to = (void *)CONFIG_PHYS_RAM_BASE;
-	size_t sz = (size_t)(end - from + 1);
+	size_t sz = (size_t)((uintptr_t)(&_end) - (uintptr_t)(&_sdata));
 
 	memcpy(to, from, sz);
 }
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 8857ec3b97eb..2a5bb4f29cfe 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -47,7 +47,7 @@ config ARCH_SUPPORTS_UPROBES
 config KASAN_SHADOW_OFFSET
 	hex
 	depends on KASAN
-	default 0x18000000000000
+	default 0x1C000000000000
 
 config S390
 	def_bool y
@@ -194,6 +194,7 @@ config S390
 	select HAVE_RELIABLE_STACKTRACE
 	select HAVE_RSEQ
 	select HAVE_SAMPLE_FTRACE_DIRECT
+	select HAVE_SAMPLE_FTRACE_DIRECT_MULTI
 	select HAVE_SOFTIRQ_ON_OWN_STACK
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_VIRT_CPU_ACCOUNTING
diff --git a/arch/s390/Makefile b/arch/s390/Makefile
index 69c45f600273..609e3697324b 100644
--- a/arch/s390/Makefile
+++ b/arch/s390/Makefile
@@ -77,10 +77,12 @@ KBUILD_AFLAGS_DECOMPRESSOR += $(aflags-y)
 KBUILD_CFLAGS_DECOMPRESSOR += $(cflags-y)
 
 ifneq ($(call cc-option,-mstack-size=8192 -mstack-guard=128),)
-cflags-$(CONFIG_CHECK_STACK) += -mstack-size=$(STACK_SIZE)
-ifeq ($(call cc-option,-mstack-size=8192),)
-cflags-$(CONFIG_CHECK_STACK) += -mstack-guard=$(CONFIG_STACK_GUARD)
-endif
+  CC_FLAGS_CHECK_STACK := -mstack-size=$(STACK_SIZE)
+  ifeq ($(call cc-option,-mstack-size=8192),)
+    CC_FLAGS_CHECK_STACK += -mstack-guard=$(CONFIG_STACK_GUARD)
+  endif
+  export CC_FLAGS_CHECK_STACK
+  cflags-$(CONFIG_CHECK_STACK) += $(CC_FLAGS_CHECK_STACK)
 endif
 
 ifdef CONFIG_EXPOLINE
diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c
index 7571dee72a0c..1aa11a8f57dd 100644
--- a/arch/s390/boot/startup.c
+++ b/arch/s390/boot/startup.c
@@ -149,82 +149,56 @@ static void setup_ident_map_size(unsigned long max_physmem_end)
 
 static void setup_kernel_memory_layout(void)
 {
-	bool vmalloc_size_verified = false;
-	unsigned long vmemmap_off;
-	unsigned long vspace_left;
+	unsigned long vmemmap_start;
 	unsigned long rte_size;
 	unsigned long pages;
-	unsigned long vmax;
 
 	pages = ident_map_size / PAGE_SIZE;
 	/* vmemmap contains a multiple of PAGES_PER_SECTION struct pages */
 	vmemmap_size = SECTION_ALIGN_UP(pages) * sizeof(struct page);
 
 	/* choose kernel address space layout: 4 or 3 levels. */
-	vmemmap_off = round_up(ident_map_size, _REGION3_SIZE);
+	vmemmap_start = round_up(ident_map_size, _REGION3_SIZE);
 	if (IS_ENABLED(CONFIG_KASAN) ||
 	    vmalloc_size > _REGION2_SIZE ||
-	    vmemmap_off + vmemmap_size + vmalloc_size + MODULES_LEN > _REGION2_SIZE)
-		vmax = _REGION1_SIZE;
-	else
-		vmax = _REGION2_SIZE;
-
-	/* keep vmemmap_off aligned to a top level region table entry */
-	rte_size = vmax == _REGION1_SIZE ? _REGION2_SIZE : _REGION3_SIZE;
-	MODULES_END = vmax;
-	if (is_prot_virt_host()) {
-		/*
-		 * forcing modules and vmalloc area under the ultravisor
-		 * secure storage limit, so that any vmalloc allocation
-		 * we do could be used to back secure guest storage.
-		 */
-		adjust_to_uv_max(&MODULES_END);
-	}
-
-#ifdef CONFIG_KASAN
-	if (MODULES_END < vmax) {
-		/* force vmalloc and modules below kasan shadow */
-		MODULES_END = min(MODULES_END, KASAN_SHADOW_START);
+	    vmemmap_start + vmemmap_size + vmalloc_size + MODULES_LEN >
+		    _REGION2_SIZE) {
+		MODULES_END = _REGION1_SIZE;
+		rte_size = _REGION2_SIZE;
 	} else {
-		/*
-		 * leave vmalloc and modules above kasan shadow but make
-		 * sure they don't overlap with it
-		 */
-		vmalloc_size = min(vmalloc_size, vmax - KASAN_SHADOW_END - MODULES_LEN);
-		vmalloc_size_verified = true;
-		vspace_left = KASAN_SHADOW_START;
+		MODULES_END = _REGION2_SIZE;
+		rte_size = _REGION3_SIZE;
 	}
+	/*
+	 * forcing modules and vmalloc area under the ultravisor
+	 * secure storage limit, so that any vmalloc allocation
+	 * we do could be used to back secure guest storage.
+	 */
+	adjust_to_uv_max(&MODULES_END);
+#ifdef CONFIG_KASAN
+	/* force vmalloc and modules below kasan shadow */
+	MODULES_END = min(MODULES_END, KASAN_SHADOW_START);
 #endif
 	MODULES_VADDR = MODULES_END - MODULES_LEN;
 	VMALLOC_END = MODULES_VADDR;
 
-	if (vmalloc_size_verified) {
-		VMALLOC_START = VMALLOC_END - vmalloc_size;
-	} else {
-		vmemmap_off = round_up(ident_map_size, rte_size);
-
-		if (vmemmap_off + vmemmap_size > VMALLOC_END ||
-		    vmalloc_size > VMALLOC_END - vmemmap_off - vmemmap_size) {
-			/*
-			 * allow vmalloc area to occupy up to 1/2 of
-			 * the rest virtual space left.
-			 */
-			vmalloc_size = min(vmalloc_size, VMALLOC_END / 2);
-		}
-		VMALLOC_START = VMALLOC_END - vmalloc_size;
-		vspace_left = VMALLOC_START;
-	}
+	/* allow vmalloc area to occupy up to about 1/2 of the rest virtual space left */
+	vmalloc_size = min(vmalloc_size, round_down(VMALLOC_END / 2, _REGION3_SIZE));
+	VMALLOC_START = VMALLOC_END - vmalloc_size;
 
-	pages = vspace_left / (PAGE_SIZE + sizeof(struct page));
+	/* split remaining virtual space between 1:1 mapping & vmemmap array */
+	pages = VMALLOC_START / (PAGE_SIZE + sizeof(struct page));
 	pages = SECTION_ALIGN_UP(pages);
-	vmemmap_off = round_up(vspace_left - pages * sizeof(struct page), rte_size);
-	/* keep vmemmap left most starting from a fresh region table entry */
-	vmemmap_off = min(vmemmap_off, round_up(ident_map_size, rte_size));
-	/* take care that identity map is lower then vmemmap */
-	ident_map_size = min(ident_map_size, vmemmap_off);
+	/* keep vmemmap_start aligned to a top level region table entry */
+	vmemmap_start = round_down(VMALLOC_START - pages * sizeof(struct page), rte_size);
+	/* vmemmap_start is the future VMEM_MAX_PHYS, make sure it is within MAX_PHYSMEM */
+	vmemmap_start = min(vmemmap_start, 1UL << MAX_PHYSMEM_BITS);
+	/* make sure identity map doesn't overlay with vmemmap */
+	ident_map_size = min(ident_map_size, vmemmap_start);
 	vmemmap_size = SECTION_ALIGN_UP(ident_map_size / PAGE_SIZE) * sizeof(struct page);
-	VMALLOC_START = max(vmemmap_off + vmemmap_size, VMALLOC_START);
-	vmemmap = (struct page *)vmemmap_off;
+	/* make sure vmemmap doesn't overlay with vmalloc area */
+	VMALLOC_START = max(vmemmap_start + vmemmap_size, VMALLOC_START);
+	vmemmap = (struct page *)vmemmap_start;
 }
 
 /*
diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig
index fd825097cf04..e45cc27716de 100644
--- a/arch/s390/configs/debug_defconfig
+++ b/arch/s390/configs/debug_defconfig
@@ -117,6 +117,7 @@ CONFIG_UNIX=y
 CONFIG_UNIX_DIAG=m
 CONFIG_XFRM_USER=m
 CONFIG_NET_KEY=m
+CONFIG_NET_SWITCHDEV=y
 CONFIG_SMC=m
 CONFIG_SMC_DIAG=m
 CONFIG_INET=y
@@ -403,7 +404,6 @@ CONFIG_DEVTMPFS=y
 CONFIG_CONNECTOR=y
 CONFIG_ZRAM=y
 CONFIG_BLK_DEV_LOOP=m
-CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_DRBD=m
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
@@ -476,6 +476,7 @@ CONFIG_MACVLAN=m
 CONFIG_MACVTAP=m
 CONFIG_VXLAN=m
 CONFIG_BAREUDP=m
+CONFIG_AMT=m
 CONFIG_TUN=m
 CONFIG_VETH=m
 CONFIG_VIRTIO_NET=m
@@ -489,6 +490,7 @@ CONFIG_NLMON=m
 # CONFIG_NET_VENDOR_AMD is not set
 # CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_VENDOR_ASIX is not set
 # CONFIG_NET_VENDOR_ATHEROS is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
 # CONFIG_NET_VENDOR_BROCADE is not set
@@ -510,6 +512,7 @@ CONFIG_NLMON=m
 CONFIG_MLX4_EN=m
 CONFIG_MLX5_CORE=m
 CONFIG_MLX5_CORE_EN=y
+CONFIG_MLX5_ESWITCH=y
 # CONFIG_NET_VENDOR_MICREL is not set
 # CONFIG_NET_VENDOR_MICROCHIP is not set
 # CONFIG_NET_VENDOR_MICROSEMI is not set
@@ -571,6 +574,7 @@ CONFIG_WATCHDOG=y
 CONFIG_WATCHDOG_NOWAYOUT=y
 CONFIG_SOFT_WATCHDOG=m
 CONFIG_DIAG288_WATCHDOG=m
+# CONFIG_DRM_DEBUG_MODESET_LOCK is not set
 CONFIG_FB=y
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y
@@ -775,12 +779,14 @@ CONFIG_CRC4=m
 CONFIG_CRC7=m
 CONFIG_CRC8=m
 CONFIG_RANDOM32_SELFTEST=y
+CONFIG_XZ_DEC_MICROLZMA=y
 CONFIG_DMA_CMA=y
 CONFIG_CMA_SIZE_MBYTES=0
 CONFIG_PRINTK_TIME=y
 CONFIG_DYNAMIC_DEBUG=y
 CONFIG_DEBUG_INFO=y
 CONFIG_DEBUG_INFO_DWARF4=y
+CONFIG_DEBUG_INFO_BTF=y
 CONFIG_GDB_SCRIPTS=y
 CONFIG_HEADERS_INSTALL=y
 CONFIG_DEBUG_SECTION_MISMATCH=y
@@ -807,6 +813,7 @@ CONFIG_DEBUG_MEMORY_INIT=y
 CONFIG_MEMORY_NOTIFIER_ERROR_INJECT=m
 CONFIG_DEBUG_PER_CPU_MAPS=y
 CONFIG_KFENCE=y
+CONFIG_KFENCE_STATIC_KEYS=y
 CONFIG_DEBUG_SHIRQ=y
 CONFIG_PANIC_ON_OOPS=y
 CONFIG_DETECT_HUNG_TASK=y
@@ -842,6 +849,7 @@ CONFIG_FTRACE_STARTUP_TEST=y
 CONFIG_SAMPLES=y
 CONFIG_SAMPLE_TRACE_PRINTK=m
 CONFIG_SAMPLE_FTRACE_DIRECT=m
+CONFIG_SAMPLE_FTRACE_DIRECT_MULTI=m
 CONFIG_DEBUG_ENTRY=y
 CONFIG_CIO_INJECT=y
 CONFIG_KUNIT=m
@@ -860,7 +868,7 @@ CONFIG_FAIL_FUNCTION=y
 CONFIG_FAULT_INJECTION_STACKTRACE_FILTER=y
 CONFIG_LKDTM=m
 CONFIG_TEST_MIN_HEAP=y
-CONFIG_KPROBES_SANITY_TEST=y
+CONFIG_KPROBES_SANITY_TEST=m
 CONFIG_RBTREE_TEST=y
 CONFIG_INTERVAL_TREE_TEST=m
 CONFIG_PERCPU_TEST=m
diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig
index c9c3cedff2d8..1c750bfca2d8 100644
--- a/arch/s390/configs/defconfig
+++ b/arch/s390/configs/defconfig
@@ -109,6 +109,7 @@ CONFIG_UNIX=y
 CONFIG_UNIX_DIAG=m
 CONFIG_XFRM_USER=m
 CONFIG_NET_KEY=m
+CONFIG_NET_SWITCHDEV=y
 CONFIG_SMC=m
 CONFIG_SMC_DIAG=m
 CONFIG_INET=y
@@ -394,7 +395,6 @@ CONFIG_DEVTMPFS=y
 CONFIG_CONNECTOR=y
 CONFIG_ZRAM=y
 CONFIG_BLK_DEV_LOOP=m
-CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_DRBD=m
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
@@ -467,6 +467,7 @@ CONFIG_MACVLAN=m
 CONFIG_MACVTAP=m
 CONFIG_VXLAN=m
 CONFIG_BAREUDP=m
+CONFIG_AMT=m
 CONFIG_TUN=m
 CONFIG_VETH=m
 CONFIG_VIRTIO_NET=m
@@ -480,6 +481,7 @@ CONFIG_NLMON=m
 # CONFIG_NET_VENDOR_AMD is not set
 # CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_VENDOR_ASIX is not set
 # CONFIG_NET_VENDOR_ATHEROS is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
 # CONFIG_NET_VENDOR_BROCADE is not set
@@ -501,6 +503,7 @@ CONFIG_NLMON=m
 CONFIG_MLX4_EN=m
 CONFIG_MLX5_CORE=m
 CONFIG_MLX5_CORE_EN=y
+CONFIG_MLX5_ESWITCH=y
 # CONFIG_NET_VENDOR_MICREL is not set
 # CONFIG_NET_VENDOR_MICROCHIP is not set
 # CONFIG_NET_VENDOR_MICROSEMI is not set
@@ -762,12 +765,14 @@ CONFIG_PRIME_NUMBERS=m
 CONFIG_CRC4=m
 CONFIG_CRC7=m
 CONFIG_CRC8=m
+CONFIG_XZ_DEC_MICROLZMA=y
 CONFIG_DMA_CMA=y
 CONFIG_CMA_SIZE_MBYTES=0
 CONFIG_PRINTK_TIME=y
 CONFIG_DYNAMIC_DEBUG=y
 CONFIG_DEBUG_INFO=y
 CONFIG_DEBUG_INFO_DWARF4=y
+CONFIG_DEBUG_INFO_BTF=y
 CONFIG_GDB_SCRIPTS=y
 CONFIG_DEBUG_SECTION_MISMATCH=y
 CONFIG_MAGIC_SYSRQ=y
@@ -792,9 +797,11 @@ CONFIG_HIST_TRIGGERS=y
 CONFIG_SAMPLES=y
 CONFIG_SAMPLE_TRACE_PRINTK=m
 CONFIG_SAMPLE_FTRACE_DIRECT=m
+CONFIG_SAMPLE_FTRACE_DIRECT_MULTI=m
 CONFIG_KUNIT=m
 CONFIG_KUNIT_DEBUGFS=y
 CONFIG_LKDTM=m
+CONFIG_KPROBES_SANITY_TEST=m
 CONFIG_PERCPU_TEST=m
 CONFIG_ATOMIC64_SELFTEST=y
 CONFIG_TEST_BPF=m
diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig
index aceccf3b9a88..eed3b9acfa71 100644
--- a/arch/s390/configs/zfcpdump_defconfig
+++ b/arch/s390/configs/zfcpdump_defconfig
@@ -65,9 +65,11 @@ CONFIG_ZFCP=y
 # CONFIG_NETWORK_FILESYSTEMS is not set
 CONFIG_LSM="yama,loadpin,safesetid,integrity"
 # CONFIG_ZLIB_DFLTCC is not set
+CONFIG_XZ_DEC_MICROLZMA=y
 CONFIG_PRINTK_TIME=y
 # CONFIG_SYMBOLIC_ERRNAME is not set
 CONFIG_DEBUG_INFO=y
+CONFIG_DEBUG_INFO_BTF=y
 CONFIG_DEBUG_FS=y
 CONFIG_DEBUG_KERNEL=y
 CONFIG_PANIC_ON_OOPS=y
diff --git a/arch/s390/include/asm/kexec.h b/arch/s390/include/asm/kexec.h
index ea398a05f643..7f3c9ac34bd8 100644
--- a/arch/s390/include/asm/kexec.h
+++ b/arch/s390/include/asm/kexec.h
@@ -74,6 +74,12 @@ void *kexec_file_add_components(struct kimage *image,
 int arch_kexec_do_relocs(int r_type, void *loc, unsigned long val,
 			 unsigned long addr);
 
+#define ARCH_HAS_KIMAGE_ARCH
+
+struct kimage_arch {
+	void *ipl_buf;
+};
+
 extern const struct kexec_file_ops s390_kexec_image_ops;
 extern const struct kexec_file_ops s390_kexec_elf_ops;
 
diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h
index 6b3c366af78e..90824be5ce9a 100644
--- a/arch/s390/include/asm/pci.h
+++ b/arch/s390/include/asm/pci.h
@@ -210,9 +210,11 @@ int zpci_deconfigure_device(struct zpci_dev *zdev);
 void zpci_device_reserved(struct zpci_dev *zdev);
 bool zpci_is_device_configured(struct zpci_dev *zdev);
 
+int zpci_hot_reset_device(struct zpci_dev *zdev);
 int zpci_register_ioat(struct zpci_dev *, u8, u64, u64, u64);
 int zpci_unregister_ioat(struct zpci_dev *, u8);
 void zpci_remove_reserved_devices(void);
+void zpci_update_fh(struct zpci_dev *zdev, u32 fh);
 
 /* CLP */
 int clp_setup_writeback_mio(void);
@@ -294,8 +296,10 @@ void zpci_debug_exit(void);
 void zpci_debug_init_device(struct zpci_dev *, const char *);
 void zpci_debug_exit_device(struct zpci_dev *);
 
-/* Error reporting */
+/* Error handling */
 int zpci_report_error(struct pci_dev *, struct zpci_report_error_header *);
+int zpci_clear_error_state(struct zpci_dev *zdev);
+int zpci_reset_load_store_blocked(struct zpci_dev *zdev);
 
 #ifdef CONFIG_NUMA
 
diff --git a/arch/s390/include/asm/pci_io.h b/arch/s390/include/asm/pci_io.h
index e4dc64cc9c55..287bb88f7698 100644
--- a/arch/s390/include/asm/pci_io.h
+++ b/arch/s390/include/asm/pci_io.h
@@ -14,12 +14,13 @@
 
 /* I/O Map */
 #define ZPCI_IOMAP_SHIFT		48
-#define ZPCI_IOMAP_ADDR_BASE		0x8000000000000000UL
+#define ZPCI_IOMAP_ADDR_SHIFT		62
+#define ZPCI_IOMAP_ADDR_BASE		(1UL << ZPCI_IOMAP_ADDR_SHIFT)
 #define ZPCI_IOMAP_ADDR_OFF_MASK	((1UL << ZPCI_IOMAP_SHIFT) - 1)
 #define ZPCI_IOMAP_MAX_ENTRIES							\
-	((ULONG_MAX - ZPCI_IOMAP_ADDR_BASE + 1) / (1UL << ZPCI_IOMAP_SHIFT))
+	(1UL << (ZPCI_IOMAP_ADDR_SHIFT - ZPCI_IOMAP_SHIFT))
 #define ZPCI_IOMAP_ADDR_IDX_MASK						\
-	(~ZPCI_IOMAP_ADDR_OFF_MASK - ZPCI_IOMAP_ADDR_BASE)
+	((ZPCI_IOMAP_ADDR_BASE - 1) & ~ZPCI_IOMAP_ADDR_OFF_MASK)
 
 struct zpci_iomap_entry {
 	u32 fh;
diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c
index d72a6df058d7..785d54c9350c 100644
--- a/arch/s390/kernel/crash_dump.c
+++ b/arch/s390/kernel/crash_dump.c
@@ -191,8 +191,8 @@ static int copy_oldmem_user(void __user *dst, void *src, size_t count)
 				return rc;
 		} else {
 			/* Check for swapped kdump oldmem areas */
-			if (oldmem_data.start && from - oldmem_data.size < oldmem_data.size) {
-				from -= oldmem_data.size;
+			if (oldmem_data.start && from - oldmem_data.start < oldmem_data.size) {
+				from -= oldmem_data.start;
 				len = min(count, oldmem_data.size - from);
 			} else if (oldmem_data.start && from < oldmem_data.size) {
 				len = min(count, oldmem_data.size - from);
diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c
index 5510c7d10ddc..21d62d8b6b9a 100644
--- a/arch/s390/kernel/ftrace.c
+++ b/arch/s390/kernel/ftrace.c
@@ -290,7 +290,6 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
 		return;
 
 	regs = ftrace_get_regs(fregs);
-	preempt_disable_notrace();
 	p = get_kprobe((kprobe_opcode_t *)ip);
 	if (unlikely(!p) || kprobe_disabled(p))
 		goto out;
@@ -318,7 +317,6 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
 	}
 	__this_cpu_write(current_kprobe, NULL);
 out:
-	preempt_enable_notrace();
 	ftrace_test_recursion_unlock(bit);
 }
 NOKPROBE_SYMBOL(kprobe_ftrace_handler);
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index e2cc35775b99..5ad1dde23dc5 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -2156,7 +2156,7 @@ void *ipl_report_finish(struct ipl_report *report)
 
 	buf = vzalloc(report->size);
 	if (!buf)
-		return ERR_PTR(-ENOMEM);
+		goto out;
 	ptr = buf;
 
 	memcpy(ptr, report->ipib, report->ipib->hdr.len);
@@ -2195,6 +2195,7 @@ void *ipl_report_finish(struct ipl_report *report)
 	}
 
 	BUG_ON(ptr > buf + report->size);
+out:
 	return buf;
 }
 
diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
index 0df83ecaa2e0..cb7099682340 100644
--- a/arch/s390/kernel/irq.c
+++ b/arch/s390/kernel/irq.c
@@ -138,7 +138,7 @@ void noinstr do_io_irq(struct pt_regs *regs)
 	struct pt_regs *old_regs = set_irq_regs(regs);
 	int from_idle;
 
-	irq_enter();
+	irq_enter_rcu();
 
 	if (user_mode(regs)) {
 		update_timer_sys();
@@ -158,7 +158,8 @@ void noinstr do_io_irq(struct pt_regs *regs)
 			do_irq_async(regs, IO_INTERRUPT);
 	} while (MACHINE_IS_LPAR && irq_pending(regs));
 
-	irq_exit();
+	irq_exit_rcu();
+
 	set_irq_regs(old_regs);
 	irqentry_exit(regs, state);
 
@@ -172,7 +173,7 @@ void noinstr do_ext_irq(struct pt_regs *regs)
 	struct pt_regs *old_regs = set_irq_regs(regs);
 	int from_idle;
 
-	irq_enter();
+	irq_enter_rcu();
 
 	if (user_mode(regs)) {
 		update_timer_sys();
@@ -190,7 +191,7 @@ void noinstr do_ext_irq(struct pt_regs *regs)
 
 	do_irq_async(regs, EXT_INTERRUPT);
 
-	irq_exit();
+	irq_exit_rcu();
 	set_irq_regs(old_regs);
 	irqentry_exit(regs, state);
 
diff --git a/arch/s390/kernel/machine_kexec_file.c b/arch/s390/kernel/machine_kexec_file.c
index 528edff085d9..8f43575a4dd3 100644
--- a/arch/s390/kernel/machine_kexec_file.c
+++ b/arch/s390/kernel/machine_kexec_file.c
@@ -7,11 +7,14 @@
  * Author(s): Philipp Rudo <prudo@linux.vnet.ibm.com>
  */
 
+#define pr_fmt(fmt)	"kexec: " fmt
+
 #include <linux/elf.h>
 #include <linux/errno.h>
 #include <linux/kexec.h>
 #include <linux/module_signature.h>
 #include <linux/verification.h>
+#include <linux/vmalloc.h>
 #include <asm/boot_data.h>
 #include <asm/ipl.h>
 #include <asm/setup.h>
@@ -170,6 +173,7 @@ static int kexec_file_add_ipl_report(struct kimage *image,
 	struct kexec_buf buf;
 	unsigned long addr;
 	void *ptr, *end;
+	int ret;
 
 	buf.image = image;
 
@@ -199,9 +203,13 @@ static int kexec_file_add_ipl_report(struct kimage *image,
 		ptr += len;
 	}
 
+	ret = -ENOMEM;
 	buf.buffer = ipl_report_finish(data->report);
+	if (!buf.buffer)
+		goto out;
 	buf.bufsz = data->report->size;
 	buf.memsz = buf.bufsz;
+	image->arch.ipl_buf = buf.buffer;
 
 	data->memsz += buf.memsz;
 
@@ -209,7 +217,9 @@ static int kexec_file_add_ipl_report(struct kimage *image,
 		data->kernel_buf + offsetof(struct lowcore, ipl_parmblock_ptr);
 	*lc_ipl_parmblock_ptr = (__u32)buf.mem;
 
-	return kexec_add_buffer(&buf);
+	ret = kexec_add_buffer(&buf);
+out:
+	return ret;
 }
 
 void *kexec_file_add_components(struct kimage *image,
@@ -282,8 +292,16 @@ int arch_kexec_apply_relocations_add(struct purgatory_info *pi,
 				     const Elf_Shdr *relsec,
 				     const Elf_Shdr *symtab)
 {
+	const char *strtab, *name, *shstrtab;
+	const Elf_Shdr *sechdrs;
 	Elf_Rela *relas;
 	int i, r_type;
+	int ret;
+
+	/* String & section header string table */
+	sechdrs = (void *)pi->ehdr + pi->ehdr->e_shoff;
+	strtab = (char *)pi->ehdr + sechdrs[symtab->sh_link].sh_offset;
+	shstrtab = (char *)pi->ehdr + sechdrs[pi->ehdr->e_shstrndx].sh_offset;
 
 	relas = (void *)pi->ehdr + relsec->sh_offset;
 
@@ -296,15 +314,27 @@ int arch_kexec_apply_relocations_add(struct purgatory_info *pi,
 		sym = (void *)pi->ehdr + symtab->sh_offset;
 		sym += ELF64_R_SYM(relas[i].r_info);
 
-		if (sym->st_shndx == SHN_UNDEF)
+		if (sym->st_name)
+			name = strtab + sym->st_name;
+		else
+			name = shstrtab + sechdrs[sym->st_shndx].sh_name;
+
+		if (sym->st_shndx == SHN_UNDEF) {
+			pr_err("Undefined symbol: %s\n", name);
 			return -ENOEXEC;
+		}
 
-		if (sym->st_shndx == SHN_COMMON)
+		if (sym->st_shndx == SHN_COMMON) {
+			pr_err("symbol '%s' in common section\n", name);
 			return -ENOEXEC;
+		}
 
 		if (sym->st_shndx >= pi->ehdr->e_shnum &&
-		    sym->st_shndx != SHN_ABS)
+		    sym->st_shndx != SHN_ABS) {
+			pr_err("Invalid section %d for symbol %s\n",
+			       sym->st_shndx, name);
 			return -ENOEXEC;
+		}
 
 		loc = pi->purgatory_buf;
 		loc += section->sh_offset;
@@ -318,7 +348,23 @@ int arch_kexec_apply_relocations_add(struct purgatory_info *pi,
 		addr = section->sh_addr + relas[i].r_offset;
 
 		r_type = ELF64_R_TYPE(relas[i].r_info);
-		arch_kexec_do_relocs(r_type, loc, val, addr);
+
+		if (r_type == R_390_PLT32DBL)
+			r_type = R_390_PC32DBL;
+
+		ret = arch_kexec_do_relocs(r_type, loc, val, addr);
+		if (ret) {
+			pr_err("Unknown rela relocation: %d\n", r_type);
+			return -ENOEXEC;
+		}
 	}
 	return 0;
 }
+
+int arch_kimage_file_post_load_cleanup(struct kimage *image)
+{
+	vfree(image->arch.ipl_buf);
+	image->arch.ipl_buf = NULL;
+
+	return kexec_image_post_load_cleanup_default(image);
+}
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index 6f431fa9e4d7..ee8707abdb6a 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -687,8 +687,10 @@ static void cpumf_pmu_stop(struct perf_event *event, int flags)
 						      false);
 			if (cfdiag_diffctr(cpuhw, event->hw.config_base))
 				cfdiag_push_sample(event, cpuhw);
-		} else
+		} else if (cpuhw->flags & PMU_F_RESERVED) {
+			/* Only update when PMU not hotplugged off */
 			hw_perf_event_update(event);
+		}
 		hwc->state |= PERF_HES_UPTODATE;
 	}
 }
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 40405f2304f1..225ab2d0a4c6 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -606,7 +606,7 @@ static void __init setup_resources(void)
 
 static void __init setup_memory_end(void)
 {
-	memblock_remove(ident_map_size, ULONG_MAX);
+	memblock_remove(ident_map_size, PHYS_ADDR_MAX - ident_map_size);
 	max_pfn = max_low_pfn = PFN_DOWN(ident_map_size);
 	pr_notice("The maximum memory size is %luMB\n", ident_map_size >> 20);
 }
@@ -638,14 +638,6 @@ static struct notifier_block kdump_mem_nb = {
 #endif
 
 /*
- * Make sure that the area above identity mapping is protected
- */
-static void __init reserve_above_ident_map(void)
-{
-	memblock_reserve(ident_map_size, ULONG_MAX);
-}
-
-/*
  * Reserve memory for kdump kernel to be loaded with kexec
  */
 static void __init reserve_crashkernel(void)
@@ -785,7 +777,6 @@ static void __init memblock_add_mem_detect_info(void)
 	}
 	memblock_set_bottom_up(false);
 	memblock_set_node(0, ULONG_MAX, &memblock.memory, 0);
-	memblock_dump_all();
 }
 
 /*
@@ -826,9 +817,6 @@ static void __init setup_memory(void)
 		storage_key_init_range(start, end);
 
 	psw_set_key(PAGE_DEFAULT_KEY);
-
-	/* Only cosmetics */
-	memblock_enforce_memory_limit(memblock_end_of_DRAM());
 }
 
 static void __init relocate_amode31_section(void)
@@ -999,24 +987,24 @@ void __init setup_arch(char **cmdline_p)
 	setup_control_program_code();
 
 	/* Do some memory reservations *before* memory is added to memblock */
-	reserve_above_ident_map();
 	reserve_kernel();
 	reserve_initrd();
 	reserve_certificate_list();
 	reserve_mem_detect_info();
+	memblock_set_current_limit(ident_map_size);
 	memblock_allow_resize();
 
 	/* Get information about *all* installed memory */
 	memblock_add_mem_detect_info();
 
 	free_mem_detect_info();
+	setup_memory_end();
+	memblock_dump_all();
+	setup_memory();
 
 	relocate_amode31_section();
 	setup_cr();
-
 	setup_uv();
-	setup_memory_end();
-	setup_memory();
 	dma_contiguous_reserve(ident_map_size);
 	vmcp_cma_reserve();
 	if (MACHINE_HAS_EDAT2)
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index df5261e5cfe1..ed9c5c2eafad 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -451,3 +451,4 @@
 446  common	landlock_restrict_self	sys_landlock_restrict_self	sys_landlock_restrict_self
 # 447 reserved for memfd_secret
 448  common	process_mrelease	sys_process_mrelease		sys_process_mrelease
+449  common	futex_waitv		sys_futex_waitv			sys_futex_waitv
diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c
index 035705c9f23e..2b780786fc68 100644
--- a/arch/s390/kernel/traps.c
+++ b/arch/s390/kernel/traps.c
@@ -84,7 +84,7 @@ static void default_trap_handler(struct pt_regs *regs)
 {
 	if (user_mode(regs)) {
 		report_user_fault(regs, SIGSEGV, 0);
-		force_fatal_sig(SIGSEGV);
+		force_exit_sig(SIGSEGV);
 	} else
 		die(regs, "Unknown program exception");
 }
diff --git a/arch/s390/kernel/vdso32/Makefile b/arch/s390/kernel/vdso32/Makefile
index e3e6ac5686df..245bddfe9bc0 100644
--- a/arch/s390/kernel/vdso32/Makefile
+++ b/arch/s390/kernel/vdso32/Makefile
@@ -22,7 +22,7 @@ KBUILD_AFLAGS_32 += -m31 -s
 KBUILD_CFLAGS_32 := $(filter-out -m64,$(KBUILD_CFLAGS))
 KBUILD_CFLAGS_32 += -m31 -fPIC -shared -fno-common -fno-builtin
 
-LDFLAGS_vdso32.so.dbg += -fPIC -shared -nostdlib -soname=linux-vdso32.so.1 \
+LDFLAGS_vdso32.so.dbg += -fPIC -shared -soname=linux-vdso32.so.1 \
 	--hash-style=both --build-id=sha1 -melf_s390 -T
 
 $(targets:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_32)
diff --git a/arch/s390/kernel/vdso64/Makefile b/arch/s390/kernel/vdso64/Makefile
index 6568de236701..9e2b95a222a9 100644
--- a/arch/s390/kernel/vdso64/Makefile
+++ b/arch/s390/kernel/vdso64/Makefile
@@ -8,8 +8,9 @@ ARCH_REL_TYPE_ABS += R_390_GOT|R_390_PLT
 include $(srctree)/lib/vdso/Makefile
 obj-vdso64 = vdso_user_wrapper.o note.o
 obj-cvdso64 = vdso64_generic.o getcpu.o
-CFLAGS_REMOVE_getcpu.o = -pg $(CC_FLAGS_FTRACE) $(CC_FLAGS_EXPOLINE)
-CFLAGS_REMOVE_vdso64_generic.o = -pg $(CC_FLAGS_FTRACE) $(CC_FLAGS_EXPOLINE)
+VDSO_CFLAGS_REMOVE := -pg $(CC_FLAGS_FTRACE) $(CC_FLAGS_EXPOLINE) $(CC_FLAGS_CHECK_STACK)
+CFLAGS_REMOVE_getcpu.o = $(VDSO_CFLAGS_REMOVE)
+CFLAGS_REMOVE_vdso64_generic.o = $(VDSO_CFLAGS_REMOVE)
 
 # Build rules
 
@@ -25,7 +26,7 @@ KBUILD_AFLAGS_64 += -m64 -s
 
 KBUILD_CFLAGS_64 := $(filter-out -m64,$(KBUILD_CFLAGS))
 KBUILD_CFLAGS_64 += -m64 -fPIC -shared -fno-common -fno-builtin
-ldflags-y := -fPIC -shared -nostdlib -soname=linux-vdso64.so.1 \
+ldflags-y := -fPIC -shared -soname=linux-vdso64.so.1 \
 	     --hash-style=both --build-id=sha1 -T
 
 $(targets:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_64)
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index c6257f625929..14a18ba5ff2c 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -585,6 +585,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 			r = KVM_MAX_VCPUS;
 		else if (sclp.has_esca && sclp.has_64bscao)
 			r = KVM_S390_ESCA_CPU_SLOTS;
+		if (ext == KVM_CAP_NR_VCPUS)
+			r = min_t(unsigned int, num_online_cpus(), r);
 		break;
 	case KVM_CAP_S390_COW:
 		r = MACHINE_HAS_ESOP;
diff --git a/arch/s390/lib/test_unwind.c b/arch/s390/lib/test_unwind.c
index cfc5f5557c06..bc7973359ae2 100644
--- a/arch/s390/lib/test_unwind.c
+++ b/arch/s390/lib/test_unwind.c
@@ -173,10 +173,11 @@ static noinline int unwindme_func4(struct unwindme *u)
 		}
 
 		/*
-		 * trigger specification exception
+		 * Trigger operation exception; use insn notation to bypass
+		 * llvm's integrated assembler sanity checks.
 		 */
 		asm volatile(
-			"	mvcl	%%r1,%%r1\n"
+			"	.insn	e,0x0000\n"	/* illegal opcode */
 			"0:	nopr	%%r7\n"
 			EX_TABLE(0b, 0b)
 			:);
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index 872d772b73d2..2f9b78fa82a5 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -481,6 +481,34 @@ static void zpci_free_iomap(struct zpci_dev *zdev, int entry)
 	spin_unlock(&zpci_iomap_lock);
 }
 
+static void zpci_do_update_iomap_fh(struct zpci_dev *zdev, u32 fh)
+{
+	int bar, idx;
+
+	spin_lock(&zpci_iomap_lock);
+	for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) {
+		if (!zdev->bars[bar].size)
+			continue;
+		idx = zdev->bars[bar].map_idx;
+		if (!zpci_iomap_start[idx].count)
+			continue;
+		WRITE_ONCE(zpci_iomap_start[idx].fh, zdev->fh);
+	}
+	spin_unlock(&zpci_iomap_lock);
+}
+
+void zpci_update_fh(struct zpci_dev *zdev, u32 fh)
+{
+	if (!fh || zdev->fh == fh)
+		return;
+
+	zdev->fh = fh;
+	if (zpci_use_mio(zdev))
+		return;
+	if (zdev->has_resources && zdev_enabled(zdev))
+		zpci_do_update_iomap_fh(zdev, fh);
+}
+
 static struct resource *__alloc_res(struct zpci_dev *zdev, unsigned long start,
 				    unsigned long size, unsigned long flags)
 {
@@ -668,7 +696,7 @@ int zpci_enable_device(struct zpci_dev *zdev)
 	if (clp_enable_fh(zdev, &fh, ZPCI_NR_DMA_SPACES))
 		rc = -EIO;
 	else
-		zdev->fh = fh;
+		zpci_update_fh(zdev, fh);
 	return rc;
 }
 
@@ -679,14 +707,14 @@ int zpci_disable_device(struct zpci_dev *zdev)
 
 	cc = clp_disable_fh(zdev, &fh);
 	if (!cc) {
-		zdev->fh = fh;
+		zpci_update_fh(zdev, fh);
 	} else if (cc == CLP_RC_SETPCIFN_ALRDY) {
 		pr_info("Disabling PCI function %08x had no effect as it was already disabled\n",
 			zdev->fid);
 		/* Function is already disabled - update handle */
 		rc = clp_refresh_fh(zdev->fid, &fh);
 		if (!rc) {
-			zdev->fh = fh;
+			zpci_update_fh(zdev, fh);
 			rc = -EINVAL;
 		}
 	} else {
@@ -696,6 +724,65 @@ int zpci_disable_device(struct zpci_dev *zdev)
 }
 
 /**
+ * zpci_hot_reset_device - perform a reset of the given zPCI function
+ * @zdev: the slot which should be reset
+ *
+ * Performs a low level reset of the zPCI function. The reset is low level in
+ * the sense that the zPCI function can be reset without detaching it from the
+ * common PCI subsystem. The reset may be performed while under control of
+ * either DMA or IOMMU APIs in which case the existing DMA/IOMMU translation
+ * table is reinstated at the end of the reset.
+ *
+ * After the reset the functions internal state is reset to an initial state
+ * equivalent to its state during boot when first probing a driver.
+ * Consequently after reset the PCI function requires re-initialization via the
+ * common PCI code including re-enabling IRQs via pci_alloc_irq_vectors()
+ * and enabling the function via e.g.pci_enablde_device_flags().The caller
+ * must guard against concurrent reset attempts.
+ *
+ * In most cases this function should not be called directly but through
+ * pci_reset_function() or pci_reset_bus() which handle the save/restore and
+ * locking.
+ *
+ * Return: 0 on success and an error value otherwise
+ */
+int zpci_hot_reset_device(struct zpci_dev *zdev)
+{
+	int rc;
+
+	zpci_dbg(3, "rst fid:%x, fh:%x\n", zdev->fid, zdev->fh);
+	if (zdev_enabled(zdev)) {
+		/* Disables device access, DMAs and IRQs (reset state) */
+		rc = zpci_disable_device(zdev);
+		/*
+		 * Due to a z/VM vs LPAR inconsistency in the error state the
+		 * FH may indicate an enabled device but disable says the
+		 * device is already disabled don't treat it as an error here.
+		 */
+		if (rc == -EINVAL)
+			rc = 0;
+		if (rc)
+			return rc;
+	}
+
+	rc = zpci_enable_device(zdev);
+	if (rc)
+		return rc;
+
+	if (zdev->dma_table)
+		rc = zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma,
+					(u64)zdev->dma_table);
+	else
+		rc = zpci_dma_init_device(zdev);
+	if (rc) {
+		zpci_disable_device(zdev);
+		return rc;
+	}
+
+	return 0;
+}
+
+/**
  * zpci_create_device() - Create a new zpci_dev and add it to the zbus
  * @fid: Function ID of the device to be created
  * @fh: Current Function Handle of the device to be created
@@ -776,7 +863,7 @@ int zpci_scan_configured_device(struct zpci_dev *zdev, u32 fh)
 {
 	int rc;
 
-	zdev->fh = fh;
+	zpci_update_fh(zdev, fh);
 	/* the PCI function will be scanned once function 0 appears */
 	if (!zdev->zbus->bus)
 		return 0;
@@ -903,6 +990,59 @@ int zpci_report_error(struct pci_dev *pdev,
 }
 EXPORT_SYMBOL(zpci_report_error);
 
+/**
+ * zpci_clear_error_state() - Clears the zPCI error state of the device
+ * @zdev: The zdev for which the zPCI error state should be reset
+ *
+ * Clear the zPCI error state of the device. If clearing the zPCI error state
+ * fails the device is left in the error state. In this case it may make sense
+ * to call zpci_io_perm_failure() on the associated pdev if it exists.
+ *
+ * Returns: 0 on success, -EIO otherwise
+ */
+int zpci_clear_error_state(struct zpci_dev *zdev)
+{
+	u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_RESET_ERROR);
+	struct zpci_fib fib = {0};
+	u8 status;
+	int cc;
+
+	cc = zpci_mod_fc(req, &fib, &status);
+	if (cc) {
+		zpci_dbg(3, "ces fid:%x, cc:%d, status:%x\n", zdev->fid, cc, status);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+/**
+ * zpci_reset_load_store_blocked() - Re-enables L/S from error state
+ * @zdev: The zdev for which to unblock load/store access
+ *
+ * Re-enables load/store access for a PCI function in the error state while
+ * keeping DMA blocked. In this state drivers can poke MMIO space to determine
+ * if error recovery is possible while catching any rogue DMA access from the
+ * device.
+ *
+ * Returns: 0 on success, -EIO otherwise
+ */
+int zpci_reset_load_store_blocked(struct zpci_dev *zdev)
+{
+	u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_RESET_BLOCK);
+	struct zpci_fib fib = {0};
+	u8 status;
+	int cc;
+
+	cc = zpci_mod_fc(req, &fib, &status);
+	if (cc) {
+		zpci_dbg(3, "rls fid:%x, cc:%d, status:%x\n", zdev->fid, cc, status);
+		return -EIO;
+	}
+
+	return 0;
+}
+
 static int zpci_mem_init(void)
 {
 	BUILD_BUG_ON(!is_power_of_2(__alignof__(struct zpci_fmb)) ||
diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c
index 6a5bfa9dc1f2..2e3e5b278925 100644
--- a/arch/s390/pci/pci_event.c
+++ b/arch/s390/pci/pci_event.c
@@ -47,18 +47,223 @@ struct zpci_ccdf_avail {
 	u16 pec;			/* PCI event code */
 } __packed;
 
+static inline bool ers_result_indicates_abort(pci_ers_result_t ers_res)
+{
+	switch (ers_res) {
+	case PCI_ERS_RESULT_CAN_RECOVER:
+	case PCI_ERS_RESULT_RECOVERED:
+	case PCI_ERS_RESULT_NEED_RESET:
+		return false;
+	default:
+		return true;
+	}
+}
+
+static bool is_passed_through(struct zpci_dev *zdev)
+{
+	return zdev->s390_domain;
+}
+
+static bool is_driver_supported(struct pci_driver *driver)
+{
+	if (!driver || !driver->err_handler)
+		return false;
+	if (!driver->err_handler->error_detected)
+		return false;
+	if (!driver->err_handler->slot_reset)
+		return false;
+	if (!driver->err_handler->resume)
+		return false;
+	return true;
+}
+
+static pci_ers_result_t zpci_event_notify_error_detected(struct pci_dev *pdev,
+							 struct pci_driver *driver)
+{
+	pci_ers_result_t ers_res = PCI_ERS_RESULT_DISCONNECT;
+
+	ers_res = driver->err_handler->error_detected(pdev,  pdev->error_state);
+	if (ers_result_indicates_abort(ers_res))
+		pr_info("%s: Automatic recovery failed after initial reporting\n", pci_name(pdev));
+	else if (ers_res == PCI_ERS_RESULT_NEED_RESET)
+		pr_debug("%s: Driver needs reset to recover\n", pci_name(pdev));
+
+	return ers_res;
+}
+
+static pci_ers_result_t zpci_event_do_error_state_clear(struct pci_dev *pdev,
+							struct pci_driver *driver)
+{
+	pci_ers_result_t ers_res = PCI_ERS_RESULT_DISCONNECT;
+	struct zpci_dev *zdev = to_zpci(pdev);
+	int rc;
+
+	pr_info("%s: Unblocking device access for examination\n", pci_name(pdev));
+	rc = zpci_reset_load_store_blocked(zdev);
+	if (rc) {
+		pr_err("%s: Unblocking device access failed\n", pci_name(pdev));
+		/* Let's try a full reset instead */
+		return PCI_ERS_RESULT_NEED_RESET;
+	}
+
+	if (driver->err_handler->mmio_enabled) {
+		ers_res = driver->err_handler->mmio_enabled(pdev);
+		if (ers_result_indicates_abort(ers_res)) {
+			pr_info("%s: Automatic recovery failed after MMIO re-enable\n",
+				pci_name(pdev));
+			return ers_res;
+		} else if (ers_res == PCI_ERS_RESULT_NEED_RESET) {
+			pr_debug("%s: Driver needs reset to recover\n", pci_name(pdev));
+			return ers_res;
+		}
+	}
+
+	pr_debug("%s: Unblocking DMA\n", pci_name(pdev));
+	rc = zpci_clear_error_state(zdev);
+	if (!rc) {
+		pdev->error_state = pci_channel_io_normal;
+	} else {
+		pr_err("%s: Unblocking DMA failed\n", pci_name(pdev));
+		/* Let's try a full reset instead */
+		return PCI_ERS_RESULT_NEED_RESET;
+	}
+
+	return ers_res;
+}
+
+static pci_ers_result_t zpci_event_do_reset(struct pci_dev *pdev,
+					    struct pci_driver *driver)
+{
+	pci_ers_result_t ers_res = PCI_ERS_RESULT_DISCONNECT;
+
+	pr_info("%s: Initiating reset\n", pci_name(pdev));
+	if (zpci_hot_reset_device(to_zpci(pdev))) {
+		pr_err("%s: The reset request failed\n", pci_name(pdev));
+		return ers_res;
+	}
+	pdev->error_state = pci_channel_io_normal;
+	ers_res = driver->err_handler->slot_reset(pdev);
+	if (ers_result_indicates_abort(ers_res)) {
+		pr_info("%s: Automatic recovery failed after slot reset\n", pci_name(pdev));
+		return ers_res;
+	}
+
+	return ers_res;
+}
+
+/* zpci_event_attempt_error_recovery - Try to recover the given PCI function
+ * @pdev: PCI function to recover currently in the error state
+ *
+ * We follow the scheme outlined in Documentation/PCI/pci-error-recovery.rst.
+ * With the simplification that recovery always happens per function
+ * and the platform determines which functions are affected for
+ * multi-function devices.
+ */
+static pci_ers_result_t zpci_event_attempt_error_recovery(struct pci_dev *pdev)
+{
+	pci_ers_result_t ers_res = PCI_ERS_RESULT_DISCONNECT;
+	struct pci_driver *driver;
+
+	/*
+	 * Ensure that the PCI function is not removed concurrently, no driver
+	 * is unbound or probed and that userspace can't access its
+	 * configuration space while we perform recovery.
+	 */
+	pci_dev_lock(pdev);
+	if (pdev->error_state == pci_channel_io_perm_failure) {
+		ers_res = PCI_ERS_RESULT_DISCONNECT;
+		goto out_unlock;
+	}
+	pdev->error_state = pci_channel_io_frozen;
+
+	if (is_passed_through(to_zpci(pdev))) {
+		pr_info("%s: Cannot be recovered in the host because it is a pass-through device\n",
+			pci_name(pdev));
+		goto out_unlock;
+	}
+
+	driver = to_pci_driver(pdev->dev.driver);
+	if (!is_driver_supported(driver)) {
+		if (!driver)
+			pr_info("%s: Cannot be recovered because no driver is bound to the device\n",
+				pci_name(pdev));
+		else
+			pr_info("%s: The %s driver bound to the device does not support error recovery\n",
+				pci_name(pdev),
+				driver->name);
+		goto out_unlock;
+	}
+
+	ers_res = zpci_event_notify_error_detected(pdev, driver);
+	if (ers_result_indicates_abort(ers_res))
+		goto out_unlock;
+
+	if (ers_res == PCI_ERS_RESULT_CAN_RECOVER) {
+		ers_res = zpci_event_do_error_state_clear(pdev, driver);
+		if (ers_result_indicates_abort(ers_res))
+			goto out_unlock;
+	}
+
+	if (ers_res == PCI_ERS_RESULT_NEED_RESET)
+		ers_res = zpci_event_do_reset(pdev, driver);
+
+	if (ers_res != PCI_ERS_RESULT_RECOVERED) {
+		pr_err("%s: Automatic recovery failed; operator intervention is required\n",
+		       pci_name(pdev));
+		goto out_unlock;
+	}
+
+	pr_info("%s: The device is ready to resume operations\n", pci_name(pdev));
+	if (driver->err_handler->resume)
+		driver->err_handler->resume(pdev);
+out_unlock:
+	pci_dev_unlock(pdev);
+
+	return ers_res;
+}
+
+/* zpci_event_io_failure - Report PCI channel failure state to driver
+ * @pdev: PCI function for which to report
+ * @es: PCI channel failure state to report
+ */
+static void zpci_event_io_failure(struct pci_dev *pdev, pci_channel_state_t es)
+{
+	struct pci_driver *driver;
+
+	pci_dev_lock(pdev);
+	pdev->error_state = es;
+	/**
+	 * While vfio-pci's error_detected callback notifies user-space QEMU
+	 * reacts to this by freezing the guest. In an s390 environment PCI
+	 * errors are rarely fatal so this is overkill. Instead in the future
+	 * we will inject the error event and let the guest recover the device
+	 * itself.
+	 */
+	if (is_passed_through(to_zpci(pdev)))
+		goto out;
+	driver = to_pci_driver(pdev->dev.driver);
+	if (driver && driver->err_handler && driver->err_handler->error_detected)
+		driver->err_handler->error_detected(pdev, pdev->error_state);
+out:
+	pci_dev_unlock(pdev);
+}
+
 static void __zpci_event_error(struct zpci_ccdf_err *ccdf)
 {
 	struct zpci_dev *zdev = get_zdev_by_fid(ccdf->fid);
 	struct pci_dev *pdev = NULL;
+	pci_ers_result_t ers_res;
 
 	zpci_dbg(3, "err fid:%x, fh:%x, pec:%x\n",
 		 ccdf->fid, ccdf->fh, ccdf->pec);
 	zpci_err("error CCDF:\n");
 	zpci_err_hex(ccdf, sizeof(*ccdf));
 
-	if (zdev)
-		pdev = pci_get_slot(zdev->zbus->bus, zdev->devfn);
+	if (zdev) {
+		zpci_update_fh(zdev, ccdf->fh);
+		if (zdev->zbus->bus)
+			pdev = pci_get_slot(zdev->zbus->bus, zdev->devfn);
+	}
 
 	pr_err("%s: Event 0x%x reports an error for PCI function 0x%x\n",
 	       pdev ? pci_name(pdev) : "n/a", ccdf->pec, ccdf->fid);
@@ -66,7 +271,20 @@ static void __zpci_event_error(struct zpci_ccdf_err *ccdf)
 	if (!pdev)
 		return;
 
-	pdev->error_state = pci_channel_io_perm_failure;
+	switch (ccdf->pec) {
+	case 0x003a: /* Service Action or Error Recovery Successful */
+		ers_res = zpci_event_attempt_error_recovery(pdev);
+		if (ers_res != PCI_ERS_RESULT_RECOVERED)
+			zpci_event_io_failure(pdev, pci_channel_io_perm_failure);
+		break;
+	default:
+		/*
+		 * Mark as frozen not permanently failed because the device
+		 * could be subsequently recovered by the platform.
+		 */
+		zpci_event_io_failure(pdev, pci_channel_io_frozen);
+		break;
+	}
 	pci_dev_put(pdev);
 }
 
@@ -78,7 +296,7 @@ void zpci_event_error(void *data)
 
 static void zpci_event_hard_deconfigured(struct zpci_dev *zdev, u32 fh)
 {
-	zdev->fh = fh;
+	zpci_update_fh(zdev, fh);
 	/* Give the driver a hint that the function is
 	 * already unusable.
 	 */
@@ -121,7 +339,7 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
 		if (!zdev)
 			zpci_create_device(ccdf->fid, ccdf->fh, ZPCI_FN_STATE_STANDBY);
 		else
-			zdev->fh = ccdf->fh;
+			zpci_update_fh(zdev, ccdf->fh);
 		break;
 	case 0x0303: /* Deconfiguration requested */
 		if (zdev) {
@@ -130,7 +348,7 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
 			 */
 			if (zdev->state != ZPCI_FN_STATE_CONFIGURED)
 				break;
-			zdev->fh = ccdf->fh;
+			zpci_update_fh(zdev, ccdf->fh);
 			zpci_deconfigure_device(zdev);
 		}
 		break;
diff --git a/arch/s390/pci/pci_insn.c b/arch/s390/pci/pci_insn.c
index 2e43996159f0..28d863aaafea 100644
--- a/arch/s390/pci/pci_insn.c
+++ b/arch/s390/pci/pci_insn.c
@@ -163,7 +163,7 @@ static inline int zpci_load_fh(u64 *data, const volatile void __iomem *addr,
 			       unsigned long len)
 {
 	struct zpci_iomap_entry *entry = &zpci_iomap_start[ZPCI_IDX(addr)];
-	u64 req = ZPCI_CREATE_REQ(entry->fh, entry->bar, len);
+	u64 req = ZPCI_CREATE_REQ(READ_ONCE(entry->fh), entry->bar, len);
 
 	return __zpci_load(data, req, ZPCI_OFFSET(addr));
 }
@@ -244,7 +244,7 @@ static inline int zpci_store_fh(const volatile void __iomem *addr, u64 data,
 				unsigned long len)
 {
 	struct zpci_iomap_entry *entry = &zpci_iomap_start[ZPCI_IDX(addr)];
-	u64 req = ZPCI_CREATE_REQ(entry->fh, entry->bar, len);
+	u64 req = ZPCI_CREATE_REQ(READ_ONCE(entry->fh), entry->bar, len);
 
 	return __zpci_store(data, req, ZPCI_OFFSET(addr));
 }
diff --git a/arch/s390/pci/pci_irq.c b/arch/s390/pci/pci_irq.c
index 3823e159bf74..954bb7a83124 100644
--- a/arch/s390/pci/pci_irq.c
+++ b/arch/s390/pci/pci_irq.c
@@ -387,6 +387,15 @@ void arch_teardown_msi_irqs(struct pci_dev *pdev)
 		airq_iv_free(zpci_ibv[0], zdev->msi_first_bit, zdev->msi_nr_irqs);
 }
 
+void arch_restore_msi_irqs(struct pci_dev *pdev)
+{
+	struct zpci_dev *zdev = to_zpci(pdev);
+
+	if (!zdev->irqs_registered)
+		zpci_set_irq(zdev);
+	default_restore_msi_irqs(pdev);
+}
+
 static struct airq_struct zpci_airq = {
 	.handler = zpci_floating_irq_handler,
 	.isc = PCI_ISC,
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index 6904f4bdbf00..70afb30e0b32 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -56,7 +56,6 @@ config SUPERH
 	select HAVE_STACKPROTECTOR
 	select HAVE_SYSCALL_TRACEPOINTS
 	select IRQ_FORCED_THREADING
-	select MAY_HAVE_SPARSE_IRQ
 	select MODULES_USE_ELF_RELA
 	select NEED_SG_DMA_LENGTH
 	select NO_DMA if !MMU && !DMA_COHERENT
diff --git a/arch/sh/Kconfig.debug b/arch/sh/Kconfig.debug
index 958f790273ab..10290e5c1f43 100644
--- a/arch/sh/Kconfig.debug
+++ b/arch/sh/Kconfig.debug
@@ -54,6 +54,7 @@ config DUMP_CODE
 
 config DWARF_UNWINDER
 	bool "Enable the DWARF unwinder for stacktraces"
+	depends on DEBUG_KERNEL
 	select FRAME_POINTER
 	default n
 	help
diff --git a/arch/sh/boards/mach-landisk/irq.c b/arch/sh/boards/mach-landisk/irq.c
index 29b8b1f85246..0b672b80c561 100644
--- a/arch/sh/boards/mach-landisk/irq.c
+++ b/arch/sh/boards/mach-landisk/irq.c
@@ -26,8 +26,8 @@ enum {
 	PCI_INTD, /* PCI int D */
 	ATA,	  /* ATA */
 	FATA,	  /* CF */
-	POWER,	  /* Power swtich */
-	BUTTON,	  /* Button swtich */
+	POWER,	  /* Power switch */
+	BUTTON,	  /* Button switch */
 };
 
 /* Vectors for LANDISK */
diff --git a/arch/sh/boot/Makefile b/arch/sh/boot/Makefile
index c081e7e2d6e7..5c123f5b2797 100644
--- a/arch/sh/boot/Makefile
+++ b/arch/sh/boot/Makefile
@@ -27,8 +27,8 @@ suffix-$(CONFIG_KERNEL_XZ)	:= xz
 suffix-$(CONFIG_KERNEL_LZO)	:= lzo
 
 targets := zImage vmlinux.srec romImage uImage uImage.srec uImage.gz \
-	   uImage.bz2 uImage.lzma uImage.xz uImage.lzo uImage.bin
-extra-y += vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma \
+	   uImage.bz2 uImage.lzma uImage.xz uImage.lzo uImage.bin \
+	   vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma \
 	   vmlinux.bin.xz vmlinux.bin.lzo
 subdir- := compressed romimage
 
diff --git a/arch/sh/boot/compressed/.gitignore b/arch/sh/boot/compressed/.gitignore
index 37aa53057369..cd16663bc7c8 100644
--- a/arch/sh/boot/compressed/.gitignore
+++ b/arch/sh/boot/compressed/.gitignore
@@ -1,7 +1,2 @@
 # SPDX-License-Identifier: GPL-2.0-only
-ashiftrt.S
-ashldi3.c
-ashlsi3.S
-ashrsi3.S
-lshrsi3.S
 vmlinux.bin.*
diff --git a/arch/sh/boot/compressed/Makefile b/arch/sh/boot/compressed/Makefile
index 589d2d8a573d..cf3174df7859 100644
--- a/arch/sh/boot/compressed/Makefile
+++ b/arch/sh/boot/compressed/Makefile
@@ -5,12 +5,18 @@
 # create a compressed vmlinux image from the original vmlinux
 #
 
-targets		:= vmlinux vmlinux.bin vmlinux.bin.gz \
-		   vmlinux.bin.bz2 vmlinux.bin.lzma \
-		   vmlinux.bin.xz vmlinux.bin.lzo \
-		   head_32.o misc.o piggy.o
+OBJECTS := head_32.o misc.o cache.o piggy.o \
+           ashiftrt.o ashldi3.o ashrsi3.o ashlsi3.o lshrsi3.o
+
+# These were previously generated files. When you are building the kernel
+# with O=, make sure to remove the stale files in the output tree. Otherwise,
+# the build system wrongly compiles the stale ones.
+ifdef building_out_of_srctree
+$(shell rm -f $(addprefix $(obj)/, ashiftrt.S ashldi3.c ashrsi3.S ashlsi3.S lshrsi3.S))
+endif
 
-OBJECTS = $(obj)/head_32.o $(obj)/misc.o $(obj)/cache.o
+targets := vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 \
+           vmlinux.bin.lzma vmlinux.bin.xz vmlinux.bin.lzo $(OBJECTS)
 
 GCOV_PROFILE := n
 
@@ -33,21 +39,9 @@ ccflags-remove-$(CONFIG_MCOUNT) += -pg
 LDFLAGS_vmlinux := --oformat $(ld-bfd) -Ttext $(IMAGE_OFFSET) -e startup \
 		   -T $(obj)/../../kernel/vmlinux.lds
 
-#
-# Pull in the necessary libgcc bits from the in-kernel implementation.
-#
-lib1funcs-y	:= ashiftrt.S ashldi3.c ashrsi3.S ashlsi3.S lshrsi3.S
-lib1funcs-obj   := \
-	$(addsuffix .o, $(basename $(addprefix $(obj)/, $(lib1funcs-y))))
-
-lib1funcs-dir		:= $(srctree)/arch/$(SRCARCH)/lib
-
-KBUILD_CFLAGS += -I$(lib1funcs-dir) -DDISABLE_BRANCH_PROFILING
-
-$(addprefix $(obj)/,$(lib1funcs-y)): $(obj)/%: $(lib1funcs-dir)/% FORCE
-	$(call cmd,shipped)
+KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
 
-$(obj)/vmlinux: $(OBJECTS) $(obj)/piggy.o $(lib1funcs-obj) FORCE
+$(obj)/vmlinux: $(addprefix $(obj)/, $(OBJECTS)) FORCE
 	$(call if_changed,ld)
 
 $(obj)/vmlinux.bin: vmlinux FORCE
diff --git a/arch/sh/boot/compressed/ashiftrt.S b/arch/sh/boot/compressed/ashiftrt.S
new file mode 100644
index 000000000000..0f3b291a3f4b
--- /dev/null
+++ b/arch/sh/boot/compressed/ashiftrt.S
@@ -0,0 +1,2 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#include "../../lib/ashiftrt.S"
diff --git a/arch/sh/boot/compressed/ashldi3.c b/arch/sh/boot/compressed/ashldi3.c
new file mode 100644
index 000000000000..7cebd646df83
--- /dev/null
+++ b/arch/sh/boot/compressed/ashldi3.c
@@ -0,0 +1,2 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include "../../lib/ashldi3.c"
diff --git a/arch/sh/boot/compressed/ashlsi3.S b/arch/sh/boot/compressed/ashlsi3.S
new file mode 100644
index 000000000000..e354262b275f
--- /dev/null
+++ b/arch/sh/boot/compressed/ashlsi3.S
@@ -0,0 +1,2 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#include "../../lib/ashlsi3.S"
diff --git a/arch/sh/boot/compressed/ashrsi3.S b/arch/sh/boot/compressed/ashrsi3.S
new file mode 100644
index 000000000000..e564be9a4dcd
--- /dev/null
+++ b/arch/sh/boot/compressed/ashrsi3.S
@@ -0,0 +1,2 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#include "../../lib/ashrsi3.S"
diff --git a/arch/sh/boot/compressed/lshrsi3.S b/arch/sh/boot/compressed/lshrsi3.S
new file mode 100644
index 000000000000..5a8281b7e516
--- /dev/null
+++ b/arch/sh/boot/compressed/lshrsi3.S
@@ -0,0 +1,2 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#include "../../lib/lshrsi3.S"
diff --git a/arch/sh/include/asm/cacheflush.h b/arch/sh/include/asm/cacheflush.h
index c7a97f32432f..481a664287e2 100644
--- a/arch/sh/include/asm/cacheflush.h
+++ b/arch/sh/include/asm/cacheflush.h
@@ -43,7 +43,6 @@ extern void flush_cache_range(struct vm_area_struct *vma,
 				 unsigned long start, unsigned long end);
 #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
 void flush_dcache_page(struct page *page);
-void flush_dcache_folio(struct folio *folio);
 extern void flush_icache_range(unsigned long start, unsigned long end);
 #define flush_icache_user_range flush_icache_range
 extern void flush_icache_page(struct vm_area_struct *vma,
diff --git a/arch/sh/include/asm/checksum_32.h b/arch/sh/include/asm/checksum_32.h
index 1a391e3a7659..a6501b856f3e 100644
--- a/arch/sh/include/asm/checksum_32.h
+++ b/arch/sh/include/asm/checksum_32.h
@@ -84,7 +84,8 @@ static inline __sum16 csum_fold(__wsum sum)
  */
 static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
 {
-	unsigned int sum, __dummy0, __dummy1;
+	__wsum sum;
+	unsigned int __dummy0, __dummy1;
 
 	__asm__ __volatile__(
 		"mov.l	@%1+, %0\n\t"
@@ -197,6 +198,6 @@ static inline __wsum csum_and_copy_to_user(const void *src,
 {
 	if (!access_ok(dst, len))
 		return 0;
-	return csum_partial_copy_generic((__force const void *)src, dst, len);
+	return csum_partial_copy_generic(src, (__force void *)dst, len);
 }
 #endif /* __ASM_SH_CHECKSUM_H */
diff --git a/arch/sh/include/asm/irq.h b/arch/sh/include/asm/irq.h
index 839551ce398c..1c4923502fd4 100644
--- a/arch/sh/include/asm/irq.h
+++ b/arch/sh/include/asm/irq.h
@@ -6,17 +6,6 @@
 #include <asm/machvec.h>
 
 /*
- * Only legacy non-sparseirq platforms have to set a reasonably sane
- * value here. sparseirq platforms allocate their irq_descs on the fly,
- * so will expand automatically based on the number of registered IRQs.
- */
-#ifdef CONFIG_SPARSE_IRQ
-# define NR_IRQS		8
-#else
-# define NR_IRQS		512
-#endif
-
-/*
  * This is a special IRQ number for indicating that no IRQ has been
  * triggered and to simply ignore the IRQ dispatch. This is a special
  * case that can happen with IRQ auto-distribution when multiple CPUs
diff --git a/arch/sh/include/asm/sfp-machine.h b/arch/sh/include/asm/sfp-machine.h
index cbc7cf8c97ce..2d2423478b71 100644
--- a/arch/sh/include/asm/sfp-machine.h
+++ b/arch/sh/include/asm/sfp-machine.h
@@ -13,6 +13,14 @@
 #ifndef _SFP_MACHINE_H
 #define _SFP_MACHINE_H
 
+#ifdef __BIG_ENDIAN__
+#define __BYTE_ORDER __BIG_ENDIAN
+#define __LITTLE_ENDIAN 0
+#else
+#define __BYTE_ORDER __LITTLE_ENDIAN
+#define __BIG_ENDIAN 0
+#endif
+
 #define _FP_W_TYPE_SIZE		32
 #define _FP_W_TYPE		unsigned long
 #define _FP_WS_TYPE		signed long
diff --git a/arch/sh/include/asm/uaccess.h b/arch/sh/include/asm/uaccess.h
index 73f3b48d4a34..8867bb04b00e 100644
--- a/arch/sh/include/asm/uaccess.h
+++ b/arch/sh/include/asm/uaccess.h
@@ -68,7 +68,7 @@ struct __large_struct { unsigned long buf[100]; };
 ({									\
 	long __gu_err = -EFAULT;					\
 	unsigned long __gu_val = 0;					\
-	const __typeof__(*(ptr)) *__gu_addr = (ptr);			\
+	const __typeof__(*(ptr)) __user *__gu_addr = (ptr);			\
 	if (likely(access_ok(__gu_addr, (size))))		\
 		__get_user_size(__gu_val, __gu_addr, (size), __gu_err);	\
 	(x) = (__force __typeof__(*(ptr)))__gu_val;			\
@@ -124,7 +124,7 @@ raw_copy_to_user(void __user *to, const void *from, unsigned long n)
  * Clear the area and return remaining number of bytes
  * (on failure.  Usually it's 0.)
  */
-__kernel_size_t __clear_user(void *addr, __kernel_size_t size);
+__kernel_size_t __clear_user(void __user *addr, __kernel_size_t size);
 
 #define clear_user(addr,n)						\
 ({									\
diff --git a/arch/sh/kernel/cpu/sh4a/smp-shx3.c b/arch/sh/kernel/cpu/sh4a/smp-shx3.c
index f8a2bec0f260..1261dc7b84e8 100644
--- a/arch/sh/kernel/cpu/sh4a/smp-shx3.c
+++ b/arch/sh/kernel/cpu/sh4a/smp-shx3.c
@@ -73,8 +73,9 @@ static void shx3_prepare_cpus(unsigned int max_cpus)
 	BUILD_BUG_ON(SMP_MSG_NR >= 8);
 
 	for (i = 0; i < SMP_MSG_NR; i++)
-		request_irq(104 + i, ipi_interrupt_handler,
-			    IRQF_PERCPU, "IPI", (void *)(long)i);
+		if (request_irq(104 + i, ipi_interrupt_handler,
+			    IRQF_PERCPU, "IPI", (void *)(long)i))
+			pr_err("Failed to request irq %d\n", i);
 
 	for (i = 0; i < max_cpus; i++)
 		set_cpu_present(i, true);
diff --git a/arch/sh/kernel/crash_dump.c b/arch/sh/kernel/crash_dump.c
index a9086127b16d..5b41b59698c1 100644
--- a/arch/sh/kernel/crash_dump.c
+++ b/arch/sh/kernel/crash_dump.c
@@ -26,7 +26,7 @@
 ssize_t copy_oldmem_page(unsigned long pfn, char *buf,
                                size_t csize, unsigned long offset, int userbuf)
 {
-	void  *vaddr;
+	void  __iomem *vaddr;
 
 	if (!csize)
 		return 0;
@@ -34,7 +34,7 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf,
 	vaddr = ioremap(pfn << PAGE_SHIFT, PAGE_SIZE);
 
 	if (userbuf) {
-		if (copy_to_user(buf, (vaddr + offset), csize)) {
+		if (copy_to_user((void __user *)buf, (vaddr + offset), csize)) {
 			iounmap(vaddr);
 			return -EFAULT;
 		}
diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl
index 208f131659c5..d9539d28bdaa 100644
--- a/arch/sh/kernel/syscalls/syscall.tbl
+++ b/arch/sh/kernel/syscalls/syscall.tbl
@@ -451,3 +451,4 @@
 446	common	landlock_restrict_self		sys_landlock_restrict_self
 # 447 reserved for memfd_secret
 448	common	process_mrelease		sys_process_mrelease
+449	common  futex_waitv                     sys_futex_waitv
diff --git a/arch/sh/kernel/traps_32.c b/arch/sh/kernel/traps_32.c
index b62ad0ba2395..b3c715bc254b 100644
--- a/arch/sh/kernel/traps_32.c
+++ b/arch/sh/kernel/traps_32.c
@@ -490,7 +490,7 @@ asmlinkage void do_address_error(struct pt_regs *regs,
 		inc_unaligned_user_access();
 
 		oldfs = force_uaccess_begin();
-		if (copy_from_user(&instruction, (insn_size_t *)(regs->pc & ~1),
+		if (copy_from_user(&instruction, (insn_size_t __user *)(regs->pc & ~1),
 				   sizeof(instruction))) {
 			force_uaccess_end(oldfs);
 			goto uspace_segv;
@@ -614,7 +614,7 @@ asmlinkage void do_reserved_inst(void)
 	unsigned short inst = 0;
 	int err;
 
-	get_user(inst, (unsigned short*)regs->pc);
+	get_user(inst, (unsigned short __user *)regs->pc);
 
 	err = do_fpu_inst(inst, regs);
 	if (!err) {
@@ -699,9 +699,9 @@ asmlinkage void do_illegal_slot_inst(void)
 		return;
 
 #ifdef CONFIG_SH_FPU_EMU
-	get_user(inst, (unsigned short *)regs->pc + 1);
+	get_user(inst, (unsigned short __user *)regs->pc + 1);
 	if (!do_fpu_inst(inst, regs)) {
-		get_user(inst, (unsigned short *)regs->pc);
+		get_user(inst, (unsigned short __user *)regs->pc);
 		if (!emulate_branch(inst, regs))
 			return;
 		/* fault in branch.*/
diff --git a/arch/sh/math-emu/math.c b/arch/sh/math-emu/math.c
index e8be0eca0444..cdaef6501d76 100644
--- a/arch/sh/math-emu/math.c
+++ b/arch/sh/math-emu/math.c
@@ -51,8 +51,8 @@
 #define Rn	(regs->regs[n])
 #define Rm	(regs->regs[m])
 
-#define WRITE(d,a)	({if(put_user(d, (typeof (d)*)a)) return -EFAULT;})
-#define READ(d,a)	({if(get_user(d, (typeof (d)*)a)) return -EFAULT;})
+#define MWRITE(d,a)	({if(put_user(d, (typeof (d) __user *)a)) return -EFAULT;})
+#define MREAD(d,a)	({if(get_user(d, (typeof (d) __user *)a)) return -EFAULT;})
 
 #define PACK_S(r,f)	FP_PACK_SP(&r,f)
 #define UNPACK_S(f,r)	FP_UNPACK_SP(f,&r)
@@ -157,11 +157,11 @@ fmov_idx_reg(struct sh_fpu_soft_struct *fregs, struct pt_regs *regs, int m,
 {
 	if (FPSCR_SZ) {
 		FMOV_EXT(n);
-		READ(FRn, Rm + R0 + 4);
+		MREAD(FRn, Rm + R0 + 4);
 		n++;
-		READ(FRn, Rm + R0);
+		MREAD(FRn, Rm + R0);
 	} else {
-		READ(FRn, Rm + R0);
+		MREAD(FRn, Rm + R0);
 	}
 
 	return 0;
@@ -173,11 +173,11 @@ fmov_mem_reg(struct sh_fpu_soft_struct *fregs, struct pt_regs *regs, int m,
 {
 	if (FPSCR_SZ) {
 		FMOV_EXT(n);
-		READ(FRn, Rm + 4);
+		MREAD(FRn, Rm + 4);
 		n++;
-		READ(FRn, Rm);
+		MREAD(FRn, Rm);
 	} else {
-		READ(FRn, Rm);
+		MREAD(FRn, Rm);
 	}
 
 	return 0;
@@ -189,12 +189,12 @@ fmov_inc_reg(struct sh_fpu_soft_struct *fregs, struct pt_regs *regs, int m,
 {
 	if (FPSCR_SZ) {
 		FMOV_EXT(n);
-		READ(FRn, Rm + 4);
+		MREAD(FRn, Rm + 4);
 		n++;
-		READ(FRn, Rm);
+		MREAD(FRn, Rm);
 		Rm += 8;
 	} else {
-		READ(FRn, Rm);
+		MREAD(FRn, Rm);
 		Rm += 4;
 	}
 
@@ -207,11 +207,11 @@ fmov_reg_idx(struct sh_fpu_soft_struct *fregs, struct pt_regs *regs, int m,
 {
 	if (FPSCR_SZ) {
 		FMOV_EXT(m);
-		WRITE(FRm, Rn + R0 + 4);
+		MWRITE(FRm, Rn + R0 + 4);
 		m++;
-		WRITE(FRm, Rn + R0);
+		MWRITE(FRm, Rn + R0);
 	} else {
-		WRITE(FRm, Rn + R0);
+		MWRITE(FRm, Rn + R0);
 	}
 
 	return 0;
@@ -223,11 +223,11 @@ fmov_reg_mem(struct sh_fpu_soft_struct *fregs, struct pt_regs *regs, int m,
 {
 	if (FPSCR_SZ) {
 		FMOV_EXT(m);
-		WRITE(FRm, Rn + 4);
+		MWRITE(FRm, Rn + 4);
 		m++;
-		WRITE(FRm, Rn);
+		MWRITE(FRm, Rn);
 	} else {
-		WRITE(FRm, Rn);
+		MWRITE(FRm, Rn);
 	}
 
 	return 0;
@@ -240,12 +240,12 @@ fmov_reg_dec(struct sh_fpu_soft_struct *fregs, struct pt_regs *regs, int m,
 	if (FPSCR_SZ) {
 		FMOV_EXT(m);
 		Rn -= 8;
-		WRITE(FRm, Rn + 4);
+		MWRITE(FRm, Rn + 4);
 		m++;
-		WRITE(FRm, Rn);
+		MWRITE(FRm, Rn);
 	} else {
 		Rn -= 4;
-		WRITE(FRm, Rn);
+		MWRITE(FRm, Rn);
 	}
 
 	return 0;
@@ -445,11 +445,11 @@ id_sys(struct sh_fpu_soft_struct *fregs, struct pt_regs *regs, u16 code)
 	case 0x4052:
 	case 0x4062:
 		Rn -= 4;
-		WRITE(*reg, Rn);
+		MWRITE(*reg, Rn);
 		break;
 	case 0x4056:
 	case 0x4066:
-		READ(*reg, Rn);
+		MREAD(*reg, Rn);
 		Rn += 4;
 		break;
 	default:
@@ -468,109 +468,6 @@ static int fpu_emulate(u16 code, struct sh_fpu_soft_struct *fregs, struct pt_reg
 }
 
 /**
- *	denormal_to_double - Given denormalized float number,
- *	                     store double float
- *
- *	@fpu: Pointer to sh_fpu_soft structure
- *	@n: Index to FP register
- */
-static void denormal_to_double(struct sh_fpu_soft_struct *fpu, int n)
-{
-	unsigned long du, dl;
-	unsigned long x = fpu->fpul;
-	int exp = 1023 - 126;
-
-	if (x != 0 && (x & 0x7f800000) == 0) {
-		du = (x & 0x80000000);
-		while ((x & 0x00800000) == 0) {
-			x <<= 1;
-			exp--;
-		}
-		x &= 0x007fffff;
-		du |= (exp << 20) | (x >> 3);
-		dl = x << 29;
-
-		fpu->fp_regs[n] = du;
-		fpu->fp_regs[n+1] = dl;
-	}
-}
-
-/**
- *	ieee_fpe_handler - Handle denormalized number exception
- *
- *	@regs: Pointer to register structure
- *
- *	Returns 1 when it's handled (should not cause exception).
- */
-static int ieee_fpe_handler(struct pt_regs *regs)
-{
-	unsigned short insn = *(unsigned short *)regs->pc;
-	unsigned short finsn;
-	unsigned long nextpc;
-	int nib[4] = {
-		(insn >> 12) & 0xf,
-		(insn >> 8) & 0xf,
-		(insn >> 4) & 0xf,
-		insn & 0xf};
-
-	if (nib[0] == 0xb ||
-	    (nib[0] == 0x4 && nib[2] == 0x0 && nib[3] == 0xb)) /* bsr & jsr */
-		regs->pr = regs->pc + 4;
-
-	if (nib[0] == 0xa || nib[0] == 0xb) { /* bra & bsr */
-		nextpc = regs->pc + 4 + ((short) ((insn & 0xfff) << 4) >> 3);
-		finsn = *(unsigned short *) (regs->pc + 2);
-	} else if (nib[0] == 0x8 && nib[1] == 0xd) { /* bt/s */
-		if (regs->sr & 1)
-			nextpc = regs->pc + 4 + ((char) (insn & 0xff) << 1);
-		else
-			nextpc = regs->pc + 4;
-		finsn = *(unsigned short *) (regs->pc + 2);
-	} else if (nib[0] == 0x8 && nib[1] == 0xf) { /* bf/s */
-		if (regs->sr & 1)
-			nextpc = regs->pc + 4;
-		else
-			nextpc = regs->pc + 4 + ((char) (insn & 0xff) << 1);
-		finsn = *(unsigned short *) (regs->pc + 2);
-	} else if (nib[0] == 0x4 && nib[3] == 0xb &&
-		 (nib[2] == 0x0 || nib[2] == 0x2)) { /* jmp & jsr */
-		nextpc = regs->regs[nib[1]];
-		finsn = *(unsigned short *) (regs->pc + 2);
-	} else if (nib[0] == 0x0 && nib[3] == 0x3 &&
-		 (nib[2] == 0x0 || nib[2] == 0x2)) { /* braf & bsrf */
-		nextpc = regs->pc + 4 + regs->regs[nib[1]];
-		finsn = *(unsigned short *) (regs->pc + 2);
-	} else if (insn == 0x000b) { /* rts */
-		nextpc = regs->pr;
-		finsn = *(unsigned short *) (regs->pc + 2);
-	} else {
-		nextpc = regs->pc + 2;
-		finsn = insn;
-	}
-
-	if ((finsn & 0xf1ff) == 0xf0ad) { /* fcnvsd */
-		struct task_struct *tsk = current;
-
-		if ((tsk->thread.xstate->softfpu.fpscr & (1 << 17))) {
-			/* FPU error */
-			denormal_to_double (&tsk->thread.xstate->softfpu,
-					    (finsn >> 8) & 0xf);
-			tsk->thread.xstate->softfpu.fpscr &=
-				~(FPSCR_CAUSE_MASK | FPSCR_FLAG_MASK);
-			task_thread_info(tsk)->status |= TS_USEDFPU;
-		} else {
-			force_sig_fault(SIGFPE, FPE_FLTINV,
-					(void __user *)regs->pc);
-		}
-
-		regs->pc = nextpc;
-		return 1;
-	}
-
-	return 0;
-}
-
-/**
  * fpu_init - Initialize FPU registers
  * @fpu: Pointer to software emulated FPU registers.
  */
diff --git a/arch/sh/mm/nommu.c b/arch/sh/mm/nommu.c
index 8b4504413c5f..78c4b6e6d33b 100644
--- a/arch/sh/mm/nommu.c
+++ b/arch/sh/mm/nommu.c
@@ -28,9 +28,9 @@ __kernel_size_t __copy_user(void *to, const void *from, __kernel_size_t n)
 	return 0;
 }
 
-__kernel_size_t __clear_user(void *to, __kernel_size_t n)
+__kernel_size_t __clear_user(void __user *to, __kernel_size_t n)
 {
-	memset(to, 0, n);
+	memset((__force void *)to, 0, n);
 	return 0;
 }
 
diff --git a/arch/sparc/kernel/signal_32.c b/arch/sparc/kernel/signal_32.c
index cd677bc564a7..ffab16369bea 100644
--- a/arch/sparc/kernel/signal_32.c
+++ b/arch/sparc/kernel/signal_32.c
@@ -244,7 +244,7 @@ static int setup_frame(struct ksignal *ksig, struct pt_regs *regs,
 		get_sigframe(ksig, regs, sigframe_size);
 
 	if (invalid_frame_pointer(sf, sigframe_size)) {
-		force_fatal_sig(SIGILL);
+		force_exit_sig(SIGILL);
 		return -EINVAL;
 	}
 
@@ -336,7 +336,7 @@ static int setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs,
 	sf = (struct rt_signal_frame __user *)
 		get_sigframe(ksig, regs, sigframe_size);
 	if (invalid_frame_pointer(sf, sigframe_size)) {
-		force_fatal_sig(SIGILL);
+		force_exit_sig(SIGILL);
 		return -EINVAL;
 	}
 
diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl
index c37764dc764d..46adabcb1720 100644
--- a/arch/sparc/kernel/syscalls/syscall.tbl
+++ b/arch/sparc/kernel/syscalls/syscall.tbl
@@ -494,3 +494,4 @@
 446	common	landlock_restrict_self		sys_landlock_restrict_self
 # 447 reserved for memfd_secret
 448	common	process_mrelease		sys_process_mrelease
+449	common  futex_waitv                     sys_futex_waitv
diff --git a/arch/sparc/kernel/windows.c b/arch/sparc/kernel/windows.c
index bbbd40cc6b28..8f20862ccc83 100644
--- a/arch/sparc/kernel/windows.c
+++ b/arch/sparc/kernel/windows.c
@@ -122,7 +122,7 @@ void try_to_clear_window_buffer(struct pt_regs *regs, int who)
 		if ((sp & 7) ||
 		    copy_to_user((char __user *) sp, &tp->reg_window[window],
 				 sizeof(struct reg_window32))) {
-			force_fatal_sig(SIGILL);
+			force_exit_sig(SIGILL);
 			return;
 		}
 	}
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 95dd1ee01546..5c2ccb85f2ef 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -193,7 +193,7 @@ config X86
 	select HAVE_DYNAMIC_FTRACE_WITH_ARGS	if X86_64
 	select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
 	select HAVE_SAMPLE_FTRACE_DIRECT	if X86_64
-	select HAVE_SAMPLE_FTRACE_MULTI_DIRECT	if X86_64
+	select HAVE_SAMPLE_FTRACE_DIRECT_MULTI	if X86_64
 	select HAVE_EBPF_JIT
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
 	select HAVE_EISA
@@ -1932,6 +1932,7 @@ config EFI
 	depends on ACPI
 	select UCS2_STRING
 	select EFI_RUNTIME_WRAPPERS
+	select ARCH_USE_MEMREMAP_PROT
 	help
 	  This enables the kernel to use EFI runtime services that are
 	  available (such as the EFI variable services).
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index e38a4cf795d9..97b1f84bb53f 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -574,6 +574,10 @@ SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL)
 	ud2
 1:
 #endif
+#ifdef CONFIG_XEN_PV
+	ALTERNATIVE "", "jmp xenpv_restore_regs_and_return_to_usermode", X86_FEATURE_XENPV
+#endif
+
 	POP_REGS pop_rdi=0
 
 	/*
@@ -890,6 +894,7 @@ SYM_CODE_START_LOCAL(paranoid_entry)
 .Lparanoid_entry_checkgs:
 	/* EBX = 1 -> kernel GSBASE active, no restore required */
 	movl	$1, %ebx
+
 	/*
 	 * The kernel-enforced convention is a negative GSBASE indicates
 	 * a kernel value. No SWAPGS needed on entry and exit.
@@ -897,21 +902,14 @@ SYM_CODE_START_LOCAL(paranoid_entry)
 	movl	$MSR_GS_BASE, %ecx
 	rdmsr
 	testl	%edx, %edx
-	jns	.Lparanoid_entry_swapgs
-	ret
+	js	.Lparanoid_kernel_gsbase
 
-.Lparanoid_entry_swapgs:
+	/* EBX = 0 -> SWAPGS required on exit */
+	xorl	%ebx, %ebx
 	swapgs
+.Lparanoid_kernel_gsbase:
 
-	/*
-	 * The above SAVE_AND_SWITCH_TO_KERNEL_CR3 macro doesn't do an
-	 * unconditional CR3 write, even in the PTI case.  So do an lfence
-	 * to prevent GS speculation, regardless of whether PTI is enabled.
-	 */
 	FENCE_SWAPGS_KERNEL_ENTRY
-
-	/* EBX = 0 -> SWAPGS required on exit */
-	xorl	%ebx, %ebx
 	ret
 SYM_CODE_END(paranoid_entry)
 
@@ -993,11 +991,6 @@ SYM_CODE_START_LOCAL(error_entry)
 	pushq	%r12
 	ret
 
-.Lerror_entry_done_lfence:
-	FENCE_SWAPGS_KERNEL_ENTRY
-.Lerror_entry_done:
-	ret
-
 	/*
 	 * There are two places in the kernel that can potentially fault with
 	 * usergs. Handle them here.  B stepping K8s sometimes report a
@@ -1020,8 +1013,14 @@ SYM_CODE_START_LOCAL(error_entry)
 	 * .Lgs_change's error handler with kernel gsbase.
 	 */
 	SWAPGS
-	FENCE_SWAPGS_USER_ENTRY
-	jmp .Lerror_entry_done
+
+	/*
+	 * Issue an LFENCE to prevent GS speculation, regardless of whether it is a
+	 * kernel or user gsbase.
+	 */
+.Lerror_entry_done_lfence:
+	FENCE_SWAPGS_KERNEL_ENTRY
+	ret
 
 .Lbstep_iret:
 	/* Fix truncated RIP */
diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c
index 0b6b277ee050..fd2ee9408e91 100644
--- a/arch/x86/entry/vsyscall/vsyscall_64.c
+++ b/arch/x86/entry/vsyscall/vsyscall_64.c
@@ -226,7 +226,7 @@ bool emulate_vsyscall(unsigned long error_code,
 	if ((!tmp && regs->orig_ax != syscall_nr) || regs->ip != address) {
 		warn_bad_vsyscall(KERN_DEBUG, regs,
 				  "seccomp tried to change syscall nr or ip");
-		force_fatal_sig(SIGSYS);
+		force_exit_sig(SIGSYS);
 		return true;
 	}
 	regs->orig_ax = -1;
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 603964408d2d..ec6444f2c9dc 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2211,7 +2211,6 @@ intel_pmu_snapshot_branch_stack(struct perf_branch_entry *entries, unsigned int
 	/* must not have branches... */
 	local_irq_save(flags);
 	__intel_pmu_disable_all(false); /* we don't care about BTS */
-	__intel_pmu_pebs_disable_all();
 	__intel_pmu_lbr_disable();
 	/*            ... until here */
 	return __intel_pmu_snapshot_branch_stack(entries, cnt, flags);
@@ -2225,7 +2224,6 @@ intel_pmu_snapshot_arch_branch_stack(struct perf_branch_entry *entries, unsigned
 	/* must not have branches... */
 	local_irq_save(flags);
 	__intel_pmu_disable_all(false); /* we don't care about BTS */
-	__intel_pmu_pebs_disable_all();
 	__intel_pmu_arch_lbr_disable();
 	/*            ... until here */
 	return __intel_pmu_snapshot_branch_stack(entries, cnt, flags);
@@ -3048,8 +3046,10 @@ intel_vlbr_constraints(struct perf_event *event)
 {
 	struct event_constraint *c = &vlbr_constraint;
 
-	if (unlikely(constraint_match(c, event->hw.config)))
+	if (unlikely(constraint_match(c, event->hw.config))) {
+		event->hw.flags |= c->flags;
 		return c;
+	}
 
 	return NULL;
 }
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index 6b72e9b55c69..8043213b75a5 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -265,6 +265,8 @@ void intel_pmu_lbr_reset(void)
 
 	cpuc->last_task_ctx = NULL;
 	cpuc->last_log_id = 0;
+	if (!static_cpu_has(X86_FEATURE_ARCH_LBR) && cpuc->lbr_select)
+		wrmsrl(MSR_LBR_SELECT, 0);
 }
 
 /*
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index eb2c6cea9d0d..3660f698fb2a 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -3608,6 +3608,9 @@ static int skx_cha_hw_config(struct intel_uncore_box *box, struct perf_event *ev
 	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
 	struct extra_reg *er;
 	int idx = 0;
+	/* Any of the CHA events may be filtered by Thread/Core-ID.*/
+	if (event->hw.config & SNBEP_CBO_PMON_CTL_TID_EN)
+		idx = SKX_CHA_MSR_PMON_BOX_FILTER_TID;
 
 	for (er = skx_uncore_cha_extra_regs; er->msr; er++) {
 		if (er->event != (event->hw.config & er->config_mask))
@@ -3675,6 +3678,7 @@ static struct event_constraint skx_uncore_iio_constraints[] = {
 	UNCORE_EVENT_CONSTRAINT(0xc0, 0xc),
 	UNCORE_EVENT_CONSTRAINT(0xc5, 0xc),
 	UNCORE_EVENT_CONSTRAINT(0xd4, 0xc),
+	UNCORE_EVENT_CONSTRAINT(0xd5, 0xc),
 	EVENT_CONSTRAINT_END
 };
 
@@ -4525,6 +4529,13 @@ static void snr_iio_cleanup_mapping(struct intel_uncore_type *type)
 	pmu_iio_cleanup_mapping(type, &snr_iio_mapping_group);
 }
 
+static struct event_constraint snr_uncore_iio_constraints[] = {
+	UNCORE_EVENT_CONSTRAINT(0x83, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0xc0, 0xc),
+	UNCORE_EVENT_CONSTRAINT(0xd5, 0xc),
+	EVENT_CONSTRAINT_END
+};
+
 static struct intel_uncore_type snr_uncore_iio = {
 	.name			= "iio",
 	.num_counters		= 4,
@@ -4536,6 +4547,7 @@ static struct intel_uncore_type snr_uncore_iio = {
 	.event_mask_ext		= SNR_IIO_PMON_RAW_EVENT_MASK_EXT,
 	.box_ctl		= SNR_IIO_MSR_PMON_BOX_CTL,
 	.msr_offset		= SNR_IIO_MSR_OFFSET,
+	.constraints		= snr_uncore_iio_constraints,
 	.ops			= &ivbep_uncore_msr_ops,
 	.format_group		= &snr_uncore_iio_format_group,
 	.attr_update		= snr_iio_attr_update,
diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index 24f4a06ac46a..96eb7db31c8e 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -177,6 +177,9 @@ void set_hv_tscchange_cb(void (*cb)(void))
 		return;
 	}
 
+	if (!hv_vp_index)
+		return;
+
 	hv_reenlightenment_cb = cb;
 
 	/* Make sure callback is registered before we write to MSRs */
@@ -383,20 +386,13 @@ static void __init hv_get_partition_id(void)
  */
 void __init hyperv_init(void)
 {
-	u64 guest_id, required_msrs;
+	u64 guest_id;
 	union hv_x64_msr_hypercall_contents hypercall_msr;
 	int cpuhp;
 
 	if (x86_hyper_type != X86_HYPER_MS_HYPERV)
 		return;
 
-	/* Absolutely required MSRs */
-	required_msrs = HV_MSR_HYPERCALL_AVAILABLE |
-		HV_MSR_VP_INDEX_AVAILABLE;
-
-	if ((ms_hyperv.features & required_msrs) != required_msrs)
-		return;
-
 	if (hv_common_init())
 		return;
 
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 4d0b126835b8..63158fd55856 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -197,8 +197,6 @@ static inline bool efi_runtime_supported(void)
 
 extern void parse_efi_setup(u64 phys_addr, u32 data_len);
 
-extern void efifb_setup_from_dmi(struct screen_info *si, const char *opt);
-
 extern void efi_thunk_runtime_setup(void);
 efi_status_t efi_set_virtual_address_map(unsigned long memory_map_size,
 					 unsigned long descriptor_size,
diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h
index 6053674f9132..c2767a6a387e 100644
--- a/arch/x86/include/asm/fpu/api.h
+++ b/arch/x86/include/asm/fpu/api.h
@@ -102,12 +102,6 @@ extern void switch_fpu_return(void);
  */
 extern int cpu_has_xfeatures(u64 xfeatures_mask, const char **feature_name);
 
-/*
- * Tasks that are not using SVA have mm->pasid set to zero to note that they
- * will not have the valid bit set in MSR_IA32_PASID while they are running.
- */
-#define PASID_DISABLED	0
-
 /* Trap handling */
 extern int  fpu__exception_code(struct fpu *fpu, int trap_nr);
 extern void fpu_sync_fpstate(struct fpu *fpu);
diff --git a/arch/x86/include/asm/fpu/xcr.h b/arch/x86/include/asm/fpu/xcr.h
index 79f95d3787e2..9656a5bc6fea 100644
--- a/arch/x86/include/asm/fpu/xcr.h
+++ b/arch/x86/include/asm/fpu/xcr.h
@@ -3,6 +3,7 @@
 #define _ASM_X86_FPU_XCR_H
 
 #define XCR_XFEATURE_ENABLED_MASK	0x00000000
+#define XCR_XFEATURE_IN_USE_MASK	0x00000001
 
 static inline u64 xgetbv(u32 index)
 {
@@ -20,4 +21,15 @@ static inline void xsetbv(u32 index, u64 value)
 	asm volatile("xsetbv" :: "a" (eax), "d" (edx), "c" (index));
 }
 
+/*
+ * Return a mask of xfeatures which are currently being tracked
+ * by the processor as being in the initial configuration.
+ *
+ * Callers should check X86_FEATURE_XGETBV1.
+ */
+static inline u64 xfeatures_in_use(void)
+{
+	return xgetbv(XCR_XFEATURE_IN_USE_MASK);
+}
+
 #endif /* _ASM_X86_FPU_XCR_H */
diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h
index 0f8b90ab18c9..cd3dd170e23a 100644
--- a/arch/x86/include/asm/fpu/xstate.h
+++ b/arch/x86/include/asm/fpu/xstate.h
@@ -92,6 +92,13 @@
 #define XFEATURE_MASK_FPSTATE	(XFEATURE_MASK_USER_RESTORE | \
 				 XFEATURE_MASK_SUPERVISOR_SUPPORTED)
 
+/*
+ * Features in this mask have space allocated in the signal frame, but may not
+ * have that space initialized when the feature is in its init state.
+ */
+#define XFEATURE_MASK_SIGFRAME_INITOPT	(XFEATURE_MASK_XTILE | \
+					 XFEATURE_MASK_USER_DYNAMIC)
+
 extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS];
 
 extern void __init update_regset_xstate_info(unsigned int size,
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index 27158436f322..048b6d5aff50 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -108,6 +108,8 @@
 #define INTEL_FAM6_ALDERLAKE		0x97	/* Golden Cove / Gracemont */
 #define INTEL_FAM6_ALDERLAKE_L		0x9A	/* Golden Cove / Gracemont */
 
+#define INTEL_FAM6_RAPTORLAKE		0xB7
+
 /* "Small Core" Processors (Atom) */
 
 #define INTEL_FAM6_ATOM_BONNELL		0x1C /* Diamondville, Pineview */
diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
index cefe1d81e2e8..9e50da3ed01a 100644
--- a/arch/x86/include/asm/kvm-x86-ops.h
+++ b/arch/x86/include/asm/kvm-x86-ops.h
@@ -47,6 +47,7 @@ KVM_X86_OP(set_dr7)
 KVM_X86_OP(cache_reg)
 KVM_X86_OP(get_rflags)
 KVM_X86_OP(set_rflags)
+KVM_X86_OP(get_if_flag)
 KVM_X86_OP(tlb_flush_all)
 KVM_X86_OP(tlb_flush_current)
 KVM_X86_OP_NULL(tlb_remote_flush)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 2acf37cc1991..555f4de47ef2 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -38,7 +38,6 @@
 #define __KVM_HAVE_ARCH_VCPU_DEBUGFS
 
 #define KVM_MAX_VCPUS 1024
-#define KVM_SOFT_MAX_VCPUS 710
 
 /*
  * In x86, the VCPU ID corresponds to the APIC ID, and APIC IDs
@@ -98,7 +97,7 @@
 	KVM_ARCH_REQ_FLAGS(25, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
 #define KVM_REQ_TLB_FLUSH_CURRENT	KVM_ARCH_REQ(26)
 #define KVM_REQ_TLB_FLUSH_GUEST \
-	KVM_ARCH_REQ_FLAGS(27, KVM_REQUEST_NO_WAKEUP)
+	KVM_ARCH_REQ_FLAGS(27, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
 #define KVM_REQ_APF_READY		KVM_ARCH_REQ(28)
 #define KVM_REQ_MSR_FILTER_CHANGED	KVM_ARCH_REQ(29)
 #define KVM_REQ_UPDATE_CPU_DIRTY_LOGGING \
@@ -364,6 +363,7 @@ union kvm_mmu_extended_role {
 		unsigned int cr4_smap:1;
 		unsigned int cr4_smep:1;
 		unsigned int cr4_la57:1;
+		unsigned int efer_lma:1;
 	};
 };
 
@@ -725,6 +725,7 @@ struct kvm_vcpu_arch {
 
 	int cpuid_nent;
 	struct kvm_cpuid_entry2 *cpuid_entries;
+	u32 kvm_cpuid_base;
 
 	u64 reserved_gpa_bits;
 	int maxphyaddr;
@@ -748,7 +749,7 @@ struct kvm_vcpu_arch {
 		u8 preempted;
 		u64 msr_val;
 		u64 last_steal;
-		struct gfn_to_pfn_cache cache;
+		struct gfn_to_hva_cache cache;
 	} st;
 
 	u64 l1_tsc_offset;
@@ -1034,6 +1035,8 @@ struct kvm_x86_msr_filter {
 #define APICV_INHIBIT_REASON_IRQWIN     3
 #define APICV_INHIBIT_REASON_PIT_REINJ  4
 #define APICV_INHIBIT_REASON_X2APIC	5
+#define APICV_INHIBIT_REASON_BLOCKIRQ	6
+#define APICV_INHIBIT_REASON_ABSENT	7
 
 struct kvm_arch {
 	unsigned long n_used_mmu_pages;
@@ -1346,6 +1349,7 @@ struct kvm_x86_ops {
 	void (*cache_reg)(struct kvm_vcpu *vcpu, enum kvm_reg reg);
 	unsigned long (*get_rflags)(struct kvm_vcpu *vcpu);
 	void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags);
+	bool (*get_if_flag)(struct kvm_vcpu *vcpu);
 
 	void (*tlb_flush_all)(struct kvm_vcpu *vcpu);
 	void (*tlb_flush_current)(struct kvm_vcpu *vcpu);
@@ -1476,6 +1480,7 @@ struct kvm_x86_ops {
 	int (*mem_enc_reg_region)(struct kvm *kvm, struct kvm_enc_region *argp);
 	int (*mem_enc_unreg_region)(struct kvm *kvm, struct kvm_enc_region *argp);
 	int (*vm_copy_enc_context_from)(struct kvm *kvm, unsigned int source_fd);
+	int (*vm_move_enc_context_from)(struct kvm *kvm, unsigned int source_fd);
 
 	int (*get_msr_feature)(struct kvm_msr_entry *entry);
 
diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index 69299878b200..56935ebb1dfe 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -83,6 +83,18 @@ static inline long kvm_hypercall4(unsigned int nr, unsigned long p1,
 	return ret;
 }
 
+static inline long kvm_sev_hypercall3(unsigned int nr, unsigned long p1,
+				      unsigned long p2, unsigned long p3)
+{
+	long ret;
+
+	asm volatile("vmmcall"
+		     : "=a"(ret)
+		     : "a"(nr), "b"(p1), "c"(p2), "d"(p3)
+		     : "memory");
+	return ret;
+}
+
 #ifdef CONFIG_KVM_GUEST
 void kvmclock_init(void);
 void kvmclock_disable(void);
diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h
index 2d4f5c17d79c..e2c6f433ed10 100644
--- a/arch/x86/include/asm/mem_encrypt.h
+++ b/arch/x86/include/asm/mem_encrypt.h
@@ -44,6 +44,8 @@ void __init sme_enable(struct boot_params *bp);
 
 int __init early_set_memory_decrypted(unsigned long vaddr, unsigned long size);
 int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size);
+void __init early_set_mem_enc_dec_hypercall(unsigned long vaddr, int npages,
+					    bool enc);
 
 void __init mem_encrypt_free_decrypted_mem(void);
 
@@ -78,6 +80,8 @@ static inline int __init
 early_set_memory_decrypted(unsigned long vaddr, unsigned long size) { return 0; }
 static inline int __init
 early_set_memory_encrypted(unsigned long vaddr, unsigned long size) { return 0; }
+static inline void __init
+early_set_mem_enc_dec_hypercall(unsigned long vaddr, int npages, bool enc) {}
 
 static inline void mem_encrypt_free_decrypted_mem(void) { }
 
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index cebec95a7124..21c4a694ca11 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -97,6 +97,12 @@ static inline void paravirt_arch_exit_mmap(struct mm_struct *mm)
 	PVOP_VCALL1(mmu.exit_mmap, mm);
 }
 
+static inline void notify_page_enc_status_changed(unsigned long pfn,
+						  int npages, bool enc)
+{
+	PVOP_VCALL3(mmu.notify_page_enc_status_changed, pfn, npages, enc);
+}
+
 #ifdef CONFIG_PARAVIRT_XXL
 static inline void load_sp0(unsigned long sp0)
 {
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index fc1151e77569..a69012e1903f 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -168,6 +168,7 @@ struct pv_mmu_ops {
 
 	/* Hook for intercepting the destruction of an mm_struct. */
 	void (*exit_mmap)(struct mm_struct *mm);
+	void (*notify_page_enc_status_changed)(unsigned long pfn, int npages, bool enc);
 
 #ifdef CONFIG_PARAVIRT_XXL
 	struct paravirt_callee_save read_cr2;
diff --git a/arch/x86/include/asm/pkru.h b/arch/x86/include/asm/pkru.h
index 4cd49afa0ca4..74f0a2d34ffd 100644
--- a/arch/x86/include/asm/pkru.h
+++ b/arch/x86/include/asm/pkru.h
@@ -4,8 +4,8 @@
 
 #include <asm/cpufeature.h>
 
-#define PKRU_AD_BIT 0x1
-#define PKRU_WD_BIT 0x2
+#define PKRU_AD_BIT 0x1u
+#define PKRU_WD_BIT 0x2u
 #define PKRU_BITS_PER_PKEY 2
 
 #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 191878a65c61..355d38c0cf60 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -806,11 +806,14 @@ static inline u32 amd_get_nodes_per_socket(void)	{ return 0; }
 static inline u32 amd_get_highest_perf(void)		{ return 0; }
 #endif
 
+#define for_each_possible_hypervisor_cpuid_base(function) \
+	for (function = 0x40000000; function < 0x40010000; function += 0x100)
+
 static inline uint32_t hypervisor_cpuid_base(const char *sig, uint32_t leaves)
 {
 	uint32_t base, eax, signature[3];
 
-	for (base = 0x40000000; base < 0x40010000; base += 0x100) {
+	for_each_possible_hypervisor_cpuid_base(base) {
 		cpuid(base, &eax, &signature[0], &signature[1], &signature[2]);
 
 		if (!memcmp(sig, signature, 12) &&
diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h
index 43fa081a1adb..872617542bbc 100644
--- a/arch/x86/include/asm/set_memory.h
+++ b/arch/x86/include/asm/set_memory.h
@@ -83,6 +83,7 @@ int set_pages_rw(struct page *page, int numpages);
 int set_direct_map_invalid_noflush(struct page *page);
 int set_direct_map_default_noflush(struct page *page);
 bool kernel_page_present(struct page *page);
+void notify_range_enc_status_changed(unsigned long vaddr, int npages, bool enc);
 
 extern int kernel_set_to_readonly;
 
diff --git a/arch/x86/include/asm/sev-common.h b/arch/x86/include/asm/sev-common.h
index 2cef6c5a52c2..6acaf5af0a3d 100644
--- a/arch/x86/include/asm/sev-common.h
+++ b/arch/x86/include/asm/sev-common.h
@@ -73,4 +73,15 @@
 
 #define GHCB_RESP_CODE(v)		((v) & GHCB_MSR_INFO_MASK)
 
+/*
+ * Error codes related to GHCB input that can be communicated back to the guest
+ * by setting the lower 32-bits of the GHCB SW_EXITINFO1 field to 2.
+ */
+#define GHCB_ERR_NOT_REGISTERED		1
+#define GHCB_ERR_INVALID_USAGE		2
+#define GHCB_ERR_INVALID_SCRATCH_AREA	3
+#define GHCB_ERR_MISSING_INPUT		4
+#define GHCB_ERR_INVALID_INPUT		5
+#define GHCB_ERR_INVALID_EVENT		6
+
 #endif
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 08b0e90623ad..81a0211a372d 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -126,6 +126,7 @@ static inline void arch_send_call_function_ipi_mask(const struct cpumask *mask)
 
 void cpu_disable_common(void);
 void native_smp_prepare_boot_cpu(void);
+void smp_prepare_cpus_common(void);
 void native_smp_prepare_cpus(unsigned int max_cpus);
 void calculate_max_logical_packages(void);
 void native_smp_cpus_done(unsigned int max_cpus);
diff --git a/arch/x86/include/asm/static_call.h b/arch/x86/include/asm/static_call.h
index cbb67b6030f9..39ebe0511869 100644
--- a/arch/x86/include/asm/static_call.h
+++ b/arch/x86/include/asm/static_call.h
@@ -27,6 +27,7 @@
 	    ".globl " STATIC_CALL_TRAMP_STR(name) "		\n"	\
 	    STATIC_CALL_TRAMP_STR(name) ":			\n"	\
 	    insns "						\n"	\
+	    ".byte 0x53, 0x43, 0x54				\n"	\
 	    ".type " STATIC_CALL_TRAMP_STR(name) ", @function	\n"	\
 	    ".size " STATIC_CALL_TRAMP_STR(name) ", . - " STATIC_CALL_TRAMP_STR(name) " \n" \
 	    ".popsection					\n")
diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index 0575f5863b7f..e5e0fe10c692 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -281,13 +281,13 @@ HYPERVISOR_callback_op(int cmd, void *arg)
 	return _hypercall2(int, callback_op, cmd, arg);
 }
 
-static inline int
+static __always_inline int
 HYPERVISOR_set_debugreg(int reg, unsigned long value)
 {
 	return _hypercall2(int, set_debugreg, reg, value);
 }
 
-static inline unsigned long
+static __always_inline unsigned long
 HYPERVISOR_get_debugreg(int reg)
 {
 	return _hypercall1(unsigned long, get_debugreg, reg);
diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h
index 4957f59deb40..5adab895127e 100644
--- a/arch/x86/include/asm/xen/hypervisor.h
+++ b/arch/x86/include/asm/xen/hypervisor.h
@@ -64,6 +64,7 @@ void xen_arch_unregister_cpu(int num);
 
 #ifdef CONFIG_PVH
 void __init xen_pvh_init(struct boot_params *boot_params);
+void __init mem_map_via_hcall(struct boot_params *boot_params_p);
 #endif
 
 #endif /* _ASM_X86_XEN_HYPERVISOR_H */
diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h
index 5146bbab84d4..6e64b27b2c1e 100644
--- a/arch/x86/include/uapi/asm/kvm_para.h
+++ b/arch/x86/include/uapi/asm/kvm_para.h
@@ -8,6 +8,7 @@
  * should be used to determine that a VM is running under KVM.
  */
 #define KVM_CPUID_SIGNATURE	0x40000000
+#define KVM_SIGNATURE "KVMKVMKVM\0\0\0"
 
 /* This CPUID returns two feature bitmaps in eax, edx. Before enabling
  * a particular paravirtualization, the appropriate feature bit should
diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c
index cb2fdd130aae..c881bcafba7d 100644
--- a/arch/x86/kernel/cpu/cpuid-deps.c
+++ b/arch/x86/kernel/cpu/cpuid-deps.c
@@ -76,6 +76,7 @@ static const struct cpuid_dep cpuid_deps[] = {
 	{ X86_FEATURE_SGX1,			X86_FEATURE_SGX       },
 	{ X86_FEATURE_SGX2,			X86_FEATURE_SGX1      },
 	{ X86_FEATURE_XFD,			X86_FEATURE_XSAVES    },
+	{ X86_FEATURE_XFD,			X86_FEATURE_XGETBV1   },
 	{ X86_FEATURE_AMX_TILE,			X86_FEATURE_XFD       },
 	{}
 };
diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c
index acfd5d9f93c6..bb9a46a804bf 100644
--- a/arch/x86/kernel/cpu/mce/intel.c
+++ b/arch/x86/kernel/cpu/mce/intel.c
@@ -547,12 +547,13 @@ bool intel_filter_mce(struct mce *m)
 {
 	struct cpuinfo_x86 *c = &boot_cpu_data;
 
-	/* MCE errata HSD131, HSM142, HSW131, BDM48, and HSM142 */
+	/* MCE errata HSD131, HSM142, HSW131, BDM48, HSM142 and SKX37 */
 	if ((c->x86 == 6) &&
 	    ((c->x86_model == INTEL_FAM6_HASWELL) ||
 	     (c->x86_model == INTEL_FAM6_HASWELL_L) ||
 	     (c->x86_model == INTEL_FAM6_BROADWELL) ||
-	     (c->x86_model == INTEL_FAM6_HASWELL_G)) &&
+	     (c->x86_model == INTEL_FAM6_HASWELL_G) ||
+	     (c->x86_model == INTEL_FAM6_SKYLAKE_X)) &&
 	    (m->bank == 0) &&
 	    ((m->status & 0xa0000000ffffffff) == 0x80000000000f0005))
 		return true;
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 4794b716ec79..ff55df60228f 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -163,12 +163,22 @@ static uint32_t  __init ms_hyperv_platform(void)
 	cpuid(HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS,
 	      &eax, &hyp_signature[0], &hyp_signature[1], &hyp_signature[2]);
 
-	if (eax >= HYPERV_CPUID_MIN &&
-	    eax <= HYPERV_CPUID_MAX &&
-	    !memcmp("Microsoft Hv", hyp_signature, 12))
-		return HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS;
+	if (eax < HYPERV_CPUID_MIN || eax > HYPERV_CPUID_MAX ||
+	    memcmp("Microsoft Hv", hyp_signature, 12))
+		return 0;
 
-	return 0;
+	/* HYPERCALL and VP_INDEX MSRs are mandatory for all features. */
+	eax = cpuid_eax(HYPERV_CPUID_FEATURES);
+	if (!(eax & HV_MSR_HYPERCALL_AVAILABLE)) {
+		pr_warn("x86/hyperv: HYPERCALL MSR not available.\n");
+		return 0;
+	}
+	if (!(eax & HV_MSR_VP_INDEX_AVAILABLE)) {
+		pr_warn("x86/hyperv: VP_INDEX MSR not available.\n");
+		return 0;
+	}
+
+	return HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS;
 }
 
 static unsigned char hv_get_nmi_reason(void)
diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c
index 63d3de02bbcc..8471a8b9b48e 100644
--- a/arch/x86/kernel/cpu/sgx/main.c
+++ b/arch/x86/kernel/cpu/sgx/main.c
@@ -28,8 +28,7 @@ static DECLARE_WAIT_QUEUE_HEAD(ksgxd_waitq);
 static LIST_HEAD(sgx_active_page_list);
 static DEFINE_SPINLOCK(sgx_reclaimer_lock);
 
-/* The free page list lock protected variables prepend the lock. */
-static unsigned long sgx_nr_free_pages;
+static atomic_long_t sgx_nr_free_pages = ATOMIC_LONG_INIT(0);
 
 /* Nodes with one or more EPC sections. */
 static nodemask_t sgx_numa_mask;
@@ -403,14 +402,15 @@ skip:
 
 		spin_lock(&node->lock);
 		list_add_tail(&epc_page->list, &node->free_page_list);
-		sgx_nr_free_pages++;
 		spin_unlock(&node->lock);
+		atomic_long_inc(&sgx_nr_free_pages);
 	}
 }
 
 static bool sgx_should_reclaim(unsigned long watermark)
 {
-	return sgx_nr_free_pages < watermark && !list_empty(&sgx_active_page_list);
+	return atomic_long_read(&sgx_nr_free_pages) < watermark &&
+	       !list_empty(&sgx_active_page_list);
 }
 
 static int ksgxd(void *p)
@@ -471,9 +471,9 @@ static struct sgx_epc_page *__sgx_alloc_epc_page_from_node(int nid)
 
 	page = list_first_entry(&node->free_page_list, struct sgx_epc_page, list);
 	list_del_init(&page->list);
-	sgx_nr_free_pages--;
 
 	spin_unlock(&node->lock);
+	atomic_long_dec(&sgx_nr_free_pages);
 
 	return page;
 }
@@ -625,9 +625,9 @@ void sgx_free_epc_page(struct sgx_epc_page *page)
 	spin_lock(&node->lock);
 
 	list_add_tail(&page->list, &node->free_page_list);
-	sgx_nr_free_pages++;
 
 	spin_unlock(&node->lock);
+	atomic_long_inc(&sgx_nr_free_pages);
 }
 
 static bool __init sgx_setup_epc_section(u64 phys_addr, u64 size,
diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
index d5958278eba6..91d4b6de58ab 100644
--- a/arch/x86/kernel/fpu/signal.c
+++ b/arch/x86/kernel/fpu/signal.c
@@ -118,7 +118,7 @@ static inline bool save_xstate_epilog(void __user *buf, int ia32_frame,
 				      struct fpstate *fpstate)
 {
 	struct xregs_state __user *x = buf;
-	struct _fpx_sw_bytes sw_bytes;
+	struct _fpx_sw_bytes sw_bytes = {};
 	u32 xfeatures;
 	int err;
 
diff --git a/arch/x86/kernel/fpu/xstate.h b/arch/x86/kernel/fpu/xstate.h
index e18210dff88c..86ea7c0fa2f6 100644
--- a/arch/x86/kernel/fpu/xstate.h
+++ b/arch/x86/kernel/fpu/xstate.h
@@ -4,6 +4,7 @@
 
 #include <asm/cpufeature.h>
 #include <asm/fpu/xstate.h>
+#include <asm/fpu/xcr.h>
 
 #ifdef CONFIG_X86_64
 DECLARE_PER_CPU(u64, xfd_state);
@@ -199,6 +200,32 @@ static inline void os_xrstor_supervisor(struct fpstate *fpstate)
 }
 
 /*
+ * XSAVE itself always writes all requested xfeatures.  Removing features
+ * from the request bitmap reduces the features which are written.
+ * Generate a mask of features which must be written to a sigframe.  The
+ * unset features can be optimized away and not written.
+ *
+ * This optimization is user-visible.  Only use for states where
+ * uninitialized sigframe contents are tolerable, like dynamic features.
+ *
+ * Users of buffers produced with this optimization must check XSTATE_BV
+ * to determine which features have been optimized out.
+ */
+static inline u64 xfeatures_need_sigframe_write(void)
+{
+	u64 xfeaures_to_write;
+
+	/* In-use features must be written: */
+	xfeaures_to_write = xfeatures_in_use();
+
+	/* Also write all non-optimizable sigframe features: */
+	xfeaures_to_write |= XFEATURE_MASK_USER_SUPPORTED &
+			     ~XFEATURE_MASK_SIGFRAME_INITOPT;
+
+	return xfeaures_to_write;
+}
+
+/*
  * Save xstate to user space xsave area.
  *
  * We don't use modified optimization because xrstor/xrstors might track
@@ -220,10 +247,16 @@ static inline int xsave_to_user_sigframe(struct xregs_state __user *buf)
 	 */
 	struct fpstate *fpstate = current->thread.fpu.fpstate;
 	u64 mask = fpstate->user_xfeatures;
-	u32 lmask = mask;
-	u32 hmask = mask >> 32;
+	u32 lmask;
+	u32 hmask;
 	int err;
 
+	/* Optimize away writing unnecessary xfeatures: */
+	if (fpu_state_size_dynamic())
+		mask &= xfeatures_need_sigframe_write();
+
+	lmask = mask;
+	hmask = mask >> 32;
 	xfd_validate_state(fpstate, mask, false);
 
 	stac();
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 8863d1941f1b..59abbdad7729 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -28,6 +28,7 @@
 #include <linux/swait.h>
 #include <linux/syscore_ops.h>
 #include <linux/cc_platform.h>
+#include <linux/efi.h>
 #include <asm/timer.h>
 #include <asm/cpu.h>
 #include <asm/traps.h>
@@ -41,6 +42,7 @@
 #include <asm/ptrace.h>
 #include <asm/reboot.h>
 #include <asm/svm.h>
+#include <asm/e820/api.h>
 
 DEFINE_STATIC_KEY_FALSE(kvm_async_pf_enabled);
 
@@ -434,6 +436,8 @@ static void kvm_guest_cpu_offline(bool shutdown)
 	kvm_disable_steal_time();
 	if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
 		wrmsrl(MSR_KVM_PV_EOI_EN, 0);
+	if (kvm_para_has_feature(KVM_FEATURE_MIGRATION_CONTROL))
+		wrmsrl(MSR_KVM_MIGRATION_CONTROL, 0);
 	kvm_pv_disable_apf();
 	if (!shutdown)
 		apf_task_wake_all();
@@ -548,6 +552,55 @@ static void kvm_send_ipi_mask_allbutself(const struct cpumask *mask, int vector)
 	__send_ipi_mask(local_mask, vector);
 }
 
+static int __init setup_efi_kvm_sev_migration(void)
+{
+	efi_char16_t efi_sev_live_migration_enabled[] = L"SevLiveMigrationEnabled";
+	efi_guid_t efi_variable_guid = AMD_SEV_MEM_ENCRYPT_GUID;
+	efi_status_t status;
+	unsigned long size;
+	bool enabled;
+
+	if (!cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT) ||
+	    !kvm_para_has_feature(KVM_FEATURE_MIGRATION_CONTROL))
+		return 0;
+
+	if (!efi_enabled(EFI_BOOT))
+		return 0;
+
+	if (!efi_enabled(EFI_RUNTIME_SERVICES)) {
+		pr_info("%s : EFI runtime services are not enabled\n", __func__);
+		return 0;
+	}
+
+	size = sizeof(enabled);
+
+	/* Get variable contents into buffer */
+	status = efi.get_variable(efi_sev_live_migration_enabled,
+				  &efi_variable_guid, NULL, &size, &enabled);
+
+	if (status == EFI_NOT_FOUND) {
+		pr_info("%s : EFI live migration variable not found\n", __func__);
+		return 0;
+	}
+
+	if (status != EFI_SUCCESS) {
+		pr_info("%s : EFI variable retrieval failed\n", __func__);
+		return 0;
+	}
+
+	if (enabled == 0) {
+		pr_info("%s: live migration disabled in EFI\n", __func__);
+		return 0;
+	}
+
+	pr_info("%s : live migration enabled in EFI\n", __func__);
+	wrmsrl(MSR_KVM_MIGRATION_CONTROL, KVM_MIGRATION_READY);
+
+	return 1;
+}
+
+late_initcall(setup_efi_kvm_sev_migration);
+
 /*
  * Set the IPI entry points
  */
@@ -756,7 +809,7 @@ static noinline uint32_t __kvm_cpuid_base(void)
 		return 0;	/* So we don't blow up on old processors */
 
 	if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
-		return hypervisor_cpuid_base("KVMKVMKVM\0\0\0", 0);
+		return hypervisor_cpuid_base(KVM_SIGNATURE, 0);
 
 	return 0;
 }
@@ -806,8 +859,62 @@ static bool __init kvm_msi_ext_dest_id(void)
 	return kvm_para_has_feature(KVM_FEATURE_MSI_EXT_DEST_ID);
 }
 
+static void kvm_sev_hc_page_enc_status(unsigned long pfn, int npages, bool enc)
+{
+	kvm_sev_hypercall3(KVM_HC_MAP_GPA_RANGE, pfn << PAGE_SHIFT, npages,
+			   KVM_MAP_GPA_RANGE_ENC_STAT(enc) | KVM_MAP_GPA_RANGE_PAGE_SZ_4K);
+}
+
 static void __init kvm_init_platform(void)
 {
+	if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT) &&
+	    kvm_para_has_feature(KVM_FEATURE_MIGRATION_CONTROL)) {
+		unsigned long nr_pages;
+		int i;
+
+		pv_ops.mmu.notify_page_enc_status_changed =
+			kvm_sev_hc_page_enc_status;
+
+		/*
+		 * Reset the host's shared pages list related to kernel
+		 * specific page encryption status settings before we load a
+		 * new kernel by kexec. Reset the page encryption status
+		 * during early boot intead of just before kexec to avoid SMP
+		 * races during kvm_pv_guest_cpu_reboot().
+		 * NOTE: We cannot reset the complete shared pages list
+		 * here as we need to retain the UEFI/OVMF firmware
+		 * specific settings.
+		 */
+
+		for (i = 0; i < e820_table->nr_entries; i++) {
+			struct e820_entry *entry = &e820_table->entries[i];
+
+			if (entry->type != E820_TYPE_RAM)
+				continue;
+
+			nr_pages = DIV_ROUND_UP(entry->size, PAGE_SIZE);
+
+			kvm_sev_hypercall3(KVM_HC_MAP_GPA_RANGE, entry->addr,
+				       nr_pages,
+				       KVM_MAP_GPA_RANGE_ENCRYPTED | KVM_MAP_GPA_RANGE_PAGE_SZ_4K);
+		}
+
+		/*
+		 * Ensure that _bss_decrypted section is marked as decrypted in the
+		 * shared pages list.
+		 */
+		nr_pages = DIV_ROUND_UP(__end_bss_decrypted - __start_bss_decrypted,
+					PAGE_SIZE);
+		early_set_mem_enc_dec_hypercall((unsigned long)__start_bss_decrypted,
+						nr_pages, 0);
+
+		/*
+		 * If not booted using EFI, enable Live migration support.
+		 */
+		if (!efi_enabled(EFI_BOOT))
+			wrmsrl(MSR_KVM_MIGRATION_CONTROL,
+			       KVM_MIGRATION_READY);
+	}
 	kvmclock_init();
 	x86_platform.apic_post_init = kvm_apic_init;
 }
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 7157c2df3bc2..7f7636aac620 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -337,6 +337,7 @@ struct paravirt_patch_template pv_ops = {
 			(void (*)(struct mmu_gather *, void *))tlb_remove_page,
 
 	.mmu.exit_mmap		= paravirt_nop,
+	.mmu.notify_page_enc_status_changed	= paravirt_nop,
 
 #ifdef CONFIG_PARAVIRT_XXL
 	.mmu.read_cr2		= __PV_IS_CALLEE_SAVE(pv_native_read_cr2),
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index e9ee8b526319..04143a653a8a 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -964,6 +964,9 @@ unsigned long __get_wchan(struct task_struct *p)
 	struct unwind_state state;
 	unsigned long addr = 0;
 
+	if (!try_get_task_stack(p))
+		return 0;
+
 	for (unwind_start(&state, p, NULL, NULL); !unwind_done(&state);
 	     unwind_next_frame(&state)) {
 		addr = unwind_get_return_address(&state);
@@ -974,6 +977,8 @@ unsigned long __get_wchan(struct task_struct *p)
 		break;
 	}
 
+	put_task_stack(p);
+
 	return addr;
 }
 
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 49b596db5631..e04f5e6eb33f 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -713,9 +713,6 @@ static void __init early_reserve_memory(void)
 
 	early_reserve_initrd();
 
-	if (efi_enabled(EFI_BOOT))
-		efi_memblock_x86_reserve_range();
-
 	memblock_x86_reserve_range_setup_data();
 
 	reserve_ibft_region();
@@ -890,6 +887,9 @@ void __init setup_arch(char **cmdline_p)
 
 	parse_early_param();
 
+	if (efi_enabled(EFI_BOOT))
+		efi_memblock_x86_reserve_range();
+
 #ifdef CONFIG_MEMORY_HOTPLUG
 	/*
 	 * Memory used by the kernel cannot be hot-removed because Linux
diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c
index 74f0ec955384..a9fc2ac7a8bd 100644
--- a/arch/x86/kernel/sev.c
+++ b/arch/x86/kernel/sev.c
@@ -294,11 +294,6 @@ static enum es_result vc_write_mem(struct es_em_ctxt *ctxt,
 				   char *dst, char *buf, size_t size)
 {
 	unsigned long error_code = X86_PF_PROT | X86_PF_WRITE;
-	char __user *target = (char __user *)dst;
-	u64 d8;
-	u32 d4;
-	u16 d2;
-	u8  d1;
 
 	/*
 	 * This function uses __put_user() independent of whether kernel or user
@@ -320,26 +315,42 @@ static enum es_result vc_write_mem(struct es_em_ctxt *ctxt,
 	 * instructions here would cause infinite nesting.
 	 */
 	switch (size) {
-	case 1:
+	case 1: {
+		u8 d1;
+		u8 __user *target = (u8 __user *)dst;
+
 		memcpy(&d1, buf, 1);
 		if (__put_user(d1, target))
 			goto fault;
 		break;
-	case 2:
+	}
+	case 2: {
+		u16 d2;
+		u16 __user *target = (u16 __user *)dst;
+
 		memcpy(&d2, buf, 2);
 		if (__put_user(d2, target))
 			goto fault;
 		break;
-	case 4:
+	}
+	case 4: {
+		u32 d4;
+		u32 __user *target = (u32 __user *)dst;
+
 		memcpy(&d4, buf, 4);
 		if (__put_user(d4, target))
 			goto fault;
 		break;
-	case 8:
+	}
+	case 8: {
+		u64 d8;
+		u64 __user *target = (u64 __user *)dst;
+
 		memcpy(&d8, buf, 8);
 		if (__put_user(d8, target))
 			goto fault;
 		break;
+	}
 	default:
 		WARN_ONCE(1, "%s: Invalid size: %zu\n", __func__, size);
 		return ES_UNSUPPORTED;
@@ -362,11 +373,6 @@ static enum es_result vc_read_mem(struct es_em_ctxt *ctxt,
 				  char *src, char *buf, size_t size)
 {
 	unsigned long error_code = X86_PF_PROT;
-	char __user *s = (char __user *)src;
-	u64 d8;
-	u32 d4;
-	u16 d2;
-	u8  d1;
 
 	/*
 	 * This function uses __get_user() independent of whether kernel or user
@@ -388,26 +394,41 @@ static enum es_result vc_read_mem(struct es_em_ctxt *ctxt,
 	 * instructions here would cause infinite nesting.
 	 */
 	switch (size) {
-	case 1:
+	case 1: {
+		u8 d1;
+		u8 __user *s = (u8 __user *)src;
+
 		if (__get_user(d1, s))
 			goto fault;
 		memcpy(buf, &d1, 1);
 		break;
-	case 2:
+	}
+	case 2: {
+		u16 d2;
+		u16 __user *s = (u16 __user *)src;
+
 		if (__get_user(d2, s))
 			goto fault;
 		memcpy(buf, &d2, 2);
 		break;
-	case 4:
+	}
+	case 4: {
+		u32 d4;
+		u32 __user *s = (u32 __user *)src;
+
 		if (__get_user(d4, s))
 			goto fault;
 		memcpy(buf, &d4, 4);
 		break;
-	case 8:
+	}
+	case 8: {
+		u64 d8;
+		u64 __user *s = (u64 __user *)src;
 		if (__get_user(d8, s))
 			goto fault;
 		memcpy(buf, &d8, 8);
 		break;
+	}
 	default:
 		WARN_ONCE(1, "%s: Invalid size: %zu\n", __func__, size);
 		return ES_UNSUPPORTED;
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 8241927addff..617012f4619f 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -579,6 +579,17 @@ static struct sched_domain_topology_level x86_numa_in_package_topology[] = {
 	{ NULL, },
 };
 
+static struct sched_domain_topology_level x86_hybrid_topology[] = {
+#ifdef CONFIG_SCHED_SMT
+	{ cpu_smt_mask, x86_smt_flags, SD_INIT_NAME(SMT) },
+#endif
+#ifdef CONFIG_SCHED_MC
+	{ cpu_coregroup_mask, x86_core_flags, SD_INIT_NAME(MC) },
+#endif
+	{ cpu_cpu_mask, SD_INIT_NAME(DIE) },
+	{ NULL, },
+};
+
 static struct sched_domain_topology_level x86_topology[] = {
 #ifdef CONFIG_SCHED_SMT
 	{ cpu_smt_mask, x86_smt_flags, SD_INIT_NAME(SMT) },
@@ -1350,12 +1361,7 @@ static void __init smp_get_logical_apicid(void)
 		cpu0_logical_apicid = GET_APIC_LOGICAL_ID(apic_read(APIC_LDR));
 }
 
-/*
- * Prepare for SMP bootup.
- * @max_cpus: configured maximum number of CPUs, It is a legacy parameter
- *            for common interface support.
- */
-void __init native_smp_prepare_cpus(unsigned int max_cpus)
+void __init smp_prepare_cpus_common(void)
 {
 	unsigned int i;
 
@@ -1386,6 +1392,17 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 	set_sched_topology(x86_topology);
 
 	set_cpu_sibling_map(0);
+}
+
+/*
+ * Prepare for SMP bootup.
+ * @max_cpus: configured maximum number of CPUs, It is a legacy parameter
+ *            for common interface support.
+ */
+void __init native_smp_prepare_cpus(unsigned int max_cpus)
+{
+	smp_prepare_cpus_common();
+
 	init_freq_invariance(false, false);
 	smp_sanity_check();
 
@@ -1463,8 +1480,11 @@ void __init native_smp_cpus_done(unsigned int max_cpus)
 
 	calculate_max_logical_packages();
 
+	/* XXX for now assume numa-in-package and hybrid don't overlap */
 	if (x86_has_numa_in_package)
 		set_sched_topology(x86_numa_in_package_topology);
+	if (cpu_feature_enabled(X86_FEATURE_HYBRID_CPU))
+		set_sched_topology(x86_hybrid_topology);
 
 	nmi_selftest();
 	impress_friends();
diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c
index ea028e736831..9c407a33a774 100644
--- a/arch/x86/kernel/static_call.c
+++ b/arch/x86/kernel/static_call.c
@@ -56,10 +56,15 @@ static void __ref __static_call_transform(void *insn, enum insn_type type, void
 	text_poke_bp(insn, code, size, emulate);
 }
 
-static void __static_call_validate(void *insn, bool tail)
+static void __static_call_validate(void *insn, bool tail, bool tramp)
 {
 	u8 opcode = *(u8 *)insn;
 
+	if (tramp && memcmp(insn+5, "SCT", 3)) {
+		pr_err("trampoline signature fail");
+		BUG();
+	}
+
 	if (tail) {
 		if (opcode == JMP32_INSN_OPCODE ||
 		    opcode == RET_INSN_OPCODE)
@@ -74,7 +79,8 @@ static void __static_call_validate(void *insn, bool tail)
 	/*
 	 * If we ever trigger this, our text is corrupt, we'll probably not live long.
 	 */
-	WARN_ONCE(1, "unexpected static_call insn opcode 0x%x at %pS\n", opcode, insn);
+	pr_err("unexpected static_call insn opcode 0x%x at %pS\n", opcode, insn);
+	BUG();
 }
 
 static inline enum insn_type __sc_insn(bool null, bool tail)
@@ -97,12 +103,12 @@ void arch_static_call_transform(void *site, void *tramp, void *func, bool tail)
 	mutex_lock(&text_mutex);
 
 	if (tramp) {
-		__static_call_validate(tramp, true);
+		__static_call_validate(tramp, true, true);
 		__static_call_transform(tramp, __sc_insn(!func, true), func);
 	}
 
 	if (IS_ENABLED(CONFIG_HAVE_STATIC_CALL_INLINE) && site) {
-		__static_call_validate(site, tail);
+		__static_call_validate(site, tail, false);
 		__static_call_transform(site, __sc_insn(!func, tail), func);
 	}
 
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 2e076a459a0c..a698196377be 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -1180,6 +1180,12 @@ void mark_tsc_unstable(char *reason)
 
 EXPORT_SYMBOL_GPL(mark_tsc_unstable);
 
+static void __init tsc_disable_clocksource_watchdog(void)
+{
+	clocksource_tsc_early.flags &= ~CLOCK_SOURCE_MUST_VERIFY;
+	clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY;
+}
+
 static void __init check_system_tsc_reliable(void)
 {
 #if defined(CONFIG_MGEODEGX1) || defined(CONFIG_MGEODE_LX) || defined(CONFIG_X86_GENERIC)
@@ -1196,6 +1202,23 @@ static void __init check_system_tsc_reliable(void)
 #endif
 	if (boot_cpu_has(X86_FEATURE_TSC_RELIABLE))
 		tsc_clocksource_reliable = 1;
+
+	/*
+	 * Disable the clocksource watchdog when the system has:
+	 *  - TSC running at constant frequency
+	 *  - TSC which does not stop in C-States
+	 *  - the TSC_ADJUST register which allows to detect even minimal
+	 *    modifications
+	 *  - not more than two sockets. As the number of sockets cannot be
+	 *    evaluated at the early boot stage where this has to be
+	 *    invoked, check the number of online memory nodes as a
+	 *    fallback solution which is an reasonable estimate.
+	 */
+	if (boot_cpu_has(X86_FEATURE_CONSTANT_TSC) &&
+	    boot_cpu_has(X86_FEATURE_NONSTOP_TSC) &&
+	    boot_cpu_has(X86_FEATURE_TSC_ADJUST) &&
+	    nr_online_nodes <= 2)
+		tsc_disable_clocksource_watchdog();
 }
 
 /*
@@ -1387,9 +1410,6 @@ static int __init init_tsc_clocksource(void)
 	if (tsc_unstable)
 		goto unreg;
 
-	if (tsc_clocksource_reliable || no_tsc_watchdog)
-		clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY;
-
 	if (boot_cpu_has(X86_FEATURE_NONSTOP_TSC_S3))
 		clocksource_tsc.flags |= CLOCK_SOURCE_SUSPEND_NONSTOP;
 
@@ -1527,7 +1547,7 @@ void __init tsc_init(void)
 	}
 
 	if (tsc_clocksource_reliable || no_tsc_watchdog)
-		clocksource_tsc_early.flags &= ~CLOCK_SOURCE_MUST_VERIFY;
+		tsc_disable_clocksource_watchdog();
 
 	clocksource_register_khz(&clocksource_tsc_early, tsc_khz);
 	detect_art();
diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c
index 50a4515fe0ad..9452dc9664b5 100644
--- a/arch/x86/kernel/tsc_sync.c
+++ b/arch/x86/kernel/tsc_sync.c
@@ -30,6 +30,7 @@ struct tsc_adjust {
 };
 
 static DEFINE_PER_CPU(struct tsc_adjust, tsc_adjust);
+static struct timer_list tsc_sync_check_timer;
 
 /*
  * TSC's on different sockets may be reset asynchronously.
@@ -77,6 +78,46 @@ void tsc_verify_tsc_adjust(bool resume)
 	}
 }
 
+/*
+ * Normally the tsc_sync will be checked every time system enters idle
+ * state, but there is still caveat that a system won't enter idle,
+ * either because it's too busy or configured purposely to not enter
+ * idle.
+ *
+ * So setup a periodic timer (every 10 minutes) to make sure the check
+ * is always on.
+ */
+
+#define SYNC_CHECK_INTERVAL		(HZ * 600)
+
+static void tsc_sync_check_timer_fn(struct timer_list *unused)
+{
+	int next_cpu;
+
+	tsc_verify_tsc_adjust(false);
+
+	/* Run the check for all onlined CPUs in turn */
+	next_cpu = cpumask_next(raw_smp_processor_id(), cpu_online_mask);
+	if (next_cpu >= nr_cpu_ids)
+		next_cpu = cpumask_first(cpu_online_mask);
+
+	tsc_sync_check_timer.expires += SYNC_CHECK_INTERVAL;
+	add_timer_on(&tsc_sync_check_timer, next_cpu);
+}
+
+static int __init start_sync_check_timer(void)
+{
+	if (!cpu_feature_enabled(X86_FEATURE_TSC_ADJUST) || tsc_clocksource_reliable)
+		return 0;
+
+	timer_setup(&tsc_sync_check_timer, tsc_sync_check_timer_fn, 0);
+	tsc_sync_check_timer.expires = jiffies + SYNC_CHECK_INTERVAL;
+	add_timer(&tsc_sync_check_timer);
+
+	return 0;
+}
+late_initcall(start_sync_check_timer);
+
 static void tsc_sanitize_first_cpu(struct tsc_adjust *cur, s64 bootval,
 				   unsigned int cpu, bool bootcpu)
 {
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index f14f69d7aa3c..c21bcd668284 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -106,7 +106,7 @@ void save_v86_state(struct kernel_vm86_regs *regs, int retval)
 	 */
 	local_irq_enable();
 
-	BUG_ON(!vm86 || !vm86->user_vm86);
+	BUG_ON(!vm86);
 
 	set_flags(regs->pt.flags, VEFLAGS, X86_EFLAGS_VIF | vm86->veflags_mask);
 	user = vm86->user_vm86;
@@ -160,7 +160,7 @@ Efault_end:
 	user_access_end();
 Efault:
 	pr_alert("could not access userspace vm86 info\n");
-	force_fatal_sig(SIGSEGV);
+	force_exit_sig(SIGSEGV);
 	goto exit_vm86;
 }
 
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 2d70edb0f323..07e9215e911d 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -99,11 +99,45 @@ static int kvm_check_cpuid(struct kvm_cpuid_entry2 *entries, int nent)
 	return 0;
 }
 
-void kvm_update_pv_runtime(struct kvm_vcpu *vcpu)
+static void kvm_update_kvm_cpuid_base(struct kvm_vcpu *vcpu)
 {
-	struct kvm_cpuid_entry2 *best;
+	u32 function;
+	struct kvm_cpuid_entry2 *entry;
+
+	vcpu->arch.kvm_cpuid_base = 0;
+
+	for_each_possible_hypervisor_cpuid_base(function) {
+		entry = kvm_find_cpuid_entry(vcpu, function, 0);
 
-	best = kvm_find_cpuid_entry(vcpu, KVM_CPUID_FEATURES, 0);
+		if (entry) {
+			u32 signature[3];
+
+			signature[0] = entry->ebx;
+			signature[1] = entry->ecx;
+			signature[2] = entry->edx;
+
+			BUILD_BUG_ON(sizeof(signature) > sizeof(KVM_SIGNATURE));
+			if (!memcmp(signature, KVM_SIGNATURE, sizeof(signature))) {
+				vcpu->arch.kvm_cpuid_base = function;
+				break;
+			}
+		}
+	}
+}
+
+static struct kvm_cpuid_entry2 *kvm_find_kvm_cpuid_features(struct kvm_vcpu *vcpu)
+{
+	u32 base = vcpu->arch.kvm_cpuid_base;
+
+	if (!base)
+		return NULL;
+
+	return kvm_find_cpuid_entry(vcpu, base | KVM_CPUID_FEATURES, 0);
+}
+
+void kvm_update_pv_runtime(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpuid_entry2 *best = kvm_find_kvm_cpuid_features(vcpu);
 
 	/*
 	 * save the feature bitmap to avoid cpuid lookup for every PV
@@ -142,7 +176,7 @@ void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu)
 		     cpuid_entry_has(best, X86_FEATURE_XSAVEC)))
 		best->ebx = xstate_required_size(vcpu->arch.xcr0, true);
 
-	best = kvm_find_cpuid_entry(vcpu, KVM_CPUID_FEATURES, 0);
+	best = kvm_find_kvm_cpuid_features(vcpu);
 	if (kvm_hlt_in_guest(vcpu->kvm) && best &&
 		(best->eax & (1 << KVM_FEATURE_PV_UNHALT)))
 		best->eax &= ~(1 << KVM_FEATURE_PV_UNHALT);
@@ -239,6 +273,26 @@ u64 kvm_vcpu_reserved_gpa_bits_raw(struct kvm_vcpu *vcpu)
 	return rsvd_bits(cpuid_maxphyaddr(vcpu), 63);
 }
 
+static int kvm_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *e2,
+                        int nent)
+{
+    int r;
+
+    r = kvm_check_cpuid(e2, nent);
+    if (r)
+        return r;
+
+    kvfree(vcpu->arch.cpuid_entries);
+    vcpu->arch.cpuid_entries = e2;
+    vcpu->arch.cpuid_nent = nent;
+
+    kvm_update_kvm_cpuid_base(vcpu);
+    kvm_update_cpuid_runtime(vcpu);
+    kvm_vcpu_after_set_cpuid(vcpu);
+
+    return 0;
+}
+
 /* when an old userspace process fills a new kernel module */
 int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu,
 			     struct kvm_cpuid *cpuid,
@@ -275,18 +329,9 @@ int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu,
 		e2[i].padding[2] = 0;
 	}
 
-	r = kvm_check_cpuid(e2, cpuid->nent);
-	if (r) {
+	r = kvm_set_cpuid(vcpu, e2, cpuid->nent);
+	if (r)
 		kvfree(e2);
-		goto out_free_cpuid;
-	}
-
-	kvfree(vcpu->arch.cpuid_entries);
-	vcpu->arch.cpuid_entries = e2;
-	vcpu->arch.cpuid_nent = cpuid->nent;
-
-	kvm_update_cpuid_runtime(vcpu);
-	kvm_vcpu_after_set_cpuid(vcpu);
 
 out_free_cpuid:
 	kvfree(e);
@@ -310,20 +355,11 @@ int kvm_vcpu_ioctl_set_cpuid2(struct kvm_vcpu *vcpu,
 			return PTR_ERR(e2);
 	}
 
-	r = kvm_check_cpuid(e2, cpuid->nent);
-	if (r) {
+	r = kvm_set_cpuid(vcpu, e2, cpuid->nent);
+	if (r)
 		kvfree(e2);
-		return r;
-	}
 
-	kvfree(vcpu->arch.cpuid_entries);
-	vcpu->arch.cpuid_entries = e2;
-	vcpu->arch.cpuid_nent = cpuid->nent;
-
-	kvm_update_cpuid_runtime(vcpu);
-	kvm_vcpu_after_set_cpuid(vcpu);
-
-	return 0;
+	return r;
 }
 
 int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu,
@@ -871,8 +907,7 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 		}
 		break;
 	case KVM_CPUID_SIGNATURE: {
-		static const char signature[12] = "KVMKVMKVM\0\0";
-		const u32 *sigptr = (const u32 *)signature;
+		const u32 *sigptr = (const u32 *)KVM_SIGNATURE;
 		entry->eax = KVM_CPUID_FEATURES;
 		entry->ebx = sigptr[0];
 		entry->ecx = sigptr[1];
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 4f15c0165c05..8d8c1cc7cb53 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1472,7 +1472,7 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host)
 
 		if (!(data & HV_X64_MSR_VP_ASSIST_PAGE_ENABLE)) {
 			hv_vcpu->hv_vapic = data;
-			if (kvm_lapic_enable_pv_eoi(vcpu, 0, 0))
+			if (kvm_lapic_set_pv_eoi(vcpu, 0, 0))
 				return 1;
 			break;
 		}
@@ -1490,7 +1490,7 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host)
 			return 1;
 		hv_vcpu->hv_vapic = data;
 		kvm_vcpu_mark_page_dirty(vcpu, gfn);
-		if (kvm_lapic_enable_pv_eoi(vcpu,
+		if (kvm_lapic_set_pv_eoi(vcpu,
 					    gfn_to_gpa(gfn) | KVM_MSR_ENABLED,
 					    sizeof(struct hv_vp_assist_page)))
 			return 1;
@@ -1922,11 +1922,13 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc, bool
 
 		all_cpus = send_ipi_ex.vp_set.format == HV_GENERIC_SET_ALL;
 
+		if (all_cpus)
+			goto check_and_send_ipi;
+
 		if (!sparse_banks_len)
 			goto ret_success;
 
-		if (!all_cpus &&
-		    kvm_read_guest(kvm,
+		if (kvm_read_guest(kvm,
 				   hc->ingpa + offsetof(struct hv_send_ipi_ex,
 							vp_set.bank_contents),
 				   sparse_banks,
@@ -1934,6 +1936,7 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc, bool
 			return HV_STATUS_INVALID_HYPERCALL_INPUT;
 	}
 
+check_and_send_ipi:
 	if ((vector < HV_IPI_LOW_VECTOR) || (vector > HV_IPI_HIGH_VECTOR))
 		return HV_STATUS_INVALID_HYPERCALL_INPUT;
 
@@ -2022,7 +2025,7 @@ static void kvm_hv_hypercall_set_result(struct kvm_vcpu *vcpu, u64 result)
 {
 	bool longmode;
 
-	longmode = is_64_bit_mode(vcpu);
+	longmode = is_64_bit_hypercall(vcpu);
 	if (longmode)
 		kvm_rax_write(vcpu, result);
 	else {
@@ -2171,7 +2174,7 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
 	}
 
 #ifdef CONFIG_X86_64
-	if (is_64_bit_mode(vcpu)) {
+	if (is_64_bit_hypercall(vcpu)) {
 		hc.param = kvm_rcx_read(vcpu);
 		hc.ingpa = kvm_rdx_read(vcpu);
 		hc.outgpa = kvm_r8_read(vcpu);
diff --git a/arch/x86/kvm/ioapic.h b/arch/x86/kvm/ioapic.h
index e66e620c3bed..539333ac4b38 100644
--- a/arch/x86/kvm/ioapic.h
+++ b/arch/x86/kvm/ioapic.h
@@ -81,7 +81,6 @@ struct kvm_ioapic {
 	unsigned long irq_states[IOAPIC_NUM_PINS];
 	struct kvm_io_device dev;
 	struct kvm *kvm;
-	void (*ack_notifier)(void *opaque, int irq);
 	spinlock_t lock;
 	struct rtc_status rtc_status;
 	struct delayed_work eoi_inject;
diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h
index 650642b18d15..c2d7cfe82d00 100644
--- a/arch/x86/kvm/irq.h
+++ b/arch/x86/kvm/irq.h
@@ -56,7 +56,6 @@ struct kvm_pic {
 	struct kvm_io_device dev_master;
 	struct kvm_io_device dev_slave;
 	struct kvm_io_device dev_elcr;
-	void (*ack_notifier)(void *opaque, int irq);
 	unsigned long irq_states[PIC_NUM_PINS];
 };
 
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index d6ac32f3f650..f206fc35deff 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -707,7 +707,7 @@ static void pv_eoi_clr_pending(struct kvm_vcpu *vcpu)
 static int apic_has_interrupt_for_ppr(struct kvm_lapic *apic, u32 ppr)
 {
 	int highest_irr;
-	if (apic->vcpu->arch.apicv_active)
+	if (kvm_x86_ops.sync_pir_to_irr)
 		highest_irr = static_call(kvm_x86_sync_pir_to_irr)(apic->vcpu);
 	else
 		highest_irr = apic_find_highest_irr(apic);
@@ -2856,25 +2856,30 @@ int kvm_hv_vapic_msr_read(struct kvm_vcpu *vcpu, u32 reg, u64 *data)
 	return 0;
 }
 
-int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data, unsigned long len)
+int kvm_lapic_set_pv_eoi(struct kvm_vcpu *vcpu, u64 data, unsigned long len)
 {
 	u64 addr = data & ~KVM_MSR_ENABLED;
 	struct gfn_to_hva_cache *ghc = &vcpu->arch.pv_eoi.data;
 	unsigned long new_len;
+	int ret;
 
 	if (!IS_ALIGNED(addr, 4))
 		return 1;
 
-	vcpu->arch.pv_eoi.msr_val = data;
-	if (!pv_eoi_enabled(vcpu))
-		return 0;
+	if (data & KVM_MSR_ENABLED) {
+		if (addr == ghc->gpa && len <= ghc->len)
+			new_len = ghc->len;
+		else
+			new_len = len;
 
-	if (addr == ghc->gpa && len <= ghc->len)
-		new_len = ghc->len;
-	else
-		new_len = len;
+		ret = kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, addr, new_len);
+		if (ret)
+			return ret;
+	}
+
+	vcpu->arch.pv_eoi.msr_val = data;
 
-	return kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, addr, new_len);
+	return 0;
 }
 
 int kvm_apic_accept_events(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index d7c25d0c1354..2b44e533fc8d 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -127,7 +127,7 @@ int kvm_x2apic_msr_read(struct kvm_vcpu *vcpu, u32 msr, u64 *data);
 int kvm_hv_vapic_msr_write(struct kvm_vcpu *vcpu, u32 msr, u64 data);
 int kvm_hv_vapic_msr_read(struct kvm_vcpu *vcpu, u32 msr, u64 *data);
 
-int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data, unsigned long len);
+int kvm_lapic_set_pv_eoi(struct kvm_vcpu *vcpu, u64 data, unsigned long len);
 void kvm_lapic_exit(void);
 
 #define VEC_POS(v) ((v) & (32 - 1))
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 323b5057d08f..fcdf3f8bb59a 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -1582,7 +1582,7 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
 		flush = kvm_handle_gfn_range(kvm, range, kvm_unmap_rmapp);
 
 	if (is_tdp_mmu_enabled(kvm))
-		flush |= kvm_tdp_mmu_unmap_gfn_range(kvm, range, flush);
+		flush = kvm_tdp_mmu_unmap_gfn_range(kvm, range, flush);
 
 	return flush;
 }
@@ -1936,7 +1936,11 @@ static void mmu_audit_disable(void) { }
 
 static bool is_obsolete_sp(struct kvm *kvm, struct kvm_mmu_page *sp)
 {
-	return sp->role.invalid ||
+	if (sp->role.invalid)
+		return true;
+
+	/* TDP MMU pages due not use the MMU generation. */
+	return !sp->tdp_mmu_page &&
 	       unlikely(sp->mmu_valid_gen != kvm->arch.mmu_valid_gen);
 }
 
@@ -2173,10 +2177,10 @@ static void shadow_walk_init_using_root(struct kvm_shadow_walk_iterator *iterato
 	iterator->shadow_addr = root;
 	iterator->level = vcpu->arch.mmu->shadow_root_level;
 
-	if (iterator->level == PT64_ROOT_4LEVEL &&
+	if (iterator->level >= PT64_ROOT_4LEVEL &&
 	    vcpu->arch.mmu->root_level < PT64_ROOT_4LEVEL &&
 	    !vcpu->arch.mmu->direct_map)
-		--iterator->level;
+		iterator->level = PT32E_ROOT_LEVEL;
 
 	if (iterator->level == PT32E_ROOT_LEVEL) {
 		/*
@@ -3191,17 +3195,17 @@ static int fast_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
 			new_spte |= PT_WRITABLE_MASK;
 
 			/*
-			 * Do not fix write-permission on the large spte.  Since
-			 * we only dirty the first page into the dirty-bitmap in
+			 * Do not fix write-permission on the large spte when
+			 * dirty logging is enabled. Since we only dirty the
+			 * first page into the dirty-bitmap in
 			 * fast_pf_fix_direct_spte(), other pages are missed
 			 * if its slot has dirty logging enabled.
 			 *
 			 * Instead, we let the slow page fault path create a
 			 * normal spte to fix the access.
-			 *
-			 * See the comments in kvm_arch_commit_memory_region().
 			 */
-			if (sp->role.level > PG_LEVEL_4K)
+			if (sp->role.level > PG_LEVEL_4K &&
+			    kvm_slot_dirty_track_enabled(fault->slot))
 				break;
 		}
 
@@ -3976,6 +3980,34 @@ out_retry:
 	return true;
 }
 
+/*
+ * Returns true if the page fault is stale and needs to be retried, i.e. if the
+ * root was invalidated by a memslot update or a relevant mmu_notifier fired.
+ */
+static bool is_page_fault_stale(struct kvm_vcpu *vcpu,
+				struct kvm_page_fault *fault, int mmu_seq)
+{
+	struct kvm_mmu_page *sp = to_shadow_page(vcpu->arch.mmu->root_hpa);
+
+	/* Special roots, e.g. pae_root, are not backed by shadow pages. */
+	if (sp && is_obsolete_sp(vcpu->kvm, sp))
+		return true;
+
+	/*
+	 * Roots without an associated shadow page are considered invalid if
+	 * there is a pending request to free obsolete roots.  The request is
+	 * only a hint that the current root _may_ be obsolete and needs to be
+	 * reloaded, e.g. if the guest frees a PGD that KVM is tracking as a
+	 * previous root, then __kvm_mmu_prepare_zap_page() signals all vCPUs
+	 * to reload even if no vCPU is actively using the root.
+	 */
+	if (!sp && kvm_test_request(KVM_REQ_MMU_RELOAD, vcpu))
+		return true;
+
+	return fault->slot &&
+	       mmu_notifier_retry_hva(vcpu->kvm, mmu_seq, fault->hva);
+}
+
 static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
 {
 	bool is_tdp_mmu_fault = is_tdp_mmu(vcpu->arch.mmu);
@@ -4013,8 +4045,9 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 	else
 		write_lock(&vcpu->kvm->mmu_lock);
 
-	if (fault->slot && mmu_notifier_retry_hva(vcpu->kvm, mmu_seq, fault->hva))
+	if (is_page_fault_stale(vcpu, fault, mmu_seq))
 		goto out_unlock;
+
 	r = make_mmu_pages_available(vcpu);
 	if (r)
 		goto out_unlock;
@@ -4682,6 +4715,7 @@ static union kvm_mmu_extended_role kvm_calc_mmu_role_ext(struct kvm_vcpu *vcpu,
 		/* PKEY and LA57 are active iff long mode is active. */
 		ext.cr4_pke = ____is_efer_lma(regs) && ____is_cr4_pke(regs);
 		ext.cr4_la57 = ____is_efer_lma(regs) && ____is_cr4_la57(regs);
+		ext.efer_lma = ____is_efer_lma(regs);
 	}
 
 	ext.valid = 1;
@@ -4854,7 +4888,7 @@ void kvm_init_shadow_npt_mmu(struct kvm_vcpu *vcpu, unsigned long cr0,
 	struct kvm_mmu *context = &vcpu->arch.guest_mmu;
 	struct kvm_mmu_role_regs regs = {
 		.cr0 = cr0,
-		.cr4 = cr4,
+		.cr4 = cr4 & ~X86_CR4_PKE,
 		.efer = efer,
 	};
 	union kvm_mmu_role new_role;
@@ -4918,7 +4952,7 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly,
 	context->direct_map = false;
 
 	update_permission_bitmask(context, true);
-	update_pkru_bitmask(context);
+	context->pkru_mask = 0;
 	reset_rsvds_bits_mask_ept(vcpu, context, execonly);
 	reset_ept_shadow_zero_bits_mask(vcpu, context, execonly);
 }
@@ -5024,6 +5058,14 @@ void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu)
 	/*
 	 * Invalidate all MMU roles to force them to reinitialize as CPUID
 	 * information is factored into reserved bit calculations.
+	 *
+	 * Correctly handling multiple vCPU models with respect to paging and
+	 * physical address properties) in a single VM would require tracking
+	 * all relevant CPUID information in kvm_mmu_page_role. That is very
+	 * undesirable as it would increase the memory requirements for
+	 * gfn_track (see struct kvm_mmu_page_role comments).  For now that
+	 * problem is swept under the rug; KVM's CPUID API is horrific and
+	 * it's all but impossible to solve it without introducing a new API.
 	 */
 	vcpu->arch.root_mmu.mmu_role.ext.valid = 0;
 	vcpu->arch.guest_mmu.mmu_role.ext.valid = 0;
@@ -5031,24 +5073,10 @@ void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu)
 	kvm_mmu_reset_context(vcpu);
 
 	/*
-	 * KVM does not correctly handle changing guest CPUID after KVM_RUN, as
-	 * MAXPHYADDR, GBPAGES support, AMD reserved bit behavior, etc.. aren't
-	 * tracked in kvm_mmu_page_role.  As a result, KVM may miss guest page
-	 * faults due to reusing SPs/SPTEs.  Alert userspace, but otherwise
-	 * sweep the problem under the rug.
-	 *
-	 * KVM's horrific CPUID ABI makes the problem all but impossible to
-	 * solve, as correctly handling multiple vCPU models (with respect to
-	 * paging and physical address properties) in a single VM would require
-	 * tracking all relevant CPUID information in kvm_mmu_page_role.  That
-	 * is very undesirable as it would double the memory requirements for
-	 * gfn_track (see struct kvm_mmu_page_role comments), and in practice
-	 * no sane VMM mucks with the core vCPU model on the fly.
+	 * Changing guest CPUID after KVM_RUN is forbidden, see the comment in
+	 * kvm_arch_vcpu_ioctl().
 	 */
-	if (vcpu->arch.last_vmentry_cpu != -1) {
-		pr_warn_ratelimited("KVM: KVM_SET_CPUID{,2} after KVM_RUN may cause guest instability\n");
-		pr_warn_ratelimited("KVM: KVM_SET_CPUID{,2} will fail after KVM_RUN starting with Linux 5.16\n");
-	}
+	KVM_BUG_ON(vcpu->arch.last_vmentry_cpu != -1, vcpu->kvm);
 }
 
 void kvm_mmu_reset_context(struct kvm_vcpu *vcpu)
@@ -5368,7 +5396,7 @@ void kvm_mmu_invalidate_gva(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 
 void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva)
 {
-	kvm_mmu_invalidate_gva(vcpu, vcpu->arch.mmu, gva, INVALID_PAGE);
+	kvm_mmu_invalidate_gva(vcpu, vcpu->arch.walk_mmu, gva, INVALID_PAGE);
 	++vcpu->stat.invlpg;
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_invlpg);
@@ -5853,8 +5881,6 @@ restart:
 void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm,
 				   const struct kvm_memory_slot *slot)
 {
-	bool flush = false;
-
 	if (kvm_memslots_have_rmaps(kvm)) {
 		write_lock(&kvm->mmu_lock);
 		/*
@@ -5862,17 +5888,14 @@ void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm,
 		 * logging at a 4k granularity and never creates collapsible
 		 * 2m SPTEs during dirty logging.
 		 */
-		flush = slot_handle_level_4k(kvm, slot, kvm_mmu_zap_collapsible_spte, true);
-		if (flush)
+		if (slot_handle_level_4k(kvm, slot, kvm_mmu_zap_collapsible_spte, true))
 			kvm_arch_flush_remote_tlbs_memslot(kvm, slot);
 		write_unlock(&kvm->mmu_lock);
 	}
 
 	if (is_tdp_mmu_enabled(kvm)) {
 		read_lock(&kvm->mmu_lock);
-		flush = kvm_tdp_mmu_zap_collapsible_sptes(kvm, slot, flush);
-		if (flush)
-			kvm_arch_flush_remote_tlbs_memslot(kvm, slot);
+		kvm_tdp_mmu_zap_collapsible_sptes(kvm, slot);
 		read_unlock(&kvm->mmu_lock);
 	}
 }
@@ -6181,23 +6204,46 @@ void kvm_mmu_module_exit(void)
 	mmu_audit_disable();
 }
 
+/*
+ * Calculate the effective recovery period, accounting for '0' meaning "let KVM
+ * select a halving time of 1 hour".  Returns true if recovery is enabled.
+ */
+static bool calc_nx_huge_pages_recovery_period(uint *period)
+{
+	/*
+	 * Use READ_ONCE to get the params, this may be called outside of the
+	 * param setters, e.g. by the kthread to compute its next timeout.
+	 */
+	bool enabled = READ_ONCE(nx_huge_pages);
+	uint ratio = READ_ONCE(nx_huge_pages_recovery_ratio);
+
+	if (!enabled || !ratio)
+		return false;
+
+	*period = READ_ONCE(nx_huge_pages_recovery_period_ms);
+	if (!*period) {
+		/* Make sure the period is not less than one second.  */
+		ratio = min(ratio, 3600u);
+		*period = 60 * 60 * 1000 / ratio;
+	}
+	return true;
+}
+
 static int set_nx_huge_pages_recovery_param(const char *val, const struct kernel_param *kp)
 {
 	bool was_recovery_enabled, is_recovery_enabled;
 	uint old_period, new_period;
 	int err;
 
-	was_recovery_enabled = nx_huge_pages_recovery_ratio;
-	old_period = nx_huge_pages_recovery_period_ms;
+	was_recovery_enabled = calc_nx_huge_pages_recovery_period(&old_period);
 
 	err = param_set_uint(val, kp);
 	if (err)
 		return err;
 
-	is_recovery_enabled = nx_huge_pages_recovery_ratio;
-	new_period = nx_huge_pages_recovery_period_ms;
+	is_recovery_enabled = calc_nx_huge_pages_recovery_period(&new_period);
 
-	if (READ_ONCE(nx_huge_pages) && is_recovery_enabled &&
+	if (is_recovery_enabled &&
 	    (!was_recovery_enabled || old_period > new_period)) {
 		struct kvm *kvm;
 
@@ -6261,18 +6307,13 @@ static void kvm_recover_nx_lpages(struct kvm *kvm)
 
 static long get_nx_lpage_recovery_timeout(u64 start_time)
 {
-	uint ratio = READ_ONCE(nx_huge_pages_recovery_ratio);
-	uint period = READ_ONCE(nx_huge_pages_recovery_period_ms);
+	bool enabled;
+	uint period;
 
-	if (!period && ratio) {
-		/* Make sure the period is not less than one second.  */
-		ratio = min(ratio, 3600u);
-		period = 60 * 60 * 1000 / ratio;
-	}
+	enabled = calc_nx_huge_pages_recovery_period(&period);
 
-	return READ_ONCE(nx_huge_pages) && ratio
-		? start_time + msecs_to_jiffies(period) - get_jiffies_64()
-		: MAX_SCHEDULE_TIMEOUT;
+	return enabled ? start_time + msecs_to_jiffies(period) - get_jiffies_64()
+		       : MAX_SCHEDULE_TIMEOUT;
 }
 
 static int kvm_nx_lpage_recovery_worker(struct kvm *kvm, uintptr_t data)
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index f87d36898c44..708a5d297fe1 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -911,7 +911,8 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 
 	r = RET_PF_RETRY;
 	write_lock(&vcpu->kvm->mmu_lock);
-	if (fault->slot && mmu_notifier_retry_hva(vcpu->kvm, mmu_seq, fault->hva))
+
+	if (is_page_fault_stale(vcpu, fault, mmu_seq))
 		goto out_unlock;
 
 	kvm_mmu_audit(vcpu, AUDIT_PRE_PAGE_FAULT);
diff --git a/arch/x86/kvm/mmu/tdp_iter.c b/arch/x86/kvm/mmu/tdp_iter.c
index b3ed302c1a35..caa96c270b95 100644
--- a/arch/x86/kvm/mmu/tdp_iter.c
+++ b/arch/x86/kvm/mmu/tdp_iter.c
@@ -26,6 +26,7 @@ static gfn_t round_gfn_for_level(gfn_t gfn, int level)
  */
 void tdp_iter_restart(struct tdp_iter *iter)
 {
+	iter->yielded = false;
 	iter->yielded_gfn = iter->next_last_level_gfn;
 	iter->level = iter->root_level;
 
@@ -160,6 +161,11 @@ static bool try_step_up(struct tdp_iter *iter)
  */
 void tdp_iter_next(struct tdp_iter *iter)
 {
+	if (iter->yielded) {
+		tdp_iter_restart(iter);
+		return;
+	}
+
 	if (try_step_down(iter))
 		return;
 
diff --git a/arch/x86/kvm/mmu/tdp_iter.h b/arch/x86/kvm/mmu/tdp_iter.h
index b1748b988d3a..e19cabbcb65c 100644
--- a/arch/x86/kvm/mmu/tdp_iter.h
+++ b/arch/x86/kvm/mmu/tdp_iter.h
@@ -45,6 +45,12 @@ struct tdp_iter {
 	 * iterator walks off the end of the paging structure.
 	 */
 	bool valid;
+	/*
+	 * True if KVM dropped mmu_lock and yielded in the middle of a walk, in
+	 * which case tdp_iter_next() needs to restart the walk at the root
+	 * level instead of advancing to the next entry.
+	 */
+	bool yielded;
 };
 
 /*
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 7c5dd83e52de..1beb4ca90560 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -317,9 +317,6 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, tdp_ptep_t pt,
 	struct kvm_mmu_page *sp = sptep_to_sp(rcu_dereference(pt));
 	int level = sp->role.level;
 	gfn_t base_gfn = sp->gfn;
-	u64 old_child_spte;
-	u64 *sptep;
-	gfn_t gfn;
 	int i;
 
 	trace_kvm_mmu_prepare_zap_page(sp);
@@ -327,8 +324,9 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, tdp_ptep_t pt,
 	tdp_mmu_unlink_page(kvm, sp, shared);
 
 	for (i = 0; i < PT64_ENT_PER_PAGE; i++) {
-		sptep = rcu_dereference(pt) + i;
-		gfn = base_gfn + i * KVM_PAGES_PER_HPAGE(level);
+		u64 *sptep = rcu_dereference(pt) + i;
+		gfn_t gfn = base_gfn + i * KVM_PAGES_PER_HPAGE(level);
+		u64 old_child_spte;
 
 		if (shared) {
 			/*
@@ -374,7 +372,7 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, tdp_ptep_t pt,
 				    shared);
 	}
 
-	kvm_flush_remote_tlbs_with_address(kvm, gfn,
+	kvm_flush_remote_tlbs_with_address(kvm, base_gfn,
 					   KVM_PAGES_PER_HPAGE(level + 1));
 
 	call_rcu(&sp->rcu_head, tdp_mmu_free_sp_rcu_callback);
@@ -504,6 +502,8 @@ static inline bool tdp_mmu_set_spte_atomic(struct kvm *kvm,
 					   struct tdp_iter *iter,
 					   u64 new_spte)
 {
+	WARN_ON_ONCE(iter->yielded);
+
 	lockdep_assert_held_read(&kvm->mmu_lock);
 
 	/*
@@ -577,6 +577,8 @@ static inline void __tdp_mmu_set_spte(struct kvm *kvm, struct tdp_iter *iter,
 				      u64 new_spte, bool record_acc_track,
 				      bool record_dirty_log)
 {
+	WARN_ON_ONCE(iter->yielded);
+
 	lockdep_assert_held_write(&kvm->mmu_lock);
 
 	/*
@@ -642,18 +644,19 @@ static inline void tdp_mmu_set_spte_no_dirty_log(struct kvm *kvm,
  * If this function should yield and flush is set, it will perform a remote
  * TLB flush before yielding.
  *
- * If this function yields, it will also reset the tdp_iter's walk over the
- * paging structure and the calling function should skip to the next
- * iteration to allow the iterator to continue its traversal from the
- * paging structure root.
+ * If this function yields, iter->yielded is set and the caller must skip to
+ * the next iteration, where tdp_iter_next() will reset the tdp_iter's walk
+ * over the paging structures to allow the iterator to continue its traversal
+ * from the paging structure root.
  *
- * Return true if this function yielded and the iterator's traversal was reset.
- * Return false if a yield was not needed.
+ * Returns true if this function yielded.
  */
-static inline bool tdp_mmu_iter_cond_resched(struct kvm *kvm,
-					     struct tdp_iter *iter, bool flush,
-					     bool shared)
+static inline bool __must_check tdp_mmu_iter_cond_resched(struct kvm *kvm,
+							  struct tdp_iter *iter,
+							  bool flush, bool shared)
 {
+	WARN_ON(iter->yielded);
+
 	/* Ensure forward progress has been made before yielding. */
 	if (iter->next_last_level_gfn == iter->yielded_gfn)
 		return false;
@@ -673,12 +676,10 @@ static inline bool tdp_mmu_iter_cond_resched(struct kvm *kvm,
 
 		WARN_ON(iter->gfn > iter->next_last_level_gfn);
 
-		tdp_iter_restart(iter);
-
-		return true;
+		iter->yielded = true;
 	}
 
-	return false;
+	return iter->yielded;
 }
 
 /*
@@ -897,7 +898,7 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu,
 					  struct kvm_page_fault *fault,
 					  struct tdp_iter *iter)
 {
-	struct kvm_mmu_page *sp = sptep_to_sp(iter->sptep);
+	struct kvm_mmu_page *sp = sptep_to_sp(rcu_dereference(iter->sptep));
 	u64 new_spte;
 	int ret = RET_PF_FIXED;
 	bool wrprot = false;
@@ -1033,9 +1034,9 @@ bool kvm_tdp_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range,
 {
 	struct kvm_mmu_page *root;
 
-	for_each_tdp_mmu_root(kvm, root, range->slot->as_id)
-		flush |= zap_gfn_range(kvm, root, range->start, range->end,
-				       range->may_block, flush, false);
+	for_each_tdp_mmu_root_yield_safe(kvm, root, range->slot->as_id, false)
+		flush = zap_gfn_range(kvm, root, range->start, range->end,
+				      range->may_block, flush, false);
 
 	return flush;
 }
@@ -1364,10 +1365,9 @@ void kvm_tdp_mmu_clear_dirty_pt_masked(struct kvm *kvm,
  * Clear leaf entries which could be replaced by large mappings, for
  * GFNs within the slot.
  */
-static bool zap_collapsible_spte_range(struct kvm *kvm,
+static void zap_collapsible_spte_range(struct kvm *kvm,
 				       struct kvm_mmu_page *root,
-				       const struct kvm_memory_slot *slot,
-				       bool flush)
+				       const struct kvm_memory_slot *slot)
 {
 	gfn_t start = slot->base_gfn;
 	gfn_t end = start + slot->npages;
@@ -1378,10 +1378,8 @@ static bool zap_collapsible_spte_range(struct kvm *kvm,
 
 	tdp_root_for_each_pte(iter, root, start, end) {
 retry:
-		if (tdp_mmu_iter_cond_resched(kvm, &iter, flush, true)) {
-			flush = false;
+		if (tdp_mmu_iter_cond_resched(kvm, &iter, false, true))
 			continue;
-		}
 
 		if (!is_shadow_present_pte(iter.old_spte) ||
 		    !is_last_spte(iter.old_spte, iter.level))
@@ -1393,6 +1391,7 @@ retry:
 							    pfn, PG_LEVEL_NUM))
 			continue;
 
+		/* Note, a successful atomic zap also does a remote TLB flush. */
 		if (!tdp_mmu_zap_spte_atomic(kvm, &iter)) {
 			/*
 			 * The iter must explicitly re-read the SPTE because
@@ -1401,30 +1400,24 @@ retry:
 			iter.old_spte = READ_ONCE(*rcu_dereference(iter.sptep));
 			goto retry;
 		}
-		flush = true;
 	}
 
 	rcu_read_unlock();
-
-	return flush;
 }
 
 /*
  * Clear non-leaf entries (and free associated page tables) which could
  * be replaced by large mappings, for GFNs within the slot.
  */
-bool kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm,
-				       const struct kvm_memory_slot *slot,
-				       bool flush)
+void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm,
+				       const struct kvm_memory_slot *slot)
 {
 	struct kvm_mmu_page *root;
 
 	lockdep_assert_held_read(&kvm->mmu_lock);
 
 	for_each_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, true)
-		flush = zap_collapsible_spte_range(kvm, root, slot, flush);
-
-	return flush;
+		zap_collapsible_spte_range(kvm, root, slot);
 }
 
 /*
diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h
index 476b133544dd..3899004a5d91 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.h
+++ b/arch/x86/kvm/mmu/tdp_mmu.h
@@ -64,9 +64,8 @@ void kvm_tdp_mmu_clear_dirty_pt_masked(struct kvm *kvm,
 				       struct kvm_memory_slot *slot,
 				       gfn_t gfn, unsigned long mask,
 				       bool wrprot);
-bool kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm,
-				       const struct kvm_memory_slot *slot,
-				       bool flush);
+void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm,
+				       const struct kvm_memory_slot *slot);
 
 bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm,
 				   struct kvm_memory_slot *slot, gfn_t gfn,
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index 0772bad9165c..09873f6488f7 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -319,7 +319,7 @@ void kvm_pmu_handle_event(struct kvm_vcpu *vcpu)
 }
 
 /* check if idx is a valid index to access PMU */
-int kvm_pmu_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx)
+bool kvm_pmu_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx)
 {
 	return kvm_x86_ops.pmu_ops->is_valid_rdpmc_ecx(vcpu, idx);
 }
diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h
index 0e4f2b1fa9fb..59d6b76203d5 100644
--- a/arch/x86/kvm/pmu.h
+++ b/arch/x86/kvm/pmu.h
@@ -32,7 +32,7 @@ struct kvm_pmu_ops {
 	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_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, struct msr_data *msr_info);
 	int (*set_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr_info);
@@ -149,7 +149,7 @@ 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_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx);
+bool 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, struct msr_data *msr_info);
 int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info);
diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index 8052d92069e0..8f9af7b7dbbe 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -900,11 +900,13 @@ out:
 bool svm_check_apicv_inhibit_reasons(ulong bit)
 {
 	ulong supported = BIT(APICV_INHIBIT_REASON_DISABLE) |
+			  BIT(APICV_INHIBIT_REASON_ABSENT) |
 			  BIT(APICV_INHIBIT_REASON_HYPERV) |
 			  BIT(APICV_INHIBIT_REASON_NESTED) |
 			  BIT(APICV_INHIBIT_REASON_IRQWIN) |
 			  BIT(APICV_INHIBIT_REASON_PIT_REINJ) |
-			  BIT(APICV_INHIBIT_REASON_X2APIC);
+			  BIT(APICV_INHIBIT_REASON_X2APIC) |
+			  BIT(APICV_INHIBIT_REASON_BLOCKIRQ);
 
 	return supported & BIT(bit);
 }
@@ -988,16 +990,18 @@ void avic_vcpu_put(struct kvm_vcpu *vcpu)
 static void avic_set_running(struct kvm_vcpu *vcpu, bool is_run)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
+	int cpu = get_cpu();
 
+	WARN_ON(cpu != vcpu->cpu);
 	svm->avic_is_running = is_run;
 
-	if (!kvm_vcpu_apicv_active(vcpu))
-		return;
-
-	if (is_run)
-		avic_vcpu_load(vcpu, vcpu->cpu);
-	else
-		avic_vcpu_put(vcpu);
+	if (kvm_vcpu_apicv_active(vcpu)) {
+		if (is_run)
+			avic_vcpu_load(vcpu, cpu);
+		else
+			avic_vcpu_put(vcpu);
+	}
+	put_cpu();
 }
 
 void svm_vcpu_blocking(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c
index fdf587f19c5f..b4095dfeeee6 100644
--- a/arch/x86/kvm/svm/pmu.c
+++ b/arch/x86/kvm/svm/pmu.c
@@ -181,14 +181,13 @@ static struct kvm_pmc *amd_pmc_idx_to_pmc(struct kvm_pmu *pmu, int pmc_idx)
 	return get_gp_pmc_amd(pmu, base + pmc_idx, PMU_TYPE_COUNTER);
 }
 
-/* returns 0 if idx's corresponding MSR exists; otherwise returns 1. */
-static int amd_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx)
+static bool amd_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx)
 {
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
 
 	idx &= ~(3u << 30);
 
-	return (idx >= pmu->nr_arch_gp_counters);
+	return idx < pmu->nr_arch_gp_counters;
 }
 
 /* idx is the ECX register of RDPMC instruction */
@@ -282,7 +281,7 @@ static void amd_pmu_refresh(struct kvm_vcpu *vcpu)
 		pmu->nr_arch_gp_counters = AMD64_NUM_COUNTERS;
 
 	pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << 48) - 1;
-	pmu->reserved_bits = 0xffffffff00200000ull;
+	pmu->reserved_bits = 0xfffffff000280000ull;
 	pmu->version = 1;
 	/* not applicable to AMD; but clean them to prevent any fall out */
 	pmu->counter_bitmask[KVM_PMC_FIXED] = 0;
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 1964b9a174be..7656a2c5662a 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -120,16 +120,26 @@ static bool __sev_recycle_asids(int min_asid, int max_asid)
 	return true;
 }
 
+static int sev_misc_cg_try_charge(struct kvm_sev_info *sev)
+{
+	enum misc_res_type type = sev->es_active ? MISC_CG_RES_SEV_ES : MISC_CG_RES_SEV;
+	return misc_cg_try_charge(type, sev->misc_cg, 1);
+}
+
+static void sev_misc_cg_uncharge(struct kvm_sev_info *sev)
+{
+	enum misc_res_type type = sev->es_active ? MISC_CG_RES_SEV_ES : MISC_CG_RES_SEV;
+	misc_cg_uncharge(type, sev->misc_cg, 1);
+}
+
 static int sev_asid_new(struct kvm_sev_info *sev)
 {
 	int asid, min_asid, max_asid, ret;
 	bool retry = true;
-	enum misc_res_type type;
 
-	type = sev->es_active ? MISC_CG_RES_SEV_ES : MISC_CG_RES_SEV;
 	WARN_ON(sev->misc_cg);
 	sev->misc_cg = get_current_misc_cg();
-	ret = misc_cg_try_charge(type, sev->misc_cg, 1);
+	ret = sev_misc_cg_try_charge(sev);
 	if (ret) {
 		put_misc_cg(sev->misc_cg);
 		sev->misc_cg = NULL;
@@ -162,7 +172,7 @@ again:
 
 	return asid;
 e_uncharge:
-	misc_cg_uncharge(type, sev->misc_cg, 1);
+	sev_misc_cg_uncharge(sev);
 	put_misc_cg(sev->misc_cg);
 	sev->misc_cg = NULL;
 	return ret;
@@ -179,7 +189,6 @@ static void sev_asid_free(struct kvm_sev_info *sev)
 {
 	struct svm_cpu_data *sd;
 	int cpu;
-	enum misc_res_type type;
 
 	mutex_lock(&sev_bitmap_lock);
 
@@ -192,8 +201,7 @@ static void sev_asid_free(struct kvm_sev_info *sev)
 
 	mutex_unlock(&sev_bitmap_lock);
 
-	type = sev->es_active ? MISC_CG_RES_SEV_ES : MISC_CG_RES_SEV;
-	misc_cg_uncharge(type, sev->misc_cg, 1);
+	sev_misc_cg_uncharge(sev);
 	put_misc_cg(sev->misc_cg);
 	sev->misc_cg = NULL;
 }
@@ -229,7 +237,6 @@ static void sev_unbind_asid(struct kvm *kvm, unsigned int handle)
 static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp)
 {
 	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
-	bool es_active = argp->id == KVM_SEV_ES_INIT;
 	int asid, ret;
 
 	if (kvm->created_vcpus)
@@ -239,7 +246,8 @@ static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp)
 	if (unlikely(sev->active))
 		return ret;
 
-	sev->es_active = es_active;
+	sev->active = true;
+	sev->es_active = argp->id == KVM_SEV_ES_INIT;
 	asid = sev_asid_new(sev);
 	if (asid < 0)
 		goto e_no_asid;
@@ -249,8 +257,6 @@ static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp)
 	if (ret)
 		goto e_free;
 
-	sev->active = true;
-	sev->asid = asid;
 	INIT_LIST_HEAD(&sev->regions_list);
 
 	return 0;
@@ -260,6 +266,7 @@ e_free:
 	sev->asid = 0;
 e_no_asid:
 	sev->es_active = false;
+	sev->active = false;
 	return ret;
 }
 
@@ -590,7 +597,7 @@ static int sev_es_sync_vmsa(struct vcpu_svm *svm)
 	 * traditional VMSA as it has been built so far (in prep
 	 * for LAUNCH_UPDATE_VMSA) to be the initial SEV-ES state.
 	 */
-	memcpy(svm->vmsa, save, sizeof(*save));
+	memcpy(svm->sev_es.vmsa, save, sizeof(*save));
 
 	return 0;
 }
@@ -612,11 +619,11 @@ static int __sev_launch_update_vmsa(struct kvm *kvm, struct kvm_vcpu *vcpu,
 	 * the VMSA memory content (i.e it will write the same memory region
 	 * with the guest's key), so invalidate it first.
 	 */
-	clflush_cache_range(svm->vmsa, PAGE_SIZE);
+	clflush_cache_range(svm->sev_es.vmsa, PAGE_SIZE);
 
 	vmsa.reserved = 0;
 	vmsa.handle = to_kvm_svm(kvm)->sev_info.handle;
-	vmsa.address = __sme_pa(svm->vmsa);
+	vmsa.address = __sme_pa(svm->sev_es.vmsa);
 	vmsa.len = PAGE_SIZE;
 	ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_VMSA, &vmsa, error);
 	if (ret)
@@ -1522,7 +1529,7 @@ static int sev_receive_finish(struct kvm *kvm, struct kvm_sev_cmd *argp)
 	return sev_issue_cmd(kvm, SEV_CMD_RECEIVE_FINISH, &data, &argp->error);
 }
 
-static bool cmd_allowed_from_miror(u32 cmd_id)
+static bool is_cmd_allowed_from_mirror(u32 cmd_id)
 {
 	/*
 	 * Allow mirrors VM to call KVM_SEV_LAUNCH_UPDATE_VMSA to enable SEV-ES
@@ -1536,6 +1543,223 @@ static bool cmd_allowed_from_miror(u32 cmd_id)
 	return false;
 }
 
+static int sev_lock_two_vms(struct kvm *dst_kvm, struct kvm *src_kvm)
+{
+	struct kvm_sev_info *dst_sev = &to_kvm_svm(dst_kvm)->sev_info;
+	struct kvm_sev_info *src_sev = &to_kvm_svm(src_kvm)->sev_info;
+	int r = -EBUSY;
+
+	if (dst_kvm == src_kvm)
+		return -EINVAL;
+
+	/*
+	 * Bail if these VMs are already involved in a migration to avoid
+	 * deadlock between two VMs trying to migrate to/from each other.
+	 */
+	if (atomic_cmpxchg_acquire(&dst_sev->migration_in_progress, 0, 1))
+		return -EBUSY;
+
+	if (atomic_cmpxchg_acquire(&src_sev->migration_in_progress, 0, 1))
+		goto release_dst;
+
+	r = -EINTR;
+	if (mutex_lock_killable(&dst_kvm->lock))
+		goto release_src;
+	if (mutex_lock_killable(&src_kvm->lock))
+		goto unlock_dst;
+	return 0;
+
+unlock_dst:
+	mutex_unlock(&dst_kvm->lock);
+release_src:
+	atomic_set_release(&src_sev->migration_in_progress, 0);
+release_dst:
+	atomic_set_release(&dst_sev->migration_in_progress, 0);
+	return r;
+}
+
+static void sev_unlock_two_vms(struct kvm *dst_kvm, struct kvm *src_kvm)
+{
+	struct kvm_sev_info *dst_sev = &to_kvm_svm(dst_kvm)->sev_info;
+	struct kvm_sev_info *src_sev = &to_kvm_svm(src_kvm)->sev_info;
+
+	mutex_unlock(&dst_kvm->lock);
+	mutex_unlock(&src_kvm->lock);
+	atomic_set_release(&dst_sev->migration_in_progress, 0);
+	atomic_set_release(&src_sev->migration_in_progress, 0);
+}
+
+
+static int sev_lock_vcpus_for_migration(struct kvm *kvm)
+{
+	struct kvm_vcpu *vcpu;
+	int i, j;
+
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		if (mutex_lock_killable(&vcpu->mutex))
+			goto out_unlock;
+	}
+
+	return 0;
+
+out_unlock:
+	kvm_for_each_vcpu(j, vcpu, kvm) {
+		if (i == j)
+			break;
+
+		mutex_unlock(&vcpu->mutex);
+	}
+	return -EINTR;
+}
+
+static void sev_unlock_vcpus_for_migration(struct kvm *kvm)
+{
+	struct kvm_vcpu *vcpu;
+	int i;
+
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		mutex_unlock(&vcpu->mutex);
+	}
+}
+
+static void sev_migrate_from(struct kvm_sev_info *dst,
+			      struct kvm_sev_info *src)
+{
+	dst->active = true;
+	dst->asid = src->asid;
+	dst->handle = src->handle;
+	dst->pages_locked = src->pages_locked;
+	dst->enc_context_owner = src->enc_context_owner;
+
+	src->asid = 0;
+	src->active = false;
+	src->handle = 0;
+	src->pages_locked = 0;
+	src->enc_context_owner = NULL;
+
+	list_cut_before(&dst->regions_list, &src->regions_list, &src->regions_list);
+}
+
+static int sev_es_migrate_from(struct kvm *dst, struct kvm *src)
+{
+	int i;
+	struct kvm_vcpu *dst_vcpu, *src_vcpu;
+	struct vcpu_svm *dst_svm, *src_svm;
+
+	if (atomic_read(&src->online_vcpus) != atomic_read(&dst->online_vcpus))
+		return -EINVAL;
+
+	kvm_for_each_vcpu(i, src_vcpu, src) {
+		if (!src_vcpu->arch.guest_state_protected)
+			return -EINVAL;
+	}
+
+	kvm_for_each_vcpu(i, src_vcpu, src) {
+		src_svm = to_svm(src_vcpu);
+		dst_vcpu = kvm_get_vcpu(dst, i);
+		dst_svm = to_svm(dst_vcpu);
+
+		/*
+		 * Transfer VMSA and GHCB state to the destination.  Nullify and
+		 * clear source fields as appropriate, the state now belongs to
+		 * the destination.
+		 */
+		memcpy(&dst_svm->sev_es, &src_svm->sev_es, sizeof(src_svm->sev_es));
+		dst_svm->vmcb->control.ghcb_gpa = src_svm->vmcb->control.ghcb_gpa;
+		dst_svm->vmcb->control.vmsa_pa = src_svm->vmcb->control.vmsa_pa;
+		dst_vcpu->arch.guest_state_protected = true;
+
+		memset(&src_svm->sev_es, 0, sizeof(src_svm->sev_es));
+		src_svm->vmcb->control.ghcb_gpa = INVALID_PAGE;
+		src_svm->vmcb->control.vmsa_pa = INVALID_PAGE;
+		src_vcpu->arch.guest_state_protected = false;
+	}
+	to_kvm_svm(src)->sev_info.es_active = false;
+	to_kvm_svm(dst)->sev_info.es_active = true;
+
+	return 0;
+}
+
+int svm_vm_migrate_from(struct kvm *kvm, unsigned int source_fd)
+{
+	struct kvm_sev_info *dst_sev = &to_kvm_svm(kvm)->sev_info;
+	struct kvm_sev_info *src_sev, *cg_cleanup_sev;
+	struct file *source_kvm_file;
+	struct kvm *source_kvm;
+	bool charged = false;
+	int ret;
+
+	source_kvm_file = fget(source_fd);
+	if (!file_is_kvm(source_kvm_file)) {
+		ret = -EBADF;
+		goto out_fput;
+	}
+
+	source_kvm = source_kvm_file->private_data;
+	ret = sev_lock_two_vms(kvm, source_kvm);
+	if (ret)
+		goto out_fput;
+
+	if (sev_guest(kvm) || !sev_guest(source_kvm)) {
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
+	src_sev = &to_kvm_svm(source_kvm)->sev_info;
+
+	/*
+	 * VMs mirroring src's encryption context rely on it to keep the
+	 * ASID allocated, but below we are clearing src_sev->asid.
+	 */
+	if (src_sev->num_mirrored_vms) {
+		ret = -EBUSY;
+		goto out_unlock;
+	}
+
+	dst_sev->misc_cg = get_current_misc_cg();
+	cg_cleanup_sev = dst_sev;
+	if (dst_sev->misc_cg != src_sev->misc_cg) {
+		ret = sev_misc_cg_try_charge(dst_sev);
+		if (ret)
+			goto out_dst_cgroup;
+		charged = true;
+	}
+
+	ret = sev_lock_vcpus_for_migration(kvm);
+	if (ret)
+		goto out_dst_cgroup;
+	ret = sev_lock_vcpus_for_migration(source_kvm);
+	if (ret)
+		goto out_dst_vcpu;
+
+	if (sev_es_guest(source_kvm)) {
+		ret = sev_es_migrate_from(kvm, source_kvm);
+		if (ret)
+			goto out_source_vcpu;
+	}
+	sev_migrate_from(dst_sev, src_sev);
+	kvm_vm_dead(source_kvm);
+	cg_cleanup_sev = src_sev;
+	ret = 0;
+
+out_source_vcpu:
+	sev_unlock_vcpus_for_migration(source_kvm);
+out_dst_vcpu:
+	sev_unlock_vcpus_for_migration(kvm);
+out_dst_cgroup:
+	/* Operates on the source on success, on the destination on failure.  */
+	if (charged)
+		sev_misc_cg_uncharge(cg_cleanup_sev);
+	put_misc_cg(cg_cleanup_sev->misc_cg);
+	cg_cleanup_sev->misc_cg = NULL;
+out_unlock:
+	sev_unlock_two_vms(kvm, source_kvm);
+out_fput:
+	if (source_kvm_file)
+		fput(source_kvm_file);
+	return ret;
+}
+
 int svm_mem_enc_op(struct kvm *kvm, void __user *argp)
 {
 	struct kvm_sev_cmd sev_cmd;
@@ -1554,7 +1778,7 @@ int svm_mem_enc_op(struct kvm *kvm, void __user *argp)
 
 	/* Only the enc_context_owner handles some memory enc operations. */
 	if (is_mirroring_enc_context(kvm) &&
-	    !cmd_allowed_from_miror(sev_cmd.id)) {
+	    !is_cmd_allowed_from_mirror(sev_cmd.id)) {
 		r = -EINVAL;
 		goto out;
 	}
@@ -1751,71 +1975,60 @@ int svm_vm_copy_asid_from(struct kvm *kvm, unsigned int source_fd)
 {
 	struct file *source_kvm_file;
 	struct kvm *source_kvm;
-	struct kvm_sev_info source_sev, *mirror_sev;
+	struct kvm_sev_info *source_sev, *mirror_sev;
 	int ret;
 
 	source_kvm_file = fget(source_fd);
 	if (!file_is_kvm(source_kvm_file)) {
 		ret = -EBADF;
-		goto e_source_put;
+		goto e_source_fput;
 	}
 
 	source_kvm = source_kvm_file->private_data;
-	mutex_lock(&source_kvm->lock);
-
-	if (!sev_guest(source_kvm)) {
-		ret = -EINVAL;
-		goto e_source_unlock;
-	}
+	ret = sev_lock_two_vms(kvm, source_kvm);
+	if (ret)
+		goto e_source_fput;
 
-	/* Mirrors of mirrors should work, but let's not get silly */
-	if (is_mirroring_enc_context(source_kvm) || source_kvm == kvm) {
+	/*
+	 * Mirrors of mirrors should work, but let's not get silly.  Also
+	 * disallow out-of-band SEV/SEV-ES init if the target is already an
+	 * SEV guest, or if vCPUs have been created.  KVM relies on vCPUs being
+	 * created after SEV/SEV-ES initialization, e.g. to init intercepts.
+	 */
+	if (sev_guest(kvm) || !sev_guest(source_kvm) ||
+	    is_mirroring_enc_context(source_kvm) || kvm->created_vcpus) {
 		ret = -EINVAL;
-		goto e_source_unlock;
+		goto e_unlock;
 	}
 
-	memcpy(&source_sev, &to_kvm_svm(source_kvm)->sev_info,
-	       sizeof(source_sev));
-
 	/*
 	 * The mirror kvm holds an enc_context_owner ref so its asid can't
 	 * disappear until we're done with it
 	 */
+	source_sev = &to_kvm_svm(source_kvm)->sev_info;
 	kvm_get_kvm(source_kvm);
-
-	fput(source_kvm_file);
-	mutex_unlock(&source_kvm->lock);
-	mutex_lock(&kvm->lock);
-
-	if (sev_guest(kvm)) {
-		ret = -EINVAL;
-		goto e_mirror_unlock;
-	}
+	source_sev->num_mirrored_vms++;
 
 	/* Set enc_context_owner and copy its encryption context over */
 	mirror_sev = &to_kvm_svm(kvm)->sev_info;
 	mirror_sev->enc_context_owner = source_kvm;
 	mirror_sev->active = true;
-	mirror_sev->asid = source_sev.asid;
-	mirror_sev->fd = source_sev.fd;
-	mirror_sev->es_active = source_sev.es_active;
-	mirror_sev->handle = source_sev.handle;
+	mirror_sev->asid = source_sev->asid;
+	mirror_sev->fd = source_sev->fd;
+	mirror_sev->es_active = source_sev->es_active;
+	mirror_sev->handle = source_sev->handle;
+	INIT_LIST_HEAD(&mirror_sev->regions_list);
+	ret = 0;
+
 	/*
 	 * Do not copy ap_jump_table. Since the mirror does not share the same
 	 * KVM contexts as the original, and they may have different
 	 * memory-views.
 	 */
 
-	mutex_unlock(&kvm->lock);
-	return 0;
-
-e_mirror_unlock:
-	mutex_unlock(&kvm->lock);
-	kvm_put_kvm(source_kvm);
-	return ret;
-e_source_unlock:
-	mutex_unlock(&source_kvm->lock);
-e_source_put:
+e_unlock:
+	sev_unlock_two_vms(kvm, source_kvm);
+e_source_fput:
 	if (source_kvm_file)
 		fput(source_kvm_file);
 	return ret;
@@ -1827,17 +2040,24 @@ void sev_vm_destroy(struct kvm *kvm)
 	struct list_head *head = &sev->regions_list;
 	struct list_head *pos, *q;
 
+	WARN_ON(sev->num_mirrored_vms);
+
 	if (!sev_guest(kvm))
 		return;
 
 	/* If this is a mirror_kvm release the enc_context_owner and skip sev cleanup */
 	if (is_mirroring_enc_context(kvm)) {
-		kvm_put_kvm(sev->enc_context_owner);
+		struct kvm *owner_kvm = sev->enc_context_owner;
+		struct kvm_sev_info *owner_sev = &to_kvm_svm(owner_kvm)->sev_info;
+
+		mutex_lock(&owner_kvm->lock);
+		if (!WARN_ON(!owner_sev->num_mirrored_vms))
+			owner_sev->num_mirrored_vms--;
+		mutex_unlock(&owner_kvm->lock);
+		kvm_put_kvm(owner_kvm);
 		return;
 	}
 
-	mutex_lock(&kvm->lock);
-
 	/*
 	 * Ensure that all guest tagged cache entries are flushed before
 	 * releasing the pages back to the system for use. CLFLUSH will
@@ -1857,8 +2077,6 @@ void sev_vm_destroy(struct kvm *kvm)
 		}
 	}
 
-	mutex_unlock(&kvm->lock);
-
 	sev_unbind_asid(kvm, sev->handle);
 	sev_asid_free(sev);
 }
@@ -2038,16 +2256,16 @@ void sev_free_vcpu(struct kvm_vcpu *vcpu)
 	svm = to_svm(vcpu);
 
 	if (vcpu->arch.guest_state_protected)
-		sev_flush_guest_memory(svm, svm->vmsa, PAGE_SIZE);
-	__free_page(virt_to_page(svm->vmsa));
+		sev_flush_guest_memory(svm, svm->sev_es.vmsa, PAGE_SIZE);
+	__free_page(virt_to_page(svm->sev_es.vmsa));
 
-	if (svm->ghcb_sa_free)
-		kfree(svm->ghcb_sa);
+	if (svm->sev_es.ghcb_sa_free)
+		kvfree(svm->sev_es.ghcb_sa);
 }
 
 static void dump_ghcb(struct vcpu_svm *svm)
 {
-	struct ghcb *ghcb = svm->ghcb;
+	struct ghcb *ghcb = svm->sev_es.ghcb;
 	unsigned int nbits;
 
 	/* Re-use the dump_invalid_vmcb module parameter */
@@ -2073,7 +2291,7 @@ static void dump_ghcb(struct vcpu_svm *svm)
 static void sev_es_sync_to_ghcb(struct vcpu_svm *svm)
 {
 	struct kvm_vcpu *vcpu = &svm->vcpu;
-	struct ghcb *ghcb = svm->ghcb;
+	struct ghcb *ghcb = svm->sev_es.ghcb;
 
 	/*
 	 * The GHCB protocol so far allows for the following data
@@ -2093,7 +2311,7 @@ static void sev_es_sync_from_ghcb(struct vcpu_svm *svm)
 {
 	struct vmcb_control_area *control = &svm->vmcb->control;
 	struct kvm_vcpu *vcpu = &svm->vcpu;
-	struct ghcb *ghcb = svm->ghcb;
+	struct ghcb *ghcb = svm->sev_es.ghcb;
 	u64 exit_code;
 
 	/*
@@ -2134,24 +2352,29 @@ static void sev_es_sync_from_ghcb(struct vcpu_svm *svm)
 	memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap));
 }
 
-static int sev_es_validate_vmgexit(struct vcpu_svm *svm)
+static bool sev_es_validate_vmgexit(struct vcpu_svm *svm)
 {
 	struct kvm_vcpu *vcpu;
 	struct ghcb *ghcb;
-	u64 exit_code = 0;
-
-	ghcb = svm->ghcb;
+	u64 exit_code;
+	u64 reason;
 
-	/* Only GHCB Usage code 0 is supported */
-	if (ghcb->ghcb_usage)
-		goto vmgexit_err;
+	ghcb = svm->sev_es.ghcb;
 
 	/*
-	 * Retrieve the exit code now even though is may not be marked valid
+	 * Retrieve the exit code now even though it may not be marked valid
 	 * as it could help with debugging.
 	 */
 	exit_code = ghcb_get_sw_exit_code(ghcb);
 
+	/* Only GHCB Usage code 0 is supported */
+	if (ghcb->ghcb_usage) {
+		reason = GHCB_ERR_INVALID_USAGE;
+		goto vmgexit_err;
+	}
+
+	reason = GHCB_ERR_MISSING_INPUT;
+
 	if (!ghcb_sw_exit_code_is_valid(ghcb) ||
 	    !ghcb_sw_exit_info_1_is_valid(ghcb) ||
 	    !ghcb_sw_exit_info_2_is_valid(ghcb))
@@ -2230,61 +2453,66 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm)
 	case SVM_VMGEXIT_UNSUPPORTED_EVENT:
 		break;
 	default:
+		reason = GHCB_ERR_INVALID_EVENT;
 		goto vmgexit_err;
 	}
 
-	return 0;
+	return true;
 
 vmgexit_err:
 	vcpu = &svm->vcpu;
 
-	if (ghcb->ghcb_usage) {
+	if (reason == GHCB_ERR_INVALID_USAGE) {
 		vcpu_unimpl(vcpu, "vmgexit: ghcb usage %#x is not valid\n",
 			    ghcb->ghcb_usage);
+	} else if (reason == GHCB_ERR_INVALID_EVENT) {
+		vcpu_unimpl(vcpu, "vmgexit: exit code %#llx is not valid\n",
+			    exit_code);
 	} else {
-		vcpu_unimpl(vcpu, "vmgexit: exit reason %#llx is not valid\n",
+		vcpu_unimpl(vcpu, "vmgexit: exit code %#llx input is not valid\n",
 			    exit_code);
 		dump_ghcb(svm);
 	}
 
-	vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
-	vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON;
-	vcpu->run->internal.ndata = 2;
-	vcpu->run->internal.data[0] = exit_code;
-	vcpu->run->internal.data[1] = vcpu->arch.last_vmentry_cpu;
+	/* Clear the valid entries fields */
+	memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap));
+
+	ghcb_set_sw_exit_info_1(ghcb, 2);
+	ghcb_set_sw_exit_info_2(ghcb, reason);
 
-	return -EINVAL;
+	return false;
 }
 
 void sev_es_unmap_ghcb(struct vcpu_svm *svm)
 {
-	if (!svm->ghcb)
+	if (!svm->sev_es.ghcb)
 		return;
 
-	if (svm->ghcb_sa_free) {
+	if (svm->sev_es.ghcb_sa_free) {
 		/*
 		 * The scratch area lives outside the GHCB, so there is a
 		 * buffer that, depending on the operation performed, may
 		 * need to be synced, then freed.
 		 */
-		if (svm->ghcb_sa_sync) {
+		if (svm->sev_es.ghcb_sa_sync) {
 			kvm_write_guest(svm->vcpu.kvm,
-					ghcb_get_sw_scratch(svm->ghcb),
-					svm->ghcb_sa, svm->ghcb_sa_len);
-			svm->ghcb_sa_sync = false;
+					ghcb_get_sw_scratch(svm->sev_es.ghcb),
+					svm->sev_es.ghcb_sa,
+					svm->sev_es.ghcb_sa_len);
+			svm->sev_es.ghcb_sa_sync = false;
 		}
 
-		kfree(svm->ghcb_sa);
-		svm->ghcb_sa = NULL;
-		svm->ghcb_sa_free = false;
+		kvfree(svm->sev_es.ghcb_sa);
+		svm->sev_es.ghcb_sa = NULL;
+		svm->sev_es.ghcb_sa_free = false;
 	}
 
-	trace_kvm_vmgexit_exit(svm->vcpu.vcpu_id, svm->ghcb);
+	trace_kvm_vmgexit_exit(svm->vcpu.vcpu_id, svm->sev_es.ghcb);
 
 	sev_es_sync_to_ghcb(svm);
 
-	kvm_vcpu_unmap(&svm->vcpu, &svm->ghcb_map, true);
-	svm->ghcb = NULL;
+	kvm_vcpu_unmap(&svm->vcpu, &svm->sev_es.ghcb_map, true);
+	svm->sev_es.ghcb = NULL;
 }
 
 void pre_sev_run(struct vcpu_svm *svm, int cpu)
@@ -2314,7 +2542,7 @@ void pre_sev_run(struct vcpu_svm *svm, int cpu)
 static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len)
 {
 	struct vmcb_control_area *control = &svm->vmcb->control;
-	struct ghcb *ghcb = svm->ghcb;
+	struct ghcb *ghcb = svm->sev_es.ghcb;
 	u64 ghcb_scratch_beg, ghcb_scratch_end;
 	u64 scratch_gpa_beg, scratch_gpa_end;
 	void *scratch_va;
@@ -2322,14 +2550,14 @@ static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len)
 	scratch_gpa_beg = ghcb_get_sw_scratch(ghcb);
 	if (!scratch_gpa_beg) {
 		pr_err("vmgexit: scratch gpa not provided\n");
-		return false;
+		goto e_scratch;
 	}
 
 	scratch_gpa_end = scratch_gpa_beg + len;
 	if (scratch_gpa_end < scratch_gpa_beg) {
 		pr_err("vmgexit: scratch length (%#llx) not valid for scratch address (%#llx)\n",
 		       len, scratch_gpa_beg);
-		return false;
+		goto e_scratch;
 	}
 
 	if ((scratch_gpa_beg & PAGE_MASK) == control->ghcb_gpa) {
@@ -2347,10 +2575,10 @@ static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len)
 		    scratch_gpa_end > ghcb_scratch_end) {
 			pr_err("vmgexit: scratch area is outside of GHCB shared buffer area (%#llx - %#llx)\n",
 			       scratch_gpa_beg, scratch_gpa_end);
-			return false;
+			goto e_scratch;
 		}
 
-		scratch_va = (void *)svm->ghcb;
+		scratch_va = (void *)svm->sev_es.ghcb;
 		scratch_va += (scratch_gpa_beg - control->ghcb_gpa);
 	} else {
 		/*
@@ -2360,18 +2588,18 @@ static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len)
 		if (len > GHCB_SCRATCH_AREA_LIMIT) {
 			pr_err("vmgexit: scratch area exceeds KVM limits (%#llx requested, %#llx limit)\n",
 			       len, GHCB_SCRATCH_AREA_LIMIT);
-			return false;
+			goto e_scratch;
 		}
-		scratch_va = kzalloc(len, GFP_KERNEL_ACCOUNT);
+		scratch_va = kvzalloc(len, GFP_KERNEL_ACCOUNT);
 		if (!scratch_va)
-			return false;
+			goto e_scratch;
 
 		if (kvm_read_guest(svm->vcpu.kvm, scratch_gpa_beg, scratch_va, len)) {
 			/* Unable to copy scratch area from guest */
 			pr_err("vmgexit: kvm_read_guest for scratch area failed\n");
 
-			kfree(scratch_va);
-			return false;
+			kvfree(scratch_va);
+			goto e_scratch;
 		}
 
 		/*
@@ -2380,14 +2608,20 @@ static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len)
 		 * the vCPU next time (i.e. a read was requested so the data
 		 * must be written back to the guest memory).
 		 */
-		svm->ghcb_sa_sync = sync;
-		svm->ghcb_sa_free = true;
+		svm->sev_es.ghcb_sa_sync = sync;
+		svm->sev_es.ghcb_sa_free = true;
 	}
 
-	svm->ghcb_sa = scratch_va;
-	svm->ghcb_sa_len = len;
+	svm->sev_es.ghcb_sa = scratch_va;
+	svm->sev_es.ghcb_sa_len = len;
 
 	return true;
+
+e_scratch:
+	ghcb_set_sw_exit_info_1(ghcb, 2);
+	ghcb_set_sw_exit_info_2(ghcb, GHCB_ERR_INVALID_SCRATCH_AREA);
+
+	return false;
 }
 
 static void set_ghcb_msr_bits(struct vcpu_svm *svm, u64 value, u64 mask,
@@ -2438,7 +2672,7 @@ static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm)
 
 		ret = svm_invoke_exit_handler(vcpu, SVM_EXIT_CPUID);
 		if (!ret) {
-			ret = -EINVAL;
+			/* Error, keep GHCB MSR value as-is */
 			break;
 		}
 
@@ -2474,10 +2708,13 @@ static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm)
 						GHCB_MSR_TERM_REASON_POS);
 		pr_info("SEV-ES guest requested termination: %#llx:%#llx\n",
 			reason_set, reason_code);
-		fallthrough;
+
+		ret = -EINVAL;
+		break;
 	}
 	default:
-		ret = -EINVAL;
+		/* Error, keep GHCB MSR value as-is */
+		break;
 	}
 
 	trace_kvm_vmgexit_msr_protocol_exit(svm->vcpu.vcpu_id,
@@ -2501,32 +2738,35 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu)
 
 	if (!ghcb_gpa) {
 		vcpu_unimpl(vcpu, "vmgexit: GHCB gpa is not set\n");
-		return -EINVAL;
+
+		/* Without a GHCB, just return right back to the guest */
+		return 1;
 	}
 
-	if (kvm_vcpu_map(vcpu, ghcb_gpa >> PAGE_SHIFT, &svm->ghcb_map)) {
+	if (kvm_vcpu_map(vcpu, ghcb_gpa >> PAGE_SHIFT, &svm->sev_es.ghcb_map)) {
 		/* Unable to map GHCB from guest */
 		vcpu_unimpl(vcpu, "vmgexit: error mapping GHCB [%#llx] from guest\n",
 			    ghcb_gpa);
-		return -EINVAL;
+
+		/* Without a GHCB, just return right back to the guest */
+		return 1;
 	}
 
-	svm->ghcb = svm->ghcb_map.hva;
-	ghcb = svm->ghcb_map.hva;
+	svm->sev_es.ghcb = svm->sev_es.ghcb_map.hva;
+	ghcb = svm->sev_es.ghcb_map.hva;
 
 	trace_kvm_vmgexit_enter(vcpu->vcpu_id, ghcb);
 
 	exit_code = ghcb_get_sw_exit_code(ghcb);
 
-	ret = sev_es_validate_vmgexit(svm);
-	if (ret)
-		return ret;
+	if (!sev_es_validate_vmgexit(svm))
+		return 1;
 
 	sev_es_sync_from_ghcb(svm);
 	ghcb_set_sw_exit_info_1(ghcb, 0);
 	ghcb_set_sw_exit_info_2(ghcb, 0);
 
-	ret = -EINVAL;
+	ret = 1;
 	switch (exit_code) {
 	case SVM_VMGEXIT_MMIO_READ:
 		if (!setup_vmgexit_scratch(svm, true, control->exit_info_2))
@@ -2535,7 +2775,7 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu)
 		ret = kvm_sev_es_mmio_read(vcpu,
 					   control->exit_info_1,
 					   control->exit_info_2,
-					   svm->ghcb_sa);
+					   svm->sev_es.ghcb_sa);
 		break;
 	case SVM_VMGEXIT_MMIO_WRITE:
 		if (!setup_vmgexit_scratch(svm, false, control->exit_info_2))
@@ -2544,7 +2784,7 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu)
 		ret = kvm_sev_es_mmio_write(vcpu,
 					    control->exit_info_1,
 					    control->exit_info_2,
-					    svm->ghcb_sa);
+					    svm->sev_es.ghcb_sa);
 		break;
 	case SVM_VMGEXIT_NMI_COMPLETE:
 		ret = svm_invoke_exit_handler(vcpu, SVM_EXIT_IRET);
@@ -2567,20 +2807,17 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu)
 		default:
 			pr_err("svm: vmgexit: unsupported AP jump table request - exit_info_1=%#llx\n",
 			       control->exit_info_1);
-			ghcb_set_sw_exit_info_1(ghcb, 1);
-			ghcb_set_sw_exit_info_2(ghcb,
-						X86_TRAP_UD |
-						SVM_EVTINJ_TYPE_EXEPT |
-						SVM_EVTINJ_VALID);
+			ghcb_set_sw_exit_info_1(ghcb, 2);
+			ghcb_set_sw_exit_info_2(ghcb, GHCB_ERR_INVALID_INPUT);
 		}
 
-		ret = 1;
 		break;
 	}
 	case SVM_VMGEXIT_UNSUPPORTED_EVENT:
 		vcpu_unimpl(vcpu,
 			    "vmgexit: unsupported event - exit_info_1=%#llx, exit_info_2=%#llx\n",
 			    control->exit_info_1, control->exit_info_2);
+		ret = -EINVAL;
 		break;
 	default:
 		ret = svm_invoke_exit_handler(vcpu, exit_code);
@@ -2602,9 +2839,10 @@ int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in)
 		return -EINVAL;
 
 	if (!setup_vmgexit_scratch(svm, in, bytes))
-		return -EINVAL;
+		return 1;
 
-	return kvm_sev_es_string_io(&svm->vcpu, size, port, svm->ghcb_sa, count, in);
+	return kvm_sev_es_string_io(&svm->vcpu, size, port, svm->sev_es.ghcb_sa,
+				    count, in);
 }
 
 void sev_es_init_vmcb(struct vcpu_svm *svm)
@@ -2619,7 +2857,7 @@ void sev_es_init_vmcb(struct vcpu_svm *svm)
 	 * VMCB page. Do not include the encryption mask on the VMSA physical
 	 * address since hardware will access it using the guest key.
 	 */
-	svm->vmcb->control.vmsa_pa = __pa(svm->vmsa);
+	svm->vmcb->control.vmsa_pa = __pa(svm->sev_es.vmsa);
 
 	/* Can't intercept CR register access, HV can't modify CR registers */
 	svm_clr_intercept(svm, INTERCEPT_CR0_READ);
@@ -2691,8 +2929,8 @@ void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector)
 	struct vcpu_svm *svm = to_svm(vcpu);
 
 	/* First SIPI: Use the values as initially set by the VMM */
-	if (!svm->received_first_sipi) {
-		svm->received_first_sipi = true;
+	if (!svm->sev_es.received_first_sipi) {
+		svm->sev_es.received_first_sipi = true;
 		return;
 	}
 
@@ -2701,8 +2939,8 @@ void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector)
 	 * the guest will set the CS and RIP. Set SW_EXIT_INFO_2 to a
 	 * non-zero value.
 	 */
-	if (!svm->ghcb)
+	if (!svm->sev_es.ghcb)
 		return;
 
-	ghcb_set_sw_exit_info_2(svm->ghcb, 1);
+	ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, 1);
 }
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index b36ca4e476c2..5151efa424ac 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -1452,7 +1452,7 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu)
 	svm_switch_vmcb(svm, &svm->vmcb01);
 
 	if (vmsa_page)
-		svm->vmsa = page_address(vmsa_page);
+		svm->sev_es.vmsa = page_address(vmsa_page);
 
 	svm->guest_state_loaded = false;
 
@@ -1585,6 +1585,15 @@ static void svm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
 	to_svm(vcpu)->vmcb->save.rflags = rflags;
 }
 
+static bool svm_get_if_flag(struct kvm_vcpu *vcpu)
+{
+	struct vmcb *vmcb = to_svm(vcpu)->vmcb;
+
+	return sev_es_guest(vcpu->kvm)
+		? vmcb->control.int_state & SVM_GUEST_INTERRUPT_MASK
+		: kvm_get_rflags(vcpu) & X86_EFLAGS_IF;
+}
+
 static void svm_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg)
 {
 	switch (reg) {
@@ -2835,11 +2844,11 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 static int svm_complete_emulated_msr(struct kvm_vcpu *vcpu, int err)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
-	if (!err || !sev_es_guest(vcpu->kvm) || WARN_ON_ONCE(!svm->ghcb))
+	if (!err || !sev_es_guest(vcpu->kvm) || WARN_ON_ONCE(!svm->sev_es.ghcb))
 		return kvm_complete_insn_gp(vcpu, err);
 
-	ghcb_set_sw_exit_info_1(svm->ghcb, 1);
-	ghcb_set_sw_exit_info_2(svm->ghcb,
+	ghcb_set_sw_exit_info_1(svm->sev_es.ghcb, 1);
+	ghcb_set_sw_exit_info_2(svm->sev_es.ghcb,
 				X86_TRAP_GP |
 				SVM_EVTINJ_TYPE_EXEPT |
 				SVM_EVTINJ_VALID);
@@ -3121,11 +3130,6 @@ static int invpcid_interception(struct kvm_vcpu *vcpu)
 	type = svm->vmcb->control.exit_info_2;
 	gva = svm->vmcb->control.exit_info_1;
 
-	if (type > 3) {
-		kvm_inject_gp(vcpu, 0);
-		return 1;
-	}
-
 	return kvm_handle_invpcid(vcpu, type, gva);
 }
 
@@ -3573,14 +3577,7 @@ bool svm_interrupt_blocked(struct kvm_vcpu *vcpu)
 	if (!gif_set(svm))
 		return true;
 
-	if (sev_es_guest(vcpu->kvm)) {
-		/*
-		 * SEV-ES guests to not expose RFLAGS. Use the VMCB interrupt mask
-		 * bit to determine the state of the IF flag.
-		 */
-		if (!(vmcb->control.int_state & SVM_GUEST_INTERRUPT_MASK))
-			return true;
-	} else if (is_guest_mode(vcpu)) {
+	if (is_guest_mode(vcpu)) {
 		/* As long as interrupts are being delivered...  */
 		if ((svm->nested.ctl.int_ctl & V_INTR_MASKING_MASK)
 		    ? !(svm->vmcb01.ptr->save.rflags & X86_EFLAGS_IF)
@@ -3591,7 +3588,7 @@ bool svm_interrupt_blocked(struct kvm_vcpu *vcpu)
 		if (nested_exit_on_intr(svm))
 			return false;
 	} else {
-		if (!(kvm_get_rflags(vcpu) & X86_EFLAGS_IF))
+		if (!svm_get_if_flag(vcpu))
 			return true;
 	}
 
@@ -4626,6 +4623,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 	.cache_reg = svm_cache_reg,
 	.get_rflags = svm_get_rflags,
 	.set_rflags = svm_set_rflags,
+	.get_if_flag = svm_get_if_flag,
 
 	.tlb_flush_all = svm_flush_tlb,
 	.tlb_flush_current = svm_flush_tlb,
@@ -4656,7 +4654,6 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 	.load_eoi_exitmap = svm_load_eoi_exitmap,
 	.hwapic_irr_update = svm_hwapic_irr_update,
 	.hwapic_isr_update = svm_hwapic_isr_update,
-	.sync_pir_to_irr = kvm_lapic_find_highest_irr,
 	.apicv_post_state_restore = avic_post_state_restore,
 
 	.set_tss_addr = svm_set_tss_addr,
@@ -4701,6 +4698,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 	.mem_enc_unreg_region = svm_unregister_enc_region,
 
 	.vm_copy_enc_context_from = svm_vm_copy_asid_from,
+	.vm_move_enc_context_from = svm_vm_migrate_from,
 
 	.can_emulate_instruction = svm_can_emulate_instruction,
 
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 5e9510d4574e..1c7306c370fa 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -79,7 +79,9 @@ struct kvm_sev_info {
 	struct list_head regions_list;  /* List of registered regions */
 	u64 ap_jump_table;	/* SEV-ES AP Jump Table address */
 	struct kvm *enc_context_owner; /* Owner of copied encryption context */
+	unsigned long num_mirrored_vms; /* Number of VMs sharing this ASID */
 	struct misc_cg *misc_cg; /* For misc cgroup accounting */
+	atomic_t migration_in_progress;
 };
 
 struct kvm_svm {
@@ -123,6 +125,20 @@ struct svm_nested_state {
 	bool initialized;
 };
 
+struct vcpu_sev_es_state {
+	/* SEV-ES support */
+	struct vmcb_save_area *vmsa;
+	struct ghcb *ghcb;
+	struct kvm_host_map ghcb_map;
+	bool received_first_sipi;
+
+	/* SEV-ES scratch area support */
+	void *ghcb_sa;
+	u32 ghcb_sa_len;
+	bool ghcb_sa_sync;
+	bool ghcb_sa_free;
+};
+
 struct vcpu_svm {
 	struct kvm_vcpu vcpu;
 	/* vmcb always points at current_vmcb->ptr, it's purely a shorthand. */
@@ -186,17 +202,7 @@ struct vcpu_svm {
 		DECLARE_BITMAP(write, MAX_DIRECT_ACCESS_MSRS);
 	} shadow_msr_intercept;
 
-	/* SEV-ES support */
-	struct vmcb_save_area *vmsa;
-	struct ghcb *ghcb;
-	struct kvm_host_map ghcb_map;
-	bool received_first_sipi;
-
-	/* SEV-ES scratch area support */
-	void *ghcb_sa;
-	u32 ghcb_sa_len;
-	bool ghcb_sa_sync;
-	bool ghcb_sa_free;
+	struct vcpu_sev_es_state sev_es;
 
 	bool guest_state_loaded;
 };
@@ -242,7 +248,7 @@ static __always_inline bool sev_es_guest(struct kvm *kvm)
 #ifdef CONFIG_KVM_AMD_SEV
 	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
 
-	return sev_guest(kvm) && sev->es_active;
+	return sev->es_active && !WARN_ON_ONCE(!sev->active);
 #else
 	return false;
 #endif
@@ -558,6 +564,7 @@ int svm_register_enc_region(struct kvm *kvm,
 int svm_unregister_enc_region(struct kvm *kvm,
 			      struct kvm_enc_region *range);
 int svm_vm_copy_asid_from(struct kvm *kvm, unsigned int source_fd);
+int svm_vm_migrate_from(struct kvm *kvm, unsigned int source_fd);
 void pre_sev_run(struct vcpu_svm *svm, int cpu);
 void __init sev_set_cpu_caps(void);
 void __init sev_hardware_setup(void);
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index b4ee5e9f9e20..9c941535f78c 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -525,67 +525,19 @@ static int nested_vmx_check_tpr_shadow_controls(struct kvm_vcpu *vcpu,
 }
 
 /*
- * Check if MSR is intercepted for L01 MSR bitmap.
+ * For x2APIC MSRs, ignore the vmcs01 bitmap.  L1 can enable x2APIC without L1
+ * itself utilizing x2APIC.  All MSRs were previously set to be intercepted,
+ * only the "disable intercept" case needs to be handled.
  */
-static bool msr_write_intercepted_l01(struct kvm_vcpu *vcpu, u32 msr)
+static void nested_vmx_disable_intercept_for_x2apic_msr(unsigned long *msr_bitmap_l1,
+							unsigned long *msr_bitmap_l0,
+							u32 msr, int type)
 {
-	unsigned long *msr_bitmap;
-	int f = sizeof(unsigned long);
+	if (type & MSR_TYPE_R && !vmx_test_msr_bitmap_read(msr_bitmap_l1, msr))
+		vmx_clear_msr_bitmap_read(msr_bitmap_l0, msr);
 
-	if (!cpu_has_vmx_msr_bitmap())
-		return true;
-
-	msr_bitmap = to_vmx(vcpu)->vmcs01.msr_bitmap;
-
-	if (msr <= 0x1fff) {
-		return !!test_bit(msr, msr_bitmap + 0x800 / f);
-	} else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) {
-		msr &= 0x1fff;
-		return !!test_bit(msr, msr_bitmap + 0xc00 / f);
-	}
-
-	return true;
-}
-
-/*
- * If a msr is allowed by L0, we should check whether it is allowed by L1.
- * The corresponding bit will be cleared unless both of L0 and L1 allow it.
- */
-static void nested_vmx_disable_intercept_for_msr(unsigned long *msr_bitmap_l1,
-					       unsigned long *msr_bitmap_nested,
-					       u32 msr, int type)
-{
-	int f = sizeof(unsigned long);
-
-	/*
-	 * See Intel PRM Vol. 3, 20.6.9 (MSR-Bitmap Address). Early manuals
-	 * have the write-low and read-high bitmap offsets the wrong way round.
-	 * We can control MSRs 0x00000000-0x00001fff and 0xc0000000-0xc0001fff.
-	 */
-	if (msr <= 0x1fff) {
-		if (type & MSR_TYPE_R &&
-		   !test_bit(msr, msr_bitmap_l1 + 0x000 / f))
-			/* read-low */
-			__clear_bit(msr, msr_bitmap_nested + 0x000 / f);
-
-		if (type & MSR_TYPE_W &&
-		   !test_bit(msr, msr_bitmap_l1 + 0x800 / f))
-			/* write-low */
-			__clear_bit(msr, msr_bitmap_nested + 0x800 / f);
-
-	} else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) {
-		msr &= 0x1fff;
-		if (type & MSR_TYPE_R &&
-		   !test_bit(msr, msr_bitmap_l1 + 0x400 / f))
-			/* read-high */
-			__clear_bit(msr, msr_bitmap_nested + 0x400 / f);
-
-		if (type & MSR_TYPE_W &&
-		   !test_bit(msr, msr_bitmap_l1 + 0xc00 / f))
-			/* write-high */
-			__clear_bit(msr, msr_bitmap_nested + 0xc00 / f);
-
-	}
+	if (type & MSR_TYPE_W && !vmx_test_msr_bitmap_write(msr_bitmap_l1, msr))
+		vmx_clear_msr_bitmap_write(msr_bitmap_l0, msr);
 }
 
 static inline void enable_x2apic_msr_intercepts(unsigned long *msr_bitmap)
@@ -600,6 +552,34 @@ static inline void enable_x2apic_msr_intercepts(unsigned long *msr_bitmap)
 	}
 }
 
+#define BUILD_NVMX_MSR_INTERCEPT_HELPER(rw)					\
+static inline									\
+void nested_vmx_set_msr_##rw##_intercept(struct vcpu_vmx *vmx,			\
+					 unsigned long *msr_bitmap_l1,		\
+					 unsigned long *msr_bitmap_l0, u32 msr)	\
+{										\
+	if (vmx_test_msr_bitmap_##rw(vmx->vmcs01.msr_bitmap, msr) ||		\
+	    vmx_test_msr_bitmap_##rw(msr_bitmap_l1, msr))			\
+		vmx_set_msr_bitmap_##rw(msr_bitmap_l0, msr);			\
+	else									\
+		vmx_clear_msr_bitmap_##rw(msr_bitmap_l0, msr);			\
+}
+BUILD_NVMX_MSR_INTERCEPT_HELPER(read)
+BUILD_NVMX_MSR_INTERCEPT_HELPER(write)
+
+static inline void nested_vmx_set_intercept_for_msr(struct vcpu_vmx *vmx,
+						    unsigned long *msr_bitmap_l1,
+						    unsigned long *msr_bitmap_l0,
+						    u32 msr, int types)
+{
+	if (types & MSR_TYPE_R)
+		nested_vmx_set_msr_read_intercept(vmx, msr_bitmap_l1,
+						  msr_bitmap_l0, msr);
+	if (types & MSR_TYPE_W)
+		nested_vmx_set_msr_write_intercept(vmx, msr_bitmap_l1,
+						   msr_bitmap_l0, msr);
+}
+
 /*
  * Merge L0's and L1's MSR bitmap, return false to indicate that
  * we do not use the hardware.
@@ -607,10 +587,11 @@ static inline void enable_x2apic_msr_intercepts(unsigned long *msr_bitmap)
 static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
 						 struct vmcs12 *vmcs12)
 {
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	int msr;
 	unsigned long *msr_bitmap_l1;
-	unsigned long *msr_bitmap_l0 = to_vmx(vcpu)->nested.vmcs02.msr_bitmap;
-	struct kvm_host_map *map = &to_vmx(vcpu)->nested.msr_bitmap_map;
+	unsigned long *msr_bitmap_l0 = vmx->nested.vmcs02.msr_bitmap;
+	struct kvm_host_map *map = &vmx->nested.msr_bitmap_map;
 
 	/* Nothing to do if the MSR bitmap is not in use.  */
 	if (!cpu_has_vmx_msr_bitmap() ||
@@ -625,7 +606,7 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
 	/*
 	 * To keep the control flow simple, pay eight 8-byte writes (sixteen
 	 * 4-byte writes on 32-bit systems) up front to enable intercepts for
-	 * the x2APIC MSR range and selectively disable them below.
+	 * the x2APIC MSR range and selectively toggle those relevant to L2.
 	 */
 	enable_x2apic_msr_intercepts(msr_bitmap_l0);
 
@@ -644,61 +625,44 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
 			}
 		}
 
-		nested_vmx_disable_intercept_for_msr(
+		nested_vmx_disable_intercept_for_x2apic_msr(
 			msr_bitmap_l1, msr_bitmap_l0,
 			X2APIC_MSR(APIC_TASKPRI),
 			MSR_TYPE_R | MSR_TYPE_W);
 
 		if (nested_cpu_has_vid(vmcs12)) {
-			nested_vmx_disable_intercept_for_msr(
+			nested_vmx_disable_intercept_for_x2apic_msr(
 				msr_bitmap_l1, msr_bitmap_l0,
 				X2APIC_MSR(APIC_EOI),
 				MSR_TYPE_W);
-			nested_vmx_disable_intercept_for_msr(
+			nested_vmx_disable_intercept_for_x2apic_msr(
 				msr_bitmap_l1, msr_bitmap_l0,
 				X2APIC_MSR(APIC_SELF_IPI),
 				MSR_TYPE_W);
 		}
 	}
 
-	/* KVM unconditionally exposes the FS/GS base MSRs to L1. */
+	/*
+	 * Always check vmcs01's bitmap to honor userspace MSR filters and any
+	 * other runtime changes to vmcs01's bitmap, e.g. dynamic pass-through.
+	 */
 #ifdef CONFIG_X86_64
-	nested_vmx_disable_intercept_for_msr(msr_bitmap_l1, msr_bitmap_l0,
-					     MSR_FS_BASE, MSR_TYPE_RW);
+	nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0,
+					 MSR_FS_BASE, MSR_TYPE_RW);
 
-	nested_vmx_disable_intercept_for_msr(msr_bitmap_l1, msr_bitmap_l0,
-					     MSR_GS_BASE, MSR_TYPE_RW);
+	nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0,
+					 MSR_GS_BASE, MSR_TYPE_RW);
 
-	nested_vmx_disable_intercept_for_msr(msr_bitmap_l1, msr_bitmap_l0,
-					     MSR_KERNEL_GS_BASE, MSR_TYPE_RW);
+	nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0,
+					 MSR_KERNEL_GS_BASE, MSR_TYPE_RW);
 #endif
+	nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0,
+					 MSR_IA32_SPEC_CTRL, MSR_TYPE_RW);
 
-	/*
-	 * Checking the L0->L1 bitmap is trying to verify two things:
-	 *
-	 * 1. L0 gave a permission to L1 to actually passthrough the MSR. This
-	 *    ensures that we do not accidentally generate an L02 MSR bitmap
-	 *    from the L12 MSR bitmap that is too permissive.
-	 * 2. That L1 or L2s have actually used the MSR. This avoids
-	 *    unnecessarily merging of the bitmap if the MSR is unused. This
-	 *    works properly because we only update the L01 MSR bitmap lazily.
-	 *    So even if L0 should pass L1 these MSRs, the L01 bitmap is only
-	 *    updated to reflect this when L1 (or its L2s) actually write to
-	 *    the MSR.
-	 */
-	if (!msr_write_intercepted_l01(vcpu, MSR_IA32_SPEC_CTRL))
-		nested_vmx_disable_intercept_for_msr(
-					msr_bitmap_l1, msr_bitmap_l0,
-					MSR_IA32_SPEC_CTRL,
-					MSR_TYPE_R | MSR_TYPE_W);
-
-	if (!msr_write_intercepted_l01(vcpu, MSR_IA32_PRED_CMD))
-		nested_vmx_disable_intercept_for_msr(
-					msr_bitmap_l1, msr_bitmap_l0,
-					MSR_IA32_PRED_CMD,
-					MSR_TYPE_W);
+	nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0,
+					 MSR_IA32_PRED_CMD, MSR_TYPE_W);
 
-	kvm_vcpu_unmap(vcpu, &to_vmx(vcpu)->nested.msr_bitmap_map, false);
+	kvm_vcpu_unmap(vcpu, &vmx->nested.msr_bitmap_map, false);
 
 	return true;
 }
@@ -706,33 +670,39 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
 static void nested_cache_shadow_vmcs12(struct kvm_vcpu *vcpu,
 				       struct vmcs12 *vmcs12)
 {
-	struct kvm_host_map map;
-	struct vmcs12 *shadow;
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	struct gfn_to_hva_cache *ghc = &vmx->nested.shadow_vmcs12_cache;
 
 	if (!nested_cpu_has_shadow_vmcs(vmcs12) ||
 	    vmcs12->vmcs_link_pointer == INVALID_GPA)
 		return;
 
-	shadow = get_shadow_vmcs12(vcpu);
-
-	if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmcs12->vmcs_link_pointer), &map))
+	if (ghc->gpa != vmcs12->vmcs_link_pointer &&
+	    kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc,
+				      vmcs12->vmcs_link_pointer, VMCS12_SIZE))
 		return;
 
-	memcpy(shadow, map.hva, VMCS12_SIZE);
-	kvm_vcpu_unmap(vcpu, &map, false);
+	kvm_read_guest_cached(vmx->vcpu.kvm, ghc, get_shadow_vmcs12(vcpu),
+			      VMCS12_SIZE);
 }
 
 static void nested_flush_cached_shadow_vmcs12(struct kvm_vcpu *vcpu,
 					      struct vmcs12 *vmcs12)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	struct gfn_to_hva_cache *ghc = &vmx->nested.shadow_vmcs12_cache;
 
 	if (!nested_cpu_has_shadow_vmcs(vmcs12) ||
 	    vmcs12->vmcs_link_pointer == INVALID_GPA)
 		return;
 
-	kvm_write_guest(vmx->vcpu.kvm, vmcs12->vmcs_link_pointer,
-			get_shadow_vmcs12(vcpu), VMCS12_SIZE);
+	if (ghc->gpa != vmcs12->vmcs_link_pointer &&
+	    kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc,
+				      vmcs12->vmcs_link_pointer, VMCS12_SIZE))
+		return;
+
+	kvm_write_guest_cached(vmx->vcpu.kvm, ghc, get_shadow_vmcs12(vcpu),
+			       VMCS12_SIZE);
 }
 
 /*
@@ -1192,29 +1162,26 @@ static void nested_vmx_transition_tlb_flush(struct kvm_vcpu *vcpu,
 	WARN_ON(!enable_vpid);
 
 	/*
-	 * If VPID is enabled and used by vmc12, but L2 does not have a unique
-	 * TLB tag (ASID), i.e. EPT is disabled and KVM was unable to allocate
-	 * a VPID for L2, flush the current context as the effective ASID is
-	 * common to both L1 and L2.
-	 *
-	 * Defer the flush so that it runs after vmcs02.EPTP has been set by
-	 * KVM_REQ_LOAD_MMU_PGD (if nested EPT is enabled) and to avoid
-	 * redundant flushes further down the nested pipeline.
-	 *
-	 * If a TLB flush isn't required due to any of the above, and vpid12 is
-	 * changing then the new "virtual" VPID (vpid12) will reuse the same
-	 * "real" VPID (vpid02), and so needs to be flushed.  There's no direct
-	 * mapping between vpid02 and vpid12, vpid02 is per-vCPU and reused for
-	 * all nested vCPUs.  Remember, a flush on VM-Enter does not invalidate
-	 * guest-physical mappings, so there is no need to sync the nEPT MMU.
+	 * VPID is enabled and in use by vmcs12.  If vpid12 is changing, then
+	 * emulate a guest TLB flush as KVM does not track vpid12 history nor
+	 * is the VPID incorporated into the MMU context.  I.e. KVM must assume
+	 * that the new vpid12 has never been used and thus represents a new
+	 * guest ASID that cannot have entries in the TLB.
 	 */
-	if (!nested_has_guest_tlb_tag(vcpu)) {
-		kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu);
-	} else if (is_vmenter &&
-		   vmcs12->virtual_processor_id != vmx->nested.last_vpid) {
+	if (is_vmenter && vmcs12->virtual_processor_id != vmx->nested.last_vpid) {
 		vmx->nested.last_vpid = vmcs12->virtual_processor_id;
-		vpid_sync_context(nested_get_vpid02(vcpu));
+		kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu);
+		return;
 	}
+
+	/*
+	 * If VPID is enabled, used by vmc12, and vpid12 is not changing but
+	 * does not have a unique TLB tag (ASID), i.e. EPT is disabled and
+	 * KVM was unable to allocate a VPID for L2, flush the current context
+	 * as the effective ASID is common to both L1 and L2.
+	 */
+	if (!nested_has_guest_tlb_tag(vcpu))
+		kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu);
 }
 
 static bool is_bitwise_subset(u64 superset, u64 subset, u64 mask)
@@ -2624,8 +2591,10 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 
 	if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL) &&
 	    WARN_ON_ONCE(kvm_set_msr(vcpu, MSR_CORE_PERF_GLOBAL_CTRL,
-				     vmcs12->guest_ia32_perf_global_ctrl)))
+				     vmcs12->guest_ia32_perf_global_ctrl))) {
+		*entry_failure_code = ENTRY_FAIL_DEFAULT;
 		return -EINVAL;
+	}
 
 	kvm_rsp_write(vcpu, vmcs12->guest_rsp);
 	kvm_rip_write(vcpu, vmcs12->guest_rip);
@@ -2866,6 +2835,17 @@ static int nested_vmx_check_controls(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
+static int nested_vmx_check_address_space_size(struct kvm_vcpu *vcpu,
+				       struct vmcs12 *vmcs12)
+{
+#ifdef CONFIG_X86_64
+	if (CC(!!(vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE) !=
+		!!(vcpu->arch.efer & EFER_LMA)))
+		return -EINVAL;
+#endif
+	return 0;
+}
+
 static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu,
 				       struct vmcs12 *vmcs12)
 {
@@ -2890,18 +2870,16 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu,
 		return -EINVAL;
 
 #ifdef CONFIG_X86_64
-	ia32e = !!(vcpu->arch.efer & EFER_LMA);
+	ia32e = !!(vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE);
 #else
 	ia32e = false;
 #endif
 
 	if (ia32e) {
-		if (CC(!(vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE)) ||
-		    CC(!(vmcs12->host_cr4 & X86_CR4_PAE)))
+		if (CC(!(vmcs12->host_cr4 & X86_CR4_PAE)))
 			return -EINVAL;
 	} else {
-		if (CC(vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE) ||
-		    CC(vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE) ||
+		if (CC(vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE) ||
 		    CC(vmcs12->host_cr4 & X86_CR4_PCIDE) ||
 		    CC((vmcs12->host_rip) >> 32))
 			return -EINVAL;
@@ -2946,9 +2924,9 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu,
 static int nested_vmx_check_vmcs_link_ptr(struct kvm_vcpu *vcpu,
 					  struct vmcs12 *vmcs12)
 {
-	int r = 0;
-	struct vmcs12 *shadow;
-	struct kvm_host_map map;
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	struct gfn_to_hva_cache *ghc = &vmx->nested.shadow_vmcs12_cache;
+	struct vmcs_hdr hdr;
 
 	if (vmcs12->vmcs_link_pointer == INVALID_GPA)
 		return 0;
@@ -2956,17 +2934,21 @@ static int nested_vmx_check_vmcs_link_ptr(struct kvm_vcpu *vcpu,
 	if (CC(!page_address_valid(vcpu, vmcs12->vmcs_link_pointer)))
 		return -EINVAL;
 
-	if (CC(kvm_vcpu_map(vcpu, gpa_to_gfn(vmcs12->vmcs_link_pointer), &map)))
-		return -EINVAL;
+	if (ghc->gpa != vmcs12->vmcs_link_pointer &&
+	    CC(kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc,
+					 vmcs12->vmcs_link_pointer, VMCS12_SIZE)))
+                return -EINVAL;
 
-	shadow = map.hva;
+	if (CC(kvm_read_guest_offset_cached(vcpu->kvm, ghc, &hdr,
+					    offsetof(struct vmcs12, hdr),
+					    sizeof(hdr))))
+		return -EINVAL;
 
-	if (CC(shadow->hdr.revision_id != VMCS12_REVISION) ||
-	    CC(shadow->hdr.shadow_vmcs != nested_cpu_has_shadow_vmcs(vmcs12)))
-		r = -EINVAL;
+	if (CC(hdr.revision_id != VMCS12_REVISION) ||
+	    CC(hdr.shadow_vmcs != nested_cpu_has_shadow_vmcs(vmcs12)))
+		return -EINVAL;
 
-	kvm_vcpu_unmap(vcpu, &map, false);
-	return r;
+	return 0;
 }
 
 /*
@@ -3361,8 +3343,7 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,
 	};
 	u32 failed_index;
 
-	if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu))
-		kvm_vcpu_flush_tlb_current(vcpu);
+	kvm_service_local_tlb_flush_requests(vcpu);
 
 	evaluate_pending_interrupts = exec_controls_get(vmx) &
 		(CPU_BASED_INTR_WINDOW_EXITING | CPU_BASED_NMI_WINDOW_EXITING);
@@ -3571,6 +3552,9 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 	if (nested_vmx_check_controls(vcpu, vmcs12))
 		return nested_vmx_fail(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD);
 
+	if (nested_vmx_check_address_space_size(vcpu, vmcs12))
+		return nested_vmx_fail(vcpu, VMXERR_ENTRY_INVALID_HOST_STATE_FIELD);
+
 	if (nested_vmx_check_host_state(vcpu, vmcs12))
 		return nested_vmx_fail(vcpu, VMXERR_ENTRY_INVALID_HOST_STATE_FIELD);
 
@@ -4516,9 +4500,8 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
 		(void)nested_get_evmcs_page(vcpu);
 	}
 
-	/* Service the TLB flush request for L2 before switching to L1. */
-	if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu))
-		kvm_vcpu_flush_tlb_current(vcpu);
+	/* Service pending TLB flush requests for L2 before switching to L1. */
+	kvm_service_local_tlb_flush_requests(vcpu);
 
 	/*
 	 * VCPU_EXREG_PDPTR will be clobbered in arch/x86/kvm/vmx/vmx.h between
@@ -4871,6 +4854,7 @@ static int enter_vmx_operation(struct kvm_vcpu *vcpu)
 	if (!vmx->nested.cached_vmcs12)
 		goto out_cached_vmcs12;
 
+	vmx->nested.shadow_vmcs12_cache.gpa = INVALID_GPA;
 	vmx->nested.cached_shadow_vmcs12 = kzalloc(VMCS12_SIZE, GFP_KERNEL_ACCOUNT);
 	if (!vmx->nested.cached_shadow_vmcs12)
 		goto out_cached_shadow_vmcs12;
@@ -5300,10 +5284,10 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu)
 		return 1;
 
 	if (vmx->nested.current_vmptr != vmptr) {
-		struct kvm_host_map map;
-		struct vmcs12 *new_vmcs12;
+		struct gfn_to_hva_cache *ghc = &vmx->nested.vmcs12_cache;
+		struct vmcs_hdr hdr;
 
-		if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmptr), &map)) {
+		if (kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, vmptr, VMCS12_SIZE)) {
 			/*
 			 * Reads from an unbacked page return all 1s,
 			 * which means that the 32 bits located at the
@@ -5314,12 +5298,16 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu)
 				VMXERR_VMPTRLD_INCORRECT_VMCS_REVISION_ID);
 		}
 
-		new_vmcs12 = map.hva;
+		if (kvm_read_guest_offset_cached(vcpu->kvm, ghc, &hdr,
+						 offsetof(struct vmcs12, hdr),
+						 sizeof(hdr))) {
+			return nested_vmx_fail(vcpu,
+				VMXERR_VMPTRLD_INCORRECT_VMCS_REVISION_ID);
+		}
 
-		if (new_vmcs12->hdr.revision_id != VMCS12_REVISION ||
-		    (new_vmcs12->hdr.shadow_vmcs &&
+		if (hdr.revision_id != VMCS12_REVISION ||
+		    (hdr.shadow_vmcs &&
 		     !nested_cpu_has_vmx_shadow_vmcs(vcpu))) {
-			kvm_vcpu_unmap(vcpu, &map, false);
 			return nested_vmx_fail(vcpu,
 				VMXERR_VMPTRLD_INCORRECT_VMCS_REVISION_ID);
 		}
@@ -5330,8 +5318,11 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu)
 		 * Load VMCS12 from guest memory since it is not already
 		 * cached.
 		 */
-		memcpy(vmx->nested.cached_vmcs12, new_vmcs12, VMCS12_SIZE);
-		kvm_vcpu_unmap(vcpu, &map, false);
+		if (kvm_read_guest_cached(vcpu->kvm, ghc, vmx->nested.cached_vmcs12,
+					  VMCS12_SIZE)) {
+			return nested_vmx_fail(vcpu,
+				VMXERR_VMPTRLD_INCORRECT_VMCS_REVISION_ID);
+		}
 
 		set_current_vmptr(vmx, vmptr);
 	}
@@ -5379,7 +5370,7 @@ static int handle_invept(struct kvm_vcpu *vcpu)
 	struct {
 		u64 eptp, gpa;
 	} operand;
-	int i, r;
+	int i, r, gpr_index;
 
 	if (!(vmx->nested.msrs.secondary_ctls_high &
 	      SECONDARY_EXEC_ENABLE_EPT) ||
@@ -5392,7 +5383,8 @@ static int handle_invept(struct kvm_vcpu *vcpu)
 		return 1;
 
 	vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
-	type = kvm_register_read(vcpu, (vmx_instruction_info >> 28) & 0xf);
+	gpr_index = vmx_get_instr_info_reg2(vmx_instruction_info);
+	type = kvm_register_read(vcpu, gpr_index);
 
 	types = (vmx->nested.msrs.ept_caps >> VMX_EPT_EXTENT_SHIFT) & 6;
 
@@ -5459,7 +5451,7 @@ static int handle_invvpid(struct kvm_vcpu *vcpu)
 		u64 gla;
 	} operand;
 	u16 vpid02;
-	int r;
+	int r, gpr_index;
 
 	if (!(vmx->nested.msrs.secondary_ctls_high &
 	      SECONDARY_EXEC_ENABLE_VPID) ||
@@ -5472,7 +5464,8 @@ static int handle_invvpid(struct kvm_vcpu *vcpu)
 		return 1;
 
 	vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
-	type = kvm_register_read(vcpu, (vmx_instruction_info >> 28) & 0xf);
+	gpr_index = vmx_get_instr_info_reg2(vmx_instruction_info);
+	type = kvm_register_read(vcpu, gpr_index);
 
 	types = (vmx->nested.msrs.vpid_caps &
 			VMX_VPID_EXTENT_SUPPORTED_MASK) >> 8;
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index b8e0d21b7c8a..1b7456b2177b 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -118,16 +118,15 @@ 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_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx)
+static bool 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);
 
 	idx &= ~(3u << 30);
 
-	return (!fixed && idx >= pmu->nr_arch_gp_counters) ||
-		(fixed && idx >= pmu->nr_arch_fixed_counters);
+	return fixed ? idx < pmu->nr_arch_fixed_counters
+		     : idx < pmu->nr_arch_gp_counters;
 }
 
 static struct kvm_pmc *intel_rdpmc_ecx_to_pmc(struct kvm_vcpu *vcpu,
diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c
index 5f81ef092bd4..1c94783b5a54 100644
--- a/arch/x86/kvm/vmx/posted_intr.c
+++ b/arch/x86/kvm/vmx/posted_intr.c
@@ -5,6 +5,7 @@
 #include <asm/cpu.h>
 
 #include "lapic.h"
+#include "irq.h"
 #include "posted_intr.h"
 #include "trace.h"
 #include "vmx.h"
@@ -77,13 +78,18 @@ after_clear_sn:
 		pi_set_on(pi_desc);
 }
 
+static bool vmx_can_use_vtd_pi(struct kvm *kvm)
+{
+	return irqchip_in_kernel(kvm) && enable_apicv &&
+		kvm_arch_has_assigned_device(kvm) &&
+		irq_remapping_cap(IRQ_POSTING_CAP);
+}
+
 void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu)
 {
 	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
 
-	if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
-		!irq_remapping_cap(IRQ_POSTING_CAP)  ||
-		!kvm_vcpu_apicv_active(vcpu))
+	if (!vmx_can_use_vtd_pi(vcpu->kvm))
 		return;
 
 	/* Set SN when the vCPU is preempted */
@@ -141,9 +147,7 @@ int pi_pre_block(struct kvm_vcpu *vcpu)
 	struct pi_desc old, new;
 	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
 
-	if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
-		!irq_remapping_cap(IRQ_POSTING_CAP)  ||
-		!kvm_vcpu_apicv_active(vcpu))
+	if (!vmx_can_use_vtd_pi(vcpu->kvm))
 		return 0;
 
 	WARN_ON(irqs_disabled());
@@ -270,9 +274,7 @@ int pi_update_irte(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq,
 	struct vcpu_data vcpu_info;
 	int idx, ret = 0;
 
-	if (!kvm_arch_has_assigned_device(kvm) ||
-	    !irq_remapping_cap(IRQ_POSTING_CAP) ||
-	    !kvm_vcpu_apicv_active(kvm->vcpus[0]))
+	if (!vmx_can_use_vtd_pi(kvm))
 		return 0;
 
 	idx = srcu_read_lock(&kvm->irq_srcu);
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 76861b66bbcf..0dbf94eb954f 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -769,24 +769,13 @@ void vmx_update_exception_bitmap(struct kvm_vcpu *vcpu)
 /*
  * Check if MSR is intercepted for currently loaded MSR bitmap.
  */
-static bool msr_write_intercepted(struct kvm_vcpu *vcpu, u32 msr)
+static bool msr_write_intercepted(struct vcpu_vmx *vmx, u32 msr)
 {
-	unsigned long *msr_bitmap;
-	int f = sizeof(unsigned long);
-
-	if (!cpu_has_vmx_msr_bitmap())
+	if (!(exec_controls_get(vmx) & CPU_BASED_USE_MSR_BITMAPS))
 		return true;
 
-	msr_bitmap = to_vmx(vcpu)->loaded_vmcs->msr_bitmap;
-
-	if (msr <= 0x1fff) {
-		return !!test_bit(msr, msr_bitmap + 0x800 / f);
-	} else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) {
-		msr &= 0x1fff;
-		return !!test_bit(msr, msr_bitmap + 0xc00 / f);
-	}
-
-	return true;
+	return vmx_test_msr_bitmap_write(vmx->loaded_vmcs->msr_bitmap,
+					 MSR_IA32_SPEC_CTRL);
 }
 
 static void clear_atomic_switch_msr_special(struct vcpu_vmx *vmx,
@@ -1374,6 +1363,11 @@ void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
 		vmx->emulation_required = vmx_emulation_required(vcpu);
 }
 
+static bool vmx_get_if_flag(struct kvm_vcpu *vcpu)
+{
+	return vmx_get_rflags(vcpu) & X86_EFLAGS_IF;
+}
+
 u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu)
 {
 	u32 interruptibility = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO);
@@ -2657,15 +2651,6 @@ int alloc_loaded_vmcs(struct loaded_vmcs *loaded_vmcs)
 		if (!loaded_vmcs->msr_bitmap)
 			goto out_vmcs;
 		memset(loaded_vmcs->msr_bitmap, 0xff, PAGE_SIZE);
-
-		if (IS_ENABLED(CONFIG_HYPERV) &&
-		    static_branch_unlikely(&enable_evmcs) &&
-		    (ms_hyperv.nested_features & HV_X64_NESTED_MSR_BITMAP)) {
-			struct hv_enlightened_vmcs *evmcs =
-				(struct hv_enlightened_vmcs *)loaded_vmcs->vmcs;
-
-			evmcs->hv_enlightenments_control.msr_bitmap = 1;
-		}
 	}
 
 	memset(&loaded_vmcs->host_state, 0, sizeof(struct vmcs_host_state));
@@ -2929,6 +2914,13 @@ static void vmx_flush_tlb_all(struct kvm_vcpu *vcpu)
 	}
 }
 
+static inline int vmx_get_current_vpid(struct kvm_vcpu *vcpu)
+{
+	if (is_guest_mode(vcpu))
+		return nested_get_vpid02(vcpu);
+	return to_vmx(vcpu)->vpid;
+}
+
 static void vmx_flush_tlb_current(struct kvm_vcpu *vcpu)
 {
 	struct kvm_mmu *mmu = vcpu->arch.mmu;
@@ -2941,31 +2933,29 @@ static void vmx_flush_tlb_current(struct kvm_vcpu *vcpu)
 	if (enable_ept)
 		ept_sync_context(construct_eptp(vcpu, root_hpa,
 						mmu->shadow_root_level));
-	else if (!is_guest_mode(vcpu))
-		vpid_sync_context(to_vmx(vcpu)->vpid);
 	else
-		vpid_sync_context(nested_get_vpid02(vcpu));
+		vpid_sync_context(vmx_get_current_vpid(vcpu));
 }
 
 static void vmx_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t addr)
 {
 	/*
-	 * vpid_sync_vcpu_addr() is a nop if vmx->vpid==0, see the comment in
+	 * vpid_sync_vcpu_addr() is a nop if vpid==0, see the comment in
 	 * vmx_flush_tlb_guest() for an explanation of why this is ok.
 	 */
-	vpid_sync_vcpu_addr(to_vmx(vcpu)->vpid, addr);
+	vpid_sync_vcpu_addr(vmx_get_current_vpid(vcpu), addr);
 }
 
 static void vmx_flush_tlb_guest(struct kvm_vcpu *vcpu)
 {
 	/*
-	 * vpid_sync_context() is a nop if vmx->vpid==0, e.g. if enable_vpid==0
-	 * or a vpid couldn't be allocated for this vCPU.  VM-Enter and VM-Exit
-	 * are required to flush GVA->{G,H}PA mappings from the TLB if vpid is
+	 * vpid_sync_context() is a nop if vpid==0, e.g. if enable_vpid==0 or a
+	 * vpid couldn't be allocated for this vCPU.  VM-Enter and VM-Exit are
+	 * required to flush GVA->{G,H}PA mappings from the TLB if vpid is
 	 * disabled (VM-Enter with vpid enabled and vpid==0 is disallowed),
 	 * i.e. no explicit INVVPID is necessary.
 	 */
-	vpid_sync_context(to_vmx(vcpu)->vpid);
+	vpid_sync_context(vmx_get_current_vpid(vcpu));
 }
 
 void vmx_ept_load_pdptrs(struct kvm_vcpu *vcpu)
@@ -3697,46 +3687,6 @@ void free_vpid(int vpid)
 	spin_unlock(&vmx_vpid_lock);
 }
 
-static void vmx_clear_msr_bitmap_read(ulong *msr_bitmap, u32 msr)
-{
-	int f = sizeof(unsigned long);
-
-	if (msr <= 0x1fff)
-		__clear_bit(msr, msr_bitmap + 0x000 / f);
-	else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff))
-		__clear_bit(msr & 0x1fff, msr_bitmap + 0x400 / f);
-}
-
-static void vmx_clear_msr_bitmap_write(ulong *msr_bitmap, u32 msr)
-{
-	int f = sizeof(unsigned long);
-
-	if (msr <= 0x1fff)
-		__clear_bit(msr, msr_bitmap + 0x800 / f);
-	else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff))
-		__clear_bit(msr & 0x1fff, msr_bitmap + 0xc00 / f);
-}
-
-static void vmx_set_msr_bitmap_read(ulong *msr_bitmap, u32 msr)
-{
-	int f = sizeof(unsigned long);
-
-	if (msr <= 0x1fff)
-		__set_bit(msr, msr_bitmap + 0x000 / f);
-	else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff))
-		__set_bit(msr & 0x1fff, msr_bitmap + 0x400 / f);
-}
-
-static void vmx_set_msr_bitmap_write(ulong *msr_bitmap, u32 msr)
-{
-	int f = sizeof(unsigned long);
-
-	if (msr <= 0x1fff)
-		__set_bit(msr, msr_bitmap + 0x800 / f);
-	else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff))
-		__set_bit(msr & 0x1fff, msr_bitmap + 0xc00 / f);
-}
-
 void vmx_disable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -4014,8 +3964,7 @@ static int vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector)
 	if (pi_test_and_set_on(&vmx->pi_desc))
 		return 0;
 
-	if (vcpu != kvm_get_running_vcpu() &&
-	    !kvm_vcpu_trigger_posted_interrupt(vcpu, false))
+	if (!kvm_vcpu_trigger_posted_interrupt(vcpu, false))
 		kvm_vcpu_kick(vcpu);
 
 	return 0;
@@ -5494,6 +5443,7 @@ static int handle_invpcid(struct kvm_vcpu *vcpu)
 		u64 pcid;
 		u64 gla;
 	} operand;
+	int gpr_index;
 
 	if (!guest_cpuid_has(vcpu, X86_FEATURE_INVPCID)) {
 		kvm_queue_exception(vcpu, UD_VECTOR);
@@ -5501,12 +5451,8 @@ static int handle_invpcid(struct kvm_vcpu *vcpu)
 	}
 
 	vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
-	type = kvm_register_read(vcpu, (vmx_instruction_info >> 28) & 0xf);
-
-	if (type > 3) {
-		kvm_inject_gp(vcpu, 0);
-		return 1;
-	}
+	gpr_index = vmx_get_instr_info_reg2(vmx_instruction_info);
+	type = kvm_register_read(vcpu, gpr_index);
 
 	/* According to the Intel instruction reference, the memory operand
 	 * is read even if it isn't needed (e.g., for type==all)
@@ -5935,18 +5881,14 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
 		vmx_flush_pml_buffer(vcpu);
 
 	/*
-	 * We should never reach this point with a pending nested VM-Enter, and
-	 * more specifically emulation of L2 due to invalid guest state (see
-	 * below) should never happen as that means we incorrectly allowed a
-	 * nested VM-Enter with an invalid vmcs12.
+	 * KVM should never reach this point with a pending nested VM-Enter.
+	 * More specifically, short-circuiting VM-Entry to emulate L2 due to
+	 * invalid guest state should never happen as that means KVM knowingly
+	 * allowed a nested VM-Enter with an invalid vmcs12.  More below.
 	 */
 	if (KVM_BUG_ON(vmx->nested.nested_run_pending, vcpu->kvm))
 		return -EIO;
 
-	/* If guest state is invalid, start emulating */
-	if (vmx->emulation_required)
-		return handle_invalid_guest_state(vcpu);
-
 	if (is_guest_mode(vcpu)) {
 		/*
 		 * PML is never enabled when running L2, bail immediately if a
@@ -5968,10 +5910,30 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
 		 */
 		nested_mark_vmcs12_pages_dirty(vcpu);
 
+		/*
+		 * Synthesize a triple fault if L2 state is invalid.  In normal
+		 * operation, nested VM-Enter rejects any attempt to enter L2
+		 * with invalid state.  However, those checks are skipped if
+		 * state is being stuffed via RSM or KVM_SET_NESTED_STATE.  If
+		 * L2 state is invalid, it means either L1 modified SMRAM state
+		 * or userspace provided bad state.  Synthesize TRIPLE_FAULT as
+		 * doing so is architecturally allowed in the RSM case, and is
+		 * the least awful solution for the userspace case without
+		 * risking false positives.
+		 */
+		if (vmx->emulation_required) {
+			nested_vmx_vmexit(vcpu, EXIT_REASON_TRIPLE_FAULT, 0, 0);
+			return 1;
+		}
+
 		if (nested_vmx_reflect_vmexit(vcpu))
 			return 1;
 	}
 
+	/* If guest state is invalid, start emulating.  L2 is handled above. */
+	if (vmx->emulation_required)
+		return handle_invalid_guest_state(vcpu);
+
 	if (exit_reason.failed_vmentry) {
 		dump_vmcs(vcpu);
 		vcpu->run->exit_reason = KVM_EXIT_FAIL_ENTRY;
@@ -6316,9 +6278,9 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	int max_irr;
-	bool max_irr_updated;
+	bool got_posted_interrupt;
 
-	if (KVM_BUG_ON(!vcpu->arch.apicv_active, vcpu->kvm))
+	if (KVM_BUG_ON(!enable_apicv, vcpu->kvm))
 		return -EIO;
 
 	if (pi_test_on(&vmx->pi_desc)) {
@@ -6328,22 +6290,33 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu)
 		 * But on x86 this is just a compiler barrier anyway.
 		 */
 		smp_mb__after_atomic();
-		max_irr_updated =
+		got_posted_interrupt =
 			kvm_apic_update_irr(vcpu, vmx->pi_desc.pir, &max_irr);
-
-		/*
-		 * If we are running L2 and L1 has a new pending interrupt
-		 * which can be injected, this may cause a vmexit or it may
-		 * be injected into L2.  Either way, this interrupt will be
-		 * processed via KVM_REQ_EVENT, not RVI, because we do not use
-		 * virtual interrupt delivery to inject L1 interrupts into L2.
-		 */
-		if (is_guest_mode(vcpu) && max_irr_updated)
-			kvm_make_request(KVM_REQ_EVENT, vcpu);
 	} else {
 		max_irr = kvm_lapic_find_highest_irr(vcpu);
+		got_posted_interrupt = false;
 	}
-	vmx_hwapic_irr_update(vcpu, max_irr);
+
+	/*
+	 * Newly recognized interrupts are injected via either virtual interrupt
+	 * delivery (RVI) or KVM_REQ_EVENT.  Virtual interrupt delivery is
+	 * disabled in two cases:
+	 *
+	 * 1) If L2 is running and the vCPU has a new pending interrupt.  If L1
+	 * wants to exit on interrupts, KVM_REQ_EVENT is needed to synthesize a
+	 * VM-Exit to L1.  If L1 doesn't want to exit, the interrupt is injected
+	 * into L2, but KVM doesn't use virtual interrupt delivery to inject
+	 * interrupts into L2, and so KVM_REQ_EVENT is again needed.
+	 *
+	 * 2) If APICv is disabled for this vCPU, assigned devices may still
+	 * attempt to post interrupts.  The posted interrupt vector will cause
+	 * a VM-Exit and the subsequent entry will call sync_pir_to_irr.
+	 */
+	if (!is_guest_mode(vcpu) && kvm_vcpu_apicv_active(vcpu))
+		vmx_set_rvi(max_irr);
+	else if (got_posted_interrupt)
+		kvm_make_request(KVM_REQ_EVENT, vcpu);
+
 	return max_irr;
 }
 
@@ -6655,9 +6628,7 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	 * consistency check VM-Exit due to invalid guest state and bail.
 	 */
 	if (unlikely(vmx->emulation_required)) {
-
-		/* We don't emulate invalid state of a nested guest */
-		vmx->fail = is_guest_mode(vcpu);
+		vmx->fail = 0;
 
 		vmx->exit_reason.full = EXIT_REASON_INVALID_STATE;
 		vmx->exit_reason.failed_vmentry = 1;
@@ -6749,7 +6720,7 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	 * If the L02 MSR bitmap does not intercept the MSR, then we need to
 	 * save it.
 	 */
-	if (unlikely(!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)))
+	if (unlikely(!msr_write_intercepted(vmx, MSR_IA32_SPEC_CTRL)))
 		vmx->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL);
 
 	x86_spec_ctrl_restore_host(vmx->spec_ctrl, 0);
@@ -6880,6 +6851,19 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu)
 	if (err < 0)
 		goto free_pml;
 
+	/*
+	 * Use Hyper-V 'Enlightened MSR Bitmap' feature when KVM runs as a
+	 * nested (L1) hypervisor and Hyper-V in L0 supports it. Enable the
+	 * feature only for vmcs01, KVM currently isn't equipped to realize any
+	 * performance benefits from enabling it for vmcs02.
+	 */
+	if (IS_ENABLED(CONFIG_HYPERV) && static_branch_unlikely(&enable_evmcs) &&
+	    (ms_hyperv.nested_features & HV_X64_NESTED_MSR_BITMAP)) {
+		struct hv_enlightened_vmcs *evmcs = (void *)vmx->vmcs01.vmcs;
+
+		evmcs->hv_enlightenments_control.msr_bitmap = 1;
+	}
+
 	/* The MSR bitmap starts with all ones */
 	bitmap_fill(vmx->shadow_msr_intercept.read, MAX_POSSIBLE_PASSTHROUGH_MSRS);
 	bitmap_fill(vmx->shadow_msr_intercept.write, MAX_POSSIBLE_PASSTHROUGH_MSRS);
@@ -7563,7 +7547,9 @@ static void hardware_unsetup(void)
 static bool vmx_check_apicv_inhibit_reasons(ulong bit)
 {
 	ulong supported = BIT(APICV_INHIBIT_REASON_DISABLE) |
-			  BIT(APICV_INHIBIT_REASON_HYPERV);
+			  BIT(APICV_INHIBIT_REASON_ABSENT) |
+			  BIT(APICV_INHIBIT_REASON_HYPERV) |
+			  BIT(APICV_INHIBIT_REASON_BLOCKIRQ);
 
 	return supported & BIT(bit);
 }
@@ -7611,6 +7597,7 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = {
 	.cache_reg = vmx_cache_reg,
 	.get_rflags = vmx_get_rflags,
 	.set_rflags = vmx_set_rflags,
+	.get_if_flag = vmx_get_if_flag,
 
 	.tlb_flush_all = vmx_flush_tlb_all,
 	.tlb_flush_current = vmx_flush_tlb_current,
@@ -7814,10 +7801,10 @@ static __init int hardware_setup(void)
 		ple_window_shrink = 0;
 	}
 
-	if (!cpu_has_vmx_apicv()) {
+	if (!cpu_has_vmx_apicv())
 		enable_apicv = 0;
+	if (!enable_apicv)
 		vmx_x86_ops.sync_pir_to_irr = NULL;
-	}
 
 	if (cpu_has_vmx_tsc_scaling()) {
 		kvm_has_tsc_control = true;
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index e7db42e3b0ce..4df2ac24ffc1 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -142,6 +142,16 @@ struct nested_vmx {
 	struct vmcs12 *cached_shadow_vmcs12;
 
 	/*
+	 * GPA to HVA cache for accessing vmcs12->vmcs_link_pointer
+	 */
+	struct gfn_to_hva_cache shadow_vmcs12_cache;
+
+	/*
+	 * GPA to HVA cache for VMCS12
+	 */
+	struct gfn_to_hva_cache vmcs12_cache;
+
+	/*
 	 * Indicates if the shadow vmcs or enlightened vmcs must be updated
 	 * with the data held by struct vmcs12.
 	 */
@@ -400,6 +410,34 @@ static inline void vmx_set_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr,
 
 void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu);
 
+/*
+ * Note, early Intel manuals have the write-low and read-high bitmap offsets
+ * the wrong way round.  The bitmaps control MSRs 0x00000000-0x00001fff and
+ * 0xc0000000-0xc0001fff.  The former (low) uses bytes 0-0x3ff for reads and
+ * 0x800-0xbff for writes.  The latter (high) uses 0x400-0x7ff for reads and
+ * 0xc00-0xfff for writes.  MSRs not covered by either of the ranges always
+ * VM-Exit.
+ */
+#define __BUILD_VMX_MSR_BITMAP_HELPER(rtype, action, bitop, access, base)      \
+static inline rtype vmx_##action##_msr_bitmap_##access(unsigned long *bitmap,  \
+						       u32 msr)		       \
+{									       \
+	int f = sizeof(unsigned long);					       \
+									       \
+	if (msr <= 0x1fff)						       \
+		return bitop##_bit(msr, bitmap + base / f);		       \
+	else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff))		       \
+		return bitop##_bit(msr & 0x1fff, bitmap + (base + 0x400) / f); \
+	return (rtype)true;						       \
+}
+#define BUILD_VMX_MSR_BITMAP_HELPERS(ret_type, action, bitop)		       \
+	__BUILD_VMX_MSR_BITMAP_HELPER(ret_type, action, bitop, read,  0x0)     \
+	__BUILD_VMX_MSR_BITMAP_HELPER(ret_type, action, bitop, write, 0x800)
+
+BUILD_VMX_MSR_BITMAP_HELPERS(bool, test, test)
+BUILD_VMX_MSR_BITMAP_HELPERS(void, clear, __clear)
+BUILD_VMX_MSR_BITMAP_HELPERS(void, set, __set)
+
 static inline u8 vmx_get_rvi(void)
 {
 	return vmcs_read16(GUEST_INTR_STATUS) & 0xff;
@@ -522,4 +560,9 @@ static inline bool vmx_guest_state_valid(struct kvm_vcpu *vcpu)
 
 void dump_vmcs(struct kvm_vcpu *vcpu);
 
+static inline int vmx_get_instr_info_reg2(u32 vmx_instr_info)
+{
+	return (vmx_instr_info >> 28) & 0xf;
+}
+
 #endif /* __KVM_X86_VMX_H */
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index c1c4e2b05a63..e50e97ac4408 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -890,7 +890,8 @@ int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 	    !load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu)))
 		return 1;
 
-	if (!(cr0 & X86_CR0_PG) && kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE))
+	if (!(cr0 & X86_CR0_PG) &&
+	    (is_64_bit_mode(vcpu) || kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE)))
 		return 1;
 
 	static_call(kvm_x86_set_cr0)(vcpu, cr0);
@@ -1330,7 +1331,7 @@ static const u32 msrs_to_save_all[] = {
 	MSR_IA32_UMWAIT_CONTROL,
 
 	MSR_ARCH_PERFMON_FIXED_CTR0, MSR_ARCH_PERFMON_FIXED_CTR1,
-	MSR_ARCH_PERFMON_FIXED_CTR0 + 2, MSR_ARCH_PERFMON_FIXED_CTR0 + 3,
+	MSR_ARCH_PERFMON_FIXED_CTR0 + 2,
 	MSR_CORE_PERF_FIXED_CTR_CTRL, MSR_CORE_PERF_GLOBAL_STATUS,
 	MSR_CORE_PERF_GLOBAL_CTRL, MSR_CORE_PERF_GLOBAL_OVF_CTRL,
 	MSR_ARCH_PERFMON_PERFCTR0, MSR_ARCH_PERFMON_PERFCTR1,
@@ -3258,10 +3259,36 @@ static void kvm_vcpu_flush_tlb_guest(struct kvm_vcpu *vcpu)
 	static_call(kvm_x86_tlb_flush_guest)(vcpu);
 }
 
+
+static inline void kvm_vcpu_flush_tlb_current(struct kvm_vcpu *vcpu)
+{
+	++vcpu->stat.tlb_flush;
+	static_call(kvm_x86_tlb_flush_current)(vcpu);
+}
+
+/*
+ * Service "local" TLB flush requests, which are specific to the current MMU
+ * context.  In addition to the generic event handling in vcpu_enter_guest(),
+ * TLB flushes that are targeted at an MMU context also need to be serviced
+ * prior before nested VM-Enter/VM-Exit.
+ */
+void kvm_service_local_tlb_flush_requests(struct kvm_vcpu *vcpu)
+{
+	if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu))
+		kvm_vcpu_flush_tlb_current(vcpu);
+
+	if (kvm_check_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu))
+		kvm_vcpu_flush_tlb_guest(vcpu);
+}
+EXPORT_SYMBOL_GPL(kvm_service_local_tlb_flush_requests);
+
 static void record_steal_time(struct kvm_vcpu *vcpu)
 {
-	struct kvm_host_map map;
-	struct kvm_steal_time *st;
+	struct gfn_to_hva_cache *ghc = &vcpu->arch.st.cache;
+	struct kvm_steal_time __user *st;
+	struct kvm_memslots *slots;
+	u64 steal;
+	u32 version;
 
 	if (kvm_xen_msr_enabled(vcpu->kvm)) {
 		kvm_xen_runstate_set_running(vcpu);
@@ -3271,47 +3298,86 @@ static void record_steal_time(struct kvm_vcpu *vcpu)
 	if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED))
 		return;
 
-	/* -EAGAIN is returned in atomic context so we can just return. */
-	if (kvm_map_gfn(vcpu, vcpu->arch.st.msr_val >> PAGE_SHIFT,
-			&map, &vcpu->arch.st.cache, false))
+	if (WARN_ON_ONCE(current->mm != vcpu->kvm->mm))
 		return;
 
-	st = map.hva +
-		offset_in_page(vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS);
+	slots = kvm_memslots(vcpu->kvm);
+
+	if (unlikely(slots->generation != ghc->generation ||
+		     kvm_is_error_hva(ghc->hva) || !ghc->memslot)) {
+		gfn_t gfn = vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS;
 
+		/* We rely on the fact that it fits in a single page. */
+		BUILD_BUG_ON((sizeof(*st) - 1) & KVM_STEAL_VALID_BITS);
+
+		if (kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, gfn, sizeof(*st)) ||
+		    kvm_is_error_hva(ghc->hva) || !ghc->memslot)
+			return;
+	}
+
+	st = (struct kvm_steal_time __user *)ghc->hva;
 	/*
 	 * Doing a TLB flush here, on the guest's behalf, can avoid
 	 * expensive IPIs.
 	 */
 	if (guest_pv_has(vcpu, KVM_FEATURE_PV_TLB_FLUSH)) {
-		u8 st_preempted = xchg(&st->preempted, 0);
+		u8 st_preempted = 0;
+		int err = -EFAULT;
+
+		if (!user_access_begin(st, sizeof(*st)))
+			return;
+
+		asm volatile("1: xchgb %0, %2\n"
+			     "xor %1, %1\n"
+			     "2:\n"
+			     _ASM_EXTABLE_UA(1b, 2b)
+			     : "+q" (st_preempted),
+			       "+&r" (err),
+			       "+m" (st->preempted));
+		if (err)
+			goto out;
+
+		user_access_end();
+
+		vcpu->arch.st.preempted = 0;
 
 		trace_kvm_pv_tlb_flush(vcpu->vcpu_id,
 				       st_preempted & KVM_VCPU_FLUSH_TLB);
 		if (st_preempted & KVM_VCPU_FLUSH_TLB)
 			kvm_vcpu_flush_tlb_guest(vcpu);
+
+		if (!user_access_begin(st, sizeof(*st)))
+			goto dirty;
 	} else {
-		st->preempted = 0;
-	}
+		if (!user_access_begin(st, sizeof(*st)))
+			return;
 
-	vcpu->arch.st.preempted = 0;
+		unsafe_put_user(0, &st->preempted, out);
+		vcpu->arch.st.preempted = 0;
+	}
 
-	if (st->version & 1)
-		st->version += 1;  /* first time write, random junk */
+	unsafe_get_user(version, &st->version, out);
+	if (version & 1)
+		version += 1;  /* first time write, random junk */
 
-	st->version += 1;
+	version += 1;
+	unsafe_put_user(version, &st->version, out);
 
 	smp_wmb();
 
-	st->steal += current->sched_info.run_delay -
+	unsafe_get_user(steal, &st->steal, out);
+	steal += current->sched_info.run_delay -
 		vcpu->arch.st.last_steal;
 	vcpu->arch.st.last_steal = current->sched_info.run_delay;
+	unsafe_put_user(steal, &st->steal, out);
 
-	smp_wmb();
-
-	st->version += 1;
+	version += 1;
+	unsafe_put_user(version, &st->version, out);
 
-	kvm_unmap_gfn(vcpu, &map, &vcpu->arch.st.cache, true, false);
+ out:
+	user_access_end();
+ dirty:
+	mark_page_dirty_in_slot(vcpu->kvm, ghc->memslot, gpa_to_gfn(ghc->gpa));
 }
 
 int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
@@ -3347,7 +3413,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 
 		if (!msr_info->host_initiated)
 			return 1;
-		if (guest_cpuid_has(vcpu, X86_FEATURE_PDCM) && kvm_get_msr_feature(&msr_ent))
+		if (kvm_get_msr_feature(&msr_ent))
 			return 1;
 		if (data & ~msr_ent.data)
 			return 1;
@@ -3517,7 +3583,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (!guest_pv_has(vcpu, KVM_FEATURE_PV_EOI))
 			return 1;
 
-		if (kvm_lapic_enable_pv_eoi(vcpu, data, sizeof(u8)))
+		if (kvm_lapic_set_pv_eoi(vcpu, data, sizeof(u8)))
 			return 1;
 		break;
 
@@ -4091,6 +4157,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_SGX_ATTRIBUTE:
 #endif
 	case KVM_CAP_VM_COPY_ENC_CONTEXT_FROM:
+	case KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM:
 	case KVM_CAP_SREGS2:
 	case KVM_CAP_EXIT_ON_EMULATION_FAILURE:
 	case KVM_CAP_VCPU_ATTRIBUTES:
@@ -4137,7 +4204,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		r = !static_call(kvm_x86_cpu_has_accelerated_tpr)();
 		break;
 	case KVM_CAP_NR_VCPUS:
-		r = KVM_SOFT_MAX_VCPUS;
+		r = min_t(unsigned int, num_online_cpus(), KVM_MAX_VCPUS);
 		break;
 	case KVM_CAP_MAX_VCPUS:
 		r = KVM_MAX_VCPUS;
@@ -4351,8 +4418,10 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu)
 {
-	struct kvm_host_map map;
-	struct kvm_steal_time *st;
+	struct gfn_to_hva_cache *ghc = &vcpu->arch.st.cache;
+	struct kvm_steal_time __user *st;
+	struct kvm_memslots *slots;
+	static const u8 preempted = KVM_VCPU_PREEMPTED;
 
 	if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED))
 		return;
@@ -4360,16 +4429,23 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu)
 	if (vcpu->arch.st.preempted)
 		return;
 
-	if (kvm_map_gfn(vcpu, vcpu->arch.st.msr_val >> PAGE_SHIFT, &map,
-			&vcpu->arch.st.cache, true))
+	/* This happens on process exit */
+	if (unlikely(current->mm != vcpu->kvm->mm))
 		return;
 
-	st = map.hva +
-		offset_in_page(vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS);
+	slots = kvm_memslots(vcpu->kvm);
+
+	if (unlikely(slots->generation != ghc->generation ||
+		     kvm_is_error_hva(ghc->hva) || !ghc->memslot))
+		return;
 
-	st->preempted = vcpu->arch.st.preempted = KVM_VCPU_PREEMPTED;
+	st = (struct kvm_steal_time __user *)ghc->hva;
+	BUILD_BUG_ON(sizeof(st->preempted) != sizeof(preempted));
 
-	kvm_unmap_gfn(vcpu, &map, &vcpu->arch.st.cache, true, true);
+	if (!copy_to_user_nofault(&st->preempted, &preempted, sizeof(preempted)))
+		vcpu->arch.st.preempted = KVM_VCPU_PREEMPTED;
+
+	mark_page_dirty_in_slot(vcpu->kvm, ghc->memslot, gpa_to_gfn(ghc->gpa));
 }
 
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
@@ -4397,8 +4473,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu,
 				    struct kvm_lapic_state *s)
 {
-	if (vcpu->arch.apicv_active)
-		static_call(kvm_x86_sync_pir_to_irr)(vcpu);
+	static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu);
 
 	return kvm_apic_get_state(vcpu, s);
 }
@@ -5073,6 +5148,17 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		struct kvm_cpuid __user *cpuid_arg = argp;
 		struct kvm_cpuid cpuid;
 
+		/*
+		 * KVM does not correctly handle changing guest CPUID after KVM_RUN, as
+		 * MAXPHYADDR, GBPAGES support, AMD reserved bit behavior, etc.. aren't
+		 * tracked in kvm_mmu_page_role.  As a result, KVM may miss guest page
+		 * faults due to reusing SPs/SPTEs.  In practice no sane VMM mucks with
+		 * the core vCPU model on the fly, so fail.
+		 */
+		r = -EINVAL;
+		if (vcpu->arch.last_vmentry_cpu != -1)
+			goto out;
+
 		r = -EFAULT;
 		if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid)))
 			goto out;
@@ -5083,6 +5169,14 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		struct kvm_cpuid2 __user *cpuid_arg = argp;
 		struct kvm_cpuid2 cpuid;
 
+		/*
+		 * KVM_SET_CPUID{,2} after KVM_RUN is forbidded, see the comment in
+		 * KVM_SET_CPUID case above.
+		 */
+		r = -EINVAL;
+		if (vcpu->arch.last_vmentry_cpu != -1)
+			goto out;
+
 		r = -EFAULT;
 		if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid)))
 			goto out;
@@ -5647,6 +5741,7 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
 		smp_wmb();
 		kvm->arch.irqchip_mode = KVM_IRQCHIP_SPLIT;
 		kvm->arch.nr_reserved_ioapic_pins = cap->args[0];
+		kvm_request_apicv_update(kvm, true, APICV_INHIBIT_REASON_ABSENT);
 		r = 0;
 split_irqchip_unlock:
 		mutex_unlock(&kvm->lock);
@@ -5728,6 +5823,12 @@ split_irqchip_unlock:
 		if (kvm_x86_ops.vm_copy_enc_context_from)
 			r = kvm_x86_ops.vm_copy_enc_context_from(kvm, cap->args[0]);
 		return r;
+	case KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM:
+		r = -EINVAL;
+		if (kvm_x86_ops.vm_move_enc_context_from)
+			r = kvm_x86_ops.vm_move_enc_context_from(
+				kvm, cap->args[0]);
+		return r;
 	case KVM_CAP_EXIT_HYPERCALL:
 		if (cap->args[0] & ~KVM_EXIT_HYPERCALL_VALID_MASK) {
 			r = -EINVAL;
@@ -6021,6 +6122,7 @@ set_identity_unlock:
 		/* Write kvm->irq_routing before enabling irqchip_in_kernel. */
 		smp_wmb();
 		kvm->arch.irqchip_mode = KVM_IRQCHIP_KERNEL;
+		kvm_request_apicv_update(kvm, true, APICV_INHIBIT_REASON_ABSENT);
 	create_irqchip_unlock:
 		mutex_unlock(&kvm->lock);
 		break;
@@ -7020,7 +7122,13 @@ static int emulator_pio_in(struct kvm_vcpu *vcpu, int size,
 			   unsigned short port, void *val, unsigned int count)
 {
 	if (vcpu->arch.pio.count) {
-		/* Complete previous iteration.  */
+		/*
+		 * Complete a previous iteration that required userspace I/O.
+		 * Note, @count isn't guaranteed to match pio.count as userspace
+		 * can modify ECX before rerunning the vCPU.  Ignore any such
+		 * shenanigans as KVM doesn't support modifying the rep count,
+		 * and the emulator ensures @count doesn't overflow the buffer.
+		 */
 	} else {
 		int r = __emulator_pio_in(vcpu, size, port, count);
 		if (!r)
@@ -7029,7 +7137,6 @@ static int emulator_pio_in(struct kvm_vcpu *vcpu, int size,
 		/* Results already available, fall through.  */
 	}
 
-	WARN_ON(count != vcpu->arch.pio.count);
 	complete_emulator_pio_in(vcpu, val);
 	return 1;
 }
@@ -7328,7 +7435,9 @@ 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_rdpmc_ecx(emul_to_vcpu(ctxt), pmc);
+	if (kvm_pmu_is_valid_rdpmc_ecx(emul_to_vcpu(ctxt), pmc))
+		return 0;
+	return -EINVAL;
 }
 
 static int emulator_read_pmc(struct x86_emulate_ctxt *ctxt,
@@ -8717,10 +8826,9 @@ static void kvm_apicv_init(struct kvm *kvm)
 {
 	init_rwsem(&kvm->arch.apicv_update_lock);
 
-	if (enable_apicv)
-		clear_bit(APICV_INHIBIT_REASON_DISABLE,
-			  &kvm->arch.apicv_inhibit_reasons);
-	else
+	set_bit(APICV_INHIBIT_REASON_ABSENT,
+		&kvm->arch.apicv_inhibit_reasons);
+	if (!enable_apicv)
 		set_bit(APICV_INHIBIT_REASON_DISABLE,
 			&kvm->arch.apicv_inhibit_reasons);
 }
@@ -8789,7 +8897,7 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 
 	trace_kvm_hypercall(nr, a0, a1, a2, a3);
 
-	op_64_bit = is_64_bit_mode(vcpu);
+	op_64_bit = is_64_bit_hypercall(vcpu);
 	if (!op_64_bit) {
 		nr &= 0xFFFFFFFF;
 		a0 &= 0xFFFFFFFF;
@@ -8893,14 +9001,7 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu)
 {
 	struct kvm_run *kvm_run = vcpu->run;
 
-	/*
-	 * if_flag is obsolete and useless, so do not bother
-	 * setting it for SEV-ES guests.  Userspace can just
-	 * use kvm_run->ready_for_interrupt_injection.
-	 */
-	kvm_run->if_flag = !vcpu->arch.guest_state_protected
-		&& (kvm_get_rflags(vcpu) & X86_EFLAGS_IF) != 0;
-
+	kvm_run->if_flag = static_call(kvm_x86_get_if_flag)(vcpu);
 	kvm_run->cr8 = kvm_get_cr8(vcpu);
 	kvm_run->apic_base = kvm_get_apic_base(vcpu);
 
@@ -9469,8 +9570,7 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu)
 	if (irqchip_split(vcpu->kvm))
 		kvm_scan_ioapic_routes(vcpu, vcpu->arch.ioapic_handled_vectors);
 	else {
-		if (vcpu->arch.apicv_active)
-			static_call(kvm_x86_sync_pir_to_irr)(vcpu);
+		static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu);
 		if (ioapic_in_kernel(vcpu->kvm))
 			kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors);
 	}
@@ -9488,12 +9588,16 @@ static void vcpu_load_eoi_exitmap(struct kvm_vcpu *vcpu)
 	if (!kvm_apic_hw_enabled(vcpu->arch.apic))
 		return;
 
-	if (to_hv_vcpu(vcpu))
+	if (to_hv_vcpu(vcpu)) {
 		bitmap_or((ulong *)eoi_exit_bitmap,
 			  vcpu->arch.ioapic_handled_vectors,
 			  to_hv_synic(vcpu)->vec_bitmap, 256);
+		static_call(kvm_x86_load_eoi_exitmap)(vcpu, eoi_exit_bitmap);
+		return;
+	}
 
-	static_call(kvm_x86_load_eoi_exitmap)(vcpu, eoi_exit_bitmap);
+	static_call(kvm_x86_load_eoi_exitmap)(
+		vcpu, (u64 *)vcpu->arch.ioapic_handled_vectors);
 }
 
 void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
@@ -9552,7 +9656,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	}
 
 	if (kvm_request_pending(vcpu)) {
-		if (kvm_check_request(KVM_REQ_VM_BUGGED, vcpu)) {
+		if (kvm_check_request(KVM_REQ_VM_DEAD, vcpu)) {
 			r = -EIO;
 			goto out;
 		}
@@ -9585,10 +9689,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 			/* Flushing all ASIDs flushes the current ASID... */
 			kvm_clear_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu);
 		}
-		if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu))
-			kvm_vcpu_flush_tlb_current(vcpu);
-		if (kvm_check_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu))
-			kvm_vcpu_flush_tlb_guest(vcpu);
+		kvm_service_local_tlb_flush_requests(vcpu);
 
 		if (kvm_check_request(KVM_REQ_REPORT_TPR_ACCESS, vcpu)) {
 			vcpu->run->exit_reason = KVM_EXIT_TPR_ACCESS;
@@ -9739,10 +9840,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 
 	/*
 	 * This handles the case where a posted interrupt was
-	 * notified with kvm_vcpu_kick.
+	 * notified with kvm_vcpu_kick.  Assigned devices can
+	 * use the POSTED_INTR_VECTOR even if APICv is disabled,
+	 * so do it even if APICv is disabled on this vCPU.
 	 */
-	if (kvm_lapic_enabled(vcpu) && vcpu->arch.apicv_active)
-		static_call(kvm_x86_sync_pir_to_irr)(vcpu);
+	if (kvm_lapic_enabled(vcpu))
+		static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu);
 
 	if (kvm_vcpu_exit_request(vcpu)) {
 		vcpu->mode = OUTSIDE_GUEST_MODE;
@@ -9786,8 +9889,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		if (likely(exit_fastpath != EXIT_FASTPATH_REENTER_GUEST))
 			break;
 
-		if (vcpu->arch.apicv_active)
-			static_call(kvm_x86_sync_pir_to_irr)(vcpu);
+		if (kvm_lapic_enabled(vcpu))
+			static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu);
 
 		if (unlikely(kvm_vcpu_exit_request(vcpu))) {
 			exit_fastpath = EXIT_FASTPATH_EXIT_HANDLED;
@@ -10564,6 +10667,24 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 	return ret;
 }
 
+static void kvm_arch_vcpu_guestdbg_update_apicv_inhibit(struct kvm *kvm)
+{
+	bool inhibit = false;
+	struct kvm_vcpu *vcpu;
+	int i;
+
+	down_write(&kvm->arch.apicv_update_lock);
+
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		if (vcpu->guest_debug & KVM_GUESTDBG_BLOCKIRQ) {
+			inhibit = true;
+			break;
+		}
+	}
+	__kvm_request_apicv_update(kvm, !inhibit, APICV_INHIBIT_REASON_BLOCKIRQ);
+	up_write(&kvm->arch.apicv_update_lock);
+}
+
 int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 					struct kvm_guest_debug *dbg)
 {
@@ -10616,6 +10737,8 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 
 	static_call(kvm_x86_update_exception_bitmap)(vcpu);
 
+	kvm_arch_vcpu_guestdbg_update_apicv_inhibit(vcpu->kvm);
+
 	r = 0;
 
 out:
@@ -10859,11 +10982,8 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
 
 void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 {
-	struct gfn_to_pfn_cache *cache = &vcpu->arch.st.cache;
 	int idx;
 
-	kvm_release_pfn(cache->pfn, cache->dirty, cache);
-
 	kvmclock_reset(vcpu);
 
 	static_call(kvm_x86_vcpu_free)(vcpu);
@@ -12275,7 +12395,8 @@ int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva)
 		return kvm_skip_emulated_instruction(vcpu);
 
 	default:
-		BUG(); /* We have already checked above that type <= 3 */
+		kvm_inject_gp(vcpu, 0);
+		return 1;
 	}
 }
 EXPORT_SYMBOL_GPL(kvm_handle_invpcid);
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index ea264c4502e4..4abcd8d9836d 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -103,6 +103,7 @@ static inline unsigned int __shrink_ple_window(unsigned int val,
 
 #define MSR_IA32_CR_PAT_DEFAULT  0x0007040600070406ULL
 
+void kvm_service_local_tlb_flush_requests(struct kvm_vcpu *vcpu);
 int kvm_check_nested_events(struct kvm_vcpu *vcpu);
 
 static inline void kvm_clear_exception_queue(struct kvm_vcpu *vcpu)
@@ -153,12 +154,24 @@ static inline bool is_64_bit_mode(struct kvm_vcpu *vcpu)
 {
 	int cs_db, cs_l;
 
+	WARN_ON_ONCE(vcpu->arch.guest_state_protected);
+
 	if (!is_long_mode(vcpu))
 		return false;
 	static_call(kvm_x86_get_cs_db_l_bits)(vcpu, &cs_db, &cs_l);
 	return cs_l;
 }
 
+static inline bool is_64_bit_hypercall(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * If running with protected guest state, the CS register is not
+	 * accessible. The hypercall register values will have had to been
+	 * provided in 64-bit mode, so assume the guest is in 64-bit.
+	 */
+	return vcpu->arch.guest_state_protected || is_64_bit_mode(vcpu);
+}
+
 static inline bool x86_exception_has_error_code(unsigned int vector)
 {
 	static u32 exception_has_error_code = BIT(DF_VECTOR) | BIT(TS_VECTOR) |
@@ -173,12 +186,6 @@ static inline bool mmu_is_nested(struct kvm_vcpu *vcpu)
 	return vcpu->arch.walk_mmu == &vcpu->arch.nested_mmu;
 }
 
-static inline void kvm_vcpu_flush_tlb_current(struct kvm_vcpu *vcpu)
-{
-	++vcpu->stat.tlb_flush;
-	static_call(kvm_x86_tlb_flush_current)(vcpu);
-}
-
 static inline int is_pae(struct kvm_vcpu *vcpu)
 {
 	return kvm_read_cr4_bits(vcpu, X86_CR4_PAE);
diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c
index 8f62baebd028..dff2bdf9507a 100644
--- a/arch/x86/kvm/xen.c
+++ b/arch/x86/kvm/xen.c
@@ -127,9 +127,9 @@ void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, int state)
 	state_entry_time = vx->runstate_entry_time;
 	state_entry_time |= XEN_RUNSTATE_UPDATE;
 
-	BUILD_BUG_ON(sizeof(((struct vcpu_runstate_info *)0)->state_entry_time) !=
+	BUILD_BUG_ON(sizeof_field(struct vcpu_runstate_info, state_entry_time) !=
 		     sizeof(state_entry_time));
-	BUILD_BUG_ON(sizeof(((struct compat_vcpu_runstate_info *)0)->state_entry_time) !=
+	BUILD_BUG_ON(sizeof_field(struct compat_vcpu_runstate_info, state_entry_time) !=
 		     sizeof(state_entry_time));
 
 	if (kvm_write_guest_offset_cached(v->kvm, &v->arch.xen.runstate_cache,
@@ -144,9 +144,9 @@ void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, int state)
 	 */
 	BUILD_BUG_ON(offsetof(struct vcpu_runstate_info, state) !=
 		     offsetof(struct compat_vcpu_runstate_info, state));
-	BUILD_BUG_ON(sizeof(((struct vcpu_runstate_info *)0)->state) !=
+	BUILD_BUG_ON(sizeof_field(struct vcpu_runstate_info, state) !=
 		     sizeof(vx->current_runstate));
-	BUILD_BUG_ON(sizeof(((struct compat_vcpu_runstate_info *)0)->state) !=
+	BUILD_BUG_ON(sizeof_field(struct compat_vcpu_runstate_info, state) !=
 		     sizeof(vx->current_runstate));
 
 	if (kvm_write_guest_offset_cached(v->kvm, &v->arch.xen.runstate_cache,
@@ -163,9 +163,9 @@ void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, int state)
 		     offsetof(struct vcpu_runstate_info, time) - sizeof(u64));
 	BUILD_BUG_ON(offsetof(struct compat_vcpu_runstate_info, state_entry_time) !=
 		     offsetof(struct compat_vcpu_runstate_info, time) - sizeof(u64));
-	BUILD_BUG_ON(sizeof(((struct vcpu_runstate_info *)0)->time) !=
-		     sizeof(((struct compat_vcpu_runstate_info *)0)->time));
-	BUILD_BUG_ON(sizeof(((struct vcpu_runstate_info *)0)->time) !=
+	BUILD_BUG_ON(sizeof_field(struct vcpu_runstate_info, time) !=
+		     sizeof_field(struct compat_vcpu_runstate_info, time));
+	BUILD_BUG_ON(sizeof_field(struct vcpu_runstate_info, time) !=
 		     sizeof(vx->runstate_times));
 
 	if (kvm_write_guest_offset_cached(v->kvm, &v->arch.xen.runstate_cache,
@@ -205,9 +205,9 @@ int __kvm_xen_has_interrupt(struct kvm_vcpu *v)
 	BUILD_BUG_ON(offsetof(struct vcpu_info, evtchn_upcall_pending) !=
 		     offsetof(struct compat_vcpu_info, evtchn_upcall_pending));
 	BUILD_BUG_ON(sizeof(rc) !=
-		     sizeof(((struct vcpu_info *)0)->evtchn_upcall_pending));
+		     sizeof_field(struct vcpu_info, evtchn_upcall_pending));
 	BUILD_BUG_ON(sizeof(rc) !=
-		     sizeof(((struct compat_vcpu_info *)0)->evtchn_upcall_pending));
+		     sizeof_field(struct compat_vcpu_info, evtchn_upcall_pending));
 
 	/*
 	 * For efficiency, this mirrors the checks for using the valid
@@ -299,7 +299,7 @@ int kvm_xen_hvm_get_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data)
 		break;
 
 	case KVM_XEN_ATTR_TYPE_SHARED_INFO:
-		data->u.shared_info.gfn = gpa_to_gfn(kvm->arch.xen.shinfo_gfn);
+		data->u.shared_info.gfn = kvm->arch.xen.shinfo_gfn;
 		r = 0;
 		break;
 
@@ -698,7 +698,7 @@ int kvm_xen_hypercall(struct kvm_vcpu *vcpu)
 	    kvm_hv_hypercall_enabled(vcpu))
 		return kvm_hv_hypercall(vcpu);
 
-	longmode = is_64_bit_mode(vcpu);
+	longmode = is_64_bit_hypercall(vcpu);
 	if (!longmode) {
 		params[0] = (u32)kvm_rbx_read(vcpu);
 		params[1] = (u32)kvm_rcx_read(vcpu);
diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c
index 23d54b810f08..35487305d8af 100644
--- a/arch/x86/mm/mem_encrypt.c
+++ b/arch/x86/mm/mem_encrypt.c
@@ -229,28 +229,75 @@ void __init sev_setup_arch(void)
 	swiotlb_adjust_size(size);
 }
 
-static void __init __set_clr_pte_enc(pte_t *kpte, int level, bool enc)
+static unsigned long pg_level_to_pfn(int level, pte_t *kpte, pgprot_t *ret_prot)
 {
-	pgprot_t old_prot, new_prot;
-	unsigned long pfn, pa, size;
-	pte_t new_pte;
+	unsigned long pfn = 0;
+	pgprot_t prot;
 
 	switch (level) {
 	case PG_LEVEL_4K:
 		pfn = pte_pfn(*kpte);
-		old_prot = pte_pgprot(*kpte);
+		prot = pte_pgprot(*kpte);
 		break;
 	case PG_LEVEL_2M:
 		pfn = pmd_pfn(*(pmd_t *)kpte);
-		old_prot = pmd_pgprot(*(pmd_t *)kpte);
+		prot = pmd_pgprot(*(pmd_t *)kpte);
 		break;
 	case PG_LEVEL_1G:
 		pfn = pud_pfn(*(pud_t *)kpte);
-		old_prot = pud_pgprot(*(pud_t *)kpte);
+		prot = pud_pgprot(*(pud_t *)kpte);
 		break;
 	default:
-		return;
+		WARN_ONCE(1, "Invalid level for kpte\n");
+		return 0;
+	}
+
+	if (ret_prot)
+		*ret_prot = prot;
+
+	return pfn;
+}
+
+void notify_range_enc_status_changed(unsigned long vaddr, int npages, bool enc)
+{
+#ifdef CONFIG_PARAVIRT
+	unsigned long sz = npages << PAGE_SHIFT;
+	unsigned long vaddr_end = vaddr + sz;
+
+	while (vaddr < vaddr_end) {
+		int psize, pmask, level;
+		unsigned long pfn;
+		pte_t *kpte;
+
+		kpte = lookup_address(vaddr, &level);
+		if (!kpte || pte_none(*kpte)) {
+			WARN_ONCE(1, "kpte lookup for vaddr\n");
+			return;
+		}
+
+		pfn = pg_level_to_pfn(level, kpte, NULL);
+		if (!pfn)
+			continue;
+
+		psize = page_level_size(level);
+		pmask = page_level_mask(level);
+
+		notify_page_enc_status_changed(pfn, psize >> PAGE_SHIFT, enc);
+
+		vaddr = (vaddr & pmask) + psize;
 	}
+#endif
+}
+
+static void __init __set_clr_pte_enc(pte_t *kpte, int level, bool enc)
+{
+	pgprot_t old_prot, new_prot;
+	unsigned long pfn, pa, size;
+	pte_t new_pte;
+
+	pfn = pg_level_to_pfn(level, kpte, &old_prot);
+	if (!pfn)
+		return;
 
 	new_prot = old_prot;
 	if (enc)
@@ -286,12 +333,13 @@ static void __init __set_clr_pte_enc(pte_t *kpte, int level, bool enc)
 static int __init early_set_memory_enc_dec(unsigned long vaddr,
 					   unsigned long size, bool enc)
 {
-	unsigned long vaddr_end, vaddr_next;
+	unsigned long vaddr_end, vaddr_next, start;
 	unsigned long psize, pmask;
 	int split_page_size_mask;
 	int level, ret;
 	pte_t *kpte;
 
+	start = vaddr;
 	vaddr_next = vaddr;
 	vaddr_end = vaddr + size;
 
@@ -346,6 +394,7 @@ static int __init early_set_memory_enc_dec(unsigned long vaddr,
 
 	ret = 0;
 
+	notify_range_enc_status_changed(start, PAGE_ALIGN(size) >> PAGE_SHIFT, enc);
 out:
 	__flush_tlb_all();
 	return ret;
@@ -361,6 +410,11 @@ int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size)
 	return early_set_memory_enc_dec(vaddr, size, true);
 }
 
+void __init early_set_mem_enc_dec_hypercall(unsigned long vaddr, int npages, bool enc)
+{
+	notify_range_enc_status_changed(vaddr, npages, enc);
+}
+
 /* Override for DMA direct allocation check - ARCH_HAS_FORCE_DMA_UNENCRYPTED */
 bool force_dma_unencrypted(struct device *dev)
 {
diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c
index 934dc5b2df36..b4072115c8ef 100644
--- a/arch/x86/mm/pat/set_memory.c
+++ b/arch/x86/mm/pat/set_memory.c
@@ -2023,6 +2023,12 @@ static int __set_memory_enc_pgtable(unsigned long addr, int numpages, bool enc)
 	 */
 	cpa_flush(&cpa, 0);
 
+	/*
+	 * Notify hypervisor that a given memory range is mapped encrypted
+	 * or decrypted.
+	 */
+	notify_range_enc_status_changed(addr, numpages, enc);
+
 	return ret;
 }
 
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 726700fabca6..bafe36e69227 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -1252,19 +1252,54 @@ st:			if (is_imm8(insn->off))
 		case BPF_LDX | BPF_MEM | BPF_DW:
 		case BPF_LDX | BPF_PROBE_MEM | BPF_DW:
 			if (BPF_MODE(insn->code) == BPF_PROBE_MEM) {
-				/* test src_reg, src_reg */
-				maybe_emit_mod(&prog, src_reg, src_reg, true); /* always 1 byte */
-				EMIT2(0x85, add_2reg(0xC0, src_reg, src_reg));
-				/* jne start_of_ldx */
-				EMIT2(X86_JNE, 0);
+				/* Though the verifier prevents negative insn->off in BPF_PROBE_MEM
+				 * add abs(insn->off) to the limit to make sure that negative
+				 * offset won't be an issue.
+				 * insn->off is s16, so it won't affect valid pointers.
+				 */
+				u64 limit = TASK_SIZE_MAX + PAGE_SIZE + abs(insn->off);
+				u8 *end_of_jmp1, *end_of_jmp2;
+
+				/* Conservatively check that src_reg + insn->off is a kernel address:
+				 * 1. src_reg + insn->off >= limit
+				 * 2. src_reg + insn->off doesn't become small positive.
+				 * Cannot do src_reg + insn->off >= limit in one branch,
+				 * since it needs two spare registers, but JIT has only one.
+				 */
+
+				/* movabsq r11, limit */
+				EMIT2(add_1mod(0x48, AUX_REG), add_1reg(0xB8, AUX_REG));
+				EMIT((u32)limit, 4);
+				EMIT(limit >> 32, 4);
+				/* cmp src_reg, r11 */
+				maybe_emit_mod(&prog, src_reg, AUX_REG, true);
+				EMIT2(0x39, add_2reg(0xC0, src_reg, AUX_REG));
+				/* if unsigned '<' goto end_of_jmp2 */
+				EMIT2(X86_JB, 0);
+				end_of_jmp1 = prog;
+
+				/* mov r11, src_reg */
+				emit_mov_reg(&prog, true, AUX_REG, src_reg);
+				/* add r11, insn->off */
+				maybe_emit_1mod(&prog, AUX_REG, true);
+				EMIT2_off32(0x81, add_1reg(0xC0, AUX_REG), insn->off);
+				/* jmp if not carry to start_of_ldx
+				 * Otherwise ERR_PTR(-EINVAL) + 128 will be the user addr
+				 * that has to be rejected.
+				 */
+				EMIT2(0x73 /* JNC */, 0);
+				end_of_jmp2 = prog;
+
 				/* xor dst_reg, dst_reg */
 				emit_mov_imm32(&prog, false, dst_reg, 0);
 				/* jmp byte_after_ldx */
 				EMIT2(0xEB, 0);
 
-				/* populate jmp_offset for JNE above */
-				temp[4] = prog - temp - 5 /* sizeof(test + jne) */;
+				/* populate jmp_offset for JB above to jump to xor dst_reg */
+				end_of_jmp1[-1] = end_of_jmp2 - end_of_jmp1;
+				/* populate jmp_offset for JNC above to jump to start_of_ldx */
 				start_of_ldx = prog;
+				end_of_jmp2[-1] = start_of_ldx - end_of_jmp2;
 			}
 			emit_ldx(&prog, BPF_SIZE(insn->code), dst_reg, src_reg, insn->off);
 			if (BPF_MODE(insn->code) == BPF_PROBE_MEM) {
@@ -1305,7 +1340,7 @@ st:			if (is_imm8(insn->off))
 				 * End result: x86 insn "mov rbx, qword ptr [rax+0x14]"
 				 * of 4 bytes will be ignored and rbx will be zero inited.
 				 */
-				ex->fixup = (prog - temp) | (reg2pt_regs[dst_reg] << 8);
+				ex->fixup = (prog - start_of_ldx) | (reg2pt_regs[dst_reg] << 8);
 			}
 			break;
 
diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c
index b15ebfe40a73..b0b848d6933a 100644
--- a/arch/x86/platform/efi/quirks.c
+++ b/arch/x86/platform/efi/quirks.c
@@ -277,7 +277,8 @@ void __init efi_arch_mem_reserve(phys_addr_t addr, u64 size)
 		return;
 	}
 
-	new = early_memremap(data.phys_map, data.size);
+	new = early_memremap_prot(data.phys_map, data.size,
+				  pgprot_val(pgprot_encrypted(FIXMAP_PAGE_NORMAL)));
 	if (!new) {
 		pr_err("Failed to map new boot services memmap\n");
 		return;
diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c
index 4a3da7592b99..38d24d2ab38b 100644
--- a/arch/x86/realmode/init.c
+++ b/arch/x86/realmode/init.c
@@ -72,6 +72,7 @@ static void __init setup_real_mode(void)
 #ifdef CONFIG_X86_64
 	u64 *trampoline_pgd;
 	u64 efer;
+	int i;
 #endif
 
 	base = (unsigned char *)real_mode_header;
@@ -128,8 +129,17 @@ static void __init setup_real_mode(void)
 	trampoline_header->flags = 0;
 
 	trampoline_pgd = (u64 *) __va(real_mode_header->trampoline_pgd);
+
+	/* Map the real mode stub as virtual == physical */
 	trampoline_pgd[0] = trampoline_pgd_entry.pgd;
-	trampoline_pgd[511] = init_top_pgt[511].pgd;
+
+	/*
+	 * Include the entirety of the kernel mapping into the trampoline
+	 * PGD.  This way, all mappings present in the normal kernel page
+	 * tables are usable while running on trampoline_pgd.
+	 */
+	for (i = pgd_index(__PAGE_OFFSET); i < PTRS_PER_PGD; i++)
+		trampoline_pgd[i] = init_top_pgt[i].pgd;
 #endif
 
 	sme_sev_setup_real_mode(trampoline_header);
diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c
index 9e55bcbfcd33..6a8f3b53ab83 100644
--- a/arch/x86/xen/smp_pv.c
+++ b/arch/x86/xen/smp_pv.c
@@ -225,7 +225,6 @@ static void __init xen_pv_smp_prepare_boot_cpu(void)
 static void __init xen_pv_smp_prepare_cpus(unsigned int max_cpus)
 {
 	unsigned cpu;
-	unsigned int i;
 
 	if (skip_ioapic_setup) {
 		char *m = (max_cpus == 0) ?
@@ -238,16 +237,9 @@ static void __init xen_pv_smp_prepare_cpus(unsigned int max_cpus)
 	}
 	xen_init_lock_cpu(0);
 
-	smp_store_boot_cpu_info();
-	cpu_data(0).x86_max_cores = 1;
+	smp_prepare_cpus_common();
 
-	for_each_possible_cpu(i) {
-		zalloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL);
-		zalloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL);
-		zalloc_cpumask_var(&per_cpu(cpu_die_map, i), GFP_KERNEL);
-		zalloc_cpumask_var(&per_cpu(cpu_llc_shared_map, i), GFP_KERNEL);
-	}
-	set_cpu_sibling_map(0);
+	cpu_data(0).x86_max_cores = 1;
 
 	speculative_store_bypass_ht_init();
 
diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S
index 220dd9678494..444d824775f6 100644
--- a/arch/x86/xen/xen-asm.S
+++ b/arch/x86/xen/xen-asm.S
@@ -20,6 +20,7 @@
 
 #include <linux/init.h>
 #include <linux/linkage.h>
+#include <../entry/calling.h>
 
 .pushsection .noinstr.text, "ax"
 /*
@@ -193,6 +194,25 @@ SYM_CODE_START(xen_iret)
 SYM_CODE_END(xen_iret)
 
 /*
+ * XEN pv doesn't use trampoline stack, PER_CPU_VAR(cpu_tss_rw + TSS_sp0) is
+ * also the kernel stack.  Reusing swapgs_restore_regs_and_return_to_usermode()
+ * in XEN pv would cause %rsp to move up to the top of the kernel stack and
+ * leave the IRET frame below %rsp, which is dangerous to be corrupted if #NMI
+ * interrupts. And swapgs_restore_regs_and_return_to_usermode() pushing the IRET
+ * frame at the same address is useless.
+ */
+SYM_CODE_START(xenpv_restore_regs_and_return_to_usermode)
+	UNWIND_HINT_REGS
+	POP_REGS
+
+	/* stackleak_erase() can work safely on the kernel stack. */
+	STACKLEAK_ERASE_NOCLOBBER
+
+	addq	$8, %rsp	/* skip regs->orig_ax */
+	jmp xen_iret
+SYM_CODE_END(xenpv_restore_regs_and_return_to_usermode)
+
+/*
  * Xen handles syscall callbacks much like ordinary exceptions, which
  * means we have:
  * - kernel gs
diff --git a/arch/xtensa/include/asm/cacheflush.h b/arch/xtensa/include/asm/cacheflush.h
index a8a041609c5d..7b4359312c25 100644
--- a/arch/xtensa/include/asm/cacheflush.h
+++ b/arch/xtensa/include/asm/cacheflush.h
@@ -121,7 +121,6 @@ void flush_cache_page(struct vm_area_struct*,
 
 #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
 void flush_dcache_page(struct page *);
-void flush_dcache_folio(struct folio *);
 
 void local_flush_cache_range(struct vm_area_struct *vma,
 		unsigned long start, unsigned long end);
@@ -138,9 +137,7 @@ void local_flush_cache_page(struct vm_area_struct *vma,
 #define flush_cache_vunmap(start,end)			do { } while (0)
 
 #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0
-#define ARCH_IMPLEMENTS_FLUSH_DCACHE_FOLIO
 #define flush_dcache_page(page)				do { } while (0)
-static inline void flush_dcache_folio(struct folio *folio) { }
 
 #define flush_icache_range local_flush_icache_range
 #define flush_cache_page(vma, addr, pfn)		do { } while (0)
diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl
index 104b327f8ac9..3e3e1a506bed 100644
--- a/arch/xtensa/kernel/syscalls/syscall.tbl
+++ b/arch/xtensa/kernel/syscalls/syscall.tbl
@@ -419,3 +419,4 @@
 446	common	landlock_restrict_self		sys_landlock_restrict_self
 # 447 reserved for memfd_secret
 448	common	process_mrelease		sys_process_mrelease
+449	common  futex_waitv                     sys_futex_waitv
diff --git a/block/bdev.c b/block/bdev.c
index b4dab2fb6a74..b1d087e5e205 100644
--- a/block/bdev.c
+++ b/block/bdev.c
@@ -753,8 +753,7 @@ struct block_device *blkdev_get_no_open(dev_t dev)
 
 	if (!bdev)
 		return NULL;
-	if ((bdev->bd_disk->flags & GENHD_FL_HIDDEN) ||
-	    !try_module_get(bdev->bd_disk->fops->owner)) {
+	if ((bdev->bd_disk->flags & GENHD_FL_HIDDEN)) {
 		put_device(&bdev->bd_device);
 		return NULL;
 	}
@@ -764,7 +763,6 @@ struct block_device *blkdev_get_no_open(dev_t dev)
 
 void blkdev_put_no_open(struct block_device *bdev)
 {
-	module_put(bdev->bd_disk->fops->owner);
 	put_device(&bdev->bd_device);
 }
 
@@ -820,12 +818,14 @@ struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder)
 	ret = -ENXIO;
 	if (!disk_live(disk))
 		goto abort_claiming;
+	if (!try_module_get(disk->fops->owner))
+		goto abort_claiming;
 	if (bdev_is_partition(bdev))
 		ret = blkdev_get_part(bdev, mode);
 	else
 		ret = blkdev_get_whole(bdev, mode);
 	if (ret)
-		goto abort_claiming;
+		goto put_module;
 	if (mode & FMODE_EXCL) {
 		bd_finish_claiming(bdev, holder);
 
@@ -847,7 +847,8 @@ struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder)
 	if (unblock_events)
 		disk_unblock_events(disk);
 	return bdev;
-
+put_module:
+	module_put(disk->fops->owner);
 abort_claiming:
 	if (mode & FMODE_EXCL)
 		bd_abort_claiming(bdev, holder);
@@ -956,6 +957,7 @@ void blkdev_put(struct block_device *bdev, fmode_t mode)
 		blkdev_put_whole(bdev, mode);
 	mutex_unlock(&disk->open_mutex);
 
+	module_put(disk->fops->owner);
 	blkdev_put_no_open(bdev);
 }
 EXPORT_SYMBOL(blkdev_put);
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 88b1fce90520..663aabfeba18 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -640,7 +640,7 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 	 */
 	ret = blk_queue_enter(q, 0);
 	if (ret)
-		return ret;
+		goto fail;
 
 	rcu_read_lock();
 	spin_lock_irq(&q->queue_lock);
@@ -676,13 +676,13 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 		new_blkg = blkg_alloc(pos, q, GFP_KERNEL);
 		if (unlikely(!new_blkg)) {
 			ret = -ENOMEM;
-			goto fail;
+			goto fail_exit_queue;
 		}
 
 		if (radix_tree_preload(GFP_KERNEL)) {
 			blkg_free(new_blkg);
 			ret = -ENOMEM;
-			goto fail;
+			goto fail_exit_queue;
 		}
 
 		rcu_read_lock();
@@ -722,9 +722,10 @@ fail_preloaded:
 fail_unlock:
 	spin_unlock_irq(&q->queue_lock);
 	rcu_read_unlock();
+fail_exit_queue:
+	blk_queue_exit(q);
 fail:
 	blkdev_put_no_open(bdev);
-	blk_queue_exit(q);
 	/*
 	 * If queue was bypassing, we should retry.  Do so after a
 	 * short msleep().  It isn't strictly necessary but queue
diff --git a/block/blk-core.c b/block/blk-core.c
index b043de2baaac..1378d084c770 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -363,8 +363,10 @@ void blk_cleanup_queue(struct request_queue *q)
 	blk_queue_flag_set(QUEUE_FLAG_DEAD, q);
 
 	blk_sync_queue(q);
-	if (queue_is_mq(q))
+	if (queue_is_mq(q)) {
+		blk_mq_cancel_work_sync(q);
 		blk_mq_exit_queue(q);
+	}
 
 	/*
 	 * In theory, request pool of sched_tags belongs to request queue.
@@ -809,10 +811,8 @@ noinline_for_stack bool submit_bio_checks(struct bio *bio)
 	if (unlikely(!current->io_context))
 		create_task_io_context(current, GFP_ATOMIC, q->node);
 
-	if (blk_throtl_bio(bio)) {
-		blkcg_bio_issue_init(bio);
+	if (blk_throtl_bio(bio))
 		return false;
-	}
 
 	blk_cgroup_bio_start(bio);
 	blkcg_bio_issue_init(bio);
@@ -1017,6 +1017,7 @@ EXPORT_SYMBOL(submit_bio);
 /**
  * bio_poll - poll for BIO completions
  * @bio: bio to poll for
+ * @iob: batches of IO
  * @flags: BLK_POLL_* flags that control the behavior
  *
  * Poll for completions on queue associated with the bio. Returns number of
diff --git a/block/blk-flush.c b/block/blk-flush.c
index 8e364bda5166..1fce6d16e6d3 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -379,7 +379,7 @@ static void mq_flush_data_end_io(struct request *rq, blk_status_t error)
  * @rq is being submitted.  Analyze what needs to be done and put it on the
  * right queue.
  */
-bool blk_insert_flush(struct request *rq)
+void blk_insert_flush(struct request *rq)
 {
 	struct request_queue *q = rq->q;
 	unsigned long fflags = q->queue_flags;	/* may change, cache */
@@ -409,7 +409,7 @@ bool blk_insert_flush(struct request *rq)
 	 */
 	if (!policy) {
 		blk_mq_end_request(rq, 0);
-		return true;
+		return;
 	}
 
 	BUG_ON(rq->bio != rq->biotail); /*assumes zero or single bio rq */
@@ -420,8 +420,10 @@ bool blk_insert_flush(struct request *rq)
 	 * for normal execution.
 	 */
 	if ((policy & REQ_FSEQ_DATA) &&
-	    !(policy & (REQ_FSEQ_PREFLUSH | REQ_FSEQ_POSTFLUSH)))
-		return false;
+	    !(policy & (REQ_FSEQ_PREFLUSH | REQ_FSEQ_POSTFLUSH))) {
+		blk_mq_request_bypass_insert(rq, false, true);
+		return;
+	}
 
 	/*
 	 * @rq should go through flush machinery.  Mark it part of flush
@@ -437,8 +439,6 @@ bool blk_insert_flush(struct request *rq)
 	spin_lock_irq(&fq->mq_flush_lock);
 	blk_flush_complete_seq(rq, fq, REQ_FSEQ_ACTIONS & ~policy, 0);
 	spin_unlock_irq(&fq->mq_flush_lock);
-
-	return true;
 }
 
 /**
diff --git a/block/blk-ia-ranges.c b/block/blk-ia-ranges.c
index c246c425d0d7..b925f3db3ab7 100644
--- a/block/blk-ia-ranges.c
+++ b/block/blk-ia-ranges.c
@@ -104,8 +104,8 @@ static struct kobj_type blk_ia_ranges_ktype = {
 };
 
 /**
- * disk_register_ia_ranges - register with sysfs a set of independent
- *			    access ranges
+ * disk_register_independent_access_ranges - register with sysfs a set of
+ *		independent access ranges
  * @disk:	Target disk
  * @new_iars:	New set of independent access ranges
  *
diff --git a/block/blk-iocost.c b/block/blk-iocost.c
index a5b37cc65b17..769b64394298 100644
--- a/block/blk-iocost.c
+++ b/block/blk-iocost.c
@@ -2311,7 +2311,14 @@ static void ioc_timer_fn(struct timer_list *timer)
 			hwm = current_hweight_max(iocg);
 			new_hwi = hweight_after_donation(iocg, old_hwi, hwm,
 							 usage, &now);
-			if (new_hwi < hwm) {
+			/*
+			 * Donation calculation assumes hweight_after_donation
+			 * to be positive, a condition that a donor w/ hwa < 2
+			 * can't meet. Don't bother with donation if hwa is
+			 * below 2. It's not gonna make a meaningful difference
+			 * anyway.
+			 */
+			if (new_hwi < hwm && hwa >= 2) {
 				iocg->hweight_donating = hwa;
 				iocg->hweight_after_donation = new_hwi;
 				list_add(&iocg->surplus_list, &surpluses);
diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index 4be652fa38e7..ba21449439cc 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -370,9 +370,6 @@ bool blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio,
 	bool ret = false;
 	enum hctx_type type;
 
-	if (bio_queue_enter(bio))
-		return false;
-
 	if (e && e->type->ops.bio_merge) {
 		ret = e->type->ops.bio_merge(q, bio, nr_segs);
 		goto out_put;
@@ -397,7 +394,6 @@ bool blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio,
 
 	spin_unlock(&ctx->lock);
 out_put:
-	blk_queue_exit(q);
 	return ret;
 }
 
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 629cf421417f..8874a63ae952 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -860,13 +860,14 @@ void blk_mq_end_request_batch(struct io_comp_batch *iob)
 		if (iob->need_ts)
 			__blk_mq_end_request_acct(rq, now);
 
+		rq_qos_done(rq->q, rq);
+
 		WRITE_ONCE(rq->state, MQ_RQ_IDLE);
 		if (!refcount_dec_and_test(&rq->ref))
 			continue;
 
 		blk_crypto_free_request(rq);
 		blk_pm_mark_last_busy(rq);
-		rq_qos_done(rq->q, rq);
 
 		if (nr_tags == TAG_COMP_BATCH || cur_hctx != rq->mq_hctx) {
 			if (cur_hctx)
@@ -2495,8 +2496,9 @@ static inline unsigned short blk_plug_max_rq_count(struct blk_plug *plug)
 	return BLK_MAX_REQUEST_COUNT;
 }
 
-static bool blk_attempt_bio_merge(struct request_queue *q, struct bio *bio,
-				  unsigned int nr_segs, bool *same_queue_rq)
+static bool blk_mq_attempt_bio_merge(struct request_queue *q,
+				     struct bio *bio, unsigned int nr_segs,
+				     bool *same_queue_rq)
 {
 	if (!blk_queue_nomerges(q) && bio_mergeable(bio)) {
 		if (blk_attempt_plug_merge(q, bio, nr_segs, same_queue_rq))
@@ -2520,12 +2522,8 @@ static struct request *blk_mq_get_new_requests(struct request_queue *q,
 	};
 	struct request *rq;
 
-	if (unlikely(bio_queue_enter(bio)))
+	if (blk_mq_attempt_bio_merge(q, bio, nsegs, same_queue_rq))
 		return NULL;
-	if (unlikely(!submit_bio_checks(bio)))
-		goto put_exit;
-	if (blk_attempt_bio_merge(q, bio, nsegs, same_queue_rq))
-		goto put_exit;
 
 	rq_qos_throttle(q, bio);
 
@@ -2542,26 +2540,42 @@ static struct request *blk_mq_get_new_requests(struct request_queue *q,
 	rq_qos_cleanup(q, bio);
 	if (bio->bi_opf & REQ_NOWAIT)
 		bio_wouldblock_error(bio);
-put_exit:
-	blk_queue_exit(q);
+
 	return NULL;
 }
 
+static inline bool blk_mq_can_use_cached_rq(struct request *rq, struct bio *bio)
+{
+	if (blk_mq_get_hctx_type(bio->bi_opf) != rq->mq_hctx->type)
+		return false;
+
+	if (op_is_flush(rq->cmd_flags) != op_is_flush(bio->bi_opf))
+		return false;
+
+	return true;
+}
+
 static inline struct request *blk_mq_get_request(struct request_queue *q,
 						 struct blk_plug *plug,
 						 struct bio *bio,
 						 unsigned int nsegs,
 						 bool *same_queue_rq)
 {
-	if (plug) {
-		struct request *rq;
+	struct request *rq;
+	bool checked = false;
 
+	if (plug) {
 		rq = rq_list_peek(&plug->cached_rq);
 		if (rq && rq->q == q) {
 			if (unlikely(!submit_bio_checks(bio)))
 				return NULL;
-			if (blk_attempt_bio_merge(q, bio, nsegs, same_queue_rq))
+			if (blk_mq_attempt_bio_merge(q, bio, nsegs,
+						same_queue_rq))
 				return NULL;
+			checked = true;
+			if (!blk_mq_can_use_cached_rq(rq, bio))
+				goto fallback;
+			rq->cmd_flags = bio->bi_opf;
 			plug->cached_rq = rq_list_next(rq);
 			INIT_LIST_HEAD(&rq->queuelist);
 			rq_qos_throttle(q, bio);
@@ -2569,7 +2583,17 @@ static inline struct request *blk_mq_get_request(struct request_queue *q,
 		}
 	}
 
-	return blk_mq_get_new_requests(q, plug, bio, nsegs, same_queue_rq);
+fallback:
+	if (unlikely(bio_queue_enter(bio)))
+		return NULL;
+	if (unlikely(!checked && !submit_bio_checks(bio)))
+		goto out_put;
+	rq = blk_mq_get_new_requests(q, plug, bio, nsegs, same_queue_rq);
+	if (rq)
+		return rq;
+out_put:
+	blk_queue_exit(q);
+	return NULL;
 }
 
 /**
@@ -2624,8 +2648,10 @@ void blk_mq_submit_bio(struct bio *bio)
 		return;
 	}
 
-	if (op_is_flush(bio->bi_opf) && blk_insert_flush(rq))
+	if (op_is_flush(bio->bi_opf)) {
+		blk_insert_flush(rq);
 		return;
+	}
 
 	if (plug && (q->nr_hw_queues == 1 ||
 	    blk_mq_is_shared_tags(rq->mq_hctx->flags) ||
@@ -4394,6 +4420,19 @@ unsigned int blk_mq_rq_cpu(struct request *rq)
 }
 EXPORT_SYMBOL(blk_mq_rq_cpu);
 
+void blk_mq_cancel_work_sync(struct request_queue *q)
+{
+	if (queue_is_mq(q)) {
+		struct blk_mq_hw_ctx *hctx;
+		int i;
+
+		cancel_delayed_work_sync(&q->requeue_work);
+
+		queue_for_each_hw_ctx(q, hctx, i)
+			cancel_delayed_work_sync(&hctx->run_work);
+	}
+}
+
 static int __init blk_mq_init(void)
 {
 	int i;
diff --git a/block/blk-mq.h b/block/blk-mq.h
index cb0b5482ca5e..afcf9931a489 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -89,15 +89,7 @@ static inline struct blk_mq_hw_ctx *blk_mq_map_queue_type(struct request_queue *
 	return q->queue_hw_ctx[q->tag_set->map[type].mq_map[cpu]];
 }
 
-/*
- * blk_mq_map_queue() - map (cmd_flags,type) to hardware queue
- * @q: request queue
- * @flags: request command flags
- * @ctx: software queue cpu ctx
- */
-static inline struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *q,
-						     unsigned int flags,
-						     struct blk_mq_ctx *ctx)
+static inline enum hctx_type blk_mq_get_hctx_type(unsigned int flags)
 {
 	enum hctx_type type = HCTX_TYPE_DEFAULT;
 
@@ -108,8 +100,20 @@ static inline struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *q,
 		type = HCTX_TYPE_POLL;
 	else if ((flags & REQ_OP_MASK) == REQ_OP_READ)
 		type = HCTX_TYPE_READ;
-	
-	return ctx->hctxs[type];
+	return type;
+}
+
+/*
+ * blk_mq_map_queue() - map (cmd_flags,type) to hardware queue
+ * @q: request queue
+ * @flags: request command flags
+ * @ctx: software queue cpu ctx
+ */
+static inline struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *q,
+						     unsigned int flags,
+						     struct blk_mq_ctx *ctx)
+{
+	return ctx->hctxs[blk_mq_get_hctx_type(flags)];
 }
 
 /*
@@ -124,6 +128,8 @@ extern void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx);
 void blk_mq_free_plug_rqs(struct blk_plug *plug);
 void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule);
 
+void blk_mq_cancel_work_sync(struct request_queue *q);
+
 void blk_mq_release(struct request_queue *q);
 
 static inline struct blk_mq_ctx *__blk_mq_get_ctx(struct request_queue *q,
@@ -149,7 +155,7 @@ struct blk_mq_alloc_data {
 	blk_mq_req_flags_t flags;
 	unsigned int shallow_depth;
 	unsigned int cmd_flags;
-	unsigned int rq_flags;
+	req_flags_t rq_flags;
 
 	/* allocate multiple requests/tags in one go */
 	unsigned int nr_tags;
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index cef1f713370b..cd75b0f73dc6 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -791,16 +791,6 @@ static void blk_release_queue(struct kobject *kobj)
 
 	blk_free_queue_stats(q->stats);
 
-	if (queue_is_mq(q)) {
-		struct blk_mq_hw_ctx *hctx;
-		int i;
-
-		cancel_delayed_work_sync(&q->requeue_work);
-
-		queue_for_each_hw_ctx(q, hctx, i)
-			cancel_delayed_work_sync(&hctx->run_work);
-	}
-
 	blk_exit_queue(q);
 
 	blk_queue_free_zone_bitmaps(q);
diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index 1d0c76c18fc5..774ecc598bee 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -429,9 +429,10 @@ int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode,
 		op = REQ_OP_ZONE_RESET;
 
 		/* Invalidate the page cache, including dirty pages. */
+		filemap_invalidate_lock(bdev->bd_inode->i_mapping);
 		ret = blkdev_truncate_zone_range(bdev, mode, &zrange);
 		if (ret)
-			return ret;
+			goto fail;
 		break;
 	case BLKOPENZONE:
 		op = REQ_OP_ZONE_OPEN;
@@ -449,15 +450,9 @@ int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode,
 	ret = blkdev_zone_mgmt(bdev, op, zrange.sector, zrange.nr_sectors,
 			       GFP_KERNEL);
 
-	/*
-	 * Invalidate the page cache again for zone reset: writes can only be
-	 * direct for zoned devices so concurrent writes would not add any page
-	 * to the page cache after/during reset. The page cache may be filled
-	 * again due to concurrent reads though and dropping the pages for
-	 * these is fine.
-	 */
-	if (!ret && cmd == BLKRESETZONE)
-		ret = blkdev_truncate_zone_range(bdev, mode, &zrange);
+fail:
+	if (cmd == BLKRESETZONE)
+		filemap_invalidate_unlock(bdev->bd_inode->i_mapping);
 
 	return ret;
 }
diff --git a/block/blk.h b/block/blk.h
index b4fed2033e48..ccde6e6f1736 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -271,7 +271,7 @@ void __blk_account_io_done(struct request *req, u64 now);
  */
 #define ELV_ON_HASH(rq) ((rq)->rq_flags & RQF_HASHED)
 
-bool blk_insert_flush(struct request *rq);
+void blk_insert_flush(struct request *rq);
 
 int elevator_switch_mq(struct request_queue *q,
 			      struct elevator_type *new_e);
diff --git a/block/elevator.c b/block/elevator.c
index 1f39f6e8ebb9..19a78d5516ba 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -694,12 +694,18 @@ void elevator_init_mq(struct request_queue *q)
 	if (!e)
 		return;
 
+	/*
+	 * We are called before adding disk, when there isn't any FS I/O,
+	 * so freezing queue plus canceling dispatch work is enough to
+	 * drain any dispatch activities originated from passthrough
+	 * requests, then no need to quiesce queue which may add long boot
+	 * latency, especially when lots of disks are involved.
+	 */
 	blk_mq_freeze_queue(q);
-	blk_mq_quiesce_queue(q);
+	blk_mq_cancel_work_sync(q);
 
 	err = blk_mq_init_sched(q, e);
 
-	blk_mq_unquiesce_queue(q);
 	blk_mq_unfreeze_queue(q);
 
 	if (err) {
diff --git a/block/fops.c b/block/fops.c
index ad732a36f9b3..0da147edbd18 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -15,6 +15,7 @@
 #include <linux/falloc.h>
 #include <linux/suspend.h>
 #include <linux/fs.h>
+#include <linux/module.h>
 #include "blk.h"
 
 static inline struct inode *bdev_file_inode(struct file *file)
@@ -340,8 +341,7 @@ static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb,
 	} else {
 		ret = bio_iov_iter_get_pages(bio, iter);
 		if (unlikely(ret)) {
-			bio->bi_status = BLK_STS_IOERR;
-			bio_endio(bio);
+			bio_put(bio);
 			return ret;
 		}
 	}
diff --git a/block/genhd.c b/block/genhd.c
index ca2fbab1d425..30362aeacac4 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -394,8 +394,8 @@ static void disk_scan_partitions(struct gendisk *disk)
  * This function registers the partitioning information in @disk
  * with the kernel.
  */
-int device_add_disk(struct device *parent, struct gendisk *disk,
-		     const struct attribute_group **groups)
+int __must_check device_add_disk(struct device *parent, struct gendisk *disk,
+				 const struct attribute_group **groups)
 
 {
 	struct device *ddev = disk_to_dev(disk);
@@ -544,7 +544,7 @@ out_disk_release_events:
 out_free_ext_minor:
 	if (disk->major == BLOCK_EXT_MAJOR)
 		blk_free_ext_minor(disk->first_minor);
-	return WARN_ON_ONCE(ret); /* keep until all callers handle errors */
+	return ret;
 }
 EXPORT_SYMBOL(device_add_disk);
 
@@ -1111,6 +1111,8 @@ static void disk_release(struct device *dev)
 	might_sleep();
 	WARN_ON_ONCE(disk_live(disk));
 
+	blk_mq_cancel_work_sync(disk->queue);
+
 	disk_release_events(disk);
 	kfree(disk->random);
 	xa_destroy(&disk->part_tbl);
diff --git a/block/ioctl.c b/block/ioctl.c
index d6af0ac97e57..0a1d10ac2e1a 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -113,6 +113,7 @@ static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode,
 	uint64_t range[2];
 	uint64_t start, len;
 	struct request_queue *q = bdev_get_queue(bdev);
+	struct inode *inode = bdev->bd_inode;
 	int err;
 
 	if (!(mode & FMODE_WRITE))
@@ -135,12 +136,17 @@ static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode,
 	if (start + len > bdev_nr_bytes(bdev))
 		return -EINVAL;
 
+	filemap_invalidate_lock(inode->i_mapping);
 	err = truncate_bdev_range(bdev, mode, start, start + len - 1);
 	if (err)
-		return err;
+		goto fail;
 
-	return blkdev_issue_discard(bdev, start >> 9, len >> 9,
-				    GFP_KERNEL, flags);
+	err = blkdev_issue_discard(bdev, start >> 9, len >> 9,
+				   GFP_KERNEL, flags);
+
+fail:
+	filemap_invalidate_unlock(inode->i_mapping);
+	return err;
 }
 
 static int blk_ioctl_zeroout(struct block_device *bdev, fmode_t mode,
@@ -148,6 +154,7 @@ static int blk_ioctl_zeroout(struct block_device *bdev, fmode_t mode,
 {
 	uint64_t range[2];
 	uint64_t start, end, len;
+	struct inode *inode = bdev->bd_inode;
 	int err;
 
 	if (!(mode & FMODE_WRITE))
@@ -170,12 +177,17 @@ static int blk_ioctl_zeroout(struct block_device *bdev, fmode_t mode,
 		return -EINVAL;
 
 	/* Invalidate the page cache, including dirty pages */
+	filemap_invalidate_lock(inode->i_mapping);
 	err = truncate_bdev_range(bdev, mode, start, end);
 	if (err)
-		return err;
+		goto fail;
+
+	err = blkdev_issue_zeroout(bdev, start >> 9, len >> 9, GFP_KERNEL,
+				   BLKDEV_ZERO_NOUNMAP);
 
-	return blkdev_issue_zeroout(bdev, start >> 9, len >> 9, GFP_KERNEL,
-			BLKDEV_ZERO_NOUNMAP);
+fail:
+	filemap_invalidate_unlock(inode->i_mapping);
+	return err;
 }
 
 static int put_ushort(unsigned short __user *argp, unsigned short val)
diff --git a/block/ioprio.c b/block/ioprio.c
index 0e4ff245f2bf..6f01d35a5145 100644
--- a/block/ioprio.c
+++ b/block/ioprio.c
@@ -69,7 +69,14 @@ int ioprio_check_cap(int ioprio)
 
 	switch (class) {
 		case IOPRIO_CLASS_RT:
-			if (!capable(CAP_SYS_NICE) && !capable(CAP_SYS_ADMIN))
+			/*
+			 * Originally this only checked for CAP_SYS_ADMIN,
+			 * which was implicitly allowed for pid 0 by security
+			 * modules such as SELinux. Make sure we check
+			 * CAP_SYS_ADMIN first to avoid a denial/avc for
+			 * possibly missing CAP_SYS_NICE permission.
+			 */
+			if (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_NICE))
 				return -EPERM;
 			fallthrough;
 			/* rt has prio field too */
@@ -213,6 +220,7 @@ SYSCALL_DEFINE2(ioprio_get, int, which, int, who)
 				pgrp = task_pgrp(current);
 			else
 				pgrp = find_vpid(who);
+			read_lock(&tasklist_lock);
 			do_each_pid_thread(pgrp, PIDTYPE_PGID, p) {
 				tmpio = get_task_ioprio(p);
 				if (tmpio < 0)
@@ -222,6 +230,8 @@ SYSCALL_DEFINE2(ioprio_get, int, which, int, who)
 				else
 					ret = ioprio_best(ret, tmpio);
 			} while_each_pid_thread(pgrp, PIDTYPE_PGID, p);
+			read_unlock(&tasklist_lock);
+
 			break;
 		case IOPRIO_WHO_USER:
 			uid = make_kuid(current_user_ns(), who);
diff --git a/crypto/zstd.c b/crypto/zstd.c
index 1a3309f066f7..154a969c83a8 100644
--- a/crypto/zstd.c
+++ b/crypto/zstd.c
@@ -18,22 +18,22 @@
 #define ZSTD_DEF_LEVEL	3
 
 struct zstd_ctx {
-	ZSTD_CCtx *cctx;
-	ZSTD_DCtx *dctx;
+	zstd_cctx *cctx;
+	zstd_dctx *dctx;
 	void *cwksp;
 	void *dwksp;
 };
 
-static ZSTD_parameters zstd_params(void)
+static zstd_parameters zstd_params(void)
 {
-	return ZSTD_getParams(ZSTD_DEF_LEVEL, 0, 0);
+	return zstd_get_params(ZSTD_DEF_LEVEL, 0);
 }
 
 static int zstd_comp_init(struct zstd_ctx *ctx)
 {
 	int ret = 0;
-	const ZSTD_parameters params = zstd_params();
-	const size_t wksp_size = ZSTD_CCtxWorkspaceBound(params.cParams);
+	const zstd_parameters params = zstd_params();
+	const size_t wksp_size = zstd_cctx_workspace_bound(&params.cParams);
 
 	ctx->cwksp = vzalloc(wksp_size);
 	if (!ctx->cwksp) {
@@ -41,7 +41,7 @@ static int zstd_comp_init(struct zstd_ctx *ctx)
 		goto out;
 	}
 
-	ctx->cctx = ZSTD_initCCtx(ctx->cwksp, wksp_size);
+	ctx->cctx = zstd_init_cctx(ctx->cwksp, wksp_size);
 	if (!ctx->cctx) {
 		ret = -EINVAL;
 		goto out_free;
@@ -56,7 +56,7 @@ out_free:
 static int zstd_decomp_init(struct zstd_ctx *ctx)
 {
 	int ret = 0;
-	const size_t wksp_size = ZSTD_DCtxWorkspaceBound();
+	const size_t wksp_size = zstd_dctx_workspace_bound();
 
 	ctx->dwksp = vzalloc(wksp_size);
 	if (!ctx->dwksp) {
@@ -64,7 +64,7 @@ static int zstd_decomp_init(struct zstd_ctx *ctx)
 		goto out;
 	}
 
-	ctx->dctx = ZSTD_initDCtx(ctx->dwksp, wksp_size);
+	ctx->dctx = zstd_init_dctx(ctx->dwksp, wksp_size);
 	if (!ctx->dctx) {
 		ret = -EINVAL;
 		goto out_free;
@@ -152,10 +152,10 @@ static int __zstd_compress(const u8 *src, unsigned int slen,
 {
 	size_t out_len;
 	struct zstd_ctx *zctx = ctx;
-	const ZSTD_parameters params = zstd_params();
+	const zstd_parameters params = zstd_params();
 
-	out_len = ZSTD_compressCCtx(zctx->cctx, dst, *dlen, src, slen, params);
-	if (ZSTD_isError(out_len))
+	out_len = zstd_compress_cctx(zctx->cctx, dst, *dlen, src, slen, &params);
+	if (zstd_is_error(out_len))
 		return -EINVAL;
 	*dlen = out_len;
 	return 0;
@@ -182,8 +182,8 @@ static int __zstd_decompress(const u8 *src, unsigned int slen,
 	size_t out_len;
 	struct zstd_ctx *zctx = ctx;
 
-	out_len = ZSTD_decompressDCtx(zctx->dctx, dst, *dlen, src, slen);
-	if (ZSTD_isError(out_len))
+	out_len = zstd_decompress_dctx(zctx->dctx, dst, *dlen, src, slen);
+	if (zstd_is_error(out_len))
 		return -EINVAL;
 	*dlen = out_len;
 	return 0;
diff --git a/drivers/Makefile b/drivers/Makefile
index be5d40ae1488..a110338c860c 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -41,8 +41,7 @@ obj-$(CONFIG_DMADEVICES)	+= dma/
 # SOC specific infrastructure drivers.
 obj-y				+= soc/
 
-obj-$(CONFIG_VIRTIO)		+= virtio/
-obj-$(CONFIG_VIRTIO_PCI_LIB)	+= virtio/
+obj-y				+= virtio/
 obj-$(CONFIG_VDPA)		+= vdpa/
 obj-$(CONFIG_XEN)		+= xen/
 
diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c
index a85c351589be..b62c87b8ce4a 100644
--- a/drivers/acpi/cppc_acpi.c
+++ b/drivers/acpi/cppc_acpi.c
@@ -998,7 +998,14 @@ static int cpc_write(int cpu, struct cpc_register_resource *reg_res, u64 val)
 static int cppc_get_perf(int cpunum, enum cppc_regs reg_idx, u64 *perf)
 {
 	struct cpc_desc *cpc_desc = per_cpu(cpc_desc_ptr, cpunum);
-	struct cpc_register_resource *reg = &cpc_desc->cpc_regs[reg_idx];
+	struct cpc_register_resource *reg;
+
+	if (!cpc_desc) {
+		pr_debug("No CPC descriptor for CPU:%d\n", cpunum);
+		return -ENODEV;
+	}
+
+	reg = &cpc_desc->cpc_regs[reg_idx];
 
 	if (CPC_IN_PCC(reg)) {
 		int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpunum);
diff --git a/drivers/acpi/glue.c b/drivers/acpi/glue.c
index 7cd0009e7ff3..ef104809f27b 100644
--- a/drivers/acpi/glue.c
+++ b/drivers/acpi/glue.c
@@ -347,28 +347,3 @@ void acpi_device_notify_remove(struct device *dev)
 
 	acpi_unbind_one(dev);
 }
-
-int acpi_dev_turn_off_if_unused(struct device *dev, void *not_used)
-{
-	struct acpi_device *adev = to_acpi_device(dev);
-
-	/*
-	 * Skip device objects with device IDs, because they may be in use even
-	 * if they are not companions of any physical device objects.
-	 */
-	if (adev->pnp.type.hardware_id)
-		return 0;
-
-	mutex_lock(&adev->physical_node_lock);
-
-	/*
-	 * Device objects without device IDs are not in use if they have no
-	 * corresponding physical device objects.
-	 */
-	if (list_empty(&adev->physical_node_list))
-		acpi_device_set_power(adev, ACPI_STATE_D3_COLD);
-
-	mutex_unlock(&adev->physical_node_lock);
-
-	return 0;
-}
diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h
index 8fbdc172864b..d91b560e8867 100644
--- a/drivers/acpi/internal.h
+++ b/drivers/acpi/internal.h
@@ -117,7 +117,6 @@ bool acpi_device_is_battery(struct acpi_device *adev);
 bool acpi_device_is_first_physical_node(struct acpi_device *adev,
 					const struct device *dev);
 int acpi_bus_register_early_device(int type);
-int acpi_dev_turn_off_if_unused(struct device *dev, void *not_used);
 
 /* --------------------------------------------------------------------------
                      Device Matching and Notification
diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c
index e312ebaed8db..2366f54d8e9c 100644
--- a/drivers/acpi/property.c
+++ b/drivers/acpi/property.c
@@ -1084,21 +1084,17 @@ struct fwnode_handle *acpi_get_next_subnode(const struct fwnode_handle *fwnode,
  * Returns parent node of an ACPI device or data firmware node or %NULL if
  * not available.
  */
-struct fwnode_handle *acpi_node_get_parent(const struct fwnode_handle *fwnode)
+static struct fwnode_handle *
+acpi_node_get_parent(const struct fwnode_handle *fwnode)
 {
 	if (is_acpi_data_node(fwnode)) {
 		/* All data nodes have parent pointer so just return that */
 		return to_acpi_data_node(fwnode)->parent;
 	} else if (is_acpi_device_node(fwnode)) {
-		acpi_handle handle, parent_handle;
-
-		handle = to_acpi_device_node(fwnode)->handle;
-		if (ACPI_SUCCESS(acpi_get_parent(handle, &parent_handle))) {
-			struct acpi_device *adev;
+		struct device *dev = to_acpi_device_node(fwnode)->dev.parent;
 
-			if (!acpi_bus_get_device(parent_handle, &adev))
-				return acpi_fwnode_handle(adev);
-		}
+		if (dev)
+			return acpi_fwnode_handle(to_acpi_device(dev));
 	}
 
 	return NULL;
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index a50f1967c73d..2c80765670bc 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -2564,12 +2564,6 @@ int __init acpi_scan_init(void)
 		}
 	}
 
-	/*
-	 * Make sure that power management resources are not blocked by ACPI
-	 * device objects with no users.
-	 */
-	bus_for_each_dev(&acpi_bus_type, NULL, NULL, acpi_dev_turn_off_if_unused);
-
 	acpi_turn_off_unused_power_resources();
 
 	acpi_scan_initialized = true;
diff --git a/drivers/android/binder.c b/drivers/android/binder.c
index 49fb74196d02..c75fb600740c 100644
--- a/drivers/android/binder.c
+++ b/drivers/android/binder.c
@@ -2710,7 +2710,7 @@ static void binder_transaction(struct binder_proc *proc,
 		t->from = thread;
 	else
 		t->from = NULL;
-	t->sender_euid = proc->cred->euid;
+	t->sender_euid = task_euid(proc->tsk);
 	t->to_proc = target_proc;
 	t->to_thread = target_thread;
 	t->code = tr->code;
@@ -4422,23 +4422,20 @@ static int binder_thread_release(struct binder_proc *proc,
 	__release(&t->lock);
 
 	/*
-	 * If this thread used poll, make sure we remove the waitqueue
-	 * from any epoll data structures holding it with POLLFREE.
-	 * waitqueue_active() is safe to use here because we're holding
-	 * the inner lock.
+	 * If this thread used poll, make sure we remove the waitqueue from any
+	 * poll data structures holding it.
 	 */
-	if ((thread->looper & BINDER_LOOPER_STATE_POLL) &&
-	    waitqueue_active(&thread->wait)) {
-		wake_up_poll(&thread->wait, EPOLLHUP | POLLFREE);
-	}
+	if (thread->looper & BINDER_LOOPER_STATE_POLL)
+		wake_up_pollfree(&thread->wait);
 
 	binder_inner_proc_unlock(thread->proc);
 
 	/*
-	 * This is needed to avoid races between wake_up_poll() above and
-	 * and ep_remove_waitqueue() called for other reasons (eg the epoll file
-	 * descriptor being closed); ep_remove_waitqueue() holds an RCU read
-	 * lock, so we can be sure it's done after calling synchronize_rcu().
+	 * This is needed to avoid races between wake_up_pollfree() above and
+	 * someone else removing the last entry from the queue for other reasons
+	 * (e.g. ep_remove_wait_queue() being called due to an epoll file
+	 * descriptor being closed).  Such other users hold an RCU read lock, so
+	 * we can be sure they're done after we call synchronize_rcu().
 	 */
 	if (thread->looper & BINDER_LOOPER_STATE_POLL)
 		synchronize_rcu();
diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index 340515f54498..47bc74a8c7b6 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -671,7 +671,7 @@ static void binder_free_buf_locked(struct binder_alloc *alloc,
 	BUG_ON(buffer->user_data > alloc->buffer + alloc->buffer_size);
 
 	if (buffer->async_transaction) {
-		alloc->free_async_space += size + sizeof(struct binder_buffer);
+		alloc->free_async_space += buffer_size + sizeof(struct binder_buffer);
 
 		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC_ASYNC,
 			     "%d: binder_free_buf size %zd async free %zd\n",
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index d60f34718b5d..1e1167e725a4 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -438,6 +438,7 @@ static const struct pci_device_id ahci_pci_tbl[] = {
 	/* AMD */
 	{ PCI_VDEVICE(AMD, 0x7800), board_ahci }, /* AMD Hudson-2 */
 	{ PCI_VDEVICE(AMD, 0x7900), board_ahci }, /* AMD CZ */
+	{ PCI_VDEVICE(AMD, 0x7901), board_ahci_mobile }, /* AMD Green Sardine */
 	/* AMD is using RAID class only for ahci controllers */
 	{ PCI_VENDOR_ID_AMD, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID,
 	  PCI_CLASS_STORAGE_RAID << 8, 0xffffff, board_ahci },
diff --git a/drivers/ata/ahci_ceva.c b/drivers/ata/ahci_ceva.c
index 50b56cd0039d..e9c7c07fd84c 100644
--- a/drivers/ata/ahci_ceva.c
+++ b/drivers/ata/ahci_ceva.c
@@ -94,6 +94,7 @@ struct ceva_ahci_priv {
 static unsigned int ceva_ahci_read_id(struct ata_device *dev,
 					struct ata_taskfile *tf, u16 *id)
 {
+	__le16 *__id = (__le16 *)id;
 	u32 err_mask;
 
 	err_mask = ata_do_dev_read_id(dev, tf, id);
@@ -103,7 +104,7 @@ static unsigned int ceva_ahci_read_id(struct ata_device *dev,
 	 * Since CEVA controller does not support device sleep feature, we
 	 * need to clear DEVSLP (bit 8) in word78 of the IDENTIFY DEVICE data.
 	 */
-	id[ATA_ID_FEATURE_SUPP] &= cpu_to_le16(~(1 << 8));
+	__id[ATA_ID_FEATURE_SUPP] &= cpu_to_le16(~(1 << 8));
 
 	return 0;
 }
diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c
index 8a6835bfd18a..f76b8418e6fb 100644
--- a/drivers/ata/libahci.c
+++ b/drivers/ata/libahci.c
@@ -2323,6 +2323,18 @@ int ahci_port_resume(struct ata_port *ap)
 EXPORT_SYMBOL_GPL(ahci_port_resume);
 
 #ifdef CONFIG_PM
+static void ahci_handle_s2idle(struct ata_port *ap)
+{
+	void __iomem *port_mmio = ahci_port_base(ap);
+	u32 devslp;
+
+	if (pm_suspend_via_firmware())
+		return;
+	devslp = readl(port_mmio + PORT_DEVSLP);
+	if ((devslp & PORT_DEVSLP_ADSE))
+		ata_msleep(ap, devslp_idle_timeout);
+}
+
 static int ahci_port_suspend(struct ata_port *ap, pm_message_t mesg)
 {
 	const char *emsg = NULL;
@@ -2336,6 +2348,9 @@ static int ahci_port_suspend(struct ata_port *ap, pm_message_t mesg)
 		ata_port_freeze(ap);
 	}
 
+	if (acpi_storage_d3(ap->host->dev))
+		ahci_handle_s2idle(ap);
+
 	ahci_rpm_put_port(ap);
 	return rc;
 }
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 8a0ccb190d76..aba0c67d1bd6 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -2031,8 +2031,9 @@ retry:
 			dev->horkage |= ATA_HORKAGE_NO_DMA_LOG;
 			goto retry;
 		}
-		ata_dev_err(dev, "Read log page 0x%02x failed, Emask 0x%x\n",
-			    (unsigned int)page, err_mask);
+		ata_dev_err(dev,
+			    "Read log 0x%02x page 0x%02x failed, Emask 0x%x\n",
+			    (unsigned int)log, (unsigned int)page, err_mask);
 	}
 
 	return err_mask;
@@ -2177,6 +2178,9 @@ static void ata_dev_config_ncq_prio(struct ata_device *dev)
 	struct ata_port *ap = dev->link->ap;
 	unsigned int err_mask;
 
+	if (!ata_identify_page_supported(dev, ATA_LOG_SATA_SETTINGS))
+		return;
+
 	err_mask = ata_read_log_page(dev,
 				     ATA_LOG_IDENTIFY_DEVICE,
 				     ATA_LOG_SATA_SETTINGS,
@@ -2453,7 +2457,8 @@ static void ata_dev_config_devslp(struct ata_device *dev)
 	 * Check device sleep capability. Get DevSlp timing variables
 	 * from SATA Settings page of Identify Device Data Log.
 	 */
-	if (!ata_id_has_devslp(dev->id))
+	if (!ata_id_has_devslp(dev->id) ||
+	    !ata_identify_page_supported(dev, ATA_LOG_SATA_SETTINGS))
 		return;
 
 	err_mask = ata_read_log_page(dev,
@@ -3915,6 +3920,8 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = {
 	{ "VRFDFC22048UCHC-TE*", NULL,		ATA_HORKAGE_NODMA },
 	/* Odd clown on sil3726/4726 PMPs */
 	{ "Config  Disk",	NULL,		ATA_HORKAGE_DISABLE },
+	/* Similar story with ASMedia 1092 */
+	{ "ASMT109x- Config",	NULL,		ATA_HORKAGE_DISABLE },
 
 	/* Weird ATAPI devices */
 	{ "TORiSAN DVD-ROM DRD-N216", NULL,	ATA_HORKAGE_MAX_SEC_128 },
diff --git a/drivers/ata/libata-sata.c b/drivers/ata/libata-sata.c
index 4e88597aa9df..b9c77885b872 100644
--- a/drivers/ata/libata-sata.c
+++ b/drivers/ata/libata-sata.c
@@ -827,7 +827,7 @@ static ssize_t ata_scsi_lpm_show(struct device *dev,
 	if (ap->target_lpm_policy >= ARRAY_SIZE(ata_lpm_policy_names))
 		return -EINVAL;
 
-	return snprintf(buf, PAGE_SIZE, "%s\n",
+	return sysfs_emit(buf, "%s\n",
 			ata_lpm_policy_names[ap->target_lpm_policy]);
 }
 DEVICE_ATTR(link_power_management_policy, S_IRUGO | S_IWUSR,
@@ -922,7 +922,7 @@ DEVICE_ATTR(ncq_prio_enable, S_IRUGO | S_IWUSR,
 	    ata_ncq_prio_enable_show, ata_ncq_prio_enable_store);
 EXPORT_SYMBOL_GPL(dev_attr_ncq_prio_enable);
 
-struct attribute *ata_ncq_sdev_attrs[] = {
+static struct attribute *ata_ncq_sdev_attrs[] = {
 	&dev_attr_unload_heads.attr,
 	&dev_attr_ncq_prio_enable.attr,
 	&dev_attr_ncq_prio_supported.attr,
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 1b84d5526d77..313e9475507b 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -2859,8 +2859,19 @@ static unsigned int ata_scsi_pass_thru(struct ata_queued_cmd *qc)
 		goto invalid_fld;
 	}
 
-	if (ata_is_ncq(tf->protocol) && (cdb[2 + cdb_offset] & 0x3) == 0)
-		tf->protocol = ATA_PROT_NCQ_NODATA;
+	if ((cdb[2 + cdb_offset] & 0x3) == 0) {
+		/*
+		 * When T_LENGTH is zero (No data is transferred), dir should
+		 * be DMA_NONE.
+		 */
+		if (scmd->sc_data_direction != DMA_NONE) {
+			fp = 2 + cdb_offset;
+			goto invalid_fld;
+		}
+
+		if (ata_is_ncq(tf->protocol))
+			tf->protocol = ATA_PROT_NCQ_NODATA;
+	}
 
 	/* enable LBA */
 	tf->flags |= ATA_TFLAG_LBA;
diff --git a/drivers/ata/pata_falcon.c b/drivers/ata/pata_falcon.c
index 121635aa8c00..823c88622e34 100644
--- a/drivers/ata/pata_falcon.c
+++ b/drivers/ata/pata_falcon.c
@@ -55,14 +55,14 @@ static unsigned int pata_falcon_data_xfer(struct ata_queued_cmd *qc,
 	/* Transfer multiple of 2 bytes */
 	if (rw == READ) {
 		if (swap)
-			raw_insw_swapw((u16 *)data_addr, (u16 *)buf, words);
+			raw_insw_swapw(data_addr, (u16 *)buf, words);
 		else
-			raw_insw((u16 *)data_addr, (u16 *)buf, words);
+			raw_insw(data_addr, (u16 *)buf, words);
 	} else {
 		if (swap)
-			raw_outsw_swapw((u16 *)data_addr, (u16 *)buf, words);
+			raw_outsw_swapw(data_addr, (u16 *)buf, words);
 		else
-			raw_outsw((u16 *)data_addr, (u16 *)buf, words);
+			raw_outsw(data_addr, (u16 *)buf, words);
 	}
 
 	/* Transfer trailing byte, if any. */
@@ -74,16 +74,16 @@ static unsigned int pata_falcon_data_xfer(struct ata_queued_cmd *qc,
 
 		if (rw == READ) {
 			if (swap)
-				raw_insw_swapw((u16 *)data_addr, (u16 *)pad, 1);
+				raw_insw_swapw(data_addr, (u16 *)pad, 1);
 			else
-				raw_insw((u16 *)data_addr, (u16 *)pad, 1);
+				raw_insw(data_addr, (u16 *)pad, 1);
 			*buf = pad[0];
 		} else {
 			pad[0] = *buf;
 			if (swap)
-				raw_outsw_swapw((u16 *)data_addr, (u16 *)pad, 1);
+				raw_outsw_swapw(data_addr, (u16 *)pad, 1);
 			else
-				raw_outsw((u16 *)data_addr, (u16 *)pad, 1);
+				raw_outsw(data_addr, (u16 *)pad, 1);
 		}
 		words++;
 	}
diff --git a/drivers/ata/sata_fsl.c b/drivers/ata/sata_fsl.c
index e5838b23c9e0..3b31a4f596d8 100644
--- a/drivers/ata/sata_fsl.c
+++ b/drivers/ata/sata_fsl.c
@@ -1394,6 +1394,14 @@ static int sata_fsl_init_controller(struct ata_host *host)
 	return 0;
 }
 
+static void sata_fsl_host_stop(struct ata_host *host)
+{
+        struct sata_fsl_host_priv *host_priv = host->private_data;
+
+        iounmap(host_priv->hcr_base);
+        kfree(host_priv);
+}
+
 /*
  * scsi mid-layer and libata interface structures
  */
@@ -1426,6 +1434,8 @@ static struct ata_port_operations sata_fsl_ops = {
 	.port_start = sata_fsl_port_start,
 	.port_stop = sata_fsl_port_stop,
 
+	.host_stop      = sata_fsl_host_stop,
+
 	.pmp_attach = sata_fsl_pmp_attach,
 	.pmp_detach = sata_fsl_pmp_detach,
 };
@@ -1480,9 +1490,9 @@ static int sata_fsl_probe(struct platform_device *ofdev)
 	host_priv->ssr_base = ssr_base;
 	host_priv->csr_base = csr_base;
 
-	irq = irq_of_parse_and_map(ofdev->dev.of_node, 0);
-	if (!irq) {
-		dev_err(&ofdev->dev, "invalid irq from platform\n");
+	irq = platform_get_irq(ofdev, 0);
+	if (irq < 0) {
+		retval = irq;
 		goto error_exit_with_cleanup;
 	}
 	host_priv->irq = irq;
@@ -1557,10 +1567,6 @@ static int sata_fsl_remove(struct platform_device *ofdev)
 
 	ata_host_detach(host);
 
-	irq_dispose_mapping(host_priv->irq);
-	iounmap(host_priv->hcr_base);
-	kfree(host_priv);
-
 	return 0;
 }
 
diff --git a/drivers/auxdisplay/charlcd.c b/drivers/auxdisplay/charlcd.c
index 304accde365c..6d309e4971b6 100644
--- a/drivers/auxdisplay/charlcd.c
+++ b/drivers/auxdisplay/charlcd.c
@@ -37,7 +37,7 @@ struct charlcd_priv {
 	bool must_clear;
 
 	/* contains the LCD config state */
-	unsigned long int flags;
+	unsigned long flags;
 
 	/* Current escape sequence and it's length or -1 if outside */
 	struct {
@@ -578,6 +578,9 @@ static int charlcd_init(struct charlcd *lcd)
 	 * Since charlcd_init_display() needs to write data, we have to
 	 * enable mark the LCD initialized just before.
 	 */
+	if (WARN_ON(!lcd->ops->init_display))
+		return -EINVAL;
+
 	ret = lcd->ops->init_display(lcd);
 	if (ret)
 		return ret;
diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c
index 981e72a3dafb..ff16a36a908b 100644
--- a/drivers/base/arch_topology.c
+++ b/drivers/base/arch_topology.c
@@ -677,6 +677,8 @@ void remove_cpu_topology(unsigned int cpu)
 		cpumask_clear_cpu(cpu, topology_core_cpumask(sibling));
 	for_each_cpu(sibling, topology_sibling_cpumask(cpu))
 		cpumask_clear_cpu(cpu, topology_sibling_cpumask(sibling));
+	for_each_cpu(sibling, topology_cluster_cpumask(cpu))
+		cpumask_clear_cpu(cpu, topology_cluster_cpumask(sibling));
 	for_each_cpu(sibling, topology_llc_cpumask(cpu))
 		cpumask_clear_cpu(cpu, topology_llc_cpumask(sibling));
 
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index f4d0c555de29..04ea92cbd9cf 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -1902,7 +1902,7 @@ int dpm_prepare(pm_message_t state)
 	device_block_probing();
 
 	mutex_lock(&dpm_list_mtx);
-	while (!list_empty(&dpm_list)) {
+	while (!list_empty(&dpm_list) && !error) {
 		struct device *dev = to_device(dpm_list.next);
 
 		get_device(dev);
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index a154cab6cd98..c3a36cfaa855 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -2103,7 +2103,7 @@ static int loop_control_remove(int idx)
 	int ret;
 
 	if (idx < 0) {
-		pr_warn("deleting an unspecified loop device is not supported.\n");
+		pr_warn_once("deleting an unspecified loop device is not supported.\n");
 		return -EINVAL;
 	}
 		
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 97bf051a50ce..6ae38776e30e 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -316,7 +316,7 @@ static blk_status_t virtio_queue_rq(struct blk_mq_hw_ctx *hctx,
 	struct request *req = bd->rq;
 	struct virtblk_req *vbr = blk_mq_rq_to_pdu(req);
 	unsigned long flags;
-	unsigned int num;
+	int num;
 	int qid = hctx->queue_num;
 	bool notify = false;
 	blk_status_t status;
@@ -1049,7 +1049,6 @@ static struct virtio_driver virtio_blk = {
 	.feature_table_size		= ARRAY_SIZE(features),
 	.feature_table_legacy		= features_legacy,
 	.feature_table_size_legacy	= ARRAY_SIZE(features_legacy),
-	.suppress_used_validation	= true,
 	.driver.name			= KBUILD_MODNAME,
 	.driver.owner			= THIS_MODULE,
 	.id_table			= id_table,
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 8e3983e456f3..286cf1afad78 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -1512,9 +1512,12 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
 	unsigned long flags;
 	struct blkfront_ring_info *rinfo = (struct blkfront_ring_info *)dev_id;
 	struct blkfront_info *info = rinfo->dev_info;
+	unsigned int eoiflag = XEN_EOI_FLAG_SPURIOUS;
 
-	if (unlikely(info->connected != BLKIF_STATE_CONNECTED))
+	if (unlikely(info->connected != BLKIF_STATE_CONNECTED)) {
+		xen_irq_lateeoi(irq, XEN_EOI_FLAG_SPURIOUS);
 		return IRQ_HANDLED;
+	}
 
 	spin_lock_irqsave(&rinfo->ring_lock, flags);
  again:
@@ -1530,6 +1533,8 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
 		unsigned long id;
 		unsigned int op;
 
+		eoiflag = 0;
+
 		RING_COPY_RESPONSE(&rinfo->ring, i, &bret);
 		id = bret.id;
 
@@ -1646,6 +1651,8 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
 
 	spin_unlock_irqrestore(&rinfo->ring_lock, flags);
 
+	xen_irq_lateeoi(irq, eoiflag);
+
 	return IRQ_HANDLED;
 
  err:
@@ -1653,6 +1660,8 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
 
 	spin_unlock_irqrestore(&rinfo->ring_lock, flags);
 
+	/* No EOI in order to avoid further interrupts. */
+
 	pr_alert("%s disabled for further use\n", info->gd->disk_name);
 	return IRQ_HANDLED;
 }
@@ -1692,8 +1701,8 @@ static int setup_blkring(struct xenbus_device *dev,
 	if (err)
 		goto fail;
 
-	err = bind_evtchn_to_irqhandler(rinfo->evtchn, blkif_interrupt, 0,
-					"blkif", rinfo);
+	err = bind_evtchn_to_irqhandler_lateeoi(rinfo->evtchn, blkif_interrupt,
+						0, "blkif", rinfo);
 	if (err <= 0) {
 		xenbus_dev_fatal(dev, err,
 				 "bind_evtchn_to_irqhandler failed");
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 08d7953ec5f1..25071126995b 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -1853,12 +1853,14 @@ static const struct block_device_operations zram_devops = {
 	.owner = THIS_MODULE
 };
 
+#ifdef CONFIG_ZRAM_WRITEBACK
 static const struct block_device_operations zram_wb_devops = {
 	.open = zram_open,
 	.submit_bio = zram_submit_bio,
 	.swap_slot_free_notify = zram_slot_free_notify,
 	.owner = THIS_MODULE
 };
+#endif
 
 static DEVICE_ATTR_WO(compact);
 static DEVICE_ATTR_RW(disksize);
diff --git a/drivers/bus/brcmstb_gisb.c b/drivers/bus/brcmstb_gisb.c
index 4c2f7d61cb9b..183d5cc37d42 100644
--- a/drivers/bus/brcmstb_gisb.c
+++ b/drivers/bus/brcmstb_gisb.c
@@ -485,7 +485,7 @@ static int __init brcmstb_gisb_arb_probe(struct platform_device *pdev)
 	list_add_tail(&gdev->next, &brcmstb_gisb_arb_device_list);
 
 #ifdef CONFIG_MIPS
-	board_be_handler = brcmstb_bus_error_handler;
+	mips_set_be_handler(brcmstb_bus_error_handler);
 #endif
 
 	if (list_is_singular(&brcmstb_gisb_arb_device_list)) {
diff --git a/drivers/bus/mhi/core/pm.c b/drivers/bus/mhi/core/pm.c
index fb99e3727155..547e6e769546 100644
--- a/drivers/bus/mhi/core/pm.c
+++ b/drivers/bus/mhi/core/pm.c
@@ -881,7 +881,7 @@ int mhi_pm_suspend(struct mhi_controller *mhi_cntrl)
 }
 EXPORT_SYMBOL_GPL(mhi_pm_suspend);
 
-int mhi_pm_resume(struct mhi_controller *mhi_cntrl)
+static int __mhi_pm_resume(struct mhi_controller *mhi_cntrl, bool force)
 {
 	struct mhi_chan *itr, *tmp;
 	struct device *dev = &mhi_cntrl->mhi_dev->dev;
@@ -898,8 +898,12 @@ int mhi_pm_resume(struct mhi_controller *mhi_cntrl)
 	if (MHI_PM_IN_ERROR_STATE(mhi_cntrl->pm_state))
 		return -EIO;
 
-	if (mhi_get_mhi_state(mhi_cntrl) != MHI_STATE_M3)
-		return -EINVAL;
+	if (mhi_get_mhi_state(mhi_cntrl) != MHI_STATE_M3) {
+		dev_warn(dev, "Resuming from non M3 state (%s)\n",
+			 TO_MHI_STATE_STR(mhi_get_mhi_state(mhi_cntrl)));
+		if (!force)
+			return -EINVAL;
+	}
 
 	/* Notify clients about exiting LPM */
 	list_for_each_entry_safe(itr, tmp, &mhi_cntrl->lpm_chans, node) {
@@ -940,8 +944,19 @@ int mhi_pm_resume(struct mhi_controller *mhi_cntrl)
 
 	return 0;
 }
+
+int mhi_pm_resume(struct mhi_controller *mhi_cntrl)
+{
+	return __mhi_pm_resume(mhi_cntrl, false);
+}
 EXPORT_SYMBOL_GPL(mhi_pm_resume);
 
+int mhi_pm_resume_force(struct mhi_controller *mhi_cntrl)
+{
+	return __mhi_pm_resume(mhi_cntrl, true);
+}
+EXPORT_SYMBOL_GPL(mhi_pm_resume_force);
+
 int __mhi_device_get_sync(struct mhi_controller *mhi_cntrl)
 {
 	int ret;
diff --git a/drivers/bus/mhi/pci_generic.c b/drivers/bus/mhi/pci_generic.c
index 59a4896a8030..4c577a731709 100644
--- a/drivers/bus/mhi/pci_generic.c
+++ b/drivers/bus/mhi/pci_generic.c
@@ -20,7 +20,7 @@
 
 #define MHI_PCI_DEFAULT_BAR_NUM 0
 
-#define MHI_POST_RESET_DELAY_MS 500
+#define MHI_POST_RESET_DELAY_MS 2000
 
 #define HEALTH_CHECK_PERIOD (HZ * 2)
 
diff --git a/drivers/bus/sunxi-rsb.c b/drivers/bus/sunxi-rsb.c
index 6f225dddc74f..4566e730ef2b 100644
--- a/drivers/bus/sunxi-rsb.c
+++ b/drivers/bus/sunxi-rsb.c
@@ -687,11 +687,11 @@ err_clk_disable:
 
 static void sunxi_rsb_hw_exit(struct sunxi_rsb *rsb)
 {
-	/* Keep the clock and PM reference counts consistent. */
-	if (pm_runtime_status_suspended(rsb->dev))
-		pm_runtime_resume(rsb->dev);
 	reset_control_assert(rsb->rstc);
-	clk_disable_unprepare(rsb->clk);
+
+	/* Keep the clock and PM reference counts consistent. */
+	if (!pm_runtime_status_suspended(rsb->dev))
+		clk_disable_unprepare(rsb->clk);
 }
 
 static int __maybe_unused sunxi_rsb_runtime_suspend(struct device *dev)
diff --git a/drivers/char/agp/parisc-agp.c b/drivers/char/agp/parisc-agp.c
index ed3c4c42fc23..d68d05d5d383 100644
--- a/drivers/char/agp/parisc-agp.c
+++ b/drivers/char/agp/parisc-agp.c
@@ -281,7 +281,7 @@ agp_ioc_init(void __iomem *ioc_regs)
         return 0;
 }
 
-static int
+static int __init
 lba_find_capability(int cap)
 {
 	struct _parisc_agp_info *info = &parisc_agp_info;
@@ -366,7 +366,7 @@ fail:
 	return error;
 }
 
-static int
+static int __init
 find_quicksilver(struct device *dev, void *data)
 {
 	struct parisc_device **lba = data;
@@ -378,7 +378,7 @@ find_quicksilver(struct device *dev, void *data)
 	return 0;
 }
 
-static int
+static int __init
 parisc_agp_init(void)
 {
 	extern struct sba_device *sba_list;
diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c
index deed355422f4..c59265146e9c 100644
--- a/drivers/char/ipmi/ipmi_msghandler.c
+++ b/drivers/char/ipmi/ipmi_msghandler.c
@@ -191,6 +191,8 @@ struct ipmi_user {
 	struct work_struct remove_work;
 };
 
+static struct workqueue_struct *remove_work_wq;
+
 static struct ipmi_user *acquire_ipmi_user(struct ipmi_user *user, int *index)
 	__acquires(user->release_barrier)
 {
@@ -1297,7 +1299,7 @@ static void free_user(struct kref *ref)
 	struct ipmi_user *user = container_of(ref, struct ipmi_user, refcount);
 
 	/* SRCU cleanup must happen in task context. */
-	schedule_work(&user->remove_work);
+	queue_work(remove_work_wq, &user->remove_work);
 }
 
 static void _ipmi_destroy_user(struct ipmi_user *user)
@@ -3029,7 +3031,7 @@ cleanup_bmc_device(struct kref *ref)
 	 * with removing the device attributes while reading a device
 	 * attribute.
 	 */
-	schedule_work(&bmc->remove_work);
+	queue_work(remove_work_wq, &bmc->remove_work);
 }
 
 /*
@@ -3918,9 +3920,11 @@ static int handle_ipmb_direct_rcv_cmd(struct ipmi_smi *intf,
 		/* We didn't find a user, deliver an error response. */
 		ipmi_inc_stat(intf, unhandled_commands);
 
-		msg->data[0] = ((netfn + 1) << 2) | (msg->rsp[4] & 0x3);
-		msg->data[1] = msg->rsp[2];
-		msg->data[2] = msg->rsp[4] & ~0x3;
+		msg->data[0] = (netfn + 1) << 2;
+		msg->data[0] |= msg->rsp[2] & 0x3; /* rqLUN */
+		msg->data[1] = msg->rsp[1]; /* Addr */
+		msg->data[2] = msg->rsp[2] & ~0x3; /* rqSeq */
+		msg->data[2] |= msg->rsp[0] & 0x3; /* rsLUN */
 		msg->data[3] = cmd;
 		msg->data[4] = IPMI_INVALID_CMD_COMPLETION_CODE;
 		msg->data_size = 5;
@@ -4455,13 +4459,24 @@ return_unspecified:
 		msg->rsp[2] = IPMI_ERR_UNSPECIFIED;
 		msg->rsp_size = 3;
 	} else if (msg->type == IPMI_SMI_MSG_TYPE_IPMB_DIRECT) {
-		/* commands must have at least 3 bytes, responses 4. */
-		if (is_cmd && (msg->rsp_size < 3)) {
+		/* commands must have at least 4 bytes, responses 5. */
+		if (is_cmd && (msg->rsp_size < 4)) {
 			ipmi_inc_stat(intf, invalid_commands);
 			goto out;
 		}
-		if (!is_cmd && (msg->rsp_size < 4))
-			goto return_unspecified;
+		if (!is_cmd && (msg->rsp_size < 5)) {
+			ipmi_inc_stat(intf, invalid_ipmb_responses);
+			/* Construct a valid error response. */
+			msg->rsp[0] = msg->data[0] & 0xfc; /* NetFN */
+			msg->rsp[0] |= (1 << 2); /* Make it a response */
+			msg->rsp[0] |= msg->data[2] & 3; /* rqLUN */
+			msg->rsp[1] = msg->data[1]; /* Addr */
+			msg->rsp[2] = msg->data[2] & 0xfc; /* rqSeq */
+			msg->rsp[2] |= msg->data[0] & 0x3; /* rsLUN */
+			msg->rsp[3] = msg->data[3]; /* Cmd */
+			msg->rsp[4] = IPMI_ERR_UNSPECIFIED;
+			msg->rsp_size = 5;
+		}
 	} else if ((msg->data_size >= 2)
 	    && (msg->data[0] == (IPMI_NETFN_APP_REQUEST << 2))
 	    && (msg->data[1] == IPMI_SEND_MSG_CMD)
@@ -5031,6 +5046,7 @@ struct ipmi_smi_msg *ipmi_alloc_smi_msg(void)
 	if (rv) {
 		rv->done = free_smi_msg;
 		rv->user_data = NULL;
+		rv->type = IPMI_SMI_MSG_TYPE_NORMAL;
 		atomic_inc(&smi_msg_inuse_count);
 	}
 	return rv;
@@ -5376,7 +5392,16 @@ static int ipmi_init_msghandler(void)
 	if (initialized)
 		goto out;
 
-	init_srcu_struct(&ipmi_interfaces_srcu);
+	rv = init_srcu_struct(&ipmi_interfaces_srcu);
+	if (rv)
+		goto out;
+
+	remove_work_wq = create_singlethread_workqueue("ipmi-msghandler-remove-wq");
+	if (!remove_work_wq) {
+		pr_err("unable to create ipmi-msghandler-remove-wq workqueue");
+		rv = -ENOMEM;
+		goto out_wq;
+	}
 
 	timer_setup(&ipmi_timer, ipmi_timeout, 0);
 	mod_timer(&ipmi_timer, jiffies + IPMI_TIMEOUT_JIFFIES);
@@ -5385,6 +5410,9 @@ static int ipmi_init_msghandler(void)
 
 	initialized = true;
 
+out_wq:
+	if (rv)
+		cleanup_srcu_struct(&ipmi_interfaces_srcu);
 out:
 	mutex_unlock(&ipmi_interfaces_mutex);
 	return rv;
@@ -5408,6 +5436,8 @@ static void __exit cleanup_ipmi(void)
 	int count;
 
 	if (initialized) {
+		destroy_workqueue(remove_work_wq);
+
 		atomic_notifier_chain_unregister(&panic_notifier_list,
 						 &panic_block);
 
diff --git a/drivers/char/ipmi/ipmi_ssif.c b/drivers/char/ipmi/ipmi_ssif.c
index 0c62e578749e..48aab77abebf 100644
--- a/drivers/char/ipmi/ipmi_ssif.c
+++ b/drivers/char/ipmi/ipmi_ssif.c
@@ -1659,6 +1659,9 @@ static int ssif_probe(struct i2c_client *client, const struct i2c_device_id *id)
 		}
 	}
 
+	ssif_info->client = client;
+	i2c_set_clientdata(client, ssif_info);
+
 	rv = ssif_check_and_remove(client, ssif_info);
 	/* If rv is 0 and addr source is not SI_ACPI, continue probing */
 	if (!rv && ssif_info->addr_source == SI_ACPI) {
@@ -1679,9 +1682,6 @@ static int ssif_probe(struct i2c_client *client, const struct i2c_device_id *id)
 		ipmi_addr_src_to_str(ssif_info->addr_source),
 		client->addr, client->adapter->name, slave_addr);
 
-	ssif_info->client = client;
-	i2c_set_clientdata(client, ssif_info);
-
 	/* Now check for system interface capabilities */
 	msg[0] = IPMI_NETFN_APP_REQUEST << 2;
 	msg[1] = IPMI_GET_SYSTEM_INTERFACE_CAPABILITIES_CMD;
@@ -1881,6 +1881,7 @@ static int ssif_probe(struct i2c_client *client, const struct i2c_device_id *id)
 
 		dev_err(&ssif_info->client->dev,
 			"Unable to start IPMI SSIF: %d\n", rv);
+		i2c_set_clientdata(client, NULL);
 		kfree(ssif_info);
 	}
 	kfree(resp);
diff --git a/drivers/clk/actions/owl-factor.c b/drivers/clk/actions/owl-factor.c
index f15e2621fa18..64f316cf7cfc 100644
--- a/drivers/clk/actions/owl-factor.c
+++ b/drivers/clk/actions/owl-factor.c
@@ -10,7 +10,6 @@
 
 #include <linux/clk-provider.h>
 #include <linux/regmap.h>
-#include <linux/slab.h>
 
 #include "owl-factor.h"
 
diff --git a/drivers/clk/clk-ast2600.c b/drivers/clk/clk-ast2600.c
index bc3be5f3eae1..24dab2312bc6 100644
--- a/drivers/clk/clk-ast2600.c
+++ b/drivers/clk/clk-ast2600.c
@@ -51,6 +51,8 @@ static DEFINE_SPINLOCK(aspeed_g6_clk_lock);
 static struct clk_hw_onecell_data *aspeed_g6_clk_data;
 
 static void __iomem *scu_g6_base;
+/* AST2600 revision: A0, A1, A2, etc */
+static u8 soc_rev;
 
 /*
  * Clocks marked with CLK_IS_CRITICAL:
@@ -191,9 +193,8 @@ static struct clk_hw *ast2600_calc_pll(const char *name, u32 val)
 static struct clk_hw *ast2600_calc_apll(const char *name, u32 val)
 {
 	unsigned int mult, div;
-	u32 chip_id = readl(scu_g6_base + ASPEED_G6_SILICON_REV);
 
-	if (((chip_id & CHIP_REVISION_ID) >> 16) >= 2) {
+	if (soc_rev >= 2) {
 		if (val & BIT(24)) {
 			/* Pass through mode */
 			mult = div = 1;
@@ -707,7 +708,7 @@ static const u32 ast2600_a1_axi_ahb200_tbl[] = {
 static void __init aspeed_g6_cc(struct regmap *map)
 {
 	struct clk_hw *hw;
-	u32 val, div, divbits, chip_id, axi_div, ahb_div;
+	u32 val, div, divbits, axi_div, ahb_div;
 
 	clk_hw_register_fixed_rate(NULL, "clkin", NULL, 0, 25000000);
 
@@ -738,8 +739,7 @@ static void __init aspeed_g6_cc(struct regmap *map)
 		axi_div = 2;
 
 	divbits = (val >> 11) & 0x3;
-	regmap_read(map, ASPEED_G6_SILICON_REV, &chip_id);
-	if (chip_id & BIT(16)) {
+	if (soc_rev >= 1) {
 		if (!divbits) {
 			ahb_div = ast2600_a1_axi_ahb200_tbl[(val >> 8) & 0x3];
 			if (val & BIT(16))
@@ -784,6 +784,8 @@ static void __init aspeed_g6_cc_init(struct device_node *np)
 	if (!scu_g6_base)
 		return;
 
+	soc_rev = (readl(scu_g6_base + ASPEED_G6_SILICON_REV) & CHIP_REVISION_ID) >> 16;
+
 	aspeed_g6_clk_data = kzalloc(struct_size(aspeed_g6_clk_data, hws,
 				      ASPEED_G6_NUM_CLKS), GFP_KERNEL);
 	if (!aspeed_g6_clk_data)
diff --git a/drivers/clk/clk-composite.c b/drivers/clk/clk-composite.c
index c04ae0e7e4b4..b9c5f904f535 100644
--- a/drivers/clk/clk-composite.c
+++ b/drivers/clk/clk-composite.c
@@ -97,6 +97,7 @@ static int clk_composite_determine_rate(struct clk_hw *hw,
 				return ret;
 
 			req->rate = tmp_req.rate;
+			req->best_parent_hw = tmp_req.best_parent_hw;
 			req->best_parent_rate = tmp_req.best_parent_rate;
 
 			return 0;
diff --git a/drivers/clk/clk-si5351.c b/drivers/clk/clk-si5351.c
index 57e4597cdf4c..93fa8c9e11be 100644
--- a/drivers/clk/clk-si5351.c
+++ b/drivers/clk/clk-si5351.c
@@ -1,15 +1,15 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * clk-si5351.c: Silicon Laboratories Si5351A/B/C I2C Clock Generator
+ * clk-si5351.c: Skyworks / Silicon Labs Si5351A/B/C I2C Clock Generator
  *
  * Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
  * Rabeeh Khoury <rabeeh@solid-run.com>
  *
  * References:
  * [1] "Si5351A/B/C Data Sheet"
- *     https://www.silabs.com/Support%20Documents/TechnicalDocs/Si5351.pdf
- * [2] "Manually Generating an Si5351 Register Map"
- *     https://www.silabs.com/Support%20Documents/TechnicalDocs/AN619.pdf
+ *     https://www.skyworksinc.com/-/media/Skyworks/SL/documents/public/data-sheets/Si5351-B.pdf
+ * [2] "AN619: Manually Generating an Si5351 Register Map"
+ *     https://www.skyworksinc.com/-/media/Skyworks/SL/documents/public/application-notes/AN619.pdf
  */
 
 #include <linux/module.h>
diff --git a/drivers/clk/clk-si5351.h b/drivers/clk/clk-si5351.h
index 73dc8effc519..e9e2bfdaaedf 100644
--- a/drivers/clk/clk-si5351.h
+++ b/drivers/clk/clk-si5351.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
- * clk-si5351.h: Silicon Laboratories Si5351A/B/C I2C Clock Generator
+ * clk-si5351.h: Skyworks / Silicon Labs Si5351A/B/C I2C Clock Generator
  *
  * Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
  * Rabeeh Khoury <rabeeh@solid-run.com>
diff --git a/drivers/clk/clk-versaclock5.c b/drivers/clk/clk-versaclock5.c
index c6d3b1ab3d55..e7be3e54b9be 100644
--- a/drivers/clk/clk-versaclock5.c
+++ b/drivers/clk/clk-versaclock5.c
@@ -905,7 +905,7 @@ output_error:
 
 static const struct of_device_id clk_vc5_of_match[];
 
-static int vc5_probe(struct i2c_client *client, const struct i2c_device_id *id)
+static int vc5_probe(struct i2c_client *client)
 {
 	unsigned int oe, sd, src_mask = 0, src_val = 0;
 	struct vc5_driver_data *vc5;
@@ -1244,7 +1244,7 @@ static struct i2c_driver vc5_driver = {
 		.pm	= &vc5_pm_ops,
 		.of_match_table = clk_vc5_of_match,
 	},
-	.probe		= vc5_probe,
+	.probe_new	= vc5_probe,
 	.remove		= vc5_remove,
 	.id_table	= vc5_id,
 };
diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index f467d63bbf1e..566ee2c78709 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -3418,6 +3418,14 @@ static int __clk_core_init(struct clk_core *core)
 
 	clk_prepare_lock();
 
+	/*
+	 * Set hw->core after grabbing the prepare_lock to synchronize with
+	 * callers of clk_core_fill_parent_index() where we treat hw->core
+	 * being NULL as the clk not being registered yet. This is crucial so
+	 * that clks aren't parented until their parent is fully registered.
+	 */
+	core->hw->core = core;
+
 	ret = clk_pm_runtime_get(core);
 	if (ret)
 		goto unlock;
@@ -3582,8 +3590,10 @@ static int __clk_core_init(struct clk_core *core)
 out:
 	clk_pm_runtime_put(core);
 unlock:
-	if (ret)
+	if (ret) {
 		hlist_del_init(&core->child_node);
+		core->hw->core = NULL;
+	}
 
 	clk_prepare_unlock();
 
@@ -3847,7 +3857,6 @@ __clk_register(struct device *dev, struct device_node *np, struct clk_hw *hw)
 	core->num_parents = init->num_parents;
 	core->min_rate = 0;
 	core->max_rate = ULONG_MAX;
-	hw->core = core;
 
 	ret = clk_core_populate_parent_map(core, init);
 	if (ret)
@@ -3865,7 +3874,7 @@ __clk_register(struct device *dev, struct device_node *np, struct clk_hw *hw)
 		goto fail_create_clk;
 	}
 
-	clk_core_link_consumer(hw->core, hw->clk);
+	clk_core_link_consumer(core, hw->clk);
 
 	ret = __clk_core_init(core);
 	if (!ret)
diff --git a/drivers/clk/imx/clk-imx8qxp-lpcg.c b/drivers/clk/imx/clk-imx8qxp-lpcg.c
index d3e905cf867d..b23758083ce5 100644
--- a/drivers/clk/imx/clk-imx8qxp-lpcg.c
+++ b/drivers/clk/imx/clk-imx8qxp-lpcg.c
@@ -370,7 +370,7 @@ static struct platform_driver imx8qxp_lpcg_clk_driver = {
 	.probe = imx8qxp_lpcg_clk_probe,
 };
 
-builtin_platform_driver(imx8qxp_lpcg_clk_driver);
+module_platform_driver(imx8qxp_lpcg_clk_driver);
 
 MODULE_AUTHOR("Aisheng Dong <aisheng.dong@nxp.com>");
 MODULE_DESCRIPTION("NXP i.MX8QXP LPCG clock driver");
diff --git a/drivers/clk/imx/clk-imx8qxp.c b/drivers/clk/imx/clk-imx8qxp.c
index c53a688d8ccc..40a2efb1329b 100644
--- a/drivers/clk/imx/clk-imx8qxp.c
+++ b/drivers/clk/imx/clk-imx8qxp.c
@@ -308,7 +308,7 @@ static struct platform_driver imx8qxp_clk_driver = {
 	},
 	.probe = imx8qxp_clk_probe,
 };
-builtin_platform_driver(imx8qxp_clk_driver);
+module_platform_driver(imx8qxp_clk_driver);
 
 MODULE_AUTHOR("Aisheng Dong <aisheng.dong@nxp.com>");
 MODULE_DESCRIPTION("NXP i.MX8QXP clock driver");
diff --git a/drivers/clk/imx/clk.h b/drivers/clk/imx/clk.h
index 819949973db1..7d220a01de1f 100644
--- a/drivers/clk/imx/clk.h
+++ b/drivers/clk/imx/clk.h
@@ -391,11 +391,11 @@ struct clk_hw *__imx8m_clk_hw_composite(const char *name,
 
 #define imx8m_clk_hw_composite(name, parent_names, reg) \
 	_imx8m_clk_hw_composite(name, parent_names, reg, \
-			IMX_COMPOSITE_CORE, IMX_COMPOSITE_CLK_FLAGS_DEFAULT)
+			0, IMX_COMPOSITE_CLK_FLAGS_DEFAULT)
 
 #define imx8m_clk_hw_composite_critical(name, parent_names, reg) \
 	_imx8m_clk_hw_composite(name, parent_names, reg, \
-			IMX_COMPOSITE_CORE, IMX_COMPOSITE_CLK_FLAGS_CRITICAL)
+			0, IMX_COMPOSITE_CLK_FLAGS_CRITICAL)
 
 #define imx8m_clk_hw_composite_bus(name, parent_names, reg)	\
 	_imx8m_clk_hw_composite(name, parent_names, reg, \
diff --git a/drivers/clk/ingenic/cgu.c b/drivers/clk/ingenic/cgu.c
index 266c7595d330..af31633a8862 100644
--- a/drivers/clk/ingenic/cgu.c
+++ b/drivers/clk/ingenic/cgu.c
@@ -453,15 +453,15 @@ ingenic_clk_calc_div(struct clk_hw *hw,
 	}
 
 	/* Impose hardware constraints */
-	div = min_t(unsigned, div, 1 << clk_info->div.bits);
-	div = max_t(unsigned, div, 1);
+	div = clamp_t(unsigned int, div, clk_info->div.div,
+		      clk_info->div.div << clk_info->div.bits);
 
 	/*
 	 * If the divider value itself must be divided before being written to
 	 * the divider register, we must ensure we don't have any bits set that
 	 * would be lost as a result of doing so.
 	 */
-	div /= clk_info->div.div;
+	div = DIV_ROUND_UP(div, clk_info->div.div);
 	div *= clk_info->div.div;
 
 	return div;
diff --git a/drivers/clk/ingenic/jz4725b-cgu.c b/drivers/clk/ingenic/jz4725b-cgu.c
index 5154b0cf8ad6..744d136b721b 100644
--- a/drivers/clk/ingenic/jz4725b-cgu.c
+++ b/drivers/clk/ingenic/jz4725b-cgu.c
@@ -10,7 +10,7 @@
 #include <linux/delay.h>
 #include <linux/of.h>
 
-#include <dt-bindings/clock/jz4725b-cgu.h>
+#include <dt-bindings/clock/ingenic,jz4725b-cgu.h>
 
 #include "cgu.h"
 #include "pm.h"
diff --git a/drivers/clk/ingenic/jz4740-cgu.c b/drivers/clk/ingenic/jz4740-cgu.c
index cd878f08aca3..43ffb62c42bb 100644
--- a/drivers/clk/ingenic/jz4740-cgu.c
+++ b/drivers/clk/ingenic/jz4740-cgu.c
@@ -11,7 +11,7 @@
 #include <linux/io.h>
 #include <linux/of.h>
 
-#include <dt-bindings/clock/jz4740-cgu.h>
+#include <dt-bindings/clock/ingenic,jz4740-cgu.h>
 
 #include "cgu.h"
 #include "pm.h"
diff --git a/drivers/clk/ingenic/jz4760-cgu.c b/drivers/clk/ingenic/jz4760-cgu.c
index 14483797a4db..080d492ac95c 100644
--- a/drivers/clk/ingenic/jz4760-cgu.c
+++ b/drivers/clk/ingenic/jz4760-cgu.c
@@ -12,7 +12,7 @@
 
 #include <linux/clk.h>
 
-#include <dt-bindings/clock/jz4760-cgu.h>
+#include <dt-bindings/clock/ingenic,jz4760-cgu.h>
 
 #include "cgu.h"
 #include "pm.h"
diff --git a/drivers/clk/ingenic/jz4770-cgu.c b/drivers/clk/ingenic/jz4770-cgu.c
index 2321742b3471..8c6c1208f462 100644
--- a/drivers/clk/ingenic/jz4770-cgu.c
+++ b/drivers/clk/ingenic/jz4770-cgu.c
@@ -10,7 +10,7 @@
 #include <linux/io.h>
 #include <linux/of.h>
 
-#include <dt-bindings/clock/jz4770-cgu.h>
+#include <dt-bindings/clock/ingenic,jz4770-cgu.h>
 
 #include "cgu.h"
 #include "pm.h"
diff --git a/drivers/clk/ingenic/jz4780-cgu.c b/drivers/clk/ingenic/jz4780-cgu.c
index 0268d23ebe2e..e357c228e0f1 100644
--- a/drivers/clk/ingenic/jz4780-cgu.c
+++ b/drivers/clk/ingenic/jz4780-cgu.c
@@ -13,7 +13,7 @@
 #include <linux/iopoll.h>
 #include <linux/of.h>
 
-#include <dt-bindings/clock/jz4780-cgu.h>
+#include <dt-bindings/clock/ingenic,jz4780-cgu.h>
 
 #include "cgu.h"
 #include "pm.h"
diff --git a/drivers/clk/ingenic/x1000-cgu.c b/drivers/clk/ingenic/x1000-cgu.c
index 9aa20b52e1c3..3c4d5a77ccbd 100644
--- a/drivers/clk/ingenic/x1000-cgu.c
+++ b/drivers/clk/ingenic/x1000-cgu.c
@@ -9,7 +9,7 @@
 #include <linux/io.h>
 #include <linux/of.h>
 
-#include <dt-bindings/clock/x1000-cgu.h>
+#include <dt-bindings/clock/ingenic,x1000-cgu.h>
 
 #include "cgu.h"
 #include "pm.h"
diff --git a/drivers/clk/ingenic/x1830-cgu.c b/drivers/clk/ingenic/x1830-cgu.c
index 950aee243364..e01ec2dc7a1a 100644
--- a/drivers/clk/ingenic/x1830-cgu.c
+++ b/drivers/clk/ingenic/x1830-cgu.c
@@ -9,7 +9,7 @@
 #include <linux/io.h>
 #include <linux/of.h>
 
-#include <dt-bindings/clock/x1830-cgu.h>
+#include <dt-bindings/clock/ingenic,x1830-cgu.h>
 
 #include "cgu.h"
 #include "pm.h"
diff --git a/drivers/clk/mediatek/clk-mt8195-imp_iic_wrap.c b/drivers/clk/mediatek/clk-mt8195-imp_iic_wrap.c
index 0e2ac0a30aa0..4ab312eb26a5 100644
--- a/drivers/clk/mediatek/clk-mt8195-imp_iic_wrap.c
+++ b/drivers/clk/mediatek/clk-mt8195-imp_iic_wrap.c
@@ -10,8 +10,6 @@
 #include <linux/clk-provider.h>
 #include <linux/platform_device.h>
 
-#include <dt-bindings/clock/mt8195-clk.h>
-
 static const struct mtk_gate_regs imp_iic_wrap_cg_regs = {
 	.set_ofs = 0xe08,
 	.clr_ofs = 0xe04,
diff --git a/drivers/clk/qcom/clk-alpha-pll.c b/drivers/clk/qcom/clk-alpha-pll.c
index eaedcceb766f..8f65b9bdafce 100644
--- a/drivers/clk/qcom/clk-alpha-pll.c
+++ b/drivers/clk/qcom/clk-alpha-pll.c
@@ -1429,6 +1429,15 @@ EXPORT_SYMBOL_GPL(clk_alpha_pll_postdiv_fabia_ops);
 void clk_trion_pll_configure(struct clk_alpha_pll *pll, struct regmap *regmap,
 			     const struct alpha_pll_config *config)
 {
+	/*
+	 * If the bootloader left the PLL enabled it's likely that there are
+	 * RCGs that will lock up if we disable the PLL below.
+	 */
+	if (trion_pll_is_enabled(pll, regmap)) {
+		pr_debug("Trion PLL is already enabled, skipping configuration\n");
+		return;
+	}
+
 	clk_alpha_pll_write_config(regmap, PLL_L_VAL(pll), config->l);
 	regmap_write(regmap, PLL_CAL_L_VAL(pll), TRION_PLL_CAL_VAL);
 	clk_alpha_pll_write_config(regmap, PLL_ALPHA_VAL(pll), config->alpha);
diff --git a/drivers/clk/qcom/clk-regmap-mux.c b/drivers/clk/qcom/clk-regmap-mux.c
index b2d00b451963..45d9cca28064 100644
--- a/drivers/clk/qcom/clk-regmap-mux.c
+++ b/drivers/clk/qcom/clk-regmap-mux.c
@@ -28,7 +28,7 @@ static u8 mux_get_parent(struct clk_hw *hw)
 	val &= mask;
 
 	if (mux->parent_map)
-		return qcom_find_src_index(hw, mux->parent_map, val);
+		return qcom_find_cfg_index(hw, mux->parent_map, val);
 
 	return val;
 }
diff --git a/drivers/clk/qcom/common.c b/drivers/clk/qcom/common.c
index 0932e019dd12..75f09e6e057e 100644
--- a/drivers/clk/qcom/common.c
+++ b/drivers/clk/qcom/common.c
@@ -69,6 +69,18 @@ int qcom_find_src_index(struct clk_hw *hw, const struct parent_map *map, u8 src)
 }
 EXPORT_SYMBOL_GPL(qcom_find_src_index);
 
+int qcom_find_cfg_index(struct clk_hw *hw, const struct parent_map *map, u8 cfg)
+{
+	int i, num_parents = clk_hw_get_num_parents(hw);
+
+	for (i = 0; i < num_parents; i++)
+		if (cfg == map[i].cfg)
+			return i;
+
+	return -ENOENT;
+}
+EXPORT_SYMBOL_GPL(qcom_find_cfg_index);
+
 struct regmap *
 qcom_cc_map(struct platform_device *pdev, const struct qcom_cc_desc *desc)
 {
diff --git a/drivers/clk/qcom/common.h b/drivers/clk/qcom/common.h
index bb39a7e106d8..9c8f7b798d9f 100644
--- a/drivers/clk/qcom/common.h
+++ b/drivers/clk/qcom/common.h
@@ -49,6 +49,8 @@ extern void
 qcom_pll_set_fsm_mode(struct regmap *m, u32 reg, u8 bias_count, u8 lock_count);
 extern int qcom_find_src_index(struct clk_hw *hw, const struct parent_map *map,
 			       u8 src);
+extern int qcom_find_cfg_index(struct clk_hw *hw, const struct parent_map *map,
+			       u8 cfg);
 
 extern int qcom_cc_register_board_clk(struct device *dev, const char *path,
 				      const char *name, unsigned long rate);
diff --git a/drivers/clk/qcom/gcc-msm8996.c b/drivers/clk/qcom/gcc-msm8996.c
index 3c3a7ff04562..9b1674b28d45 100644
--- a/drivers/clk/qcom/gcc-msm8996.c
+++ b/drivers/clk/qcom/gcc-msm8996.c
@@ -2937,20 +2937,6 @@ static struct clk_branch gcc_smmu_aggre0_ahb_clk = {
 	},
 };
 
-static struct clk_branch gcc_aggre1_pnoc_ahb_clk = {
-	.halt_reg = 0x82014,
-	.clkr = {
-		.enable_reg = 0x82014,
-		.enable_mask = BIT(0),
-		.hw.init = &(struct clk_init_data){
-			.name = "gcc_aggre1_pnoc_ahb_clk",
-			.parent_names = (const char *[]){ "periph_noc_clk_src" },
-			.num_parents = 1,
-			.ops = &clk_branch2_ops,
-		},
-	},
-};
-
 static struct clk_branch gcc_aggre2_ufs_axi_clk = {
 	.halt_reg = 0x83014,
 	.clkr = {
@@ -3474,7 +3460,6 @@ static struct clk_regmap *gcc_msm8996_clocks[] = {
 	[GCC_AGGRE0_CNOC_AHB_CLK] = &gcc_aggre0_cnoc_ahb_clk.clkr,
 	[GCC_SMMU_AGGRE0_AXI_CLK] = &gcc_smmu_aggre0_axi_clk.clkr,
 	[GCC_SMMU_AGGRE0_AHB_CLK] = &gcc_smmu_aggre0_ahb_clk.clkr,
-	[GCC_AGGRE1_PNOC_AHB_CLK] = &gcc_aggre1_pnoc_ahb_clk.clkr,
 	[GCC_AGGRE2_UFS_AXI_CLK] = &gcc_aggre2_ufs_axi_clk.clkr,
 	[GCC_AGGRE2_USB3_AXI_CLK] = &gcc_aggre2_usb3_axi_clk.clkr,
 	[GCC_QSPI_AHB_CLK] = &gcc_qspi_ahb_clk.clkr,
diff --git a/drivers/clk/qcom/gcc-sm6125.c b/drivers/clk/qcom/gcc-sm6125.c
index 543cfab7561f..431b55bb0d2f 100644
--- a/drivers/clk/qcom/gcc-sm6125.c
+++ b/drivers/clk/qcom/gcc-sm6125.c
@@ -1121,7 +1121,7 @@ static struct clk_rcg2 gcc_sdcc1_apps_clk_src = {
 		.name = "gcc_sdcc1_apps_clk_src",
 		.parent_data = gcc_parent_data_1,
 		.num_parents = ARRAY_SIZE(gcc_parent_data_1),
-		.ops = &clk_rcg2_ops,
+		.ops = &clk_rcg2_floor_ops,
 	},
 };
 
@@ -1143,7 +1143,7 @@ static struct clk_rcg2 gcc_sdcc1_ice_core_clk_src = {
 		.name = "gcc_sdcc1_ice_core_clk_src",
 		.parent_data = gcc_parent_data_0,
 		.num_parents = ARRAY_SIZE(gcc_parent_data_0),
-		.ops = &clk_rcg2_floor_ops,
+		.ops = &clk_rcg2_ops,
 	},
 };
 
diff --git a/drivers/clk/rockchip/Kconfig b/drivers/clk/rockchip/Kconfig
index 2dfd6a383393..3067bdb6e119 100644
--- a/drivers/clk/rockchip/Kconfig
+++ b/drivers/clk/rockchip/Kconfig
@@ -80,14 +80,14 @@ config CLK_RK3368
 	  Build the driver for RK3368 Clock Driver.
 
 config CLK_RK3399
-	tristate "Rockchip RK3399 clock controller support"
+	bool "Rockchip RK3399 clock controller support"
 	depends on ARM64 || COMPILE_TEST
 	default y
 	help
 	  Build the driver for RK3399 Clock Driver.
 
 config CLK_RK3568
-	tristate "Rockchip RK3568 clock controller support"
+	bool "Rockchip RK3568 clock controller support"
 	depends on ARM64 || COMPILE_TEST
 	default y
 	help
diff --git a/drivers/clk/rockchip/clk-rk3399.c b/drivers/clk/rockchip/clk-rk3399.c
index 7924598747b6..306910a3a0d3 100644
--- a/drivers/clk/rockchip/clk-rk3399.c
+++ b/drivers/clk/rockchip/clk-rk3399.c
@@ -1630,7 +1630,6 @@ static const struct of_device_id clk_rk3399_match_table[] = {
 	},
 	{ }
 };
-MODULE_DEVICE_TABLE(of, clk_rk3399_match_table);
 
 static int __init clk_rk3399_probe(struct platform_device *pdev)
 {
@@ -1656,7 +1655,4 @@ static struct platform_driver clk_rk3399_driver = {
 		.suppress_bind_attrs = true,
 	},
 };
-module_platform_driver_probe(clk_rk3399_driver, clk_rk3399_probe);
-
-MODULE_DESCRIPTION("Rockchip RK3399 Clock Driver");
-MODULE_LICENSE("GPL");
+builtin_platform_driver_probe(clk_rk3399_driver, clk_rk3399_probe);
diff --git a/drivers/clk/rockchip/clk-rk3568.c b/drivers/clk/rockchip/clk-rk3568.c
index 939e7079c334..69a9e8069a48 100644
--- a/drivers/clk/rockchip/clk-rk3568.c
+++ b/drivers/clk/rockchip/clk-rk3568.c
@@ -1693,7 +1693,6 @@ static const struct of_device_id clk_rk3568_match_table[] = {
 	},
 	{ }
 };
-MODULE_DEVICE_TABLE(of, clk_rk3568_match_table);
 
 static int __init clk_rk3568_probe(struct platform_device *pdev)
 {
@@ -1719,7 +1718,4 @@ static struct platform_driver clk_rk3568_driver = {
 		.suppress_bind_attrs = true,
 	},
 };
-module_platform_driver_probe(clk_rk3568_driver, clk_rk3568_probe);
-
-MODULE_DESCRIPTION("Rockchip RK3568 Clock Driver");
-MODULE_LICENSE("GPL");
+builtin_platform_driver_probe(clk_rk3568_driver, clk_rk3568_probe);
diff --git a/drivers/clk/uniphier/clk-uniphier-core.c b/drivers/clk/uniphier/clk-uniphier-core.c
index 12380236d7ab..46c66fac48e6 100644
--- a/drivers/clk/uniphier/clk-uniphier-core.c
+++ b/drivers/clk/uniphier/clk-uniphier-core.c
@@ -132,6 +132,10 @@ static const struct of_device_id uniphier_clk_match[] = {
 		.compatible = "socionext,uniphier-pxs3-clock",
 		.data = uniphier_pxs3_sys_clk_data,
 	},
+	{
+		.compatible = "socionext,uniphier-nx1-clock",
+		.data = uniphier_nx1_sys_clk_data,
+	},
 	/* Media I/O clock, SD clock */
 	{
 		.compatible = "socionext,uniphier-ld4-mio-clock",
@@ -165,6 +169,10 @@ static const struct of_device_id uniphier_clk_match[] = {
 		.compatible = "socionext,uniphier-pxs3-sd-clock",
 		.data = uniphier_pro5_sd_clk_data,
 	},
+	{
+		.compatible = "socionext,uniphier-nx1-sd-clock",
+		.data = uniphier_pro5_sd_clk_data,
+	},
 	/* Peripheral clock */
 	{
 		.compatible = "socionext,uniphier-ld4-peri-clock",
@@ -198,6 +206,15 @@ static const struct of_device_id uniphier_clk_match[] = {
 		.compatible = "socionext,uniphier-pxs3-peri-clock",
 		.data = uniphier_pro4_peri_clk_data,
 	},
+	{
+		.compatible = "socionext,uniphier-nx1-peri-clock",
+		.data = uniphier_pro4_peri_clk_data,
+	},
+	/* SoC-glue clock */
+	{
+		.compatible = "socionext,uniphier-pro4-sg-clock",
+		.data = uniphier_pro4_sg_clk_data,
+	},
 	{ /* sentinel */ }
 };
 
diff --git a/drivers/clk/uniphier/clk-uniphier-sys.c b/drivers/clk/uniphier/clk-uniphier-sys.c
index 32b301724183..0180470b24db 100644
--- a/drivers/clk/uniphier/clk-uniphier-sys.c
+++ b/drivers/clk/uniphier/clk-uniphier-sys.c
@@ -20,6 +20,10 @@
 	UNIPHIER_CLK_FACTOR("sd-200m", -1, "spll", 1, 10),		\
 	UNIPHIER_CLK_FACTOR("sd-133m", -1, "spll", 1, 15)
 
+#define UNIPHIER_NX1_SYS_CLK_SD						\
+	UNIPHIER_CLK_FACTOR("sd-200m", -1, "spll", 1, 4),		\
+	UNIPHIER_CLK_FACTOR("sd-133m", -1, "spll", 1, 6)
+
 #define UNIPHIER_LD4_SYS_CLK_NAND(idx)					\
 	UNIPHIER_CLK_FACTOR("nand-50m", -1, "spll", 1, 32),		\
 	UNIPHIER_CLK_GATE("nand", (idx), "nand-50m", 0x2104, 2)
@@ -288,6 +292,8 @@ const struct uniphier_clk_data uniphier_pxs3_sys_clk_data[] = {
 	UNIPHIER_CLK_GATE("sata0", 28, NULL, 0x210c, 7),
 	UNIPHIER_CLK_GATE("sata1", 29, NULL, 0x210c, 8),
 	UNIPHIER_CLK_GATE("sata-phy", 30, NULL, 0x210c, 21),
+	UNIPHIER_LD11_SYS_CLK_AIO(40),
+	UNIPHIER_LD11_SYS_CLK_EXIV(42),
 	/* CPU gears */
 	UNIPHIER_CLK_DIV4("cpll", 2, 3, 4, 8),
 	UNIPHIER_CLK_DIV4("spll", 2, 3, 4, 8),
@@ -300,3 +306,44 @@ const struct uniphier_clk_data uniphier_pxs3_sys_clk_data[] = {
 			     "spll/4", "spll/8", "s2pll/4", "s2pll/8"),
 	{ /* sentinel */ }
 };
+
+const struct uniphier_clk_data uniphier_nx1_sys_clk_data[] = {
+	UNIPHIER_CLK_FACTOR("cpll", -1, "ref", 100, 1),		/* ARM: 2500 MHz */
+	UNIPHIER_CLK_FACTOR("spll", -1, "ref", 32, 1),		/* 800 MHz */
+	UNIPHIER_CLK_FACTOR("uart", 0, "spll", 1, 6),
+	UNIPHIER_CLK_FACTOR("i2c", 1, "spll", 1, 16),
+	UNIPHIER_NX1_SYS_CLK_SD,
+	UNIPHIER_CLK_GATE("emmc", 4, NULL, 0x2108, 8),
+	UNIPHIER_CLK_GATE("ether", 6, NULL, 0x210c, 0),
+	UNIPHIER_CLK_GATE("usb30-0", 12, NULL, 0x210c, 16),	/* =GIO */
+	UNIPHIER_CLK_GATE("usb30-1", 13, NULL, 0x210c, 20),	/* =GIO1P */
+	UNIPHIER_CLK_GATE("usb30-hsphy0", 16, NULL, 0x210c, 24),
+	UNIPHIER_CLK_GATE("usb30-ssphy0", 17, NULL, 0x210c, 25),
+	UNIPHIER_CLK_GATE("usb30-ssphy1", 18, NULL, 0x210c, 26),
+	UNIPHIER_CLK_GATE("pcie", 24, NULL, 0x210c, 8),
+	UNIPHIER_CLK_GATE("voc", 52, NULL, 0x2110, 0),
+	UNIPHIER_CLK_GATE("hdmitx", 58, NULL, 0x2110, 8),
+	/* CPU gears */
+	UNIPHIER_CLK_DIV5("cpll", 2, 4, 8, 16, 32),
+	UNIPHIER_CLK_CPUGEAR("cpu-ca53", 33, 0x8080, 0xf, 5,
+			     "cpll/2", "cpll/4", "cpll/8", "cpll/16",
+			     "cpll/32"),
+	{ /* sentinel */ }
+};
+
+const struct uniphier_clk_data uniphier_pro4_sg_clk_data[] = {
+	UNIPHIER_CLK_DIV("gpll", 4),
+	{
+		.name = "sata-ref",
+		.type = UNIPHIER_CLK_TYPE_MUX,
+		.idx = 0,
+		.data.mux = {
+			.parent_names = { "gpll/4", "ref", },
+			.num_parents = 2,
+			.reg = 0x1a28,
+			.masks = { 0x1, 0x1, },
+			.vals  = { 0x0, 0x1, },
+		},
+	},
+	{ /* sentinel */ }
+};
diff --git a/drivers/clk/uniphier/clk-uniphier.h b/drivers/clk/uniphier/clk-uniphier.h
index 9e30362e55e1..dea0c7829aee 100644
--- a/drivers/clk/uniphier/clk-uniphier.h
+++ b/drivers/clk/uniphier/clk-uniphier.h
@@ -119,6 +119,10 @@ struct uniphier_clk_data {
 	UNIPHIER_CLK_DIV2(parent, div0, div1),			\
 	UNIPHIER_CLK_DIV2(parent, div2, div3)
 
+#define UNIPHIER_CLK_DIV5(parent, div0, div1, div2, div3, div4)	\
+	UNIPHIER_CLK_DIV4(parent, div0, div1, div2, div3),	\
+	UNIPHIER_CLK_DIV(parent, div4)
+
 struct clk_hw *uniphier_clk_register_cpugear(struct device *dev,
 					     struct regmap *regmap,
 					     const char *name,
@@ -146,9 +150,11 @@ extern const struct uniphier_clk_data uniphier_pxs2_sys_clk_data[];
 extern const struct uniphier_clk_data uniphier_ld11_sys_clk_data[];
 extern const struct uniphier_clk_data uniphier_ld20_sys_clk_data[];
 extern const struct uniphier_clk_data uniphier_pxs3_sys_clk_data[];
+extern const struct uniphier_clk_data uniphier_nx1_sys_clk_data[];
 extern const struct uniphier_clk_data uniphier_ld4_mio_clk_data[];
 extern const struct uniphier_clk_data uniphier_pro5_sd_clk_data[];
 extern const struct uniphier_clk_data uniphier_ld4_peri_clk_data[];
 extern const struct uniphier_clk_data uniphier_pro4_peri_clk_data[];
+extern const struct uniphier_clk_data uniphier_pro4_sg_clk_data[];
 
 #endif /* __CLK_UNIPHIER_H__ */
diff --git a/drivers/clk/versatile/clk-icst.c b/drivers/clk/versatile/clk-icst.c
index 77fd0ecaf155..d5cb372f0901 100644
--- a/drivers/clk/versatile/clk-icst.c
+++ b/drivers/clk/versatile/clk-icst.c
@@ -484,7 +484,7 @@ static void __init of_syscon_icst_setup(struct device_node *np)
 	struct device_node *parent;
 	struct regmap *map;
 	struct clk_icst_desc icst_desc;
-	const char *name = np->name;
+	const char *name;
 	const char *parent_name;
 	struct clk *regclk;
 	enum icst_control_type ctype;
@@ -533,16 +533,18 @@ static void __init of_syscon_icst_setup(struct device_node *np)
 		icst_desc.params = &icst525_apcp_cm_params;
 		ctype = ICST_INTEGRATOR_CP_CM_MEM;
 	} else {
-		pr_err("unknown ICST clock %s\n", name);
+		pr_err("unknown ICST clock %pOF\n", np);
 		return;
 	}
 
 	/* Parent clock name is not the same as node parent */
 	parent_name = of_clk_get_parent_name(np, 0);
+	name = kasprintf(GFP_KERNEL, "%pOFP", np);
 
 	regclk = icst_clk_setup(NULL, &icst_desc, name, parent_name, map, ctype);
 	if (IS_ERR(regclk)) {
 		pr_err("error setting up syscon ICST clock %s\n", name);
+		kfree(name);
 		return;
 	}
 	of_clk_add_provider(np, of_clk_src_simple_get, regclk);
diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c
index 9a04eacc4412..1ecd52f903b8 100644
--- a/drivers/clocksource/arm_arch_timer.c
+++ b/drivers/clocksource/arm_arch_timer.c
@@ -394,8 +394,13 @@ EXPORT_SYMBOL_GPL(timer_unstable_counter_workaround);
 
 static atomic_t timer_unstable_counter_workaround_in_use = ATOMIC_INIT(0);
 
-static void erratum_set_next_event_generic(const int access, unsigned long evt,
-						struct clock_event_device *clk)
+/*
+ * Force the inlining of this function so that the register accesses
+ * can be themselves correctly inlined.
+ */
+static __always_inline
+void erratum_set_next_event_generic(const int access, unsigned long evt,
+				    struct clock_event_device *clk)
 {
 	unsigned long ctrl;
 	u64 cval;
diff --git a/drivers/clocksource/dw_apb_timer_of.c b/drivers/clocksource/dw_apb_timer_of.c
index 3819ef5b7098..3245eb0c602d 100644
--- a/drivers/clocksource/dw_apb_timer_of.c
+++ b/drivers/clocksource/dw_apb_timer_of.c
@@ -47,7 +47,7 @@ static int __init timer_get_base_and_rate(struct device_node *np,
 			pr_warn("pclk for %pOFn is present, but could not be activated\n",
 				np);
 
-	if (!of_property_read_u32(np, "clock-freq", rate) &&
+	if (!of_property_read_u32(np, "clock-freq", rate) ||
 	    !of_property_read_u32(np, "clock-frequency", rate))
 		return 0;
 
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index e338d2f010fe..096c3848fa41 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -1004,10 +1004,9 @@ static struct kobj_type ktype_cpufreq = {
 	.release	= cpufreq_sysfs_release,
 };
 
-static void add_cpu_dev_symlink(struct cpufreq_policy *policy, unsigned int cpu)
+static void add_cpu_dev_symlink(struct cpufreq_policy *policy, unsigned int cpu,
+				struct device *dev)
 {
-	struct device *dev = get_cpu_device(cpu);
-
 	if (unlikely(!dev))
 		return;
 
@@ -1296,8 +1295,9 @@ static void cpufreq_policy_free(struct cpufreq_policy *policy)
 
 	if (policy->max_freq_req) {
 		/*
-		 * CPUFREQ_CREATE_POLICY notification is sent only after
-		 * successfully adding max_freq_req request.
+		 * Remove max_freq_req after sending CPUFREQ_REMOVE_POLICY
+		 * notification, since CPUFREQ_CREATE_POLICY notification was
+		 * sent after adding max_freq_req earlier.
 		 */
 		blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
 					     CPUFREQ_REMOVE_POLICY, policy);
@@ -1391,7 +1391,7 @@ static int cpufreq_online(unsigned int cpu)
 	if (new_policy) {
 		for_each_cpu(j, policy->related_cpus) {
 			per_cpu(cpufreq_cpu_data, j) = policy;
-			add_cpu_dev_symlink(policy, j);
+			add_cpu_dev_symlink(policy, j, get_cpu_device(j));
 		}
 
 		policy->min_freq_req = kzalloc(2 * sizeof(*policy->min_freq_req),
@@ -1565,7 +1565,7 @@ static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
 	/* Create sysfs link on CPU registration */
 	policy = per_cpu(cpufreq_cpu_data, cpu);
 	if (policy)
-		add_cpu_dev_symlink(policy, cpu);
+		add_cpu_dev_symlink(policy, cpu, dev);
 
 	return 0;
 }
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 815df3daae9d..dec2a5649ac1 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -338,6 +338,8 @@ static void intel_pstste_sched_itmt_work_fn(struct work_struct *work)
 
 static DECLARE_WORK(sched_itmt_work, intel_pstste_sched_itmt_work_fn);
 
+#define CPPC_MAX_PERF	U8_MAX
+
 static void intel_pstate_set_itmt_prio(int cpu)
 {
 	struct cppc_perf_caps cppc_perf;
@@ -349,6 +351,14 @@ static void intel_pstate_set_itmt_prio(int cpu)
 		return;
 
 	/*
+	 * On some systems with overclocking enabled, CPPC.highest_perf is hardcoded to 0xff.
+	 * In this case we can't use CPPC.highest_perf to enable ITMT.
+	 * In this case we can look at MSR_HWP_CAPABILITIES bits [8:0] to decide.
+	 */
+	if (cppc_perf.highest_perf == CPPC_MAX_PERF)
+		cppc_perf.highest_perf = HWP_HIGHEST_PERF(READ_ONCE(all_cpu_data[cpu]->hwp_cap_cached));
+
+	/*
 	 * The priorities can be set regardless of whether or not
 	 * sched_set_itmt_support(true) has been called and it is valid to
 	 * update them at any time after it has been called.
@@ -1006,6 +1016,12 @@ static void intel_pstate_hwp_offline(struct cpudata *cpu)
 		 */
 		value &= ~GENMASK_ULL(31, 24);
 		value |= HWP_ENERGY_PERF_PREFERENCE(cpu->epp_cached);
+		/*
+		 * However, make sure that EPP will be set to "performance" when
+		 * the CPU is brought back online again and the "performance"
+		 * scaling algorithm is still in effect.
+		 */
+		cpu->epp_policy = CPUFREQ_POLICY_UNKNOWN;
 	}
 
 	/*
@@ -2353,6 +2369,7 @@ static const struct x86_cpu_id intel_pstate_cpu_oob_ids[] __initconst = {
 	X86_MATCH(BROADWELL_D,		core_funcs),
 	X86_MATCH(BROADWELL_X,		core_funcs),
 	X86_MATCH(SKYLAKE_X,		core_funcs),
+	X86_MATCH(ICELAKE_X,		core_funcs),
 	{}
 };
 
diff --git a/drivers/crypto/qat/qat_4xxx/adf_4xxx_hw_data.c b/drivers/crypto/qat/qat_4xxx/adf_4xxx_hw_data.c
index fa768f10635f..fd29861526d6 100644
--- a/drivers/crypto/qat/qat_4xxx/adf_4xxx_hw_data.c
+++ b/drivers/crypto/qat/qat_4xxx/adf_4xxx_hw_data.c
@@ -211,6 +211,12 @@ static u32 uof_get_ae_mask(u32 obj_num)
 	return adf_4xxx_fw_config[obj_num].ae_mask;
 }
 
+static u32 get_vf2pf_sources(void __iomem *pmisc_addr)
+{
+	/* For the moment do not report vf2pf sources */
+	return 0;
+}
+
 void adf_init_hw_data_4xxx(struct adf_hw_device_data *hw_data)
 {
 	hw_data->dev_class = &adf_4xxx_class;
@@ -254,6 +260,7 @@ void adf_init_hw_data_4xxx(struct adf_hw_device_data *hw_data)
 	hw_data->set_msix_rttable = set_msix_default_rttable;
 	hw_data->set_ssm_wdtimer = adf_gen4_set_ssm_wdtimer;
 	hw_data->enable_pfvf_comms = pfvf_comms_disabled;
+	hw_data->get_vf2pf_sources = get_vf2pf_sources;
 	hw_data->disable_iov = adf_disable_sriov;
 	hw_data->min_iov_compat_ver = ADF_PFVF_COMPAT_THIS_VERSION;
 
diff --git a/drivers/dma-buf/heaps/system_heap.c b/drivers/dma-buf/heaps/system_heap.c
index f57a39ddd063..ab7fd896d2c4 100644
--- a/drivers/dma-buf/heaps/system_heap.c
+++ b/drivers/dma-buf/heaps/system_heap.c
@@ -290,7 +290,7 @@ static void system_heap_dma_buf_release(struct dma_buf *dmabuf)
 	int i;
 
 	table = &buffer->sg_table;
-	for_each_sg(table->sgl, sg, table->nents, i) {
+	for_each_sgtable_sg(table, sg, i) {
 		struct page *page = sg_page(sg);
 
 		__free_pages(page, compound_order(page));
diff --git a/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c b/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c
index cd0d745eb071..33baf1591a49 100644
--- a/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c
+++ b/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c
@@ -373,7 +373,7 @@ static void axi_chan_block_xfer_start(struct axi_dma_chan *chan,
 				      struct axi_dma_desc *first)
 {
 	u32 priority = chan->chip->dw->hdata->priority[chan->id];
-	struct axi_dma_chan_config config;
+	struct axi_dma_chan_config config = {};
 	u32 irq_mask;
 	u8 lms = 0; /* Select AXI0 master for LLI fetching */
 
@@ -391,7 +391,7 @@ static void axi_chan_block_xfer_start(struct axi_dma_chan *chan,
 	config.tt_fc = DWAXIDMAC_TT_FC_MEM_TO_MEM_DMAC;
 	config.prior = priority;
 	config.hs_sel_dst = DWAXIDMAC_HS_SEL_HW;
-	config.hs_sel_dst = DWAXIDMAC_HS_SEL_HW;
+	config.hs_sel_src = DWAXIDMAC_HS_SEL_HW;
 	switch (chan->direction) {
 	case DMA_MEM_TO_DEV:
 		dw_axi_dma_set_byte_halfword(chan, true);
diff --git a/drivers/dma/dw-edma/dw-edma-pcie.c b/drivers/dma/dw-edma/dw-edma-pcie.c
index 198f6cd8ac1b..cee7aa231d7b 100644
--- a/drivers/dma/dw-edma/dw-edma-pcie.c
+++ b/drivers/dma/dw-edma/dw-edma-pcie.c
@@ -187,17 +187,9 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev,
 
 	/* DMA configuration */
 	err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
-	if (!err) {
+	if (err) {
 		pci_err(pdev, "DMA mask 64 set failed\n");
 		return err;
-	} else {
-		pci_err(pdev, "DMA mask 64 set failed\n");
-
-		err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
-		if (err) {
-			pci_err(pdev, "DMA mask 32 set failed\n");
-			return err;
-		}
 	}
 
 	/* Data structure allocation */
diff --git a/drivers/dma/idxd/irq.c b/drivers/dma/idxd/irq.c
index 17f2f8a31b63..cf2c8bc4f147 100644
--- a/drivers/dma/idxd/irq.c
+++ b/drivers/dma/idxd/irq.c
@@ -137,10 +137,10 @@ halt:
 			INIT_WORK(&idxd->work, idxd_device_reinit);
 			queue_work(idxd->wq, &idxd->work);
 		} else {
-			spin_lock(&idxd->dev_lock);
 			idxd->state = IDXD_DEV_HALTED;
 			idxd_wqs_quiesce(idxd);
 			idxd_wqs_unmap_portal(idxd);
+			spin_lock(&idxd->dev_lock);
 			idxd_device_clear_state(idxd);
 			dev_err(&idxd->pdev->dev,
 				"idxd halted, need %s.\n",
diff --git a/drivers/dma/idxd/submit.c b/drivers/dma/idxd/submit.c
index de76fb4abac2..83452fbbb168 100644
--- a/drivers/dma/idxd/submit.c
+++ b/drivers/dma/idxd/submit.c
@@ -106,6 +106,7 @@ static void llist_abort_desc(struct idxd_wq *wq, struct idxd_irq_entry *ie,
 {
 	struct idxd_desc *d, *t, *found = NULL;
 	struct llist_node *head;
+	LIST_HEAD(flist);
 
 	desc->completion->status = IDXD_COMP_DESC_ABORT;
 	/*
@@ -120,7 +121,11 @@ static void llist_abort_desc(struct idxd_wq *wq, struct idxd_irq_entry *ie,
 				found = desc;
 				continue;
 			}
-			list_add_tail(&desc->list, &ie->work_list);
+
+			if (d->completion->status)
+				list_add_tail(&d->list, &flist);
+			else
+				list_add_tail(&d->list, &ie->work_list);
 		}
 	}
 
@@ -130,6 +135,17 @@ static void llist_abort_desc(struct idxd_wq *wq, struct idxd_irq_entry *ie,
 
 	if (found)
 		complete_desc(found, IDXD_COMPLETE_ABORT);
+
+	/*
+	 * complete_desc() will return desc to allocator and the desc can be
+	 * acquired by a different process and the desc->list can be modified.
+	 * Delete desc from list so the list trasversing does not get corrupted
+	 * by the other process.
+	 */
+	list_for_each_entry_safe(d, t, &flist, list) {
+		list_del_init(&d->list);
+		complete_desc(d, IDXD_COMPLETE_NORMAL);
+	}
 }
 
 int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc)
diff --git a/drivers/dma/st_fdma.c b/drivers/dma/st_fdma.c
index 962b6e05287b..d95c421877fb 100644
--- a/drivers/dma/st_fdma.c
+++ b/drivers/dma/st_fdma.c
@@ -874,4 +874,4 @@ MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("STMicroelectronics FDMA engine driver");
 MODULE_AUTHOR("Ludovic.barre <Ludovic.barre@st.com>");
 MODULE_AUTHOR("Peter Griffin <peter.griffin@linaro.org>");
-MODULE_ALIAS("platform: " DRIVER_NAME);
+MODULE_ALIAS("platform:" DRIVER_NAME);
diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c
index 041d8e32d630..6e56d1cef5ee 100644
--- a/drivers/dma/ti/k3-udma.c
+++ b/drivers/dma/ti/k3-udma.c
@@ -4534,45 +4534,60 @@ static int udma_setup_resources(struct udma_dev *ud)
 	rm_res = tisci_rm->rm_ranges[RM_RANGE_TCHAN];
 	if (IS_ERR(rm_res)) {
 		bitmap_zero(ud->tchan_map, ud->tchan_cnt);
+		irq_res.sets = 1;
 	} else {
 		bitmap_fill(ud->tchan_map, ud->tchan_cnt);
 		for (i = 0; i < rm_res->sets; i++)
 			udma_mark_resource_ranges(ud, ud->tchan_map,
 						  &rm_res->desc[i], "tchan");
+		irq_res.sets = rm_res->sets;
 	}
-	irq_res.sets = rm_res->sets;
 
 	/* rchan and matching default flow ranges */
 	rm_res = tisci_rm->rm_ranges[RM_RANGE_RCHAN];
 	if (IS_ERR(rm_res)) {
 		bitmap_zero(ud->rchan_map, ud->rchan_cnt);
+		irq_res.sets++;
 	} else {
 		bitmap_fill(ud->rchan_map, ud->rchan_cnt);
 		for (i = 0; i < rm_res->sets; i++)
 			udma_mark_resource_ranges(ud, ud->rchan_map,
 						  &rm_res->desc[i], "rchan");
+		irq_res.sets += rm_res->sets;
 	}
 
-	irq_res.sets += rm_res->sets;
 	irq_res.desc = kcalloc(irq_res.sets, sizeof(*irq_res.desc), GFP_KERNEL);
+	if (!irq_res.desc)
+		return -ENOMEM;
 	rm_res = tisci_rm->rm_ranges[RM_RANGE_TCHAN];
-	for (i = 0; i < rm_res->sets; i++) {
-		irq_res.desc[i].start = rm_res->desc[i].start;
-		irq_res.desc[i].num = rm_res->desc[i].num;
-		irq_res.desc[i].start_sec = rm_res->desc[i].start_sec;
-		irq_res.desc[i].num_sec = rm_res->desc[i].num_sec;
+	if (IS_ERR(rm_res)) {
+		irq_res.desc[0].start = 0;
+		irq_res.desc[0].num = ud->tchan_cnt;
+		i = 1;
+	} else {
+		for (i = 0; i < rm_res->sets; i++) {
+			irq_res.desc[i].start = rm_res->desc[i].start;
+			irq_res.desc[i].num = rm_res->desc[i].num;
+			irq_res.desc[i].start_sec = rm_res->desc[i].start_sec;
+			irq_res.desc[i].num_sec = rm_res->desc[i].num_sec;
+		}
 	}
 	rm_res = tisci_rm->rm_ranges[RM_RANGE_RCHAN];
-	for (j = 0; j < rm_res->sets; j++, i++) {
-		if (rm_res->desc[j].num) {
-			irq_res.desc[i].start = rm_res->desc[j].start +
-					ud->soc_data->oes.udma_rchan;
-			irq_res.desc[i].num = rm_res->desc[j].num;
-		}
-		if (rm_res->desc[j].num_sec) {
-			irq_res.desc[i].start_sec = rm_res->desc[j].start_sec +
-					ud->soc_data->oes.udma_rchan;
-			irq_res.desc[i].num_sec = rm_res->desc[j].num_sec;
+	if (IS_ERR(rm_res)) {
+		irq_res.desc[i].start = 0;
+		irq_res.desc[i].num = ud->rchan_cnt;
+	} else {
+		for (j = 0; j < rm_res->sets; j++, i++) {
+			if (rm_res->desc[j].num) {
+				irq_res.desc[i].start = rm_res->desc[j].start +
+						ud->soc_data->oes.udma_rchan;
+				irq_res.desc[i].num = rm_res->desc[j].num;
+			}
+			if (rm_res->desc[j].num_sec) {
+				irq_res.desc[i].start_sec = rm_res->desc[j].start_sec +
+						ud->soc_data->oes.udma_rchan;
+				irq_res.desc[i].num_sec = rm_res->desc[j].num_sec;
+			}
 		}
 	}
 	ret = ti_sci_inta_msi_domain_alloc_irqs(ud->dev, &irq_res);
@@ -4690,14 +4705,15 @@ static int bcdma_setup_resources(struct udma_dev *ud)
 		rm_res = tisci_rm->rm_ranges[RM_RANGE_BCHAN];
 		if (IS_ERR(rm_res)) {
 			bitmap_zero(ud->bchan_map, ud->bchan_cnt);
+			irq_res.sets++;
 		} else {
 			bitmap_fill(ud->bchan_map, ud->bchan_cnt);
 			for (i = 0; i < rm_res->sets; i++)
 				udma_mark_resource_ranges(ud, ud->bchan_map,
 							  &rm_res->desc[i],
 							  "bchan");
+			irq_res.sets += rm_res->sets;
 		}
-		irq_res.sets += rm_res->sets;
 	}
 
 	/* tchan ranges */
@@ -4705,14 +4721,15 @@ static int bcdma_setup_resources(struct udma_dev *ud)
 		rm_res = tisci_rm->rm_ranges[RM_RANGE_TCHAN];
 		if (IS_ERR(rm_res)) {
 			bitmap_zero(ud->tchan_map, ud->tchan_cnt);
+			irq_res.sets += 2;
 		} else {
 			bitmap_fill(ud->tchan_map, ud->tchan_cnt);
 			for (i = 0; i < rm_res->sets; i++)
 				udma_mark_resource_ranges(ud, ud->tchan_map,
 							  &rm_res->desc[i],
 							  "tchan");
+			irq_res.sets += rm_res->sets * 2;
 		}
-		irq_res.sets += rm_res->sets * 2;
 	}
 
 	/* rchan ranges */
@@ -4720,47 +4737,72 @@ static int bcdma_setup_resources(struct udma_dev *ud)
 		rm_res = tisci_rm->rm_ranges[RM_RANGE_RCHAN];
 		if (IS_ERR(rm_res)) {
 			bitmap_zero(ud->rchan_map, ud->rchan_cnt);
+			irq_res.sets += 2;
 		} else {
 			bitmap_fill(ud->rchan_map, ud->rchan_cnt);
 			for (i = 0; i < rm_res->sets; i++)
 				udma_mark_resource_ranges(ud, ud->rchan_map,
 							  &rm_res->desc[i],
 							  "rchan");
+			irq_res.sets += rm_res->sets * 2;
 		}
-		irq_res.sets += rm_res->sets * 2;
 	}
 
 	irq_res.desc = kcalloc(irq_res.sets, sizeof(*irq_res.desc), GFP_KERNEL);
+	if (!irq_res.desc)
+		return -ENOMEM;
 	if (ud->bchan_cnt) {
 		rm_res = tisci_rm->rm_ranges[RM_RANGE_BCHAN];
-		for (i = 0; i < rm_res->sets; i++) {
-			irq_res.desc[i].start = rm_res->desc[i].start +
-						oes->bcdma_bchan_ring;
-			irq_res.desc[i].num = rm_res->desc[i].num;
+		if (IS_ERR(rm_res)) {
+			irq_res.desc[0].start = oes->bcdma_bchan_ring;
+			irq_res.desc[0].num = ud->bchan_cnt;
+			i = 1;
+		} else {
+			for (i = 0; i < rm_res->sets; i++) {
+				irq_res.desc[i].start = rm_res->desc[i].start +
+							oes->bcdma_bchan_ring;
+				irq_res.desc[i].num = rm_res->desc[i].num;
+			}
 		}
 	}
 	if (ud->tchan_cnt) {
 		rm_res = tisci_rm->rm_ranges[RM_RANGE_TCHAN];
-		for (j = 0; j < rm_res->sets; j++, i += 2) {
-			irq_res.desc[i].start = rm_res->desc[j].start +
-						oes->bcdma_tchan_data;
-			irq_res.desc[i].num = rm_res->desc[j].num;
-
-			irq_res.desc[i + 1].start = rm_res->desc[j].start +
-						oes->bcdma_tchan_ring;
-			irq_res.desc[i + 1].num = rm_res->desc[j].num;
+		if (IS_ERR(rm_res)) {
+			irq_res.desc[i].start = oes->bcdma_tchan_data;
+			irq_res.desc[i].num = ud->tchan_cnt;
+			irq_res.desc[i + 1].start = oes->bcdma_tchan_ring;
+			irq_res.desc[i + 1].num = ud->tchan_cnt;
+			i += 2;
+		} else {
+			for (j = 0; j < rm_res->sets; j++, i += 2) {
+				irq_res.desc[i].start = rm_res->desc[j].start +
+							oes->bcdma_tchan_data;
+				irq_res.desc[i].num = rm_res->desc[j].num;
+
+				irq_res.desc[i + 1].start = rm_res->desc[j].start +
+							oes->bcdma_tchan_ring;
+				irq_res.desc[i + 1].num = rm_res->desc[j].num;
+			}
 		}
 	}
 	if (ud->rchan_cnt) {
 		rm_res = tisci_rm->rm_ranges[RM_RANGE_RCHAN];
-		for (j = 0; j < rm_res->sets; j++, i += 2) {
-			irq_res.desc[i].start = rm_res->desc[j].start +
-						oes->bcdma_rchan_data;
-			irq_res.desc[i].num = rm_res->desc[j].num;
-
-			irq_res.desc[i + 1].start = rm_res->desc[j].start +
-						oes->bcdma_rchan_ring;
-			irq_res.desc[i + 1].num = rm_res->desc[j].num;
+		if (IS_ERR(rm_res)) {
+			irq_res.desc[i].start = oes->bcdma_rchan_data;
+			irq_res.desc[i].num = ud->rchan_cnt;
+			irq_res.desc[i + 1].start = oes->bcdma_rchan_ring;
+			irq_res.desc[i + 1].num = ud->rchan_cnt;
+			i += 2;
+		} else {
+			for (j = 0; j < rm_res->sets; j++, i += 2) {
+				irq_res.desc[i].start = rm_res->desc[j].start +
+							oes->bcdma_rchan_data;
+				irq_res.desc[i].num = rm_res->desc[j].num;
+
+				irq_res.desc[i + 1].start = rm_res->desc[j].start +
+							oes->bcdma_rchan_ring;
+				irq_res.desc[i + 1].num = rm_res->desc[j].num;
+			}
 		}
 	}
 
@@ -4858,39 +4900,54 @@ static int pktdma_setup_resources(struct udma_dev *ud)
 	if (IS_ERR(rm_res)) {
 		/* all rflows are assigned exclusively to Linux */
 		bitmap_zero(ud->rflow_in_use, ud->rflow_cnt);
+		irq_res.sets = 1;
 	} else {
 		bitmap_fill(ud->rflow_in_use, ud->rflow_cnt);
 		for (i = 0; i < rm_res->sets; i++)
 			udma_mark_resource_ranges(ud, ud->rflow_in_use,
 						  &rm_res->desc[i], "rflow");
+		irq_res.sets = rm_res->sets;
 	}
-	irq_res.sets = rm_res->sets;
 
 	/* tflow ranges */
 	rm_res = tisci_rm->rm_ranges[RM_RANGE_TFLOW];
 	if (IS_ERR(rm_res)) {
 		/* all tflows are assigned exclusively to Linux */
 		bitmap_zero(ud->tflow_map, ud->tflow_cnt);
+		irq_res.sets++;
 	} else {
 		bitmap_fill(ud->tflow_map, ud->tflow_cnt);
 		for (i = 0; i < rm_res->sets; i++)
 			udma_mark_resource_ranges(ud, ud->tflow_map,
 						  &rm_res->desc[i], "tflow");
+		irq_res.sets += rm_res->sets;
 	}
-	irq_res.sets += rm_res->sets;
 
 	irq_res.desc = kcalloc(irq_res.sets, sizeof(*irq_res.desc), GFP_KERNEL);
+	if (!irq_res.desc)
+		return -ENOMEM;
 	rm_res = tisci_rm->rm_ranges[RM_RANGE_TFLOW];
-	for (i = 0; i < rm_res->sets; i++) {
-		irq_res.desc[i].start = rm_res->desc[i].start +
-					oes->pktdma_tchan_flow;
-		irq_res.desc[i].num = rm_res->desc[i].num;
+	if (IS_ERR(rm_res)) {
+		irq_res.desc[0].start = oes->pktdma_tchan_flow;
+		irq_res.desc[0].num = ud->tflow_cnt;
+		i = 1;
+	} else {
+		for (i = 0; i < rm_res->sets; i++) {
+			irq_res.desc[i].start = rm_res->desc[i].start +
+						oes->pktdma_tchan_flow;
+			irq_res.desc[i].num = rm_res->desc[i].num;
+		}
 	}
 	rm_res = tisci_rm->rm_ranges[RM_RANGE_RFLOW];
-	for (j = 0; j < rm_res->sets; j++, i++) {
-		irq_res.desc[i].start = rm_res->desc[j].start +
-					oes->pktdma_rchan_flow;
-		irq_res.desc[i].num = rm_res->desc[j].num;
+	if (IS_ERR(rm_res)) {
+		irq_res.desc[i].start = oes->pktdma_rchan_flow;
+		irq_res.desc[i].num = ud->rflow_cnt;
+	} else {
+		for (j = 0; j < rm_res->sets; j++, i++) {
+			irq_res.desc[i].start = rm_res->desc[j].start +
+						oes->pktdma_rchan_flow;
+			irq_res.desc[i].num = rm_res->desc[j].num;
+		}
 	}
 	ret = ti_sci_inta_msi_domain_alloc_irqs(ud->dev, &irq_res);
 	kfree(irq_res.desc);
diff --git a/drivers/firmware/arm_scmi/base.c b/drivers/firmware/arm_scmi/base.c
index de416f9e7921..f5219334fd3a 100644
--- a/drivers/firmware/arm_scmi/base.c
+++ b/drivers/firmware/arm_scmi/base.c
@@ -34,6 +34,12 @@ struct scmi_msg_resp_base_attributes {
 	__le16 reserved;
 };
 
+struct scmi_msg_resp_base_discover_agent {
+	__le32 agent_id;
+	u8 name[SCMI_MAX_STR_SIZE];
+};
+
+
 struct scmi_msg_base_error_notify {
 	__le32 event_control;
 #define BASE_TP_NOTIFY_ALL	BIT(0)
@@ -225,18 +231,21 @@ static int scmi_base_discover_agent_get(const struct scmi_protocol_handle *ph,
 					int id, char *name)
 {
 	int ret;
+	struct scmi_msg_resp_base_discover_agent *agent_info;
 	struct scmi_xfer *t;
 
 	ret = ph->xops->xfer_get_init(ph, BASE_DISCOVER_AGENT,
-				      sizeof(__le32), SCMI_MAX_STR_SIZE, &t);
+				      sizeof(__le32), sizeof(*agent_info), &t);
 	if (ret)
 		return ret;
 
 	put_unaligned_le32(id, t->tx.buf);
 
 	ret = ph->xops->do_xfer(ph, t);
-	if (!ret)
-		strlcpy(name, t->rx.buf, SCMI_MAX_STR_SIZE);
+	if (!ret) {
+		agent_info = t->rx.buf;
+		strlcpy(name, agent_info->name, SCMI_MAX_STR_SIZE);
+	}
 
 	ph->xops->xfer_put(ph, t);
 
diff --git a/drivers/firmware/arm_scmi/scmi_pm_domain.c b/drivers/firmware/arm_scmi/scmi_pm_domain.c
index 4371fdcd5a73..581d34c95769 100644
--- a/drivers/firmware/arm_scmi/scmi_pm_domain.c
+++ b/drivers/firmware/arm_scmi/scmi_pm_domain.c
@@ -138,9 +138,7 @@ static int scmi_pm_domain_probe(struct scmi_device *sdev)
 	scmi_pd_data->domains = domains;
 	scmi_pd_data->num_domains = num_domains;
 
-	of_genpd_add_provider_onecell(np, scmi_pd_data);
-
-	return 0;
+	return of_genpd_add_provider_onecell(np, scmi_pd_data);
 }
 
 static const struct scmi_device_id scmi_id_table[] = {
diff --git a/drivers/firmware/arm_scmi/sensors.c b/drivers/firmware/arm_scmi/sensors.c
index 308471586381..cdbb287bd8bc 100644
--- a/drivers/firmware/arm_scmi/sensors.c
+++ b/drivers/firmware/arm_scmi/sensors.c
@@ -637,7 +637,7 @@ static int scmi_sensor_config_get(const struct scmi_protocol_handle *ph,
 	if (ret)
 		return ret;
 
-	put_unaligned_le32(cpu_to_le32(sensor_id), t->tx.buf);
+	put_unaligned_le32(sensor_id, t->tx.buf);
 	ret = ph->xops->do_xfer(ph, t);
 	if (!ret) {
 		struct sensors_info *si = ph->get_priv(ph);
diff --git a/drivers/firmware/arm_scmi/virtio.c b/drivers/firmware/arm_scmi/virtio.c
index 11e8efb71375..87039c5c03fd 100644
--- a/drivers/firmware/arm_scmi/virtio.c
+++ b/drivers/firmware/arm_scmi/virtio.c
@@ -82,7 +82,8 @@ static bool scmi_vio_have_vq_rx(struct virtio_device *vdev)
 }
 
 static int scmi_vio_feed_vq_rx(struct scmi_vio_channel *vioch,
-			       struct scmi_vio_msg *msg)
+			       struct scmi_vio_msg *msg,
+			       struct device *dev)
 {
 	struct scatterlist sg_in;
 	int rc;
@@ -94,8 +95,7 @@ static int scmi_vio_feed_vq_rx(struct scmi_vio_channel *vioch,
 
 	rc = virtqueue_add_inbuf(vioch->vqueue, &sg_in, 1, msg, GFP_ATOMIC);
 	if (rc)
-		dev_err_once(vioch->cinfo->dev,
-			     "failed to add to virtqueue (%d)\n", rc);
+		dev_err_once(dev, "failed to add to virtqueue (%d)\n", rc);
 	else
 		virtqueue_kick(vioch->vqueue);
 
@@ -108,7 +108,7 @@ static void scmi_finalize_message(struct scmi_vio_channel *vioch,
 				  struct scmi_vio_msg *msg)
 {
 	if (vioch->is_rx) {
-		scmi_vio_feed_vq_rx(vioch, msg);
+		scmi_vio_feed_vq_rx(vioch, msg, vioch->cinfo->dev);
 	} else {
 		/* Here IRQs are assumed to be already disabled by the caller */
 		spin_lock(&vioch->lock);
@@ -269,7 +269,7 @@ static int virtio_chan_setup(struct scmi_chan_info *cinfo, struct device *dev,
 			list_add_tail(&msg->list, &vioch->free_list);
 			spin_unlock_irqrestore(&vioch->lock, flags);
 		} else {
-			scmi_vio_feed_vq_rx(vioch, msg);
+			scmi_vio_feed_vq_rx(vioch, msg, cinfo->dev);
 		}
 	}
 
diff --git a/drivers/firmware/arm_scmi/voltage.c b/drivers/firmware/arm_scmi/voltage.c
index a5048956a0be..ac08e819088b 100644
--- a/drivers/firmware/arm_scmi/voltage.c
+++ b/drivers/firmware/arm_scmi/voltage.c
@@ -156,7 +156,7 @@ static int scmi_voltage_descriptors_get(const struct scmi_protocol_handle *ph,
 			int cnt;
 
 			cmd->domain_id = cpu_to_le32(v->id);
-			cmd->level_index = desc_index;
+			cmd->level_index = cpu_to_le32(desc_index);
 			ret = ph->xops->do_xfer(ph, tl);
 			if (ret)
 				break;
diff --git a/drivers/firmware/scpi_pm_domain.c b/drivers/firmware/scpi_pm_domain.c
index 51201600d789..800673910b51 100644
--- a/drivers/firmware/scpi_pm_domain.c
+++ b/drivers/firmware/scpi_pm_domain.c
@@ -16,7 +16,6 @@ struct scpi_pm_domain {
 	struct generic_pm_domain genpd;
 	struct scpi_ops *ops;
 	u32 domain;
-	char name[30];
 };
 
 /*
@@ -110,8 +109,13 @@ static int scpi_pm_domain_probe(struct platform_device *pdev)
 
 		scpi_pd->domain = i;
 		scpi_pd->ops = scpi_ops;
-		sprintf(scpi_pd->name, "%pOFn.%d", np, i);
-		scpi_pd->genpd.name = scpi_pd->name;
+		scpi_pd->genpd.name = devm_kasprintf(dev, GFP_KERNEL,
+						     "%pOFn.%d", np, i);
+		if (!scpi_pd->genpd.name) {
+			dev_err(dev, "Failed to allocate genpd name:%pOFn.%d\n",
+				np, i);
+			continue;
+		}
 		scpi_pd->genpd.power_off = scpi_pd_power_off;
 		scpi_pd->genpd.power_on = scpi_pd_power_on;
 
diff --git a/drivers/firmware/smccc/soc_id.c b/drivers/firmware/smccc/soc_id.c
index 581aa5e9b077..dd7c3d5e8b0b 100644
--- a/drivers/firmware/smccc/soc_id.c
+++ b/drivers/firmware/smccc/soc_id.c
@@ -50,7 +50,7 @@ static int __init smccc_soc_init(void)
 	arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
 			     ARM_SMCCC_ARCH_SOC_ID, &res);
 
-	if (res.a0 == SMCCC_RET_NOT_SUPPORTED) {
+	if ((int)res.a0 == SMCCC_RET_NOT_SUPPORTED) {
 		pr_info("ARCH_SOC_ID not implemented, skipping ....\n");
 		return 0;
 	}
diff --git a/drivers/firmware/tegra/bpmp-debugfs.c b/drivers/firmware/tegra/bpmp-debugfs.c
index 6d66fe03fb6a..fd89899aeeed 100644
--- a/drivers/firmware/tegra/bpmp-debugfs.c
+++ b/drivers/firmware/tegra/bpmp-debugfs.c
@@ -77,13 +77,14 @@ static const char *get_filename(struct tegra_bpmp *bpmp,
 	const char *root_path, *filename = NULL;
 	char *root_path_buf;
 	size_t root_len;
+	size_t root_path_buf_len = 512;
 
-	root_path_buf = kzalloc(512, GFP_KERNEL);
+	root_path_buf = kzalloc(root_path_buf_len, GFP_KERNEL);
 	if (!root_path_buf)
 		goto out;
 
 	root_path = dentry_path(bpmp->debugfs_mirror, root_path_buf,
-				sizeof(root_path_buf));
+				root_path_buf_len);
 	if (IS_ERR(root_path))
 		goto out;
 
diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index 072ed610f9c6..60d9374c72c0 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -523,6 +523,7 @@ config GPIO_REG
 config GPIO_ROCKCHIP
 	tristate "Rockchip GPIO support"
 	depends on ARCH_ROCKCHIP || COMPILE_TEST
+	select GENERIC_IRQ_CHIP
 	select GPIOLIB_IRQCHIP
 	default ARCH_ROCKCHIP
 	help
diff --git a/drivers/gpio/gpio-dln2.c b/drivers/gpio/gpio-dln2.c
index 026903e3ef54..08b9e2cf4f2d 100644
--- a/drivers/gpio/gpio-dln2.c
+++ b/drivers/gpio/gpio-dln2.c
@@ -46,6 +46,7 @@
 struct dln2_gpio {
 	struct platform_device *pdev;
 	struct gpio_chip gpio;
+	struct irq_chip irqchip;
 
 	/*
 	 * Cache pin direction to save us one transfer, since the hardware has
@@ -383,15 +384,6 @@ static void dln2_irq_bus_unlock(struct irq_data *irqd)
 	mutex_unlock(&dln2->irq_lock);
 }
 
-static struct irq_chip dln2_gpio_irqchip = {
-	.name = "dln2-irq",
-	.irq_mask = dln2_irq_mask,
-	.irq_unmask = dln2_irq_unmask,
-	.irq_set_type = dln2_irq_set_type,
-	.irq_bus_lock = dln2_irq_bus_lock,
-	.irq_bus_sync_unlock = dln2_irq_bus_unlock,
-};
-
 static void dln2_gpio_event(struct platform_device *pdev, u16 echo,
 			    const void *data, int len)
 {
@@ -473,8 +465,15 @@ static int dln2_gpio_probe(struct platform_device *pdev)
 	dln2->gpio.direction_output = dln2_gpio_direction_output;
 	dln2->gpio.set_config = dln2_gpio_set_config;
 
+	dln2->irqchip.name = "dln2-irq",
+	dln2->irqchip.irq_mask = dln2_irq_mask,
+	dln2->irqchip.irq_unmask = dln2_irq_unmask,
+	dln2->irqchip.irq_set_type = dln2_irq_set_type,
+	dln2->irqchip.irq_bus_lock = dln2_irq_bus_lock,
+	dln2->irqchip.irq_bus_sync_unlock = dln2_irq_bus_unlock,
+
 	girq = &dln2->gpio.irq;
-	girq->chip = &dln2_gpio_irqchip;
+	girq->chip = &dln2->irqchip;
 	/* The event comes from the outside so no parent handler */
 	girq->parent_handler = NULL;
 	girq->num_parents = 0;
diff --git a/drivers/gpio/gpio-virtio.c b/drivers/gpio/gpio-virtio.c
index aeec4bf0b625..9f4941bc5760 100644
--- a/drivers/gpio/gpio-virtio.c
+++ b/drivers/gpio/gpio-virtio.c
@@ -100,11 +100,7 @@ static int _virtio_gpio_req(struct virtio_gpio *vgpio, u16 type, u16 gpio,
 	virtqueue_kick(vgpio->request_vq);
 	mutex_unlock(&vgpio->lock);
 
-	if (!wait_for_completion_timeout(&line->completion, HZ)) {
-		dev_err(dev, "GPIO operation timed out\n");
-		ret = -ETIMEDOUT;
-		goto out;
-	}
+	wait_for_completion(&line->completion);
 
 	if (unlikely(res->status != VIRTIO_GPIO_STATUS_OK)) {
 		dev_err(dev, "GPIO request failed: %d\n", gpio);
@@ -434,7 +430,7 @@ static void virtio_gpio_event_vq(struct virtqueue *vq)
 		ret = generic_handle_domain_irq(vgpio->gc.irq.domain, gpio);
 		if (ret)
 			dev_err(dev, "failed to handle interrupt: %d\n", ret);
-	};
+	}
 }
 
 static void virtio_gpio_request_vq(struct virtqueue *vq)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 71acd577803e..6348559608ce 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -646,12 +646,6 @@ kfd_mem_attach_dmabuf(struct amdgpu_device *adev, struct kgd_mem *mem,
 	if (IS_ERR(gobj))
 		return PTR_ERR(gobj);
 
-	/* Import takes an extra reference on the dmabuf. Drop it now to
-	 * avoid leaking it. We only need the one reference in
-	 * kgd_mem->dmabuf.
-	 */
-	dma_buf_put(mem->dmabuf);
-
 	*bo = gem_to_amdgpu_bo(gobj);
 	(*bo)->flags |= AMDGPU_GEM_CREATE_PREEMPTIBLE;
 	(*bo)->parent = amdgpu_bo_ref(mem->bo);
@@ -1402,7 +1396,7 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(
 	struct sg_table *sg = NULL;
 	uint64_t user_addr = 0;
 	struct amdgpu_bo *bo;
-	struct drm_gem_object *gobj;
+	struct drm_gem_object *gobj = NULL;
 	u32 domain, alloc_domain;
 	u64 alloc_flags;
 	int ret;
@@ -1512,14 +1506,16 @@ allocate_init_user_pages_failed:
 	remove_kgd_mem_from_kfd_bo_list(*mem, avm->process_info);
 	drm_vma_node_revoke(&gobj->vma_node, drm_priv);
 err_node_allow:
-	drm_gem_object_put(gobj);
 	/* Don't unreserve system mem limit twice */
 	goto err_reserve_limit;
 err_bo_create:
 	unreserve_mem_limit(adev, size, alloc_domain, !!sg);
 err_reserve_limit:
 	mutex_destroy(&(*mem)->lock);
-	kfree(*mem);
+	if (gobj)
+		drm_gem_object_put(gobj);
+	else
+		kfree(*mem);
 err:
 	if (sg) {
 		sg_free_table(sg);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
index 96b7bb13a2dd..12a6b1c99c93 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
@@ -1569,6 +1569,18 @@ void amdgpu_atombios_scratch_regs_engine_hung(struct amdgpu_device *adev,
 	WREG32(adev->bios_scratch_reg_offset + 3, tmp);
 }
 
+void amdgpu_atombios_scratch_regs_set_backlight_level(struct amdgpu_device *adev,
+						      u32 backlight_level)
+{
+	u32 tmp = RREG32(adev->bios_scratch_reg_offset + 2);
+
+	tmp &= ~ATOM_S2_CURRENT_BL_LEVEL_MASK;
+	tmp |= (backlight_level << ATOM_S2_CURRENT_BL_LEVEL_SHIFT) &
+		ATOM_S2_CURRENT_BL_LEVEL_MASK;
+
+	WREG32(adev->bios_scratch_reg_offset + 2, tmp);
+}
+
 bool amdgpu_atombios_scratch_need_asic_init(struct amdgpu_device *adev)
 {
 	u32 tmp = RREG32(adev->bios_scratch_reg_offset + 7);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.h
index 8cc0222dba19..27e74b1fc260 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.h
@@ -185,6 +185,8 @@ bool amdgpu_atombios_has_gpu_virtualization_table(struct amdgpu_device *adev);
 void amdgpu_atombios_scratch_regs_lock(struct amdgpu_device *adev, bool lock);
 void amdgpu_atombios_scratch_regs_engine_hung(struct amdgpu_device *adev,
 					      bool hung);
+void amdgpu_atombios_scratch_regs_set_backlight_level(struct amdgpu_device *adev,
+						      u32 backlight_level);
 bool amdgpu_atombios_scratch_need_asic_init(struct amdgpu_device *adev);
 
 void amdgpu_atombios_copy_swap(u8 *dst, u8 *src, u8 num_bytes, bool to_le);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
index b9c11c2b2885..0de66f59adb8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
@@ -827,6 +827,7 @@ static int amdgpu_connector_vga_get_modes(struct drm_connector *connector)
 
 	amdgpu_connector_get_edid(connector);
 	ret = amdgpu_connector_ddc_get_modes(connector);
+	amdgpu_get_native_mode(connector);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 5625f7736e37..1e651b959141 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3509,6 +3509,9 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 		adev->rmmio_size = pci_resource_len(adev->pdev, 2);
 	}
 
+	for (i = 0; i < AMD_IP_BLOCK_TYPE_NUM; i++)
+		atomic_set(&adev->pm.pwr_state[i], POWER_STATE_UNKNOWN);
+
 	adev->rmmio = ioremap(adev->rmmio_base, adev->rmmio_size);
 	if (adev->rmmio == NULL) {
 		return -ENOMEM;
@@ -3830,7 +3833,7 @@ void amdgpu_device_fini_hw(struct amdgpu_device *adev)
 	/* disable all interrupts */
 	amdgpu_irq_disable_all(adev);
 	if (adev->mode_info.mode_config_initialized){
-		if (!amdgpu_device_has_dc_support(adev))
+		if (!drm_drv_uses_atomic_modeset(adev_to_drm(adev)))
 			drm_helper_force_disable_all(adev_to_drm(adev));
 		else
 			drm_atomic_helper_shutdown(adev_to_drm(adev));
@@ -4286,6 +4289,8 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev,
 {
 	int r;
 
+	amdgpu_amdkfd_pre_reset(adev);
+
 	if (from_hypervisor)
 		r = amdgpu_virt_request_full_gpu(adev, true);
 	else
@@ -5028,7 +5033,8 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 
 		cancel_delayed_work_sync(&tmp_adev->delayed_init_work);
 
-		amdgpu_amdkfd_pre_reset(tmp_adev);
+		if (!amdgpu_sriov_vf(tmp_adev))
+			amdgpu_amdkfd_pre_reset(tmp_adev);
 
 		/*
 		 * Mark these ASICs to be reseted as untracked first
@@ -5086,7 +5092,7 @@ retry:	/* Rest of adevs pre asic reset from XGMI hive. */
 
 	tmp_vram_lost_counter = atomic_read(&((adev)->vram_lost_counter));
 	/* Actual ASIC resets if needed.*/
-	/* TODO Implement XGMI hive reset logic for SRIOV */
+	/* Host driver will handle XGMI hive reset for SRIOV */
 	if (amdgpu_sriov_vf(adev)) {
 		r = amdgpu_device_reset_sriov(adev, job ? false : true);
 		if (r)
@@ -5127,7 +5133,7 @@ skip_hw_reset:
 			drm_sched_start(&ring->sched, !tmp_adev->asic_reset_res);
 		}
 
-		if (!amdgpu_device_has_dc_support(tmp_adev) && !job_signaled) {
+		if (!drm_drv_uses_atomic_modeset(adev_to_drm(tmp_adev)) && !job_signaled) {
 			drm_helper_resume_force_mode(adev_to_drm(tmp_adev));
 		}
 
@@ -5148,7 +5154,7 @@ skip_sched_resume:
 	list_for_each_entry(tmp_adev, device_list_handle, reset_list) {
 		/* unlock kfd: SRIOV would do it separately */
 		if (!need_emergency_restart && !amdgpu_sriov_vf(tmp_adev))
-	                amdgpu_amdkfd_post_reset(tmp_adev);
+			amdgpu_amdkfd_post_reset(tmp_adev);
 
 		/* kfd_post_reset will do nothing if kfd device is not initialized,
 		 * need to bring up kfd here if it's not be initialized before
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
index ff70bc233489..ea00090b3fb3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
@@ -157,6 +157,8 @@ static int hw_id_map[MAX_HWIP] = {
 	[HDP_HWIP]	= HDP_HWID,
 	[SDMA0_HWIP]	= SDMA0_HWID,
 	[SDMA1_HWIP]	= SDMA1_HWID,
+	[SDMA2_HWIP]    = SDMA2_HWID,
+	[SDMA3_HWIP]    = SDMA3_HWID,
 	[MMHUB_HWIP]	= MMHUB_HWID,
 	[ATHUB_HWIP]	= ATHUB_HWID,
 	[NBIO_HWIP]	= NBIF_HWID,
@@ -248,8 +250,8 @@ get_from_vram:
 
 	offset = offsetof(struct binary_header, binary_checksum) +
 		sizeof(bhdr->binary_checksum);
-	size = bhdr->binary_size - offset;
-	checksum = bhdr->binary_checksum;
+	size = le16_to_cpu(bhdr->binary_size) - offset;
+	checksum = le16_to_cpu(bhdr->binary_checksum);
 
 	if (!amdgpu_discovery_verify_checksum(adev->mman.discovery_bin + offset,
 					      size, checksum)) {
@@ -270,7 +272,7 @@ get_from_vram:
 	}
 
 	if (!amdgpu_discovery_verify_checksum(adev->mman.discovery_bin + offset,
-					      ihdr->size, checksum)) {
+					      le16_to_cpu(ihdr->size), checksum)) {
 		DRM_ERROR("invalid ip discovery data table checksum\n");
 		r = -EINVAL;
 		goto out;
@@ -282,7 +284,7 @@ get_from_vram:
 	ghdr = (struct gpu_info_header *)(adev->mman.discovery_bin + offset);
 
 	if (!amdgpu_discovery_verify_checksum(adev->mman.discovery_bin + offset,
-				              ghdr->size, checksum)) {
+				              le32_to_cpu(ghdr->size), checksum)) {
 		DRM_ERROR("invalid gc data table checksum\n");
 		r = -EINVAL;
 		goto out;
@@ -489,10 +491,10 @@ void amdgpu_discovery_harvest_ip(struct amdgpu_device *adev)
 			le16_to_cpu(bhdr->table_list[HARVEST_INFO].offset));
 
 	for (i = 0; i < 32; i++) {
-		if (le32_to_cpu(harvest_info->list[i].hw_id) == 0)
+		if (le16_to_cpu(harvest_info->list[i].hw_id) == 0)
 			break;
 
-		switch (le32_to_cpu(harvest_info->list[i].hw_id)) {
+		switch (le16_to_cpu(harvest_info->list[i].hw_id)) {
 		case VCN_HWID:
 			vcn_harvest_count++;
 			if (harvest_info->list[i].number_instance == 0)
@@ -587,6 +589,9 @@ static int amdgpu_discovery_set_common_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &nv_common_ip_block);
 		break;
 	default:
+		dev_err(adev->dev,
+			"Failed to add common ip block(GC_HWIP:0x%x)\n",
+			adev->ip_versions[GC_HWIP][0]);
 		return -EINVAL;
 	}
 	return 0;
@@ -619,6 +624,9 @@ static int amdgpu_discovery_set_gmc_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &gmc_v10_0_ip_block);
 		break;
 	default:
+		dev_err(adev->dev,
+			"Failed to add gmc ip block(GC_HWIP:0x%x)\n",
+			adev->ip_versions[GC_HWIP][0]);
 		return -EINVAL;
 	}
 	return 0;
@@ -648,6 +656,9 @@ static int amdgpu_discovery_set_ih_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &navi10_ih_ip_block);
 		break;
 	default:
+		dev_err(adev->dev,
+			"Failed to add ih ip block(OSSSYS_HWIP:0x%x)\n",
+			adev->ip_versions[OSSSYS_HWIP][0]);
 		return -EINVAL;
 	}
 	return 0;
@@ -688,6 +699,9 @@ static int amdgpu_discovery_set_psp_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &psp_v13_0_ip_block);
 		break;
 	default:
+		dev_err(adev->dev,
+			"Failed to add psp ip block(MP0_HWIP:0x%x)\n",
+			adev->ip_versions[MP0_HWIP][0]);
 		return -EINVAL;
 	}
 	return 0;
@@ -726,6 +740,9 @@ static int amdgpu_discovery_set_smu_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &smu_v13_0_ip_block);
 		break;
 	default:
+		dev_err(adev->dev,
+			"Failed to add smu ip block(MP1_HWIP:0x%x)\n",
+			adev->ip_versions[MP1_HWIP][0]);
 		return -EINVAL;
 	}
 	return 0;
@@ -753,6 +770,9 @@ static int amdgpu_discovery_set_display_ip_blocks(struct amdgpu_device *adev)
 			amdgpu_device_ip_block_add(adev, &dm_ip_block);
 			break;
 		default:
+			dev_err(adev->dev,
+				"Failed to add dm ip block(DCE_HWIP:0x%x)\n",
+				adev->ip_versions[DCE_HWIP][0]);
 			return -EINVAL;
 		}
 	} else if (adev->ip_versions[DCI_HWIP][0]) {
@@ -763,6 +783,9 @@ static int amdgpu_discovery_set_display_ip_blocks(struct amdgpu_device *adev)
 			amdgpu_device_ip_block_add(adev, &dm_ip_block);
 			break;
 		default:
+			dev_err(adev->dev,
+				"Failed to add dm ip block(DCI_HWIP:0x%x)\n",
+				adev->ip_versions[DCI_HWIP][0]);
 			return -EINVAL;
 		}
 #endif
@@ -796,6 +819,9 @@ static int amdgpu_discovery_set_gc_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &gfx_v10_0_ip_block);
 		break;
 	default:
+		dev_err(adev->dev,
+			"Failed to add gfx ip block(GC_HWIP:0x%x)\n",
+			adev->ip_versions[GC_HWIP][0]);
 		return -EINVAL;
 	}
 	return 0;
@@ -829,6 +855,9 @@ static int amdgpu_discovery_set_sdma_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &sdma_v5_2_ip_block);
 		break;
 	default:
+		dev_err(adev->dev,
+			"Failed to add sdma ip block(SDMA0_HWIP:0x%x)\n",
+			adev->ip_versions[SDMA0_HWIP][0]);
 		return -EINVAL;
 	}
 	return 0;
@@ -845,6 +874,9 @@ static int amdgpu_discovery_set_mm_ip_blocks(struct amdgpu_device *adev)
 				amdgpu_device_ip_block_add(adev, &uvd_v7_0_ip_block);
 			break;
 		default:
+			dev_err(adev->dev,
+				"Failed to add uvd v7 ip block(UVD_HWIP:0x%x)\n",
+				adev->ip_versions[UVD_HWIP][0]);
 			return -EINVAL;
 		}
 		switch (adev->ip_versions[VCE_HWIP][0]) {
@@ -855,6 +887,9 @@ static int amdgpu_discovery_set_mm_ip_blocks(struct amdgpu_device *adev)
 				amdgpu_device_ip_block_add(adev, &vce_v4_0_ip_block);
 			break;
 		default:
+			dev_err(adev->dev,
+				"Failed to add VCE v4 ip block(VCE_HWIP:0x%x)\n",
+				adev->ip_versions[VCE_HWIP][0]);
 			return -EINVAL;
 		}
 	} else {
@@ -885,6 +920,7 @@ static int amdgpu_discovery_set_mm_ip_blocks(struct amdgpu_device *adev)
 		case IP_VERSION(3, 0, 64):
 		case IP_VERSION(3, 1, 1):
 		case IP_VERSION(3, 0, 2):
+		case IP_VERSION(3, 0, 192):
 			amdgpu_device_ip_block_add(adev, &vcn_v3_0_ip_block);
 			if (!amdgpu_sriov_vf(adev))
 				amdgpu_device_ip_block_add(adev, &jpeg_v3_0_ip_block);
@@ -893,6 +929,9 @@ static int amdgpu_discovery_set_mm_ip_blocks(struct amdgpu_device *adev)
 			amdgpu_device_ip_block_add(adev, &vcn_v3_0_ip_block);
 			break;
 		default:
+			dev_err(adev->dev,
+				"Failed to add vcn/jpeg ip block(UVD_HWIP:0x%x)\n",
+				adev->ip_versions[UVD_HWIP][0]);
 			return -EINVAL;
 		}
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.c
index f3d62e196901..0c7963dfacad 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.c
@@ -223,7 +223,7 @@ int amdgpu_ih_wait_on_checkpoint_process(struct amdgpu_device *adev,
  */
 int amdgpu_ih_process(struct amdgpu_device *adev, struct amdgpu_ih_ring *ih)
 {
-	unsigned int count = AMDGPU_IH_MAX_NUM_IVS;
+	unsigned int count;
 	u32 wptr;
 
 	if (!ih->enabled || adev->shutdown)
@@ -232,6 +232,7 @@ int amdgpu_ih_process(struct amdgpu_device *adev, struct amdgpu_ih_ring *ih)
 	wptr = amdgpu_ih_get_wptr(adev, ih);
 
 restart_ih:
+	count  = AMDGPU_IH_MAX_NUM_IVS;
 	DRM_DEBUG("%s: rptr %d, wptr %d\n", __func__, ih->rptr, wptr);
 
 	/* Order reading of wptr vs. reading of IH ring data */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
index 4f7c70845785..585961c2f5f2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@@ -135,6 +135,7 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev)
 		break;
 	case IP_VERSION(3, 0, 0):
 	case IP_VERSION(3, 0, 64):
+	case IP_VERSION(3, 0, 192):
 		if (adev->ip_versions[GC_HWIP][0] == IP_VERSION(10, 3, 0))
 			fw_name = FIRMWARE_SIENNA_CICHLID;
 		else
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c
index ce982afeff91..ac9a8cd21c4b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c
@@ -504,8 +504,8 @@ static int amdgpu_vkms_sw_fini(void *handle)
 	int i = 0;
 
 	for (i = 0; i < adev->mode_info.num_crtc; i++)
-		if (adev->mode_info.crtcs[i])
-			hrtimer_cancel(&adev->mode_info.crtcs[i]->vblank_timer);
+		if (adev->amdgpu_vkms_output[i].vblank_hrtimer.function)
+			hrtimer_cancel(&adev->amdgpu_vkms_output[i].vblank_hrtimer);
 
 	kfree(adev->mode_info.bios_hardcoded_edid);
 	kfree(adev->amdgpu_vkms_output);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
index 0fad2bf854ae..567df2db23ac 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
@@ -386,6 +386,7 @@ struct amdgpu_hive_info *amdgpu_get_xgmi_hive(struct amdgpu_device *adev)
 			"%s", "xgmi_hive_info");
 	if (ret) {
 		dev_err(adev->dev, "XGMI: failed initializing kobject for xgmi hive\n");
+		kobject_put(&hive->kobj);
 		kfree(hive);
 		hive = NULL;
 		goto pro_end;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index e7dfeb466a0e..dbe7442fb25c 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -7707,8 +7707,19 @@ static uint64_t gfx_v10_0_get_gpu_clock_counter(struct amdgpu_device *adev)
 	switch (adev->ip_versions[GC_HWIP][0]) {
 	case IP_VERSION(10, 3, 1):
 	case IP_VERSION(10, 3, 3):
-		clock = (uint64_t)RREG32_SOC15(SMUIO, 0, mmGOLDEN_TSC_COUNT_LOWER_Vangogh) |
-			((uint64_t)RREG32_SOC15(SMUIO, 0, mmGOLDEN_TSC_COUNT_UPPER_Vangogh) << 32ULL);
+		preempt_disable();
+		clock_hi = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_UPPER_Vangogh);
+		clock_lo = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_LOWER_Vangogh);
+		hi_check = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_UPPER_Vangogh);
+		/* The SMUIO TSC clock frequency is 100MHz, which sets 32-bit carry over
+		 * roughly every 42 seconds.
+		 */
+		if (hi_check != clock_hi) {
+			clock_lo = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_LOWER_Vangogh);
+			clock_hi = hi_check;
+		}
+		preempt_enable();
+		clock = clock_lo | (clock_hi << 32ULL);
 		break;
 	default:
 		preempt_disable();
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index b4b80f27b894..edb3e3b08eed 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -140,6 +140,11 @@ MODULE_FIRMWARE("amdgpu/aldebaran_rlc.bin");
 #define mmTCP_CHAN_STEER_5_ARCT								0x0b0c
 #define mmTCP_CHAN_STEER_5_ARCT_BASE_IDX							0
 
+#define mmGOLDEN_TSC_COUNT_UPPER_Renoir                0x0025
+#define mmGOLDEN_TSC_COUNT_UPPER_Renoir_BASE_IDX       1
+#define mmGOLDEN_TSC_COUNT_LOWER_Renoir                0x0026
+#define mmGOLDEN_TSC_COUNT_LOWER_Renoir_BASE_IDX       1
+
 enum ta_ras_gfx_subblock {
 	/*CPC*/
 	TA_RAS_BLOCK__GFX_CPC_INDEX_START = 0,
@@ -3065,8 +3070,8 @@ static void gfx_v9_0_init_pg(struct amdgpu_device *adev)
 			      AMD_PG_SUPPORT_CP |
 			      AMD_PG_SUPPORT_GDS |
 			      AMD_PG_SUPPORT_RLC_SMU_HS)) {
-		WREG32(mmRLC_JUMP_TABLE_RESTORE,
-		       adev->gfx.rlc.cp_table_gpu_addr >> 8);
+		WREG32_SOC15(GC, 0, mmRLC_JUMP_TABLE_RESTORE,
+			     adev->gfx.rlc.cp_table_gpu_addr >> 8);
 		gfx_v9_0_init_gfx_power_gating(adev);
 	}
 }
@@ -4055,9 +4060,10 @@ static int gfx_v9_0_hw_fini(void *handle)
 
 	gfx_v9_0_cp_enable(adev, false);
 
-	/* Skip suspend with A+A reset */
-	if (adev->gmc.xgmi.connected_to_cpu && amdgpu_in_reset(adev)) {
-		dev_dbg(adev->dev, "Device in reset. Skipping RLC halt\n");
+	/* Skip stopping RLC with A+A reset or when RLC controls GFX clock */
+	if ((adev->gmc.xgmi.connected_to_cpu && amdgpu_in_reset(adev)) ||
+	    (adev->ip_versions[GC_HWIP][0] >= IP_VERSION(9, 4, 2))) {
+		dev_dbg(adev->dev, "Skipping RLC halt\n");
 		return 0;
 	}
 
@@ -4238,19 +4244,38 @@ failed_kiq_read:
 
 static uint64_t gfx_v9_0_get_gpu_clock_counter(struct amdgpu_device *adev)
 {
-	uint64_t clock;
+	uint64_t clock, clock_lo, clock_hi, hi_check;
 
-	amdgpu_gfx_off_ctrl(adev, false);
-	mutex_lock(&adev->gfx.gpu_clock_mutex);
-	if (adev->ip_versions[GC_HWIP][0] == IP_VERSION(9, 0, 1) && amdgpu_sriov_runtime(adev)) {
-		clock = gfx_v9_0_kiq_read_clock(adev);
-	} else {
-		WREG32_SOC15(GC, 0, mmRLC_CAPTURE_GPU_CLOCK_COUNT, 1);
-		clock = (uint64_t)RREG32_SOC15(GC, 0, mmRLC_GPU_CLOCK_COUNT_LSB) |
-			((uint64_t)RREG32_SOC15(GC, 0, mmRLC_GPU_CLOCK_COUNT_MSB) << 32ULL);
+	switch (adev->ip_versions[GC_HWIP][0]) {
+	case IP_VERSION(9, 3, 0):
+		preempt_disable();
+		clock_hi = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_UPPER_Renoir);
+		clock_lo = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_LOWER_Renoir);
+		hi_check = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_UPPER_Renoir);
+		/* The SMUIO TSC clock frequency is 100MHz, which sets 32-bit carry over
+		 * roughly every 42 seconds.
+		 */
+		if (hi_check != clock_hi) {
+			clock_lo = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_LOWER_Renoir);
+			clock_hi = hi_check;
+		}
+		preempt_enable();
+		clock = clock_lo | (clock_hi << 32ULL);
+		break;
+	default:
+		amdgpu_gfx_off_ctrl(adev, false);
+		mutex_lock(&adev->gfx.gpu_clock_mutex);
+		if (adev->ip_versions[GC_HWIP][0] == IP_VERSION(9, 0, 1) && amdgpu_sriov_runtime(adev)) {
+			clock = gfx_v9_0_kiq_read_clock(adev);
+		} else {
+			WREG32_SOC15(GC, 0, mmRLC_CAPTURE_GPU_CLOCK_COUNT, 1);
+			clock = (uint64_t)RREG32_SOC15(GC, 0, mmRLC_GPU_CLOCK_COUNT_LSB) |
+				((uint64_t)RREG32_SOC15(GC, 0, mmRLC_GPU_CLOCK_COUNT_MSB) << 32ULL);
+		}
+		mutex_unlock(&adev->gfx.gpu_clock_mutex);
+		amdgpu_gfx_off_ctrl(adev, true);
+		break;
 	}
-	mutex_unlock(&adev->gfx.gpu_clock_mutex);
-	amdgpu_gfx_off_ctrl(adev, true);
 	return clock;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
index 480e41847d7c..ec4d5e15b766 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
@@ -162,7 +162,6 @@ static void gfxhub_v1_0_init_tlb_regs(struct amdgpu_device *adev)
 			    ENABLE_ADVANCED_DRIVER_MODEL, 1);
 	tmp = REG_SET_FIELD(tmp, MC_VM_MX_L1_TLB_CNTL,
 			    SYSTEM_APERTURE_UNMAPPED_ACCESS, 0);
-	tmp = REG_SET_FIELD(tmp, MC_VM_MX_L1_TLB_CNTL, ECO_BITS, 0);
 	tmp = REG_SET_FIELD(tmp, MC_VM_MX_L1_TLB_CNTL,
 			    MTYPE, MTYPE_UC);/* XXX for emulation. */
 	tmp = REG_SET_FIELD(tmp, MC_VM_MX_L1_TLB_CNTL, ATC_EN, 1);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c
index 14c1c1a297dd..6e0ace2fbfab 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c
@@ -196,7 +196,6 @@ static void gfxhub_v2_0_init_tlb_regs(struct amdgpu_device *adev)
 			    ENABLE_ADVANCED_DRIVER_MODEL, 1);
 	tmp = REG_SET_FIELD(tmp, GCMC_VM_MX_L1_TLB_CNTL,
 			    SYSTEM_APERTURE_UNMAPPED_ACCESS, 0);
-	tmp = REG_SET_FIELD(tmp, GCMC_VM_MX_L1_TLB_CNTL, ECO_BITS, 0);
 	tmp = REG_SET_FIELD(tmp, GCMC_VM_MX_L1_TLB_CNTL,
 			    MTYPE, MTYPE_UC); /* UC, uncached */
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c
index e80d1dc43079..b4eddf6e98a6 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c
@@ -197,7 +197,6 @@ static void gfxhub_v2_1_init_tlb_regs(struct amdgpu_device *adev)
 			    ENABLE_ADVANCED_DRIVER_MODEL, 1);
 	tmp = REG_SET_FIELD(tmp, GCMC_VM_MX_L1_TLB_CNTL,
 			    SYSTEM_APERTURE_UNMAPPED_ACCESS, 0);
-	tmp = REG_SET_FIELD(tmp, GCMC_VM_MX_L1_TLB_CNTL, ECO_BITS, 0);
 	tmp = REG_SET_FIELD(tmp, GCMC_VM_MX_L1_TLB_CNTL,
 			    MTYPE, MTYPE_UC); /* UC, uncached */
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index cb82404df534..d84523cf5f75 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -1808,6 +1808,14 @@ static int gmc_v9_0_hw_fini(void *handle)
 		return 0;
 	}
 
+	/*
+	 * Pair the operations did in gmc_v9_0_hw_init and thus maintain
+	 * a correct cached state for GMC. Otherwise, the "gate" again
+	 * operation on S3 resuming will fail due to wrong cached state.
+	 */
+	if (adev->mmhub.funcs->update_power_gating)
+		adev->mmhub.funcs->update_power_gating(adev, false);
+
 	amdgpu_irq_put(adev, &adev->gmc.ecc_irq, 0);
 	amdgpu_irq_put(adev, &adev->gmc.vm_fault, 0);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
index a99953833820..1da2ec692057 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
@@ -145,7 +145,6 @@ static void mmhub_v1_0_init_tlb_regs(struct amdgpu_device *adev)
 			    ENABLE_ADVANCED_DRIVER_MODEL, 1);
 	tmp = REG_SET_FIELD(tmp, MC_VM_MX_L1_TLB_CNTL,
 			    SYSTEM_APERTURE_UNMAPPED_ACCESS, 0);
-	tmp = REG_SET_FIELD(tmp, MC_VM_MX_L1_TLB_CNTL, ECO_BITS, 0);
 	tmp = REG_SET_FIELD(tmp, MC_VM_MX_L1_TLB_CNTL,
 			    MTYPE, MTYPE_UC);/* XXX for emulation. */
 	tmp = REG_SET_FIELD(tmp, MC_VM_MX_L1_TLB_CNTL, ATC_EN, 1);
@@ -302,10 +301,10 @@ static void mmhub_v1_0_update_power_gating(struct amdgpu_device *adev,
 	if (amdgpu_sriov_vf(adev))
 		return;
 
-	if (enable && adev->pg_flags & AMD_PG_SUPPORT_MMHUB) {
-		amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_GMC, true);
-
-	}
+	if (adev->pg_flags & AMD_PG_SUPPORT_MMHUB)
+		amdgpu_dpm_set_powergating_by_smu(adev,
+						  AMD_IP_BLOCK_TYPE_GMC,
+						  enable);
 }
 
 static int mmhub_v1_0_gart_enable(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_7.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_7.c
index f80a14a1b82d..f5f7181f9af5 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_7.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_7.c
@@ -165,7 +165,6 @@ static void mmhub_v1_7_init_tlb_regs(struct amdgpu_device *adev)
 			    ENABLE_ADVANCED_DRIVER_MODEL, 1);
 	tmp = REG_SET_FIELD(tmp, MC_VM_MX_L1_TLB_CNTL,
 			    SYSTEM_APERTURE_UNMAPPED_ACCESS, 0);
-	tmp = REG_SET_FIELD(tmp, MC_VM_MX_L1_TLB_CNTL, ECO_BITS, 0);
 	tmp = REG_SET_FIELD(tmp, MC_VM_MX_L1_TLB_CNTL,
 			    MTYPE, MTYPE_UC);/* XXX for emulation. */
 	tmp = REG_SET_FIELD(tmp, MC_VM_MX_L1_TLB_CNTL, ATC_EN, 1);
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
index 25f8e93e5ec3..3718ff610ab2 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
@@ -267,7 +267,6 @@ static void mmhub_v2_0_init_tlb_regs(struct amdgpu_device *adev)
 			    ENABLE_ADVANCED_DRIVER_MODEL, 1);
 	tmp = REG_SET_FIELD(tmp, MMMC_VM_MX_L1_TLB_CNTL,
 			    SYSTEM_APERTURE_UNMAPPED_ACCESS, 0);
-	tmp = REG_SET_FIELD(tmp, MMMC_VM_MX_L1_TLB_CNTL, ECO_BITS, 0);
 	tmp = REG_SET_FIELD(tmp, MMMC_VM_MX_L1_TLB_CNTL,
 			    MTYPE, MTYPE_UC); /* UC, uncached */
 
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c
index a11d60ec6321..9e16da28505a 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c
@@ -194,7 +194,6 @@ static void mmhub_v2_3_init_tlb_regs(struct amdgpu_device *adev)
 			    ENABLE_ADVANCED_DRIVER_MODEL, 1);
 	tmp = REG_SET_FIELD(tmp, MMMC_VM_MX_L1_TLB_CNTL,
 			    SYSTEM_APERTURE_UNMAPPED_ACCESS, 0);
-	tmp = REG_SET_FIELD(tmp, MMMC_VM_MX_L1_TLB_CNTL, ECO_BITS, 0);
 	tmp = REG_SET_FIELD(tmp, MMMC_VM_MX_L1_TLB_CNTL,
 			    MTYPE, MTYPE_UC); /* UC, uncached */
 
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
index c4ef822bbe8c..ff49eeaf7882 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
@@ -190,8 +190,6 @@ static void mmhub_v9_4_init_tlb_regs(struct amdgpu_device *adev, int hubid)
 	tmp = REG_SET_FIELD(tmp, VMSHAREDVC0_MC_VM_MX_L1_TLB_CNTL,
 			    SYSTEM_APERTURE_UNMAPPED_ACCESS, 0);
 	tmp = REG_SET_FIELD(tmp, VMSHAREDVC0_MC_VM_MX_L1_TLB_CNTL,
-			    ECO_BITS, 0);
-	tmp = REG_SET_FIELD(tmp, VMSHAREDVC0_MC_VM_MX_L1_TLB_CNTL,
 			    MTYPE, MTYPE_UC);/* XXX for emulation. */
 	tmp = REG_SET_FIELD(tmp, VMSHAREDVC0_MC_VM_MX_L1_TLB_CNTL,
 			    ATC_EN, 1);
diff --git a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
index 1d8414c3fadb..38241cf0e1f1 100644
--- a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
@@ -160,6 +160,7 @@ static int navi10_ih_toggle_ring_interrupts(struct amdgpu_device *adev,
 
 	tmp = RREG32(ih_regs->ih_rb_cntl);
 	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, RB_ENABLE, (enable ? 1 : 0));
+	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, RB_GPU_TS_ENABLE, 1);
 	/* enable_intr field is only valid in ring0 */
 	if (ih == &adev->irq.ih)
 		tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, ENABLE_INTR, (enable ? 1 : 0));
@@ -275,10 +276,8 @@ static int navi10_ih_enable_ring(struct amdgpu_device *adev,
 	tmp = navi10_ih_rb_cntl(ih, tmp);
 	if (ih == &adev->irq.ih)
 		tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, RPTR_REARM, !!adev->irq.msi_enabled);
-	if (ih == &adev->irq.ih1) {
-		tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_ENABLE, 0);
+	if (ih == &adev->irq.ih1)
 		tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, RB_FULL_DRAIN_ENABLE, 1);
-	}
 
 	if (amdgpu_sriov_vf(adev) && amdgpu_sriov_reg_indirect_ih(adev)) {
 		if (psp_reg_program(&adev->psp, ih_regs->psp_reg_id, tmp)) {
@@ -319,7 +318,6 @@ static int navi10_ih_irq_init(struct amdgpu_device *adev)
 {
 	struct amdgpu_ih_ring *ih[] = {&adev->irq.ih, &adev->irq.ih1, &adev->irq.ih2};
 	u32 ih_chicken;
-	u32 tmp;
 	int ret;
 	int i;
 
@@ -363,15 +361,6 @@ static int navi10_ih_irq_init(struct amdgpu_device *adev)
 	adev->nbio.funcs->ih_doorbell_range(adev, ih[0]->use_doorbell,
 					    ih[0]->doorbell_index);
 
-	tmp = RREG32_SOC15(OSSSYS, 0, mmIH_STORM_CLIENT_LIST_CNTL);
-	tmp = REG_SET_FIELD(tmp, IH_STORM_CLIENT_LIST_CNTL,
-			    CLIENT18_IS_STORM_CLIENT, 1);
-	WREG32_SOC15(OSSSYS, 0, mmIH_STORM_CLIENT_LIST_CNTL, tmp);
-
-	tmp = RREG32_SOC15(OSSSYS, 0, mmIH_INT_FLOOD_CNTL);
-	tmp = REG_SET_FIELD(tmp, IH_INT_FLOOD_CNTL, FLOOD_CNTL_ENABLE, 1);
-	WREG32_SOC15(OSSSYS, 0, mmIH_INT_FLOOD_CNTL, tmp);
-
 	pci_set_master(adev->pdev);
 
 	/* enable interrupts */
@@ -420,12 +409,19 @@ static u32 navi10_ih_get_wptr(struct amdgpu_device *adev,
 	u32 wptr, tmp;
 	struct amdgpu_ih_regs *ih_regs;
 
-	wptr = le32_to_cpu(*ih->wptr_cpu);
-	ih_regs = &ih->ih_regs;
+	if (ih == &adev->irq.ih) {
+		/* Only ring0 supports writeback. On other rings fall back
+		 * to register-based code with overflow checking below.
+		 */
+		wptr = le32_to_cpu(*ih->wptr_cpu);
 
-	if (!REG_GET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW))
-		goto out;
+		if (!REG_GET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW))
+			goto out;
+	}
 
+	ih_regs = &ih->ih_regs;
+
+	/* Double check that the overflow wasn't already cleared. */
 	wptr = RREG32_NO_KIQ(ih_regs->ih_rb_wptr);
 	if (!REG_GET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW))
 		goto out;
@@ -513,15 +509,11 @@ static int navi10_ih_self_irq(struct amdgpu_device *adev,
 			      struct amdgpu_irq_src *source,
 			      struct amdgpu_iv_entry *entry)
 {
-	uint32_t wptr = cpu_to_le32(entry->src_data[0]);
-
 	switch (entry->ring_id) {
 	case 1:
-		*adev->irq.ih1.wptr_cpu = wptr;
 		schedule_work(&adev->irq.ih1_work);
 		break;
 	case 2:
-		*adev->irq.ih2.wptr_cpu = wptr;
 		schedule_work(&adev->irq.ih2_work);
 		break;
 	default: break;
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c b/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c
index 4ecd2b5808ce..ee7cab37dfd5 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c
@@ -359,6 +359,10 @@ static void nbio_v2_3_init_registers(struct amdgpu_device *adev)
 
 	if (def != data)
 		WREG32_PCIE(smnPCIE_CONFIG_CNTL, data);
+
+	if (amdgpu_sriov_vf(adev))
+		adev->rmmio_remap.reg_offset = SOC15_REG_OFFSET(NBIO, 0,
+			mmBIF_BX_DEV0_EPF0_VF0_HDP_MEM_COHERENCY_FLUSH_CNTL) << 2;
 }
 
 #define NAVI10_PCIE__LC_L0S_INACTIVITY_DEFAULT		0x00000000 // off by default, no gains over L1
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c b/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c
index 0d2d629e2d6a..4bbacf1be25a 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c
@@ -276,6 +276,10 @@ static void nbio_v6_1_init_registers(struct amdgpu_device *adev)
 
 	if (def != data)
 		WREG32_PCIE(smnPCIE_CI_CNTL, data);
+
+	if (amdgpu_sriov_vf(adev))
+		adev->rmmio_remap.reg_offset = SOC15_REG_OFFSET(NBIO, 0,
+			mmBIF_BX_DEV0_EPF0_VF0_HDP_MEM_COHERENCY_FLUSH_CNTL) << 2;
 }
 
 static void nbio_v6_1_program_ltr(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.c
index 3c00666a13e1..37a4039fdfc5 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.c
@@ -273,7 +273,9 @@ const struct nbio_hdp_flush_reg nbio_v7_0_hdp_flush_reg = {
 
 static void nbio_v7_0_init_registers(struct amdgpu_device *adev)
 {
-
+	if (amdgpu_sriov_vf(adev))
+		adev->rmmio_remap.reg_offset =
+			SOC15_REG_OFFSET(NBIO, 0, mmHDP_MEM_COHERENCY_FLUSH_CNTL) << 2;
 }
 
 const struct amdgpu_nbio_funcs nbio_v7_0_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_2.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_2.c
index 8f2a315e7c73..3444332ea110 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_2.c
@@ -371,6 +371,10 @@ static void nbio_v7_2_init_registers(struct amdgpu_device *adev)
 		if (def != data)
 			WREG32_PCIE_PORT(SOC15_REG_OFFSET(NBIO, 0, regPCIE_CONFIG_CNTL), data);
 	}
+
+	if (amdgpu_sriov_vf(adev))
+		adev->rmmio_remap.reg_offset = SOC15_REG_OFFSET(NBIO, 0,
+			regBIF_BX_PF0_HDP_MEM_COHERENCY_FLUSH_CNTL) << 2;
 }
 
 const struct amdgpu_nbio_funcs nbio_v7_2_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
index b8bd03d16dba..dc5e93756fea 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
@@ -362,7 +362,9 @@ const struct nbio_hdp_flush_reg nbio_v7_4_hdp_flush_reg_ald = {
 
 static void nbio_v7_4_init_registers(struct amdgpu_device *adev)
 {
-
+	if (amdgpu_sriov_vf(adev))
+		adev->rmmio_remap.reg_offset = SOC15_REG_OFFSET(NBIO, 0,
+			mmBIF_BX_DEV0_EPF0_VF0_HDP_MEM_COHERENCY_FLUSH_CNTL) << 2;
 }
 
 static void nbio_v7_4_handle_ras_controller_intr_no_bifring(struct amdgpu_device *adev)
@@ -692,6 +694,9 @@ static void nbio_v7_4_program_aspm(struct amdgpu_device *adev)
 {
 	uint32_t def, data;
 
+	if (adev->ip_versions[NBIO_HWIP][0] == IP_VERSION(7, 4, 4))
+		return;
+
 	def = data = RREG32_PCIE(smnPCIE_LC_CNTL);
 	data &= ~PCIE_LC_CNTL__LC_L1_INACTIVITY_MASK;
 	data &= ~PCIE_LC_CNTL__LC_L0S_INACTIVITY_MASK;
diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c
index 59eafa31c626..2ec1ffb36b1f 100644
--- a/drivers/gpu/drm/amd/amdgpu/nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/nv.c
@@ -183,6 +183,7 @@ static int nv_query_video_codecs(struct amdgpu_device *adev, bool encode,
 	switch (adev->ip_versions[UVD_HWIP][0]) {
 	case IP_VERSION(3, 0, 0):
 	case IP_VERSION(3, 0, 64):
+	case IP_VERSION(3, 0, 192):
 		if (amdgpu_sriov_vf(adev)) {
 			if (encode)
 				*codecs = &sriov_sc_video_codecs_encode;
@@ -731,8 +732,10 @@ static int nv_common_early_init(void *handle)
 #define MMIO_REG_HOLE_OFFSET (0x80000 - PAGE_SIZE)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	adev->rmmio_remap.reg_offset = MMIO_REG_HOLE_OFFSET;
-	adev->rmmio_remap.bus_addr = adev->rmmio_base + MMIO_REG_HOLE_OFFSET;
+	if (!amdgpu_sriov_vf(adev)) {
+		adev->rmmio_remap.reg_offset = MMIO_REG_HOLE_OFFSET;
+		adev->rmmio_remap.bus_addr = adev->rmmio_base + MMIO_REG_HOLE_OFFSET;
+	}
 	adev->smc_rreg = NULL;
 	adev->smc_wreg = NULL;
 	adev->pcie_rreg = &nv_pcie_rreg;
@@ -1032,7 +1035,7 @@ static int nv_common_hw_init(void *handle)
 	 * for the purpose of expose those registers
 	 * to process space
 	 */
-	if (adev->nbio.funcs->remap_hdp_registers)
+	if (adev->nbio.funcs->remap_hdp_registers && !amdgpu_sriov_vf(adev))
 		adev->nbio.funcs->remap_hdp_registers(adev);
 	/* enable the doorbell aperture */
 	nv_enable_doorbell_aperture(adev, true);
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index 0c316a2d42ed..de9b55383e9f 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -971,8 +971,10 @@ static int soc15_common_early_init(void *handle)
 #define MMIO_REG_HOLE_OFFSET (0x80000 - PAGE_SIZE)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	adev->rmmio_remap.reg_offset = MMIO_REG_HOLE_OFFSET;
-	adev->rmmio_remap.bus_addr = adev->rmmio_base + MMIO_REG_HOLE_OFFSET;
+	if (!amdgpu_sriov_vf(adev)) {
+		adev->rmmio_remap.reg_offset = MMIO_REG_HOLE_OFFSET;
+		adev->rmmio_remap.bus_addr = adev->rmmio_base + MMIO_REG_HOLE_OFFSET;
+	}
 	adev->smc_rreg = NULL;
 	adev->smc_wreg = NULL;
 	adev->pcie_rreg = &soc15_pcie_rreg;
@@ -1285,7 +1287,7 @@ static int soc15_common_hw_init(void *handle)
 	 * for the purpose of expose those registers
 	 * to process space
 	 */
-	if (adev->nbio.funcs->remap_hdp_registers)
+	if (adev->nbio.funcs->remap_hdp_registers && !amdgpu_sriov_vf(adev))
 		adev->nbio.funcs->remap_hdp_registers(adev);
 
 	/* enable the doorbell aperture */
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index 003ba6a373ff..93e33dd84dd4 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -1226,6 +1226,11 @@ static int stop_cpsch(struct device_queue_manager *dqm)
 	bool hanging;
 
 	dqm_lock(dqm);
+	if (!dqm->sched_running) {
+		dqm_unlock(dqm);
+		return 0;
+	}
+
 	if (!dqm->is_hws_hang)
 		unmap_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES, 0);
 	hanging = dqm->is_hws_hang || dqm->is_resetting;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 94e92c0812db..8fd48d0ed240 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -766,7 +766,7 @@ struct svm_range_list {
 	struct list_head		deferred_range_list;
 	spinlock_t			deferred_list_lock;
 	atomic_t			evicted_ranges;
-	bool				drain_pagefaults;
+	atomic_t			drain_pagefaults;
 	struct delayed_work		restore_work;
 	DECLARE_BITMAP(bitmap_supported, MAX_GPU_INSTANCE);
 	struct task_struct 		*faulting_task;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index 16137c4247bb..3cb4681c5f53 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -1574,7 +1574,6 @@ retry_flush_work:
 static void svm_range_restore_work(struct work_struct *work)
 {
 	struct delayed_work *dwork = to_delayed_work(work);
-	struct amdkfd_process_info *process_info;
 	struct svm_range_list *svms;
 	struct svm_range *prange;
 	struct kfd_process *p;
@@ -1594,12 +1593,10 @@ static void svm_range_restore_work(struct work_struct *work)
 	 * the lifetime of this thread, kfd_process and mm will be valid.
 	 */
 	p = container_of(svms, struct kfd_process, svms);
-	process_info = p->kgd_process_info;
 	mm = p->mm;
 	if (!mm)
 		return;
 
-	mutex_lock(&process_info->lock);
 	svm_range_list_lock_and_flush_work(svms, mm);
 	mutex_lock(&svms->lock);
 
@@ -1652,7 +1649,6 @@ static void svm_range_restore_work(struct work_struct *work)
 out_reschedule:
 	mutex_unlock(&svms->lock);
 	mmap_write_unlock(mm);
-	mutex_unlock(&process_info->lock);
 
 	/* If validation failed, reschedule another attempt */
 	if (evicted_ranges) {
@@ -1968,10 +1964,16 @@ static void svm_range_drain_retry_fault(struct svm_range_list *svms)
 	struct kfd_process_device *pdd;
 	struct amdgpu_device *adev;
 	struct kfd_process *p;
+	int drain;
 	uint32_t i;
 
 	p = container_of(svms, struct kfd_process, svms);
 
+restart:
+	drain = atomic_read(&svms->drain_pagefaults);
+	if (!drain)
+		return;
+
 	for_each_set_bit(i, svms->bitmap_supported, p->n_pdds) {
 		pdd = p->pdds[i];
 		if (!pdd)
@@ -1983,6 +1985,8 @@ static void svm_range_drain_retry_fault(struct svm_range_list *svms)
 		amdgpu_ih_wait_on_checkpoint_process(adev, &adev->irq.ih1);
 		pr_debug("drain retry fault gpu %d svms 0x%p done\n", i, svms);
 	}
+	if (atomic_cmpxchg(&svms->drain_pagefaults, drain, 0) != drain)
+		goto restart;
 }
 
 static void svm_range_deferred_list_work(struct work_struct *work)
@@ -1990,43 +1994,41 @@ static void svm_range_deferred_list_work(struct work_struct *work)
 	struct svm_range_list *svms;
 	struct svm_range *prange;
 	struct mm_struct *mm;
+	struct kfd_process *p;
 
 	svms = container_of(work, struct svm_range_list, deferred_list_work);
 	pr_debug("enter svms 0x%p\n", svms);
 
+	p = container_of(svms, struct kfd_process, svms);
+	/* Avoid mm is gone when inserting mmu notifier */
+	mm = get_task_mm(p->lead_thread);
+	if (!mm) {
+		pr_debug("svms 0x%p process mm gone\n", svms);
+		return;
+	}
+retry:
+	mmap_write_lock(mm);
+
+	/* Checking for the need to drain retry faults must be inside
+	 * mmap write lock to serialize with munmap notifiers.
+	 */
+	if (unlikely(atomic_read(&svms->drain_pagefaults))) {
+		mmap_write_unlock(mm);
+		svm_range_drain_retry_fault(svms);
+		goto retry;
+	}
+
 	spin_lock(&svms->deferred_list_lock);
 	while (!list_empty(&svms->deferred_range_list)) {
 		prange = list_first_entry(&svms->deferred_range_list,
 					  struct svm_range, deferred_list);
+		list_del_init(&prange->deferred_list);
 		spin_unlock(&svms->deferred_list_lock);
+
 		pr_debug("prange 0x%p [0x%lx 0x%lx] op %d\n", prange,
 			 prange->start, prange->last, prange->work_item.op);
 
-		mm = prange->work_item.mm;
-retry:
-		mmap_write_lock(mm);
 		mutex_lock(&svms->lock);
-
-		/* Checking for the need to drain retry faults must be in
-		 * mmap write lock to serialize with munmap notifiers.
-		 *
-		 * Remove from deferred_list must be inside mmap write lock,
-		 * otherwise, svm_range_list_lock_and_flush_work may hold mmap
-		 * write lock, and continue because deferred_list is empty, then
-		 * deferred_list handle is blocked by mmap write lock.
-		 */
-		spin_lock(&svms->deferred_list_lock);
-		if (unlikely(svms->drain_pagefaults)) {
-			svms->drain_pagefaults = false;
-			spin_unlock(&svms->deferred_list_lock);
-			mutex_unlock(&svms->lock);
-			mmap_write_unlock(mm);
-			svm_range_drain_retry_fault(svms);
-			goto retry;
-		}
-		list_del_init(&prange->deferred_list);
-		spin_unlock(&svms->deferred_list_lock);
-
 		mutex_lock(&prange->migrate_mutex);
 		while (!list_empty(&prange->child_list)) {
 			struct svm_range *pchild;
@@ -2042,12 +2044,13 @@ retry:
 
 		svm_range_handle_list_op(svms, prange);
 		mutex_unlock(&svms->lock);
-		mmap_write_unlock(mm);
 
 		spin_lock(&svms->deferred_list_lock);
 	}
 	spin_unlock(&svms->deferred_list_lock);
 
+	mmap_write_unlock(mm);
+	mmput(mm);
 	pr_debug("exit svms 0x%p\n", svms);
 }
 
@@ -2056,12 +2059,6 @@ svm_range_add_list_work(struct svm_range_list *svms, struct svm_range *prange,
 			struct mm_struct *mm, enum svm_work_list_ops op)
 {
 	spin_lock(&svms->deferred_list_lock);
-	/* Make sure pending page faults are drained in the deferred worker
-	 * before the range is freed to avoid straggler interrupts on
-	 * unmapped memory causing "phantom faults".
-	 */
-	if (op == SVM_OP_UNMAP_RANGE)
-		svms->drain_pagefaults = true;
 	/* if prange is on the deferred list */
 	if (!list_empty(&prange->deferred_list)) {
 		pr_debug("update exist prange 0x%p work op %d\n", prange, op);
@@ -2140,6 +2137,12 @@ svm_range_unmap_from_cpu(struct mm_struct *mm, struct svm_range *prange,
 	pr_debug("svms 0x%p prange 0x%p [0x%lx 0x%lx] [0x%lx 0x%lx]\n", svms,
 		 prange, prange->start, prange->last, start, last);
 
+	/* Make sure pending page faults are drained in the deferred worker
+	 * before the range is freed to avoid straggler interrupts on
+	 * unmapped memory causing "phantom faults".
+	 */
+	atomic_inc(&svms->drain_pagefaults);
+
 	unmap_parent = start <= prange->start && last >= prange->last;
 
 	list_for_each_entry(pchild, &prange->child_list, child_list) {
@@ -2559,20 +2562,13 @@ svm_range_count_fault(struct amdgpu_device *adev, struct kfd_process *p,
 }
 
 static bool
-svm_fault_allowed(struct mm_struct *mm, uint64_t addr, bool write_fault)
+svm_fault_allowed(struct vm_area_struct *vma, bool write_fault)
 {
 	unsigned long requested = VM_READ;
-	struct vm_area_struct *vma;
 
 	if (write_fault)
 		requested |= VM_WRITE;
 
-	vma = find_vma(mm, addr << PAGE_SHIFT);
-	if (!vma || (addr << PAGE_SHIFT) < vma->vm_start) {
-		pr_debug("address 0x%llx VMA is removed\n", addr);
-		return true;
-	}
-
 	pr_debug("requested 0x%lx, vma permission flags 0x%lx\n", requested,
 		vma->vm_flags);
 	return (vma->vm_flags & requested) == requested;
@@ -2590,6 +2586,7 @@ svm_range_restore_pages(struct amdgpu_device *adev, unsigned int pasid,
 	int32_t best_loc;
 	int32_t gpuidx = MAX_GPU_INSTANCE;
 	bool write_locked = false;
+	struct vm_area_struct *vma;
 	int r = 0;
 
 	if (!KFD_IS_SVM_API_SUPPORTED(adev->kfd.dev)) {
@@ -2600,7 +2597,7 @@ svm_range_restore_pages(struct amdgpu_device *adev, unsigned int pasid,
 	p = kfd_lookup_process_by_pasid(pasid);
 	if (!p) {
 		pr_debug("kfd process not founded pasid 0x%x\n", pasid);
-		return -ESRCH;
+		return 0;
 	}
 	if (!p->xnack_enabled) {
 		pr_debug("XNACK not enabled for pasid 0x%x\n", pasid);
@@ -2611,10 +2608,19 @@ svm_range_restore_pages(struct amdgpu_device *adev, unsigned int pasid,
 
 	pr_debug("restoring svms 0x%p fault address 0x%llx\n", svms, addr);
 
+	if (atomic_read(&svms->drain_pagefaults)) {
+		pr_debug("draining retry fault, drop fault 0x%llx\n", addr);
+		r = 0;
+		goto out;
+	}
+
+	/* p->lead_thread is available as kfd_process_wq_release flush the work
+	 * before releasing task ref.
+	 */
 	mm = get_task_mm(p->lead_thread);
 	if (!mm) {
 		pr_debug("svms 0x%p failed to get mm\n", svms);
-		r = -ESRCH;
+		r = 0;
 		goto out;
 	}
 
@@ -2652,6 +2658,7 @@ retry_write_locked:
 
 	if (svm_range_skip_recover(prange)) {
 		amdgpu_gmc_filter_faults_remove(adev, addr, pasid);
+		r = 0;
 		goto out_unlock_range;
 	}
 
@@ -2660,10 +2667,21 @@ retry_write_locked:
 	if (timestamp < AMDGPU_SVM_RANGE_RETRY_FAULT_PENDING) {
 		pr_debug("svms 0x%p [0x%lx %lx] already restored\n",
 			 svms, prange->start, prange->last);
+		r = 0;
 		goto out_unlock_range;
 	}
 
-	if (!svm_fault_allowed(mm, addr, write_fault)) {
+	/* __do_munmap removed VMA, return success as we are handling stale
+	 * retry fault.
+	 */
+	vma = find_vma(mm, addr << PAGE_SHIFT);
+	if (!vma || (addr << PAGE_SHIFT) < vma->vm_start) {
+		pr_debug("address 0x%llx VMA is removed\n", addr);
+		r = 0;
+		goto out_unlock_range;
+	}
+
+	if (!svm_fault_allowed(vma, write_fault)) {
 		pr_debug("fault addr 0x%llx no %s permission\n", addr,
 			write_fault ? "write" : "read");
 		r = -EPERM;
@@ -2741,6 +2759,14 @@ void svm_range_list_fini(struct kfd_process *p)
 	/* Ensure list work is finished before process is destroyed */
 	flush_work(&p->svms.deferred_list_work);
 
+	/*
+	 * Ensure no retry fault comes in afterwards, as page fault handler will
+	 * not find kfd process and take mm lock to recover fault.
+	 */
+	atomic_inc(&p->svms.drain_pagefaults);
+	svm_range_drain_retry_fault(&p->svms);
+
+
 	list_for_each_entry_safe(prange, next, &p->svms.list, list) {
 		svm_range_unlink(prange);
 		svm_range_remove_notifier(prange);
@@ -2761,6 +2787,7 @@ int svm_range_list_init(struct kfd_process *p)
 	mutex_init(&svms->lock);
 	INIT_LIST_HEAD(&svms->list);
 	atomic_set(&svms->evicted_ranges, 0);
+	atomic_set(&svms->drain_pagefaults, 0);
 	INIT_DELAYED_WORK(&svms->restore_work, svm_range_restore_work);
 	INIT_WORK(&svms->deferred_list_work, svm_range_deferred_list_work);
 	INIT_LIST_HEAD(&svms->deferred_range_list);
@@ -3150,7 +3177,6 @@ static int
 svm_range_set_attr(struct kfd_process *p, uint64_t start, uint64_t size,
 		   uint32_t nattr, struct kfd_ioctl_svm_attribute *attrs)
 {
-	struct amdkfd_process_info *process_info = p->kgd_process_info;
 	struct mm_struct *mm = current->mm;
 	struct list_head update_list;
 	struct list_head insert_list;
@@ -3169,8 +3195,6 @@ svm_range_set_attr(struct kfd_process *p, uint64_t start, uint64_t size,
 
 	svms = &p->svms;
 
-	mutex_lock(&process_info->lock);
-
 	svm_range_list_lock_and_flush_work(svms, mm);
 
 	r = svm_range_is_valid(p, start, size);
@@ -3246,8 +3270,6 @@ out_unlock_range:
 	mutex_unlock(&svms->lock);
 	mmap_read_unlock(mm);
 out:
-	mutex_unlock(&process_info->lock);
-
 	pr_debug("pasid 0x%x svms 0x%p [0x%llx 0x%llx] done, r=%d\n", p->pasid,
 		 &p->svms, start, start + size - 1, r);
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index c911b30de658..e727f1dd2a9a 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -51,6 +51,7 @@
 #include <drm/drm_hdcp.h>
 #endif
 #include "amdgpu_pm.h"
+#include "amdgpu_atombios.h"
 
 #include "amd_shared.h"
 #include "amdgpu_dm_irq.h"
@@ -1050,6 +1051,11 @@ static int dm_dmub_hw_init(struct amdgpu_device *adev)
 		return 0;
 	}
 
+	/* Reset DMCUB if it was previously running - before we overwrite its memory. */
+	status = dmub_srv_hw_reset(dmub_srv);
+	if (status != DMUB_STATUS_OK)
+		DRM_WARN("Error resetting DMUB HW: %d\n", status);
+
 	hdr = (const struct dmcub_firmware_header_v1_0 *)dmub_fw->data;
 
 	fw_inst_const = dmub_fw->data +
@@ -2561,6 +2567,23 @@ static int dm_resume(void *handle)
 	if (amdgpu_in_reset(adev)) {
 		dc_state = dm->cached_dc_state;
 
+		/*
+		 * The dc->current_state is backed up into dm->cached_dc_state
+		 * before we commit 0 streams.
+		 *
+		 * DC will clear link encoder assignments on the real state
+		 * but the changes won't propagate over to the copy we made
+		 * before the 0 streams commit.
+		 *
+		 * DC expects that link encoder assignments are *not* valid
+		 * when committing a state, so as a workaround it needs to be
+		 * cleared here.
+		 */
+		link_enc_cfg_init(dm->dc, dc_state);
+
+		if (dc_enable_dmub_notifications(adev->dm.dc))
+			amdgpu_dm_outbox_init(adev);
+
 		r = dm_dmub_hw_init(adev);
 		if (r)
 			DRM_ERROR("DMUB interface failed to initialize: status=%d\n", r);
@@ -2572,8 +2595,8 @@ static int dm_resume(void *handle)
 
 		for (i = 0; i < dc_state->stream_count; i++) {
 			dc_state->streams[i]->mode_changed = true;
-			for (j = 0; j < dc_state->stream_status->plane_count; j++) {
-				dc_state->stream_status->plane_states[j]->update_flags.raw
+			for (j = 0; j < dc_state->stream_status[i].plane_count; j++) {
+				dc_state->stream_status[i].plane_states[j]->update_flags.raw
 					= 0xffffffff;
 			}
 		}
@@ -2608,6 +2631,10 @@ static int dm_resume(void *handle)
 	/* TODO: Remove dc_state->dccg, use dc->dccg directly. */
 	dc_resource_state_construct(dm->dc, dm_state->context);
 
+	/* Re-enable outbox interrupts for DPIA. */
+	if (dc_enable_dmub_notifications(adev->dm.dc))
+		amdgpu_dm_outbox_init(adev);
+
 	/* Before powering on DC we need to re-initialize DMUB. */
 	r = dm_dmub_hw_init(adev);
 	if (r)
@@ -3909,6 +3936,9 @@ static int amdgpu_dm_backlight_set_level(struct amdgpu_display_manager *dm,
 	caps = dm->backlight_caps[bl_idx];
 
 	dm->brightness[bl_idx] = user_brightness;
+	/* update scratch register */
+	if (bl_idx == 0)
+		amdgpu_atombios_scratch_regs_set_backlight_level(dm->adev, dm->brightness[bl_idx]);
 	brightness = convert_brightness_from_user(&caps, dm->brightness[bl_idx]);
 	link = (struct dc_link *)dm->backlight_link[bl_idx];
 
@@ -4242,7 +4272,8 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev)
 		} else if (dc_link_detect(link, DETECT_REASON_BOOT)) {
 			amdgpu_dm_update_connector_after_detect(aconnector);
 			register_backlight_device(dm, link);
-
+			if (dm->num_of_edps)
+				update_connector_ext_caps(aconnector);
 			if (psr_feature_enabled)
 				amdgpu_dm_set_psr_caps(link);
 		}
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.c
index cce062adc439..8a441a22c46e 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.c
@@ -314,6 +314,14 @@ int amdgpu_dm_crtc_set_crc_source(struct drm_crtc *crtc, const char *src_name)
 			ret = -EINVAL;
 			goto cleanup;
 		}
+
+		if ((aconn->base.connector_type != DRM_MODE_CONNECTOR_DisplayPort) &&
+				(aconn->base.connector_type != DRM_MODE_CONNECTOR_eDP)) {
+			DRM_DEBUG_DRIVER("No DP connector available for CRC source\n");
+			ret = -EINVAL;
+			goto cleanup;
+		}
+
 	}
 
 #if defined(CONFIG_DRM_AMD_SECURE_DISPLAY)
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
index 32a5ce09a62a..cc34a35d0bcb 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
@@ -36,6 +36,8 @@
 #include "dm_helpers.h"
 
 #include "dc_link_ddc.h"
+#include "ddc_service_types.h"
+#include "dpcd_defs.h"
 
 #include "i2caux_interface.h"
 #include "dmub_cmd.h"
@@ -157,6 +159,16 @@ static const struct drm_connector_funcs dm_dp_mst_connector_funcs = {
 };
 
 #if defined(CONFIG_DRM_AMD_DC_DCN)
+static bool needs_dsc_aux_workaround(struct dc_link *link)
+{
+	if (link->dpcd_caps.branch_dev_id == DP_BRANCH_DEVICE_ID_90CC24 &&
+	    (link->dpcd_caps.dpcd_rev.raw == DPCD_REV_14 || link->dpcd_caps.dpcd_rev.raw == DPCD_REV_12) &&
+	    link->dpcd_caps.sink_count.bits.SINK_COUNT >= 2)
+		return true;
+
+	return false;
+}
+
 static bool validate_dsc_caps_on_connector(struct amdgpu_dm_connector *aconnector)
 {
 	struct dc_sink *dc_sink = aconnector->dc_sink;
@@ -166,7 +178,7 @@ static bool validate_dsc_caps_on_connector(struct amdgpu_dm_connector *aconnecto
 	u8 *dsc_branch_dec_caps = NULL;
 
 	aconnector->dsc_aux = drm_dp_mst_dsc_aux_for_port(port);
-#if defined(CONFIG_HP_HOOK_WORKAROUND)
+
 	/*
 	 * drm_dp_mst_dsc_aux_for_port() will return NULL for certain configs
 	 * because it only check the dsc/fec caps of the "port variable" and not the dock
@@ -176,10 +188,10 @@ static bool validate_dsc_caps_on_connector(struct amdgpu_dm_connector *aconnecto
 	 * Workaround: explicitly check the use case above and use the mst dock's aux as dsc_aux
 	 *
 	 */
-
-	if (!aconnector->dsc_aux && !port->parent->port_parent)
+	if (!aconnector->dsc_aux && !port->parent->port_parent &&
+	    needs_dsc_aux_workaround(aconnector->dc_link))
 		aconnector->dsc_aux = &aconnector->mst_port->dm_dp_aux.aux;
-#endif
+
 	if (!aconnector->dsc_aux)
 		return false;
 
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
index 60544788e911..c8457babfdea 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
@@ -758,6 +758,18 @@ static bool detect_dp(struct dc_link *link,
 			dal_ddc_service_set_transaction_type(link->ddc,
 							     sink_caps->transaction_type);
 
+#if defined(CONFIG_DRM_AMD_DC_DCN)
+			/* Apply work around for tunneled MST on certain USB4 docks. Always use DSC if dock
+			 * reports DSC support.
+			 */
+			if (link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA &&
+					link->type == dc_connection_mst_branch &&
+					link->dpcd_caps.branch_dev_id == DP_BRANCH_DEVICE_ID_90CC24 &&
+					link->dpcd_caps.dsc_caps.dsc_basic_caps.fields.dsc_support.DSC_SUPPORT &&
+					!link->dc->debug.dpia_debug.bits.disable_mst_dsc_work_around)
+				link->wa_flags.dpia_mst_dsc_always_on = true;
+#endif
+
 #if defined(CONFIG_DRM_AMD_DC_HDCP)
 			/* In case of fallback to SST when topology discovery below fails
 			 * HDCP caps will be querried again later by the upper layer (caller
@@ -1203,6 +1215,10 @@ static bool dc_link_detect_helper(struct dc_link *link,
 			LINK_INFO("link=%d, mst branch is now Disconnected\n",
 				  link->link_index);
 
+			/* Disable work around which keeps DSC on for tunneled MST on certain USB4 docks. */
+			if (link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA)
+				link->wa_flags.dpia_mst_dsc_always_on = false;
+
 			dm_helpers_dp_mst_stop_top_mgr(link->ctx, link);
 
 			link->mst_stream_alloc_table.stream_count = 0;
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
index cb7bf9148904..13bc69d6b679 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
@@ -2138,7 +2138,7 @@ static enum link_training_result dp_perform_8b_10b_link_training(
 		}
 
 		for (lane = 0; lane < (uint8_t)lt_settings->link_settings.lane_count; lane++)
-			lt_settings->dpcd_lane_settings[lane].bits.VOLTAGE_SWING_SET = VOLTAGE_SWING_LEVEL0;
+			lt_settings->dpcd_lane_settings[lane].raw = 0;
 	}
 
 	if (status == LINK_TRAINING_SUCCESS) {
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
index c32fdccd4d92..e2d9a46d0e1a 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
@@ -1664,6 +1664,10 @@ bool dc_is_stream_unchanged(
 	if (old_stream->ignore_msa_timing_param != stream->ignore_msa_timing_param)
 		return false;
 
+	// Only Have Audio left to check whether it is same or not. This is a corner case for Tiled sinks
+	if (old_stream->audio_info.mode_count != stream->audio_info.mode_count)
+		return false;
+
 	return true;
 }
 
@@ -2252,16 +2256,6 @@ enum dc_status dc_validate_global_state(
 
 	if (!new_ctx)
 		return DC_ERROR_UNEXPECTED;
-#if defined(CONFIG_DRM_AMD_DC_DCN)
-
-	/*
-	 * Update link encoder to stream assignment.
-	 * TODO: Split out reason allocation from validation.
-	 */
-	if (dc->res_pool->funcs->link_encs_assign && fast_validate == false)
-		dc->res_pool->funcs->link_encs_assign(
-			dc, new_ctx, new_ctx->streams, new_ctx->stream_count);
-#endif
 
 	if (dc->res_pool->funcs->validate_global) {
 		result = dc->res_pool->funcs->validate_global(dc, new_ctx);
@@ -2313,6 +2307,16 @@ enum dc_status dc_validate_global_state(
 		if (!dc->res_pool->funcs->validate_bandwidth(dc, new_ctx, fast_validate))
 			result = DC_FAIL_BANDWIDTH_VALIDATE;
 
+#if defined(CONFIG_DRM_AMD_DC_DCN)
+	/*
+	 * Only update link encoder to stream assignment after bandwidth validation passed.
+	 * TODO: Split out assignment and validation.
+	 */
+	if (result == DC_OK && dc->res_pool->funcs->link_encs_assign && fast_validate == false)
+		dc->res_pool->funcs->link_encs_assign(
+			dc, new_ctx, new_ctx->streams, new_ctx->stream_count);
+#endif
+
 	return result;
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 3aac3f4a2852..618e7989176f 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -508,7 +508,8 @@ union dpia_debug_options {
 		uint32_t disable_dpia:1;
 		uint32_t force_non_lttpr:1;
 		uint32_t extend_aux_rd_interval:1;
-		uint32_t reserved:29;
+		uint32_t disable_mst_dsc_work_around:1;
+		uint32_t reserved:28;
 	} bits;
 	uint32_t raw;
 };
diff --git a/drivers/gpu/drm/amd/display/dc/dc_link.h b/drivers/gpu/drm/amd/display/dc/dc_link.h
index 180ecd860296..fad3d883ed89 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_link.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_link.h
@@ -191,6 +191,8 @@ struct dc_link {
 		bool dp_skip_DID2;
 		bool dp_skip_reset_segment;
 		bool dp_mot_reset_segment;
+		/* Some USB4 docks do not handle turning off MST DSC once it has been enabled. */
+		bool dpia_mst_dsc_always_on;
 	} wa_flags;
 	struct link_mst_stream_allocation_table mst_stream_alloc_table;
 
@@ -224,6 +226,8 @@ static inline void get_edp_links(const struct dc *dc,
 	*edp_num = 0;
 	for (i = 0; i < dc->link_count; i++) {
 		// report any eDP links, even unconnected DDI's
+		if (!dc->links[i])
+			continue;
 		if (dc->links[i]->connector_signal == SIGNAL_TYPE_EDP) {
 			edp_links[*edp_num] = dc->links[i];
 			if (++(*edp_num) == MAX_NUM_EDP)
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
index 0b788d794fb3..04d7bddc915b 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
@@ -1637,7 +1637,7 @@ void dcn10_reset_hw_ctx_wrap(
 
 			dcn10_reset_back_end_for_pipe(dc, pipe_ctx_old, dc->current_state);
 			if (hws->funcs.enable_stream_gating)
-				hws->funcs.enable_stream_gating(dc, pipe_ctx);
+				hws->funcs.enable_stream_gating(dc, pipe_ctx_old);
 			if (old_clk)
 				old_clk->funcs->cs_power_down(old_clk);
 		}
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
index 4f88376a118f..e6af99ae3d9f 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
@@ -2270,7 +2270,7 @@ void dcn20_reset_hw_ctx_wrap(
 
 			dcn20_reset_back_end_for_pipe(dc, pipe_ctx_old, dc->current_state);
 			if (hws->funcs.enable_stream_gating)
-				hws->funcs.enable_stream_gating(dc, pipe_ctx);
+				hws->funcs.enable_stream_gating(dc, pipe_ctx_old);
 			if (old_clk)
 				old_clk->funcs->cs_power_down(old_clk);
 		}
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c
index 5dd1ce9ddb53..4d4ac4ceb1e8 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c
@@ -602,7 +602,7 @@ void dcn31_reset_hw_ctx_wrap(
 
 			dcn31_reset_back_end_for_pipe(dc, pipe_ctx_old, dc->current_state);
 			if (hws->funcs.enable_stream_gating)
-				hws->funcs.enable_stream_gating(dc, pipe_ctx);
+				hws->funcs.enable_stream_gating(dc, pipe_ctx_old);
 			if (old_clk)
 				old_clk->funcs->cs_power_down(old_clk);
 		}
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c
index 05335a8c3c2d..4f6e639e9353 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c
@@ -101,6 +101,7 @@ static const struct hw_sequencer_funcs dcn31_funcs = {
 	.z10_restore = dcn31_z10_restore,
 	.z10_save_init = dcn31_z10_save_init,
 	.set_disp_pattern_generator = dcn30_set_disp_pattern_generator,
+	.exit_optimized_pwr_state = dcn21_exit_optimized_pwr_state,
 	.update_visual_confirm_color = dcn20_update_visual_confirm_color,
 };
 
diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h
index f1a46d16f7ea..4b9e68a79f06 100644
--- a/drivers/gpu/drm/amd/include/amd_shared.h
+++ b/drivers/gpu/drm/amd/include/amd_shared.h
@@ -98,7 +98,8 @@ enum amd_ip_block_type {
 	AMD_IP_BLOCK_TYPE_ACP,
 	AMD_IP_BLOCK_TYPE_VCN,
 	AMD_IP_BLOCK_TYPE_MES,
-	AMD_IP_BLOCK_TYPE_JPEG
+	AMD_IP_BLOCK_TYPE_JPEG,
+	AMD_IP_BLOCK_TYPE_NUM,
 };
 
 enum amd_clockgating_state {
diff --git a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
index 03581d5b1836..08362d506534 100644
--- a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
@@ -927,6 +927,13 @@ int amdgpu_dpm_set_powergating_by_smu(struct amdgpu_device *adev, uint32_t block
 {
 	int ret = 0;
 	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
+	enum ip_power_state pwr_state = gate ? POWER_STATE_OFF : POWER_STATE_ON;
+
+	if (atomic_read(&adev->pm.pwr_state[block_type]) == pwr_state) {
+		dev_dbg(adev->dev, "IP block%d already in the target %s state!",
+				block_type, gate ? "gate" : "ungate");
+		return 0;
+	}
 
 	switch (block_type) {
 	case AMD_IP_BLOCK_TYPE_UVD:
@@ -979,6 +986,9 @@ int amdgpu_dpm_set_powergating_by_smu(struct amdgpu_device *adev, uint32_t block
 		break;
 	}
 
+	if (!ret)
+		atomic_set(&adev->pm.pwr_state[block_type], pwr_state);
+
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
index 98f1b3d8c1d5..16e3f72d31b9 100644
--- a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
+++ b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
@@ -417,6 +417,12 @@ struct amdgpu_dpm {
 	enum amd_dpm_forced_level forced_level;
 };
 
+enum ip_power_state {
+	POWER_STATE_UNKNOWN,
+	POWER_STATE_ON,
+	POWER_STATE_OFF,
+};
+
 struct amdgpu_pm {
 	struct mutex		mutex;
 	u32                     current_sclk;
@@ -452,6 +458,8 @@ struct amdgpu_pm {
 	struct i2c_adapter smu_i2c;
 	struct mutex		smu_i2c_mutex;
 	struct list_head	pm_attr_list;
+
+	atomic_t		pwr_state[AMD_IP_BLOCK_TYPE_NUM];
 };
 
 #define R600_SSTU_DFLT                               0
diff --git a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c
index 8d796ed3b7d1..619f8d305292 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c
@@ -1328,7 +1328,12 @@ static int pp_set_powergating_by_smu(void *handle,
 		pp_dpm_powergate_vce(handle, gate);
 		break;
 	case AMD_IP_BLOCK_TYPE_GMC:
-		pp_dpm_powergate_mmhub(handle);
+		/*
+		 * For now, this is only used on PICASSO.
+		 * And only "gate" operation is supported.
+		 */
+		if (gate)
+			pp_dpm_powergate_mmhub(handle);
 		break;
 	case AMD_IP_BLOCK_TYPE_GFX:
 		ret = pp_dpm_powergate_gfx(handle, gate);
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c
index 258c573acc97..1f406f21b452 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c
@@ -1024,8 +1024,6 @@ static int smu10_print_clock_levels(struct pp_hwmgr *hwmgr,
 	uint32_t min_freq, max_freq = 0;
 	uint32_t ret = 0;
 
-	phm_get_sysfs_buf(&buf, &size);
-
 	switch (type) {
 	case PP_SCLK:
 		smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetGfxclkFrequency, &now);
@@ -1038,13 +1036,13 @@ static int smu10_print_clock_levels(struct pp_hwmgr *hwmgr,
 		else
 			i = 1;
 
-		size += sysfs_emit_at(buf, size, "0: %uMhz %s\n",
+		size += sprintf(buf + size, "0: %uMhz %s\n",
 					data->gfx_min_freq_limit/100,
 					i == 0 ? "*" : "");
-		size += sysfs_emit_at(buf, size, "1: %uMhz %s\n",
+		size += sprintf(buf + size, "1: %uMhz %s\n",
 					i == 1 ? now : SMU10_UMD_PSTATE_GFXCLK,
 					i == 1 ? "*" : "");
-		size += sysfs_emit_at(buf, size, "2: %uMhz %s\n",
+		size += sprintf(buf + size, "2: %uMhz %s\n",
 					data->gfx_max_freq_limit/100,
 					i == 2 ? "*" : "");
 		break;
@@ -1052,7 +1050,7 @@ static int smu10_print_clock_levels(struct pp_hwmgr *hwmgr,
 		smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetFclkFrequency, &now);
 
 		for (i = 0; i < mclk_table->count; i++)
-			size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n",
+			size += sprintf(buf + size, "%d: %uMhz %s\n",
 					i,
 					mclk_table->entries[i].clk / 100,
 					((mclk_table->entries[i].clk / 100)
@@ -1067,10 +1065,10 @@ static int smu10_print_clock_levels(struct pp_hwmgr *hwmgr,
 			if (ret)
 				return ret;
 
-			size += sysfs_emit_at(buf, size, "%s:\n", "OD_SCLK");
-			size += sysfs_emit_at(buf, size, "0: %10uMhz\n",
+			size += sprintf(buf + size, "%s:\n", "OD_SCLK");
+			size += sprintf(buf + size, "0: %10uMhz\n",
 			(data->gfx_actual_soft_min_freq > 0) ? data->gfx_actual_soft_min_freq : min_freq);
-			size += sysfs_emit_at(buf, size, "1: %10uMhz\n",
+			size += sprintf(buf + size, "1: %10uMhz\n",
 			(data->gfx_actual_soft_max_freq > 0) ? data->gfx_actual_soft_max_freq : max_freq);
 		}
 		break;
@@ -1083,8 +1081,8 @@ static int smu10_print_clock_levels(struct pp_hwmgr *hwmgr,
 			if (ret)
 				return ret;
 
-			size += sysfs_emit_at(buf, size, "%s:\n", "OD_RANGE");
-			size += sysfs_emit_at(buf, size, "SCLK: %7uMHz %10uMHz\n",
+			size += sprintf(buf + size, "%s:\n", "OD_RANGE");
+			size += sprintf(buf + size, "SCLK: %7uMHz %10uMHz\n",
 				min_freq, max_freq);
 		}
 		break;
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
index aceebf584225..611969bf4520 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
@@ -4914,8 +4914,6 @@ static int smu7_print_clock_levels(struct pp_hwmgr *hwmgr,
 	int size = 0;
 	uint32_t i, now, clock, pcie_speed;
 
-	phm_get_sysfs_buf(&buf, &size);
-
 	switch (type) {
 	case PP_SCLK:
 		smum_send_msg_to_smc(hwmgr, PPSMC_MSG_API_GetSclkFrequency, &clock);
@@ -4928,7 +4926,7 @@ static int smu7_print_clock_levels(struct pp_hwmgr *hwmgr,
 		now = i;
 
 		for (i = 0; i < sclk_table->count; i++)
-			size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n",
+			size += sprintf(buf + size, "%d: %uMhz %s\n",
 					i, sclk_table->dpm_levels[i].value / 100,
 					(i == now) ? "*" : "");
 		break;
@@ -4943,7 +4941,7 @@ static int smu7_print_clock_levels(struct pp_hwmgr *hwmgr,
 		now = i;
 
 		for (i = 0; i < mclk_table->count; i++)
-			size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n",
+			size += sprintf(buf + size, "%d: %uMhz %s\n",
 					i, mclk_table->dpm_levels[i].value / 100,
 					(i == now) ? "*" : "");
 		break;
@@ -4957,7 +4955,7 @@ static int smu7_print_clock_levels(struct pp_hwmgr *hwmgr,
 		now = i;
 
 		for (i = 0; i < pcie_table->count; i++)
-			size += sysfs_emit_at(buf, size, "%d: %s %s\n", i,
+			size += sprintf(buf + size, "%d: %s %s\n", i,
 					(pcie_table->dpm_levels[i].value == 0) ? "2.5GT/s, x8" :
 					(pcie_table->dpm_levels[i].value == 1) ? "5.0GT/s, x16" :
 					(pcie_table->dpm_levels[i].value == 2) ? "8.0GT/s, x16" : "",
@@ -4965,32 +4963,32 @@ static int smu7_print_clock_levels(struct pp_hwmgr *hwmgr,
 		break;
 	case OD_SCLK:
 		if (hwmgr->od_enabled) {
-			size += sysfs_emit_at(buf, size, "%s:\n", "OD_SCLK");
+			size += sprintf(buf + size, "%s:\n", "OD_SCLK");
 			for (i = 0; i < odn_sclk_table->num_of_pl; i++)
-				size += sysfs_emit_at(buf, size, "%d: %10uMHz %10umV\n",
+				size += sprintf(buf + size, "%d: %10uMHz %10umV\n",
 					i, odn_sclk_table->entries[i].clock/100,
 					odn_sclk_table->entries[i].vddc);
 		}
 		break;
 	case OD_MCLK:
 		if (hwmgr->od_enabled) {
-			size += sysfs_emit_at(buf, size, "%s:\n", "OD_MCLK");
+			size += sprintf(buf + size, "%s:\n", "OD_MCLK");
 			for (i = 0; i < odn_mclk_table->num_of_pl; i++)
-				size += sysfs_emit_at(buf, size, "%d: %10uMHz %10umV\n",
+				size += sprintf(buf + size, "%d: %10uMHz %10umV\n",
 					i, odn_mclk_table->entries[i].clock/100,
 					odn_mclk_table->entries[i].vddc);
 		}
 		break;
 	case OD_RANGE:
 		if (hwmgr->od_enabled) {
-			size += sysfs_emit_at(buf, size, "%s:\n", "OD_RANGE");
-			size += sysfs_emit_at(buf, size, "SCLK: %7uMHz %10uMHz\n",
+			size += sprintf(buf + size, "%s:\n", "OD_RANGE");
+			size += sprintf(buf + size, "SCLK: %7uMHz %10uMHz\n",
 				data->golden_dpm_table.sclk_table.dpm_levels[0].value/100,
 				hwmgr->platform_descriptor.overdriveLimit.engineClock/100);
-			size += sysfs_emit_at(buf, size, "MCLK: %7uMHz %10uMHz\n",
+			size += sprintf(buf + size, "MCLK: %7uMHz %10uMHz\n",
 				data->golden_dpm_table.mclk_table.dpm_levels[0].value/100,
 				hwmgr->platform_descriptor.overdriveLimit.memoryClock/100);
-			size += sysfs_emit_at(buf, size, "VDDC: %7umV %11umV\n",
+			size += sprintf(buf + size, "VDDC: %7umV %11umV\n",
 				data->odn_dpm_table.min_vddc,
 				data->odn_dpm_table.max_vddc);
 		}
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c
index 8e28a8eecefc..03bf8f069222 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c
@@ -1550,8 +1550,6 @@ static int smu8_print_clock_levels(struct pp_hwmgr *hwmgr,
 	uint32_t i, now;
 	int size = 0;
 
-	phm_get_sysfs_buf(&buf, &size);
-
 	switch (type) {
 	case PP_SCLK:
 		now = PHM_GET_FIELD(cgs_read_ind_register(hwmgr->device,
@@ -1561,7 +1559,7 @@ static int smu8_print_clock_levels(struct pp_hwmgr *hwmgr,
 				CURR_SCLK_INDEX);
 
 		for (i = 0; i < sclk_table->count; i++)
-			size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n",
+			size += sprintf(buf + size, "%d: %uMhz %s\n",
 					i, sclk_table->entries[i].clk / 100,
 					(i == now) ? "*" : "");
 		break;
@@ -1573,7 +1571,7 @@ static int smu8_print_clock_levels(struct pp_hwmgr *hwmgr,
 				CURR_MCLK_INDEX);
 
 		for (i = SMU8_NUM_NBPMEMORYCLOCK; i > 0; i--)
-			size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n",
+			size += sprintf(buf + size, "%d: %uMhz %s\n",
 					SMU8_NUM_NBPMEMORYCLOCK-i, data->sys_info.nbp_memory_clock[i-1] / 100,
 					(SMU8_NUM_NBPMEMORYCLOCK-i == now) ? "*" : "");
 		break;
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c
index c981fc2882f0..e6336654c565 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c
@@ -4639,8 +4639,6 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr,
 
 	int i, now, size = 0, count = 0;
 
-	phm_get_sysfs_buf(&buf, &size);
-
 	switch (type) {
 	case PP_SCLK:
 		if (data->registry_data.sclk_dpm_key_disabled)
@@ -4654,7 +4652,7 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr,
 		else
 			count = sclk_table->count;
 		for (i = 0; i < count; i++)
-			size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n",
+			size += sprintf(buf + size, "%d: %uMhz %s\n",
 					i, sclk_table->dpm_levels[i].value / 100,
 					(i == now) ? "*" : "");
 		break;
@@ -4665,7 +4663,7 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr,
 		smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetCurrentUclkIndex, &now);
 
 		for (i = 0; i < mclk_table->count; i++)
-			size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n",
+			size += sprintf(buf + size, "%d: %uMhz %s\n",
 					i, mclk_table->dpm_levels[i].value / 100,
 					(i == now) ? "*" : "");
 		break;
@@ -4676,7 +4674,7 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr,
 		smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetCurrentSocclkIndex, &now);
 
 		for (i = 0; i < soc_table->count; i++)
-			size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n",
+			size += sprintf(buf + size, "%d: %uMhz %s\n",
 					i, soc_table->dpm_levels[i].value / 100,
 					(i == now) ? "*" : "");
 		break;
@@ -4688,7 +4686,7 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr,
 				PPSMC_MSG_GetClockFreqMHz, CLK_DCEFCLK, &now);
 
 		for (i = 0; i < dcef_table->count; i++)
-			size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n",
+			size += sprintf(buf + size, "%d: %uMhz %s\n",
 					i, dcef_table->dpm_levels[i].value / 100,
 					(dcef_table->dpm_levels[i].value / 100 == now) ?
 					"*" : "");
@@ -4702,7 +4700,7 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr,
 			gen_speed = pptable->PcieGenSpeed[i];
 			lane_width = pptable->PcieLaneCount[i];
 
-			size += sysfs_emit_at(buf, size, "%d: %s %s %s\n", i,
+			size += sprintf(buf + size, "%d: %s %s %s\n", i,
 					(gen_speed == 0) ? "2.5GT/s," :
 					(gen_speed == 1) ? "5.0GT/s," :
 					(gen_speed == 2) ? "8.0GT/s," :
@@ -4721,34 +4719,34 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr,
 
 	case OD_SCLK:
 		if (hwmgr->od_enabled) {
-			size += sysfs_emit_at(buf, size, "%s:\n", "OD_SCLK");
+			size += sprintf(buf + size, "%s:\n", "OD_SCLK");
 			podn_vdd_dep = &data->odn_dpm_table.vdd_dep_on_sclk;
 			for (i = 0; i < podn_vdd_dep->count; i++)
-				size += sysfs_emit_at(buf, size, "%d: %10uMhz %10umV\n",
+				size += sprintf(buf + size, "%d: %10uMhz %10umV\n",
 					i, podn_vdd_dep->entries[i].clk / 100,
 						podn_vdd_dep->entries[i].vddc);
 		}
 		break;
 	case OD_MCLK:
 		if (hwmgr->od_enabled) {
-			size += sysfs_emit_at(buf, size, "%s:\n", "OD_MCLK");
+			size += sprintf(buf + size, "%s:\n", "OD_MCLK");
 			podn_vdd_dep = &data->odn_dpm_table.vdd_dep_on_mclk;
 			for (i = 0; i < podn_vdd_dep->count; i++)
-				size += sysfs_emit_at(buf, size, "%d: %10uMhz %10umV\n",
+				size += sprintf(buf + size, "%d: %10uMhz %10umV\n",
 					i, podn_vdd_dep->entries[i].clk/100,
 						podn_vdd_dep->entries[i].vddc);
 		}
 		break;
 	case OD_RANGE:
 		if (hwmgr->od_enabled) {
-			size += sysfs_emit_at(buf, size, "%s:\n", "OD_RANGE");
-			size += sysfs_emit_at(buf, size, "SCLK: %7uMHz %10uMHz\n",
+			size += sprintf(buf + size, "%s:\n", "OD_RANGE");
+			size += sprintf(buf + size, "SCLK: %7uMHz %10uMHz\n",
 				data->golden_dpm_table.gfx_table.dpm_levels[0].value/100,
 				hwmgr->platform_descriptor.overdriveLimit.engineClock/100);
-			size += sysfs_emit_at(buf, size, "MCLK: %7uMHz %10uMHz\n",
+			size += sprintf(buf + size, "MCLK: %7uMHz %10uMHz\n",
 				data->golden_dpm_table.mem_table.dpm_levels[0].value/100,
 				hwmgr->platform_descriptor.overdriveLimit.memoryClock/100);
-			size += sysfs_emit_at(buf, size, "VDDC: %7umV %11umV\n",
+			size += sprintf(buf + size, "VDDC: %7umV %11umV\n",
 				data->odn_dpm_table.min_vddc,
 				data->odn_dpm_table.max_vddc);
 		}
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c
index f7e783e1c888..a2f4d6773d45 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c
@@ -2246,8 +2246,6 @@ static int vega12_print_clock_levels(struct pp_hwmgr *hwmgr,
 	int i, now, size = 0;
 	struct pp_clock_levels_with_latency clocks;
 
-	phm_get_sysfs_buf(&buf, &size);
-
 	switch (type) {
 	case PP_SCLK:
 		PP_ASSERT_WITH_CODE(
@@ -2260,7 +2258,7 @@ static int vega12_print_clock_levels(struct pp_hwmgr *hwmgr,
 				"Attempt to get gfx clk levels Failed!",
 				return -1);
 		for (i = 0; i < clocks.num_levels; i++)
-			size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n",
+			size += sprintf(buf + size, "%d: %uMhz %s\n",
 				i, clocks.data[i].clocks_in_khz / 1000,
 				(clocks.data[i].clocks_in_khz / 1000 == now / 100) ? "*" : "");
 		break;
@@ -2276,7 +2274,7 @@ static int vega12_print_clock_levels(struct pp_hwmgr *hwmgr,
 				"Attempt to get memory clk levels Failed!",
 				return -1);
 		for (i = 0; i < clocks.num_levels; i++)
-			size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n",
+			size += sprintf(buf + size, "%d: %uMhz %s\n",
 				i, clocks.data[i].clocks_in_khz / 1000,
 				(clocks.data[i].clocks_in_khz / 1000 == now / 100) ? "*" : "");
 		break;
@@ -2294,7 +2292,7 @@ static int vega12_print_clock_levels(struct pp_hwmgr *hwmgr,
 				"Attempt to get soc clk levels Failed!",
 				return -1);
 		for (i = 0; i < clocks.num_levels; i++)
-			size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n",
+			size += sprintf(buf + size, "%d: %uMhz %s\n",
 				i, clocks.data[i].clocks_in_khz / 1000,
 				(clocks.data[i].clocks_in_khz / 1000 == now) ? "*" : "");
 		break;
@@ -2312,7 +2310,7 @@ static int vega12_print_clock_levels(struct pp_hwmgr *hwmgr,
 				"Attempt to get dcef clk levels Failed!",
 				return -1);
 		for (i = 0; i < clocks.num_levels; i++)
-			size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n",
+			size += sprintf(buf + size, "%d: %uMhz %s\n",
 				i, clocks.data[i].clocks_in_khz / 1000,
 				(clocks.data[i].clocks_in_khz / 1000 == now) ? "*" : "");
 		break;
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c
index 03e63be4ee27..85d55ab4e369 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c
@@ -3366,8 +3366,6 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr,
 	int ret = 0;
 	uint32_t gen_speed, lane_width, current_gen_speed, current_lane_width;
 
-	phm_get_sysfs_buf(&buf, &size);
-
 	switch (type) {
 	case PP_SCLK:
 		ret = vega20_get_current_clk_freq(hwmgr, PPCLK_GFXCLK, &now);
@@ -3376,13 +3374,13 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr,
 				return ret);
 
 		if (vega20_get_sclks(hwmgr, &clocks)) {
-			size += sysfs_emit_at(buf, size, "0: %uMhz * (DPM disabled)\n",
+			size += sprintf(buf + size, "0: %uMhz * (DPM disabled)\n",
 				now / 100);
 			break;
 		}
 
 		for (i = 0; i < clocks.num_levels; i++)
-			size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n",
+			size += sprintf(buf + size, "%d: %uMhz %s\n",
 				i, clocks.data[i].clocks_in_khz / 1000,
 				(clocks.data[i].clocks_in_khz == now * 10) ? "*" : "");
 		break;
@@ -3394,13 +3392,13 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr,
 				return ret);
 
 		if (vega20_get_memclocks(hwmgr, &clocks)) {
-			size += sysfs_emit_at(buf, size, "0: %uMhz * (DPM disabled)\n",
+			size += sprintf(buf + size, "0: %uMhz * (DPM disabled)\n",
 				now / 100);
 			break;
 		}
 
 		for (i = 0; i < clocks.num_levels; i++)
-			size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n",
+			size += sprintf(buf + size, "%d: %uMhz %s\n",
 				i, clocks.data[i].clocks_in_khz / 1000,
 				(clocks.data[i].clocks_in_khz == now * 10) ? "*" : "");
 		break;
@@ -3412,13 +3410,13 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr,
 				return ret);
 
 		if (vega20_get_socclocks(hwmgr, &clocks)) {
-			size += sysfs_emit_at(buf, size, "0: %uMhz * (DPM disabled)\n",
+			size += sprintf(buf + size, "0: %uMhz * (DPM disabled)\n",
 				now / 100);
 			break;
 		}
 
 		for (i = 0; i < clocks.num_levels; i++)
-			size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n",
+			size += sprintf(buf + size, "%d: %uMhz %s\n",
 				i, clocks.data[i].clocks_in_khz / 1000,
 				(clocks.data[i].clocks_in_khz == now * 10) ? "*" : "");
 		break;
@@ -3430,7 +3428,7 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr,
 				return ret);
 
 		for (i = 0; i < fclk_dpm_table->count; i++)
-			size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n",
+			size += sprintf(buf + size, "%d: %uMhz %s\n",
 				i, fclk_dpm_table->dpm_levels[i].value,
 				fclk_dpm_table->dpm_levels[i].value == (now / 100) ? "*" : "");
 		break;
@@ -3442,13 +3440,13 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr,
 				return ret);
 
 		if (vega20_get_dcefclocks(hwmgr, &clocks)) {
-			size += sysfs_emit_at(buf, size, "0: %uMhz * (DPM disabled)\n",
+			size += sprintf(buf + size, "0: %uMhz * (DPM disabled)\n",
 				now / 100);
 			break;
 		}
 
 		for (i = 0; i < clocks.num_levels; i++)
-			size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n",
+			size += sprintf(buf + size, "%d: %uMhz %s\n",
 				i, clocks.data[i].clocks_in_khz / 1000,
 				(clocks.data[i].clocks_in_khz == now * 10) ? "*" : "");
 		break;
@@ -3462,7 +3460,7 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr,
 			gen_speed = pptable->PcieGenSpeed[i];
 			lane_width = pptable->PcieLaneCount[i];
 
-			size += sysfs_emit_at(buf, size, "%d: %s %s %dMhz %s\n", i,
+			size += sprintf(buf + size, "%d: %s %s %dMhz %s\n", i,
 					(gen_speed == 0) ? "2.5GT/s," :
 					(gen_speed == 1) ? "5.0GT/s," :
 					(gen_speed == 2) ? "8.0GT/s," :
@@ -3483,18 +3481,18 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr,
 	case OD_SCLK:
 		if (od8_settings[OD8_SETTING_GFXCLK_FMIN].feature_id &&
 		    od8_settings[OD8_SETTING_GFXCLK_FMAX].feature_id) {
-			size += sysfs_emit_at(buf, size, "%s:\n", "OD_SCLK");
-			size += sysfs_emit_at(buf, size, "0: %10uMhz\n",
+			size += sprintf(buf + size, "%s:\n", "OD_SCLK");
+			size += sprintf(buf + size, "0: %10uMhz\n",
 				od_table->GfxclkFmin);
-			size += sysfs_emit_at(buf, size, "1: %10uMhz\n",
+			size += sprintf(buf + size, "1: %10uMhz\n",
 				od_table->GfxclkFmax);
 		}
 		break;
 
 	case OD_MCLK:
 		if (od8_settings[OD8_SETTING_UCLK_FMAX].feature_id) {
-			size += sysfs_emit_at(buf, size, "%s:\n", "OD_MCLK");
-			size += sysfs_emit_at(buf, size, "1: %10uMhz\n",
+			size += sprintf(buf + size, "%s:\n", "OD_MCLK");
+			size += sprintf(buf + size, "1: %10uMhz\n",
 				od_table->UclkFmax);
 		}
 
@@ -3507,14 +3505,14 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr,
 		    od8_settings[OD8_SETTING_GFXCLK_VOLTAGE1].feature_id &&
 		    od8_settings[OD8_SETTING_GFXCLK_VOLTAGE2].feature_id &&
 		    od8_settings[OD8_SETTING_GFXCLK_VOLTAGE3].feature_id) {
-			size += sysfs_emit_at(buf, size, "%s:\n", "OD_VDDC_CURVE");
-			size += sysfs_emit_at(buf, size, "0: %10uMhz %10dmV\n",
+			size += sprintf(buf + size, "%s:\n", "OD_VDDC_CURVE");
+			size += sprintf(buf + size, "0: %10uMhz %10dmV\n",
 				od_table->GfxclkFreq1,
 				od_table->GfxclkVolt1 / VOLTAGE_SCALE);
-			size += sysfs_emit_at(buf, size, "1: %10uMhz %10dmV\n",
+			size += sprintf(buf + size, "1: %10uMhz %10dmV\n",
 				od_table->GfxclkFreq2,
 				od_table->GfxclkVolt2 / VOLTAGE_SCALE);
-			size += sysfs_emit_at(buf, size, "2: %10uMhz %10dmV\n",
+			size += sprintf(buf + size, "2: %10uMhz %10dmV\n",
 				od_table->GfxclkFreq3,
 				od_table->GfxclkVolt3 / VOLTAGE_SCALE);
 		}
@@ -3522,17 +3520,17 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr,
 		break;
 
 	case OD_RANGE:
-		size += sysfs_emit_at(buf, size, "%s:\n", "OD_RANGE");
+		size += sprintf(buf + size, "%s:\n", "OD_RANGE");
 
 		if (od8_settings[OD8_SETTING_GFXCLK_FMIN].feature_id &&
 		    od8_settings[OD8_SETTING_GFXCLK_FMAX].feature_id) {
-			size += sysfs_emit_at(buf, size, "SCLK: %7uMhz %10uMhz\n",
+			size += sprintf(buf + size, "SCLK: %7uMhz %10uMhz\n",
 				od8_settings[OD8_SETTING_GFXCLK_FMIN].min_value,
 				od8_settings[OD8_SETTING_GFXCLK_FMAX].max_value);
 		}
 
 		if (od8_settings[OD8_SETTING_UCLK_FMAX].feature_id) {
-			size += sysfs_emit_at(buf, size, "MCLK: %7uMhz %10uMhz\n",
+			size += sprintf(buf + size, "MCLK: %7uMhz %10uMhz\n",
 				od8_settings[OD8_SETTING_UCLK_FMAX].min_value,
 				od8_settings[OD8_SETTING_UCLK_FMAX].max_value);
 		}
@@ -3543,22 +3541,22 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr,
 		    od8_settings[OD8_SETTING_GFXCLK_VOLTAGE1].feature_id &&
 		    od8_settings[OD8_SETTING_GFXCLK_VOLTAGE2].feature_id &&
 		    od8_settings[OD8_SETTING_GFXCLK_VOLTAGE3].feature_id) {
-			size += sysfs_emit_at(buf, size, "VDDC_CURVE_SCLK[0]: %7uMhz %10uMhz\n",
+			size += sprintf(buf + size, "VDDC_CURVE_SCLK[0]: %7uMhz %10uMhz\n",
 				od8_settings[OD8_SETTING_GFXCLK_FREQ1].min_value,
 				od8_settings[OD8_SETTING_GFXCLK_FREQ1].max_value);
-			size += sysfs_emit_at(buf, size, "VDDC_CURVE_VOLT[0]: %7dmV %11dmV\n",
+			size += sprintf(buf + size, "VDDC_CURVE_VOLT[0]: %7dmV %11dmV\n",
 				od8_settings[OD8_SETTING_GFXCLK_VOLTAGE1].min_value,
 				od8_settings[OD8_SETTING_GFXCLK_VOLTAGE1].max_value);
-			size += sysfs_emit_at(buf, size, "VDDC_CURVE_SCLK[1]: %7uMhz %10uMhz\n",
+			size += sprintf(buf + size, "VDDC_CURVE_SCLK[1]: %7uMhz %10uMhz\n",
 				od8_settings[OD8_SETTING_GFXCLK_FREQ2].min_value,
 				od8_settings[OD8_SETTING_GFXCLK_FREQ2].max_value);
-			size += sysfs_emit_at(buf, size, "VDDC_CURVE_VOLT[1]: %7dmV %11dmV\n",
+			size += sprintf(buf + size, "VDDC_CURVE_VOLT[1]: %7dmV %11dmV\n",
 				od8_settings[OD8_SETTING_GFXCLK_VOLTAGE2].min_value,
 				od8_settings[OD8_SETTING_GFXCLK_VOLTAGE2].max_value);
-			size += sysfs_emit_at(buf, size, "VDDC_CURVE_SCLK[2]: %7uMhz %10uMhz\n",
+			size += sprintf(buf + size, "VDDC_CURVE_SCLK[2]: %7uMhz %10uMhz\n",
 				od8_settings[OD8_SETTING_GFXCLK_FREQ3].min_value,
 				od8_settings[OD8_SETTING_GFXCLK_FREQ3].max_value);
-			size += sysfs_emit_at(buf, size, "VDDC_CURVE_VOLT[2]: %7dmV %11dmV\n",
+			size += sprintf(buf + size, "VDDC_CURVE_VOLT[2]: %7dmV %11dmV\n",
 				od8_settings[OD8_SETTING_GFXCLK_VOLTAGE3].min_value,
 				od8_settings[OD8_SETTING_GFXCLK_VOLTAGE3].max_value);
 		}
diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index 01168b8955bf..8a3244585d80 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -1468,7 +1468,7 @@ static int smu_disable_dpms(struct smu_context *smu)
 			dev_err(adev->dev, "Failed to disable smu features.\n");
 	}
 
-	if (adev->ip_versions[GC_HWIP][0] >= IP_VERSION(10, 0, 0) &&
+	if (adev->ip_versions[GC_HWIP][0] >= IP_VERSION(9, 4, 2) &&
 	    adev->gfx.rlc.funcs->stop)
 		adev->gfx.rlc.funcs->stop(adev);
 
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/cyan_skillfish_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/cyan_skillfish_ppt.c
index cbc3f99e8573..2238ee19c222 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/cyan_skillfish_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/cyan_skillfish_ppt.c
@@ -309,6 +309,7 @@ static int cyan_skillfish_print_clk_levels(struct smu_context *smu,
 {
 	int ret = 0, size = 0;
 	uint32_t cur_value = 0;
+	int i;
 
 	smu_cmn_get_sysfs_buf(&buf, &size);
 
@@ -334,8 +335,6 @@ static int cyan_skillfish_print_clk_levels(struct smu_context *smu,
 		size += sysfs_emit_at(buf, size, "VDDC: %7umV  %10umV\n",
 						CYAN_SKILLFISH_VDDC_MIN, CYAN_SKILLFISH_VDDC_MAX);
 		break;
-	case SMU_GFXCLK:
-	case SMU_SCLK:
 	case SMU_FCLK:
 	case SMU_MCLK:
 	case SMU_SOCCLK:
@@ -346,6 +345,25 @@ static int cyan_skillfish_print_clk_levels(struct smu_context *smu,
 			return ret;
 		size += sysfs_emit_at(buf, size, "0: %uMhz *\n", cur_value);
 		break;
+	case SMU_SCLK:
+	case SMU_GFXCLK:
+		ret = cyan_skillfish_get_current_clk_freq(smu, clk_type, &cur_value);
+		if (ret)
+			return ret;
+		if (cur_value  == CYAN_SKILLFISH_SCLK_MAX)
+			i = 2;
+		else if (cur_value == CYAN_SKILLFISH_SCLK_MIN)
+			i = 0;
+		else
+			i = 1;
+		size += sysfs_emit_at(buf, size, "0: %uMhz %s\n", CYAN_SKILLFISH_SCLK_MIN,
+				i == 0 ? "*" : "");
+		size += sysfs_emit_at(buf, size, "1: %uMhz %s\n",
+				i == 1 ? cur_value : cyan_skillfish_sclk_default,
+				i == 1 ? "*" : "");
+		size += sysfs_emit_at(buf, size, "2: %uMhz %s\n", CYAN_SKILLFISH_SCLK_MAX,
+				i == 2 ? "*" : "");
+		break;
 	default:
 		dev_warn(smu->adev->dev, "Unsupported clock type\n");
 		return ret;
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
index 71161f6b78fe..60a557068ea4 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
@@ -1265,7 +1265,7 @@ static int navi10_print_clk_levels(struct smu_context *smu,
 			enum smu_clk_type clk_type, char *buf)
 {
 	uint16_t *curve_settings;
-	int i, size = 0, ret = 0;
+	int i, levels, size = 0, ret = 0;
 	uint32_t cur_value = 0, value = 0, count = 0;
 	uint32_t freq_values[3] = {0};
 	uint32_t mark_index = 0;
@@ -1319,14 +1319,17 @@ static int navi10_print_clk_levels(struct smu_context *smu,
 			freq_values[1] = cur_value;
 			mark_index = cur_value == freq_values[0] ? 0 :
 				     cur_value == freq_values[2] ? 2 : 1;
-			if (mark_index != 1)
-				freq_values[1] = (freq_values[0] + freq_values[2]) / 2;
 
-			for (i = 0; i < 3; i++) {
+			levels = 3;
+			if (mark_index != 1) {
+				levels = 2;
+				freq_values[1] = freq_values[2];
+			}
+
+			for (i = 0; i < levels; i++) {
 				size += sysfs_emit_at(buf, size, "%d: %uMhz %s\n", i, freq_values[i],
 						i == mark_index ? "*" : "");
 			}
-
 		}
 		break;
 	case SMU_PCIE:
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
index 421f38e8dada..c02ed65ffa38 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
@@ -683,6 +683,7 @@ static int vangogh_print_clk_levels(struct smu_context *smu,
 	int i, size = 0, ret = 0;
 	uint32_t cur_value = 0, value = 0, count = 0;
 	bool cur_value_match_level = false;
+	uint32_t min, max;
 
 	memset(&metrics, 0, sizeof(metrics));
 
@@ -743,6 +744,13 @@ static int vangogh_print_clk_levels(struct smu_context *smu,
 		if (ret)
 			return ret;
 		break;
+	case SMU_GFXCLK:
+	case SMU_SCLK:
+		ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_GetGfxclkFrequency, 0, &cur_value);
+		if (ret) {
+			return ret;
+		}
+		break;
 	default:
 		break;
 	}
@@ -768,6 +776,24 @@ static int vangogh_print_clk_levels(struct smu_context *smu,
 		if (!cur_value_match_level)
 			size += sysfs_emit_at(buf, size, "   %uMhz *\n", cur_value);
 		break;
+	case SMU_GFXCLK:
+	case SMU_SCLK:
+		min = (smu->gfx_actual_hard_min_freq > 0) ? smu->gfx_actual_hard_min_freq : smu->gfx_default_hard_min_freq;
+		max = (smu->gfx_actual_soft_max_freq > 0) ? smu->gfx_actual_soft_max_freq : smu->gfx_default_soft_max_freq;
+		if (cur_value  == max)
+			i = 2;
+		else if (cur_value == min)
+			i = 0;
+		else
+			i = 1;
+		size += sysfs_emit_at(buf, size, "0: %uMhz %s\n", min,
+				i == 0 ? "*" : "");
+		size += sysfs_emit_at(buf, size, "1: %uMhz %s\n",
+				i == 1 ? cur_value : VANGOGH_UMD_PSTATE_STANDARD_GFXCLK,
+				i == 1 ? "*" : "");
+		size += sysfs_emit_at(buf, size, "2: %uMhz %s\n", max,
+				i == 2 ? "*" : "");
+		break;
 	default:
 		break;
 	}
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu12/smu_v12_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu12/smu_v12_0.c
index d60b8c5e8715..43028f2cd28b 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu12/smu_v12_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu12/smu_v12_0.c
@@ -191,6 +191,9 @@ int smu_v12_0_fini_smc_tables(struct smu_context *smu)
 	kfree(smu_table->watermarks_table);
 	smu_table->watermarks_table = NULL;
 
+	kfree(smu_table->gpu_metrics_table);
+	smu_table->gpu_metrics_table = NULL;
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
index 35145db6eedf..19a5d2c39c8d 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
@@ -198,6 +198,7 @@ int smu_v13_0_check_fw_status(struct smu_context *smu)
 
 int smu_v13_0_check_fw_version(struct smu_context *smu)
 {
+	struct amdgpu_device *adev = smu->adev;
 	uint32_t if_version = 0xff, smu_version = 0xff;
 	uint16_t smu_major;
 	uint8_t smu_minor, smu_debug;
@@ -210,6 +211,8 @@ int smu_v13_0_check_fw_version(struct smu_context *smu)
 	smu_major = (smu_version >> 16) & 0xffff;
 	smu_minor = (smu_version >> 8) & 0xff;
 	smu_debug = (smu_version >> 0) & 0xff;
+	if (smu->is_apu)
+		adev->pm.fw_version = smu_version;
 
 	switch (smu->adev->ip_versions[MP1_HWIP][0]) {
 	case IP_VERSION(13, 0, 2):
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c
index 8215bbf5ed7c..caf1775d48ef 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c
@@ -697,6 +697,11 @@ static int yellow_carp_get_current_clk_freq(struct smu_context *smu,
 	case SMU_FCLK:
 		return smu_cmn_send_smc_msg_with_param(smu,
 				SMU_MSG_GetFclkFrequency, 0, value);
+	case SMU_GFXCLK:
+	case SMU_SCLK:
+		return smu_cmn_send_smc_msg_with_param(smu,
+				SMU_MSG_GetGfxclkFrequency, 0, value);
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -967,6 +972,7 @@ static int yellow_carp_print_clk_levels(struct smu_context *smu,
 {
 	int i, size = 0, ret = 0;
 	uint32_t cur_value = 0, value = 0, count = 0;
+	uint32_t min, max;
 
 	smu_cmn_get_sysfs_buf(&buf, &size);
 
@@ -1005,6 +1011,27 @@ static int yellow_carp_print_clk_levels(struct smu_context *smu,
 					cur_value == value ? "*" : "");
 		}
 		break;
+	case SMU_GFXCLK:
+	case SMU_SCLK:
+		ret = yellow_carp_get_current_clk_freq(smu, clk_type, &cur_value);
+		if (ret)
+			goto print_clk_out;
+		min = (smu->gfx_actual_hard_min_freq > 0) ? smu->gfx_actual_hard_min_freq : smu->gfx_default_hard_min_freq;
+		max = (smu->gfx_actual_soft_max_freq > 0) ? smu->gfx_actual_soft_max_freq : smu->gfx_default_soft_max_freq;
+		if (cur_value  == max)
+			i = 2;
+		else if (cur_value == min)
+			i = 0;
+		else
+			i = 1;
+		size += sysfs_emit_at(buf, size, "0: %uMhz %s\n", min,
+				i == 0 ? "*" : "");
+		size += sysfs_emit_at(buf, size, "1: %uMhz %s\n",
+				i == 1 ? cur_value : YELLOW_CARP_UMD_PSTATE_GFXCLK,
+				i == 1 ? "*" : "");
+		size += sysfs_emit_at(buf, size, "2: %uMhz %s\n", max,
+				i == 2 ? "*" : "");
+		break;
 	default:
 		break;
 	}
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.h b/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.h
index b3ad8352c68a..a9205a8ea3ad 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.h
@@ -24,5 +24,6 @@
 #define __YELLOW_CARP_PPT_H__
 
 extern void yellow_carp_set_ppt_funcs(struct smu_context *smu);
+#define YELLOW_CARP_UMD_PSTATE_GFXCLK       1100
 
 #endif
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
index 843d2cbfc71d..ea6f50c08c5f 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
@@ -139,9 +139,13 @@ static void __smu_cmn_reg_print_error(struct smu_context *smu,
 	const char *message = smu_get_message_name(smu, msg);
 
 	switch (reg_c2pmsg_90) {
-	case SMU_RESP_NONE:
+	case SMU_RESP_NONE: {
+		u32 msg_idx = RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_66);
+		u32 prm     = RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_82);
 		dev_err_ratelimited(adev->dev,
-				    "SMU: I'm not done with your previous command!");
+				    "SMU: I'm not done with your previous command: SMN_C2PMSG_66:0x%08X SMN_C2PMSG_82:0x%08X",
+				    msg_idx, prm);
+	}
 		break;
 	case SMU_RESP_OK:
 		/* The SMU executed the command. It completed with a
diff --git a/drivers/gpu/drm/aspeed/aspeed_gfx_drv.c b/drivers/gpu/drm/aspeed/aspeed_gfx_drv.c
index b53fee6f1c17..65f172807a0d 100644
--- a/drivers/gpu/drm/aspeed/aspeed_gfx_drv.c
+++ b/drivers/gpu/drm/aspeed/aspeed_gfx_drv.c
@@ -291,7 +291,7 @@ vga_pw_show(struct device *dev, struct device_attribute *attr, char *buf)
 	if (rc)
 		return rc;
 
-	return sprintf(buf, "%u\n", reg & 1);
+	return sprintf(buf, "%u\n", reg);
 }
 static DEVICE_ATTR_RO(vga_pw);
 
diff --git a/drivers/gpu/drm/ast/ast_mode.c b/drivers/gpu/drm/ast/ast_mode.c
index 1e30eaeb0e1b..d5c98f79d58d 100644
--- a/drivers/gpu/drm/ast/ast_mode.c
+++ b/drivers/gpu/drm/ast/ast_mode.c
@@ -1121,7 +1121,10 @@ static void ast_crtc_reset(struct drm_crtc *crtc)
 	if (crtc->state)
 		crtc->funcs->atomic_destroy_state(crtc, crtc->state);
 
-	__drm_atomic_helper_crtc_reset(crtc, &ast_state->base);
+	if (ast_state)
+		__drm_atomic_helper_crtc_reset(crtc, &ast_state->base);
+	else
+		__drm_atomic_helper_crtc_reset(crtc, NULL);
 }
 
 static struct drm_crtc_state *
diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index 8e7a124d6c5a..22bf690910b2 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -1743,7 +1743,13 @@ void drm_fb_helper_fill_info(struct fb_info *info,
 			       sizes->fb_width, sizes->fb_height);
 
 	info->par = fb_helper;
-	snprintf(info->fix.id, sizeof(info->fix.id), "%s",
+	/*
+	 * The DRM drivers fbdev emulation device name can be confusing if the
+	 * driver name also has a "drm" suffix on it. Leading to names such as
+	 * "simpledrmdrmfb" in /proc/fb. Unfortunately, it's an uAPI and can't
+	 * be changed due user-space tools (e.g: pm-utils) matching against it.
+	 */
+	snprintf(info->fix.id, sizeof(info->fix.id), "%sdrmfb",
 		 fb_helper->dev->driver->name);
 
 }
diff --git a/drivers/gpu/drm/drm_gem_cma_helper.c b/drivers/gpu/drm/drm_gem_cma_helper.c
index d53388199f34..9d05674550a4 100644
--- a/drivers/gpu/drm/drm_gem_cma_helper.c
+++ b/drivers/gpu/drm/drm_gem_cma_helper.c
@@ -210,8 +210,13 @@ void drm_gem_cma_free_object(struct drm_gem_object *gem_obj)
 			dma_buf_vunmap(gem_obj->import_attach->dmabuf, &map);
 		drm_prime_gem_destroy(gem_obj, cma_obj->sgt);
 	} else if (cma_obj->vaddr) {
-		dma_free_wc(gem_obj->dev->dev, cma_obj->base.size,
-			    cma_obj->vaddr, cma_obj->paddr);
+		if (cma_obj->map_noncoherent)
+			dma_free_noncoherent(gem_obj->dev->dev, cma_obj->base.size,
+					     cma_obj->vaddr, cma_obj->paddr,
+					     DMA_TO_DEVICE);
+		else
+			dma_free_wc(gem_obj->dev->dev, cma_obj->base.size,
+				    cma_obj->vaddr, cma_obj->paddr);
 	}
 
 	drm_gem_object_release(gem_obj);
diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c
index 7b9f69f21f1e..bca0de92802e 100644
--- a/drivers/gpu/drm/drm_gem_shmem_helper.c
+++ b/drivers/gpu/drm/drm_gem_shmem_helper.c
@@ -9,6 +9,7 @@
 #include <linux/shmem_fs.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
+#include <linux/module.h>
 
 #ifdef CONFIG_X86
 #include <asm/set_memory.h>
diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c
index c9a9d74f338c..c313a5b4549c 100644
--- a/drivers/gpu/drm/drm_syncobj.c
+++ b/drivers/gpu/drm/drm_syncobj.c
@@ -404,8 +404,17 @@ int drm_syncobj_find_fence(struct drm_file *file_private,
 
 	if (*fence) {
 		ret = dma_fence_chain_find_seqno(fence, point);
-		if (!ret)
+		if (!ret) {
+			/* If the requested seqno is already signaled
+			 * drm_syncobj_find_fence may return a NULL
+			 * fence. To make sure the recipient gets
+			 * signalled, use a new fence instead.
+			 */
+			if (!*fence)
+				*fence = dma_fence_get_stub();
+
 			goto out;
+		}
 		dma_fence_put(*fence);
 	} else {
 		ret = -EINVAL;
diff --git a/drivers/gpu/drm/hyperv/hyperv_drm_drv.c b/drivers/gpu/drm/hyperv/hyperv_drm_drv.c
index cd818a629183..00e53de4812b 100644
--- a/drivers/gpu/drm/hyperv/hyperv_drm_drv.c
+++ b/drivers/gpu/drm/hyperv/hyperv_drm_drv.c
@@ -225,12 +225,29 @@ static int hyperv_vmbus_remove(struct hv_device *hdev)
 {
 	struct drm_device *dev = hv_get_drvdata(hdev);
 	struct hyperv_drm_device *hv = to_hv(dev);
+	struct pci_dev *pdev;
 
 	drm_dev_unplug(dev);
 	drm_atomic_helper_shutdown(dev);
 	vmbus_close(hdev->channel);
 	hv_set_drvdata(hdev, NULL);
-	vmbus_free_mmio(hv->mem->start, hv->fb_size);
+
+	/*
+	 * Free allocated MMIO memory only on Gen2 VMs.
+	 * On Gen1 VMs, release the PCI device
+	 */
+	if (efi_enabled(EFI_BOOT)) {
+		vmbus_free_mmio(hv->mem->start, hv->fb_size);
+	} else {
+		pdev = pci_get_device(PCI_VENDOR_ID_MICROSOFT,
+				      PCI_DEVICE_ID_HYPERV_VIDEO, NULL);
+		if (!pdev) {
+			drm_err(dev, "Unable to find PCI Hyper-V video\n");
+			return -ENODEV;
+		}
+		pci_release_region(pdev, 0);
+		pci_dev_put(pdev);
+	}
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/display/icl_dsi.c b/drivers/gpu/drm/i915/display/icl_dsi.c
index 168c84a74d30..71fbdcddd31f 100644
--- a/drivers/gpu/drm/i915/display/icl_dsi.c
+++ b/drivers/gpu/drm/i915/display/icl_dsi.c
@@ -696,10 +696,7 @@ static void gen11_dsi_map_pll(struct intel_encoder *encoder,
 	intel_de_write(dev_priv, ICL_DPCLKA_CFGCR0, val);
 
 	for_each_dsi_phy(phy, intel_dsi->phys) {
-		if (DISPLAY_VER(dev_priv) >= 12)
-			val |= ICL_DPCLKA_CFGCR0_DDI_CLK_OFF(phy);
-		else
-			val &= ~ICL_DPCLKA_CFGCR0_DDI_CLK_OFF(phy);
+		val &= ~ICL_DPCLKA_CFGCR0_DDI_CLK_OFF(phy);
 	}
 	intel_de_write(dev_priv, ICL_DPCLKA_CFGCR0, val);
 
@@ -1135,8 +1132,6 @@ static void
 gen11_dsi_enable_port_and_phy(struct intel_encoder *encoder,
 			      const struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-
 	/* step 4a: power up all lanes of the DDI used by DSI */
 	gen11_dsi_power_up_lanes(encoder);
 
@@ -1162,8 +1157,7 @@ gen11_dsi_enable_port_and_phy(struct intel_encoder *encoder,
 	gen11_dsi_configure_transcoder(encoder, crtc_state);
 
 	/* Step 4l: Gate DDI clocks */
-	if (DISPLAY_VER(dev_priv) == 11)
-		gen11_dsi_gate_clocks(encoder);
+	gen11_dsi_gate_clocks(encoder);
 }
 
 static void gen11_dsi_powerup_panel(struct intel_encoder *encoder)
@@ -1271,7 +1265,8 @@ static void adlp_set_lp_hs_wakeup_gb(struct intel_encoder *encoder)
 	if (DISPLAY_VER(i915) == 13) {
 		for_each_dsi_port(port, intel_dsi->ports)
 			intel_de_rmw(i915, TGL_DSI_CHKN_REG(port),
-				     TGL_DSI_CHKN_LSHS_GB, 0x4);
+				     TGL_DSI_CHKN_LSHS_GB_MASK,
+				     TGL_DSI_CHKN_LSHS_GB(4));
 	}
 }
 
diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h
index 39e11eaec1a3..aa7238245b0e 100644
--- a/drivers/gpu/drm/i915/display/intel_display_types.h
+++ b/drivers/gpu/drm/i915/display/intel_display_types.h
@@ -1640,6 +1640,9 @@ struct intel_dp {
 	struct intel_dp_pcon_frl frl;
 
 	struct intel_psr psr;
+
+	/* When we last wrote the OUI for eDP */
+	unsigned long last_oui_write;
 };
 
 enum lspcon_vendor {
diff --git a/drivers/gpu/drm/i915/display/intel_dmc.c b/drivers/gpu/drm/i915/display/intel_dmc.c
index 2dc9d632969d..aef69522f0be 100644
--- a/drivers/gpu/drm/i915/display/intel_dmc.c
+++ b/drivers/gpu/drm/i915/display/intel_dmc.c
@@ -596,7 +596,7 @@ static void parse_dmc_fw(struct drm_i915_private *dev_priv,
 			continue;
 
 		offset = readcount + dmc->dmc_info[id].dmc_offset * 4;
-		if (fw->size - offset < 0) {
+		if (offset > fw->size) {
 			drm_err(&dev_priv->drm, "Reading beyond the fw_size\n");
 			continue;
 		}
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index be883469d2fc..a552f05a67e5 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -29,6 +29,7 @@
 #include <linux/i2c.h>
 #include <linux/notifier.h>
 #include <linux/slab.h>
+#include <linux/timekeeping.h>
 #include <linux/types.h>
 
 #include <asm/byteorder.h>
@@ -1955,6 +1956,16 @@ intel_edp_init_source_oui(struct intel_dp *intel_dp, bool careful)
 
 	if (drm_dp_dpcd_write(&intel_dp->aux, DP_SOURCE_OUI, oui, sizeof(oui)) < 0)
 		drm_err(&i915->drm, "Failed to write source OUI\n");
+
+	intel_dp->last_oui_write = jiffies;
+}
+
+void intel_dp_wait_source_oui(struct intel_dp *intel_dp)
+{
+	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
+
+	drm_dbg_kms(&i915->drm, "Performing OUI wait\n");
+	wait_remaining_ms_from_jiffies(intel_dp->last_oui_write, 30);
 }
 
 /* If the device supports it, try to set the power state appropriately */
diff --git a/drivers/gpu/drm/i915/display/intel_dp.h b/drivers/gpu/drm/i915/display/intel_dp.h
index ce229026dc91..b64145a3869a 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.h
+++ b/drivers/gpu/drm/i915/display/intel_dp.h
@@ -119,4 +119,6 @@ void intel_dp_pcon_dsc_configure(struct intel_dp *intel_dp,
 				 const struct intel_crtc_state *crtc_state);
 void intel_dp_phy_test(struct intel_encoder *encoder);
 
+void intel_dp_wait_source_oui(struct intel_dp *intel_dp);
+
 #endif /* __INTEL_DP_H__ */
diff --git a/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c b/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c
index 569d17b4d00f..3897468140e0 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c
@@ -36,6 +36,7 @@
 
 #include "intel_backlight.h"
 #include "intel_display_types.h"
+#include "intel_dp.h"
 #include "intel_dp_aux_backlight.h"
 
 /* TODO:
@@ -106,6 +107,8 @@ intel_dp_aux_supports_hdr_backlight(struct intel_connector *connector)
 	int ret;
 	u8 tcon_cap[4];
 
+	intel_dp_wait_source_oui(intel_dp);
+
 	ret = drm_dp_dpcd_read(aux, INTEL_EDP_HDR_TCON_CAP0, tcon_cap, sizeof(tcon_cap));
 	if (ret != sizeof(tcon_cap))
 		return false;
@@ -204,6 +207,8 @@ intel_dp_aux_hdr_enable_backlight(const struct intel_crtc_state *crtc_state,
 	int ret;
 	u8 old_ctrl, ctrl;
 
+	intel_dp_wait_source_oui(intel_dp);
+
 	ret = drm_dp_dpcd_readb(&intel_dp->aux, INTEL_EDP_HDR_GETSET_CTRL_PARAMS, &old_ctrl);
 	if (ret != 1) {
 		drm_err(&i915->drm, "Failed to read current backlight control mode: %d\n", ret);
@@ -293,6 +298,13 @@ intel_dp_aux_vesa_enable_backlight(const struct intel_crtc_state *crtc_state,
 	struct intel_panel *panel = &connector->panel;
 	struct intel_dp *intel_dp = enc_to_intel_dp(connector->encoder);
 
+	if (!panel->backlight.edp.vesa.info.aux_enable) {
+		u32 pwm_level = intel_backlight_invert_pwm_level(connector,
+								 panel->backlight.pwm_level_max);
+
+		panel->backlight.pwm_funcs->enable(crtc_state, conn_state, pwm_level);
+	}
+
 	drm_edp_backlight_enable(&intel_dp->aux, &panel->backlight.edp.vesa.info, level);
 }
 
@@ -304,6 +316,10 @@ static void intel_dp_aux_vesa_disable_backlight(const struct drm_connector_state
 	struct intel_dp *intel_dp = enc_to_intel_dp(connector->encoder);
 
 	drm_edp_backlight_disable(&intel_dp->aux, &panel->backlight.edp.vesa.info);
+
+	if (!panel->backlight.edp.vesa.info.aux_enable)
+		panel->backlight.pwm_funcs->disable(old_conn_state,
+						    intel_backlight_invert_pwm_level(connector, 0));
 }
 
 static int intel_dp_aux_vesa_setup_backlight(struct intel_connector *connector, enum pipe pipe)
@@ -321,6 +337,15 @@ static int intel_dp_aux_vesa_setup_backlight(struct intel_connector *connector,
 	if (ret < 0)
 		return ret;
 
+	if (!panel->backlight.edp.vesa.info.aux_enable) {
+		ret = panel->backlight.pwm_funcs->setup(connector, pipe);
+		if (ret < 0) {
+			drm_err(&i915->drm,
+				"Failed to setup PWM backlight controls for eDP backlight: %d\n",
+				ret);
+			return ret;
+		}
+	}
 	panel->backlight.max = panel->backlight.edp.vesa.info.max;
 	panel->backlight.min = 0;
 	if (current_mode == DP_EDP_BACKLIGHT_CONTROL_MODE_DPCD) {
@@ -340,12 +365,7 @@ intel_dp_aux_supports_vesa_backlight(struct intel_connector *connector)
 	struct intel_dp *intel_dp = intel_attached_dp(connector);
 	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
 
-	/* TODO: We currently only support AUX only backlight configurations, not backlights which
-	 * require a mix of PWM and AUX controls to work. In the mean time, these machines typically
-	 * work just fine using normal PWM controls anyway.
-	 */
-	if ((intel_dp->edp_dpcd[1] & DP_EDP_BACKLIGHT_AUX_ENABLE_CAP) &&
-	    drm_edp_backlight_supported(intel_dp->edp_dpcd)) {
+	if (drm_edp_backlight_supported(intel_dp->edp_dpcd)) {
 		drm_dbg_kms(&i915->drm, "AUX Backlight Control Supported!\n");
 		return true;
 	}
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index 4d7da07442f2..9b24d9b5ade1 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -3277,6 +3277,7 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 	out_fence = eb_requests_create(&eb, in_fence, out_fence_fd);
 	if (IS_ERR(out_fence)) {
 		err = PTR_ERR(out_fence);
+		out_fence = NULL;
 		if (eb.requests[0])
 			goto err_request;
 		else
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.c b/drivers/gpu/drm/i915/gt/intel_gt_pm.c
index 524eaf678790..795689eb3fc7 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.c
@@ -301,7 +301,7 @@ void intel_gt_suspend_prepare(struct intel_gt *gt)
 	user_forcewake(gt, true);
 	wait_for_suspend(gt);
 
-	intel_pxp_suspend(&gt->pxp, false);
+	intel_pxp_suspend_prepare(&gt->pxp);
 }
 
 static suspend_state_t pm_suspend_target(void)
@@ -326,6 +326,7 @@ void intel_gt_suspend_late(struct intel_gt *gt)
 	GEM_BUG_ON(gt->awake);
 
 	intel_uc_suspend(&gt->uc);
+	intel_pxp_suspend(&gt->pxp);
 
 	/*
 	 * On disabling the device, we want to turn off HW access to memory
@@ -353,7 +354,7 @@ void intel_gt_suspend_late(struct intel_gt *gt)
 
 void intel_gt_runtime_suspend(struct intel_gt *gt)
 {
-	intel_pxp_suspend(&gt->pxp, true);
+	intel_pxp_runtime_suspend(&gt->pxp);
 	intel_uc_runtime_suspend(&gt->uc);
 
 	GT_TRACE(gt, "\n");
@@ -371,7 +372,7 @@ int intel_gt_runtime_resume(struct intel_gt *gt)
 	if (ret)
 		return ret;
 
-	intel_pxp_resume(&gt->pxp);
+	intel_pxp_runtime_resume(&gt->pxp);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.c b/drivers/gpu/drm/i915/gt/intel_gtt.c
index 67d14afa6623..b67f620c3d93 100644
--- a/drivers/gpu/drm/i915/gt/intel_gtt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gtt.c
@@ -6,6 +6,7 @@
 #include <linux/slab.h> /* fault-inject.h is not standalone! */
 
 #include <linux/fault-inject.h>
+#include <linux/sched/mm.h>
 
 #include "gem/i915_gem_lmem.h"
 #include "i915_trace.h"
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index e1f362530889..2400d6423ba5 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -621,13 +621,6 @@ static void gen12_ctx_workarounds_init(struct intel_engine_cs *engine,
 	       FF_MODE2_GS_TIMER_MASK,
 	       FF_MODE2_GS_TIMER_224,
 	       0, false);
-
-	/*
-	 * Wa_14012131227:dg1
-	 * Wa_1508744258:tgl,rkl,dg1,adl-s,adl-p
-	 */
-	wa_masked_en(wal, GEN7_COMMON_SLICE_CHICKEN1,
-		     GEN9_RHWO_OPTIMIZATION_DISABLE);
 }
 
 static void dg1_ctx_workarounds_init(struct intel_engine_cs *engine,
@@ -1134,6 +1127,15 @@ icl_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal)
 		    GAMT_CHKN_BIT_REG,
 		    GAMT_CHKN_DISABLE_L3_COH_PIPE);
 
+	/* Wa_1407352427:icl,ehl */
+	wa_write_or(wal, UNSLICE_UNIT_LEVEL_CLKGATE2,
+		    PSDUNIT_CLKGATE_DIS);
+
+	/* Wa_1406680159:icl,ehl */
+	wa_write_or(wal,
+		    SUBSLICE_UNIT_LEVEL_CLKGATE,
+		    GWUNIT_CLKGATE_DIS);
+
 	/* Wa_1607087056:icl,ehl,jsl */
 	if (IS_ICELAKE(i915) ||
 	    IS_JSL_EHL_GT_STEP(i915, STEP_A0, STEP_B0))
@@ -1859,15 +1861,6 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 		wa_write_or(wal, UNSLICE_UNIT_LEVEL_CLKGATE,
 			    VSUNIT_CLKGATE_DIS | HSUNIT_CLKGATE_DIS);
 
-		/* Wa_1407352427:icl,ehl */
-		wa_write_or(wal, UNSLICE_UNIT_LEVEL_CLKGATE2,
-			    PSDUNIT_CLKGATE_DIS);
-
-		/* Wa_1406680159:icl,ehl */
-		wa_write_or(wal,
-			    SUBSLICE_UNIT_LEVEL_CLKGATE,
-			    GWUNIT_CLKGATE_DIS);
-
 		/*
 		 * Wa_1408767742:icl[a2..forever],ehl[all]
 		 * Wa_1605460711:icl[a0..c0]
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
index 38b47e73e35d..302e9ff0602c 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -1662,11 +1662,11 @@ static int steal_guc_id(struct intel_guc *guc, struct intel_context *ce)
 		GEM_BUG_ON(intel_context_is_parent(cn));
 
 		list_del_init(&cn->guc_id.link);
-		ce->guc_id = cn->guc_id;
+		ce->guc_id.id = cn->guc_id.id;
 
-		spin_lock(&ce->guc_state.lock);
+		spin_lock(&cn->guc_state.lock);
 		clr_context_registered(cn);
-		spin_unlock(&ce->guc_state.lock);
+		spin_unlock(&cn->guc_state.lock);
 
 		set_context_guc_id_invalid(cn);
 
@@ -3080,8 +3080,8 @@ guc_create_parallel(struct intel_engine_cs **engines,
 
 		ce = intel_engine_create_virtual(siblings, num_siblings,
 						 FORCE_VIRTUAL);
-		if (!ce) {
-			err = ERR_PTR(-ENOMEM);
+		if (IS_ERR(ce)) {
+			err = ERR_CAST(ce);
 			goto unwind;
 		}
 
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index da9055c3ebf0..bcee121bec5a 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -11717,7 +11717,9 @@ enum skl_power_gate {
 #define TGL_DSI_CHKN_REG(port)		_MMIO_PORT(port,	\
 						    _TGL_DSI_CHKN_REG_0, \
 						    _TGL_DSI_CHKN_REG_1)
-#define TGL_DSI_CHKN_LSHS_GB			REG_GENMASK(15, 12)
+#define TGL_DSI_CHKN_LSHS_GB_MASK		REG_GENMASK(15, 12)
+#define TGL_DSI_CHKN_LSHS_GB(byte_clocks)	REG_FIELD_PREP(TGL_DSI_CHKN_LSHS_GB_MASK, \
+							       (byte_clocks))
 
 /* Display Stream Splitter Control */
 #define DSS_CTL1				_MMIO(0x67400)
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 820a1f38b271..89cccefeea63 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -29,6 +29,7 @@
 #include <linux/sched.h>
 #include <linux/sched/clock.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/mm.h>
 
 #include "gem/i915_gem_context.h"
 #include "gt/intel_breadcrumbs.h"
diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_pm.c b/drivers/gpu/drm/i915/pxp/intel_pxp_pm.c
index 23fd86de5a24..6a7d4e2ee138 100644
--- a/drivers/gpu/drm/i915/pxp/intel_pxp_pm.c
+++ b/drivers/gpu/drm/i915/pxp/intel_pxp_pm.c
@@ -7,26 +7,29 @@
 #include "intel_pxp_irq.h"
 #include "intel_pxp_pm.h"
 #include "intel_pxp_session.h"
+#include "i915_drv.h"
 
-void intel_pxp_suspend(struct intel_pxp *pxp, bool runtime)
+void intel_pxp_suspend_prepare(struct intel_pxp *pxp)
 {
 	if (!intel_pxp_is_enabled(pxp))
 		return;
 
 	pxp->arb_is_valid = false;
 
-	/*
-	 * Contexts using protected objects keep a runtime PM reference, so we
-	 * can only runtime suspend when all of them have been either closed
-	 * or banned. Therefore, there is no need to invalidate in that
-	 * scenario.
-	 */
-	if (!runtime)
-		intel_pxp_invalidate(pxp);
+	intel_pxp_invalidate(pxp);
+}
 
-	intel_pxp_fini_hw(pxp);
+void intel_pxp_suspend(struct intel_pxp *pxp)
+{
+	intel_wakeref_t wakeref;
 
-	pxp->hw_state_invalidated = false;
+	if (!intel_pxp_is_enabled(pxp))
+		return;
+
+	with_intel_runtime_pm(&pxp_to_gt(pxp)->i915->runtime_pm, wakeref) {
+		intel_pxp_fini_hw(pxp);
+		pxp->hw_state_invalidated = false;
+	}
 }
 
 void intel_pxp_resume(struct intel_pxp *pxp)
@@ -44,3 +47,15 @@ void intel_pxp_resume(struct intel_pxp *pxp)
 
 	intel_pxp_init_hw(pxp);
 }
+
+void intel_pxp_runtime_suspend(struct intel_pxp *pxp)
+{
+	if (!intel_pxp_is_enabled(pxp))
+		return;
+
+	pxp->arb_is_valid = false;
+
+	intel_pxp_fini_hw(pxp);
+
+	pxp->hw_state_invalidated = false;
+}
diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_pm.h b/drivers/gpu/drm/i915/pxp/intel_pxp_pm.h
index c89e97a0c3d0..16990a3f2f85 100644
--- a/drivers/gpu/drm/i915/pxp/intel_pxp_pm.h
+++ b/drivers/gpu/drm/i915/pxp/intel_pxp_pm.h
@@ -9,16 +9,29 @@
 #include "intel_pxp_types.h"
 
 #ifdef CONFIG_DRM_I915_PXP
-void intel_pxp_suspend(struct intel_pxp *pxp, bool runtime);
+void intel_pxp_suspend_prepare(struct intel_pxp *pxp);
+void intel_pxp_suspend(struct intel_pxp *pxp);
 void intel_pxp_resume(struct intel_pxp *pxp);
+void intel_pxp_runtime_suspend(struct intel_pxp *pxp);
 #else
-static inline void intel_pxp_suspend(struct intel_pxp *pxp, bool runtime)
+static inline void intel_pxp_suspend_prepare(struct intel_pxp *pxp)
+{
+}
+
+static inline void intel_pxp_suspend(struct intel_pxp *pxp)
 {
 }
 
 static inline void intel_pxp_resume(struct intel_pxp *pxp)
 {
 }
-#endif
 
+static inline void intel_pxp_runtime_suspend(struct intel_pxp *pxp)
+{
+}
+#endif
+static inline void intel_pxp_runtime_resume(struct intel_pxp *pxp)
+{
+	intel_pxp_resume(pxp);
+}
 #endif /* __INTEL_PXP_PM_H__ */
diff --git a/drivers/gpu/drm/lima/lima_device.c b/drivers/gpu/drm/lima/lima_device.c
index 65fdca366e41..f74f8048af8f 100644
--- a/drivers/gpu/drm/lima/lima_device.c
+++ b/drivers/gpu/drm/lima/lima_device.c
@@ -4,6 +4,7 @@
 #include <linux/regulator/consumer.h>
 #include <linux/reset.h>
 #include <linux/clk.h>
+#include <linux/slab.h>
 #include <linux/dma-mapping.h>
 #include <linux/platform_device.h>
 
diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi.c b/drivers/gpu/drm/mediatek/mtk_hdmi.c
index 5838c44cbf6f..3196189429bc 100644
--- a/drivers/gpu/drm/mediatek/mtk_hdmi.c
+++ b/drivers/gpu/drm/mediatek/mtk_hdmi.c
@@ -1224,12 +1224,14 @@ static int mtk_hdmi_bridge_mode_valid(struct drm_bridge *bridge,
 			return MODE_BAD;
 	}
 
-	if (hdmi->conf->cea_modes_only && !drm_match_cea_mode(mode))
-		return MODE_BAD;
+	if (hdmi->conf) {
+		if (hdmi->conf->cea_modes_only && !drm_match_cea_mode(mode))
+			return MODE_BAD;
 
-	if (hdmi->conf->max_mode_clock &&
-	    mode->clock > hdmi->conf->max_mode_clock)
-		return MODE_CLOCK_HIGH;
+		if (hdmi->conf->max_mode_clock &&
+		    mode->clock > hdmi->conf->max_mode_clock)
+			return MODE_CLOCK_HIGH;
+	}
 
 	if (mode->clock < 27000)
 		return MODE_CLOCK_LOW;
diff --git a/drivers/gpu/drm/msm/Kconfig b/drivers/gpu/drm/msm/Kconfig
index ae11061727ff..39197b4beea7 100644
--- a/drivers/gpu/drm/msm/Kconfig
+++ b/drivers/gpu/drm/msm/Kconfig
@@ -4,8 +4,8 @@ config DRM_MSM
 	tristate "MSM DRM"
 	depends on DRM
 	depends on ARCH_QCOM || SOC_IMX5 || COMPILE_TEST
+	depends on COMMON_CLK
 	depends on IOMMU_SUPPORT
-	depends on (OF && COMMON_CLK) || COMPILE_TEST
 	depends on QCOM_OCMEM || QCOM_OCMEM=n
 	depends on QCOM_LLCC || QCOM_LLCC=n
 	depends on QCOM_COMMAND_DB || QCOM_COMMAND_DB=n
diff --git a/drivers/gpu/drm/msm/Makefile b/drivers/gpu/drm/msm/Makefile
index 40577f8856d8..093454457545 100644
--- a/drivers/gpu/drm/msm/Makefile
+++ b/drivers/gpu/drm/msm/Makefile
@@ -23,8 +23,10 @@ msm-y := \
 	hdmi/hdmi_i2c.o \
 	hdmi/hdmi_phy.o \
 	hdmi/hdmi_phy_8960.o \
+	hdmi/hdmi_phy_8996.o \
 	hdmi/hdmi_phy_8x60.o \
 	hdmi/hdmi_phy_8x74.o \
+	hdmi/hdmi_pll_8960.o \
 	edp/edp.o \
 	edp/edp_aux.o \
 	edp/edp_bridge.o \
@@ -37,6 +39,7 @@ msm-y := \
 	disp/mdp4/mdp4_dtv_encoder.o \
 	disp/mdp4/mdp4_lcdc_encoder.o \
 	disp/mdp4/mdp4_lvds_connector.o \
+	disp/mdp4/mdp4_lvds_pll.o \
 	disp/mdp4/mdp4_irq.o \
 	disp/mdp4/mdp4_kms.o \
 	disp/mdp4/mdp4_plane.o \
@@ -116,9 +119,6 @@ msm-$(CONFIG_DRM_MSM_DP)+= dp/dp_aux.o \
 	dp/dp_audio.o
 
 msm-$(CONFIG_DRM_FBDEV_EMULATION) += msm_fbdev.o
-msm-$(CONFIG_COMMON_CLK) += disp/mdp4/mdp4_lvds_pll.o
-msm-$(CONFIG_COMMON_CLK) += hdmi/hdmi_pll_8960.o
-msm-$(CONFIG_COMMON_CLK) += hdmi/hdmi_phy_8996.o
 
 msm-$(CONFIG_DRM_MSM_HDMI_HDCP) += hdmi/hdmi_hdcp.o
 
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index 267a880811d6..78aad5216a61 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -1424,17 +1424,24 @@ static void a6xx_llc_activate(struct a6xx_gpu *a6xx_gpu)
 {
 	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
 	struct msm_gpu *gpu = &adreno_gpu->base;
-	u32 gpu_scid, cntl1_regval = 0;
+	u32 cntl1_regval = 0;
 
 	if (IS_ERR(a6xx_gpu->llc_mmio))
 		return;
 
 	if (!llcc_slice_activate(a6xx_gpu->llc_slice)) {
-		gpu_scid = llcc_get_slice_id(a6xx_gpu->llc_slice);
+		u32 gpu_scid = llcc_get_slice_id(a6xx_gpu->llc_slice);
 
 		gpu_scid &= 0x1f;
 		cntl1_regval = (gpu_scid << 0) | (gpu_scid << 5) | (gpu_scid << 10) |
 			       (gpu_scid << 15) | (gpu_scid << 20);
+
+		/* On A660, the SCID programming for UCHE traffic is done in
+		 * A6XX_GBIF_SCACHE_CNTL0[14:10]
+		 */
+		if (adreno_is_a660_family(adreno_gpu))
+			gpu_rmw(gpu, REG_A6XX_GBIF_SCACHE_CNTL0, (0x1f << 10) |
+				(1 << 8), (gpu_scid << 10) | (1 << 8));
 	}
 
 	/*
@@ -1471,13 +1478,6 @@ static void a6xx_llc_activate(struct a6xx_gpu *a6xx_gpu)
 	}
 
 	gpu_rmw(gpu, REG_A6XX_GBIF_SCACHE_CNTL1, GENMASK(24, 0), cntl1_regval);
-
-	/* On A660, the SCID programming for UCHE traffic is done in
-	 * A6XX_GBIF_SCACHE_CNTL0[14:10]
-	 */
-	if (adreno_is_a660_family(adreno_gpu))
-		gpu_rmw(gpu, REG_A6XX_GBIF_SCACHE_CNTL0, (0x1f << 10) |
-			(1 << 8), (gpu_scid << 10) | (1 << 8));
 }
 
 static void a6xx_llc_slices_destroy(struct a6xx_gpu *a6xx_gpu)
@@ -1640,7 +1640,7 @@ static unsigned long a6xx_gpu_busy(struct msm_gpu *gpu)
 	return (unsigned long)busy_time;
 }
 
-void a6xx_gpu_set_freq(struct msm_gpu *gpu, struct dev_pm_opp *opp)
+static void a6xx_gpu_set_freq(struct msm_gpu *gpu, struct dev_pm_opp *opp)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
 	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
index 7501849ed15d..6e90209cd543 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
@@ -777,12 +777,12 @@ static void a6xx_get_gmu_registers(struct msm_gpu *gpu,
 	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
 
 	a6xx_state->gmu_registers = state_kcalloc(a6xx_state,
-		2, sizeof(*a6xx_state->gmu_registers));
+		3, sizeof(*a6xx_state->gmu_registers));
 
 	if (!a6xx_state->gmu_registers)
 		return;
 
-	a6xx_state->nr_gmu_registers = 2;
+	a6xx_state->nr_gmu_registers = 3;
 
 	/* Get the CX GMU registers from AHB */
 	_a6xx_get_gmu_registers(gpu, a6xx_state, &a6xx_gmu_reglist[0],
diff --git a/drivers/gpu/drm/msm/dp/dp_aux.c b/drivers/gpu/drm/msm/dp/dp_aux.c
index eb40d8413bca..6d36f63c3338 100644
--- a/drivers/gpu/drm/msm/dp/dp_aux.c
+++ b/drivers/gpu/drm/msm/dp/dp_aux.c
@@ -33,6 +33,7 @@ struct dp_aux_private {
 	bool read;
 	bool no_send_addr;
 	bool no_send_stop;
+	bool initted;
 	u32 offset;
 	u32 segment;
 
@@ -331,6 +332,10 @@ static ssize_t dp_aux_transfer(struct drm_dp_aux *dp_aux,
 	}
 
 	mutex_lock(&aux->mutex);
+	if (!aux->initted) {
+		ret = -EIO;
+		goto exit;
+	}
 
 	dp_aux_update_offset_and_segment(aux, msg);
 	dp_aux_transfer_helper(aux, msg, true);
@@ -380,6 +385,8 @@ static ssize_t dp_aux_transfer(struct drm_dp_aux *dp_aux,
 	}
 
 	aux->cmd_busy = false;
+
+exit:
 	mutex_unlock(&aux->mutex);
 
 	return ret;
@@ -431,8 +438,13 @@ void dp_aux_init(struct drm_dp_aux *dp_aux)
 
 	aux = container_of(dp_aux, struct dp_aux_private, dp_aux);
 
+	mutex_lock(&aux->mutex);
+
 	dp_catalog_aux_enable(aux->catalog, true);
 	aux->retry_cnt = 0;
+	aux->initted = true;
+
+	mutex_unlock(&aux->mutex);
 }
 
 void dp_aux_deinit(struct drm_dp_aux *dp_aux)
@@ -441,7 +453,12 @@ void dp_aux_deinit(struct drm_dp_aux *dp_aux)
 
 	aux = container_of(dp_aux, struct dp_aux_private, dp_aux);
 
+	mutex_lock(&aux->mutex);
+
+	aux->initted = false;
 	dp_catalog_aux_enable(aux->catalog, false);
+
+	mutex_unlock(&aux->mutex);
 }
 
 int dp_aux_register(struct drm_dp_aux *dp_aux)
diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c
index f69a125f9559..0afc3b756f92 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_host.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_host.c
@@ -1658,6 +1658,8 @@ static int dsi_host_parse_lane_data(struct msm_dsi_host *msm_host,
 	if (!prop) {
 		DRM_DEV_DEBUG(dev,
 			"failed to find data lane mapping, using default\n");
+		/* Set the number of date lanes to 4 by default. */
+		msm_host->num_data_lanes = 4;
 		return 0;
 	}
 
diff --git a/drivers/gpu/drm/msm/msm_debugfs.c b/drivers/gpu/drm/msm/msm_debugfs.c
index 09d2d279c30a..dee13fedee3b 100644
--- a/drivers/gpu/drm/msm/msm_debugfs.c
+++ b/drivers/gpu/drm/msm/msm_debugfs.c
@@ -77,6 +77,7 @@ static int msm_gpu_open(struct inode *inode, struct file *file)
 		goto free_priv;
 
 	pm_runtime_get_sync(&gpu->pdev->dev);
+	msm_gpu_hw_init(gpu);
 	show_priv->state = gpu->funcs->gpu_state_get(gpu);
 	pm_runtime_put_sync(&gpu->pdev->dev);
 
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index 7936e8d498dd..892c04365239 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -967,29 +967,18 @@ static int msm_ioctl_gem_info(struct drm_device *dev, void *data,
 	return ret;
 }
 
-static int msm_ioctl_wait_fence(struct drm_device *dev, void *data,
-		struct drm_file *file)
+static int wait_fence(struct msm_gpu_submitqueue *queue, uint32_t fence_id,
+		      ktime_t timeout)
 {
-	struct msm_drm_private *priv = dev->dev_private;
-	struct drm_msm_wait_fence *args = data;
-	ktime_t timeout = to_ktime(args->timeout);
-	struct msm_gpu_submitqueue *queue;
-	struct msm_gpu *gpu = priv->gpu;
 	struct dma_fence *fence;
 	int ret;
 
-	if (args->pad) {
-		DRM_ERROR("invalid pad: %08x\n", args->pad);
+	if (fence_id > queue->last_fence) {
+		DRM_ERROR_RATELIMITED("waiting on invalid fence: %u (of %u)\n",
+				      fence_id, queue->last_fence);
 		return -EINVAL;
 	}
 
-	if (!gpu)
-		return 0;
-
-	queue = msm_submitqueue_get(file->driver_priv, args->queueid);
-	if (!queue)
-		return -ENOENT;
-
 	/*
 	 * Map submitqueue scoped "seqno" (which is actually an idr key)
 	 * back to underlying dma-fence
@@ -1001,7 +990,7 @@ static int msm_ioctl_wait_fence(struct drm_device *dev, void *data,
 	ret = mutex_lock_interruptible(&queue->lock);
 	if (ret)
 		return ret;
-	fence = idr_find(&queue->fence_idr, args->fence);
+	fence = idr_find(&queue->fence_idr, fence_id);
 	if (fence)
 		fence = dma_fence_get_rcu(fence);
 	mutex_unlock(&queue->lock);
@@ -1017,6 +1006,32 @@ static int msm_ioctl_wait_fence(struct drm_device *dev, void *data,
 	}
 
 	dma_fence_put(fence);
+
+	return ret;
+}
+
+static int msm_ioctl_wait_fence(struct drm_device *dev, void *data,
+		struct drm_file *file)
+{
+	struct msm_drm_private *priv = dev->dev_private;
+	struct drm_msm_wait_fence *args = data;
+	struct msm_gpu_submitqueue *queue;
+	int ret;
+
+	if (args->pad) {
+		DRM_ERROR("invalid pad: %08x\n", args->pad);
+		return -EINVAL;
+	}
+
+	if (!priv->gpu)
+		return 0;
+
+	queue = msm_submitqueue_get(file->driver_priv, args->queueid);
+	if (!queue)
+		return -ENOENT;
+
+	ret = wait_fence(queue, args->fence, to_ktime(args->timeout));
+
 	msm_submitqueue_put(queue);
 
 	return ret;
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index 104fdfc14027..512d55eecbaf 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -1056,8 +1056,7 @@ static int msm_gem_object_mmap(struct drm_gem_object *obj, struct vm_area_struct
 {
 	struct msm_gem_object *msm_obj = to_msm_bo(obj);
 
-	vma->vm_flags &= ~VM_PFNMAP;
-	vma->vm_flags |= VM_MIXEDMAP | VM_DONTEXPAND;
+	vma->vm_flags |= VM_IO | VM_MIXEDMAP | VM_DONTEXPAND | VM_DONTDUMP;
 	vma->vm_page_prot = msm_gem_pgprot(msm_obj, vm_get_page_prot(vma->vm_flags));
 
 	return 0;
@@ -1121,7 +1120,7 @@ static int msm_gem_new_impl(struct drm_device *dev,
 			break;
 		fallthrough;
 	default:
-		DRM_DEV_ERROR(dev->dev, "invalid cache flag: %x\n",
+		DRM_DEV_DEBUG(dev->dev, "invalid cache flag: %x\n",
 				(flags & MSM_BO_CACHE_MASK));
 		return -EINVAL;
 	}
diff --git a/drivers/gpu/drm/msm/msm_gem_shrinker.c b/drivers/gpu/drm/msm/msm_gem_shrinker.c
index 4a1420b05e97..086dacf2f26a 100644
--- a/drivers/gpu/drm/msm/msm_gem_shrinker.c
+++ b/drivers/gpu/drm/msm/msm_gem_shrinker.c
@@ -5,6 +5,7 @@
  */
 
 #include <linux/vmalloc.h>
+#include <linux/sched/mm.h>
 
 #include "msm_drv.h"
 #include "msm_gem.h"
diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index 3cb029f10925..282628d6b72c 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -772,6 +772,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 		args->nr_cmds);
 	if (IS_ERR(submit)) {
 		ret = PTR_ERR(submit);
+		submit = NULL;
 		goto out_unlock;
 	}
 
@@ -904,6 +905,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 	drm_sched_entity_push_job(&submit->base);
 
 	args->fence = submit->fence_id;
+	queue->last_fence = submit->fence_id;
 
 	msm_reset_syncobjs(syncobjs_to_reset, args->nr_in_syncobjs);
 	msm_process_post_deps(post_deps, args->nr_out_syncobjs,
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index 59cdd00b69d0..48ea2de911f1 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -359,6 +359,8 @@ static inline int msm_gpu_convert_priority(struct msm_gpu *gpu, int prio,
  * @ring_nr:   the ringbuffer used by this submitqueue, which is determined
  *             by the submitqueue's priority
  * @faults:    the number of GPU hangs associated with this submitqueue
+ * @last_fence: the sequence number of the last allocated fence (for error
+ *             checking)
  * @ctx:       the per-drm_file context associated with the submitqueue (ie.
  *             which set of pgtables do submits jobs associated with the
  *             submitqueue use)
@@ -374,6 +376,7 @@ struct msm_gpu_submitqueue {
 	u32 flags;
 	u32 ring_nr;
 	int faults;
+	uint32_t last_fence;
 	struct msm_file_private *ctx;
 	struct list_head node;
 	struct idr fence_idr;
diff --git a/drivers/gpu/drm/msm/msm_gpu_devfreq.c b/drivers/gpu/drm/msm/msm_gpu_devfreq.c
index 8b7473f69cb8..384e90c4b2a7 100644
--- a/drivers/gpu/drm/msm/msm_gpu_devfreq.c
+++ b/drivers/gpu/drm/msm/msm_gpu_devfreq.c
@@ -20,6 +20,10 @@ static int msm_devfreq_target(struct device *dev, unsigned long *freq,
 	struct msm_gpu *gpu = dev_to_gpu(dev);
 	struct dev_pm_opp *opp;
 
+	/*
+	 * Note that devfreq_recommended_opp() can modify the freq
+	 * to something that actually is in the opp table:
+	 */
 	opp = devfreq_recommended_opp(dev, freq, flags);
 
 	/*
@@ -28,6 +32,7 @@ static int msm_devfreq_target(struct device *dev, unsigned long *freq,
 	 */
 	if (gpu->devfreq.idle_freq) {
 		gpu->devfreq.idle_freq = *freq;
+		dev_pm_opp_put(opp);
 		return 0;
 	}
 
@@ -203,9 +208,6 @@ static void msm_devfreq_idle_work(struct kthread_work *work)
 	struct msm_gpu *gpu = container_of(df, struct msm_gpu, devfreq);
 	unsigned long idle_freq, target_freq = 0;
 
-	if (!df->devfreq)
-		return;
-
 	/*
 	 * Hold devfreq lock to synchronize with get_dev_status()/
 	 * target() callbacks
@@ -227,6 +229,9 @@ void msm_devfreq_idle(struct msm_gpu *gpu)
 {
 	struct msm_gpu_devfreq *df = &gpu->devfreq;
 
+	if (!df->devfreq)
+		return;
+
 	msm_hrtimer_queue_work(&df->idle_work, ms_to_ktime(1),
-			       HRTIMER_MODE_ABS);
+			       HRTIMER_MODE_REL);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
index b51d690f375f..88d262ba648c 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
@@ -2627,6 +2627,27 @@ nv174_chipset = {
 };
 
 static const struct nvkm_device_chip
+nv176_chipset = {
+	.name = "GA106",
+	.bar      = { 0x00000001, tu102_bar_new },
+	.bios     = { 0x00000001, nvkm_bios_new },
+	.devinit  = { 0x00000001, ga100_devinit_new },
+	.fb       = { 0x00000001, ga102_fb_new },
+	.gpio     = { 0x00000001, ga102_gpio_new },
+	.i2c      = { 0x00000001, gm200_i2c_new },
+	.imem     = { 0x00000001, nv50_instmem_new },
+	.mc       = { 0x00000001, ga100_mc_new },
+	.mmu      = { 0x00000001, tu102_mmu_new },
+	.pci      = { 0x00000001, gp100_pci_new },
+	.privring = { 0x00000001, gm200_privring_new },
+	.timer    = { 0x00000001, gk20a_timer_new },
+	.top      = { 0x00000001, ga100_top_new },
+	.disp     = { 0x00000001, ga102_disp_new },
+	.dma      = { 0x00000001, gv100_dma_new },
+	.fifo     = { 0x00000001, ga102_fifo_new },
+};
+
+static const struct nvkm_device_chip
 nv177_chipset = {
 	.name = "GA107",
 	.bar      = { 0x00000001, tu102_bar_new },
@@ -3072,6 +3093,7 @@ nvkm_device_ctor(const struct nvkm_device_func *func,
 		case 0x168: device->chip = &nv168_chipset; break;
 		case 0x172: device->chip = &nv172_chipset; break;
 		case 0x174: device->chip = &nv174_chipset; break;
+		case 0x176: device->chip = &nv176_chipset; break;
 		case 0x177: device->chip = &nv177_chipset; break;
 		default:
 			if (nvkm_boolopt(device->cfgopt, "NvEnableUnsupportedChipsets", false)) {
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/hdmigv100.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/hdmigv100.c
index 6e3c450eaace..3ff49344abc7 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/hdmigv100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/hdmigv100.c
@@ -62,7 +62,6 @@ gv100_hdmi_ctrl(struct nvkm_ior *ior, int head, bool enable, u8 max_ac_packet,
 		nvkm_wr32(device, 0x6f0108 + hdmi, vendor_infoframe.header);
 		nvkm_wr32(device, 0x6f010c + hdmi, vendor_infoframe.subpack0_low);
 		nvkm_wr32(device, 0x6f0110 + hdmi, vendor_infoframe.subpack0_high);
-		nvkm_wr32(device, 0x6f0110 + hdmi, 0x00000000);
 		nvkm_wr32(device, 0x6f0114 + hdmi, 0x00000000);
 		nvkm_wr32(device, 0x6f0118 + hdmi, 0x00000000);
 		nvkm_wr32(device, 0x6f011c + hdmi, 0x00000000);
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/acr/gm200.c b/drivers/gpu/drm/nouveau/nvkm/subdev/acr/gm200.c
index cdb1ead26d84..82b4c8e1457c 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/acr/gm200.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/acr/gm200.c
@@ -207,11 +207,13 @@ int
 gm200_acr_wpr_parse(struct nvkm_acr *acr)
 {
 	const struct wpr_header *hdr = (void *)acr->wpr_fw->data;
+	struct nvkm_acr_lsfw *lsfw;
 
 	while (hdr->falcon_id != WPR_HEADER_V0_FALCON_ID_INVALID) {
 		wpr_header_dump(&acr->subdev, hdr);
-		if (!nvkm_acr_lsfw_add(NULL, acr, NULL, (hdr++)->falcon_id))
-			return -ENOMEM;
+		lsfw = nvkm_acr_lsfw_add(NULL, acr, NULL, (hdr++)->falcon_id);
+		if (IS_ERR(lsfw))
+			return PTR_ERR(lsfw);
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/acr/gp102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/acr/gp102.c
index fb9132a39bb1..fd97a935a380 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/acr/gp102.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/acr/gp102.c
@@ -161,11 +161,13 @@ int
 gp102_acr_wpr_parse(struct nvkm_acr *acr)
 {
 	const struct wpr_header_v1 *hdr = (void *)acr->wpr_fw->data;
+	struct nvkm_acr_lsfw *lsfw;
 
 	while (hdr->falcon_id != WPR_HEADER_V1_FALCON_ID_INVALID) {
 		wpr_header_v1_dump(&acr->subdev, hdr);
-		if (!nvkm_acr_lsfw_add(NULL, acr, NULL, (hdr++)->falcon_id))
-			return -ENOMEM;
+		lsfw = nvkm_acr_lsfw_add(NULL, acr, NULL, (hdr++)->falcon_id);
+		if (IS_ERR(lsfw))
+			return PTR_ERR(lsfw);
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index 5bc5f775abe1..f91fb31ab7a7 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -704,9 +704,13 @@ int drm_sched_job_add_implicit_dependencies(struct drm_sched_job *job,
 	int ret;
 
 	dma_resv_for_each_fence(&cursor, obj->resv, write, fence) {
+		/* Make sure to grab an additional ref on the added fence */
+		dma_fence_get(fence);
 		ret = drm_sched_job_add_dependency(job, fence);
-		if (ret)
+		if (ret) {
+			dma_fence_put(fence);
 			return ret;
+		}
 	}
 	return 0;
 }
diff --git a/drivers/gpu/drm/sun4i/Kconfig b/drivers/gpu/drm/sun4i/Kconfig
index 5755f0432e77..8c796de53222 100644
--- a/drivers/gpu/drm/sun4i/Kconfig
+++ b/drivers/gpu/drm/sun4i/Kconfig
@@ -46,6 +46,7 @@ config DRM_SUN6I_DSI
 	default MACH_SUN8I
 	select CRC_CCITT
 	select DRM_MIPI_DSI
+	select RESET_CONTROLLER
 	select PHY_SUN6I_MIPI_DPHY
 	help
 	  Choose this option if you want have an Allwinner SoC with
diff --git a/drivers/gpu/drm/tiny/simpledrm.c b/drivers/gpu/drm/tiny/simpledrm.c
index 481b48bde047..5a6e89825bc2 100644
--- a/drivers/gpu/drm/tiny/simpledrm.c
+++ b/drivers/gpu/drm/tiny/simpledrm.c
@@ -458,7 +458,7 @@ static struct drm_display_mode simpledrm_mode(unsigned int width,
 {
 	struct drm_display_mode mode = { SIMPLEDRM_MODE(width, height) };
 
-	mode.clock = 60 /* Hz */ * mode.hdisplay * mode.vdisplay;
+	mode.clock = mode.hdisplay * mode.vdisplay * 60 / 1000 /* kHz */;
 	drm_mode_set_name(&mode);
 
 	return mode;
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 739f11c0109c..047adc42d9a0 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -1103,7 +1103,7 @@ int ttm_bo_swapout(struct ttm_buffer_object *bo, struct ttm_operation_ctx *ctx,
 	 * as an indication that we're about to swap out.
 	 */
 	memset(&place, 0, sizeof(place));
-	place.mem_type = TTM_PL_SYSTEM;
+	place.mem_type = bo->resource->mem_type;
 	if (!ttm_bo_evict_swapout_allowable(bo, ctx, &place, &locked, NULL))
 		return -EBUSY;
 
@@ -1135,6 +1135,7 @@ int ttm_bo_swapout(struct ttm_buffer_object *bo, struct ttm_operation_ctx *ctx,
 		struct ttm_place hop;
 
 		memset(&hop, 0, sizeof(hop));
+		place.mem_type = TTM_PL_SYSTEM;
 		ret = ttm_resource_alloc(bo, &place, &evict_mem);
 		if (unlikely(ret))
 			goto out;
diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c
index 7e83c00a3f48..79c870a3bef8 100644
--- a/drivers/gpu/drm/ttm/ttm_tt.c
+++ b/drivers/gpu/drm/ttm/ttm_tt.c
@@ -34,6 +34,7 @@
 #include <linux/sched.h>
 #include <linux/shmem_fs.h>
 #include <linux/file.h>
+#include <linux/module.h>
 #include <drm/drm_cache.h>
 #include <drm/ttm/ttm_bo_driver.h>
 
diff --git a/drivers/gpu/drm/vc4/vc4_bo.c b/drivers/gpu/drm/vc4/vc4_bo.c
index fddaeb0b09c1..f642bd6e71ff 100644
--- a/drivers/gpu/drm/vc4/vc4_bo.c
+++ b/drivers/gpu/drm/vc4/vc4_bo.c
@@ -391,7 +391,7 @@ struct drm_gem_object *vc4_create_object(struct drm_device *dev, size_t size)
 
 	bo = kzalloc(sizeof(*bo), GFP_KERNEL);
 	if (!bo)
-		return ERR_PTR(-ENOMEM);
+		return NULL;
 
 	bo->madv = VC4_MADV_WILLNEED;
 	refcount_set(&bo->usecnt, 0);
diff --git a/drivers/gpu/drm/vc4/vc4_kms.c b/drivers/gpu/drm/vc4/vc4_kms.c
index f0b3e4cf5bce..b61792d2aa65 100644
--- a/drivers/gpu/drm/vc4/vc4_kms.c
+++ b/drivers/gpu/drm/vc4/vc4_kms.c
@@ -337,10 +337,10 @@ static void vc4_atomic_commit_tail(struct drm_atomic_state *state)
 	struct drm_device *dev = state->dev;
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	struct vc4_hvs *hvs = vc4->hvs;
-	struct drm_crtc_state *old_crtc_state;
 	struct drm_crtc_state *new_crtc_state;
 	struct drm_crtc *crtc;
 	struct vc4_hvs_state *old_hvs_state;
+	unsigned int channel;
 	int i;
 
 	for_each_new_crtc_in_state(state, crtc, new_crtc_state, i) {
@@ -353,30 +353,32 @@ static void vc4_atomic_commit_tail(struct drm_atomic_state *state)
 		vc4_hvs_mask_underrun(dev, vc4_crtc_state->assigned_channel);
 	}
 
-	if (vc4->hvs->hvs5)
-		clk_set_min_rate(hvs->core_clk, 500000000);
-
 	old_hvs_state = vc4_hvs_get_old_global_state(state);
-	if (!old_hvs_state)
+	if (IS_ERR(old_hvs_state))
 		return;
 
-	for_each_old_crtc_in_state(state, crtc, old_crtc_state, i) {
-		struct vc4_crtc_state *vc4_crtc_state =
-			to_vc4_crtc_state(old_crtc_state);
-		unsigned int channel = vc4_crtc_state->assigned_channel;
+	for (channel = 0; channel < HVS_NUM_CHANNELS; channel++) {
+		struct drm_crtc_commit *commit;
 		int ret;
 
-		if (channel == VC4_HVS_CHANNEL_DISABLED)
+		if (!old_hvs_state->fifo_state[channel].in_use)
 			continue;
 
-		if (!old_hvs_state->fifo_state[channel].in_use)
+		commit = old_hvs_state->fifo_state[channel].pending_commit;
+		if (!commit)
 			continue;
 
-		ret = drm_crtc_commit_wait(old_hvs_state->fifo_state[channel].pending_commit);
+		ret = drm_crtc_commit_wait(commit);
 		if (ret)
 			drm_err(dev, "Timed out waiting for commit\n");
+
+		drm_crtc_commit_put(commit);
+		old_hvs_state->fifo_state[channel].pending_commit = NULL;
 	}
 
+	if (vc4->hvs->hvs5)
+		clk_set_min_rate(hvs->core_clk, 500000000);
+
 	drm_atomic_helper_commit_modeset_disables(dev, state);
 
 	vc4_ctm_commit(vc4, state);
@@ -410,8 +412,8 @@ static int vc4_atomic_commit_setup(struct drm_atomic_state *state)
 	unsigned int i;
 
 	hvs_state = vc4_hvs_get_new_global_state(state);
-	if (!hvs_state)
-		return -EINVAL;
+	if (WARN_ON(IS_ERR(hvs_state)))
+		return PTR_ERR(hvs_state);
 
 	for_each_new_crtc_in_state(state, crtc, crtc_state, i) {
 		struct vc4_crtc_state *vc4_crtc_state =
@@ -668,12 +670,6 @@ vc4_hvs_channels_duplicate_state(struct drm_private_obj *obj)
 
 	for (i = 0; i < HVS_NUM_CHANNELS; i++) {
 		state->fifo_state[i].in_use = old_state->fifo_state[i].in_use;
-
-		if (!old_state->fifo_state[i].pending_commit)
-			continue;
-
-		state->fifo_state[i].pending_commit =
-			drm_crtc_commit_get(old_state->fifo_state[i].pending_commit);
 	}
 
 	return &state->base;
@@ -762,8 +758,8 @@ static int vc4_pv_muxing_atomic_check(struct drm_device *dev,
 	unsigned int i;
 
 	hvs_new_state = vc4_hvs_get_global_state(state);
-	if (!hvs_new_state)
-		return -EINVAL;
+	if (IS_ERR(hvs_new_state))
+		return PTR_ERR(hvs_new_state);
 
 	for (i = 0; i < ARRAY_SIZE(hvs_new_state->fifo_state); i++)
 		if (!hvs_new_state->fifo_state[i].in_use)
diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.c b/drivers/gpu/drm/virtio/virtgpu_drv.c
index d86e1ad4a972..5072dbb0669a 100644
--- a/drivers/gpu/drm/virtio/virtgpu_drv.c
+++ b/drivers/gpu/drm/virtio/virtgpu_drv.c
@@ -157,36 +157,6 @@ static void virtio_gpu_config_changed(struct virtio_device *vdev)
 	schedule_work(&vgdev->config_changed_work);
 }
 
-static __poll_t virtio_gpu_poll(struct file *filp,
-				struct poll_table_struct *wait)
-{
-	struct drm_file *drm_file = filp->private_data;
-	struct virtio_gpu_fpriv *vfpriv = drm_file->driver_priv;
-	struct drm_device *dev = drm_file->minor->dev;
-	struct virtio_gpu_device *vgdev = dev->dev_private;
-	struct drm_pending_event *e = NULL;
-	__poll_t mask = 0;
-
-	if (!vgdev->has_virgl_3d || !vfpriv || !vfpriv->ring_idx_mask)
-		return drm_poll(filp, wait);
-
-	poll_wait(filp, &drm_file->event_wait, wait);
-
-	if (!list_empty(&drm_file->event_list)) {
-		spin_lock_irq(&dev->event_lock);
-		e = list_first_entry(&drm_file->event_list,
-				     struct drm_pending_event, link);
-		drm_file->event_space += e->event->length;
-		list_del(&e->link);
-		spin_unlock_irq(&dev->event_lock);
-
-		kfree(e);
-		mask |= EPOLLIN | EPOLLRDNORM;
-	}
-
-	return mask;
-}
-
 static struct virtio_device_id id_table[] = {
 	{ VIRTIO_ID_GPU, VIRTIO_DEV_ANY_ID },
 	{ 0 },
@@ -226,17 +196,7 @@ MODULE_AUTHOR("Dave Airlie <airlied@redhat.com>");
 MODULE_AUTHOR("Gerd Hoffmann <kraxel@redhat.com>");
 MODULE_AUTHOR("Alon Levy");
 
-static const struct file_operations virtio_gpu_driver_fops = {
-	.owner          = THIS_MODULE,
-	.open           = drm_open,
-	.release        = drm_release,
-	.unlocked_ioctl = drm_ioctl,
-	.compat_ioctl   = drm_compat_ioctl,
-	.poll           = virtio_gpu_poll,
-	.read           = drm_read,
-	.llseek         = noop_llseek,
-	.mmap           = drm_gem_mmap
-};
+DEFINE_DRM_GEM_FOPS(virtio_gpu_driver_fops);
 
 static const struct drm_driver driver = {
 	.driver_features = DRIVER_MODESET | DRIVER_GEM | DRIVER_RENDER | DRIVER_ATOMIC,
diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.h b/drivers/gpu/drm/virtio/virtgpu_drv.h
index e0265fe74aa5..0a194aaad419 100644
--- a/drivers/gpu/drm/virtio/virtgpu_drv.h
+++ b/drivers/gpu/drm/virtio/virtgpu_drv.h
@@ -138,7 +138,6 @@ struct virtio_gpu_fence_driver {
 	spinlock_t       lock;
 };
 
-#define VIRTGPU_EVENT_FENCE_SIGNALED_INTERNAL 0x10000000
 struct virtio_gpu_fence_event {
 	struct drm_pending_event base;
 	struct drm_event event;
diff --git a/drivers/gpu/drm/virtio/virtgpu_ioctl.c b/drivers/gpu/drm/virtio/virtgpu_ioctl.c
index 5618a1d5879c..3607646d3229 100644
--- a/drivers/gpu/drm/virtio/virtgpu_ioctl.c
+++ b/drivers/gpu/drm/virtio/virtgpu_ioctl.c
@@ -54,7 +54,7 @@ static int virtio_gpu_fence_event_create(struct drm_device *dev,
 	if (!e)
 		return -ENOMEM;
 
-	e->event.type = VIRTGPU_EVENT_FENCE_SIGNALED_INTERNAL;
+	e->event.type = VIRTGPU_EVENT_FENCE_SIGNALED;
 	e->event.length = sizeof(e->event);
 
 	ret = drm_event_reserve_init(dev, file, &e->base, &e->event);
diff --git a/drivers/gpu/drm/xen/xen_drm_front.c b/drivers/gpu/drm/xen/xen_drm_front.c
index 9f14d99c763c..bc7605324db3 100644
--- a/drivers/gpu/drm/xen/xen_drm_front.c
+++ b/drivers/gpu/drm/xen/xen_drm_front.c
@@ -773,6 +773,7 @@ static struct xenbus_driver xen_driver = {
 	.probe = xen_drv_probe,
 	.remove = xen_drv_remove,
 	.otherend_changed = displback_changed,
+	.not_essential = true,
 };
 
 static int __init xen_drv_init(void)
diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig
index 9f5435b55949..a7c78ac96270 100644
--- a/drivers/hid/Kconfig
+++ b/drivers/hid/Kconfig
@@ -207,14 +207,14 @@ config HID_CHERRY
 
 config HID_CHICONY
 	tristate "Chicony devices"
-	depends on HID
+	depends on USB_HID
 	default !EXPERT
 	help
 	Support for Chicony Tactical pad and special keys on Chicony keyboards.
 
 config HID_CORSAIR
 	tristate "Corsair devices"
-	depends on HID && USB && LEDS_CLASS
+	depends on USB_HID && LEDS_CLASS
 	help
 	Support for Corsair devices that are not fully compliant with the
 	HID standard.
@@ -245,7 +245,7 @@ config HID_MACALLY
 
 config HID_PRODIKEYS
 	tristate "Prodikeys PC-MIDI Keyboard support"
-	depends on HID && SND
+	depends on USB_HID && SND
 	select SND_RAWMIDI
 	help
 	Support for Prodikeys PC-MIDI Keyboard device support.
@@ -560,7 +560,7 @@ config HID_LENOVO
 
 config HID_LOGITECH
 	tristate "Logitech devices"
-	depends on HID
+	depends on USB_HID
 	depends on LEDS_CLASS
 	default !EXPERT
 	help
@@ -951,7 +951,7 @@ config HID_SAITEK
 
 config HID_SAMSUNG
 	tristate "Samsung InfraRed remote control or keyboards"
-	depends on HID
+	depends on USB_HID
 	help
 	Support for Samsung InfraRed remote control or keyboards.
 
diff --git a/drivers/hid/hid-asus.c b/drivers/hid/hid-asus.c
index 5d57214d8dee..08c9a9a60ae4 100644
--- a/drivers/hid/hid-asus.c
+++ b/drivers/hid/hid-asus.c
@@ -854,7 +854,7 @@ static int asus_input_mapping(struct hid_device *hdev,
 		switch (usage->hid & HID_USAGE) {
 		case 0x10: asus_map_key_clear(KEY_BRIGHTNESSDOWN);	break;
 		case 0x20: asus_map_key_clear(KEY_BRIGHTNESSUP);		break;
-		case 0x35: asus_map_key_clear(KEY_SCREENLOCK);		break;
+		case 0x35: asus_map_key_clear(KEY_DISPLAY_OFF);		break;
 		case 0x6c: asus_map_key_clear(KEY_SLEEP);		break;
 		case 0x7c: asus_map_key_clear(KEY_MICMUTE);		break;
 		case 0x82: asus_map_key_clear(KEY_CAMERA);		break;
@@ -1028,8 +1028,7 @@ static int asus_probe(struct hid_device *hdev, const struct hid_device_id *id)
 	if (drvdata->quirks & QUIRK_IS_MULTITOUCH)
 		drvdata->tp = &asus_i2c_tp;
 
-	if ((drvdata->quirks & QUIRK_T100_KEYBOARD) &&
-	    hid_is_using_ll_driver(hdev, &usb_hid_driver)) {
+	if ((drvdata->quirks & QUIRK_T100_KEYBOARD) && hid_is_usb(hdev)) {
 		struct usb_interface *intf = to_usb_interface(hdev->dev.parent);
 
 		if (intf->altsetting->desc.bInterfaceNumber == T100_TPAD_INTF) {
@@ -1057,8 +1056,7 @@ static int asus_probe(struct hid_device *hdev, const struct hid_device_id *id)
 		drvdata->tp = &asus_t100chi_tp;
 	}
 
-	if ((drvdata->quirks & QUIRK_MEDION_E1239T) &&
-	    hid_is_using_ll_driver(hdev, &usb_hid_driver)) {
+	if ((drvdata->quirks & QUIRK_MEDION_E1239T) && hid_is_usb(hdev)) {
 		struct usb_host_interface *alt =
 			to_usb_interface(hdev->dev.parent)->altsetting;
 
diff --git a/drivers/hid/hid-bigbenff.c b/drivers/hid/hid-bigbenff.c
index db6da21ade06..74ad8bf98bfd 100644
--- a/drivers/hid/hid-bigbenff.c
+++ b/drivers/hid/hid-bigbenff.c
@@ -191,7 +191,7 @@ static void bigben_worker(struct work_struct *work)
 		struct bigben_device, worker);
 	struct hid_field *report_field = bigben->report->field[0];
 
-	if (bigben->removed)
+	if (bigben->removed || !report_field)
 		return;
 
 	if (bigben->work_led) {
diff --git a/drivers/hid/hid-chicony.c b/drivers/hid/hid-chicony.c
index ca556d39da2a..f04d2aa23efe 100644
--- a/drivers/hid/hid-chicony.c
+++ b/drivers/hid/hid-chicony.c
@@ -114,6 +114,9 @@ static int ch_probe(struct hid_device *hdev, const struct hid_device_id *id)
 {
 	int ret;
 
+	if (!hid_is_usb(hdev))
+		return -EINVAL;
+
 	hdev->quirks |= HID_QUIRK_INPUT_PER_APP;
 	ret = hid_parse(hdev);
 	if (ret) {
diff --git a/drivers/hid/hid-corsair.c b/drivers/hid/hid-corsair.c
index 902a60e249ed..8c895c820b67 100644
--- a/drivers/hid/hid-corsair.c
+++ b/drivers/hid/hid-corsair.c
@@ -553,7 +553,12 @@ static int corsair_probe(struct hid_device *dev, const struct hid_device_id *id)
 	int ret;
 	unsigned long quirks = id->driver_data;
 	struct corsair_drvdata *drvdata;
-	struct usb_interface *usbif = to_usb_interface(dev->dev.parent);
+	struct usb_interface *usbif;
+
+	if (!hid_is_usb(dev))
+		return -EINVAL;
+
+	usbif = to_usb_interface(dev->dev.parent);
 
 	drvdata = devm_kzalloc(&dev->dev, sizeof(struct corsair_drvdata),
 			       GFP_KERNEL);
diff --git a/drivers/hid/hid-elan.c b/drivers/hid/hid-elan.c
index 021049805bb7..3091355d48df 100644
--- a/drivers/hid/hid-elan.c
+++ b/drivers/hid/hid-elan.c
@@ -50,7 +50,7 @@ struct elan_drvdata {
 
 static int is_not_elan_touchpad(struct hid_device *hdev)
 {
-	if (hdev->bus == BUS_USB) {
+	if (hid_is_usb(hdev)) {
 		struct usb_interface *intf = to_usb_interface(hdev->dev.parent);
 
 		return (intf->altsetting->desc.bInterfaceNumber !=
diff --git a/drivers/hid/hid-elo.c b/drivers/hid/hid-elo.c
index 383dfda8c12f..8e960d7b233b 100644
--- a/drivers/hid/hid-elo.c
+++ b/drivers/hid/hid-elo.c
@@ -230,6 +230,9 @@ static int elo_probe(struct hid_device *hdev, const struct hid_device_id *id)
 	int ret;
 	struct usb_device *udev;
 
+	if (!hid_is_usb(hdev))
+		return -EINVAL;
+
 	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
 	if (!priv)
 		return -ENOMEM;
diff --git a/drivers/hid/hid-ft260.c b/drivers/hid/hid-ft260.c
index 4ef1c3b8094e..79505c64dbfe 100644
--- a/drivers/hid/hid-ft260.c
+++ b/drivers/hid/hid-ft260.c
@@ -915,6 +915,9 @@ static int ft260_probe(struct hid_device *hdev, const struct hid_device_id *id)
 	struct ft260_get_chip_version_report version;
 	int ret;
 
+	if (!hid_is_usb(hdev))
+		return -EINVAL;
+
 	dev = devm_kzalloc(&hdev->dev, sizeof(*dev), GFP_KERNEL);
 	if (!dev)
 		return -ENOMEM;
@@ -966,24 +969,23 @@ static int ft260_probe(struct hid_device *hdev, const struct hid_device_id *id)
 	mutex_init(&dev->lock);
 	init_completion(&dev->wait);
 
+	ret = ft260_xfer_status(dev);
+	if (ret)
+		ft260_i2c_reset(hdev);
+
+	i2c_set_adapdata(&dev->adap, dev);
 	ret = i2c_add_adapter(&dev->adap);
 	if (ret) {
 		hid_err(hdev, "failed to add i2c adapter\n");
 		goto err_hid_close;
 	}
 
-	i2c_set_adapdata(&dev->adap, dev);
-
 	ret = sysfs_create_group(&hdev->dev.kobj, &ft260_attr_group);
 	if (ret < 0) {
 		hid_err(hdev, "failed to create sysfs attrs\n");
 		goto err_i2c_free;
 	}
 
-	ret = ft260_xfer_status(dev);
-	if (ret)
-		ft260_i2c_reset(hdev);
-
 	return 0;
 
 err_i2c_free:
diff --git a/drivers/hid/hid-google-hammer.c b/drivers/hid/hid-google-hammer.c
index 8123b871a3eb..0403beb3104b 100644
--- a/drivers/hid/hid-google-hammer.c
+++ b/drivers/hid/hid-google-hammer.c
@@ -586,6 +586,8 @@ static const struct hid_device_id hammer_devices[] = {
 	{ HID_DEVICE(BUS_USB, HID_GROUP_GENERIC,
 		     USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_DON) },
 	{ HID_DEVICE(BUS_USB, HID_GROUP_GENERIC,
+		     USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_EEL) },
+	{ HID_DEVICE(BUS_USB, HID_GROUP_GENERIC,
 		     USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_HAMMER) },
 	{ HID_DEVICE(BUS_USB, HID_GROUP_GENERIC,
 		     USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_MAGNEMITE) },
diff --git a/drivers/hid/hid-holtek-kbd.c b/drivers/hid/hid-holtek-kbd.c
index 0a38e8e9bc78..403506b9697e 100644
--- a/drivers/hid/hid-holtek-kbd.c
+++ b/drivers/hid/hid-holtek-kbd.c
@@ -140,12 +140,17 @@ static int holtek_kbd_input_event(struct input_dev *dev, unsigned int type,
 static int holtek_kbd_probe(struct hid_device *hdev,
 		const struct hid_device_id *id)
 {
-	struct usb_interface *intf = to_usb_interface(hdev->dev.parent);
-	int ret = hid_parse(hdev);
+	struct usb_interface *intf;
+	int ret;
+
+	if (!hid_is_usb(hdev))
+		return -EINVAL;
 
+	ret = hid_parse(hdev);
 	if (!ret)
 		ret = hid_hw_start(hdev, HID_CONNECT_DEFAULT);
 
+	intf = to_usb_interface(hdev->dev.parent);
 	if (!ret && intf->cur_altsetting->desc.bInterfaceNumber == 1) {
 		struct hid_input *hidinput;
 		list_for_each_entry(hidinput, &hdev->inputs, list) {
diff --git a/drivers/hid/hid-holtek-mouse.c b/drivers/hid/hid-holtek-mouse.c
index 195b735b001d..7c907939bfae 100644
--- a/drivers/hid/hid-holtek-mouse.c
+++ b/drivers/hid/hid-holtek-mouse.c
@@ -62,6 +62,29 @@ static __u8 *holtek_mouse_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 	return rdesc;
 }
 
+static int holtek_mouse_probe(struct hid_device *hdev,
+			      const struct hid_device_id *id)
+{
+	int ret;
+
+	if (!hid_is_usb(hdev))
+		return -EINVAL;
+
+	ret = hid_parse(hdev);
+	if (ret) {
+		hid_err(hdev, "hid parse failed: %d\n", ret);
+		return ret;
+	}
+
+	ret = hid_hw_start(hdev, HID_CONNECT_DEFAULT);
+	if (ret) {
+		hid_err(hdev, "hw start failed: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
 static const struct hid_device_id holtek_mouse_devices[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_HOLTEK_ALT,
 			USB_DEVICE_ID_HOLTEK_ALT_MOUSE_A067) },
@@ -83,6 +106,7 @@ static struct hid_driver holtek_mouse_driver = {
 	.name = "holtek_mouse",
 	.id_table = holtek_mouse_devices,
 	.report_fixup = holtek_mouse_report_fixup,
+	.probe = holtek_mouse_probe,
 };
 
 module_hid_driver(holtek_mouse_driver);
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 95037a3e2e6e..19da07777d62 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -397,7 +397,9 @@
 #define USB_DEVICE_ID_TOSHIBA_CLICK_L9W	0x0401
 #define USB_DEVICE_ID_HP_X2		0x074d
 #define USB_DEVICE_ID_HP_X2_10_COVER	0x0755
+#define I2C_DEVICE_ID_HP_ENVY_X360_15	0x2d05
 #define I2C_DEVICE_ID_HP_SPECTRE_X360_15	0x2817
+#define USB_DEVICE_ID_ASUS_UX550VE_TOUCHSCREEN	0x2544
 #define USB_DEVICE_ID_ASUS_UX550_TOUCHSCREEN	0x2706
 #define I2C_DEVICE_ID_SURFACE_GO_TOUCHSCREEN	0x261A
 
@@ -500,6 +502,7 @@
 #define USB_DEVICE_ID_GOOGLE_MAGNEMITE	0x503d
 #define USB_DEVICE_ID_GOOGLE_MOONBALL	0x5044
 #define USB_DEVICE_ID_GOOGLE_DON	0x5050
+#define USB_DEVICE_ID_GOOGLE_EEL	0x5057
 
 #define USB_VENDOR_ID_GOTOP		0x08f2
 #define USB_DEVICE_ID_SUPER_Q2		0x007f
@@ -885,6 +888,7 @@
 #define USB_DEVICE_ID_MS_TOUCH_COVER_2   0x07a7
 #define USB_DEVICE_ID_MS_TYPE_COVER_2    0x07a9
 #define USB_DEVICE_ID_MS_POWER_COVER     0x07da
+#define USB_DEVICE_ID_MS_SURFACE3_COVER		0x07de
 #define USB_DEVICE_ID_MS_XBOX_ONE_S_CONTROLLER	0x02fd
 #define USB_DEVICE_ID_MS_PIXART_MOUSE    0x00cb
 #define USB_DEVICE_ID_8BITDO_SN30_PRO_PLUS      0x02e0
diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c
index 2c72ce4147b1..03f994541981 100644
--- a/drivers/hid/hid-input.c
+++ b/drivers/hid/hid-input.c
@@ -160,6 +160,7 @@ static int hidinput_setkeycode(struct input_dev *dev,
 	if (usage) {
 		*old_keycode = usage->type == EV_KEY ?
 				usage->code : KEY_RESERVED;
+		usage->type = EV_KEY;
 		usage->code = ke->keycode;
 
 		clear_bit(*old_keycode, dev->keybit);
@@ -324,6 +325,10 @@ static const struct hid_device_id hid_battery_quirks[] = {
 	  HID_BATTERY_QUIRK_IGNORE },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ELAN, USB_DEVICE_ID_ASUS_UX550_TOUCHSCREEN),
 	  HID_BATTERY_QUIRK_IGNORE },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_ELAN, USB_DEVICE_ID_ASUS_UX550VE_TOUCHSCREEN),
+	  HID_BATTERY_QUIRK_IGNORE },
+	{ HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_HP_ENVY_X360_15),
+	  HID_BATTERY_QUIRK_IGNORE },
 	{ HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_HP_SPECTRE_X360_15),
 	  HID_BATTERY_QUIRK_IGNORE },
 	{ HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_SURFACE_GO_TOUCHSCREEN),
@@ -650,10 +655,9 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel
 						code += KEY_MACRO1;
 					else
 						code += BTN_TRIGGER_HAPPY - 0x1e;
-				} else {
-					goto ignore;
+					break;
 				}
-				break;
+				fallthrough;
 		default:
 			switch (field->physical) {
 			case HID_GD_MOUSE:
diff --git a/drivers/hid/hid-lg.c b/drivers/hid/hid-lg.c
index d40af911df63..fb3f7258009c 100644
--- a/drivers/hid/hid-lg.c
+++ b/drivers/hid/hid-lg.c
@@ -749,12 +749,18 @@ static int lg_raw_event(struct hid_device *hdev, struct hid_report *report,
 
 static int lg_probe(struct hid_device *hdev, const struct hid_device_id *id)
 {
-	struct usb_interface *iface = to_usb_interface(hdev->dev.parent);
-	__u8 iface_num = iface->cur_altsetting->desc.bInterfaceNumber;
+	struct usb_interface *iface;
+	__u8 iface_num;
 	unsigned int connect_mask = HID_CONNECT_DEFAULT;
 	struct lg_drv_data *drv_data;
 	int ret;
 
+	if (!hid_is_usb(hdev))
+		return -EINVAL;
+
+	iface = to_usb_interface(hdev->dev.parent);
+	iface_num = iface->cur_altsetting->desc.bInterfaceNumber;
+
 	/* G29 only work with the 1st interface */
 	if ((hdev->product == USB_DEVICE_ID_LOGITECH_G29_WHEEL) &&
 	    (iface_num != 0)) {
diff --git a/drivers/hid/hid-logitech-dj.c b/drivers/hid/hid-logitech-dj.c
index a0017b010c34..7106b921b53c 100644
--- a/drivers/hid/hid-logitech-dj.c
+++ b/drivers/hid/hid-logitech-dj.c
@@ -1777,7 +1777,7 @@ static int logi_dj_probe(struct hid_device *hdev,
 	case recvr_type_bluetooth:	no_dj_interfaces = 2; break;
 	case recvr_type_dinovo:		no_dj_interfaces = 2; break;
 	}
-	if (hid_is_using_ll_driver(hdev, &usb_hid_driver)) {
+	if (hid_is_usb(hdev)) {
 		intf = to_usb_interface(hdev->dev.parent);
 		if (intf && intf->altsetting->desc.bInterfaceNumber >=
 							no_dj_interfaces) {
diff --git a/drivers/hid/hid-magicmouse.c b/drivers/hid/hid-magicmouse.c
index 686788ebf3e1..d7687ce70614 100644
--- a/drivers/hid/hid-magicmouse.c
+++ b/drivers/hid/hid-magicmouse.c
@@ -256,8 +256,11 @@ static void magicmouse_emit_touch(struct magicmouse_sc *msc, int raw_id, u8 *tda
 		unsigned long now = jiffies;
 		int step_x = msc->touches[id].scroll_x - x;
 		int step_y = msc->touches[id].scroll_y - y;
-		int step_hr = ((64 - (int)scroll_speed) * msc->scroll_accel) /
-			      SCROLL_HR_STEPS;
+		int step_hr =
+			max_t(int,
+			      ((64 - (int)scroll_speed) * msc->scroll_accel) /
+					SCROLL_HR_STEPS,
+			      1);
 		int step_x_hr = msc->touches[id].scroll_x_hr - x;
 		int step_y_hr = msc->touches[id].scroll_y_hr - y;
 
diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c
index e1afddb7b33d..082376a6cb3d 100644
--- a/drivers/hid/hid-multitouch.c
+++ b/drivers/hid/hid-multitouch.c
@@ -1888,6 +1888,11 @@ static const struct hid_device_id mt_devices[] = {
 		MT_USB_DEVICE(USB_VENDOR_ID_CVTOUCH,
 			USB_DEVICE_ID_CVTOUCH_SCREEN) },
 
+	/* eGalax devices (SAW) */
+	{ .driver_data = MT_CLS_EXPORT_ALL_INPUTS,
+		MT_USB_DEVICE(USB_VENDOR_ID_DWAV,
+			USB_DEVICE_ID_EGALAX_TOUCHCONTROLLER) },
+
 	/* eGalax devices (resistive) */
 	{ .driver_data = MT_CLS_EGALAX,
 		MT_USB_DEVICE(USB_VENDOR_ID_DWAV,
diff --git a/drivers/hid/hid-nintendo.c b/drivers/hid/hid-nintendo.c
index a1e0f6849875..b6a9a0f3966e 100644
--- a/drivers/hid/hid-nintendo.c
+++ b/drivers/hid/hid-nintendo.c
@@ -189,6 +189,7 @@ struct joycon_rumble_amp_data {
 	u16 amp;
 };
 
+#if IS_ENABLED(CONFIG_NINTENDO_FF)
 /*
  * These tables are from
  * https://github.com/dekuNukem/Nintendo_Switch_Reverse_Engineering/blob/master/rumble_data_table.md
@@ -289,6 +290,10 @@ static const struct joycon_rumble_amp_data joycon_rumble_amplitudes[] = {
 	{ 0xc2, 0x8070,  940 }, { 0xc4, 0x0071,  960 }, { 0xc6, 0x8071,  981 },
 	{ 0xc8, 0x0072, joycon_max_rumble_amp }
 };
+static const u16 JC_RUMBLE_DFLT_LOW_FREQ = 160;
+static const u16 JC_RUMBLE_DFLT_HIGH_FREQ = 320;
+#endif /* IS_ENABLED(CONFIG_NINTENDO_FF) */
+static const u16 JC_RUMBLE_PERIOD_MS = 50;
 
 /* States for controller state machine */
 enum joycon_ctlr_state {
@@ -397,9 +402,6 @@ struct joycon_input_report {
 #define JC_RUMBLE_DATA_SIZE	8
 #define JC_RUMBLE_QUEUE_SIZE	8
 
-static const u16 JC_RUMBLE_DFLT_LOW_FREQ = 160;
-static const u16 JC_RUMBLE_DFLT_HIGH_FREQ = 320;
-static const u16 JC_RUMBLE_PERIOD_MS = 50;
 static const unsigned short JC_RUMBLE_ZERO_AMP_PKT_CNT = 5;
 
 static const char * const joycon_player_led_names[] = {
@@ -1850,8 +1852,10 @@ static int joycon_leds_create(struct joycon_ctlr *ctlr)
 				      d_name,
 				      "green",
 				      joycon_player_led_names[i]);
-		if (!name)
+		if (!name) {
+			mutex_unlock(&joycon_input_num_mutex);
 			return -ENOMEM;
+		}
 
 		led = &ctlr->leds[i];
 		led->name = name;
@@ -1864,6 +1868,7 @@ static int joycon_leds_create(struct joycon_ctlr *ctlr)
 		ret = devm_led_classdev_register(&hdev->dev, led);
 		if (ret) {
 			hid_err(hdev, "Failed registering %s LED\n", led->name);
+			mutex_unlock(&joycon_input_num_mutex);
 			return ret;
 		}
 	}
diff --git a/drivers/hid/hid-prodikeys.c b/drivers/hid/hid-prodikeys.c
index 2666af02d5c1..e4e9471d0f1e 100644
--- a/drivers/hid/hid-prodikeys.c
+++ b/drivers/hid/hid-prodikeys.c
@@ -798,12 +798,18 @@ static int pk_raw_event(struct hid_device *hdev, struct hid_report *report,
 static int pk_probe(struct hid_device *hdev, const struct hid_device_id *id)
 {
 	int ret;
-	struct usb_interface *intf = to_usb_interface(hdev->dev.parent);
-	unsigned short ifnum = intf->cur_altsetting->desc.bInterfaceNumber;
+	struct usb_interface *intf;
+	unsigned short ifnum;
 	unsigned long quirks = id->driver_data;
 	struct pk_device *pk;
 	struct pcmidi_snd *pm = NULL;
 
+	if (!hid_is_usb(hdev))
+		return -EINVAL;
+
+	intf = to_usb_interface(hdev->dev.parent);
+	ifnum = intf->cur_altsetting->desc.bInterfaceNumber;
+
 	pk = kzalloc(sizeof(*pk), GFP_KERNEL);
 	if (pk == NULL) {
 		hid_err(hdev, "can't alloc descriptor\n");
diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c
index 06b7908c874c..ee7e504e7279 100644
--- a/drivers/hid/hid-quirks.c
+++ b/drivers/hid/hid-quirks.c
@@ -124,6 +124,7 @@ static const struct hid_device_id hid_quirks[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MCS, USB_DEVICE_ID_MCS_GAMEPADBLOCK), HID_QUIRK_MULTI_INPUT },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_PIXART_MOUSE), HID_QUIRK_ALWAYS_POLL },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_POWER_COVER), HID_QUIRK_NO_INIT_REPORTS },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_SURFACE3_COVER), HID_QUIRK_NO_INIT_REPORTS },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_SURFACE_PRO_2), HID_QUIRK_NO_INIT_REPORTS },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TOUCH_COVER_2), HID_QUIRK_NO_INIT_REPORTS },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_2), HID_QUIRK_NO_INIT_REPORTS },
diff --git a/drivers/hid/hid-roccat-arvo.c b/drivers/hid/hid-roccat-arvo.c
index 4556d2a50f75..d94ee0539421 100644
--- a/drivers/hid/hid-roccat-arvo.c
+++ b/drivers/hid/hid-roccat-arvo.c
@@ -344,6 +344,9 @@ static int arvo_probe(struct hid_device *hdev,
 {
 	int retval;
 
+	if (!hid_is_usb(hdev))
+		return -EINVAL;
+
 	retval = hid_parse(hdev);
 	if (retval) {
 		hid_err(hdev, "parse failed\n");
diff --git a/drivers/hid/hid-roccat-isku.c b/drivers/hid/hid-roccat-isku.c
index ce5f22519956..e95d59cd8d07 100644
--- a/drivers/hid/hid-roccat-isku.c
+++ b/drivers/hid/hid-roccat-isku.c
@@ -324,6 +324,9 @@ static int isku_probe(struct hid_device *hdev,
 {
 	int retval;
 
+	if (!hid_is_usb(hdev))
+		return -EINVAL;
+
 	retval = hid_parse(hdev);
 	if (retval) {
 		hid_err(hdev, "parse failed\n");
diff --git a/drivers/hid/hid-roccat-kone.c b/drivers/hid/hid-roccat-kone.c
index ea17abc7ad52..76da04801ca9 100644
--- a/drivers/hid/hid-roccat-kone.c
+++ b/drivers/hid/hid-roccat-kone.c
@@ -749,6 +749,9 @@ static int kone_probe(struct hid_device *hdev, const struct hid_device_id *id)
 {
 	int retval;
 
+	if (!hid_is_usb(hdev))
+		return -EINVAL;
+
 	retval = hid_parse(hdev);
 	if (retval) {
 		hid_err(hdev, "parse failed\n");
diff --git a/drivers/hid/hid-roccat-koneplus.c b/drivers/hid/hid-roccat-koneplus.c
index 0316edf8c5bb..1896c69ea512 100644
--- a/drivers/hid/hid-roccat-koneplus.c
+++ b/drivers/hid/hid-roccat-koneplus.c
@@ -431,6 +431,9 @@ static int koneplus_probe(struct hid_device *hdev,
 {
 	int retval;
 
+	if (!hid_is_usb(hdev))
+		return -EINVAL;
+
 	retval = hid_parse(hdev);
 	if (retval) {
 		hid_err(hdev, "parse failed\n");
diff --git a/drivers/hid/hid-roccat-konepure.c b/drivers/hid/hid-roccat-konepure.c
index 5248b3c7cf78..cf8eeb33a125 100644
--- a/drivers/hid/hid-roccat-konepure.c
+++ b/drivers/hid/hid-roccat-konepure.c
@@ -133,6 +133,9 @@ static int konepure_probe(struct hid_device *hdev,
 {
 	int retval;
 
+	if (!hid_is_usb(hdev))
+		return -EINVAL;
+
 	retval = hid_parse(hdev);
 	if (retval) {
 		hid_err(hdev, "parse failed\n");
diff --git a/drivers/hid/hid-roccat-kovaplus.c b/drivers/hid/hid-roccat-kovaplus.c
index 960012881570..6fb9b9563769 100644
--- a/drivers/hid/hid-roccat-kovaplus.c
+++ b/drivers/hid/hid-roccat-kovaplus.c
@@ -501,6 +501,9 @@ static int kovaplus_probe(struct hid_device *hdev,
 {
 	int retval;
 
+	if (!hid_is_usb(hdev))
+		return -EINVAL;
+
 	retval = hid_parse(hdev);
 	if (retval) {
 		hid_err(hdev, "parse failed\n");
diff --git a/drivers/hid/hid-roccat-lua.c b/drivers/hid/hid-roccat-lua.c
index 4a88a76d5c62..d5ddf0d68346 100644
--- a/drivers/hid/hid-roccat-lua.c
+++ b/drivers/hid/hid-roccat-lua.c
@@ -160,6 +160,9 @@ static int lua_probe(struct hid_device *hdev,
 {
 	int retval;
 
+	if (!hid_is_usb(hdev))
+		return -EINVAL;
+
 	retval = hid_parse(hdev);
 	if (retval) {
 		hid_err(hdev, "parse failed\n");
diff --git a/drivers/hid/hid-roccat-pyra.c b/drivers/hid/hid-roccat-pyra.c
index 989927defe8d..4fcc8e7d276f 100644
--- a/drivers/hid/hid-roccat-pyra.c
+++ b/drivers/hid/hid-roccat-pyra.c
@@ -449,6 +449,9 @@ static int pyra_probe(struct hid_device *hdev, const struct hid_device_id *id)
 {
 	int retval;
 
+	if (!hid_is_usb(hdev))
+		return -EINVAL;
+
 	retval = hid_parse(hdev);
 	if (retval) {
 		hid_err(hdev, "parse failed\n");
diff --git a/drivers/hid/hid-roccat-ryos.c b/drivers/hid/hid-roccat-ryos.c
index 3956a6c9c521..5bf1971a2b14 100644
--- a/drivers/hid/hid-roccat-ryos.c
+++ b/drivers/hid/hid-roccat-ryos.c
@@ -141,6 +141,9 @@ static int ryos_probe(struct hid_device *hdev,
 {
 	int retval;
 
+	if (!hid_is_usb(hdev))
+		return -EINVAL;
+
 	retval = hid_parse(hdev);
 	if (retval) {
 		hid_err(hdev, "parse failed\n");
diff --git a/drivers/hid/hid-roccat-savu.c b/drivers/hid/hid-roccat-savu.c
index 818701f7a028..a784bb4ee651 100644
--- a/drivers/hid/hid-roccat-savu.c
+++ b/drivers/hid/hid-roccat-savu.c
@@ -113,6 +113,9 @@ static int savu_probe(struct hid_device *hdev,
 {
 	int retval;
 
+	if (!hid_is_usb(hdev))
+		return -EINVAL;
+
 	retval = hid_parse(hdev);
 	if (retval) {
 		hid_err(hdev, "parse failed\n");
diff --git a/drivers/hid/hid-samsung.c b/drivers/hid/hid-samsung.c
index 2e1c31156eca..cf5992e97094 100644
--- a/drivers/hid/hid-samsung.c
+++ b/drivers/hid/hid-samsung.c
@@ -152,6 +152,9 @@ static int samsung_probe(struct hid_device *hdev,
 	int ret;
 	unsigned int cmask = HID_CONNECT_DEFAULT;
 
+	if (!hid_is_usb(hdev))
+		return -EINVAL;
+
 	ret = hid_parse(hdev);
 	if (ret) {
 		hid_err(hdev, "parse failed\n");
diff --git a/drivers/hid/hid-sony.c b/drivers/hid/hid-sony.c
index d1b107d547f5..60ec2b29d54d 100644
--- a/drivers/hid/hid-sony.c
+++ b/drivers/hid/hid-sony.c
@@ -3000,7 +3000,6 @@ static int sony_probe(struct hid_device *hdev, const struct hid_device_id *id)
 	sc->quirks = quirks;
 	hid_set_drvdata(hdev, sc);
 	sc->hdev = hdev;
-	usbdev = to_usb_device(sc->hdev->dev.parent->parent);
 
 	ret = hid_parse(hdev);
 	if (ret) {
@@ -3038,14 +3037,23 @@ static int sony_probe(struct hid_device *hdev, const struct hid_device_id *id)
 	 */
 	if (!(hdev->claimed & HID_CLAIMED_INPUT)) {
 		hid_err(hdev, "failed to claim input\n");
-		hid_hw_stop(hdev);
-		return -ENODEV;
+		ret = -ENODEV;
+		goto err;
 	}
 
 	if (sc->quirks & (GHL_GUITAR_PS3WIIU | GHL_GUITAR_PS4)) {
+		if (!hid_is_usb(hdev)) {
+			ret = -EINVAL;
+			goto err;
+		}
+
+		usbdev = to_usb_device(sc->hdev->dev.parent->parent);
+
 		sc->ghl_urb = usb_alloc_urb(0, GFP_ATOMIC);
-		if (!sc->ghl_urb)
-			return -ENOMEM;
+		if (!sc->ghl_urb) {
+			ret = -ENOMEM;
+			goto err;
+		}
 
 		if (sc->quirks & GHL_GUITAR_PS3WIIU)
 			ret = ghl_init_urb(sc, usbdev, ghl_ps3wiiu_magic_data,
@@ -3055,7 +3063,7 @@ static int sony_probe(struct hid_device *hdev, const struct hid_device_id *id)
 							   ARRAY_SIZE(ghl_ps4_magic_data));
 		if (ret) {
 			hid_err(hdev, "error preparing URB\n");
-			return ret;
+			goto err;
 		}
 
 		timer_setup(&sc->ghl_poke_timer, ghl_magic_poke, 0);
@@ -3064,6 +3072,10 @@ static int sony_probe(struct hid_device *hdev, const struct hid_device_id *id)
 	}
 
 	return ret;
+
+err:
+	hid_hw_stop(hdev);
+	return ret;
 }
 
 static void sony_remove(struct hid_device *hdev)
diff --git a/drivers/hid/hid-thrustmaster.c b/drivers/hid/hid-thrustmaster.c
index d44550aa8805..03b935ff02d5 100644
--- a/drivers/hid/hid-thrustmaster.c
+++ b/drivers/hid/hid-thrustmaster.c
@@ -205,7 +205,7 @@ static void thrustmaster_model_handler(struct urb *urb)
 	struct tm_wheel *tm_wheel = hid_get_drvdata(hdev);
 	uint16_t model = 0;
 	int i, ret;
-	const struct tm_wheel_info *twi = 0;
+	const struct tm_wheel_info *twi = NULL;
 
 	if (urb->status) {
 		hid_err(hdev, "URB to get model id failed with error %d\n", urb->status);
@@ -238,7 +238,7 @@ static void thrustmaster_model_handler(struct urb *urb)
 		tm_wheel->usb_dev,
 		usb_sndctrlpipe(tm_wheel->usb_dev, 0),
 		(char *)tm_wheel->change_request,
-		0, 0, // We do not expect any response from the wheel
+		NULL, 0, // We do not expect any response from the wheel
 		thrustmaster_change_handler,
 		hdev
 	);
@@ -272,7 +272,10 @@ static void thrustmaster_remove(struct hid_device *hdev)
 static int thrustmaster_probe(struct hid_device *hdev, const struct hid_device_id *id)
 {
 	int ret = 0;
-	struct tm_wheel *tm_wheel = 0;
+	struct tm_wheel *tm_wheel = NULL;
+
+	if (!hid_is_usb(hdev))
+		return -EINVAL;
 
 	ret = hid_parse(hdev);
 	if (ret) {
diff --git a/drivers/hid/hid-u2fzero.c b/drivers/hid/hid-u2fzero.c
index 31ea7fc69916..ad489caf53ad 100644
--- a/drivers/hid/hid-u2fzero.c
+++ b/drivers/hid/hid-u2fzero.c
@@ -311,7 +311,7 @@ static int u2fzero_probe(struct hid_device *hdev,
 	unsigned int minor;
 	int ret;
 
-	if (!hid_is_using_ll_driver(hdev, &usb_hid_driver))
+	if (!hid_is_usb(hdev))
 		return -EINVAL;
 
 	dev = devm_kzalloc(&hdev->dev, sizeof(*dev), GFP_KERNEL);
diff --git a/drivers/hid/hid-uclogic-core.c b/drivers/hid/hid-uclogic-core.c
index 6a9865dd703c..d8ab0139e5cd 100644
--- a/drivers/hid/hid-uclogic-core.c
+++ b/drivers/hid/hid-uclogic-core.c
@@ -164,6 +164,9 @@ static int uclogic_probe(struct hid_device *hdev,
 	struct uclogic_drvdata *drvdata = NULL;
 	bool params_initialized = false;
 
+	if (!hid_is_usb(hdev))
+		return -EINVAL;
+
 	/*
 	 * libinput requires the pad interface to be on a different node
 	 * than the pen, so use QUIRK_MULTI_INPUT for all tablets.
diff --git a/drivers/hid/hid-uclogic-params.c b/drivers/hid/hid-uclogic-params.c
index 3d67b748a3b9..adff1bd68d9f 100644
--- a/drivers/hid/hid-uclogic-params.c
+++ b/drivers/hid/hid-uclogic-params.c
@@ -843,8 +843,7 @@ int uclogic_params_init(struct uclogic_params *params,
 	struct uclogic_params p = {0, };
 
 	/* Check arguments */
-	if (params == NULL || hdev == NULL ||
-	    !hid_is_using_ll_driver(hdev, &usb_hid_driver)) {
+	if (params == NULL || hdev == NULL || !hid_is_usb(hdev)) {
 		rc = -EINVAL;
 		goto cleanup;
 	}
diff --git a/drivers/hid/hid-vivaldi.c b/drivers/hid/hid-vivaldi.c
index cd7ada48b1d9..72957a9f7117 100644
--- a/drivers/hid/hid-vivaldi.c
+++ b/drivers/hid/hid-vivaldi.c
@@ -57,6 +57,9 @@ static int vivaldi_probe(struct hid_device *hdev,
 	int ret;
 
 	drvdata = devm_kzalloc(&hdev->dev, sizeof(*drvdata), GFP_KERNEL);
+	if (!drvdata)
+		return -ENOMEM;
+
 	hid_set_drvdata(hdev, drvdata);
 
 	ret = hid_parse(hdev);
diff --git a/drivers/hid/intel-ish-hid/ipc/pci-ish.c b/drivers/hid/intel-ish-hid/ipc/pci-ish.c
index 1c5039081db2..8e9d9450cb83 100644
--- a/drivers/hid/intel-ish-hid/ipc/pci-ish.c
+++ b/drivers/hid/intel-ish-hid/ipc/pci-ish.c
@@ -266,7 +266,8 @@ static void __maybe_unused ish_resume_handler(struct work_struct *work)
 
 	if (ish_should_leave_d0i3(pdev) && !dev->suspend_flag
 			&& IPC_IS_ISH_ILUP(fwsts)) {
-		disable_irq_wake(pdev->irq);
+		if (device_may_wakeup(&pdev->dev))
+			disable_irq_wake(pdev->irq);
 
 		ish_set_host_ready(dev);
 
@@ -337,7 +338,8 @@ static int __maybe_unused ish_suspend(struct device *device)
 			 */
 			pci_save_state(pdev);
 
-			enable_irq_wake(pdev->irq);
+			if (device_may_wakeup(&pdev->dev))
+				enable_irq_wake(pdev->irq);
 		}
 	} else {
 		/*
diff --git a/drivers/hid/intel-ish-hid/ishtp-fw-loader.c b/drivers/hid/intel-ish-hid/ishtp-fw-loader.c
index 1b486f262747..0e1183e96147 100644
--- a/drivers/hid/intel-ish-hid/ishtp-fw-loader.c
+++ b/drivers/hid/intel-ish-hid/ishtp-fw-loader.c
@@ -76,9 +76,12 @@ enum ish_loader_commands {
 #define LOADER_XFER_MODE_ISHTP			BIT(1)
 
 /* ISH Transport Loader client unique GUID */
-static const guid_t loader_ishtp_guid =
-	GUID_INIT(0xc804d06a, 0x55bd, 0x4ea7,
-		  0xad, 0xed, 0x1e, 0x31, 0x22, 0x8c, 0x76, 0xdc);
+static const struct ishtp_device_id loader_ishtp_id_table[] = {
+	{ .guid = GUID_INIT(0xc804d06a, 0x55bd, 0x4ea7,
+		  0xad, 0xed, 0x1e, 0x31, 0x22, 0x8c, 0x76, 0xdc) },
+	{ }
+};
+MODULE_DEVICE_TABLE(ishtp, loader_ishtp_id_table);
 
 #define FILENAME_SIZE				256
 
@@ -880,7 +883,7 @@ static int loader_init(struct ishtp_cl *loader_ishtp_cl, int reset)
 
 	fw_client =
 		ishtp_fw_cl_get_client(ishtp_get_ishtp_device(loader_ishtp_cl),
-				       &loader_ishtp_guid);
+				       &loader_ishtp_id_table[0].guid);
 	if (!fw_client) {
 		dev_err(cl_data_to_dev(client_data),
 			"ISH client uuid not found\n");
@@ -1057,7 +1060,7 @@ static int loader_ishtp_cl_reset(struct ishtp_cl_device *cl_device)
 
 static struct ishtp_cl_driver	loader_ishtp_cl_driver = {
 	.name = "ish-loader",
-	.guid = &loader_ishtp_guid,
+	.id = loader_ishtp_id_table,
 	.probe = loader_ishtp_cl_probe,
 	.remove = loader_ishtp_cl_remove,
 	.reset = loader_ishtp_cl_reset,
@@ -1083,4 +1086,3 @@ MODULE_DESCRIPTION("ISH ISH-TP Host firmware Loader Client Driver");
 MODULE_AUTHOR("Rushikesh S Kadam <rushikesh.s.kadam@intel.com>");
 
 MODULE_LICENSE("GPL v2");
-MODULE_ALIAS("ishtp:*");
diff --git a/drivers/hid/intel-ish-hid/ishtp-hid-client.c b/drivers/hid/intel-ish-hid/ishtp-hid-client.c
index 91bf4d01e91a..4338c9b68a43 100644
--- a/drivers/hid/intel-ish-hid/ishtp-hid-client.c
+++ b/drivers/hid/intel-ish-hid/ishtp-hid-client.c
@@ -12,9 +12,12 @@
 #include "ishtp-hid.h"
 
 /* ISH Transport protocol (ISHTP in short) GUID */
-static const guid_t hid_ishtp_guid =
-	GUID_INIT(0x33AECD58, 0xB679, 0x4E54,
-		  0x9B, 0xD9, 0xA0, 0x4D, 0x34, 0xF0, 0xC2, 0x26);
+static const struct ishtp_device_id hid_ishtp_id_table[] = {
+	{ .guid = GUID_INIT(0x33AECD58, 0xB679, 0x4E54,
+		  0x9B, 0xD9, 0xA0, 0x4D, 0x34, 0xF0, 0xC2, 0x26), },
+	{ }
+};
+MODULE_DEVICE_TABLE(ishtp, hid_ishtp_id_table);
 
 /* Rx ring buffer pool size */
 #define HID_CL_RX_RING_SIZE	32
@@ -662,7 +665,7 @@ static int hid_ishtp_cl_init(struct ishtp_cl *hid_ishtp_cl, int reset)
 	ishtp_set_tx_ring_size(hid_ishtp_cl, HID_CL_TX_RING_SIZE);
 	ishtp_set_rx_ring_size(hid_ishtp_cl, HID_CL_RX_RING_SIZE);
 
-	fw_client = ishtp_fw_cl_get_client(dev, &hid_ishtp_guid);
+	fw_client = ishtp_fw_cl_get_client(dev, &hid_ishtp_id_table[0].guid);
 	if (!fw_client) {
 		dev_err(cl_data_to_dev(client_data),
 			"ish client uuid not found\n");
@@ -945,7 +948,7 @@ static const struct dev_pm_ops hid_ishtp_pm_ops = {
 
 static struct ishtp_cl_driver	hid_ishtp_cl_driver = {
 	.name = "ish-hid",
-	.guid = &hid_ishtp_guid,
+	.id = hid_ishtp_id_table,
 	.probe = hid_ishtp_cl_probe,
 	.remove = hid_ishtp_cl_remove,
 	.reset = hid_ishtp_cl_reset,
@@ -981,4 +984,3 @@ MODULE_AUTHOR("Daniel Drubin <daniel.drubin@intel.com>");
 MODULE_AUTHOR("Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>");
 
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("ishtp:*");
diff --git a/drivers/hid/intel-ish-hid/ishtp/bus.c b/drivers/hid/intel-ish-hid/ishtp/bus.c
index 334eac611774..f68aba8794fe 100644
--- a/drivers/hid/intel-ish-hid/ishtp/bus.c
+++ b/drivers/hid/intel-ish-hid/ishtp/bus.c
@@ -241,7 +241,7 @@ static int ishtp_cl_bus_match(struct device *dev, struct device_driver *drv)
 	struct ishtp_cl_device *device = to_ishtp_cl_device(dev);
 	struct ishtp_cl_driver *driver = to_ishtp_cl_driver(drv);
 
-	return guid_equal(driver->guid,
+	return guid_equal(&driver->id[0].guid,
 			  &device->fw_client->props.protocol_name);
 }
 
@@ -350,7 +350,7 @@ static ssize_t modalias_show(struct device *dev, struct device_attribute *a,
 {
 	int len;
 
-	len = snprintf(buf, PAGE_SIZE, "ishtp:%s\n", dev_name(dev));
+	len = snprintf(buf, PAGE_SIZE, ISHTP_MODULE_PREFIX "%s\n", dev_name(dev));
 	return (len >= PAGE_SIZE) ? (PAGE_SIZE - 1) : len;
 }
 static DEVICE_ATTR_RO(modalias);
@@ -363,7 +363,7 @@ ATTRIBUTE_GROUPS(ishtp_cl_dev);
 
 static int ishtp_cl_uevent(struct device *dev, struct kobj_uevent_env *env)
 {
-	if (add_uevent_var(env, "MODALIAS=ishtp:%s", dev_name(dev)))
+	if (add_uevent_var(env, "MODALIAS=" ISHTP_MODULE_PREFIX "%s", dev_name(dev)))
 		return -ENOMEM;
 	return 0;
 }
diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c
index 2717d39600b4..066c567dbaa2 100644
--- a/drivers/hid/wacom_sys.c
+++ b/drivers/hid/wacom_sys.c
@@ -726,7 +726,7 @@ static void wacom_retrieve_hid_descriptor(struct hid_device *hdev,
 	 * Skip the query for this type and modify defaults based on
 	 * interface number.
 	 */
-	if (features->type == WIRELESS) {
+	if (features->type == WIRELESS && intf) {
 		if (intf->cur_altsetting->desc.bInterfaceNumber == 0)
 			features->device_type = WACOM_DEVICETYPE_WL_MONITOR;
 		else
@@ -2214,7 +2214,7 @@ static void wacom_update_name(struct wacom *wacom, const char *suffix)
 	if ((features->type == HID_GENERIC) && !strcmp("Wacom HID", features->name)) {
 		char *product_name = wacom->hdev->name;
 
-		if (hid_is_using_ll_driver(wacom->hdev, &usb_hid_driver)) {
+		if (hid_is_usb(wacom->hdev)) {
 			struct usb_interface *intf = to_usb_interface(wacom->hdev->dev.parent);
 			struct usb_device *dev = interface_to_usbdev(intf);
 			product_name = dev->product;
@@ -2451,6 +2451,9 @@ static void wacom_wireless_work(struct work_struct *work)
 
 	wacom_destroy_battery(wacom);
 
+	if (!usbdev)
+		return;
+
 	/* Stylus interface */
 	hdev1 = usb_get_intfdata(usbdev->config->interface[1]);
 	wacom1 = hid_get_drvdata(hdev1);
@@ -2730,8 +2733,6 @@ static void wacom_mode_change_work(struct work_struct *work)
 static int wacom_probe(struct hid_device *hdev,
 		const struct hid_device_id *id)
 {
-	struct usb_interface *intf = to_usb_interface(hdev->dev.parent);
-	struct usb_device *dev = interface_to_usbdev(intf);
 	struct wacom *wacom;
 	struct wacom_wac *wacom_wac;
 	struct wacom_features *features;
@@ -2766,8 +2767,14 @@ static int wacom_probe(struct hid_device *hdev,
 	wacom_wac->hid_data.inputmode = -1;
 	wacom_wac->mode_report = -1;
 
-	wacom->usbdev = dev;
-	wacom->intf = intf;
+	if (hid_is_usb(hdev)) {
+		struct usb_interface *intf = to_usb_interface(hdev->dev.parent);
+		struct usb_device *dev = interface_to_usbdev(intf);
+
+		wacom->usbdev = dev;
+		wacom->intf = intf;
+	}
+
 	mutex_init(&wacom->lock);
 	INIT_DELAYED_WORK(&wacom->init_work, wacom_init_work);
 	INIT_WORK(&wacom->wireless_work, wacom_wireless_work);
diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c
index 33a6908995b1..2a4cc39962e7 100644
--- a/drivers/hid/wacom_wac.c
+++ b/drivers/hid/wacom_wac.c
@@ -2603,6 +2603,9 @@ static void wacom_wac_finger_event(struct hid_device *hdev,
 		return;
 
 	switch (equivalent_usage) {
+	case HID_DG_CONFIDENCE:
+		wacom_wac->hid_data.confidence = value;
+		break;
 	case HID_GD_X:
 		wacom_wac->hid_data.x = value;
 		break;
@@ -2635,7 +2638,8 @@ static void wacom_wac_finger_event(struct hid_device *hdev,
 	}
 
 	if (usage->usage_index + 1 == field->report_count) {
-		if (equivalent_usage == wacom_wac->hid_data.last_slot_field)
+		if (equivalent_usage == wacom_wac->hid_data.last_slot_field &&
+		    wacom_wac->hid_data.confidence)
 			wacom_wac_finger_slot(wacom_wac, wacom_wac->touch_input);
 	}
 }
@@ -2653,6 +2657,8 @@ static void wacom_wac_finger_pre_report(struct hid_device *hdev,
 
 	wacom_wac->is_invalid_bt_frame = false;
 
+	hid_data->confidence = true;
+
 	for (i = 0; i < report->maxfield; i++) {
 		struct hid_field *field = report->field[i];
 		int j;
diff --git a/drivers/hid/wacom_wac.h b/drivers/hid/wacom_wac.h
index 8b2d4e5b2303..466b62cc16dc 100644
--- a/drivers/hid/wacom_wac.h
+++ b/drivers/hid/wacom_wac.h
@@ -301,6 +301,7 @@ struct hid_data {
 	bool barrelswitch;
 	bool barrelswitch2;
 	bool serialhi;
+	bool confidence;
 	int x;
 	int y;
 	int pressure;
diff --git a/drivers/hv/Kconfig b/drivers/hv/Kconfig
index dd12af20e467..0747a8f1fcee 100644
--- a/drivers/hv/Kconfig
+++ b/drivers/hv/Kconfig
@@ -19,6 +19,7 @@ config HYPERV_TIMER
 config HYPERV_UTILS
 	tristate "Microsoft Hyper-V Utilities driver"
 	depends on HYPERV && CONNECTOR && NLS
+	depends on PTP_1588_CLOCK_OPTIONAL
 	help
 	  Select this option to enable the Hyper-V Utilities.
 
diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c
index 7f11ea07d698..ca873a3b98db 100644
--- a/drivers/hv/hv_balloon.c
+++ b/drivers/hv/hv_balloon.c
@@ -480,7 +480,7 @@ module_param(pressure_report_delay, uint, (S_IRUGO | S_IWUSR));
 MODULE_PARM_DESC(pressure_report_delay, "Delay in secs in reporting pressure");
 static atomic_t trans_id = ATOMIC_INIT(0);
 
-static int dm_ring_size = 20 * 1024;
+static int dm_ring_size = VMBUS_RING_SIZE(16 * 1024);
 
 /*
  * Driver specific state.
diff --git a/drivers/hwmon/corsair-psu.c b/drivers/hwmon/corsair-psu.c
index 731d5117f9f1..14389fd7afb8 100644
--- a/drivers/hwmon/corsair-psu.c
+++ b/drivers/hwmon/corsair-psu.c
@@ -729,7 +729,7 @@ static int corsairpsu_probe(struct hid_device *hdev, const struct hid_device_id
 	corsairpsu_check_cmd_support(priv);
 
 	priv->hwmon_dev = hwmon_device_register_with_info(&hdev->dev, "corsairpsu", priv,
-							  &corsairpsu_chip_info, 0);
+							  &corsairpsu_chip_info, NULL);
 
 	if (IS_ERR(priv->hwmon_dev)) {
 		ret = PTR_ERR(priv->hwmon_dev);
diff --git a/drivers/hwmon/dell-smm-hwmon.c b/drivers/hwmon/dell-smm-hwmon.c
index eaace478f508..5596c211f38d 100644
--- a/drivers/hwmon/dell-smm-hwmon.c
+++ b/drivers/hwmon/dell-smm-hwmon.c
@@ -627,10 +627,9 @@ static void __init i8k_init_procfs(struct device *dev)
 {
 	struct dell_smm_data *data = dev_get_drvdata(dev);
 
-	/* Register the proc entry */
-	proc_create_data("i8k", 0, NULL, &i8k_proc_ops, data);
-
-	devm_add_action_or_reset(dev, i8k_exit_procfs, NULL);
+	/* Only register exit function if creation was successful */
+	if (proc_create_data("i8k", 0, NULL, &i8k_proc_ops, data))
+		devm_add_action_or_reset(dev, i8k_exit_procfs, NULL);
 }
 
 #else
diff --git a/drivers/hwmon/lm90.c b/drivers/hwmon/lm90.c
index 618052c6cdb6..74019dff2550 100644
--- a/drivers/hwmon/lm90.c
+++ b/drivers/hwmon/lm90.c
@@ -35,13 +35,14 @@
  * explicitly as max6659, or if its address is not 0x4c.
  * These chips lack the remote temperature offset feature.
  *
- * This driver also supports the MAX6654 chip made by Maxim. This chip can
- * be at 9 different addresses, similar to MAX6680/MAX6681. The MAX6654 is
- * otherwise similar to MAX6657/MAX6658/MAX6659. Extended range is available
- * by setting the configuration register accordingly, and is done during
- * initialization. Extended precision is only available at conversion rates
- * of 1 Hz and slower. Note that extended precision is not enabled by
- * default, as this driver initializes all chips to 2 Hz by design.
+ * This driver also supports the MAX6654 chip made by Maxim. This chip can be
+ * at 9 different addresses, similar to MAX6680/MAX6681. The MAX6654 is similar
+ * to MAX6657/MAX6658/MAX6659, but does not support critical temperature
+ * limits. Extended range is available by setting the configuration register
+ * accordingly, and is done during initialization. Extended precision is only
+ * available at conversion rates of 1 Hz and slower. Note that extended
+ * precision is not enabled by default, as this driver initializes all chips
+ * to 2 Hz by design.
  *
  * This driver also supports the MAX6646, MAX6647, MAX6648, MAX6649 and
  * MAX6692 chips made by Maxim.  These are again similar to the LM86,
@@ -188,6 +189,8 @@ enum chips { lm90, adm1032, lm99, lm86, max6657, max6659, adt7461, max6680,
 #define LM90_HAVE_BROKEN_ALERT	(1 << 7) /* Broken alert		*/
 #define LM90_HAVE_EXTENDED_TEMP	(1 << 8) /* extended temperature support*/
 #define LM90_PAUSE_FOR_CONFIG	(1 << 9) /* Pause conversion for config	*/
+#define LM90_HAVE_CRIT		(1 << 10)/* Chip supports CRIT/OVERT register	*/
+#define LM90_HAVE_CRIT_ALRM_SWP	(1 << 11)/* critical alarm bits swapped	*/
 
 /* LM90 status */
 #define LM90_STATUS_LTHRM	(1 << 0) /* local THERM limit tripped */
@@ -197,6 +200,7 @@ enum chips { lm90, adm1032, lm99, lm86, max6657, max6659, adt7461, max6680,
 #define LM90_STATUS_RHIGH	(1 << 4) /* remote high temp limit tripped */
 #define LM90_STATUS_LLOW	(1 << 5) /* local low temp limit tripped */
 #define LM90_STATUS_LHIGH	(1 << 6) /* local high temp limit tripped */
+#define LM90_STATUS_BUSY	(1 << 7) /* conversion is ongoing */
 
 #define MAX6696_STATUS2_R2THRM	(1 << 1) /* remote2 THERM limit tripped */
 #define MAX6696_STATUS2_R2OPEN	(1 << 2) /* remote2 is an open circuit */
@@ -354,38 +358,43 @@ struct lm90_params {
 static const struct lm90_params lm90_params[] = {
 	[adm1032] = {
 		.flags = LM90_HAVE_OFFSET | LM90_HAVE_REM_LIMIT_EXT
-		  | LM90_HAVE_BROKEN_ALERT,
+		  | LM90_HAVE_BROKEN_ALERT | LM90_HAVE_CRIT,
 		.alert_alarms = 0x7c,
 		.max_convrate = 10,
 	},
 	[adt7461] = {
 		.flags = LM90_HAVE_OFFSET | LM90_HAVE_REM_LIMIT_EXT
-		  | LM90_HAVE_BROKEN_ALERT | LM90_HAVE_EXTENDED_TEMP,
+		  | LM90_HAVE_BROKEN_ALERT | LM90_HAVE_EXTENDED_TEMP
+		  | LM90_HAVE_CRIT,
 		.alert_alarms = 0x7c,
 		.max_convrate = 10,
 	},
 	[g781] = {
 		.flags = LM90_HAVE_OFFSET | LM90_HAVE_REM_LIMIT_EXT
-		  | LM90_HAVE_BROKEN_ALERT,
+		  | LM90_HAVE_BROKEN_ALERT | LM90_HAVE_CRIT,
 		.alert_alarms = 0x7c,
 		.max_convrate = 8,
 	},
 	[lm86] = {
-		.flags = LM90_HAVE_OFFSET | LM90_HAVE_REM_LIMIT_EXT,
+		.flags = LM90_HAVE_OFFSET | LM90_HAVE_REM_LIMIT_EXT
+		  | LM90_HAVE_CRIT,
 		.alert_alarms = 0x7b,
 		.max_convrate = 9,
 	},
 	[lm90] = {
-		.flags = LM90_HAVE_OFFSET | LM90_HAVE_REM_LIMIT_EXT,
+		.flags = LM90_HAVE_OFFSET | LM90_HAVE_REM_LIMIT_EXT
+		  | LM90_HAVE_CRIT,
 		.alert_alarms = 0x7b,
 		.max_convrate = 9,
 	},
 	[lm99] = {
-		.flags = LM90_HAVE_OFFSET | LM90_HAVE_REM_LIMIT_EXT,
+		.flags = LM90_HAVE_OFFSET | LM90_HAVE_REM_LIMIT_EXT
+		  | LM90_HAVE_CRIT,
 		.alert_alarms = 0x7b,
 		.max_convrate = 9,
 	},
 	[max6646] = {
+		.flags = LM90_HAVE_CRIT,
 		.alert_alarms = 0x7c,
 		.max_convrate = 6,
 		.reg_local_ext = MAX6657_REG_R_LOCAL_TEMPL,
@@ -396,50 +405,51 @@ static const struct lm90_params lm90_params[] = {
 		.reg_local_ext = MAX6657_REG_R_LOCAL_TEMPL,
 	},
 	[max6657] = {
-		.flags = LM90_PAUSE_FOR_CONFIG,
+		.flags = LM90_PAUSE_FOR_CONFIG | LM90_HAVE_CRIT,
 		.alert_alarms = 0x7c,
 		.max_convrate = 8,
 		.reg_local_ext = MAX6657_REG_R_LOCAL_TEMPL,
 	},
 	[max6659] = {
-		.flags = LM90_HAVE_EMERGENCY,
+		.flags = LM90_HAVE_EMERGENCY | LM90_HAVE_CRIT,
 		.alert_alarms = 0x7c,
 		.max_convrate = 8,
 		.reg_local_ext = MAX6657_REG_R_LOCAL_TEMPL,
 	},
 	[max6680] = {
-		.flags = LM90_HAVE_OFFSET,
+		.flags = LM90_HAVE_OFFSET | LM90_HAVE_CRIT
+		  | LM90_HAVE_CRIT_ALRM_SWP,
 		.alert_alarms = 0x7c,
 		.max_convrate = 7,
 	},
 	[max6696] = {
 		.flags = LM90_HAVE_EMERGENCY
-		  | LM90_HAVE_EMERGENCY_ALARM | LM90_HAVE_TEMP3,
+		  | LM90_HAVE_EMERGENCY_ALARM | LM90_HAVE_TEMP3 | LM90_HAVE_CRIT,
 		.alert_alarms = 0x1c7c,
 		.max_convrate = 6,
 		.reg_local_ext = MAX6657_REG_R_LOCAL_TEMPL,
 	},
 	[w83l771] = {
-		.flags = LM90_HAVE_OFFSET | LM90_HAVE_REM_LIMIT_EXT,
+		.flags = LM90_HAVE_OFFSET | LM90_HAVE_REM_LIMIT_EXT | LM90_HAVE_CRIT,
 		.alert_alarms = 0x7c,
 		.max_convrate = 8,
 	},
 	[sa56004] = {
-		.flags = LM90_HAVE_OFFSET | LM90_HAVE_REM_LIMIT_EXT,
+		.flags = LM90_HAVE_OFFSET | LM90_HAVE_REM_LIMIT_EXT | LM90_HAVE_CRIT,
 		.alert_alarms = 0x7b,
 		.max_convrate = 9,
 		.reg_local_ext = SA56004_REG_R_LOCAL_TEMPL,
 	},
 	[tmp451] = {
 		.flags = LM90_HAVE_OFFSET | LM90_HAVE_REM_LIMIT_EXT
-		  | LM90_HAVE_BROKEN_ALERT | LM90_HAVE_EXTENDED_TEMP,
+		  | LM90_HAVE_BROKEN_ALERT | LM90_HAVE_EXTENDED_TEMP | LM90_HAVE_CRIT,
 		.alert_alarms = 0x7c,
 		.max_convrate = 9,
 		.reg_local_ext = TMP451_REG_R_LOCAL_TEMPL,
 	},
 	[tmp461] = {
 		.flags = LM90_HAVE_OFFSET | LM90_HAVE_REM_LIMIT_EXT
-		  | LM90_HAVE_BROKEN_ALERT | LM90_HAVE_EXTENDED_TEMP,
+		  | LM90_HAVE_BROKEN_ALERT | LM90_HAVE_EXTENDED_TEMP | LM90_HAVE_CRIT,
 		.alert_alarms = 0x7c,
 		.max_convrate = 9,
 		.reg_local_ext = TMP451_REG_R_LOCAL_TEMPL,
@@ -668,20 +678,22 @@ static int lm90_update_limits(struct device *dev)
 	struct i2c_client *client = data->client;
 	int val;
 
-	val = lm90_read_reg(client, LM90_REG_R_LOCAL_CRIT);
-	if (val < 0)
-		return val;
-	data->temp8[LOCAL_CRIT] = val;
+	if (data->flags & LM90_HAVE_CRIT) {
+		val = lm90_read_reg(client, LM90_REG_R_LOCAL_CRIT);
+		if (val < 0)
+			return val;
+		data->temp8[LOCAL_CRIT] = val;
 
-	val = lm90_read_reg(client, LM90_REG_R_REMOTE_CRIT);
-	if (val < 0)
-		return val;
-	data->temp8[REMOTE_CRIT] = val;
+		val = lm90_read_reg(client, LM90_REG_R_REMOTE_CRIT);
+		if (val < 0)
+			return val;
+		data->temp8[REMOTE_CRIT] = val;
 
-	val = lm90_read_reg(client, LM90_REG_R_TCRIT_HYST);
-	if (val < 0)
-		return val;
-	data->temp_hyst = val;
+		val = lm90_read_reg(client, LM90_REG_R_TCRIT_HYST);
+		if (val < 0)
+			return val;
+		data->temp_hyst = val;
+	}
 
 	val = lm90_read_reg(client, LM90_REG_R_REMOTE_LOWH);
 	if (val < 0)
@@ -809,7 +821,7 @@ static int lm90_update_device(struct device *dev)
 		val = lm90_read_reg(client, LM90_REG_R_STATUS);
 		if (val < 0)
 			return val;
-		data->alarms = val;	/* lower 8 bit of alarms */
+		data->alarms = val & ~LM90_STATUS_BUSY;
 
 		if (data->kind == max6696) {
 			val = lm90_select_remote_channel(data, 1);
@@ -1160,8 +1172,8 @@ static int lm90_set_temphyst(struct lm90_data *data, long val)
 	else
 		temp = temp_from_s8(data->temp8[LOCAL_CRIT]);
 
-	/* prevent integer underflow */
-	val = max(val, -128000l);
+	/* prevent integer overflow/underflow */
+	val = clamp_val(val, -128000l, 255000l);
 
 	data->temp_hyst = hyst_to_reg(temp - val);
 	err = i2c_smbus_write_byte_data(client, LM90_REG_W_TCRIT_HYST,
@@ -1192,6 +1204,7 @@ static const u8 lm90_temp_emerg_index[3] = {
 static const u8 lm90_min_alarm_bits[3] = { 5, 3, 11 };
 static const u8 lm90_max_alarm_bits[3] = { 6, 4, 12 };
 static const u8 lm90_crit_alarm_bits[3] = { 0, 1, 9 };
+static const u8 lm90_crit_alarm_bits_swapped[3] = { 1, 0, 9 };
 static const u8 lm90_emergency_alarm_bits[3] = { 15, 13, 14 };
 static const u8 lm90_fault_bits[3] = { 0, 2, 10 };
 
@@ -1217,7 +1230,10 @@ static int lm90_temp_read(struct device *dev, u32 attr, int channel, long *val)
 		*val = (data->alarms >> lm90_max_alarm_bits[channel]) & 1;
 		break;
 	case hwmon_temp_crit_alarm:
-		*val = (data->alarms >> lm90_crit_alarm_bits[channel]) & 1;
+		if (data->flags & LM90_HAVE_CRIT_ALRM_SWP)
+			*val = (data->alarms >> lm90_crit_alarm_bits_swapped[channel]) & 1;
+		else
+			*val = (data->alarms >> lm90_crit_alarm_bits[channel]) & 1;
 		break;
 	case hwmon_temp_emergency_alarm:
 		*val = (data->alarms >> lm90_emergency_alarm_bits[channel]) & 1;
@@ -1465,12 +1481,11 @@ static int lm90_detect(struct i2c_client *client,
 	if (man_id < 0 || chip_id < 0 || config1 < 0 || convrate < 0)
 		return -ENODEV;
 
-	if (man_id == 0x01 || man_id == 0x5C || man_id == 0x41) {
+	if (man_id == 0x01 || man_id == 0x5C || man_id == 0xA1) {
 		config2 = i2c_smbus_read_byte_data(client, LM90_REG_R_CONFIG2);
 		if (config2 < 0)
 			return -ENODEV;
-	} else
-		config2 = 0;		/* Make compiler happy */
+	}
 
 	if ((address == 0x4C || address == 0x4D)
 	 && man_id == 0x01) { /* National Semiconductor */
@@ -1903,11 +1918,14 @@ static int lm90_probe(struct i2c_client *client)
 	info->config = data->channel_config;
 
 	data->channel_config[0] = HWMON_T_INPUT | HWMON_T_MIN | HWMON_T_MAX |
-		HWMON_T_CRIT | HWMON_T_CRIT_HYST | HWMON_T_MIN_ALARM |
-		HWMON_T_MAX_ALARM | HWMON_T_CRIT_ALARM;
+		HWMON_T_MIN_ALARM | HWMON_T_MAX_ALARM;
 	data->channel_config[1] = HWMON_T_INPUT | HWMON_T_MIN | HWMON_T_MAX |
-		HWMON_T_CRIT | HWMON_T_CRIT_HYST | HWMON_T_MIN_ALARM |
-		HWMON_T_MAX_ALARM | HWMON_T_CRIT_ALARM | HWMON_T_FAULT;
+		HWMON_T_MIN_ALARM | HWMON_T_MAX_ALARM | HWMON_T_FAULT;
+
+	if (data->flags & LM90_HAVE_CRIT) {
+		data->channel_config[0] |= HWMON_T_CRIT | HWMON_T_CRIT_ALARM | HWMON_T_CRIT_HYST;
+		data->channel_config[1] |= HWMON_T_CRIT | HWMON_T_CRIT_ALARM | HWMON_T_CRIT_HYST;
+	}
 
 	if (data->flags & LM90_HAVE_OFFSET)
 		data->channel_config[1] |= HWMON_T_OFFSET;
diff --git a/drivers/hwmon/nct6775.c b/drivers/hwmon/nct6775.c
index 93dca471972e..57ce8633a725 100644
--- a/drivers/hwmon/nct6775.c
+++ b/drivers/hwmon/nct6775.c
@@ -1527,7 +1527,7 @@ static u16 nct6775_wmi_read_value(struct nct6775_data *data, u16 reg)
 
 	nct6775_wmi_set_bank(data, reg);
 
-	err = nct6775_asuswmi_read(data->bank, reg, &tmp);
+	err = nct6775_asuswmi_read(data->bank, reg & 0xff, &tmp);
 	if (err)
 		return 0;
 
diff --git a/drivers/hwmon/pwm-fan.c b/drivers/hwmon/pwm-fan.c
index 17518b4cab1b..f12b9a28a232 100644
--- a/drivers/hwmon/pwm-fan.c
+++ b/drivers/hwmon/pwm-fan.c
@@ -336,8 +336,6 @@ static int pwm_fan_probe(struct platform_device *pdev)
 			return ret;
 	}
 
-	ctx->pwm_value = MAX_PWM;
-
 	pwm_init_state(ctx->pwm, &ctx->pwm_state);
 
 	/*
diff --git a/drivers/hwmon/sht4x.c b/drivers/hwmon/sht4x.c
index 09c2a0b06444..3415d7a0e0fc 100644
--- a/drivers/hwmon/sht4x.c
+++ b/drivers/hwmon/sht4x.c
@@ -23,7 +23,7 @@
 /*
  * I2C command delays (in microseconds)
  */
-#define SHT4X_MEAS_DELAY	1000
+#define SHT4X_MEAS_DELAY_HPM	8200	/* see t_MEAS,h in datasheet */
 #define SHT4X_DELAY_EXTRA	10000
 
 /*
@@ -90,7 +90,7 @@ static int sht4x_read_values(struct sht4x_data *data)
 	if (ret < 0)
 		goto unlock;
 
-	usleep_range(SHT4X_MEAS_DELAY, SHT4X_MEAS_DELAY + SHT4X_DELAY_EXTRA);
+	usleep_range(SHT4X_MEAS_DELAY_HPM, SHT4X_MEAS_DELAY_HPM + SHT4X_DELAY_EXTRA);
 
 	ret = i2c_master_recv(client, raw_data, SHT4X_RESPONSE_LENGTH);
 	if (ret != SHT4X_RESPONSE_LENGTH) {
diff --git a/drivers/i2c/busses/i2c-cbus-gpio.c b/drivers/i2c/busses/i2c-cbus-gpio.c
index 72df563477b1..f8639a4457d2 100644
--- a/drivers/i2c/busses/i2c-cbus-gpio.c
+++ b/drivers/i2c/busses/i2c-cbus-gpio.c
@@ -195,8 +195,9 @@ static u32 cbus_i2c_func(struct i2c_adapter *adapter)
 }
 
 static const struct i2c_algorithm cbus_i2c_algo = {
-	.smbus_xfer	= cbus_i2c_smbus_xfer,
-	.functionality	= cbus_i2c_func,
+	.smbus_xfer		= cbus_i2c_smbus_xfer,
+	.smbus_xfer_atomic	= cbus_i2c_smbus_xfer,
+	.functionality		= cbus_i2c_func,
 };
 
 static int cbus_i2c_remove(struct platform_device *pdev)
diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c
index 05187457f88a..41446f9cc52d 100644
--- a/drivers/i2c/busses/i2c-i801.c
+++ b/drivers/i2c/busses/i2c-i801.c
@@ -191,6 +191,7 @@
 #define SMBSLVSTS_HST_NTFY_STS	BIT(0)
 
 /* Host Notify Command register bits */
+#define SMBSLVCMD_SMBALERT_DISABLE	BIT(2)
 #define SMBSLVCMD_HST_NTFY_INTREN	BIT(0)
 
 #define STATUS_ERROR_FLAGS	(SMBHSTSTS_FAILED | SMBHSTSTS_BUS_ERR | \
@@ -259,6 +260,7 @@ struct i801_priv {
 	struct i2c_adapter adapter;
 	unsigned long smba;
 	unsigned char original_hstcfg;
+	unsigned char original_hstcnt;
 	unsigned char original_slvcmd;
 	struct pci_dev *pci_dev;
 	unsigned int features;
@@ -641,12 +643,20 @@ static irqreturn_t i801_isr(int irq, void *dev_id)
 		i801_isr_byte_done(priv);
 
 	/*
-	 * Clear irq sources and report transaction result.
+	 * Clear remaining IRQ sources: Completion of last command, errors
+	 * and the SMB_ALERT signal. SMB_ALERT status is set after signal
+	 * assertion independently of the interrupt generation being blocked
+	 * or not so clear it always when the status is set.
+	 */
+	status &= SMBHSTSTS_INTR | STATUS_ERROR_FLAGS | SMBHSTSTS_SMBALERT_STS;
+	if (status)
+		outb_p(status, SMBHSTSTS(priv));
+	status &= ~SMBHSTSTS_SMBALERT_STS; /* SMB_ALERT not reported */
+	/*
+	 * Report transaction result.
 	 * ->status must be cleared before the next transaction is started.
 	 */
-	status &= SMBHSTSTS_INTR | STATUS_ERROR_FLAGS;
 	if (status) {
-		outb_p(status, SMBHSTSTS(priv));
 		priv->status = status;
 		complete(&priv->done);
 	}
@@ -974,9 +984,13 @@ static void i801_enable_host_notify(struct i2c_adapter *adapter)
 	if (!(priv->features & FEATURE_HOST_NOTIFY))
 		return;
 
-	if (!(SMBSLVCMD_HST_NTFY_INTREN & priv->original_slvcmd))
-		outb_p(SMBSLVCMD_HST_NTFY_INTREN | priv->original_slvcmd,
-		       SMBSLVCMD(priv));
+	/*
+	 * Enable host notify interrupt and block the generation of interrupt
+	 * from the SMB_ALERT signal because the driver does not support
+	 * SMBus Alert.
+	 */
+	outb_p(SMBSLVCMD_HST_NTFY_INTREN | SMBSLVCMD_SMBALERT_DISABLE |
+	       priv->original_slvcmd, SMBSLVCMD(priv));
 
 	/* clear Host Notify bit to allow a new notification */
 	outb_p(SMBSLVSTS_HST_NTFY_STS, SMBSLVSTS(priv));
@@ -1805,7 +1819,8 @@ static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id)
 		outb_p(inb_p(SMBAUXCTL(priv)) &
 		       ~(SMBAUXCTL_CRC | SMBAUXCTL_E32B), SMBAUXCTL(priv));
 
-	/* Remember original Host Notify setting */
+	/* Remember original Interrupt and Host Notify settings */
+	priv->original_hstcnt = inb_p(SMBHSTCNT(priv)) & ~SMBHSTCNT_KILL;
 	if (priv->features & FEATURE_HOST_NOTIFY)
 		priv->original_slvcmd = inb_p(SMBSLVCMD(priv));
 
@@ -1869,6 +1884,7 @@ static void i801_remove(struct pci_dev *dev)
 {
 	struct i801_priv *priv = pci_get_drvdata(dev);
 
+	outb_p(priv->original_hstcnt, SMBHSTCNT(priv));
 	i801_disable_host_notify(priv);
 	i801_del_mux(priv);
 	i2c_del_adapter(&priv->adapter);
@@ -1892,6 +1908,7 @@ static void i801_shutdown(struct pci_dev *dev)
 	struct i801_priv *priv = pci_get_drvdata(dev);
 
 	/* Restore config registers to avoid hard hang on some systems */
+	outb_p(priv->original_hstcnt, SMBHSTCNT(priv));
 	i801_disable_host_notify(priv);
 	pci_write_config_byte(dev, SMBHSTCFG, priv->original_hstcfg);
 }
@@ -1901,6 +1918,7 @@ static int i801_suspend(struct device *dev)
 {
 	struct i801_priv *priv = dev_get_drvdata(dev);
 
+	outb_p(priv->original_hstcnt, SMBHSTCNT(priv));
 	pci_write_config_byte(priv->pci_dev, SMBHSTCFG, priv->original_hstcfg);
 	return 0;
 }
diff --git a/drivers/i2c/busses/i2c-mpc.c b/drivers/i2c/busses/i2c-mpc.c
index a6ea1eb1394e..53b8da6dbb23 100644
--- a/drivers/i2c/busses/i2c-mpc.c
+++ b/drivers/i2c/busses/i2c-mpc.c
@@ -636,7 +636,7 @@ static irqreturn_t mpc_i2c_isr(int irq, void *dev_id)
 	status = readb(i2c->base + MPC_I2C_SR);
 	if (status & CSR_MIF) {
 		/* Wait up to 100us for transfer to properly complete */
-		readb_poll_timeout(i2c->base + MPC_I2C_SR, status, !(status & CSR_MCF), 0, 100);
+		readb_poll_timeout_atomic(i2c->base + MPC_I2C_SR, status, status & CSR_MCF, 0, 100);
 		writeb(0, i2c->base + MPC_I2C_SR);
 		mpc_i2c_do_intr(i2c, status);
 		return IRQ_HANDLED;
diff --git a/drivers/i2c/busses/i2c-rk3x.c b/drivers/i2c/busses/i2c-rk3x.c
index 819ab4ee517e..02ddb237f69a 100644
--- a/drivers/i2c/busses/i2c-rk3x.c
+++ b/drivers/i2c/busses/i2c-rk3x.c
@@ -423,8 +423,8 @@ static void rk3x_i2c_handle_read(struct rk3x_i2c *i2c, unsigned int ipd)
 	if (!(ipd & REG_INT_MBRF))
 		return;
 
-	/* ack interrupt */
-	i2c_writel(i2c, REG_INT_MBRF, REG_IPD);
+	/* ack interrupt (read also produces a spurious START flag, clear it too) */
+	i2c_writel(i2c, REG_INT_MBRF | REG_INT_START, REG_IPD);
 
 	/* Can only handle a maximum of 32 bytes at a time */
 	if (len > 32)
diff --git a/drivers/i2c/busses/i2c-stm32f7.c b/drivers/i2c/busses/i2c-stm32f7.c
index b9b19a2a2ffa..66145d2b9b55 100644
--- a/drivers/i2c/busses/i2c-stm32f7.c
+++ b/drivers/i2c/busses/i2c-stm32f7.c
@@ -1493,6 +1493,7 @@ static irqreturn_t stm32f7_i2c_isr_event(int irq, void *data)
 {
 	struct stm32f7_i2c_dev *i2c_dev = data;
 	struct stm32f7_i2c_msg *f7_msg = &i2c_dev->f7_msg;
+	struct stm32_i2c_dma *dma = i2c_dev->dma;
 	void __iomem *base = i2c_dev->base;
 	u32 status, mask;
 	int ret = IRQ_HANDLED;
@@ -1518,6 +1519,10 @@ static irqreturn_t stm32f7_i2c_isr_event(int irq, void *data)
 		dev_dbg(i2c_dev->dev, "<%s>: Receive NACK (addr %x)\n",
 			__func__, f7_msg->addr);
 		writel_relaxed(STM32F7_I2C_ICR_NACKCF, base + STM32F7_I2C_ICR);
+		if (i2c_dev->use_dma) {
+			stm32f7_i2c_disable_dma_req(i2c_dev);
+			dmaengine_terminate_async(dma->chan_using);
+		}
 		f7_msg->result = -ENXIO;
 	}
 
@@ -1533,7 +1538,7 @@ static irqreturn_t stm32f7_i2c_isr_event(int irq, void *data)
 		/* Clear STOP flag */
 		writel_relaxed(STM32F7_I2C_ICR_STOPCF, base + STM32F7_I2C_ICR);
 
-		if (i2c_dev->use_dma) {
+		if (i2c_dev->use_dma && !f7_msg->result) {
 			ret = IRQ_WAKE_THREAD;
 		} else {
 			i2c_dev->master_mode = false;
@@ -1546,7 +1551,7 @@ static irqreturn_t stm32f7_i2c_isr_event(int irq, void *data)
 		if (f7_msg->stop) {
 			mask = STM32F7_I2C_CR2_STOP;
 			stm32f7_i2c_set_bits(base + STM32F7_I2C_CR2, mask);
-		} else if (i2c_dev->use_dma) {
+		} else if (i2c_dev->use_dma && !f7_msg->result) {
 			ret = IRQ_WAKE_THREAD;
 		} else if (f7_msg->smbus) {
 			stm32f7_i2c_smbus_rep_start(i2c_dev);
@@ -1583,7 +1588,7 @@ static irqreturn_t stm32f7_i2c_isr_event_thread(int irq, void *data)
 	if (!ret) {
 		dev_dbg(i2c_dev->dev, "<%s>: Timed out\n", __func__);
 		stm32f7_i2c_disable_dma_req(i2c_dev);
-		dmaengine_terminate_all(dma->chan_using);
+		dmaengine_terminate_async(dma->chan_using);
 		f7_msg->result = -ETIMEDOUT;
 	}
 
@@ -1660,7 +1665,7 @@ static irqreturn_t stm32f7_i2c_isr_error(int irq, void *data)
 	/* Disable dma */
 	if (i2c_dev->use_dma) {
 		stm32f7_i2c_disable_dma_req(i2c_dev);
-		dmaengine_terminate_all(dma->chan_using);
+		dmaengine_terminate_async(dma->chan_using);
 	}
 
 	i2c_dev->master_mode = false;
@@ -1696,12 +1701,26 @@ static int stm32f7_i2c_xfer(struct i2c_adapter *i2c_adap,
 	time_left = wait_for_completion_timeout(&i2c_dev->complete,
 						i2c_dev->adap.timeout);
 	ret = f7_msg->result;
+	if (ret) {
+		if (i2c_dev->use_dma)
+			dmaengine_synchronize(dma->chan_using);
+
+		/*
+		 * It is possible that some unsent data have already been
+		 * written into TXDR. To avoid sending old data in a
+		 * further transfer, flush TXDR in case of any error
+		 */
+		writel_relaxed(STM32F7_I2C_ISR_TXE,
+			       i2c_dev->base + STM32F7_I2C_ISR);
+		goto pm_free;
+	}
 
 	if (!time_left) {
 		dev_dbg(i2c_dev->dev, "Access to slave 0x%x timed out\n",
 			i2c_dev->msg->addr);
 		if (i2c_dev->use_dma)
-			dmaengine_terminate_all(dma->chan_using);
+			dmaengine_terminate_sync(dma->chan_using);
+		stm32f7_i2c_wait_free_bus(i2c_dev);
 		ret = -ETIMEDOUT;
 	}
 
@@ -1744,13 +1763,25 @@ static int stm32f7_i2c_smbus_xfer(struct i2c_adapter *adapter, u16 addr,
 	timeout = wait_for_completion_timeout(&i2c_dev->complete,
 					      i2c_dev->adap.timeout);
 	ret = f7_msg->result;
-	if (ret)
+	if (ret) {
+		if (i2c_dev->use_dma)
+			dmaengine_synchronize(dma->chan_using);
+
+		/*
+		 * It is possible that some unsent data have already been
+		 * written into TXDR. To avoid sending old data in a
+		 * further transfer, flush TXDR in case of any error
+		 */
+		writel_relaxed(STM32F7_I2C_ISR_TXE,
+			       i2c_dev->base + STM32F7_I2C_ISR);
 		goto pm_free;
+	}
 
 	if (!timeout) {
 		dev_dbg(dev, "Access to slave 0x%x timed out\n", f7_msg->addr);
 		if (i2c_dev->use_dma)
-			dmaengine_terminate_all(dma->chan_using);
+			dmaengine_terminate_sync(dma->chan_using);
+		stm32f7_i2c_wait_free_bus(i2c_dev);
 		ret = -ETIMEDOUT;
 		goto pm_free;
 	}
diff --git a/drivers/i2c/busses/i2c-virtio.c b/drivers/i2c/busses/i2c-virtio.c
index 1ed4daa918a0..41eb0dcc3204 100644
--- a/drivers/i2c/busses/i2c-virtio.c
+++ b/drivers/i2c/busses/i2c-virtio.c
@@ -22,24 +22,24 @@
 /**
  * struct virtio_i2c - virtio I2C data
  * @vdev: virtio device for this controller
- * @completion: completion of virtio I2C message
  * @adap: I2C adapter for this controller
  * @vq: the virtio virtqueue for communication
  */
 struct virtio_i2c {
 	struct virtio_device *vdev;
-	struct completion completion;
 	struct i2c_adapter adap;
 	struct virtqueue *vq;
 };
 
 /**
  * struct virtio_i2c_req - the virtio I2C request structure
+ * @completion: completion of virtio I2C message
  * @out_hdr: the OUT header of the virtio I2C message
  * @buf: the buffer into which data is read, or from which it's written
  * @in_hdr: the IN header of the virtio I2C message
  */
 struct virtio_i2c_req {
+	struct completion completion;
 	struct virtio_i2c_out_hdr out_hdr	____cacheline_aligned;
 	uint8_t *buf				____cacheline_aligned;
 	struct virtio_i2c_in_hdr in_hdr		____cacheline_aligned;
@@ -47,9 +47,11 @@ struct virtio_i2c_req {
 
 static void virtio_i2c_msg_done(struct virtqueue *vq)
 {
-	struct virtio_i2c *vi = vq->vdev->priv;
+	struct virtio_i2c_req *req;
+	unsigned int len;
 
-	complete(&vi->completion);
+	while ((req = virtqueue_get_buf(vq, &len)))
+		complete(&req->completion);
 }
 
 static int virtio_i2c_prepare_reqs(struct virtqueue *vq,
@@ -62,6 +64,8 @@ static int virtio_i2c_prepare_reqs(struct virtqueue *vq,
 	for (i = 0; i < num; i++) {
 		int outcnt = 0, incnt = 0;
 
+		init_completion(&reqs[i].completion);
+
 		/*
 		 * Only 7-bit mode supported for this moment. For the address
 		 * format, Please check the Virtio I2C Specification.
@@ -104,24 +108,17 @@ static int virtio_i2c_prepare_reqs(struct virtqueue *vq,
 
 static int virtio_i2c_complete_reqs(struct virtqueue *vq,
 				    struct virtio_i2c_req *reqs,
-				    struct i2c_msg *msgs, int num,
-				    bool timedout)
+				    struct i2c_msg *msgs, int num)
 {
-	struct virtio_i2c_req *req;
-	bool failed = timedout;
-	unsigned int len;
+	bool failed = false;
 	int i, j = 0;
 
 	for (i = 0; i < num; i++) {
-		/* Detach the ith request from the vq */
-		req = virtqueue_get_buf(vq, &len);
+		struct virtio_i2c_req *req = &reqs[i];
 
-		/*
-		 * Condition req == &reqs[i] should always meet since we have
-		 * total num requests in the vq. reqs[i] can never be NULL here.
-		 */
-		if (!failed && (WARN_ON(req != &reqs[i]) ||
-				req->in_hdr.status != VIRTIO_I2C_MSG_OK))
+		wait_for_completion(&req->completion);
+
+		if (!failed && req->in_hdr.status != VIRTIO_I2C_MSG_OK)
 			failed = true;
 
 		i2c_put_dma_safe_msg_buf(reqs[i].buf, &msgs[i], !failed);
@@ -130,7 +127,7 @@ static int virtio_i2c_complete_reqs(struct virtqueue *vq,
 			j++;
 	}
 
-	return timedout ? -ETIMEDOUT : j;
+	return j;
 }
 
 static int virtio_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs,
@@ -139,7 +136,6 @@ static int virtio_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs,
 	struct virtio_i2c *vi = i2c_get_adapdata(adap);
 	struct virtqueue *vq = vi->vq;
 	struct virtio_i2c_req *reqs;
-	unsigned long time_left;
 	int count;
 
 	reqs = kcalloc(num, sizeof(*reqs), GFP_KERNEL);
@@ -158,15 +154,9 @@ static int virtio_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs,
 	 * remote here to clear the virtqueue, so we can try another set of
 	 * messages later on.
 	 */
-
-	reinit_completion(&vi->completion);
 	virtqueue_kick(vq);
 
-	time_left = wait_for_completion_timeout(&vi->completion, adap->timeout);
-	if (!time_left)
-		dev_err(&adap->dev, "virtio i2c backend timeout.\n");
-
-	count = virtio_i2c_complete_reqs(vq, reqs, msgs, count, !time_left);
+	count = virtio_i2c_complete_reqs(vq, reqs, msgs, count);
 
 err_free:
 	kfree(reqs);
@@ -214,8 +204,6 @@ static int virtio_i2c_probe(struct virtio_device *vdev)
 	vdev->priv = vi;
 	vi->vdev = vdev;
 
-	init_completion(&vi->completion);
-
 	ret = virtio_i2c_setup_vqs(vi);
 	if (ret)
 		return ret;
diff --git a/drivers/iio/accel/kxcjk-1013.c b/drivers/iio/accel/kxcjk-1013.c
index a51fdd3c9b5b..24c9387c2968 100644
--- a/drivers/iio/accel/kxcjk-1013.c
+++ b/drivers/iio/accel/kxcjk-1013.c
@@ -1595,8 +1595,7 @@ static int kxcjk1013_probe(struct i2c_client *client,
 	return 0;
 
 err_buffer_cleanup:
-	if (data->dready_trig)
-		iio_triggered_buffer_cleanup(indio_dev);
+	iio_triggered_buffer_cleanup(indio_dev);
 err_trigger_unregister:
 	if (data->dready_trig)
 		iio_trigger_unregister(data->dready_trig);
@@ -1618,8 +1617,8 @@ static int kxcjk1013_remove(struct i2c_client *client)
 	pm_runtime_disable(&client->dev);
 	pm_runtime_set_suspended(&client->dev);
 
+	iio_triggered_buffer_cleanup(indio_dev);
 	if (data->dready_trig) {
-		iio_triggered_buffer_cleanup(indio_dev);
 		iio_trigger_unregister(data->dready_trig);
 		iio_trigger_unregister(data->motion_trig);
 	}
diff --git a/drivers/iio/accel/kxsd9.c b/drivers/iio/accel/kxsd9.c
index 2faf85ca996e..552eba5e8b4f 100644
--- a/drivers/iio/accel/kxsd9.c
+++ b/drivers/iio/accel/kxsd9.c
@@ -224,14 +224,14 @@ static irqreturn_t kxsd9_trigger_handler(int irq, void *p)
 			       hw_values.chan,
 			       sizeof(hw_values.chan));
 	if (ret) {
-		dev_err(st->dev,
-			"error reading data\n");
-		return ret;
+		dev_err(st->dev, "error reading data: %d\n", ret);
+		goto out;
 	}
 
 	iio_push_to_buffers_with_timestamp(indio_dev,
 					   &hw_values,
 					   iio_get_time_ns(indio_dev));
+out:
 	iio_trigger_notify_done(indio_dev->trig);
 
 	return IRQ_HANDLED;
diff --git a/drivers/iio/accel/mma8452.c b/drivers/iio/accel/mma8452.c
index 715b8138fb71..09c7f10fefb6 100644
--- a/drivers/iio/accel/mma8452.c
+++ b/drivers/iio/accel/mma8452.c
@@ -1470,7 +1470,7 @@ static int mma8452_trigger_setup(struct iio_dev *indio_dev)
 	if (ret)
 		return ret;
 
-	indio_dev->trig = trig;
+	indio_dev->trig = iio_trigger_get(trig);
 
 	return 0;
 }
diff --git a/drivers/iio/adc/Kconfig b/drivers/iio/adc/Kconfig
index 8bf5b62a73f4..3363af15a43f 100644
--- a/drivers/iio/adc/Kconfig
+++ b/drivers/iio/adc/Kconfig
@@ -532,7 +532,7 @@ config IMX7D_ADC
 
 config IMX8QXP_ADC
 	tristate "NXP IMX8QXP ADC driver"
-	depends on ARCH_MXC_ARM64 || COMPILE_TEST
+	depends on ARCH_MXC || COMPILE_TEST
 	depends on HAS_IOMEM
 	help
 	  Say yes here to build support for IMX8QXP ADC.
diff --git a/drivers/iio/adc/ad7768-1.c b/drivers/iio/adc/ad7768-1.c
index 2c5c8a3672b2..aa42ba759fa1 100644
--- a/drivers/iio/adc/ad7768-1.c
+++ b/drivers/iio/adc/ad7768-1.c
@@ -480,8 +480,8 @@ static irqreturn_t ad7768_trigger_handler(int irq, void *p)
 	iio_push_to_buffers_with_timestamp(indio_dev, &st->data.scan,
 					   iio_get_time_ns(indio_dev));
 
-	iio_trigger_notify_done(indio_dev->trig);
 err_unlock:
+	iio_trigger_notify_done(indio_dev->trig);
 	mutex_unlock(&st->lock);
 
 	return IRQ_HANDLED;
diff --git a/drivers/iio/adc/at91-sama5d2_adc.c b/drivers/iio/adc/at91-sama5d2_adc.c
index 4c922ef634f8..92a57cf10fba 100644
--- a/drivers/iio/adc/at91-sama5d2_adc.c
+++ b/drivers/iio/adc/at91-sama5d2_adc.c
@@ -1586,7 +1586,8 @@ static int at91_adc_read_info_raw(struct iio_dev *indio_dev,
 		*val = st->conversion_value;
 		ret = at91_adc_adjust_val_osr(st, val);
 		if (chan->scan_type.sign == 's')
-			*val = sign_extend32(*val, 11);
+			*val = sign_extend32(*val,
+					     chan->scan_type.realbits - 1);
 		st->conversion_done = false;
 	}
 
diff --git a/drivers/iio/adc/axp20x_adc.c b/drivers/iio/adc/axp20x_adc.c
index 3e0c0233b431..df99f1365c39 100644
--- a/drivers/iio/adc/axp20x_adc.c
+++ b/drivers/iio/adc/axp20x_adc.c
@@ -251,19 +251,8 @@ static int axp22x_adc_raw(struct iio_dev *indio_dev,
 			  struct iio_chan_spec const *chan, int *val)
 {
 	struct axp20x_adc_iio *info = iio_priv(indio_dev);
-	int size;
 
-	/*
-	 * N.B.: Unlike the Chinese datasheets tell, the charging current is
-	 * stored on 12 bits, not 13 bits. Only discharging current is on 13
-	 * bits.
-	 */
-	if (chan->type == IIO_CURRENT && chan->channel == AXP22X_BATT_DISCHRG_I)
-		size = 13;
-	else
-		size = 12;
-
-	*val = axp20x_read_variable_width(info->regmap, chan->address, size);
+	*val = axp20x_read_variable_width(info->regmap, chan->address, 12);
 	if (*val < 0)
 		return *val;
 
@@ -386,9 +375,8 @@ static int axp22x_adc_scale(struct iio_chan_spec const *chan, int *val,
 		return IIO_VAL_INT_PLUS_MICRO;
 
 	case IIO_CURRENT:
-		*val = 0;
-		*val2 = 500000;
-		return IIO_VAL_INT_PLUS_MICRO;
+		*val = 1;
+		return IIO_VAL_INT;
 
 	case IIO_TEMP:
 		*val = 100;
diff --git a/drivers/iio/adc/dln2-adc.c b/drivers/iio/adc/dln2-adc.c
index 16407664182c..97d162a3cba4 100644
--- a/drivers/iio/adc/dln2-adc.c
+++ b/drivers/iio/adc/dln2-adc.c
@@ -248,7 +248,6 @@ static int dln2_adc_set_chan_period(struct dln2_adc *dln2,
 static int dln2_adc_read(struct dln2_adc *dln2, unsigned int channel)
 {
 	int ret, i;
-	struct iio_dev *indio_dev = platform_get_drvdata(dln2->pdev);
 	u16 conflict;
 	__le16 value;
 	int olen = sizeof(value);
@@ -257,13 +256,9 @@ static int dln2_adc_read(struct dln2_adc *dln2, unsigned int channel)
 		.chan = channel,
 	};
 
-	ret = iio_device_claim_direct_mode(indio_dev);
-	if (ret < 0)
-		return ret;
-
 	ret = dln2_adc_set_chan_enabled(dln2, channel, true);
 	if (ret < 0)
-		goto release_direct;
+		return ret;
 
 	ret = dln2_adc_set_port_enabled(dln2, true, &conflict);
 	if (ret < 0) {
@@ -300,8 +295,6 @@ disable_port:
 	dln2_adc_set_port_enabled(dln2, false, NULL);
 disable_chan:
 	dln2_adc_set_chan_enabled(dln2, channel, false);
-release_direct:
-	iio_device_release_direct_mode(indio_dev);
 
 	return ret;
 }
@@ -337,10 +330,16 @@ static int dln2_adc_read_raw(struct iio_dev *indio_dev,
 
 	switch (mask) {
 	case IIO_CHAN_INFO_RAW:
+		ret = iio_device_claim_direct_mode(indio_dev);
+		if (ret < 0)
+			return ret;
+
 		mutex_lock(&dln2->mutex);
 		ret = dln2_adc_read(dln2, chan->channel);
 		mutex_unlock(&dln2->mutex);
 
+		iio_device_release_direct_mode(indio_dev);
+
 		if (ret < 0)
 			return ret;
 
@@ -656,7 +655,11 @@ static int dln2_adc_probe(struct platform_device *pdev)
 		return -ENOMEM;
 	}
 	iio_trigger_set_drvdata(dln2->trig, dln2);
-	devm_iio_trigger_register(dev, dln2->trig);
+	ret = devm_iio_trigger_register(dev, dln2->trig);
+	if (ret) {
+		dev_err(dev, "failed to register trigger: %d\n", ret);
+		return ret;
+	}
 	iio_trigger_set_immutable(indio_dev, dln2->trig);
 
 	ret = devm_iio_triggered_buffer_setup(dev, indio_dev, NULL,
diff --git a/drivers/iio/adc/stm32-adc.c b/drivers/iio/adc/stm32-adc.c
index 6245434f8377..8cd258cb2682 100644
--- a/drivers/iio/adc/stm32-adc.c
+++ b/drivers/iio/adc/stm32-adc.c
@@ -1117,6 +1117,7 @@ static void stm32h7_adc_unprepare(struct iio_dev *indio_dev)
 {
 	struct stm32_adc *adc = iio_priv(indio_dev);
 
+	stm32_adc_writel(adc, STM32H7_ADC_PCSEL, 0);
 	stm32h7_adc_disable(indio_dev);
 	stm32_adc_int_ch_disable(adc);
 	stm32h7_adc_enter_pwr_down(adc);
@@ -1986,7 +1987,7 @@ static int stm32_adc_populate_int_ch(struct iio_dev *indio_dev, const char *ch_n
 			/* Get calibration data for vrefint channel */
 			ret = nvmem_cell_read_u16(&indio_dev->dev, "vrefint", &vrefint);
 			if (ret && ret != -ENOENT) {
-				return dev_err_probe(&indio_dev->dev, ret,
+				return dev_err_probe(indio_dev->dev.parent, ret,
 						     "nvmem access error\n");
 			}
 			if (ret == -ENOENT)
diff --git a/drivers/iio/gyro/adxrs290.c b/drivers/iio/gyro/adxrs290.c
index 3e0734ddafe3..600e9725da78 100644
--- a/drivers/iio/gyro/adxrs290.c
+++ b/drivers/iio/gyro/adxrs290.c
@@ -7,6 +7,7 @@
  */
 
 #include <linux/bitfield.h>
+#include <linux/bitops.h>
 #include <linux/delay.h>
 #include <linux/device.h>
 #include <linux/kernel.h>
@@ -124,7 +125,7 @@ static int adxrs290_get_rate_data(struct iio_dev *indio_dev, const u8 cmd, int *
 		goto err_unlock;
 	}
 
-	*val = temp;
+	*val = sign_extend32(temp, 15);
 
 err_unlock:
 	mutex_unlock(&st->lock);
@@ -146,7 +147,7 @@ static int adxrs290_get_temp_data(struct iio_dev *indio_dev, int *val)
 	}
 
 	/* extract lower 12 bits temperature reading */
-	*val = temp & 0x0FFF;
+	*val = sign_extend32(temp, 11);
 
 err_unlock:
 	mutex_unlock(&st->lock);
diff --git a/drivers/iio/gyro/itg3200_buffer.c b/drivers/iio/gyro/itg3200_buffer.c
index 04dd6a7969ea..4cfa0d439560 100644
--- a/drivers/iio/gyro/itg3200_buffer.c
+++ b/drivers/iio/gyro/itg3200_buffer.c
@@ -61,9 +61,9 @@ static irqreturn_t itg3200_trigger_handler(int irq, void *p)
 
 	iio_push_to_buffers_with_timestamp(indio_dev, &scan, pf->timestamp);
 
+error_ret:
 	iio_trigger_notify_done(indio_dev->trig);
 
-error_ret:
 	return IRQ_HANDLED;
 }
 
diff --git a/drivers/iio/industrialio-trigger.c b/drivers/iio/industrialio-trigger.c
index b23caa2f2aa1..93990ff1dfe3 100644
--- a/drivers/iio/industrialio-trigger.c
+++ b/drivers/iio/industrialio-trigger.c
@@ -556,7 +556,6 @@ struct iio_trigger *viio_trigger_alloc(struct device *parent,
 		irq_modify_status(trig->subirq_base + i,
 				  IRQ_NOREQUEST | IRQ_NOAUTOEN, IRQ_NOPROBE);
 	}
-	get_device(&trig->dev);
 
 	return trig;
 
diff --git a/drivers/iio/light/ltr501.c b/drivers/iio/light/ltr501.c
index 7e51aaac0bf8..b2983b1a9ed1 100644
--- a/drivers/iio/light/ltr501.c
+++ b/drivers/iio/light/ltr501.c
@@ -1275,7 +1275,7 @@ static irqreturn_t ltr501_trigger_handler(int irq, void *p)
 		ret = regmap_bulk_read(data->regmap, LTR501_ALS_DATA1,
 				       als_buf, sizeof(als_buf));
 		if (ret < 0)
-			return ret;
+			goto done;
 		if (test_bit(0, indio_dev->active_scan_mask))
 			scan.channels[j++] = le16_to_cpu(als_buf[1]);
 		if (test_bit(1, indio_dev->active_scan_mask))
diff --git a/drivers/iio/light/stk3310.c b/drivers/iio/light/stk3310.c
index 07e91846307c..fc63856ed54d 100644
--- a/drivers/iio/light/stk3310.c
+++ b/drivers/iio/light/stk3310.c
@@ -546,9 +546,8 @@ static irqreturn_t stk3310_irq_event_handler(int irq, void *private)
 	mutex_lock(&data->lock);
 	ret = regmap_field_read(data->reg_flag_nf, &dir);
 	if (ret < 0) {
-		dev_err(&data->client->dev, "register read failed\n");
-		mutex_unlock(&data->lock);
-		return ret;
+		dev_err(&data->client->dev, "register read failed: %d\n", ret);
+		goto out;
 	}
 	event = IIO_UNMOD_EVENT_CODE(IIO_PROXIMITY, 1,
 				     IIO_EV_TYPE_THRESH,
@@ -560,6 +559,7 @@ static irqreturn_t stk3310_irq_event_handler(int irq, void *private)
 	ret = regmap_field_write(data->reg_flag_psint, 0);
 	if (ret < 0)
 		dev_err(&data->client->dev, "failed to reset interrupts\n");
+out:
 	mutex_unlock(&data->lock);
 
 	return IRQ_HANDLED;
diff --git a/drivers/iio/trigger/stm32-timer-trigger.c b/drivers/iio/trigger/stm32-timer-trigger.c
index 33083877cd19..4353b749ecef 100644
--- a/drivers/iio/trigger/stm32-timer-trigger.c
+++ b/drivers/iio/trigger/stm32-timer-trigger.c
@@ -912,6 +912,6 @@ static struct platform_driver stm32_timer_trigger_driver = {
 };
 module_platform_driver(stm32_timer_trigger_driver);
 
-MODULE_ALIAS("platform: stm32-timer-trigger");
+MODULE_ALIAS("platform:stm32-timer-trigger");
 MODULE_DESCRIPTION("STMicroelectronics STM32 Timer Trigger driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c
index fedc0fa6ebf9..f5aacaf7fb8e 100644
--- a/drivers/infiniband/core/nldev.c
+++ b/drivers/infiniband/core/nldev.c
@@ -1906,7 +1906,8 @@ static int nldev_stat_set_mode_doit(struct sk_buff *msg,
 	int ret;
 
 	/* Currently only counter for QP is supported */
-	if (nla_get_u32(tb[RDMA_NLDEV_ATTR_STAT_RES]) != RDMA_NLDEV_ATTR_RES_QP)
+	if (!tb[RDMA_NLDEV_ATTR_STAT_RES] ||
+	    nla_get_u32(tb[RDMA_NLDEV_ATTR_STAT_RES]) != RDMA_NLDEV_ATTR_RES_QP)
 		return -EINVAL;
 
 	mode = nla_get_u32(tb[RDMA_NLDEV_ATTR_STAT_MODE]);
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index 692d5ff657df..c18634bec212 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -1232,6 +1232,9 @@ static struct ib_qp *create_qp(struct ib_device *dev, struct ib_pd *pd,
 	INIT_LIST_HEAD(&qp->rdma_mrs);
 	INIT_LIST_HEAD(&qp->sig_mrs);
 
+	qp->send_cq = attr->send_cq;
+	qp->recv_cq = attr->recv_cq;
+
 	rdma_restrack_new(&qp->res, RDMA_RESTRACK_QP);
 	WARN_ONCE(!udata && !caller, "Missing kernel QP owner");
 	rdma_restrack_set_name(&qp->res, udata ? NULL : caller);
diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c
index ec37f4fd8e96..f1245c94ae26 100644
--- a/drivers/infiniband/hw/hfi1/chip.c
+++ b/drivers/infiniband/hw/hfi1/chip.c
@@ -8415,6 +8415,8 @@ static void receive_interrupt_common(struct hfi1_ctxtdata *rcd)
  */
 static void __hfi1_rcd_eoi_intr(struct hfi1_ctxtdata *rcd)
 {
+	if (!rcd->rcvhdrq)
+		return;
 	clear_recv_intr(rcd);
 	if (check_packet_present(rcd))
 		force_recv_intr(rcd);
diff --git a/drivers/infiniband/hw/hfi1/driver.c b/drivers/infiniband/hw/hfi1/driver.c
index 61f341c3005c..e2c634af40e9 100644
--- a/drivers/infiniband/hw/hfi1/driver.c
+++ b/drivers/infiniband/hw/hfi1/driver.c
@@ -1012,6 +1012,8 @@ int handle_receive_interrupt(struct hfi1_ctxtdata *rcd, int thread)
 	struct hfi1_packet packet;
 	int skip_pkt = 0;
 
+	if (!rcd->rcvhdrq)
+		return RCV_PKT_OK;
 	/* Control context will always use the slow path interrupt handler */
 	needset = (rcd->ctxt == HFI1_CTRL_CTXT) ? 0 : 1;
 
diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c
index dbd1c31830b9..4436ed41547c 100644
--- a/drivers/infiniband/hw/hfi1/init.c
+++ b/drivers/infiniband/hw/hfi1/init.c
@@ -113,7 +113,6 @@ static int hfi1_create_kctxt(struct hfi1_devdata *dd,
 	rcd->fast_handler = get_dma_rtail_setting(rcd) ?
 				handle_receive_interrupt_dma_rtail :
 				handle_receive_interrupt_nodma_rtail;
-	rcd->slow_handler = handle_receive_interrupt;
 
 	hfi1_set_seq_cnt(rcd, 1);
 
@@ -334,6 +333,8 @@ int hfi1_create_ctxtdata(struct hfi1_pportdata *ppd, int numa,
 		rcd->numa_id = numa;
 		rcd->rcv_array_groups = dd->rcv_entries.ngroups;
 		rcd->rhf_rcv_function_map = normal_rhf_rcv_functions;
+		rcd->slow_handler = handle_receive_interrupt;
+		rcd->do_interrupt = rcd->slow_handler;
 		rcd->msix_intr = CCE_NUM_MSIX_VECTORS;
 
 		mutex_init(&rcd->exp_mutex);
@@ -874,18 +875,6 @@ int hfi1_init(struct hfi1_devdata *dd, int reinit)
 	if (ret)
 		goto done;
 
-	/* allocate dummy tail memory for all receive contexts */
-	dd->rcvhdrtail_dummy_kvaddr = dma_alloc_coherent(&dd->pcidev->dev,
-							 sizeof(u64),
-							 &dd->rcvhdrtail_dummy_dma,
-							 GFP_KERNEL);
-
-	if (!dd->rcvhdrtail_dummy_kvaddr) {
-		dd_dev_err(dd, "cannot allocate dummy tail memory\n");
-		ret = -ENOMEM;
-		goto done;
-	}
-
 	/* dd->rcd can be NULL if early initialization failed */
 	for (i = 0; dd->rcd && i < dd->first_dyn_alloc_ctxt; ++i) {
 		/*
@@ -898,8 +887,6 @@ int hfi1_init(struct hfi1_devdata *dd, int reinit)
 		if (!rcd)
 			continue;
 
-		rcd->do_interrupt = &handle_receive_interrupt;
-
 		lastfail = hfi1_create_rcvhdrq(dd, rcd);
 		if (!lastfail)
 			lastfail = hfi1_setup_eagerbufs(rcd);
@@ -1120,7 +1107,7 @@ void hfi1_free_ctxtdata(struct hfi1_devdata *dd, struct hfi1_ctxtdata *rcd)
 	rcd->egrbufs.rcvtids = NULL;
 
 	for (e = 0; e < rcd->egrbufs.alloced; e++) {
-		if (rcd->egrbufs.buffers[e].dma)
+		if (rcd->egrbufs.buffers[e].addr)
 			dma_free_coherent(&dd->pcidev->dev,
 					  rcd->egrbufs.buffers[e].len,
 					  rcd->egrbufs.buffers[e].addr,
@@ -1201,6 +1188,11 @@ void hfi1_free_devdata(struct hfi1_devdata *dd)
 	dd->tx_opstats    = NULL;
 	kfree(dd->comp_vect);
 	dd->comp_vect = NULL;
+	if (dd->rcvhdrtail_dummy_kvaddr)
+		dma_free_coherent(&dd->pcidev->dev, sizeof(u64),
+				  (void *)dd->rcvhdrtail_dummy_kvaddr,
+				  dd->rcvhdrtail_dummy_dma);
+	dd->rcvhdrtail_dummy_kvaddr = NULL;
 	sdma_clean(dd, dd->num_sdma);
 	rvt_dealloc_device(&dd->verbs_dev.rdi);
 }
@@ -1298,6 +1290,15 @@ static struct hfi1_devdata *hfi1_alloc_devdata(struct pci_dev *pdev,
 		goto bail;
 	}
 
+	/* allocate dummy tail memory for all receive contexts */
+	dd->rcvhdrtail_dummy_kvaddr =
+		dma_alloc_coherent(&dd->pcidev->dev, sizeof(u64),
+				   &dd->rcvhdrtail_dummy_dma, GFP_KERNEL);
+	if (!dd->rcvhdrtail_dummy_kvaddr) {
+		ret = -ENOMEM;
+		goto bail;
+	}
+
 	atomic_set(&dd->ipoib_rsm_usr_num, 0);
 	return dd;
 
@@ -1505,13 +1506,6 @@ static void cleanup_device_data(struct hfi1_devdata *dd)
 
 	free_credit_return(dd);
 
-	if (dd->rcvhdrtail_dummy_kvaddr) {
-		dma_free_coherent(&dd->pcidev->dev, sizeof(u64),
-				  (void *)dd->rcvhdrtail_dummy_kvaddr,
-				  dd->rcvhdrtail_dummy_dma);
-		dd->rcvhdrtail_dummy_kvaddr = NULL;
-	}
-
 	/*
 	 * Free any resources still in use (usually just kernel contexts)
 	 * at unload; we do for ctxtcnt, because that's what we allocate.
diff --git a/drivers/infiniband/hw/hfi1/sdma.c b/drivers/infiniband/hw/hfi1/sdma.c
index 2b6c24b7b586..f07d328689d3 100644
--- a/drivers/infiniband/hw/hfi1/sdma.c
+++ b/drivers/infiniband/hw/hfi1/sdma.c
@@ -838,8 +838,8 @@ struct sdma_engine *sdma_select_user_engine(struct hfi1_devdata *dd,
 	if (current->nr_cpus_allowed != 1)
 		goto out;
 
-	cpu_id = smp_processor_id();
 	rcu_read_lock();
+	cpu_id = smp_processor_id();
 	rht_node = rhashtable_lookup(dd->sdma_rht, &cpu_id,
 				     sdma_rht_params);
 
diff --git a/drivers/infiniband/hw/hfi1/verbs.c b/drivers/infiniband/hw/hfi1/verbs.c
index ed9fa0d84e9e..dc9211f3a009 100644
--- a/drivers/infiniband/hw/hfi1/verbs.c
+++ b/drivers/infiniband/hw/hfi1/verbs.c
@@ -1628,8 +1628,7 @@ static int init_cntr_names(const char *names_in, const size_t names_len,
 			n++;
 
 	names_out =
-		kmalloc((n + num_extra_names) * sizeof(struct rdma_stat_desc) +
-				names_len,
+		kzalloc((n + num_extra_names) * sizeof(*q) + names_len,
 			GFP_KERNEL);
 	if (!names_out) {
 		*num_cntrs = 0;
@@ -1637,7 +1636,7 @@ static int init_cntr_names(const char *names_in, const size_t names_len,
 		return -ENOMEM;
 	}
 
-	p = names_out + (n + num_extra_names) * sizeof(struct rdma_stat_desc);
+	p = names_out + (n + num_extra_names) * sizeof(*q);
 	memcpy(p, names_in, names_len);
 
 	q = (struct rdma_stat_desc *)names_out;
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
index 9bfbaddd1763..eb0defa80d0d 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
@@ -33,6 +33,7 @@
 #include <linux/acpi.h>
 #include <linux/etherdevice.h>
 #include <linux/interrupt.h>
+#include <linux/iopoll.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
 #include <net/addrconf.h>
@@ -1050,9 +1051,14 @@ static u32 hns_roce_v2_cmd_hw_resetting(struct hns_roce_dev *hr_dev,
 					unsigned long instance_stage,
 					unsigned long reset_stage)
 {
+#define HW_RESET_TIMEOUT_US 1000000
+#define HW_RESET_SLEEP_US 1000
+
 	struct hns_roce_v2_priv *priv = hr_dev->priv;
 	struct hnae3_handle *handle = priv->handle;
 	const struct hnae3_ae_ops *ops = handle->ae_algo->ops;
+	unsigned long val;
+	int ret;
 
 	/* When hardware reset is detected, we should stop sending mailbox&cmq&
 	 * doorbell to hardware. If now in .init_instance() function, we should
@@ -1064,7 +1070,11 @@ static u32 hns_roce_v2_cmd_hw_resetting(struct hns_roce_dev *hr_dev,
 	 * again.
 	 */
 	hr_dev->dis_db = true;
-	if (!ops->get_hw_reset_stat(handle))
+
+	ret = read_poll_timeout(ops->ae_dev_reset_cnt, val,
+				val > hr_dev->reset_cnt, HW_RESET_SLEEP_US,
+				HW_RESET_TIMEOUT_US, false, handle);
+	if (!ret)
 		hr_dev->is_reset = true;
 
 	if (!hr_dev->is_reset || reset_stage == HNS_ROCE_STATE_RST_INIT ||
@@ -1584,11 +1594,17 @@ static int hns_roce_config_global_param(struct hns_roce_dev *hr_dev)
 {
 	struct hns_roce_cmq_desc desc;
 	struct hns_roce_cmq_req *req = (struct hns_roce_cmq_req *)desc.data;
+	u32 clock_cycles_of_1us;
 
 	hns_roce_cmq_setup_basic_desc(&desc, HNS_ROCE_OPC_CFG_GLOBAL_PARAM,
 				      false);
 
-	hr_reg_write(req, CFG_GLOBAL_PARAM_1US_CYCLES, 0x3e8);
+	if (hr_dev->pci_dev->revision == PCI_REVISION_ID_HIP08)
+		clock_cycles_of_1us = HNS_ROCE_1NS_CFG;
+	else
+		clock_cycles_of_1us = HNS_ROCE_1US_CFG;
+
+	hr_reg_write(req, CFG_GLOBAL_PARAM_1US_CYCLES, clock_cycles_of_1us);
 	hr_reg_write(req, CFG_GLOBAL_PARAM_UDP_PORT, ROCE_V2_UDP_DPORT);
 
 	return hns_roce_cmq_send(hr_dev, &desc, 1);
@@ -4792,6 +4808,30 @@ static int hns_roce_v2_set_abs_fields(struct ib_qp *ibqp,
 	return ret;
 }
 
+static bool check_qp_timeout_cfg_range(struct hns_roce_dev *hr_dev, u8 *timeout)
+{
+#define QP_ACK_TIMEOUT_MAX_HIP08 20
+#define QP_ACK_TIMEOUT_OFFSET 10
+#define QP_ACK_TIMEOUT_MAX 31
+
+	if (hr_dev->pci_dev->revision == PCI_REVISION_ID_HIP08) {
+		if (*timeout > QP_ACK_TIMEOUT_MAX_HIP08) {
+			ibdev_warn(&hr_dev->ib_dev,
+				   "Local ACK timeout shall be 0 to 20.\n");
+			return false;
+		}
+		*timeout += QP_ACK_TIMEOUT_OFFSET;
+	} else if (hr_dev->pci_dev->revision > PCI_REVISION_ID_HIP08) {
+		if (*timeout > QP_ACK_TIMEOUT_MAX) {
+			ibdev_warn(&hr_dev->ib_dev,
+				   "Local ACK timeout shall be 0 to 31.\n");
+			return false;
+		}
+	}
+
+	return true;
+}
+
 static int hns_roce_v2_set_opt_fields(struct ib_qp *ibqp,
 				      const struct ib_qp_attr *attr,
 				      int attr_mask,
@@ -4801,6 +4841,7 @@ static int hns_roce_v2_set_opt_fields(struct ib_qp *ibqp,
 	struct hns_roce_dev *hr_dev = to_hr_dev(ibqp->device);
 	struct hns_roce_qp *hr_qp = to_hr_qp(ibqp);
 	int ret = 0;
+	u8 timeout;
 
 	if (attr_mask & IB_QP_AV) {
 		ret = hns_roce_v2_set_path(ibqp, attr, attr_mask, context,
@@ -4810,12 +4851,10 @@ static int hns_roce_v2_set_opt_fields(struct ib_qp *ibqp,
 	}
 
 	if (attr_mask & IB_QP_TIMEOUT) {
-		if (attr->timeout < 31) {
-			hr_reg_write(context, QPC_AT, attr->timeout);
+		timeout = attr->timeout;
+		if (check_qp_timeout_cfg_range(hr_dev, &timeout)) {
+			hr_reg_write(context, QPC_AT, timeout);
 			hr_reg_clear(qpc_mask, QPC_AT);
-		} else {
-			ibdev_warn(&hr_dev->ib_dev,
-				   "Local ACK timeout shall be 0 to 30.\n");
 		}
 	}
 
@@ -4872,7 +4911,9 @@ static int hns_roce_v2_set_opt_fields(struct ib_qp *ibqp,
 		set_access_flags(hr_qp, context, qpc_mask, attr, attr_mask);
 
 	if (attr_mask & IB_QP_MIN_RNR_TIMER) {
-		hr_reg_write(context, QPC_MIN_RNR_TIME, attr->min_rnr_timer);
+		hr_reg_write(context, QPC_MIN_RNR_TIME,
+			    hr_dev->pci_dev->revision == PCI_REVISION_ID_HIP08 ?
+			    HNS_ROCE_RNR_TIMER_10NS : attr->min_rnr_timer);
 		hr_reg_clear(qpc_mask, QPC_MIN_RNR_TIME);
 	}
 
@@ -5489,6 +5530,16 @@ static int hns_roce_v2_modify_cq(struct ib_cq *cq, u16 cq_count, u16 cq_period)
 
 	hr_reg_write(cq_context, CQC_CQ_MAX_CNT, cq_count);
 	hr_reg_clear(cqc_mask, CQC_CQ_MAX_CNT);
+
+	if (hr_dev->pci_dev->revision == PCI_REVISION_ID_HIP08) {
+		if (cq_period * HNS_ROCE_CLOCK_ADJUST > USHRT_MAX) {
+			dev_info(hr_dev->dev,
+				 "cq_period(%u) reached the upper limit, adjusted to 65.\n",
+				 cq_period);
+			cq_period = HNS_ROCE_MAX_CQ_PERIOD;
+		}
+		cq_period *= HNS_ROCE_CLOCK_ADJUST;
+	}
 	hr_reg_write(cq_context, CQC_CQ_PERIOD, cq_period);
 	hr_reg_clear(cqc_mask, CQC_CQ_PERIOD);
 
@@ -5884,6 +5935,15 @@ static int config_eqc(struct hns_roce_dev *hr_dev, struct hns_roce_eq *eq,
 	hr_reg_write(eqc, EQC_EQ_PROD_INDX, HNS_ROCE_EQ_INIT_PROD_IDX);
 	hr_reg_write(eqc, EQC_EQ_MAX_CNT, eq->eq_max_cnt);
 
+	if (hr_dev->pci_dev->revision == PCI_REVISION_ID_HIP08) {
+		if (eq->eq_period * HNS_ROCE_CLOCK_ADJUST > USHRT_MAX) {
+			dev_info(hr_dev->dev, "eq_period(%u) reached the upper limit, adjusted to 65.\n",
+				 eq->eq_period);
+			eq->eq_period = HNS_ROCE_MAX_EQ_PERIOD;
+		}
+		eq->eq_period *= HNS_ROCE_CLOCK_ADJUST;
+	}
+
 	hr_reg_write(eqc, EQC_EQ_PERIOD, eq->eq_period);
 	hr_reg_write(eqc, EQC_EQE_REPORT_TIMER, HNS_ROCE_EQ_INIT_REPORT_TIMER);
 	hr_reg_write(eqc, EQC_EQE_BA_L, bt_ba >> 3);
@@ -6387,10 +6447,8 @@ static int hns_roce_hw_v2_reset_notify_down(struct hnae3_handle *handle)
 	if (!hr_dev)
 		return 0;
 
-	hr_dev->is_reset = true;
 	hr_dev->active = false;
 	hr_dev->dis_db = true;
-
 	hr_dev->state = HNS_ROCE_DEVICE_STATE_RST_DOWN;
 
 	return 0;
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
index 4d904d5e82be..35c61da7ba15 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
@@ -1444,6 +1444,14 @@ struct hns_roce_dip {
 	struct list_head node;	/* all dips are on a list */
 };
 
+/* only for RNR timeout issue of HIP08 */
+#define HNS_ROCE_CLOCK_ADJUST 1000
+#define HNS_ROCE_MAX_CQ_PERIOD 65
+#define HNS_ROCE_MAX_EQ_PERIOD 65
+#define HNS_ROCE_RNR_TIMER_10NS 1
+#define HNS_ROCE_1US_CFG 999
+#define HNS_ROCE_1NS_CFG 0
+
 #define HNS_ROCE_AEQ_DEFAULT_BURST_NUM	0x0
 #define HNS_ROCE_AEQ_DEFAULT_INTERVAL	0x0
 #define HNS_ROCE_CEQ_DEFAULT_BURST_NUM	0x0
diff --git a/drivers/infiniband/hw/hns/hns_roce_srq.c b/drivers/infiniband/hw/hns/hns_roce_srq.c
index 6eee9deadd12..e64ef6903fb4 100644
--- a/drivers/infiniband/hw/hns/hns_roce_srq.c
+++ b/drivers/infiniband/hw/hns/hns_roce_srq.c
@@ -259,7 +259,7 @@ static int alloc_srq_wrid(struct hns_roce_dev *hr_dev, struct hns_roce_srq *srq)
 
 static void free_srq_wrid(struct hns_roce_srq *srq)
 {
-	kfree(srq->wrid);
+	kvfree(srq->wrid);
 	srq->wrid = NULL;
 }
 
diff --git a/drivers/infiniband/hw/irdma/hw.c b/drivers/infiniband/hw/irdma/hw.c
index 4108dcabece2..b4c657f5f2f9 100644
--- a/drivers/infiniband/hw/irdma/hw.c
+++ b/drivers/infiniband/hw/irdma/hw.c
@@ -60,6 +60,8 @@ static void irdma_iwarp_ce_handler(struct irdma_sc_cq *iwcq)
 {
 	struct irdma_cq *cq = iwcq->back_cq;
 
+	if (!cq->user_mode)
+		cq->armed = false;
 	if (cq->ibcq.comp_handler)
 		cq->ibcq.comp_handler(&cq->ibcq, cq->ibcq.cq_context);
 }
@@ -146,6 +148,7 @@ static void irdma_set_flush_fields(struct irdma_sc_qp *qp,
 		qp->flush_code = FLUSH_PROT_ERR;
 		break;
 	case IRDMA_AE_AMP_BAD_QP:
+	case IRDMA_AE_WQE_UNEXPECTED_OPCODE:
 		qp->flush_code = FLUSH_LOC_QP_OP_ERR;
 		break;
 	case IRDMA_AE_AMP_BAD_STAG_KEY:
@@ -156,7 +159,6 @@ static void irdma_set_flush_fields(struct irdma_sc_qp *qp,
 	case IRDMA_AE_PRIV_OPERATION_DENIED:
 	case IRDMA_AE_IB_INVALID_REQUEST:
 	case IRDMA_AE_IB_REMOTE_ACCESS_ERROR:
-	case IRDMA_AE_IB_REMOTE_OP_ERROR:
 		qp->flush_code = FLUSH_REM_ACCESS_ERR;
 		qp->event_type = IRDMA_QP_EVENT_ACCESS_ERR;
 		break;
@@ -184,6 +186,9 @@ static void irdma_set_flush_fields(struct irdma_sc_qp *qp,
 	case IRDMA_AE_AMP_MWBIND_INVALID_BOUNDS:
 		qp->flush_code = FLUSH_MW_BIND_ERR;
 		break;
+	case IRDMA_AE_IB_REMOTE_OP_ERROR:
+		qp->flush_code = FLUSH_REM_OP_ERR;
+		break;
 	default:
 		qp->flush_code = FLUSH_FATAL_ERR;
 		break;
diff --git a/drivers/infiniband/hw/irdma/main.h b/drivers/infiniband/hw/irdma/main.h
index 91a497139ba3..cb218cab79ac 100644
--- a/drivers/infiniband/hw/irdma/main.h
+++ b/drivers/infiniband/hw/irdma/main.h
@@ -542,6 +542,7 @@ int irdma_ah_cqp_op(struct irdma_pci_f *rf, struct irdma_sc_ah *sc_ah, u8 cmd,
 		    void (*callback_fcn)(struct irdma_cqp_request *cqp_request),
 		    void *cb_param);
 void irdma_gsi_ud_qp_ah_cb(struct irdma_cqp_request *cqp_request);
+bool irdma_cq_empty(struct irdma_cq *iwcq);
 int irdma_inetaddr_event(struct notifier_block *notifier, unsigned long event,
 			 void *ptr);
 int irdma_inet6addr_event(struct notifier_block *notifier, unsigned long event,
diff --git a/drivers/infiniband/hw/irdma/pble.c b/drivers/infiniband/hw/irdma/pble.c
index aeeb1c310965..fed49da770f3 100644
--- a/drivers/infiniband/hw/irdma/pble.c
+++ b/drivers/infiniband/hw/irdma/pble.c
@@ -25,8 +25,7 @@ void irdma_destroy_pble_prm(struct irdma_hmc_pble_rsrc *pble_rsrc)
 		list_del(&chunk->list);
 		if (chunk->type == PBLE_SD_PAGED)
 			irdma_pble_free_paged_mem(chunk);
-		if (chunk->bitmapbuf)
-			kfree(chunk->bitmapmem.va);
+		bitmap_free(chunk->bitmapbuf);
 		kfree(chunk->chunkmem.va);
 	}
 }
@@ -283,7 +282,6 @@ add_pble_prm(struct irdma_hmc_pble_rsrc *pble_rsrc)
 		  "PBLE: next_fpm_addr = %llx chunk_size[%llu] = 0x%llx\n",
 		  pble_rsrc->next_fpm_addr, chunk->size, chunk->size);
 	pble_rsrc->unallocated_pble -= (u32)(chunk->size >> 3);
-	list_add(&chunk->list, &pble_rsrc->pinfo.clist);
 	sd_reg_val = (sd_entry_type == IRDMA_SD_TYPE_PAGED) ?
 			     sd_entry->u.pd_table.pd_page_addr.pa :
 			     sd_entry->u.bp.addr.pa;
@@ -295,12 +293,12 @@ add_pble_prm(struct irdma_hmc_pble_rsrc *pble_rsrc)
 			goto error;
 	}
 
+	list_add(&chunk->list, &pble_rsrc->pinfo.clist);
 	sd_entry->valid = true;
 	return 0;
 
 error:
-	if (chunk->bitmapbuf)
-		kfree(chunk->bitmapmem.va);
+	bitmap_free(chunk->bitmapbuf);
 	kfree(chunk->chunkmem.va);
 
 	return ret_code;
diff --git a/drivers/infiniband/hw/irdma/pble.h b/drivers/infiniband/hw/irdma/pble.h
index e1b3b8118a2c..aa20827dcc9d 100644
--- a/drivers/infiniband/hw/irdma/pble.h
+++ b/drivers/infiniband/hw/irdma/pble.h
@@ -78,7 +78,6 @@ struct irdma_chunk {
 	u32 pg_cnt;
 	enum irdma_alloc_type type;
 	struct irdma_sc_dev *dev;
-	struct irdma_virt_mem bitmapmem;
 	struct irdma_virt_mem chunkmem;
 };
 
diff --git a/drivers/infiniband/hw/irdma/utils.c b/drivers/infiniband/hw/irdma/utils.c
index 8b42c43fc14f..398736d8c78a 100644
--- a/drivers/infiniband/hw/irdma/utils.c
+++ b/drivers/infiniband/hw/irdma/utils.c
@@ -2239,15 +2239,10 @@ enum irdma_status_code irdma_prm_add_pble_mem(struct irdma_pble_prm *pprm,
 
 	sizeofbitmap = (u64)pchunk->size >> pprm->pble_shift;
 
-	pchunk->bitmapmem.size = sizeofbitmap >> 3;
-	pchunk->bitmapmem.va = kzalloc(pchunk->bitmapmem.size, GFP_KERNEL);
-
-	if (!pchunk->bitmapmem.va)
+	pchunk->bitmapbuf = bitmap_zalloc(sizeofbitmap, GFP_KERNEL);
+	if (!pchunk->bitmapbuf)
 		return IRDMA_ERR_NO_MEMORY;
 
-	pchunk->bitmapbuf = pchunk->bitmapmem.va;
-	bitmap_zero(pchunk->bitmapbuf, sizeofbitmap);
-
 	pchunk->sizeofbitmap = sizeofbitmap;
 	/* each pble is 8 bytes hence shift by 3 */
 	pprm->total_pble_alloc += pchunk->size >> 3;
@@ -2491,3 +2486,18 @@ void irdma_ib_qp_event(struct irdma_qp *iwqp, enum irdma_qp_event_type event)
 	ibevent.element.qp = &iwqp->ibqp;
 	iwqp->ibqp.event_handler(&ibevent, iwqp->ibqp.qp_context);
 }
+
+bool irdma_cq_empty(struct irdma_cq *iwcq)
+{
+	struct irdma_cq_uk *ukcq;
+	u64 qword3;
+	__le64 *cqe;
+	u8 polarity;
+
+	ukcq  = &iwcq->sc_cq.cq_uk;
+	cqe = IRDMA_GET_CURRENT_CQ_ELEM(ukcq);
+	get_64bit_val(cqe, 24, &qword3);
+	polarity = (u8)FIELD_GET(IRDMA_CQ_VALID, qword3);
+
+	return polarity != ukcq->polarity;
+}
diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c
index 0f66e809d418..8cd5f9261692 100644
--- a/drivers/infiniband/hw/irdma/verbs.c
+++ b/drivers/infiniband/hw/irdma/verbs.c
@@ -3584,18 +3584,31 @@ static int irdma_req_notify_cq(struct ib_cq *ibcq,
 	struct irdma_cq *iwcq;
 	struct irdma_cq_uk *ukcq;
 	unsigned long flags;
-	enum irdma_cmpl_notify cq_notify = IRDMA_CQ_COMPL_EVENT;
+	enum irdma_cmpl_notify cq_notify;
+	bool promo_event = false;
+	int ret = 0;
 
+	cq_notify = notify_flags == IB_CQ_SOLICITED ?
+		    IRDMA_CQ_COMPL_SOLICITED : IRDMA_CQ_COMPL_EVENT;
 	iwcq = to_iwcq(ibcq);
 	ukcq = &iwcq->sc_cq.cq_uk;
-	if (notify_flags == IB_CQ_SOLICITED)
-		cq_notify = IRDMA_CQ_COMPL_SOLICITED;
 
 	spin_lock_irqsave(&iwcq->lock, flags);
-	irdma_uk_cq_request_notification(ukcq, cq_notify);
+	/* Only promote to arm the CQ for any event if the last arm event was solicited. */
+	if (iwcq->last_notify == IRDMA_CQ_COMPL_SOLICITED && notify_flags != IB_CQ_SOLICITED)
+		promo_event = true;
+
+	if (!iwcq->armed || promo_event) {
+		iwcq->armed = true;
+		iwcq->last_notify = cq_notify;
+		irdma_uk_cq_request_notification(ukcq, cq_notify);
+	}
+
+	if ((notify_flags & IB_CQ_REPORT_MISSED_EVENTS) && !irdma_cq_empty(iwcq))
+		ret = 1;
 	spin_unlock_irqrestore(&iwcq->lock, flags);
 
-	return 0;
+	return ret;
 }
 
 static int irdma_roce_port_immutable(struct ib_device *ibdev, u32 port_num,
diff --git a/drivers/infiniband/hw/irdma/verbs.h b/drivers/infiniband/hw/irdma/verbs.h
index 5c244cd321a3..d0fdef8d09ea 100644
--- a/drivers/infiniband/hw/irdma/verbs.h
+++ b/drivers/infiniband/hw/irdma/verbs.h
@@ -110,6 +110,8 @@ struct irdma_cq {
 	u16 cq_size;
 	u16 cq_num;
 	bool user_mode;
+	bool armed;
+	enum irdma_cmpl_notify last_notify;
 	u32 polled_cmpls;
 	u32 cq_mem_size;
 	struct irdma_dma_mem kmem;
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index ceca05982f61..0d2fa3338784 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -2215,6 +2215,11 @@ static const struct ib_device_ops mlx4_ib_hw_stats_ops = {
 	.get_hw_stats = mlx4_ib_get_hw_stats,
 };
 
+static const struct ib_device_ops mlx4_ib_hw_stats_ops1 = {
+	.alloc_hw_device_stats = mlx4_ib_alloc_hw_device_stats,
+	.get_hw_stats = mlx4_ib_get_hw_stats,
+};
+
 static int mlx4_ib_alloc_diag_counters(struct mlx4_ib_dev *ibdev)
 {
 	struct mlx4_ib_diag_counters *diag = ibdev->diag_counters;
@@ -2227,9 +2232,16 @@ static int mlx4_ib_alloc_diag_counters(struct mlx4_ib_dev *ibdev)
 		return 0;
 
 	for (i = 0; i < MLX4_DIAG_COUNTERS_TYPES; i++) {
-		/* i == 1 means we are building port counters */
-		if (i && !per_port)
-			continue;
+		/*
+		 * i == 1 means we are building port counters, set a different
+		 * stats ops without port stats callback.
+		 */
+		if (i && !per_port) {
+			ib_set_device_ops(&ibdev->ib_dev,
+					  &mlx4_ib_hw_stats_ops1);
+
+			return 0;
+		}
 
 		ret = __mlx4_ib_alloc_diag_counters(ibdev, &diag[i].descs,
 						    &diag[i].offset,
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index e636e954f6bf..4a7a56ed740b 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -664,7 +664,6 @@ struct mlx5_ib_mr {
 
 	/* User MR data */
 	struct mlx5_cache_ent *cache_ent;
-	struct ib_umem *umem;
 
 	/* This is zero'd when the MR is allocated */
 	union {
@@ -676,7 +675,7 @@ struct mlx5_ib_mr {
 			struct list_head list;
 		};
 
-		/* Used only by kernel MRs (umem == NULL) */
+		/* Used only by kernel MRs */
 		struct {
 			void *descs;
 			void *descs_alloc;
@@ -697,8 +696,9 @@ struct mlx5_ib_mr {
 			int data_length;
 		};
 
-		/* Used only by User MRs (umem != NULL) */
+		/* Used only by User MRs */
 		struct {
+			struct ib_umem *umem;
 			unsigned int page_shift;
 			/* Current access_flags */
 			int access_flags;
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 157d862fb864..63e2129f1142 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -1904,19 +1904,18 @@ err:
 	return ret;
 }
 
-static void
-mlx5_free_priv_descs(struct mlx5_ib_mr *mr)
+static void mlx5_free_priv_descs(struct mlx5_ib_mr *mr)
 {
-	if (!mr->umem && mr->descs) {
-		struct ib_device *device = mr->ibmr.device;
-		int size = mr->max_descs * mr->desc_size;
-		struct mlx5_ib_dev *dev = to_mdev(device);
+	struct mlx5_ib_dev *dev = to_mdev(mr->ibmr.device);
+	int size = mr->max_descs * mr->desc_size;
 
-		dma_unmap_single(&dev->mdev->pdev->dev, mr->desc_map, size,
-				 DMA_TO_DEVICE);
-		kfree(mr->descs_alloc);
-		mr->descs = NULL;
-	}
+	if (!mr->descs)
+		return;
+
+	dma_unmap_single(&dev->mdev->pdev->dev, mr->desc_map, size,
+			 DMA_TO_DEVICE);
+	kfree(mr->descs_alloc);
+	mr->descs = NULL;
 }
 
 int mlx5_ib_dereg_mr(struct ib_mr *ibmr, struct ib_udata *udata)
@@ -1992,7 +1991,8 @@ int mlx5_ib_dereg_mr(struct ib_mr *ibmr, struct ib_udata *udata)
 	if (mr->cache_ent) {
 		mlx5_mr_cache_free(dev, mr);
 	} else {
-		mlx5_free_priv_descs(mr);
+		if (!udata)
+			mlx5_free_priv_descs(mr);
 		kfree(mr);
 	}
 	return 0;
@@ -2079,7 +2079,6 @@ static struct mlx5_ib_mr *mlx5_ib_alloc_pi_mr(struct ib_pd *pd,
 	if (err)
 		goto err_free_in;
 
-	mr->umem = NULL;
 	kfree(in);
 
 	return mr;
@@ -2206,7 +2205,6 @@ static struct ib_mr *__mlx5_ib_alloc_mr(struct ib_pd *pd,
 	}
 
 	mr->ibmr.device = pd->device;
-	mr->umem = NULL;
 
 	switch (mr_type) {
 	case IB_MR_TYPE_MEM_REG:
diff --git a/drivers/infiniband/hw/qib/qib_user_sdma.c b/drivers/infiniband/hw/qib/qib_user_sdma.c
index ac11943a5ddb..bf2f30d67949 100644
--- a/drivers/infiniband/hw/qib/qib_user_sdma.c
+++ b/drivers/infiniband/hw/qib/qib_user_sdma.c
@@ -941,7 +941,7 @@ static int qib_user_sdma_queue_pkts(const struct qib_devdata *dd,
 					       &addrlimit) ||
 			    addrlimit > type_max(typeof(pkt->addrlimit))) {
 				ret = -EINVAL;
-				goto free_pbc;
+				goto free_pkt;
 			}
 			pkt->addrlimit = addrlimit;
 
diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c
index 975321812c87..54b8711321c1 100644
--- a/drivers/infiniband/sw/rxe/rxe_qp.c
+++ b/drivers/infiniband/sw/rxe/rxe_qp.c
@@ -359,6 +359,7 @@ int rxe_qp_from_init(struct rxe_dev *rxe, struct rxe_qp *qp, struct rxe_pd *pd,
 
 err2:
 	rxe_queue_cleanup(qp->sq.queue);
+	qp->sq.queue = NULL;
 err1:
 	qp->pd = NULL;
 	qp->rcq = NULL;
diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt-stats.c b/drivers/infiniband/ulp/rtrs/rtrs-clt-stats.c
index f7e459fe68be..76e4352fe3f6 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-clt-stats.c
+++ b/drivers/infiniband/ulp/rtrs/rtrs-clt-stats.c
@@ -19,7 +19,7 @@ void rtrs_clt_update_wc_stats(struct rtrs_clt_con *con)
 	int cpu;
 
 	cpu = raw_smp_processor_id();
-	s = this_cpu_ptr(stats->pcpu_stats);
+	s = get_cpu_ptr(stats->pcpu_stats);
 	if (con->cpu != cpu) {
 		s->cpu_migr.to++;
 
@@ -27,14 +27,16 @@ void rtrs_clt_update_wc_stats(struct rtrs_clt_con *con)
 		s = per_cpu_ptr(stats->pcpu_stats, con->cpu);
 		atomic_inc(&s->cpu_migr.from);
 	}
+	put_cpu_ptr(stats->pcpu_stats);
 }
 
 void rtrs_clt_inc_failover_cnt(struct rtrs_clt_stats *stats)
 {
 	struct rtrs_clt_stats_pcpu *s;
 
-	s = this_cpu_ptr(stats->pcpu_stats);
+	s = get_cpu_ptr(stats->pcpu_stats);
 	s->rdma.failover_cnt++;
+	put_cpu_ptr(stats->pcpu_stats);
 }
 
 int rtrs_clt_stats_migration_from_cnt_to_str(struct rtrs_clt_stats *stats, char *buf)
@@ -169,9 +171,10 @@ static inline void rtrs_clt_update_rdma_stats(struct rtrs_clt_stats *stats,
 {
 	struct rtrs_clt_stats_pcpu *s;
 
-	s = this_cpu_ptr(stats->pcpu_stats);
+	s = get_cpu_ptr(stats->pcpu_stats);
 	s->rdma.dir[d].cnt++;
 	s->rdma.dir[d].size_total += size;
+	put_cpu_ptr(stats->pcpu_stats);
 }
 
 void rtrs_clt_update_all_stats(struct rtrs_clt_io_req *req, int dir)
diff --git a/drivers/input/misc/iqs626a.c b/drivers/input/misc/iqs626a.c
index d57e996732cf..23b5dd9552dc 100644
--- a/drivers/input/misc/iqs626a.c
+++ b/drivers/input/misc/iqs626a.c
@@ -456,9 +456,10 @@ struct iqs626_private {
 	unsigned int suspend_mode;
 };
 
-static int iqs626_parse_events(struct iqs626_private *iqs626,
-			       const struct fwnode_handle *ch_node,
-			       enum iqs626_ch_id ch_id)
+static noinline_for_stack int
+iqs626_parse_events(struct iqs626_private *iqs626,
+		    const struct fwnode_handle *ch_node,
+		    enum iqs626_ch_id ch_id)
 {
 	struct iqs626_sys_reg *sys_reg = &iqs626->sys_reg;
 	struct i2c_client *client = iqs626->client;
@@ -604,9 +605,10 @@ static int iqs626_parse_events(struct iqs626_private *iqs626,
 	return 0;
 }
 
-static int iqs626_parse_ati_target(struct iqs626_private *iqs626,
-				   const struct fwnode_handle *ch_node,
-				   enum iqs626_ch_id ch_id)
+static noinline_for_stack int
+iqs626_parse_ati_target(struct iqs626_private *iqs626,
+			const struct fwnode_handle *ch_node,
+			enum iqs626_ch_id ch_id)
 {
 	struct iqs626_sys_reg *sys_reg = &iqs626->sys_reg;
 	struct i2c_client *client = iqs626->client;
@@ -885,9 +887,10 @@ static int iqs626_parse_trackpad(struct iqs626_private *iqs626,
 	return 0;
 }
 
-static int iqs626_parse_channel(struct iqs626_private *iqs626,
-				const struct fwnode_handle *ch_node,
-				enum iqs626_ch_id ch_id)
+static noinline_for_stack int
+iqs626_parse_channel(struct iqs626_private *iqs626,
+		     const struct fwnode_handle *ch_node,
+		     enum iqs626_ch_id ch_id)
 {
 	struct iqs626_sys_reg *sys_reg = &iqs626->sys_reg;
 	struct i2c_client *client = iqs626->client;
diff --git a/drivers/input/misc/xen-kbdfront.c b/drivers/input/misc/xen-kbdfront.c
index 4ff5cd2a6d8d..3d17a0b3fe51 100644
--- a/drivers/input/misc/xen-kbdfront.c
+++ b/drivers/input/misc/xen-kbdfront.c
@@ -542,6 +542,7 @@ static struct xenbus_driver xenkbd_driver = {
 	.remove = xenkbd_remove,
 	.resume = xenkbd_resume,
 	.otherend_changed = xenkbd_backend_changed,
+	.not_essential = true,
 };
 
 static int __init xenkbd_init(void)
diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c
index 956d9cd34796..ece97f8c6a3e 100644
--- a/drivers/input/mouse/elantech.c
+++ b/drivers/input/mouse/elantech.c
@@ -1588,7 +1588,13 @@ static const struct dmi_system_id no_hw_res_dmi_table[] = {
  */
 static int elantech_change_report_id(struct psmouse *psmouse)
 {
-	unsigned char param[2] = { 0x10, 0x03 };
+	/*
+	 * NOTE: the code is expecting to receive param[] as an array of 3
+	 * items (see __ps2_command()), even if in this case only 2 are
+	 * actually needed. Make sure the array size is 3 to avoid potential
+	 * stack out-of-bound accesses.
+	 */
+	unsigned char param[3] = { 0x10, 0x03 };
 
 	if (elantech_write_reg_params(psmouse, 0x7, param) ||
 	    elantech_read_reg_params(psmouse, 0x7, param) ||
diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h
index aedd05541044..148a7c5fd0e2 100644
--- a/drivers/input/serio/i8042-x86ia64io.h
+++ b/drivers/input/serio/i8042-x86ia64io.h
@@ -995,6 +995,24 @@ static const struct dmi_system_id __initconst i8042_dmi_kbdreset_table[] = {
 	{ }
 };
 
+static const struct dmi_system_id i8042_dmi_probe_defer_table[] __initconst = {
+	{
+		/* ASUS ZenBook UX425UA */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "ZenBook UX425UA"),
+		},
+	},
+	{
+		/* ASUS ZenBook UM325UA */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "ZenBook UX325UA_UM325UA"),
+		},
+	},
+	{ }
+};
+
 #endif /* CONFIG_X86 */
 
 #ifdef CONFIG_PNP
@@ -1315,6 +1333,9 @@ static int __init i8042_platform_init(void)
 	if (dmi_check_system(i8042_dmi_kbdreset_table))
 		i8042_kbdreset = true;
 
+	if (dmi_check_system(i8042_dmi_probe_defer_table))
+		i8042_probe_defer = true;
+
 	/*
 	 * A20 was already enabled during early kernel init. But some buggy
 	 * BIOSes (in MSI Laptops) require A20 to be enabled using 8042 to
diff --git a/drivers/input/serio/i8042.c b/drivers/input/serio/i8042.c
index 0b9f1d0a8f8b..3fc0a89cc785 100644
--- a/drivers/input/serio/i8042.c
+++ b/drivers/input/serio/i8042.c
@@ -45,6 +45,10 @@ static bool i8042_unlock;
 module_param_named(unlock, i8042_unlock, bool, 0);
 MODULE_PARM_DESC(unlock, "Ignore keyboard lock.");
 
+static bool i8042_probe_defer;
+module_param_named(probe_defer, i8042_probe_defer, bool, 0);
+MODULE_PARM_DESC(probe_defer, "Allow deferred probing.");
+
 enum i8042_controller_reset_mode {
 	I8042_RESET_NEVER,
 	I8042_RESET_ALWAYS,
@@ -711,7 +715,7 @@ static int i8042_set_mux_mode(bool multiplex, unsigned char *mux_version)
  * LCS/Telegraphics.
  */
 
-static int __init i8042_check_mux(void)
+static int i8042_check_mux(void)
 {
 	unsigned char mux_version;
 
@@ -740,10 +744,10 @@ static int __init i8042_check_mux(void)
 /*
  * The following is used to test AUX IRQ delivery.
  */
-static struct completion i8042_aux_irq_delivered __initdata;
-static bool i8042_irq_being_tested __initdata;
+static struct completion i8042_aux_irq_delivered;
+static bool i8042_irq_being_tested;
 
-static irqreturn_t __init i8042_aux_test_irq(int irq, void *dev_id)
+static irqreturn_t i8042_aux_test_irq(int irq, void *dev_id)
 {
 	unsigned long flags;
 	unsigned char str, data;
@@ -770,7 +774,7 @@ static irqreturn_t __init i8042_aux_test_irq(int irq, void *dev_id)
  * verifies success by readinng CTR. Used when testing for presence of AUX
  * port.
  */
-static int __init i8042_toggle_aux(bool on)
+static int i8042_toggle_aux(bool on)
 {
 	unsigned char param;
 	int i;
@@ -798,7 +802,7 @@ static int __init i8042_toggle_aux(bool on)
  * the presence of an AUX interface.
  */
 
-static int __init i8042_check_aux(void)
+static int i8042_check_aux(void)
 {
 	int retval = -1;
 	bool irq_registered = false;
@@ -1005,7 +1009,7 @@ static int i8042_controller_init(void)
 
 		if (i8042_command(&ctr[n++ % 2], I8042_CMD_CTL_RCTR)) {
 			pr_err("Can't read CTR while initializing i8042\n");
-			return -EIO;
+			return i8042_probe_defer ? -EPROBE_DEFER : -EIO;
 		}
 
 	} while (n < 2 || ctr[0] != ctr[1]);
@@ -1320,7 +1324,7 @@ static void i8042_shutdown(struct platform_device *dev)
 	i8042_controller_reset(false);
 }
 
-static int __init i8042_create_kbd_port(void)
+static int i8042_create_kbd_port(void)
 {
 	struct serio *serio;
 	struct i8042_port *port = &i8042_ports[I8042_KBD_PORT_NO];
@@ -1349,7 +1353,7 @@ static int __init i8042_create_kbd_port(void)
 	return 0;
 }
 
-static int __init i8042_create_aux_port(int idx)
+static int i8042_create_aux_port(int idx)
 {
 	struct serio *serio;
 	int port_no = idx < 0 ? I8042_AUX_PORT_NO : I8042_MUX_PORT_NO + idx;
@@ -1386,13 +1390,13 @@ static int __init i8042_create_aux_port(int idx)
 	return 0;
 }
 
-static void __init i8042_free_kbd_port(void)
+static void i8042_free_kbd_port(void)
 {
 	kfree(i8042_ports[I8042_KBD_PORT_NO].serio);
 	i8042_ports[I8042_KBD_PORT_NO].serio = NULL;
 }
 
-static void __init i8042_free_aux_ports(void)
+static void i8042_free_aux_ports(void)
 {
 	int i;
 
@@ -1402,7 +1406,7 @@ static void __init i8042_free_aux_ports(void)
 	}
 }
 
-static void __init i8042_register_ports(void)
+static void i8042_register_ports(void)
 {
 	int i;
 
@@ -1443,7 +1447,7 @@ static void i8042_free_irqs(void)
 	i8042_aux_irq_registered = i8042_kbd_irq_registered = false;
 }
 
-static int __init i8042_setup_aux(void)
+static int i8042_setup_aux(void)
 {
 	int (*aux_enable)(void);
 	int error;
@@ -1485,7 +1489,7 @@ static int __init i8042_setup_aux(void)
 	return error;
 }
 
-static int __init i8042_setup_kbd(void)
+static int i8042_setup_kbd(void)
 {
 	int error;
 
@@ -1535,7 +1539,7 @@ static int i8042_kbd_bind_notifier(struct notifier_block *nb,
 	return 0;
 }
 
-static int __init i8042_probe(struct platform_device *dev)
+static int i8042_probe(struct platform_device *dev)
 {
 	int error;
 
@@ -1600,6 +1604,7 @@ static struct platform_driver i8042_driver = {
 		.pm	= &i8042_pm_ops,
 #endif
 	},
+	.probe		= i8042_probe,
 	.remove		= i8042_remove,
 	.shutdown	= i8042_shutdown,
 };
@@ -1610,7 +1615,6 @@ static struct notifier_block i8042_kbd_bind_notifier_block = {
 
 static int __init i8042_init(void)
 {
-	struct platform_device *pdev;
 	int err;
 
 	dbg_init();
@@ -1626,17 +1630,29 @@ static int __init i8042_init(void)
 	/* Set this before creating the dev to allow i8042_command to work right away */
 	i8042_present = true;
 
-	pdev = platform_create_bundle(&i8042_driver, i8042_probe, NULL, 0, NULL, 0);
-	if (IS_ERR(pdev)) {
-		err = PTR_ERR(pdev);
+	err = platform_driver_register(&i8042_driver);
+	if (err)
 		goto err_platform_exit;
+
+	i8042_platform_device = platform_device_alloc("i8042", -1);
+	if (!i8042_platform_device) {
+		err = -ENOMEM;
+		goto err_unregister_driver;
 	}
 
+	err = platform_device_add(i8042_platform_device);
+	if (err)
+		goto err_free_device;
+
 	bus_register_notifier(&serio_bus, &i8042_kbd_bind_notifier_block);
 	panic_blink = i8042_panic_blink;
 
 	return 0;
 
+err_free_device:
+	platform_device_put(i8042_platform_device);
+err_unregister_driver:
+	platform_driver_unregister(&i8042_driver);
  err_platform_exit:
 	i8042_platform_exit();
 	return err;
diff --git a/drivers/input/touchscreen/atmel_mxt_ts.c b/drivers/input/touchscreen/atmel_mxt_ts.c
index 05de92c0293b..eb66cd2689b7 100644
--- a/drivers/input/touchscreen/atmel_mxt_ts.c
+++ b/drivers/input/touchscreen/atmel_mxt_ts.c
@@ -1882,7 +1882,7 @@ static int mxt_read_info_block(struct mxt_data *data)
 	if (error) {
 		dev_err(&client->dev, "Error %d parsing object table\n", error);
 		mxt_free_object_table(data);
-		goto err_free_mem;
+		return error;
 	}
 
 	data->object_table = (struct mxt_object *)(id_buf + MXT_OBJECT_START);
diff --git a/drivers/input/touchscreen/elants_i2c.c b/drivers/input/touchscreen/elants_i2c.c
index 7e13a66a8a95..879a4d984c90 100644
--- a/drivers/input/touchscreen/elants_i2c.c
+++ b/drivers/input/touchscreen/elants_i2c.c
@@ -117,6 +117,19 @@
 #define ELAN_POWERON_DELAY_USEC	500
 #define ELAN_RESET_DELAY_MSEC	20
 
+/* FW boot code version */
+#define BC_VER_H_BYTE_FOR_EKTH3900x1_I2C        0x72
+#define BC_VER_H_BYTE_FOR_EKTH3900x2_I2C        0x82
+#define BC_VER_H_BYTE_FOR_EKTH3900x3_I2C        0x92
+#define BC_VER_H_BYTE_FOR_EKTH5312x1_I2C        0x6D
+#define BC_VER_H_BYTE_FOR_EKTH5312x2_I2C        0x6E
+#define BC_VER_H_BYTE_FOR_EKTH5312cx1_I2C       0x77
+#define BC_VER_H_BYTE_FOR_EKTH5312cx2_I2C       0x78
+#define BC_VER_H_BYTE_FOR_EKTH5312x1_I2C_USB    0x67
+#define BC_VER_H_BYTE_FOR_EKTH5312x2_I2C_USB    0x68
+#define BC_VER_H_BYTE_FOR_EKTH5312cx1_I2C_USB   0x74
+#define BC_VER_H_BYTE_FOR_EKTH5312cx2_I2C_USB   0x75
+
 enum elants_chip_id {
 	EKTH3500,
 	EKTF3624,
@@ -736,6 +749,37 @@ static int elants_i2c_validate_remark_id(struct elants_data *ts,
 	return 0;
 }
 
+static bool elants_i2c_should_check_remark_id(struct elants_data *ts)
+{
+	struct i2c_client *client = ts->client;
+	const u8 bootcode_version = ts->iap_version;
+	bool check;
+
+	/* I2C eKTH3900 and eKTH5312 are NOT support Remark ID */
+	if ((bootcode_version == BC_VER_H_BYTE_FOR_EKTH3900x1_I2C) ||
+	    (bootcode_version == BC_VER_H_BYTE_FOR_EKTH3900x2_I2C) ||
+	    (bootcode_version == BC_VER_H_BYTE_FOR_EKTH3900x3_I2C) ||
+	    (bootcode_version == BC_VER_H_BYTE_FOR_EKTH5312x1_I2C) ||
+	    (bootcode_version == BC_VER_H_BYTE_FOR_EKTH5312x2_I2C) ||
+	    (bootcode_version == BC_VER_H_BYTE_FOR_EKTH5312cx1_I2C) ||
+	    (bootcode_version == BC_VER_H_BYTE_FOR_EKTH5312cx2_I2C) ||
+	    (bootcode_version == BC_VER_H_BYTE_FOR_EKTH5312x1_I2C_USB) ||
+	    (bootcode_version == BC_VER_H_BYTE_FOR_EKTH5312x2_I2C_USB) ||
+	    (bootcode_version == BC_VER_H_BYTE_FOR_EKTH5312cx1_I2C_USB) ||
+	    (bootcode_version == BC_VER_H_BYTE_FOR_EKTH5312cx2_I2C_USB)) {
+		dev_dbg(&client->dev,
+			"eKTH3900/eKTH5312(0x%02x) are not support remark id\n",
+			bootcode_version);
+		check = false;
+	} else if (bootcode_version >= 0x60) {
+		check = true;
+	} else {
+		check = false;
+	}
+
+	return check;
+}
+
 static int elants_i2c_do_update_firmware(struct i2c_client *client,
 					 const struct firmware *fw,
 					 bool force)
@@ -749,7 +793,7 @@ static int elants_i2c_do_update_firmware(struct i2c_client *client,
 	u16 send_id;
 	int page, n_fw_pages;
 	int error;
-	bool check_remark_id = ts->iap_version >= 0x60;
+	bool check_remark_id = elants_i2c_should_check_remark_id(ts);
 
 	/* Recovery mode detection! */
 	if (force) {
diff --git a/drivers/input/touchscreen/goodix.c b/drivers/input/touchscreen/goodix.c
index b5cc91788195..aaa3c455e01e 100644
--- a/drivers/input/touchscreen/goodix.c
+++ b/drivers/input/touchscreen/goodix.c
@@ -102,6 +102,7 @@ static const struct goodix_chip_id goodix_chip_ids[] = {
 	{ .id = "911", .data = &gt911_chip_data },
 	{ .id = "9271", .data = &gt911_chip_data },
 	{ .id = "9110", .data = &gt911_chip_data },
+	{ .id = "9111", .data = &gt911_chip_data },
 	{ .id = "927", .data = &gt911_chip_data },
 	{ .id = "928", .data = &gt911_chip_data },
 
@@ -650,10 +651,16 @@ int goodix_reset_no_int_sync(struct goodix_ts_data *ts)
 
 	usleep_range(6000, 10000);		/* T4: > 5ms */
 
-	/* end select I2C slave addr */
-	error = gpiod_direction_input(ts->gpiod_rst);
-	if (error)
-		goto error;
+	/*
+	 * Put the reset pin back in to input / high-impedance mode to save
+	 * power. Only do this in the non ACPI case since some ACPI boards
+	 * don't have a pull-up, so there the reset pin must stay active-high.
+	 */
+	if (ts->irq_pin_access_method == IRQ_PIN_ACCESS_GPIO) {
+		error = gpiod_direction_input(ts->gpiod_rst);
+		if (error)
+			goto error;
+	}
 
 	return 0;
 
@@ -787,6 +794,14 @@ static int goodix_add_acpi_gpio_mappings(struct goodix_ts_data *ts)
 		return -EINVAL;
 	}
 
+	/*
+	 * Normally we put the reset pin in input / high-impedance mode to save
+	 * power. But some x86/ACPI boards don't have a pull-up, so for the ACPI
+	 * case, leave the pin as is. This results in the pin not being touched
+	 * at all on x86/ACPI boards, except when needed for error-recover.
+	 */
+	ts->gpiod_rst_flags = GPIOD_ASIS;
+
 	return devm_acpi_dev_add_driver_gpios(dev, gpio_mapping);
 }
 #else
@@ -812,6 +827,12 @@ static int goodix_get_gpio_config(struct goodix_ts_data *ts)
 		return -EINVAL;
 	dev = &ts->client->dev;
 
+	/*
+	 * By default we request the reset pin as input, leaving it in
+	 * high-impedance when not resetting the controller to save power.
+	 */
+	ts->gpiod_rst_flags = GPIOD_IN;
+
 	ts->avdd28 = devm_regulator_get(dev, "AVDD28");
 	if (IS_ERR(ts->avdd28)) {
 		error = PTR_ERR(ts->avdd28);
@@ -849,7 +870,7 @@ retry_get_irq_gpio:
 	ts->gpiod_int = gpiod;
 
 	/* Get the reset line GPIO pin number */
-	gpiod = devm_gpiod_get_optional(dev, GOODIX_GPIO_RST_NAME, GPIOD_IN);
+	gpiod = devm_gpiod_get_optional(dev, GOODIX_GPIO_RST_NAME, ts->gpiod_rst_flags);
 	if (IS_ERR(gpiod)) {
 		error = PTR_ERR(gpiod);
 		if (error != -EPROBE_DEFER)
diff --git a/drivers/input/touchscreen/goodix.h b/drivers/input/touchscreen/goodix.h
index 62138f930d1a..02065d1c3263 100644
--- a/drivers/input/touchscreen/goodix.h
+++ b/drivers/input/touchscreen/goodix.h
@@ -87,6 +87,7 @@ struct goodix_ts_data {
 	struct gpio_desc *gpiod_rst;
 	int gpio_count;
 	int gpio_int_idx;
+	enum gpiod_flags gpiod_rst_flags;
 	char id[GOODIX_ID_MAX_LEN + 1];
 	char cfg_name[64];
 	u16 version;
diff --git a/drivers/input/touchscreen/goodix_fwupload.c b/drivers/input/touchscreen/goodix_fwupload.c
index c1e7a2413078..191d4f38d991 100644
--- a/drivers/input/touchscreen/goodix_fwupload.c
+++ b/drivers/input/touchscreen/goodix_fwupload.c
@@ -207,7 +207,7 @@ static int goodix_firmware_upload(struct goodix_ts_data *ts)
 
 	error = goodix_reset_no_int_sync(ts);
 	if (error)
-		return error;
+		goto release;
 
 	error = goodix_enter_upload_mode(ts->client);
 	if (error)
diff --git a/drivers/iommu/amd/iommu_v2.c b/drivers/iommu/amd/iommu_v2.c
index 13cbeb997cc1..58da08cc3d01 100644
--- a/drivers/iommu/amd/iommu_v2.c
+++ b/drivers/iommu/amd/iommu_v2.c
@@ -929,10 +929,8 @@ static int __init amd_iommu_v2_init(void)
 {
 	int ret;
 
-	pr_info("AMD IOMMUv2 driver by Joerg Roedel <jroedel@suse.de>\n");
-
 	if (!amd_iommu_v2_supported()) {
-		pr_info("AMD IOMMUv2 functionality not available on this system\n");
+		pr_info("AMD IOMMUv2 functionality not available on this system - This is not a bug.\n");
 		/*
 		 * Load anyway to provide the symbols to other modules
 		 * which may use AMD IOMMUv2 optionally.
@@ -947,6 +945,8 @@ static int __init amd_iommu_v2_init(void)
 
 	amd_iommu_register_ppr_notifier(&ppr_nb);
 
+	pr_info("AMD IOMMUv2 loaded and initialized\n");
+
 	return 0;
 
 out:
diff --git a/drivers/iommu/intel/cap_audit.c b/drivers/iommu/intel/cap_audit.c
index b39d223926a4..71596fc62822 100644
--- a/drivers/iommu/intel/cap_audit.c
+++ b/drivers/iommu/intel/cap_audit.c
@@ -144,6 +144,7 @@ static int cap_audit_static(struct intel_iommu *iommu, enum cap_audit_type type)
 {
 	struct dmar_drhd_unit *d;
 	struct intel_iommu *i;
+	int rc = 0;
 
 	rcu_read_lock();
 	if (list_empty(&dmar_drhd_units))
@@ -169,11 +170,11 @@ static int cap_audit_static(struct intel_iommu *iommu, enum cap_audit_type type)
 	 */
 	if (intel_cap_smts_sanity() &&
 	    !intel_cap_flts_sanity() && !intel_cap_slts_sanity())
-		return -EOPNOTSUPP;
+		rc = -EOPNOTSUPP;
 
 out:
 	rcu_read_unlock();
-	return 0;
+	return rc;
 }
 
 int intel_cap_audit(enum cap_audit_type type, struct intel_iommu *iommu)
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 0bde0c8b4126..b6a8f3282411 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -1339,13 +1339,11 @@ static struct page *dma_pte_clear_level(struct dmar_domain *domain, int level,
 	pte = &pte[pfn_level_offset(pfn, level)];
 
 	do {
-		unsigned long level_pfn;
+		unsigned long level_pfn = pfn & level_mask(level);
 
 		if (!dma_pte_present(pte))
 			goto next;
 
-		level_pfn = pfn & level_mask(level);
-
 		/* If range covers entire pagetable, free it */
 		if (start_pfn <= level_pfn &&
 		    last_pfn >= level_pfn + level_size(level) - 1) {
@@ -1366,7 +1364,7 @@ static struct page *dma_pte_clear_level(struct dmar_domain *domain, int level,
 						       freelist);
 		}
 next:
-		pfn += level_size(level);
+		pfn = level_pfn + level_size(level);
 	} while (!first_pte_in_page(++pte) && pfn <= last_pfn);
 
 	if (first_pte)
diff --git a/drivers/iommu/rockchip-iommu.c b/drivers/iommu/rockchip-iommu.c
index 5cb260820eda..7f23ad61c094 100644
--- a/drivers/iommu/rockchip-iommu.c
+++ b/drivers/iommu/rockchip-iommu.c
@@ -200,8 +200,8 @@ static inline phys_addr_t rk_dte_pt_address(u32 dte)
 #define DTE_HI_MASK2	GENMASK(7, 4)
 #define DTE_HI_SHIFT1	24 /* shift bit 8 to bit 32 */
 #define DTE_HI_SHIFT2	32 /* shift bit 4 to bit 36 */
-#define PAGE_DESC_HI_MASK1	GENMASK_ULL(39, 36)
-#define PAGE_DESC_HI_MASK2	GENMASK_ULL(35, 32)
+#define PAGE_DESC_HI_MASK1	GENMASK_ULL(35, 32)
+#define PAGE_DESC_HI_MASK2	GENMASK_ULL(39, 36)
 
 static inline phys_addr_t rk_dte_pt_address_v2(u32 dte)
 {
diff --git a/drivers/irqchip/irq-apple-aic.c b/drivers/irqchip/irq-apple-aic.c
index 3759dc36cc8f..2543ef65825b 100644
--- a/drivers/irqchip/irq-apple-aic.c
+++ b/drivers/irqchip/irq-apple-aic.c
@@ -707,7 +707,7 @@ static const struct irq_domain_ops aic_ipi_domain_ops = {
 	.free = aic_ipi_free,
 };
 
-static int aic_init_smp(struct aic_irq_chip *irqc, struct device_node *node)
+static int __init aic_init_smp(struct aic_irq_chip *irqc, struct device_node *node)
 {
 	struct irq_domain *ipi_domain;
 	int base_ipi;
diff --git a/drivers/irqchip/irq-armada-370-xp.c b/drivers/irqchip/irq-armada-370-xp.c
index 80906bfec845..5b8d571c041d 100644
--- a/drivers/irqchip/irq-armada-370-xp.c
+++ b/drivers/irqchip/irq-armada-370-xp.c
@@ -232,16 +232,12 @@ static int armada_370_xp_msi_alloc(struct irq_domain *domain, unsigned int virq,
 	int hwirq, i;
 
 	mutex_lock(&msi_used_lock);
+	hwirq = bitmap_find_free_region(msi_used, PCI_MSI_DOORBELL_NR,
+					order_base_2(nr_irqs));
+	mutex_unlock(&msi_used_lock);
 
-	hwirq = bitmap_find_next_zero_area(msi_used, PCI_MSI_DOORBELL_NR,
-					   0, nr_irqs, 0);
-	if (hwirq >= PCI_MSI_DOORBELL_NR) {
-		mutex_unlock(&msi_used_lock);
+	if (hwirq < 0)
 		return -ENOSPC;
-	}
-
-	bitmap_set(msi_used, hwirq, nr_irqs);
-	mutex_unlock(&msi_used_lock);
 
 	for (i = 0; i < nr_irqs; i++) {
 		irq_domain_set_info(domain, virq + i, hwirq + i,
@@ -250,7 +246,7 @@ static int armada_370_xp_msi_alloc(struct irq_domain *domain, unsigned int virq,
 				    NULL, NULL);
 	}
 
-	return hwirq;
+	return 0;
 }
 
 static void armada_370_xp_msi_free(struct irq_domain *domain,
@@ -259,7 +255,7 @@ static void armada_370_xp_msi_free(struct irq_domain *domain,
 	struct irq_data *d = irq_domain_get_irq_data(domain, virq);
 
 	mutex_lock(&msi_used_lock);
-	bitmap_clear(msi_used, d->hwirq, nr_irqs);
+	bitmap_release_region(msi_used, d->hwirq, order_base_2(nr_irqs));
 	mutex_unlock(&msi_used_lock);
 }
 
diff --git a/drivers/irqchip/irq-aspeed-scu-ic.c b/drivers/irqchip/irq-aspeed-scu-ic.c
index f3c6855a4cef..18b77c3e6db4 100644
--- a/drivers/irqchip/irq-aspeed-scu-ic.c
+++ b/drivers/irqchip/irq-aspeed-scu-ic.c
@@ -76,8 +76,8 @@ static void aspeed_scu_ic_irq_handler(struct irq_desc *desc)
 		generic_handle_domain_irq(scu_ic->irq_domain,
 					  bit - scu_ic->irq_shift);
 
-		regmap_update_bits(scu_ic->scu, scu_ic->reg, mask,
-				   BIT(bit + ASPEED_SCU_IC_STATUS_SHIFT));
+		regmap_write_bits(scu_ic->scu, scu_ic->reg, mask,
+				  BIT(bit + ASPEED_SCU_IC_STATUS_SHIFT));
 	}
 
 	chained_irq_exit(chip, desc);
diff --git a/drivers/irqchip/irq-bcm7120-l2.c b/drivers/irqchip/irq-bcm7120-l2.c
index d80e67a6aad2..bb6609cebdbc 100644
--- a/drivers/irqchip/irq-bcm7120-l2.c
+++ b/drivers/irqchip/irq-bcm7120-l2.c
@@ -238,6 +238,7 @@ static int __init bcm7120_l2_intc_probe(struct device_node *dn,
 	}
 
 	data->num_parent_irqs = platform_irq_count(pdev);
+	put_device(&pdev->dev);
 	if (data->num_parent_irqs <= 0) {
 		pr_err("invalid number of parent interrupts\n");
 		ret = -ENOMEM;
diff --git a/drivers/irqchip/irq-csky-mpintc.c b/drivers/irqchip/irq-csky-mpintc.c
index cb403c960ac0..4aebd67d4f8f 100644
--- a/drivers/irqchip/irq-csky-mpintc.c
+++ b/drivers/irqchip/irq-csky-mpintc.c
@@ -78,7 +78,7 @@ static void csky_mpintc_handler(struct pt_regs *regs)
 		readl_relaxed(reg_base + INTCL_RDYIR));
 }
 
-static void csky_mpintc_enable(struct irq_data *d)
+static void csky_mpintc_unmask(struct irq_data *d)
 {
 	void __iomem *reg_base = this_cpu_read(intcl_reg);
 
@@ -87,7 +87,7 @@ static void csky_mpintc_enable(struct irq_data *d)
 	writel_relaxed(d->hwirq, reg_base + INTCL_SENR);
 }
 
-static void csky_mpintc_disable(struct irq_data *d)
+static void csky_mpintc_mask(struct irq_data *d)
 {
 	void __iomem *reg_base = this_cpu_read(intcl_reg);
 
@@ -164,8 +164,8 @@ static int csky_irq_set_affinity(struct irq_data *d,
 static struct irq_chip csky_irq_chip = {
 	.name           = "C-SKY SMP Intc",
 	.irq_eoi	= csky_mpintc_eoi,
-	.irq_enable	= csky_mpintc_enable,
-	.irq_disable	= csky_mpintc_disable,
+	.irq_unmask	= csky_mpintc_unmask,
+	.irq_mask	= csky_mpintc_mask,
 	.irq_set_type	= csky_mpintc_set_type,
 #ifdef CONFIG_SMP
 	.irq_set_affinity = csky_irq_set_affinity,
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index eb0882d15366..0cb584d9815b 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -742,7 +742,7 @@ static struct its_collection *its_build_invall_cmd(struct its_node *its,
 
 	its_fixup_cmd(cmd);
 
-	return NULL;
+	return desc->its_invall_cmd.col;
 }
 
 static struct its_vpe *its_build_vinvall_cmd(struct its_node *its,
diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c
index d02b05a067d9..ff89b36267dd 100644
--- a/drivers/irqchip/irq-mips-gic.c
+++ b/drivers/irqchip/irq-mips-gic.c
@@ -9,6 +9,7 @@
 
 #define pr_fmt(fmt) "irq-mips-gic: " fmt
 
+#include <linux/bitfield.h>
 #include <linux/bitmap.h>
 #include <linux/clocksource.h>
 #include <linux/cpuhotplug.h>
@@ -735,8 +736,7 @@ static int __init gic_of_init(struct device_node *node,
 	mips_gic_base = ioremap(gic_base, gic_len);
 
 	gicconfig = read_gic_config();
-	gic_shared_intrs = gicconfig & GIC_CONFIG_NUMINTERRUPTS;
-	gic_shared_intrs >>= __ffs(GIC_CONFIG_NUMINTERRUPTS);
+	gic_shared_intrs = FIELD_GET(GIC_CONFIG_NUMINTERRUPTS, gicconfig);
 	gic_shared_intrs = (gic_shared_intrs + 1) * 8;
 
 	if (cpu_has_veic) {
diff --git a/drivers/irqchip/irq-nvic.c b/drivers/irqchip/irq-nvic.c
index 63bac3f78863..ba4759b3e269 100644
--- a/drivers/irqchip/irq-nvic.c
+++ b/drivers/irqchip/irq-nvic.c
@@ -26,7 +26,7 @@
 
 #define NVIC_ISER		0x000
 #define NVIC_ICER		0x080
-#define NVIC_IPR		0x300
+#define NVIC_IPR		0x400
 
 #define NVIC_MAX_BANKS		16
 /*
diff --git a/drivers/irqchip/irq-sifive-plic.c b/drivers/irqchip/irq-sifive-plic.c
index cf74cfa82045..259065d271ef 100644
--- a/drivers/irqchip/irq-sifive-plic.c
+++ b/drivers/irqchip/irq-sifive-plic.c
@@ -163,7 +163,13 @@ static void plic_irq_eoi(struct irq_data *d)
 {
 	struct plic_handler *handler = this_cpu_ptr(&plic_handlers);
 
-	writel(d->hwirq, handler->hart_base + CONTEXT_CLAIM);
+	if (irqd_irq_masked(d)) {
+		plic_irq_unmask(d);
+		writel(d->hwirq, handler->hart_base + CONTEXT_CLAIM);
+		plic_irq_mask(d);
+	} else {
+		writel(d->hwirq, handler->hart_base + CONTEXT_CLAIM);
+	}
 }
 
 static struct irq_chip plic_chip = {
diff --git a/drivers/isdn/mISDN/core.c b/drivers/isdn/mISDN/core.c
index 55891e420446..a41b4b264594 100644
--- a/drivers/isdn/mISDN/core.c
+++ b/drivers/isdn/mISDN/core.c
@@ -381,7 +381,7 @@ mISDNInit(void)
 	err = mISDN_inittimer(&debug);
 	if (err)
 		goto error2;
-	err = l1_init(&debug);
+	err = Isdnl1_Init(&debug);
 	if (err)
 		goto error3;
 	err = Isdnl2_Init(&debug);
@@ -395,7 +395,7 @@ mISDNInit(void)
 error5:
 	Isdnl2_cleanup();
 error4:
-	l1_cleanup();
+	Isdnl1_cleanup();
 error3:
 	mISDN_timer_cleanup();
 error2:
@@ -408,7 +408,7 @@ static void mISDN_cleanup(void)
 {
 	misdn_sock_cleanup();
 	Isdnl2_cleanup();
-	l1_cleanup();
+	Isdnl1_cleanup();
 	mISDN_timer_cleanup();
 	class_unregister(&mISDN_class);
 
diff --git a/drivers/isdn/mISDN/core.h b/drivers/isdn/mISDN/core.h
index 23b44d303327..42599f49c189 100644
--- a/drivers/isdn/mISDN/core.h
+++ b/drivers/isdn/mISDN/core.h
@@ -60,8 +60,8 @@ struct Bprotocol	*get_Bprotocol4id(u_int);
 extern int	mISDN_inittimer(u_int *);
 extern void	mISDN_timer_cleanup(void);
 
-extern int	l1_init(u_int *);
-extern void	l1_cleanup(void);
+extern int	Isdnl1_Init(u_int *);
+extern void	Isdnl1_cleanup(void);
 extern int	Isdnl2_Init(u_int *);
 extern void	Isdnl2_cleanup(void);
 
diff --git a/drivers/isdn/mISDN/layer1.c b/drivers/isdn/mISDN/layer1.c
index 98a3bc6c1700..7b31c25a550e 100644
--- a/drivers/isdn/mISDN/layer1.c
+++ b/drivers/isdn/mISDN/layer1.c
@@ -398,7 +398,7 @@ create_l1(struct dchannel *dch, dchannel_l1callback *dcb) {
 EXPORT_SYMBOL(create_l1);
 
 int
-l1_init(u_int *deb)
+Isdnl1_Init(u_int *deb)
 {
 	debug = deb;
 	l1fsm_s.state_count = L1S_STATE_COUNT;
@@ -409,7 +409,7 @@ l1_init(u_int *deb)
 }
 
 void
-l1_cleanup(void)
+Isdnl1_cleanup(void)
 {
 	mISDN_FsmFree(&l1fsm_s);
 }
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 86b9e355c583..140f35dc0c45 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -1139,6 +1139,7 @@ static void cancel_writeback_rate_update_dwork(struct cached_dev *dc)
 static void cached_dev_detach_finish(struct work_struct *w)
 {
 	struct cached_dev *dc = container_of(w, struct cached_dev, detach);
+	struct cache_set *c = dc->disk.c;
 
 	BUG_ON(!test_bit(BCACHE_DEV_DETACHING, &dc->disk.flags));
 	BUG_ON(refcount_read(&dc->count));
@@ -1156,7 +1157,7 @@ static void cached_dev_detach_finish(struct work_struct *w)
 
 	bcache_device_detach(&dc->disk);
 	list_move(&dc->list, &uncached_devices);
-	calc_cached_dev_sectors(dc->disk.c);
+	calc_cached_dev_sectors(c);
 
 	clear_bit(BCACHE_DEV_DETACHING, &dc->disk.flags);
 	clear_bit(BCACHE_DEV_UNLINK_DONE, &dc->disk.flags);
diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
index 6319deccbe09..7af242de3202 100644
--- a/drivers/md/dm-integrity.c
+++ b/drivers/md/dm-integrity.c
@@ -1963,7 +1963,7 @@ static bool __journal_read_write(struct dm_integrity_io *dio, struct bio *bio,
 		n_sectors -= bv.bv_len >> SECTOR_SHIFT;
 		bio_advance_iter(bio, &bio->bi_iter, bv.bv_len);
 retry_kmap:
-		mem = bvec_kmap_local(&bv);
+		mem = kmap_local_page(bv.bv_page);
 		if (likely(dio->op == REQ_OP_WRITE))
 			flush_dcache_page(bv.bv_page);
 
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 5111ed966947..41d6e2383517 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -2189,6 +2189,7 @@ super_1_rdev_size_change(struct md_rdev *rdev, sector_t num_sectors)
 
 		if (!num_sectors || num_sectors > max_sectors)
 			num_sectors = max_sectors;
+		rdev->sb_start = sb_start;
 	}
 	sb = page_address(rdev->sb_page);
 	sb->data_size = cpu_to_le64(num_sectors);
@@ -6270,7 +6271,8 @@ static void __md_stop(struct mddev *mddev)
 	spin_lock(&mddev->lock);
 	mddev->pers = NULL;
 	spin_unlock(&mddev->lock);
-	pers->free(mddev, mddev->private);
+	if (mddev->private)
+		pers->free(mddev, mddev->private);
 	mddev->private = NULL;
 	if (pers->sync_request && mddev->to_remove == NULL)
 		mddev->to_remove = &md_redundancy_group;
diff --git a/drivers/md/persistent-data/dm-btree-remove.c b/drivers/md/persistent-data/dm-btree-remove.c
index 70532335c7c7..cb670f16e98e 100644
--- a/drivers/md/persistent-data/dm-btree-remove.c
+++ b/drivers/md/persistent-data/dm-btree-remove.c
@@ -423,9 +423,9 @@ static int rebalance_children(struct shadow_spine *s,
 
 		memcpy(n, dm_block_data(child),
 		       dm_bm_block_size(dm_tm_get_bm(info->tm)));
-		dm_tm_unlock(info->tm, child);
 
 		dm_tm_dec(info->tm, dm_block_location(child));
+		dm_tm_unlock(info->tm, child);
 		return 0;
 	}
 
diff --git a/drivers/media/cec/core/cec-adap.c b/drivers/media/cec/core/cec-adap.c
index 79fa36de8a04..cd9cb354dc2c 100644
--- a/drivers/media/cec/core/cec-adap.c
+++ b/drivers/media/cec/core/cec-adap.c
@@ -1199,6 +1199,7 @@ void cec_received_msg_ts(struct cec_adapter *adap,
 			if (abort)
 				dst->rx_status |= CEC_RX_STATUS_FEATURE_ABORT;
 			msg->flags = dst->flags;
+			msg->sequence = dst->sequence;
 			/* Remove it from the wait_queue */
 			list_del_init(&data->list);
 
diff --git a/drivers/media/common/videobuf2/videobuf2-dma-sg.c b/drivers/media/common/videobuf2/videobuf2-dma-sg.c
index 1094575abf95..90acafd9a290 100644
--- a/drivers/media/common/videobuf2/videobuf2-dma-sg.c
+++ b/drivers/media/common/videobuf2/videobuf2-dma-sg.c
@@ -241,6 +241,7 @@ static void *vb2_dma_sg_get_userptr(struct vb2_buffer *vb, struct device *dev,
 	buf->offset = vaddr & ~PAGE_MASK;
 	buf->size = size;
 	buf->dma_sgt = &buf->sg_table;
+	buf->vb = vb;
 	vec = vb2_create_framevec(vaddr, size);
 	if (IS_ERR(vec))
 		goto userptr_fail_pfnvec;
@@ -642,6 +643,7 @@ static void *vb2_dma_sg_attach_dmabuf(struct vb2_buffer *vb, struct device *dev,
 	buf->dma_dir = vb->vb2_queue->dma_dir;
 	buf->size = size;
 	buf->db_attach = dba;
+	buf->vb = vb;
 
 	return buf;
 }
diff --git a/drivers/media/i2c/hi846.c b/drivers/media/i2c/hi846.c
index 822ce3021fde..48909faeced4 100644
--- a/drivers/media/i2c/hi846.c
+++ b/drivers/media/i2c/hi846.c
@@ -7,9 +7,9 @@
 #include <linux/gpio/consumer.h>
 #include <linux/i2c.h>
 #include <linux/module.h>
-#include <linux/of_graph.h>
 #include <linux/pm_runtime.h>
 #include <linux/pm.h>
+#include <linux/property.h>
 #include <linux/regulator/consumer.h>
 #include <media/v4l2-ctrls.h>
 #include <media/v4l2-device.h>
@@ -2176,7 +2176,7 @@ static struct i2c_driver hi846_i2c_driver = {
 	.driver = {
 		.name = "hi846",
 		.pm = &hi846_pm_ops,
-		.of_match_table = of_match_ptr(hi846_of_match),
+		.of_match_table = hi846_of_match,
 	},
 	.probe_new = hi846_probe,
 	.remove = hi846_remove,
diff --git a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c
index 8176769a89fa..0f3d6b5667b0 100644
--- a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c
+++ b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c
@@ -751,10 +751,6 @@ static int put_v4l2_ext_controls32(struct v4l2_ext_controls *p64,
 /*
  * x86 is the only compat architecture with different struct alignment
  * between 32-bit and 64-bit tasks.
- *
- * On all other architectures, v4l2_event32 and v4l2_event32_time32 are
- * the same as v4l2_event and v4l2_event_time32, so we can use the native
- * handlers, converting v4l2_event to v4l2_event_time32 if necessary.
  */
 struct v4l2_event32 {
 	__u32				type;
@@ -772,21 +768,6 @@ struct v4l2_event32 {
 	__u32				reserved[8];
 };
 
-#ifdef CONFIG_COMPAT_32BIT_TIME
-struct v4l2_event32_time32 {
-	__u32				type;
-	union {
-		compat_s64		value64;
-		__u8			data[64];
-	} u;
-	__u32				pending;
-	__u32				sequence;
-	struct old_timespec32		timestamp;
-	__u32				id;
-	__u32				reserved[8];
-};
-#endif
-
 static int put_v4l2_event32(struct v4l2_event *p64,
 			    struct v4l2_event32 __user *p32)
 {
@@ -802,7 +783,22 @@ static int put_v4l2_event32(struct v4l2_event *p64,
 	return 0;
 }
 
+#endif
+
 #ifdef CONFIG_COMPAT_32BIT_TIME
+struct v4l2_event32_time32 {
+	__u32				type;
+	union {
+		compat_s64		value64;
+		__u8			data[64];
+	} u;
+	__u32				pending;
+	__u32				sequence;
+	struct old_timespec32		timestamp;
+	__u32				id;
+	__u32				reserved[8];
+};
+
 static int put_v4l2_event32_time32(struct v4l2_event *p64,
 				   struct v4l2_event32_time32 __user *p32)
 {
@@ -818,7 +814,6 @@ static int put_v4l2_event32_time32(struct v4l2_event *p64,
 	return 0;
 }
 #endif
-#endif
 
 struct v4l2_edid32 {
 	__u32 pad;
@@ -880,9 +875,7 @@ static int put_v4l2_edid32(struct v4l2_edid *p64,
 #define VIDIOC_QUERYBUF32_TIME32	_IOWR('V',  9, struct v4l2_buffer32_time32)
 #define VIDIOC_QBUF32_TIME32		_IOWR('V', 15, struct v4l2_buffer32_time32)
 #define VIDIOC_DQBUF32_TIME32		_IOWR('V', 17, struct v4l2_buffer32_time32)
-#ifdef CONFIG_X86_64
 #define	VIDIOC_DQEVENT32_TIME32		_IOR ('V', 89, struct v4l2_event32_time32)
-#endif
 #define VIDIOC_PREPARE_BUF32_TIME32	_IOWR('V', 93, struct v4l2_buffer32_time32)
 #endif
 
@@ -936,11 +929,11 @@ unsigned int v4l2_compat_translate_cmd(unsigned int cmd)
 #ifdef CONFIG_X86_64
 	case VIDIOC_DQEVENT32:
 		return VIDIOC_DQEVENT;
+#endif
 #ifdef CONFIG_COMPAT_32BIT_TIME
 	case VIDIOC_DQEVENT32_TIME32:
 		return VIDIOC_DQEVENT;
 #endif
-#endif
 	}
 	return cmd;
 }
@@ -1032,11 +1025,11 @@ int v4l2_compat_put_user(void __user *arg, void *parg, unsigned int cmd)
 #ifdef CONFIG_X86_64
 	case VIDIOC_DQEVENT32:
 		return put_v4l2_event32(parg, arg);
+#endif
 #ifdef CONFIG_COMPAT_32BIT_TIME
 	case VIDIOC_DQEVENT32_TIME32:
 		return put_v4l2_event32_time32(parg, arg);
 #endif
-#endif
 	}
 	return 0;
 }
diff --git a/drivers/memory/mtk-smi.c b/drivers/memory/mtk-smi.c
index b883dcc0bbfa..e201e5976f34 100644
--- a/drivers/memory/mtk-smi.c
+++ b/drivers/memory/mtk-smi.c
@@ -241,7 +241,7 @@ static void mtk_smi_larb_config_port_gen2_general(struct device *dev)
 {
 	struct mtk_smi_larb *larb = dev_get_drvdata(dev);
 	u32 reg, flags_general = larb->larb_gen->flags_general;
-	const u8 *larbostd = larb->larb_gen->ostd[larb->larbid];
+	const u8 *larbostd = larb->larb_gen->ostd ? larb->larb_gen->ostd[larb->larbid] : NULL;
 	int i;
 
 	if (BIT(larb->larbid) & larb->larb_gen->larb_direct_to_common_mask)
diff --git a/drivers/misc/cardreader/rtsx_pcr.c b/drivers/misc/cardreader/rtsx_pcr.c
index 8c72eb590f79..6ac509c1821c 100644
--- a/drivers/misc/cardreader/rtsx_pcr.c
+++ b/drivers/misc/cardreader/rtsx_pcr.c
@@ -1803,8 +1803,6 @@ static int rtsx_pci_runtime_suspend(struct device *device)
 	mutex_lock(&pcr->pcr_mutex);
 	rtsx_pci_power_off(pcr, HOST_ENTER_S3);
 
-	free_irq(pcr->irq, (void *)pcr);
-
 	mutex_unlock(&pcr->pcr_mutex);
 
 	pcr->is_runtime_suspended = true;
@@ -1825,8 +1823,6 @@ static int rtsx_pci_runtime_resume(struct device *device)
 	mutex_lock(&pcr->pcr_mutex);
 
 	rtsx_pci_write_register(pcr, HOST_SLEEP_STATE, 0x03, 0x00);
-	rtsx_pci_acquire_irq(pcr);
-	synchronize_irq(pcr->irq);
 
 	if (pcr->ops->fetch_vendor_settings)
 		pcr->ops->fetch_vendor_settings(pcr);
diff --git a/drivers/misc/eeprom/at25.c b/drivers/misc/eeprom/at25.c
index 632325474233..b38978a3b3ff 100644
--- a/drivers/misc/eeprom/at25.c
+++ b/drivers/misc/eeprom/at25.c
@@ -376,7 +376,6 @@ MODULE_DEVICE_TABLE(spi, at25_spi_ids);
 static int at25_probe(struct spi_device *spi)
 {
 	struct at25_data	*at25 = NULL;
-	struct spi_eeprom	chip;
 	int			err;
 	int			sr;
 	u8 id[FM25_ID_LEN];
@@ -389,15 +388,18 @@ static int at25_probe(struct spi_device *spi)
 	if (match && !strcmp(match->compatible, "cypress,fm25"))
 		is_fram = 1;
 
+	at25 = devm_kzalloc(&spi->dev, sizeof(struct at25_data), GFP_KERNEL);
+	if (!at25)
+		return -ENOMEM;
+
 	/* Chip description */
-	if (!spi->dev.platform_data) {
-		if (!is_fram) {
-			err = at25_fw_to_chip(&spi->dev, &chip);
-			if (err)
-				return err;
-		}
-	} else
-		chip = *(struct spi_eeprom *)spi->dev.platform_data;
+	if (spi->dev.platform_data) {
+		memcpy(&at25->chip, spi->dev.platform_data, sizeof(at25->chip));
+	} else if (!is_fram) {
+		err = at25_fw_to_chip(&spi->dev, &at25->chip);
+		if (err)
+			return err;
+	}
 
 	/* Ping the chip ... the status register is pretty portable,
 	 * unlike probing manufacturer IDs.  We do expect that system
@@ -409,12 +411,7 @@ static int at25_probe(struct spi_device *spi)
 		return -ENXIO;
 	}
 
-	at25 = devm_kzalloc(&spi->dev, sizeof(struct at25_data), GFP_KERNEL);
-	if (!at25)
-		return -ENOMEM;
-
 	mutex_init(&at25->lock);
-	at25->chip = chip;
 	at25->spi = spi;
 	spi_set_drvdata(spi, at25);
 
@@ -431,7 +428,7 @@ static int at25_probe(struct spi_device *spi)
 			dev_err(&spi->dev, "Error: unsupported size (id %02x)\n", id[7]);
 			return -ENODEV;
 		}
-		chip.byte_len = int_pow(2, id[7] - 0x21 + 4) * 1024;
+		at25->chip.byte_len = int_pow(2, id[7] - 0x21 + 4) * 1024;
 
 		if (at25->chip.byte_len > 64 * 1024)
 			at25->chip.flags |= EE_ADDR3;
@@ -464,7 +461,7 @@ static int at25_probe(struct spi_device *spi)
 	at25->nvmem_config.type = is_fram ? NVMEM_TYPE_FRAM : NVMEM_TYPE_EEPROM;
 	at25->nvmem_config.name = dev_name(&spi->dev);
 	at25->nvmem_config.dev = &spi->dev;
-	at25->nvmem_config.read_only = chip.flags & EE_READONLY;
+	at25->nvmem_config.read_only = at25->chip.flags & EE_READONLY;
 	at25->nvmem_config.root_only = true;
 	at25->nvmem_config.owner = THIS_MODULE;
 	at25->nvmem_config.compat = true;
@@ -474,17 +471,18 @@ static int at25_probe(struct spi_device *spi)
 	at25->nvmem_config.priv = at25;
 	at25->nvmem_config.stride = 1;
 	at25->nvmem_config.word_size = 1;
-	at25->nvmem_config.size = chip.byte_len;
+	at25->nvmem_config.size = at25->chip.byte_len;
 
 	at25->nvmem = devm_nvmem_register(&spi->dev, &at25->nvmem_config);
 	if (IS_ERR(at25->nvmem))
 		return PTR_ERR(at25->nvmem);
 
 	dev_info(&spi->dev, "%d %s %s %s%s, pagesize %u\n",
-		 (chip.byte_len < 1024) ? chip.byte_len : (chip.byte_len / 1024),
-		 (chip.byte_len < 1024) ? "Byte" : "KByte",
+		 (at25->chip.byte_len < 1024) ?
+			at25->chip.byte_len : (at25->chip.byte_len / 1024),
+		 (at25->chip.byte_len < 1024) ? "Byte" : "KByte",
 		 at25->chip.name, is_fram ? "fram" : "eeprom",
-		 (chip.flags & EE_READONLY) ? " (readonly)" : "",
+		 (at25->chip.flags & EE_READONLY) ? " (readonly)" : "",
 		 at25->chip.page_size);
 	return 0;
 }
diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c
index 39aca7753719..4ccbf43e6bfa 100644
--- a/drivers/misc/fastrpc.c
+++ b/drivers/misc/fastrpc.c
@@ -719,16 +719,18 @@ static int fastrpc_get_meta_size(struct fastrpc_invoke_ctx *ctx)
 static u64 fastrpc_get_payload_size(struct fastrpc_invoke_ctx *ctx, int metalen)
 {
 	u64 size = 0;
-	int i;
+	int oix;
 
 	size = ALIGN(metalen, FASTRPC_ALIGN);
-	for (i = 0; i < ctx->nscalars; i++) {
+	for (oix = 0; oix < ctx->nbufs; oix++) {
+		int i = ctx->olaps[oix].raix;
+
 		if (ctx->args[i].fd == 0 || ctx->args[i].fd == -1) {
 
-			if (ctx->olaps[i].offset == 0)
+			if (ctx->olaps[oix].offset == 0)
 				size = ALIGN(size, FASTRPC_ALIGN);
 
-			size += (ctx->olaps[i].mend - ctx->olaps[i].mstart);
+			size += (ctx->olaps[oix].mend - ctx->olaps[oix].mstart);
 		}
 	}
 
diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
index 240c5af793dc..368f10405e13 100644
--- a/drivers/mmc/core/core.c
+++ b/drivers/mmc/core/core.c
@@ -2264,7 +2264,7 @@ void mmc_start_host(struct mmc_host *host)
 	_mmc_detect_change(host, 0, false);
 }
 
-void mmc_stop_host(struct mmc_host *host)
+void __mmc_stop_host(struct mmc_host *host)
 {
 	if (host->slot.cd_irq >= 0) {
 		mmc_gpio_set_cd_wake(host, false);
@@ -2273,6 +2273,11 @@ void mmc_stop_host(struct mmc_host *host)
 
 	host->rescan_disable = 1;
 	cancel_delayed_work_sync(&host->detect);
+}
+
+void mmc_stop_host(struct mmc_host *host)
+{
+	__mmc_stop_host(host);
 
 	/* clear pm flags now and let card drivers set them as needed */
 	host->pm_flags = 0;
diff --git a/drivers/mmc/core/core.h b/drivers/mmc/core/core.h
index 7931a4f0137d..f5f3f623ea49 100644
--- a/drivers/mmc/core/core.h
+++ b/drivers/mmc/core/core.h
@@ -70,6 +70,7 @@ static inline void mmc_delay(unsigned int ms)
 
 void mmc_rescan(struct work_struct *work);
 void mmc_start_host(struct mmc_host *host);
+void __mmc_stop_host(struct mmc_host *host);
 void mmc_stop_host(struct mmc_host *host);
 
 void _mmc_detect_change(struct mmc_host *host, unsigned long delay,
diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c
index d4683b1d263f..cf140f4ec864 100644
--- a/drivers/mmc/core/host.c
+++ b/drivers/mmc/core/host.c
@@ -80,9 +80,18 @@ static void mmc_host_classdev_release(struct device *dev)
 	kfree(host);
 }
 
+static int mmc_host_classdev_shutdown(struct device *dev)
+{
+	struct mmc_host *host = cls_dev_to_mmc_host(dev);
+
+	__mmc_stop_host(host);
+	return 0;
+}
+
 static struct class mmc_host_class = {
 	.name		= "mmc_host",
 	.dev_release	= mmc_host_classdev_release,
+	.shutdown_pre	= mmc_host_classdev_shutdown,
 	.pm		= MMC_HOST_CLASS_DEV_PM_OPS,
 };
 
diff --git a/drivers/mmc/host/meson-mx-sdhc-mmc.c b/drivers/mmc/host/meson-mx-sdhc-mmc.c
index 7cd9c0ec2fcf..8fdd0bbbfa21 100644
--- a/drivers/mmc/host/meson-mx-sdhc-mmc.c
+++ b/drivers/mmc/host/meson-mx-sdhc-mmc.c
@@ -135,6 +135,7 @@ static void meson_mx_sdhc_start_cmd(struct mmc_host *mmc,
 				    struct mmc_command *cmd)
 {
 	struct meson_mx_sdhc_host *host = mmc_priv(mmc);
+	bool manual_stop = false;
 	u32 ictl, send;
 	int pack_len;
 
@@ -172,12 +173,27 @@ static void meson_mx_sdhc_start_cmd(struct mmc_host *mmc,
 		else
 			/* software flush: */
 			ictl |= MESON_SDHC_ICTL_DATA_XFER_OK;
+
+		/*
+		 * Mimic the logic from the vendor driver where (only)
+		 * SD_IO_RW_EXTENDED commands with more than one block set the
+		 * MESON_SDHC_MISC_MANUAL_STOP bit. This fixes the firmware
+		 * download in the brcmfmac driver for a BCM43362/1 card.
+		 * Without this sdio_memcpy_toio() (with a size of 219557
+		 * bytes) times out if MESON_SDHC_MISC_MANUAL_STOP is not set.
+		 */
+		manual_stop = cmd->data->blocks > 1 &&
+			      cmd->opcode == SD_IO_RW_EXTENDED;
 	} else {
 		pack_len = 0;
 
 		ictl |= MESON_SDHC_ICTL_RESP_OK;
 	}
 
+	regmap_update_bits(host->regmap, MESON_SDHC_MISC,
+			   MESON_SDHC_MISC_MANUAL_STOP,
+			   manual_stop ? MESON_SDHC_MISC_MANUAL_STOP : 0);
+
 	if (cmd->opcode == MMC_STOP_TRANSMISSION)
 		send |= MESON_SDHC_SEND_DATA_STOP;
 
diff --git a/drivers/mmc/host/mmc_spi.c b/drivers/mmc/host/mmc_spi.c
index f4c8e1a61f53..b431cdd27353 100644
--- a/drivers/mmc/host/mmc_spi.c
+++ b/drivers/mmc/host/mmc_spi.c
@@ -1514,6 +1514,12 @@ static int mmc_spi_remove(struct spi_device *spi)
 	return 0;
 }
 
+static const struct spi_device_id mmc_spi_dev_ids[] = {
+	{ "mmc-spi-slot"},
+	{ },
+};
+MODULE_DEVICE_TABLE(spi, mmc_spi_dev_ids);
+
 static const struct of_device_id mmc_spi_of_match_table[] = {
 	{ .compatible = "mmc-spi-slot", },
 	{},
@@ -1525,6 +1531,7 @@ static struct spi_driver mmc_spi_driver = {
 		.name =		"mmc_spi",
 		.of_match_table = mmc_spi_of_match_table,
 	},
+	.id_table =	mmc_spi_dev_ids,
 	.probe =	mmc_spi_probe,
 	.remove =	mmc_spi_remove,
 };
diff --git a/drivers/mmc/host/mmci_stm32_sdmmc.c b/drivers/mmc/host/mmci_stm32_sdmmc.c
index fdaa11f92fe6..a75d3dd34d18 100644
--- a/drivers/mmc/host/mmci_stm32_sdmmc.c
+++ b/drivers/mmc/host/mmci_stm32_sdmmc.c
@@ -441,6 +441,8 @@ static int sdmmc_dlyb_phase_tuning(struct mmci_host *host, u32 opcode)
 		return -EINVAL;
 	}
 
+	writel_relaxed(0, dlyb->base + DLYB_CR);
+
 	phase = end_of_len - max_len / 2;
 	sdmmc_dlyb_set_cfgr(dlyb, dlyb->unit, phase, false);
 
diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c
index 943940b44e83..632775217d35 100644
--- a/drivers/mmc/host/mtk-sd.c
+++ b/drivers/mmc/host/mtk-sd.c
@@ -2291,8 +2291,10 @@ static int msdc_execute_hs400_tuning(struct mmc_host *mmc, struct mmc_card *card
 			sdr_set_field(host->base + PAD_DS_TUNE,
 				      PAD_DS_TUNE_DLY1, i);
 		ret = mmc_get_ext_csd(card, &ext_csd);
-		if (!ret)
+		if (!ret) {
 			result_dly1 |= (1 << i);
+			kfree(ext_csd);
+		}
 	}
 	host->hs400_tuning = false;
 
diff --git a/drivers/mmc/host/renesas_sdhi_core.c b/drivers/mmc/host/renesas_sdhi_core.c
index a4407f391f66..f5b2684ad805 100644
--- a/drivers/mmc/host/renesas_sdhi_core.c
+++ b/drivers/mmc/host/renesas_sdhi_core.c
@@ -673,7 +673,7 @@ static int renesas_sdhi_execute_tuning(struct mmc_host *mmc, u32 opcode)
 
 	/* Issue CMD19 twice for each tap */
 	for (i = 0; i < 2 * priv->tap_num; i++) {
-		int cmd_error;
+		int cmd_error = 0;
 
 		/* Set sampling clock position */
 		sd_scc_write32(host, priv, SH_MOBILE_SDHI_SCC_TAPSET, i % priv->tap_num);
diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c
index afaf33707d46..764ee1b761d9 100644
--- a/drivers/mmc/host/sdhci-esdhc-imx.c
+++ b/drivers/mmc/host/sdhci-esdhc-imx.c
@@ -310,7 +310,6 @@ static struct esdhc_soc_data usdhc_imx8qxp_data = {
 	.flags = ESDHC_FLAG_USDHC | ESDHC_FLAG_STD_TUNING
 			| ESDHC_FLAG_HAVE_CAP1 | ESDHC_FLAG_HS200
 			| ESDHC_FLAG_HS400 | ESDHC_FLAG_HS400_ES
-			| ESDHC_FLAG_CQHCI
 			| ESDHC_FLAG_STATE_LOST_IN_LPMODE
 			| ESDHC_FLAG_CLK_RATE_LOST_IN_PM_RUNTIME,
 };
@@ -319,7 +318,6 @@ static struct esdhc_soc_data usdhc_imx8mm_data = {
 	.flags = ESDHC_FLAG_USDHC | ESDHC_FLAG_STD_TUNING
 			| ESDHC_FLAG_HAVE_CAP1 | ESDHC_FLAG_HS200
 			| ESDHC_FLAG_HS400 | ESDHC_FLAG_HS400_ES
-			| ESDHC_FLAG_CQHCI
 			| ESDHC_FLAG_STATE_LOST_IN_LPMODE,
 };
 
diff --git a/drivers/mmc/host/sdhci-tegra.c b/drivers/mmc/host/sdhci-tegra.c
index a5001875876b..9762ffab2e23 100644
--- a/drivers/mmc/host/sdhci-tegra.c
+++ b/drivers/mmc/host/sdhci-tegra.c
@@ -356,23 +356,6 @@ static void tegra_sdhci_set_tap(struct sdhci_host *host, unsigned int tap)
 	}
 }
 
-static void tegra_sdhci_hs400_enhanced_strobe(struct mmc_host *mmc,
-					      struct mmc_ios *ios)
-{
-	struct sdhci_host *host = mmc_priv(mmc);
-	u32 val;
-
-	val = sdhci_readl(host, SDHCI_TEGRA_VENDOR_SYS_SW_CTRL);
-
-	if (ios->enhanced_strobe)
-		val |= SDHCI_TEGRA_SYS_SW_CTRL_ENHANCED_STROBE;
-	else
-		val &= ~SDHCI_TEGRA_SYS_SW_CTRL_ENHANCED_STROBE;
-
-	sdhci_writel(host, val, SDHCI_TEGRA_VENDOR_SYS_SW_CTRL);
-
-}
-
 static void tegra_sdhci_reset(struct sdhci_host *host, u8 mask)
 {
 	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
@@ -793,6 +776,32 @@ static void tegra_sdhci_set_clock(struct sdhci_host *host, unsigned int clock)
 	}
 }
 
+static void tegra_sdhci_hs400_enhanced_strobe(struct mmc_host *mmc,
+					      struct mmc_ios *ios)
+{
+	struct sdhci_host *host = mmc_priv(mmc);
+	u32 val;
+
+	val = sdhci_readl(host, SDHCI_TEGRA_VENDOR_SYS_SW_CTRL);
+
+	if (ios->enhanced_strobe) {
+		val |= SDHCI_TEGRA_SYS_SW_CTRL_ENHANCED_STROBE;
+		/*
+		 * When CMD13 is sent from mmc_select_hs400es() after
+		 * switching to HS400ES mode, the bus is operating at
+		 * either MMC_HIGH_26_MAX_DTR or MMC_HIGH_52_MAX_DTR.
+		 * To meet Tegra SDHCI requirement at HS400ES mode, force SDHCI
+		 * interface clock to MMC_HS200_MAX_DTR (200 MHz) so that host
+		 * controller CAR clock and the interface clock are rate matched.
+		 */
+		tegra_sdhci_set_clock(host, MMC_HS200_MAX_DTR);
+	} else {
+		val &= ~SDHCI_TEGRA_SYS_SW_CTRL_ENHANCED_STROBE;
+	}
+
+	sdhci_writel(host, val, SDHCI_TEGRA_VENDOR_SYS_SW_CTRL);
+}
+
 static unsigned int tegra_sdhci_get_max_clock(struct sdhci_host *host)
 {
 	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index 269c86569402..07c6da1f2f0f 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -771,7 +771,19 @@ static void sdhci_adma_table_pre(struct sdhci_host *host,
 			len -= offset;
 		}
 
-		BUG_ON(len > 65536);
+		/*
+		 * The block layer forces a minimum segment size of PAGE_SIZE,
+		 * so 'len' can be too big here if PAGE_SIZE >= 64KiB. Write
+		 * multiple descriptors, noting that the ADMA table is sized
+		 * for 4KiB chunks anyway, so it will be big enough.
+		 */
+		while (len > host->max_adma) {
+			int n = 32 * 1024; /* 32KiB*/
+
+			__sdhci_adma_write_desc(host, &desc, addr, n, ADMA2_TRAN_VALID);
+			addr += n;
+			len -= n;
+		}
 
 		/* tran, valid */
 		if (len)
@@ -3968,6 +3980,7 @@ struct sdhci_host *sdhci_alloc_host(struct device *dev,
 	 * descriptor for each segment, plus 1 for a nop end descriptor.
 	 */
 	host->adma_table_cnt = SDHCI_MAX_SEGS * 2 + 1;
+	host->max_adma = 65536;
 
 	host->max_timeout_count = 0xE;
 
@@ -4633,10 +4646,12 @@ int sdhci_setup_host(struct sdhci_host *host)
 	 * be larger than 64 KiB though.
 	 */
 	if (host->flags & SDHCI_USE_ADMA) {
-		if (host->quirks & SDHCI_QUIRK_BROKEN_ADMA_ZEROLEN_DESC)
+		if (host->quirks & SDHCI_QUIRK_BROKEN_ADMA_ZEROLEN_DESC) {
+			host->max_adma = 65532; /* 32-bit alignment */
 			mmc->max_seg_size = 65535;
-		else
+		} else {
 			mmc->max_seg_size = 65536;
+		}
 	} else {
 		mmc->max_seg_size = mmc->max_req_size;
 	}
diff --git a/drivers/mmc/host/sdhci.h b/drivers/mmc/host/sdhci.h
index bb883553d3b4..d7929d725730 100644
--- a/drivers/mmc/host/sdhci.h
+++ b/drivers/mmc/host/sdhci.h
@@ -340,7 +340,8 @@ struct sdhci_adma2_64_desc {
 
 /*
  * Maximum segments assuming a 512KiB maximum requisition size and a minimum
- * 4KiB page size.
+ * 4KiB page size. Note this also allows enough for multiple descriptors in
+ * case of PAGE_SIZE >= 64KiB.
  */
 #define SDHCI_MAX_SEGS		128
 
@@ -543,6 +544,7 @@ struct sdhci_host {
 	unsigned int blocks;	/* remaining PIO blocks */
 
 	int sg_count;		/* Mapped sg entries */
+	int max_adma;		/* Max. length in ADMA descriptor */
 
 	void *adma_table;	/* ADMA descriptor table */
 	void *align_buffer;	/* Bounce buffer */
diff --git a/drivers/mtd/devices/mtd_dataflash.c b/drivers/mtd/devices/mtd_dataflash.c
index 9802e265fca8..2b317ed6c103 100644
--- a/drivers/mtd/devices/mtd_dataflash.c
+++ b/drivers/mtd/devices/mtd_dataflash.c
@@ -96,6 +96,13 @@ struct dataflash {
 	struct mtd_info		mtd;
 };
 
+static const struct spi_device_id dataflash_dev_ids[] = {
+	{ "at45" },
+	{ "dataflash" },
+	{ },
+};
+MODULE_DEVICE_TABLE(spi, dataflash_dev_ids);
+
 #ifdef CONFIG_OF
 static const struct of_device_id dataflash_dt_ids[] = {
 	{ .compatible = "atmel,at45", },
@@ -927,6 +934,7 @@ static struct spi_driver dataflash_driver = {
 		.name		= "mtd_dataflash",
 		.of_match_table = of_match_ptr(dataflash_dt_ids),
 	},
+	.id_table = dataflash_dev_ids,
 
 	.probe		= dataflash_probe,
 	.remove		= dataflash_remove,
diff --git a/drivers/mtd/nand/raw/Kconfig b/drivers/mtd/nand/raw/Kconfig
index 67b7cb67c030..0a45d3c6c15b 100644
--- a/drivers/mtd/nand/raw/Kconfig
+++ b/drivers/mtd/nand/raw/Kconfig
@@ -26,7 +26,7 @@ config MTD_NAND_DENALI_PCI
 config MTD_NAND_DENALI_DT
 	tristate "Denali NAND controller as a DT device"
 	select MTD_NAND_DENALI
-	depends on HAS_DMA && HAVE_CLK && OF
+	depends on HAS_DMA && HAVE_CLK && OF && HAS_IOMEM
 	help
 	  Enable the driver for NAND flash on platforms using a Denali NAND
 	  controller as a DT device.
diff --git a/drivers/mtd/nand/raw/fsmc_nand.c b/drivers/mtd/nand/raw/fsmc_nand.c
index 658f0cbe7ce8..6b2bda815b88 100644
--- a/drivers/mtd/nand/raw/fsmc_nand.c
+++ b/drivers/mtd/nand/raw/fsmc_nand.c
@@ -15,6 +15,7 @@
 
 #include <linux/clk.h>
 #include <linux/completion.h>
+#include <linux/delay.h>
 #include <linux/dmaengine.h>
 #include <linux/dma-direction.h>
 #include <linux/dma-mapping.h>
@@ -93,6 +94,14 @@
 
 #define FSMC_BUSY_WAIT_TIMEOUT	(1 * HZ)
 
+/*
+ * According to SPEAr300 Reference Manual (RM0082)
+ *  TOUDEL = 7ns (Output delay from the flip-flops to the board)
+ *  TINDEL = 5ns (Input delay from the board to the flipflop)
+ */
+#define TOUTDEL	7000
+#define TINDEL	5000
+
 struct fsmc_nand_timings {
 	u8 tclr;
 	u8 tar;
@@ -277,7 +286,7 @@ static int fsmc_calc_timings(struct fsmc_nand_data *host,
 {
 	unsigned long hclk = clk_get_rate(host->clk);
 	unsigned long hclkn = NSEC_PER_SEC / hclk;
-	u32 thiz, thold, twait, tset;
+	u32 thiz, thold, twait, tset, twait_min;
 
 	if (sdrt->tRC_min < 30000)
 		return -EOPNOTSUPP;
@@ -309,13 +318,6 @@ static int fsmc_calc_timings(struct fsmc_nand_data *host,
 	else if (tims->thold > FSMC_THOLD_MASK)
 		tims->thold = FSMC_THOLD_MASK;
 
-	twait = max(sdrt->tRP_min, sdrt->tWP_min);
-	tims->twait = DIV_ROUND_UP(twait / 1000, hclkn) - 1;
-	if (tims->twait == 0)
-		tims->twait = 1;
-	else if (tims->twait > FSMC_TWAIT_MASK)
-		tims->twait = FSMC_TWAIT_MASK;
-
 	tset = max(sdrt->tCS_min - sdrt->tWP_min,
 		   sdrt->tCEA_max - sdrt->tREA_max);
 	tims->tset = DIV_ROUND_UP(tset / 1000, hclkn) - 1;
@@ -324,6 +326,21 @@ static int fsmc_calc_timings(struct fsmc_nand_data *host,
 	else if (tims->tset > FSMC_TSET_MASK)
 		tims->tset = FSMC_TSET_MASK;
 
+	/*
+	 * According to SPEAr300 Reference Manual (RM0082) which gives more
+	 * information related to FSMSC timings than the SPEAr600 one (RM0305),
+	 *   twait >= tCEA - (tset * TCLK) + TOUTDEL + TINDEL
+	 */
+	twait_min = sdrt->tCEA_max - ((tims->tset + 1) * hclkn * 1000)
+		    + TOUTDEL + TINDEL;
+	twait = max3(sdrt->tRP_min, sdrt->tWP_min, twait_min);
+
+	tims->twait = DIV_ROUND_UP(twait / 1000, hclkn) - 1;
+	if (tims->twait == 0)
+		tims->twait = 1;
+	else if (tims->twait > FSMC_TWAIT_MASK)
+		tims->twait = FSMC_TWAIT_MASK;
+
 	return 0;
 }
 
@@ -664,6 +681,9 @@ static int fsmc_exec_op(struct nand_chip *chip, const struct nand_operation *op,
 						instr->ctx.waitrdy.timeout_ms);
 			break;
 		}
+
+		if (instr->delay_ns)
+			ndelay(instr->delay_ns);
 	}
 
 	return ret;
diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index 3d6c6e880520..a130320de412 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -926,7 +926,7 @@ int nand_choose_best_sdr_timings(struct nand_chip *chip,
 				 struct nand_sdr_timings *spec_timings)
 {
 	const struct nand_controller_ops *ops = chip->controller->ops;
-	int best_mode = 0, mode, ret;
+	int best_mode = 0, mode, ret = -EOPNOTSUPP;
 
 	iface->type = NAND_SDR_IFACE;
 
@@ -977,7 +977,7 @@ int nand_choose_best_nvddr_timings(struct nand_chip *chip,
 				   struct nand_nvddr_timings *spec_timings)
 {
 	const struct nand_controller_ops *ops = chip->controller->ops;
-	int best_mode = 0, mode, ret;
+	int best_mode = 0, mode, ret = -EOPNOTSUPP;
 
 	iface->type = NAND_NVDDR_IFACE;
 
@@ -1837,7 +1837,7 @@ int nand_erase_op(struct nand_chip *chip, unsigned int eraseblock)
 			NAND_OP_CMD(NAND_CMD_ERASE1, 0),
 			NAND_OP_ADDR(2, addrs, 0),
 			NAND_OP_CMD(NAND_CMD_ERASE2,
-				    NAND_COMMON_TIMING_MS(conf, tWB_max)),
+				    NAND_COMMON_TIMING_NS(conf, tWB_max)),
 			NAND_OP_WAIT_RDY(NAND_COMMON_TIMING_MS(conf, tBERS_max),
 					 0),
 		};
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index 10506a4b66ef..6cccc3dc00bc 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -567,9 +567,7 @@ config XEN_NETDEV_BACKEND
 config VMXNET3
 	tristate "VMware VMXNET3 ethernet driver"
 	depends on PCI && INET
-	depends on !(PAGE_SIZE_64KB || ARM64_64K_PAGES || \
-		     IA64_PAGE_SIZE_64KB || PARISC_PAGE_SIZE_64KB || \
-		     PPC_64K_PAGES)
+	depends on PAGE_SIZE_LESS_THAN_64KB
 	help
 	  This driver supports VMware's vmxnet3 virtual ethernet NIC.
 	  To compile this driver as a module, choose M here: the
diff --git a/drivers/net/amt.c b/drivers/net/amt.c
index 47a04c330885..b732ee9a50ef 100644
--- a/drivers/net/amt.c
+++ b/drivers/net/amt.c
@@ -3286,7 +3286,7 @@ static void __exit amt_fini(void)
 {
 	rtnl_link_unregister(&amt_link_ops);
 	unregister_netdevice_notifier(&amt_notifier_block);
-	cancel_delayed_work(&source_gc_wq);
+	cancel_delayed_work_sync(&source_gc_wq);
 	__amt_source_gc_work();
 	destroy_workqueue(amt_wq);
 }
diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
index 2ec8e015c7b3..533e476988f2 100644
--- a/drivers/net/bonding/bond_alb.c
+++ b/drivers/net/bonding/bond_alb.c
@@ -1501,14 +1501,14 @@ void bond_alb_monitor(struct work_struct *work)
 	struct slave *slave;
 
 	if (!bond_has_slaves(bond)) {
-		bond_info->tx_rebalance_counter = 0;
+		atomic_set(&bond_info->tx_rebalance_counter, 0);
 		bond_info->lp_counter = 0;
 		goto re_arm;
 	}
 
 	rcu_read_lock();
 
-	bond_info->tx_rebalance_counter++;
+	atomic_inc(&bond_info->tx_rebalance_counter);
 	bond_info->lp_counter++;
 
 	/* send learning packets */
@@ -1530,7 +1530,7 @@ void bond_alb_monitor(struct work_struct *work)
 	}
 
 	/* rebalance tx traffic */
-	if (bond_info->tx_rebalance_counter >= BOND_TLB_REBALANCE_TICKS) {
+	if (atomic_read(&bond_info->tx_rebalance_counter) >= BOND_TLB_REBALANCE_TICKS) {
 		bond_for_each_slave_rcu(bond, slave, iter) {
 			tlb_clear_slave(bond, slave, 1);
 			if (slave == rcu_access_pointer(bond->curr_active_slave)) {
@@ -1540,7 +1540,7 @@ void bond_alb_monitor(struct work_struct *work)
 				bond_info->unbalanced_load = 0;
 			}
 		}
-		bond_info->tx_rebalance_counter = 0;
+		atomic_set(&bond_info->tx_rebalance_counter, 0);
 	}
 
 	if (bond_info->rlb_enabled) {
@@ -1610,7 +1610,8 @@ int bond_alb_init_slave(struct bonding *bond, struct slave *slave)
 	tlb_init_slave(slave);
 
 	/* order a rebalance ASAP */
-	bond->alb_info.tx_rebalance_counter = BOND_TLB_REBALANCE_TICKS;
+	atomic_set(&bond->alb_info.tx_rebalance_counter,
+		   BOND_TLB_REBALANCE_TICKS);
 
 	if (bond->alb_info.rlb_enabled)
 		bond->alb_info.rlb_rebalance = 1;
@@ -1647,7 +1648,8 @@ void bond_alb_handle_link_change(struct bonding *bond, struct slave *slave, char
 			rlb_clear_slave(bond, slave);
 	} else if (link == BOND_LINK_UP) {
 		/* order a rebalance ASAP */
-		bond_info->tx_rebalance_counter = BOND_TLB_REBALANCE_TICKS;
+		atomic_set(&bond_info->tx_rebalance_counter,
+			   BOND_TLB_REBALANCE_TICKS);
 		if (bond->alb_info.rlb_enabled) {
 			bond->alb_info.rlb_rebalance = 1;
 			/* If the updelay module parameter is smaller than the
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index a8fde3bc458f..b93337b5a721 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -1526,7 +1526,7 @@ static int bond_option_ad_actor_system_set(struct bonding *bond,
 		mac = (u8 *)&newval->value;
 	}
 
-	if (!is_valid_ether_addr(mac))
+	if (is_multicast_ether_addr(mac))
 		goto err;
 
 	netdev_dbg(bond->dev, "Setting ad_actor_system to %pM\n", mac);
diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c
index 74d9899fc904..eb74cdf26b88 100644
--- a/drivers/net/can/kvaser_pciefd.c
+++ b/drivers/net/can/kvaser_pciefd.c
@@ -248,6 +248,9 @@ MODULE_DESCRIPTION("CAN driver for Kvaser CAN/PCIe devices");
 #define KVASER_PCIEFD_SPACK_EWLR BIT(23)
 #define KVASER_PCIEFD_SPACK_EPLR BIT(24)
 
+/* Kvaser KCAN_EPACK second word */
+#define KVASER_PCIEFD_EPACK_DIR_TX BIT(0)
+
 struct kvaser_pciefd;
 
 struct kvaser_pciefd_can {
@@ -1285,7 +1288,10 @@ static int kvaser_pciefd_rx_error_frame(struct kvaser_pciefd_can *can,
 
 	can->err_rep_cnt++;
 	can->can.can_stats.bus_error++;
-	stats->rx_errors++;
+	if (p->header[1] & KVASER_PCIEFD_EPACK_DIR_TX)
+		stats->tx_errors++;
+	else
+		stats->rx_errors++;
 
 	can->bec.txerr = bec.txerr;
 	can->bec.rxerr = bec.rxerr;
diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c
index 2470c47b2e31..c2a8421e7845 100644
--- a/drivers/net/can/m_can/m_can.c
+++ b/drivers/net/can/m_can/m_can.c
@@ -204,16 +204,16 @@ enum m_can_reg {
 
 /* Interrupts for version 3.0.x */
 #define IR_ERR_LEC_30X	(IR_STE	| IR_FOE | IR_ACKE | IR_BE | IR_CRCE)
-#define IR_ERR_BUS_30X	(IR_ERR_LEC_30X | IR_WDI | IR_ELO | IR_BEU | \
-			 IR_BEC | IR_TOO | IR_MRAF | IR_TSW | IR_TEFL | \
-			 IR_RF1L | IR_RF0L)
+#define IR_ERR_BUS_30X	(IR_ERR_LEC_30X | IR_WDI | IR_BEU | IR_BEC | \
+			 IR_TOO | IR_MRAF | IR_TSW | IR_TEFL | IR_RF1L | \
+			 IR_RF0L)
 #define IR_ERR_ALL_30X	(IR_ERR_STATE | IR_ERR_BUS_30X)
 
 /* Interrupts for version >= 3.1.x */
 #define IR_ERR_LEC_31X	(IR_PED | IR_PEA)
-#define IR_ERR_BUS_31X      (IR_ERR_LEC_31X | IR_WDI | IR_ELO | IR_BEU | \
-			 IR_BEC | IR_TOO | IR_MRAF | IR_TSW | IR_TEFL | \
-			 IR_RF1L | IR_RF0L)
+#define IR_ERR_BUS_31X      (IR_ERR_LEC_31X | IR_WDI | IR_BEU | IR_BEC | \
+			 IR_TOO | IR_MRAF | IR_TSW | IR_TEFL | IR_RF1L | \
+			 IR_RF0L)
 #define IR_ERR_ALL_31X	(IR_ERR_STATE | IR_ERR_BUS_31X)
 
 /* Interrupt Line Select (ILS) */
@@ -517,7 +517,7 @@ static int m_can_read_fifo(struct net_device *dev, u32 rxfs)
 		err = m_can_fifo_read(cdev, fgi, M_CAN_FIFO_DATA,
 				      cf->data, DIV_ROUND_UP(cf->len, 4));
 		if (err)
-			goto out_fail;
+			goto out_free_skb;
 	}
 
 	/* acknowledge rx fifo 0 */
@@ -532,6 +532,8 @@ static int m_can_read_fifo(struct net_device *dev, u32 rxfs)
 
 	return 0;
 
+out_free_skb:
+	kfree_skb(skb);
 out_fail:
 	netdev_err(dev, "FIFO read returned %d\n", err);
 	return err;
@@ -810,8 +812,6 @@ static void m_can_handle_other_err(struct net_device *dev, u32 irqstatus)
 {
 	if (irqstatus & IR_WDI)
 		netdev_err(dev, "Message RAM Watchdog event due to missing READY\n");
-	if (irqstatus & IR_ELO)
-		netdev_err(dev, "Error Logging Overflow\n");
 	if (irqstatus & IR_BEU)
 		netdev_err(dev, "Bit Error Uncorrected\n");
 	if (irqstatus & IR_BEC)
@@ -1494,20 +1494,32 @@ static int m_can_dev_setup(struct m_can_classdev *cdev)
 	case 30:
 		/* CAN_CTRLMODE_FD_NON_ISO is fixed with M_CAN IP v3.0.x */
 		can_set_static_ctrlmode(dev, CAN_CTRLMODE_FD_NON_ISO);
-		cdev->can.bittiming_const = &m_can_bittiming_const_30X;
-		cdev->can.data_bittiming_const = &m_can_data_bittiming_const_30X;
+		cdev->can.bittiming_const = cdev->bit_timing ?
+			cdev->bit_timing : &m_can_bittiming_const_30X;
+
+		cdev->can.data_bittiming_const = cdev->data_timing ?
+			cdev->data_timing :
+			&m_can_data_bittiming_const_30X;
 		break;
 	case 31:
 		/* CAN_CTRLMODE_FD_NON_ISO is fixed with M_CAN IP v3.1.x */
 		can_set_static_ctrlmode(dev, CAN_CTRLMODE_FD_NON_ISO);
-		cdev->can.bittiming_const = &m_can_bittiming_const_31X;
-		cdev->can.data_bittiming_const = &m_can_data_bittiming_const_31X;
+		cdev->can.bittiming_const = cdev->bit_timing ?
+			cdev->bit_timing : &m_can_bittiming_const_31X;
+
+		cdev->can.data_bittiming_const = cdev->data_timing ?
+			cdev->data_timing :
+			&m_can_data_bittiming_const_31X;
 		break;
 	case 32:
 	case 33:
 		/* Support both MCAN version v3.2.x and v3.3.0 */
-		cdev->can.bittiming_const = &m_can_bittiming_const_31X;
-		cdev->can.data_bittiming_const = &m_can_data_bittiming_const_31X;
+		cdev->can.bittiming_const = cdev->bit_timing ?
+			cdev->bit_timing : &m_can_bittiming_const_31X;
+
+		cdev->can.data_bittiming_const = cdev->data_timing ?
+			cdev->data_timing :
+			&m_can_data_bittiming_const_31X;
 
 		cdev->can.ctrlmode_supported |=
 			(m_can_niso_supported(cdev) ?
diff --git a/drivers/net/can/m_can/m_can.h b/drivers/net/can/m_can/m_can.h
index d18b515e6ccc..2c5d40997168 100644
--- a/drivers/net/can/m_can/m_can.h
+++ b/drivers/net/can/m_can/m_can.h
@@ -85,6 +85,9 @@ struct m_can_classdev {
 	struct sk_buff *tx_skb;
 	struct phy *transceiver;
 
+	const struct can_bittiming_const *bit_timing;
+	const struct can_bittiming_const *data_timing;
+
 	struct m_can_ops *ops;
 
 	int version;
diff --git a/drivers/net/can/m_can/m_can_pci.c b/drivers/net/can/m_can/m_can_pci.c
index 89cc3d41e952..b56a54d6c5a9 100644
--- a/drivers/net/can/m_can/m_can_pci.c
+++ b/drivers/net/can/m_can/m_can_pci.c
@@ -18,9 +18,14 @@
 
 #define M_CAN_PCI_MMIO_BAR		0
 
-#define M_CAN_CLOCK_FREQ_EHL		100000000
 #define CTL_CSR_INT_CTL_OFFSET		0x508
 
+struct m_can_pci_config {
+	const struct can_bittiming_const *bit_timing;
+	const struct can_bittiming_const *data_timing;
+	unsigned int clock_freq;
+};
+
 struct m_can_pci_priv {
 	struct m_can_classdev cdev;
 
@@ -42,8 +47,13 @@ static u32 iomap_read_reg(struct m_can_classdev *cdev, int reg)
 static int iomap_read_fifo(struct m_can_classdev *cdev, int offset, void *val, size_t val_count)
 {
 	struct m_can_pci_priv *priv = cdev_to_priv(cdev);
+	void __iomem *src = priv->base + offset;
 
-	ioread32_rep(priv->base + offset, val, val_count);
+	while (val_count--) {
+		*(unsigned int *)val = ioread32(src);
+		val += 4;
+		src += 4;
+	}
 
 	return 0;
 }
@@ -61,8 +71,13 @@ static int iomap_write_fifo(struct m_can_classdev *cdev, int offset,
 			    const void *val, size_t val_count)
 {
 	struct m_can_pci_priv *priv = cdev_to_priv(cdev);
+	void __iomem *dst = priv->base + offset;
 
-	iowrite32_rep(priv->base + offset, val, val_count);
+	while (val_count--) {
+		iowrite32(*(unsigned int *)val, dst);
+		val += 4;
+		dst += 4;
+	}
 
 	return 0;
 }
@@ -74,9 +89,40 @@ static struct m_can_ops m_can_pci_ops = {
 	.read_fifo = iomap_read_fifo,
 };
 
+static const struct can_bittiming_const m_can_bittiming_const_ehl = {
+	.name = KBUILD_MODNAME,
+	.tseg1_min = 2,		/* Time segment 1 = prop_seg + phase_seg1 */
+	.tseg1_max = 64,
+	.tseg2_min = 1,		/* Time segment 2 = phase_seg2 */
+	.tseg2_max = 128,
+	.sjw_max = 128,
+	.brp_min = 1,
+	.brp_max = 512,
+	.brp_inc = 1,
+};
+
+static const struct can_bittiming_const m_can_data_bittiming_const_ehl = {
+	.name = KBUILD_MODNAME,
+	.tseg1_min = 2,		/* Time segment 1 = prop_seg + phase_seg1 */
+	.tseg1_max = 16,
+	.tseg2_min = 1,		/* Time segment 2 = phase_seg2 */
+	.tseg2_max = 8,
+	.sjw_max = 4,
+	.brp_min = 1,
+	.brp_max = 32,
+	.brp_inc = 1,
+};
+
+static const struct m_can_pci_config m_can_pci_ehl = {
+	.bit_timing = &m_can_bittiming_const_ehl,
+	.data_timing = &m_can_data_bittiming_const_ehl,
+	.clock_freq = 200000000,
+};
+
 static int m_can_pci_probe(struct pci_dev *pci, const struct pci_device_id *id)
 {
 	struct device *dev = &pci->dev;
+	const struct m_can_pci_config *cfg;
 	struct m_can_classdev *mcan_class;
 	struct m_can_pci_priv *priv;
 	void __iomem *base;
@@ -104,6 +150,8 @@ static int m_can_pci_probe(struct pci_dev *pci, const struct pci_device_id *id)
 	if (!mcan_class)
 		return -ENOMEM;
 
+	cfg = (const struct m_can_pci_config *)id->driver_data;
+
 	priv = cdev_to_priv(mcan_class);
 
 	priv->base = base;
@@ -115,7 +163,9 @@ static int m_can_pci_probe(struct pci_dev *pci, const struct pci_device_id *id)
 	mcan_class->dev = &pci->dev;
 	mcan_class->net->irq = pci_irq_vector(pci, 0);
 	mcan_class->pm_clock_support = 1;
-	mcan_class->can.clock.freq = id->driver_data;
+	mcan_class->bit_timing = cfg->bit_timing;
+	mcan_class->data_timing = cfg->data_timing;
+	mcan_class->can.clock.freq = cfg->clock_freq;
 	mcan_class->ops = &m_can_pci_ops;
 
 	pci_set_drvdata(pci, mcan_class);
@@ -168,8 +218,8 @@ static SIMPLE_DEV_PM_OPS(m_can_pci_pm_ops,
 			 m_can_pci_suspend, m_can_pci_resume);
 
 static const struct pci_device_id m_can_pci_id_table[] = {
-	{ PCI_VDEVICE(INTEL, 0x4bc1), M_CAN_CLOCK_FREQ_EHL, },
-	{ PCI_VDEVICE(INTEL, 0x4bc2), M_CAN_CLOCK_FREQ_EHL, },
+	{ PCI_VDEVICE(INTEL, 0x4bc1), (kernel_ulong_t)&m_can_pci_ehl, },
+	{ PCI_VDEVICE(INTEL, 0x4bc2), (kernel_ulong_t)&m_can_pci_ehl, },
 	{  }	/* Terminating Entry */
 };
 MODULE_DEVICE_TABLE(pci, m_can_pci_id_table);
diff --git a/drivers/net/can/pch_can.c b/drivers/net/can/pch_can.c
index 92a54a5fd4c5..964c8a09226a 100644
--- a/drivers/net/can/pch_can.c
+++ b/drivers/net/can/pch_can.c
@@ -692,11 +692,11 @@ static int pch_can_rx_normal(struct net_device *ndev, u32 obj_num, int quota)
 			cf->data[i + 1] = data_reg >> 8;
 		}
 
-		netif_receive_skb(skb);
 		rcv_pkts++;
 		stats->rx_packets++;
 		quota--;
 		stats->rx_bytes += cf->len;
+		netif_receive_skb(skb);
 
 		pch_fifo_thresh(priv, obj_num);
 		obj_num++;
diff --git a/drivers/net/can/sja1000/ems_pcmcia.c b/drivers/net/can/sja1000/ems_pcmcia.c
index e21b169c14c0..4642b6d4aaf7 100644
--- a/drivers/net/can/sja1000/ems_pcmcia.c
+++ b/drivers/net/can/sja1000/ems_pcmcia.c
@@ -234,7 +234,12 @@ static int ems_pcmcia_add_card(struct pcmcia_device *pdev, unsigned long base)
 			free_sja1000dev(dev);
 	}
 
-	err = request_irq(dev->irq, &ems_pcmcia_interrupt, IRQF_SHARED,
+	if (!card->channels) {
+		err = -ENODEV;
+		goto failure_cleanup;
+	}
+
+	err = request_irq(pdev->irq, &ems_pcmcia_interrupt, IRQF_SHARED,
 			  DRV_NAME, card);
 	if (!err)
 		return 0;
diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
index 59ba7c7beec0..f7af1bf5ab46 100644
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
@@ -28,10 +28,6 @@
 
 #include "kvaser_usb.h"
 
-/* Forward declaration */
-static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_dev_cfg;
-
-#define CAN_USB_CLOCK			8000000
 #define MAX_USBCAN_NET_DEVICES		2
 
 /* Command header size */
@@ -80,6 +76,12 @@ static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_dev_cfg;
 
 #define CMD_LEAF_LOG_MESSAGE		106
 
+/* Leaf frequency options */
+#define KVASER_USB_LEAF_SWOPTION_FREQ_MASK 0x60
+#define KVASER_USB_LEAF_SWOPTION_FREQ_16_MHZ_CLK 0
+#define KVASER_USB_LEAF_SWOPTION_FREQ_32_MHZ_CLK BIT(5)
+#define KVASER_USB_LEAF_SWOPTION_FREQ_24_MHZ_CLK BIT(6)
+
 /* error factors */
 #define M16C_EF_ACKE			BIT(0)
 #define M16C_EF_CRCE			BIT(1)
@@ -340,6 +342,50 @@ struct kvaser_usb_err_summary {
 	};
 };
 
+static const struct can_bittiming_const kvaser_usb_leaf_bittiming_const = {
+	.name = "kvaser_usb",
+	.tseg1_min = KVASER_USB_TSEG1_MIN,
+	.tseg1_max = KVASER_USB_TSEG1_MAX,
+	.tseg2_min = KVASER_USB_TSEG2_MIN,
+	.tseg2_max = KVASER_USB_TSEG2_MAX,
+	.sjw_max = KVASER_USB_SJW_MAX,
+	.brp_min = KVASER_USB_BRP_MIN,
+	.brp_max = KVASER_USB_BRP_MAX,
+	.brp_inc = KVASER_USB_BRP_INC,
+};
+
+static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_dev_cfg_8mhz = {
+	.clock = {
+		.freq = 8000000,
+	},
+	.timestamp_freq = 1,
+	.bittiming_const = &kvaser_usb_leaf_bittiming_const,
+};
+
+static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_dev_cfg_16mhz = {
+	.clock = {
+		.freq = 16000000,
+	},
+	.timestamp_freq = 1,
+	.bittiming_const = &kvaser_usb_leaf_bittiming_const,
+};
+
+static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_dev_cfg_24mhz = {
+	.clock = {
+		.freq = 24000000,
+	},
+	.timestamp_freq = 1,
+	.bittiming_const = &kvaser_usb_leaf_bittiming_const,
+};
+
+static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_dev_cfg_32mhz = {
+	.clock = {
+		.freq = 32000000,
+	},
+	.timestamp_freq = 1,
+	.bittiming_const = &kvaser_usb_leaf_bittiming_const,
+};
+
 static void *
 kvaser_usb_leaf_frame_to_cmd(const struct kvaser_usb_net_priv *priv,
 			     const struct sk_buff *skb, int *frame_len,
@@ -471,6 +517,27 @@ static int kvaser_usb_leaf_send_simple_cmd(const struct kvaser_usb *dev,
 	return rc;
 }
 
+static void kvaser_usb_leaf_get_software_info_leaf(struct kvaser_usb *dev,
+						   const struct leaf_cmd_softinfo *softinfo)
+{
+	u32 sw_options = le32_to_cpu(softinfo->sw_options);
+
+	dev->fw_version = le32_to_cpu(softinfo->fw_version);
+	dev->max_tx_urbs = le16_to_cpu(softinfo->max_outstanding_tx);
+
+	switch (sw_options & KVASER_USB_LEAF_SWOPTION_FREQ_MASK) {
+	case KVASER_USB_LEAF_SWOPTION_FREQ_16_MHZ_CLK:
+		dev->cfg = &kvaser_usb_leaf_dev_cfg_16mhz;
+		break;
+	case KVASER_USB_LEAF_SWOPTION_FREQ_24_MHZ_CLK:
+		dev->cfg = &kvaser_usb_leaf_dev_cfg_24mhz;
+		break;
+	case KVASER_USB_LEAF_SWOPTION_FREQ_32_MHZ_CLK:
+		dev->cfg = &kvaser_usb_leaf_dev_cfg_32mhz;
+		break;
+	}
+}
+
 static int kvaser_usb_leaf_get_software_info_inner(struct kvaser_usb *dev)
 {
 	struct kvaser_cmd cmd;
@@ -486,14 +553,13 @@ static int kvaser_usb_leaf_get_software_info_inner(struct kvaser_usb *dev)
 
 	switch (dev->card_data.leaf.family) {
 	case KVASER_LEAF:
-		dev->fw_version = le32_to_cpu(cmd.u.leaf.softinfo.fw_version);
-		dev->max_tx_urbs =
-			le16_to_cpu(cmd.u.leaf.softinfo.max_outstanding_tx);
+		kvaser_usb_leaf_get_software_info_leaf(dev, &cmd.u.leaf.softinfo);
 		break;
 	case KVASER_USBCAN:
 		dev->fw_version = le32_to_cpu(cmd.u.usbcan.softinfo.fw_version);
 		dev->max_tx_urbs =
 			le16_to_cpu(cmd.u.usbcan.softinfo.max_outstanding_tx);
+		dev->cfg = &kvaser_usb_leaf_dev_cfg_8mhz;
 		break;
 	}
 
@@ -1225,24 +1291,11 @@ static int kvaser_usb_leaf_init_card(struct kvaser_usb *dev)
 {
 	struct kvaser_usb_dev_card_data *card_data = &dev->card_data;
 
-	dev->cfg = &kvaser_usb_leaf_dev_cfg;
 	card_data->ctrlmode_supported |= CAN_CTRLMODE_3_SAMPLES;
 
 	return 0;
 }
 
-static const struct can_bittiming_const kvaser_usb_leaf_bittiming_const = {
-	.name = "kvaser_usb",
-	.tseg1_min = KVASER_USB_TSEG1_MIN,
-	.tseg1_max = KVASER_USB_TSEG1_MAX,
-	.tseg2_min = KVASER_USB_TSEG2_MIN,
-	.tseg2_max = KVASER_USB_TSEG2_MAX,
-	.sjw_max = KVASER_USB_SJW_MAX,
-	.brp_min = KVASER_USB_BRP_MIN,
-	.brp_max = KVASER_USB_BRP_MAX,
-	.brp_inc = KVASER_USB_BRP_INC,
-};
-
 static int kvaser_usb_leaf_set_bittiming(struct net_device *netdev)
 {
 	struct kvaser_usb_net_priv *priv = netdev_priv(netdev);
@@ -1348,11 +1401,3 @@ const struct kvaser_usb_dev_ops kvaser_usb_leaf_dev_ops = {
 	.dev_read_bulk_callback = kvaser_usb_leaf_read_bulk_callback,
 	.dev_frame_to_cmd = kvaser_usb_leaf_frame_to_cmd,
 };
-
-static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_dev_cfg = {
-	.clock = {
-		.freq = CAN_USB_CLOCK,
-	},
-	.timestamp_freq = 1,
-	.bittiming_const = &kvaser_usb_leaf_bittiming_const,
-};
diff --git a/drivers/net/dsa/b53/b53_spi.c b/drivers/net/dsa/b53/b53_spi.c
index 01e37b75471e..2b88f03e5252 100644
--- a/drivers/net/dsa/b53/b53_spi.c
+++ b/drivers/net/dsa/b53/b53_spi.c
@@ -349,6 +349,19 @@ static const struct of_device_id b53_spi_of_match[] = {
 };
 MODULE_DEVICE_TABLE(of, b53_spi_of_match);
 
+static const struct spi_device_id b53_spi_ids[] = {
+	{ .name = "bcm5325" },
+	{ .name = "bcm5365" },
+	{ .name = "bcm5395" },
+	{ .name = "bcm5397" },
+	{ .name = "bcm5398" },
+	{ .name = "bcm53115" },
+	{ .name = "bcm53125" },
+	{ .name = "bcm53128" },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(spi, b53_spi_ids);
+
 static struct spi_driver b53_spi_driver = {
 	.driver = {
 		.name	= "b53-switch",
@@ -357,6 +370,7 @@ static struct spi_driver b53_spi_driver = {
 	.probe	= b53_spi_probe,
 	.remove	= b53_spi_remove,
 	.shutdown = b53_spi_shutdown,
+	.id_table = b53_spi_ids,
 };
 
 module_spi_driver(b53_spi_driver);
diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c
index 43fc3087aeb3..013e9c02be71 100644
--- a/drivers/net/dsa/microchip/ksz8795.c
+++ b/drivers/net/dsa/microchip/ksz8795.c
@@ -1002,57 +1002,32 @@ static void ksz8_cfg_port_member(struct ksz_device *dev, int port, u8 member)
 	data &= ~PORT_VLAN_MEMBERSHIP;
 	data |= (member & dev->port_mask);
 	ksz_pwrite8(dev, port, P_MIRROR_CTRL, data);
-	dev->ports[port].member = member;
 }
 
 static void ksz8_port_stp_state_set(struct dsa_switch *ds, int port, u8 state)
 {
 	struct ksz_device *dev = ds->priv;
-	int forward = dev->member;
 	struct ksz_port *p;
-	int member = -1;
 	u8 data;
 
-	p = &dev->ports[port];
-
 	ksz_pread8(dev, port, P_STP_CTRL, &data);
 	data &= ~(PORT_TX_ENABLE | PORT_RX_ENABLE | PORT_LEARN_DISABLE);
 
 	switch (state) {
 	case BR_STATE_DISABLED:
 		data |= PORT_LEARN_DISABLE;
-		if (port < dev->phy_port_cnt)
-			member = 0;
 		break;
 	case BR_STATE_LISTENING:
 		data |= (PORT_RX_ENABLE | PORT_LEARN_DISABLE);
-		if (port < dev->phy_port_cnt &&
-		    p->stp_state == BR_STATE_DISABLED)
-			member = dev->host_mask | p->vid_member;
 		break;
 	case BR_STATE_LEARNING:
 		data |= PORT_RX_ENABLE;
 		break;
 	case BR_STATE_FORWARDING:
 		data |= (PORT_TX_ENABLE | PORT_RX_ENABLE);
-
-		/* This function is also used internally. */
-		if (port == dev->cpu_port)
-			break;
-
-		/* Port is a member of a bridge. */
-		if (dev->br_member & BIT(port)) {
-			dev->member |= BIT(port);
-			member = dev->member;
-		} else {
-			member = dev->host_mask | p->vid_member;
-		}
 		break;
 	case BR_STATE_BLOCKING:
 		data |= PORT_LEARN_DISABLE;
-		if (port < dev->phy_port_cnt &&
-		    p->stp_state == BR_STATE_DISABLED)
-			member = dev->host_mask | p->vid_member;
 		break;
 	default:
 		dev_err(ds->dev, "invalid STP state: %d\n", state);
@@ -1060,22 +1035,11 @@ static void ksz8_port_stp_state_set(struct dsa_switch *ds, int port, u8 state)
 	}
 
 	ksz_pwrite8(dev, port, P_STP_CTRL, data);
+
+	p = &dev->ports[port];
 	p->stp_state = state;
-	/* Port membership may share register with STP state. */
-	if (member >= 0 && member != p->member)
-		ksz8_cfg_port_member(dev, port, (u8)member);
-
-	/* Check if forwarding needs to be updated. */
-	if (state != BR_STATE_FORWARDING) {
-		if (dev->br_member & BIT(port))
-			dev->member &= ~BIT(port);
-	}
 
-	/* When topology has changed the function ksz_update_port_member
-	 * should be called to modify port forwarding behavior.
-	 */
-	if (forward != dev->member)
-		ksz_update_port_member(dev, port);
+	ksz_update_port_member(dev, port);
 }
 
 static void ksz8_flush_dyn_mac_table(struct ksz_device *dev, int port)
@@ -1341,7 +1305,7 @@ static void ksz8795_cpu_interface_select(struct ksz_device *dev, int port)
 
 static void ksz8_port_setup(struct ksz_device *dev, int port, bool cpu_port)
 {
-	struct ksz_port *p = &dev->ports[port];
+	struct dsa_switch *ds = dev->ds;
 	struct ksz8 *ksz8 = dev->priv;
 	const u32 *masks;
 	u8 member;
@@ -1368,10 +1332,11 @@ static void ksz8_port_setup(struct ksz_device *dev, int port, bool cpu_port)
 		if (!ksz_is_ksz88x3(dev))
 			ksz8795_cpu_interface_select(dev, port);
 
-		member = dev->port_mask;
+		member = dsa_user_ports(ds);
 	} else {
-		member = dev->host_mask | p->vid_member;
+		member = BIT(dsa_upstream_port(ds, port));
 	}
+
 	ksz8_cfg_port_member(dev, port, member);
 }
 
@@ -1392,20 +1357,13 @@ static void ksz8_config_cpu_port(struct dsa_switch *ds)
 	ksz_cfg(dev, regs[S_TAIL_TAG_CTRL], masks[SW_TAIL_TAG_ENABLE], true);
 
 	p = &dev->ports[dev->cpu_port];
-	p->vid_member = dev->port_mask;
 	p->on = 1;
 
 	ksz8_port_setup(dev, dev->cpu_port, true);
-	dev->member = dev->host_mask;
 
 	for (i = 0; i < dev->phy_port_cnt; i++) {
 		p = &dev->ports[i];
 
-		/* Initialize to non-zero so that ksz_cfg_port_member() will
-		 * be called.
-		 */
-		p->vid_member = BIT(i);
-		p->member = dev->port_mask;
 		ksz8_port_stp_state_set(ds, i, BR_STATE_DISABLED);
 
 		/* Last port may be disabled. */
diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c
index 854e25f43fa7..353b5f981740 100644
--- a/drivers/net/dsa/microchip/ksz9477.c
+++ b/drivers/net/dsa/microchip/ksz9477.c
@@ -391,7 +391,6 @@ static void ksz9477_cfg_port_member(struct ksz_device *dev, int port,
 				    u8 member)
 {
 	ksz_pwrite32(dev, port, REG_PORT_VLAN_MEMBERSHIP__4, member);
-	dev->ports[port].member = member;
 }
 
 static void ksz9477_port_stp_state_set(struct dsa_switch *ds, int port,
@@ -400,8 +399,6 @@ static void ksz9477_port_stp_state_set(struct dsa_switch *ds, int port,
 	struct ksz_device *dev = ds->priv;
 	struct ksz_port *p = &dev->ports[port];
 	u8 data;
-	int member = -1;
-	int forward = dev->member;
 
 	ksz_pread8(dev, port, P_STP_CTRL, &data);
 	data &= ~(PORT_TX_ENABLE | PORT_RX_ENABLE | PORT_LEARN_DISABLE);
@@ -409,40 +406,18 @@ static void ksz9477_port_stp_state_set(struct dsa_switch *ds, int port,
 	switch (state) {
 	case BR_STATE_DISABLED:
 		data |= PORT_LEARN_DISABLE;
-		if (port != dev->cpu_port)
-			member = 0;
 		break;
 	case BR_STATE_LISTENING:
 		data |= (PORT_RX_ENABLE | PORT_LEARN_DISABLE);
-		if (port != dev->cpu_port &&
-		    p->stp_state == BR_STATE_DISABLED)
-			member = dev->host_mask | p->vid_member;
 		break;
 	case BR_STATE_LEARNING:
 		data |= PORT_RX_ENABLE;
 		break;
 	case BR_STATE_FORWARDING:
 		data |= (PORT_TX_ENABLE | PORT_RX_ENABLE);
-
-		/* This function is also used internally. */
-		if (port == dev->cpu_port)
-			break;
-
-		member = dev->host_mask | p->vid_member;
-		mutex_lock(&dev->dev_mutex);
-
-		/* Port is a member of a bridge. */
-		if (dev->br_member & (1 << port)) {
-			dev->member |= (1 << port);
-			member = dev->member;
-		}
-		mutex_unlock(&dev->dev_mutex);
 		break;
 	case BR_STATE_BLOCKING:
 		data |= PORT_LEARN_DISABLE;
-		if (port != dev->cpu_port &&
-		    p->stp_state == BR_STATE_DISABLED)
-			member = dev->host_mask | p->vid_member;
 		break;
 	default:
 		dev_err(ds->dev, "invalid STP state: %d\n", state);
@@ -451,23 +426,8 @@ static void ksz9477_port_stp_state_set(struct dsa_switch *ds, int port,
 
 	ksz_pwrite8(dev, port, P_STP_CTRL, data);
 	p->stp_state = state;
-	mutex_lock(&dev->dev_mutex);
-	/* Port membership may share register with STP state. */
-	if (member >= 0 && member != p->member)
-		ksz9477_cfg_port_member(dev, port, (u8)member);
-
-	/* Check if forwarding needs to be updated. */
-	if (state != BR_STATE_FORWARDING) {
-		if (dev->br_member & (1 << port))
-			dev->member &= ~(1 << port);
-	}
 
-	/* When topology has changed the function ksz_update_port_member
-	 * should be called to modify port forwarding behavior.
-	 */
-	if (forward != dev->member)
-		ksz_update_port_member(dev, port);
-	mutex_unlock(&dev->dev_mutex);
+	ksz_update_port_member(dev, port);
 }
 
 static void ksz9477_flush_dyn_mac_table(struct ksz_device *dev, int port)
@@ -1168,10 +1128,10 @@ static void ksz9477_phy_errata_setup(struct ksz_device *dev, int port)
 
 static void ksz9477_port_setup(struct ksz_device *dev, int port, bool cpu_port)
 {
-	u8 data8;
-	u8 member;
-	u16 data16;
 	struct ksz_port *p = &dev->ports[port];
+	struct dsa_switch *ds = dev->ds;
+	u8 data8, member;
+	u16 data16;
 
 	/* enable tag tail for host port */
 	if (cpu_port)
@@ -1250,12 +1210,12 @@ static void ksz9477_port_setup(struct ksz_device *dev, int port, bool cpu_port)
 		ksz_pwrite8(dev, port, REG_PORT_XMII_CTRL_1, data8);
 		p->phydev.duplex = 1;
 	}
-	mutex_lock(&dev->dev_mutex);
+
 	if (cpu_port)
-		member = dev->port_mask;
+		member = dsa_user_ports(ds);
 	else
-		member = dev->host_mask | p->vid_member;
-	mutex_unlock(&dev->dev_mutex);
+		member = BIT(dsa_upstream_port(ds, port));
+
 	ksz9477_cfg_port_member(dev, port, member);
 
 	/* clear pending interrupts */
@@ -1276,8 +1236,6 @@ static void ksz9477_config_cpu_port(struct dsa_switch *ds)
 			const char *prev_mode;
 
 			dev->cpu_port = i;
-			dev->host_mask = (1 << dev->cpu_port);
-			dev->port_mask |= dev->host_mask;
 			p = &dev->ports[i];
 
 			/* Read from XMII register to determine host port
@@ -1312,23 +1270,15 @@ static void ksz9477_config_cpu_port(struct dsa_switch *ds)
 
 			/* enable cpu port */
 			ksz9477_port_setup(dev, i, true);
-			p->vid_member = dev->port_mask;
 			p->on = 1;
 		}
 	}
 
-	dev->member = dev->host_mask;
-
 	for (i = 0; i < dev->port_cnt; i++) {
 		if (i == dev->cpu_port)
 			continue;
 		p = &dev->ports[i];
 
-		/* Initialize to non-zero so that ksz_cfg_port_member() will
-		 * be called.
-		 */
-		p->vid_member = (1 << i);
-		p->member = dev->port_mask;
 		ksz9477_port_stp_state_set(ds, i, BR_STATE_DISABLED);
 		p->on = 1;
 		if (i < dev->phy_port_cnt)
diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c
index 7c2968a639eb..8a04302018dc 100644
--- a/drivers/net/dsa/microchip/ksz_common.c
+++ b/drivers/net/dsa/microchip/ksz_common.c
@@ -22,21 +22,40 @@
 
 void ksz_update_port_member(struct ksz_device *dev, int port)
 {
-	struct ksz_port *p;
+	struct ksz_port *p = &dev->ports[port];
+	struct dsa_switch *ds = dev->ds;
+	u8 port_member = 0, cpu_port;
+	const struct dsa_port *dp;
 	int i;
 
-	for (i = 0; i < dev->port_cnt; i++) {
-		if (i == port || i == dev->cpu_port)
+	if (!dsa_is_user_port(ds, port))
+		return;
+
+	dp = dsa_to_port(ds, port);
+	cpu_port = BIT(dsa_upstream_port(ds, port));
+
+	for (i = 0; i < ds->num_ports; i++) {
+		const struct dsa_port *other_dp = dsa_to_port(ds, i);
+		struct ksz_port *other_p = &dev->ports[i];
+		u8 val = 0;
+
+		if (!dsa_is_user_port(ds, i))
 			continue;
-		p = &dev->ports[i];
-		if (!(dev->member & (1 << i)))
+		if (port == i)
+			continue;
+		if (!dp->bridge_dev || dp->bridge_dev != other_dp->bridge_dev)
 			continue;
 
-		/* Port is a member of the bridge and is forwarding. */
-		if (p->stp_state == BR_STATE_FORWARDING &&
-		    p->member != dev->member)
-			dev->dev_ops->cfg_port_member(dev, i, dev->member);
+		if (other_p->stp_state == BR_STATE_FORWARDING &&
+		    p->stp_state == BR_STATE_FORWARDING) {
+			val |= BIT(port);
+			port_member |= BIT(i);
+		}
+
+		dev->dev_ops->cfg_port_member(dev, i, val | cpu_port);
 	}
+
+	dev->dev_ops->cfg_port_member(dev, port, port_member | cpu_port);
 }
 EXPORT_SYMBOL_GPL(ksz_update_port_member);
 
@@ -175,12 +194,6 @@ EXPORT_SYMBOL_GPL(ksz_get_ethtool_stats);
 int ksz_port_bridge_join(struct dsa_switch *ds, int port,
 			 struct net_device *br)
 {
-	struct ksz_device *dev = ds->priv;
-
-	mutex_lock(&dev->dev_mutex);
-	dev->br_member |= (1 << port);
-	mutex_unlock(&dev->dev_mutex);
-
 	/* port_stp_state_set() will be called after to put the port in
 	 * appropriate state so there is no need to do anything.
 	 */
@@ -192,13 +205,6 @@ EXPORT_SYMBOL_GPL(ksz_port_bridge_join);
 void ksz_port_bridge_leave(struct dsa_switch *ds, int port,
 			   struct net_device *br)
 {
-	struct ksz_device *dev = ds->priv;
-
-	mutex_lock(&dev->dev_mutex);
-	dev->br_member &= ~(1 << port);
-	dev->member &= ~(1 << port);
-	mutex_unlock(&dev->dev_mutex);
-
 	/* port_stp_state_set() will be called after to put the port in
 	 * forwarding state so there is no need to do anything.
 	 */
diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h
index 1597c63988b4..54b456bc8972 100644
--- a/drivers/net/dsa/microchip/ksz_common.h
+++ b/drivers/net/dsa/microchip/ksz_common.h
@@ -25,8 +25,6 @@ struct ksz_port_mib {
 };
 
 struct ksz_port {
-	u16 member;
-	u16 vid_member;
 	bool remove_tag;		/* Remove Tag flag set, for ksz8795 only */
 	int stp_state;
 	struct phy_device phydev;
@@ -83,8 +81,6 @@ struct ksz_device {
 	struct ksz_port *ports;
 	struct delayed_work mib_read;
 	unsigned long mib_read_interval;
-	u16 br_member;
-	u16 member;
 	u16 mirror_rx;
 	u16 mirror_tx;
 	u32 features;			/* chip specific features */
diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index f00cbf5753b9..cd8462d1e27c 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -471,6 +471,12 @@ static int mv88e6xxx_port_ppu_updates(struct mv88e6xxx_chip *chip, int port)
 	u16 reg;
 	int err;
 
+	/* The 88e6250 family does not have the PHY detect bit. Instead,
+	 * report whether the port is internal.
+	 */
+	if (chip->info->family == MV88E6XXX_FAMILY_6250)
+		return port < chip->info->num_internal_phys;
+
 	err = mv88e6xxx_port_read(chip, port, MV88E6XXX_PORT_STS, &reg);
 	if (err) {
 		dev_err(chip->dev,
@@ -692,44 +698,48 @@ static void mv88e6xxx_mac_config(struct dsa_switch *ds, int port,
 {
 	struct mv88e6xxx_chip *chip = ds->priv;
 	struct mv88e6xxx_port *p;
-	int err;
+	int err = 0;
 
 	p = &chip->ports[port];
 
-	/* FIXME: is this the correct test? If we're in fixed mode on an
-	 * internal port, why should we process this any different from
-	 * PHY mode? On the other hand, the port may be automedia between
-	 * an internal PHY and the serdes...
-	 */
-	if ((mode == MLO_AN_PHY) && mv88e6xxx_phy_is_internal(ds, port))
-		return;
-
 	mv88e6xxx_reg_lock(chip);
-	/* In inband mode, the link may come up at any time while the link
-	 * is not forced down. Force the link down while we reconfigure the
-	 * interface mode.
-	 */
-	if (mode == MLO_AN_INBAND && p->interface != state->interface &&
-	    chip->info->ops->port_set_link)
-		chip->info->ops->port_set_link(chip, port, LINK_FORCED_DOWN);
 
-	err = mv88e6xxx_port_config_interface(chip, port, state->interface);
-	if (err && err != -EOPNOTSUPP)
-		goto err_unlock;
-
-	err = mv88e6xxx_serdes_pcs_config(chip, port, mode, state->interface,
-					  state->advertising);
-	/* FIXME: we should restart negotiation if something changed - which
-	 * is something we get if we convert to using phylinks PCS operations.
-	 */
-	if (err > 0)
-		err = 0;
+	if (mode != MLO_AN_PHY || !mv88e6xxx_phy_is_internal(ds, port)) {
+		/* In inband mode, the link may come up at any time while the
+		 * link is not forced down. Force the link down while we
+		 * reconfigure the interface mode.
+		 */
+		if (mode == MLO_AN_INBAND &&
+		    p->interface != state->interface &&
+		    chip->info->ops->port_set_link)
+			chip->info->ops->port_set_link(chip, port,
+						       LINK_FORCED_DOWN);
+
+		err = mv88e6xxx_port_config_interface(chip, port,
+						      state->interface);
+		if (err && err != -EOPNOTSUPP)
+			goto err_unlock;
+
+		err = mv88e6xxx_serdes_pcs_config(chip, port, mode,
+						  state->interface,
+						  state->advertising);
+		/* FIXME: we should restart negotiation if something changed -
+		 * which is something we get if we convert to using phylinks
+		 * PCS operations.
+		 */
+		if (err > 0)
+			err = 0;
+	}
 
 	/* Undo the forced down state above after completing configuration
-	 * irrespective of its state on entry, which allows the link to come up.
+	 * irrespective of its state on entry, which allows the link to come
+	 * up in the in-band case where there is no separate SERDES. Also
+	 * ensure that the link can come up if the PPU is in use and we are
+	 * in PHY mode (we treat the PPU as an effective in-band mechanism.)
 	 */
-	if (mode == MLO_AN_INBAND && p->interface != state->interface &&
-	    chip->info->ops->port_set_link)
+	if (chip->info->ops->port_set_link &&
+	    ((mode == MLO_AN_INBAND && p->interface != state->interface) ||
+	     (mode == MLO_AN_PHY && mv88e6xxx_port_ppu_updates(chip, port))))
 		chip->info->ops->port_set_link(chip, port, LINK_UNFORCED);
 
 	p->interface = state->interface;
@@ -752,13 +762,16 @@ static void mv88e6xxx_mac_link_down(struct dsa_switch *ds, int port,
 	ops = chip->info->ops;
 
 	mv88e6xxx_reg_lock(chip);
-	/* Internal PHYs propagate their configuration directly to the MAC.
-	 * External PHYs depend on whether the PPU is enabled for this port.
+	/* Force the link down if we know the port may not be automatically
+	 * updated by the switch or if we are using fixed-link mode.
 	 */
-	if (((!mv88e6xxx_phy_is_internal(ds, port) &&
-	      !mv88e6xxx_port_ppu_updates(chip, port)) ||
+	if ((!mv88e6xxx_port_ppu_updates(chip, port) ||
 	     mode == MLO_AN_FIXED) && ops->port_sync_link)
 		err = ops->port_sync_link(chip, port, mode, false);
+
+	if (!err && ops->port_set_speed_duplex)
+		err = ops->port_set_speed_duplex(chip, port, SPEED_UNFORCED,
+						 DUPLEX_UNFORCED);
 	mv88e6xxx_reg_unlock(chip);
 
 	if (err)
@@ -779,11 +792,11 @@ static void mv88e6xxx_mac_link_up(struct dsa_switch *ds, int port,
 	ops = chip->info->ops;
 
 	mv88e6xxx_reg_lock(chip);
-	/* Internal PHYs propagate their configuration directly to the MAC.
-	 * External PHYs depend on whether the PPU is enabled for this port.
+	/* Configure and force the link up if we know that the port may not
+	 * automatically updated by the switch or if we are using fixed-link
+	 * mode.
 	 */
-	if ((!mv88e6xxx_phy_is_internal(ds, port) &&
-	     !mv88e6xxx_port_ppu_updates(chip, port)) ||
+	if (!mv88e6xxx_port_ppu_updates(chip, port) ||
 	    mode == MLO_AN_FIXED) {
 		/* FIXME: for an automedia port, should we force the link
 		 * down here - what if the link comes up due to "other" media
diff --git a/drivers/net/dsa/mv88e6xxx/port.c b/drivers/net/dsa/mv88e6xxx/port.c
index d9817b20ea64..ab41619a809b 100644
--- a/drivers/net/dsa/mv88e6xxx/port.c
+++ b/drivers/net/dsa/mv88e6xxx/port.c
@@ -283,7 +283,7 @@ static int mv88e6xxx_port_set_speed_duplex(struct mv88e6xxx_chip *chip,
 	if (err)
 		return err;
 
-	if (speed)
+	if (speed != SPEED_UNFORCED)
 		dev_dbg(chip->dev, "p%d: Speed set to %d Mbps\n", port, speed);
 	else
 		dev_dbg(chip->dev, "p%d: Speed unforced\n", port);
@@ -516,7 +516,7 @@ int mv88e6393x_port_set_speed_duplex(struct mv88e6xxx_chip *chip, int port,
 	if (err)
 		return err;
 
-	if (speed)
+	if (speed != SPEED_UNFORCED)
 		dev_dbg(chip->dev, "p%d: Speed set to %d Mbps\n", port, speed);
 	else
 		dev_dbg(chip->dev, "p%d: Speed unforced\n", port);
diff --git a/drivers/net/dsa/mv88e6xxx/serdes.c b/drivers/net/dsa/mv88e6xxx/serdes.c
index 6ea003678798..2b05ead515cd 100644
--- a/drivers/net/dsa/mv88e6xxx/serdes.c
+++ b/drivers/net/dsa/mv88e6xxx/serdes.c
@@ -50,11 +50,22 @@ static int mv88e6390_serdes_write(struct mv88e6xxx_chip *chip,
 }
 
 static int mv88e6xxx_serdes_pcs_get_state(struct mv88e6xxx_chip *chip,
-					  u16 status, u16 lpa,
+					  u16 ctrl, u16 status, u16 lpa,
 					  struct phylink_link_state *state)
 {
+	state->link = !!(status & MV88E6390_SGMII_PHY_STATUS_LINK);
+
 	if (status & MV88E6390_SGMII_PHY_STATUS_SPD_DPL_VALID) {
-		state->link = !!(status & MV88E6390_SGMII_PHY_STATUS_LINK);
+		/* The Spped and Duplex Resolved register is 1 if AN is enabled
+		 * and complete, or if AN is disabled. So with disabled AN we
+		 * still get here on link up. But we want to set an_complete
+		 * only if AN was enabled, thus we look at BMCR_ANENABLE.
+		 * (According to 802.3-2008 section 22.2.4.2.10, we should be
+		 *  able to get this same value from BMSR_ANEGCAPABLE, but tests
+		 *  show that these Marvell PHYs don't conform to this part of
+		 *  the specificaion - BMSR_ANEGCAPABLE is simply always 1.)
+		 */
+		state->an_complete = !!(ctrl & BMCR_ANENABLE);
 		state->duplex = status &
 				MV88E6390_SGMII_PHY_STATUS_DUPLEX_FULL ?
 			                         DUPLEX_FULL : DUPLEX_HALF;
@@ -81,6 +92,18 @@ static int mv88e6xxx_serdes_pcs_get_state(struct mv88e6xxx_chip *chip,
 			dev_err(chip->dev, "invalid PHY speed\n");
 			return -EINVAL;
 		}
+	} else if (state->link &&
+		   state->interface != PHY_INTERFACE_MODE_SGMII) {
+		/* If Speed and Duplex Resolved register is 0 and link is up, it
+		 * means that AN was enabled, but link partner had it disabled
+		 * and the PHY invoked the Auto-Negotiation Bypass feature and
+		 * linked anyway.
+		 */
+		state->duplex = DUPLEX_FULL;
+		if (state->interface == PHY_INTERFACE_MODE_2500BASEX)
+			state->speed = SPEED_2500;
+		else
+			state->speed = SPEED_1000;
 	} else {
 		state->link = false;
 	}
@@ -168,9 +191,15 @@ int mv88e6352_serdes_pcs_config(struct mv88e6xxx_chip *chip, int port,
 int mv88e6352_serdes_pcs_get_state(struct mv88e6xxx_chip *chip, int port,
 				   int lane, struct phylink_link_state *state)
 {
-	u16 lpa, status;
+	u16 lpa, status, ctrl;
 	int err;
 
+	err = mv88e6352_serdes_read(chip, MII_BMCR, &ctrl);
+	if (err) {
+		dev_err(chip->dev, "can't read Serdes PHY control: %d\n", err);
+		return err;
+	}
+
 	err = mv88e6352_serdes_read(chip, 0x11, &status);
 	if (err) {
 		dev_err(chip->dev, "can't read Serdes PHY status: %d\n", err);
@@ -183,7 +212,7 @@ int mv88e6352_serdes_pcs_get_state(struct mv88e6xxx_chip *chip, int port,
 		return err;
 	}
 
-	return mv88e6xxx_serdes_pcs_get_state(chip, status, lpa, state);
+	return mv88e6xxx_serdes_pcs_get_state(chip, ctrl, status, lpa, state);
 }
 
 int mv88e6352_serdes_pcs_an_restart(struct mv88e6xxx_chip *chip, int port,
@@ -801,7 +830,7 @@ int mv88e6390_serdes_power(struct mv88e6xxx_chip *chip, int port, int lane,
 			   bool up)
 {
 	u8 cmode = chip->ports[port].cmode;
-	int err = 0;
+	int err;
 
 	switch (cmode) {
 	case MV88E6XXX_PORT_STS_CMODE_SGMII:
@@ -813,6 +842,9 @@ int mv88e6390_serdes_power(struct mv88e6xxx_chip *chip, int port, int lane,
 	case MV88E6XXX_PORT_STS_CMODE_RXAUI:
 		err = mv88e6390_serdes_power_10g(chip, lane, up);
 		break;
+	default:
+		err = -EINVAL;
+		break;
 	}
 
 	if (!err && up)
@@ -883,10 +915,17 @@ int mv88e6390_serdes_pcs_config(struct mv88e6xxx_chip *chip, int port,
 static int mv88e6390_serdes_pcs_get_state_sgmii(struct mv88e6xxx_chip *chip,
 	int port, int lane, struct phylink_link_state *state)
 {
-	u16 lpa, status;
+	u16 lpa, status, ctrl;
 	int err;
 
 	err = mv88e6390_serdes_read(chip, lane, MDIO_MMD_PHYXS,
+				    MV88E6390_SGMII_BMCR, &ctrl);
+	if (err) {
+		dev_err(chip->dev, "can't read Serdes PHY control: %d\n", err);
+		return err;
+	}
+
+	err = mv88e6390_serdes_read(chip, lane, MDIO_MMD_PHYXS,
 				    MV88E6390_SGMII_PHY_STATUS, &status);
 	if (err) {
 		dev_err(chip->dev, "can't read Serdes PHY status: %d\n", err);
@@ -900,7 +939,7 @@ static int mv88e6390_serdes_pcs_get_state_sgmii(struct mv88e6xxx_chip *chip,
 		return err;
 	}
 
-	return mv88e6xxx_serdes_pcs_get_state(chip, status, lpa, state);
+	return mv88e6xxx_serdes_pcs_get_state(chip, ctrl, status, lpa, state);
 }
 
 static int mv88e6390_serdes_pcs_get_state_10g(struct mv88e6xxx_chip *chip,
@@ -1271,9 +1310,31 @@ void mv88e6390_serdes_get_regs(struct mv88e6xxx_chip *chip, int port, void *_p)
 	}
 }
 
-static int mv88e6393x_serdes_port_errata(struct mv88e6xxx_chip *chip, int lane)
+static int mv88e6393x_serdes_power_lane(struct mv88e6xxx_chip *chip, int lane,
+					bool on)
 {
-	u16 reg, pcs;
+	u16 reg;
+	int err;
+
+	err = mv88e6390_serdes_read(chip, lane, MDIO_MMD_PHYXS,
+				    MV88E6393X_SERDES_CTRL1, &reg);
+	if (err)
+		return err;
+
+	if (on)
+		reg &= ~(MV88E6393X_SERDES_CTRL1_TX_PDOWN |
+			 MV88E6393X_SERDES_CTRL1_RX_PDOWN);
+	else
+		reg |= MV88E6393X_SERDES_CTRL1_TX_PDOWN |
+		       MV88E6393X_SERDES_CTRL1_RX_PDOWN;
+
+	return mv88e6390_serdes_write(chip, lane, MDIO_MMD_PHYXS,
+				      MV88E6393X_SERDES_CTRL1, reg);
+}
+
+static int mv88e6393x_serdes_erratum_4_6(struct mv88e6xxx_chip *chip, int lane)
+{
+	u16 reg;
 	int err;
 
 	/* mv88e6393x family errata 4.6:
@@ -1284,26 +1345,45 @@ static int mv88e6393x_serdes_port_errata(struct mv88e6xxx_chip *chip, int lane)
 	 * It seems that after this workaround the SERDES is automatically
 	 * powered up (the bit is cleared), so power it down.
 	 */
-	if (lane == MV88E6393X_PORT0_LANE || lane == MV88E6393X_PORT9_LANE ||
-	    lane == MV88E6393X_PORT10_LANE) {
-		err = mv88e6390_serdes_read(chip, lane,
-					    MDIO_MMD_PHYXS,
-					    MV88E6393X_SERDES_POC, &reg);
-		if (err)
-			return err;
+	err = mv88e6390_serdes_read(chip, lane, MDIO_MMD_PHYXS,
+				    MV88E6393X_SERDES_POC, &reg);
+	if (err)
+		return err;
 
-		reg &= ~MV88E6393X_SERDES_POC_PDOWN;
-		reg |= MV88E6393X_SERDES_POC_RESET;
+	reg &= ~MV88E6393X_SERDES_POC_PDOWN;
+	reg |= MV88E6393X_SERDES_POC_RESET;
 
-		err = mv88e6390_serdes_write(chip, lane, MDIO_MMD_PHYXS,
-					     MV88E6393X_SERDES_POC, reg);
-		if (err)
-			return err;
+	err = mv88e6390_serdes_write(chip, lane, MDIO_MMD_PHYXS,
+				     MV88E6393X_SERDES_POC, reg);
+	if (err)
+		return err;
 
-		err = mv88e6390_serdes_power_sgmii(chip, lane, false);
-		if (err)
-			return err;
-	}
+	err = mv88e6390_serdes_power_sgmii(chip, lane, false);
+	if (err)
+		return err;
+
+	return mv88e6393x_serdes_power_lane(chip, lane, false);
+}
+
+int mv88e6393x_serdes_setup_errata(struct mv88e6xxx_chip *chip)
+{
+	int err;
+
+	err = mv88e6393x_serdes_erratum_4_6(chip, MV88E6393X_PORT0_LANE);
+	if (err)
+		return err;
+
+	err = mv88e6393x_serdes_erratum_4_6(chip, MV88E6393X_PORT9_LANE);
+	if (err)
+		return err;
+
+	return mv88e6393x_serdes_erratum_4_6(chip, MV88E6393X_PORT10_LANE);
+}
+
+static int mv88e6393x_serdes_erratum_4_8(struct mv88e6xxx_chip *chip, int lane)
+{
+	u16 reg, pcs;
+	int err;
 
 	/* mv88e6393x family errata 4.8:
 	 * When a SERDES port is operating in 1000BASE-X or SGMII mode link may
@@ -1334,38 +1414,152 @@ static int mv88e6393x_serdes_port_errata(struct mv88e6xxx_chip *chip, int lane)
 				      MV88E6393X_ERRATA_4_8_REG, reg);
 }
 
-int mv88e6393x_serdes_setup_errata(struct mv88e6xxx_chip *chip)
+static int mv88e6393x_serdes_erratum_5_2(struct mv88e6xxx_chip *chip, int lane,
+					 u8 cmode)
+{
+	static const struct {
+		u16 dev, reg, val, mask;
+	} fixes[] = {
+		{ MDIO_MMD_VEND1, 0x8093, 0xcb5a, 0xffff },
+		{ MDIO_MMD_VEND1, 0x8171, 0x7088, 0xffff },
+		{ MDIO_MMD_VEND1, 0x80c9, 0x311a, 0xffff },
+		{ MDIO_MMD_VEND1, 0x80a2, 0x8000, 0xff7f },
+		{ MDIO_MMD_VEND1, 0x80a9, 0x0000, 0xfff0 },
+		{ MDIO_MMD_VEND1, 0x80a3, 0x0000, 0xf8ff },
+		{ MDIO_MMD_PHYXS, MV88E6393X_SERDES_POC,
+		  MV88E6393X_SERDES_POC_RESET, MV88E6393X_SERDES_POC_RESET },
+	};
+	int err, i;
+	u16 reg;
+
+	/* mv88e6393x family errata 5.2:
+	 * For optimal signal integrity the following sequence should be applied
+	 * to SERDES operating in 10G mode. These registers only apply to 10G
+	 * operation and have no effect on other speeds.
+	 */
+	if (cmode != MV88E6393X_PORT_STS_CMODE_10GBASER)
+		return 0;
+
+	for (i = 0; i < ARRAY_SIZE(fixes); ++i) {
+		err = mv88e6390_serdes_read(chip, lane, fixes[i].dev,
+					    fixes[i].reg, &reg);
+		if (err)
+			return err;
+
+		reg &= ~fixes[i].mask;
+		reg |= fixes[i].val;
+
+		err = mv88e6390_serdes_write(chip, lane, fixes[i].dev,
+					     fixes[i].reg, reg);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int mv88e6393x_serdes_fix_2500basex_an(struct mv88e6xxx_chip *chip,
+					      int lane, u8 cmode, bool on)
 {
+	u16 reg;
 	int err;
 
-	err = mv88e6393x_serdes_port_errata(chip, MV88E6393X_PORT0_LANE);
+	if (cmode != MV88E6XXX_PORT_STS_CMODE_2500BASEX)
+		return 0;
+
+	/* Inband AN is broken on Amethyst in 2500base-x mode when set by
+	 * standard mechanism (via cmode).
+	 * We can get around this by configuring the PCS mode to 1000base-x
+	 * and then writing value 0x58 to register 1e.8000. (This must be done
+	 * while SerDes receiver and transmitter are disabled, which is, when
+	 * this function is called.)
+	 * It seem that when we do this configuration to 2500base-x mode (by
+	 * changing PCS mode to 1000base-x and frequency to 3.125 GHz from
+	 * 1.25 GHz) and then configure to sgmii or 1000base-x, the device
+	 * thinks that it already has SerDes at 1.25 GHz and does not change
+	 * the 1e.8000 register, leaving SerDes at 3.125 GHz.
+	 * To avoid this, change PCS mode back to 2500base-x when disabling
+	 * SerDes from 2500base-x mode.
+	 */
+	err = mv88e6390_serdes_read(chip, lane, MDIO_MMD_PHYXS,
+				    MV88E6393X_SERDES_POC, &reg);
+	if (err)
+		return err;
+
+	reg &= ~(MV88E6393X_SERDES_POC_PCS_MASK | MV88E6393X_SERDES_POC_AN);
+	if (on)
+		reg |= MV88E6393X_SERDES_POC_PCS_1000BASEX |
+		       MV88E6393X_SERDES_POC_AN;
+	else
+		reg |= MV88E6393X_SERDES_POC_PCS_2500BASEX;
+	reg |= MV88E6393X_SERDES_POC_RESET;
+
+	err = mv88e6390_serdes_write(chip, lane, MDIO_MMD_PHYXS,
+				     MV88E6393X_SERDES_POC, reg);
 	if (err)
 		return err;
 
-	err = mv88e6393x_serdes_port_errata(chip, MV88E6393X_PORT9_LANE);
+	err = mv88e6390_serdes_write(chip, lane, MDIO_MMD_VEND1, 0x8000, 0x58);
 	if (err)
 		return err;
 
-	return mv88e6393x_serdes_port_errata(chip, MV88E6393X_PORT10_LANE);
+	return 0;
 }
 
 int mv88e6393x_serdes_power(struct mv88e6xxx_chip *chip, int port, int lane,
 			    bool on)
 {
 	u8 cmode = chip->ports[port].cmode;
+	int err;
 
 	if (port != 0 && port != 9 && port != 10)
 		return -EOPNOTSUPP;
 
+	if (on) {
+		err = mv88e6393x_serdes_erratum_4_8(chip, lane);
+		if (err)
+			return err;
+
+		err = mv88e6393x_serdes_erratum_5_2(chip, lane, cmode);
+		if (err)
+			return err;
+
+		err = mv88e6393x_serdes_fix_2500basex_an(chip, lane, cmode,
+							 true);
+		if (err)
+			return err;
+
+		err = mv88e6393x_serdes_power_lane(chip, lane, true);
+		if (err)
+			return err;
+	}
+
 	switch (cmode) {
 	case MV88E6XXX_PORT_STS_CMODE_SGMII:
 	case MV88E6XXX_PORT_STS_CMODE_1000BASEX:
 	case MV88E6XXX_PORT_STS_CMODE_2500BASEX:
-		return mv88e6390_serdes_power_sgmii(chip, lane, on);
+		err = mv88e6390_serdes_power_sgmii(chip, lane, on);
+		break;
 	case MV88E6393X_PORT_STS_CMODE_5GBASER:
 	case MV88E6393X_PORT_STS_CMODE_10GBASER:
-		return mv88e6390_serdes_power_10g(chip, lane, on);
+		err = mv88e6390_serdes_power_10g(chip, lane, on);
+		break;
+	default:
+		err = -EINVAL;
+		break;
 	}
 
-	return 0;
+	if (err)
+		return err;
+
+	if (!on) {
+		err = mv88e6393x_serdes_power_lane(chip, lane, false);
+		if (err)
+			return err;
+
+		err = mv88e6393x_serdes_fix_2500basex_an(chip, lane, cmode,
+							 false);
+	}
+
+	return err;
 }
diff --git a/drivers/net/dsa/mv88e6xxx/serdes.h b/drivers/net/dsa/mv88e6xxx/serdes.h
index cbb3ba30caea..8dd8ed225b45 100644
--- a/drivers/net/dsa/mv88e6xxx/serdes.h
+++ b/drivers/net/dsa/mv88e6xxx/serdes.h
@@ -93,6 +93,10 @@
 #define MV88E6393X_SERDES_POC_PCS_MASK		0x0007
 #define MV88E6393X_SERDES_POC_RESET		BIT(15)
 #define MV88E6393X_SERDES_POC_PDOWN		BIT(5)
+#define MV88E6393X_SERDES_POC_AN		BIT(3)
+#define MV88E6393X_SERDES_CTRL1			0xf003
+#define MV88E6393X_SERDES_CTRL1_TX_PDOWN	BIT(9)
+#define MV88E6393X_SERDES_CTRL1_RX_PDOWN	BIT(8)
 
 #define MV88E6393X_ERRATA_4_8_REG		0xF074
 #define MV88E6393X_ERRATA_4_8_BIT		BIT(14)
diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c
index 327cc4654806..f1a05e7dc818 100644
--- a/drivers/net/dsa/ocelot/felix.c
+++ b/drivers/net/dsa/ocelot/felix.c
@@ -290,8 +290,11 @@ static int felix_setup_mmio_filtering(struct felix *felix)
 		}
 	}
 
-	if (cpu < 0)
+	if (cpu < 0) {
+		kfree(tagging_rule);
+		kfree(redirect_rule);
 		return -EINVAL;
+	}
 
 	tagging_rule->key_type = OCELOT_VCAP_KEY_ETYPE;
 	*(__be16 *)tagging_rule->key.etype.etype.value = htons(ETH_P_1588);
diff --git a/drivers/net/dsa/qca8k.c b/drivers/net/dsa/qca8k.c
index a429c9750add..147ca39531a3 100644
--- a/drivers/net/dsa/qca8k.c
+++ b/drivers/net/dsa/qca8k.c
@@ -1256,8 +1256,12 @@ qca8k_setup(struct dsa_switch *ds)
 		/* Set initial MTU for every port.
 		 * We have only have a general MTU setting. So track
 		 * every port and set the max across all port.
+		 * Set per port MTU to 1500 as the MTU change function
+		 * will add the overhead and if its set to 1518 then it
+		 * will apply the overhead again and we will end up with
+		 * MTU of 1536 instead of 1518
 		 */
-		priv->port_mtu[i] = ETH_FRAME_LEN + ETH_FCS_LEN;
+		priv->port_mtu[i] = ETH_DATA_LEN;
 	}
 
 	/* Special GLOBAL_FC_THRESH value are needed for ar8327 switch */
@@ -1433,6 +1437,12 @@ qca8k_phylink_mac_config(struct dsa_switch *ds, int port, unsigned int mode,
 
 		qca8k_write(priv, QCA8K_REG_SGMII_CTRL, val);
 
+		/* From original code is reported port instability as SGMII also
+		 * require delay set. Apply advised values here or take them from DT.
+		 */
+		if (state->interface == PHY_INTERFACE_MODE_SGMII)
+			qca8k_mac_config_setup_internal_delay(priv, cpu_port_index, reg);
+
 		/* For qca8327/qca8328/qca8334/qca8338 sgmii is unique and
 		 * falling edge is set writing in the PORT0 PAD reg
 		 */
@@ -1455,12 +1465,6 @@ qca8k_phylink_mac_config(struct dsa_switch *ds, int port, unsigned int mode,
 					QCA8K_PORT0_PAD_SGMII_TXCLK_FALLING_EDGE,
 					val);
 
-		/* From original code is reported port instability as SGMII also
-		 * require delay set. Apply advised values here or take them from DT.
-		 */
-		if (state->interface == PHY_INTERFACE_MODE_SGMII)
-			qca8k_mac_config_setup_internal_delay(priv, cpu_port_index, reg);
-
 		break;
 	default:
 		dev_err(ds->dev, "xMII mode %s not supported for port %d\n",
diff --git a/drivers/net/dsa/rtl8365mb.c b/drivers/net/dsa/rtl8365mb.c
index baaae97283c5..078ca4cd7160 100644
--- a/drivers/net/dsa/rtl8365mb.c
+++ b/drivers/net/dsa/rtl8365mb.c
@@ -107,6 +107,7 @@
 #define RTL8365MB_LEARN_LIMIT_MAX_8365MB_VC	2112
 
 /* Family-specific data and limits */
+#define RTL8365MB_PHYADDRMAX	7
 #define RTL8365MB_NUM_PHYREGS	32
 #define RTL8365MB_PHYREGMAX	(RTL8365MB_NUM_PHYREGS - 1)
 #define RTL8365MB_MAX_NUM_PORTS	(RTL8365MB_CPU_PORT_NUM_8365MB_VC + 1)
@@ -176,7 +177,7 @@
 #define RTL8365MB_INDIRECT_ACCESS_STATUS_REG			0x1F01
 #define RTL8365MB_INDIRECT_ACCESS_ADDRESS_REG			0x1F02
 #define   RTL8365MB_INDIRECT_ACCESS_ADDRESS_OCPADR_5_1_MASK	GENMASK(4, 0)
-#define   RTL8365MB_INDIRECT_ACCESS_ADDRESS_PHYNUM_MASK		GENMASK(6, 5)
+#define   RTL8365MB_INDIRECT_ACCESS_ADDRESS_PHYNUM_MASK		GENMASK(7, 5)
 #define   RTL8365MB_INDIRECT_ACCESS_ADDRESS_OCPADR_9_6_MASK	GENMASK(11, 8)
 #define   RTL8365MB_PHY_BASE					0x2000
 #define RTL8365MB_INDIRECT_ACCESS_WRITE_DATA_REG		0x1F03
@@ -679,6 +680,9 @@ static int rtl8365mb_phy_read(struct realtek_smi *smi, int phy, int regnum)
 	u16 val;
 	int ret;
 
+	if (phy > RTL8365MB_PHYADDRMAX)
+		return -EINVAL;
+
 	if (regnum > RTL8365MB_PHYREGMAX)
 		return -EINVAL;
 
@@ -704,6 +708,9 @@ static int rtl8365mb_phy_write(struct realtek_smi *smi, int phy, int regnum,
 	u32 ocp_addr;
 	int ret;
 
+	if (phy > RTL8365MB_PHYADDRMAX)
+		return -EINVAL;
+
 	if (regnum > RTL8365MB_PHYREGMAX)
 		return -EINVAL;
 
diff --git a/drivers/net/ethernet/altera/altera_tse_main.c b/drivers/net/ethernet/altera/altera_tse_main.c
index d75d95a97dd9..993b2fb42961 100644
--- a/drivers/net/ethernet/altera/altera_tse_main.c
+++ b/drivers/net/ethernet/altera/altera_tse_main.c
@@ -1430,16 +1430,19 @@ static int altera_tse_probe(struct platform_device *pdev)
 		priv->rxdescmem_busaddr = dma_res->start;
 
 	} else {
+		ret = -ENODEV;
 		goto err_free_netdev;
 	}
 
-	if (!dma_set_mask(priv->device, DMA_BIT_MASK(priv->dmaops->dmamask)))
+	if (!dma_set_mask(priv->device, DMA_BIT_MASK(priv->dmaops->dmamask))) {
 		dma_set_coherent_mask(priv->device,
 				      DMA_BIT_MASK(priv->dmaops->dmamask));
-	else if (!dma_set_mask(priv->device, DMA_BIT_MASK(32)))
+	} else if (!dma_set_mask(priv->device, DMA_BIT_MASK(32))) {
 		dma_set_coherent_mask(priv->device, DMA_BIT_MASK(32));
-	else
+	} else {
+		ret = -EIO;
 		goto err_free_netdev;
+	}
 
 	/* MAC address space */
 	ret = request_and_map(pdev, "control_port", &control_port,
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index 7d5d885d85d5..c72f0c7ff4aa 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -1288,26 +1288,22 @@ static int handle_invalid_req_id(struct ena_ring *ring, u16 req_id,
 
 static int validate_tx_req_id(struct ena_ring *tx_ring, u16 req_id)
 {
-	struct ena_tx_buffer *tx_info = NULL;
+	struct ena_tx_buffer *tx_info;
 
-	if (likely(req_id < tx_ring->ring_size)) {
-		tx_info = &tx_ring->tx_buffer_info[req_id];
-		if (likely(tx_info->skb))
-			return 0;
-	}
+	tx_info = &tx_ring->tx_buffer_info[req_id];
+	if (likely(tx_info->skb))
+		return 0;
 
 	return handle_invalid_req_id(tx_ring, req_id, tx_info, false);
 }
 
 static int validate_xdp_req_id(struct ena_ring *xdp_ring, u16 req_id)
 {
-	struct ena_tx_buffer *tx_info = NULL;
+	struct ena_tx_buffer *tx_info;
 
-	if (likely(req_id < xdp_ring->ring_size)) {
-		tx_info = &xdp_ring->tx_buffer_info[req_id];
-		if (likely(tx_info->xdpf))
-			return 0;
-	}
+	tx_info = &xdp_ring->tx_buffer_info[req_id];
+	if (likely(tx_info->xdpf))
+		return 0;
 
 	return handle_invalid_req_id(xdp_ring, req_id, tx_info, true);
 }
@@ -1332,9 +1328,14 @@ static int ena_clean_tx_irq(struct ena_ring *tx_ring, u32 budget)
 
 		rc = ena_com_tx_comp_req_id_get(tx_ring->ena_com_io_cq,
 						&req_id);
-		if (rc)
+		if (rc) {
+			if (unlikely(rc == -EINVAL))
+				handle_invalid_req_id(tx_ring, req_id, NULL,
+						      false);
 			break;
+		}
 
+		/* validate that the request id points to a valid skb */
 		rc = validate_tx_req_id(tx_ring, req_id);
 		if (rc)
 			break;
@@ -1427,6 +1428,7 @@ static struct sk_buff *ena_rx_skb(struct ena_ring *rx_ring,
 				  u16 *next_to_clean)
 {
 	struct ena_rx_buffer *rx_info;
+	struct ena_adapter *adapter;
 	u16 len, req_id, buf = 0;
 	struct sk_buff *skb;
 	void *page_addr;
@@ -1439,8 +1441,14 @@ static struct sk_buff *ena_rx_skb(struct ena_ring *rx_ring,
 	rx_info = &rx_ring->rx_buffer_info[req_id];
 
 	if (unlikely(!rx_info->page)) {
-		netif_err(rx_ring->adapter, rx_err, rx_ring->netdev,
-			  "Page is NULL\n");
+		adapter = rx_ring->adapter;
+		netif_err(adapter, rx_err, rx_ring->netdev,
+			  "Page is NULL. qid %u req_id %u\n", rx_ring->qid, req_id);
+		ena_increase_stat(&rx_ring->rx_stats.bad_req_id, 1, &rx_ring->syncp);
+		adapter->reset_reason = ENA_REGS_RESET_INV_RX_REQ_ID;
+		/* Make sure reset reason is set before triggering the reset */
+		smp_mb__before_atomic();
+		set_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags);
 		return NULL;
 	}
 
@@ -1896,9 +1904,14 @@ static int ena_clean_xdp_irq(struct ena_ring *xdp_ring, u32 budget)
 
 		rc = ena_com_tx_comp_req_id_get(xdp_ring->ena_com_io_cq,
 						&req_id);
-		if (rc)
+		if (rc) {
+			if (unlikely(rc == -EINVAL))
+				handle_invalid_req_id(xdp_ring, req_id, NULL,
+						      true);
 			break;
+		}
 
+		/* validate that the request id points to a valid xdp_frame */
 		rc = validate_xdp_req_id(xdp_ring, req_id);
 		if (rc)
 			break;
@@ -4013,10 +4026,6 @@ static u32 ena_calc_max_io_queue_num(struct pci_dev *pdev,
 	max_num_io_queues = min_t(u32, max_num_io_queues, io_tx_cq_num);
 	/* 1 IRQ for mgmnt and 1 IRQs for each IO direction */
 	max_num_io_queues = min_t(u32, max_num_io_queues, pci_msix_vec_count(pdev) - 1);
-	if (unlikely(!max_num_io_queues)) {
-		dev_err(&pdev->dev, "The device doesn't have io queues\n");
-		return -EFAULT;
-	}
 
 	return max_num_io_queues;
 }
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_common.h b/drivers/net/ethernet/aquantia/atlantic/aq_common.h
index 23b2d390fcdd..ace691d7cd75 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_common.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_common.h
@@ -40,10 +40,12 @@
 
 #define AQ_DEVICE_ID_AQC113DEV	0x00C0
 #define AQ_DEVICE_ID_AQC113CS	0x94C0
+#define AQ_DEVICE_ID_AQC113CA	0x34C0
 #define AQ_DEVICE_ID_AQC114CS	0x93C0
 #define AQ_DEVICE_ID_AQC113	0x04C0
 #define AQ_DEVICE_ID_AQC113C	0x14C0
 #define AQ_DEVICE_ID_AQC115C	0x12C0
+#define AQ_DEVICE_ID_AQC116C	0x11C0
 
 #define HW_ATL_NIC_NAME "Marvell (aQuantia) AQtion 10Gbit Network Adapter"
 
@@ -53,20 +55,19 @@
 
 #define AQ_NIC_RATE_10G		BIT(0)
 #define AQ_NIC_RATE_5G		BIT(1)
-#define AQ_NIC_RATE_5GSR	BIT(2)
-#define AQ_NIC_RATE_2G5		BIT(3)
-#define AQ_NIC_RATE_1G		BIT(4)
-#define AQ_NIC_RATE_100M	BIT(5)
-#define AQ_NIC_RATE_10M		BIT(6)
-#define AQ_NIC_RATE_1G_HALF	BIT(7)
-#define AQ_NIC_RATE_100M_HALF	BIT(8)
-#define AQ_NIC_RATE_10M_HALF	BIT(9)
+#define AQ_NIC_RATE_2G5		BIT(2)
+#define AQ_NIC_RATE_1G		BIT(3)
+#define AQ_NIC_RATE_100M	BIT(4)
+#define AQ_NIC_RATE_10M		BIT(5)
+#define AQ_NIC_RATE_1G_HALF	BIT(6)
+#define AQ_NIC_RATE_100M_HALF	BIT(7)
+#define AQ_NIC_RATE_10M_HALF	BIT(8)
 
-#define AQ_NIC_RATE_EEE_10G	BIT(10)
-#define AQ_NIC_RATE_EEE_5G	BIT(11)
-#define AQ_NIC_RATE_EEE_2G5	BIT(12)
-#define AQ_NIC_RATE_EEE_1G	BIT(13)
-#define AQ_NIC_RATE_EEE_100M	BIT(14)
+#define AQ_NIC_RATE_EEE_10G	BIT(9)
+#define AQ_NIC_RATE_EEE_5G	BIT(10)
+#define AQ_NIC_RATE_EEE_2G5	BIT(11)
+#define AQ_NIC_RATE_EEE_1G	BIT(12)
+#define AQ_NIC_RATE_EEE_100M	BIT(13)
 #define AQ_NIC_RATE_EEE_MSK     (AQ_NIC_RATE_EEE_10G |\
 				 AQ_NIC_RATE_EEE_5G |\
 				 AQ_NIC_RATE_EEE_2G5 |\
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
index 062a300a566a..dbd284660135 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
@@ -80,6 +80,8 @@ struct aq_hw_link_status_s {
 };
 
 struct aq_stats_s {
+	u64 brc;
+	u64 btc;
 	u64 uprc;
 	u64 mprc;
 	u64 bprc;
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index 1acf544afeb4..33f1a1377588 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -316,18 +316,22 @@ int aq_nic_ndev_register(struct aq_nic_s *self)
 	aq_macsec_init(self);
 #endif
 
-	mutex_lock(&self->fwreq_mutex);
-	err = self->aq_fw_ops->get_mac_permanent(self->aq_hw, addr);
-	mutex_unlock(&self->fwreq_mutex);
-	if (err)
-		goto err_exit;
+	if (platform_get_ethdev_address(&self->pdev->dev, self->ndev) != 0) {
+		// If DT has none or an invalid one, ask device for MAC address
+		mutex_lock(&self->fwreq_mutex);
+		err = self->aq_fw_ops->get_mac_permanent(self->aq_hw, addr);
+		mutex_unlock(&self->fwreq_mutex);
 
-	eth_hw_addr_set(self->ndev, addr);
+		if (err)
+			goto err_exit;
 
-	if (!is_valid_ether_addr(self->ndev->dev_addr) ||
-	    !aq_nic_is_valid_ether_addr(self->ndev->dev_addr)) {
-		netdev_warn(self->ndev, "MAC is invalid, will use random.");
-		eth_hw_addr_random(self->ndev);
+		if (is_valid_ether_addr(addr) &&
+		    aq_nic_is_valid_ether_addr(addr)) {
+			eth_hw_addr_set(self->ndev, addr);
+		} else {
+			netdev_warn(self->ndev, "MAC is invalid, will use random.");
+			eth_hw_addr_random(self->ndev);
+		}
 	}
 
 #if defined(AQ_CFG_MAC_ADDR_PERMANENT)
@@ -905,8 +909,14 @@ u64 *aq_nic_get_stats(struct aq_nic_s *self, u64 *data)
 	data[++i] = stats->mbtc;
 	data[++i] = stats->bbrc;
 	data[++i] = stats->bbtc;
-	data[++i] = stats->ubrc + stats->mbrc + stats->bbrc;
-	data[++i] = stats->ubtc + stats->mbtc + stats->bbtc;
+	if (stats->brc)
+		data[++i] = stats->brc;
+	else
+		data[++i] = stats->ubrc + stats->mbrc + stats->bbrc;
+	if (stats->btc)
+		data[++i] = stats->btc;
+	else
+		data[++i] = stats->ubtc + stats->mbtc + stats->bbtc;
 	data[++i] = stats->dma_pkt_rc;
 	data[++i] = stats->dma_pkt_tc;
 	data[++i] = stats->dma_oct_rc;
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
index d4b1976ee69b..797a95142d1f 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
@@ -49,6 +49,8 @@ static const struct pci_device_id aq_pci_tbl[] = {
 	{ PCI_VDEVICE(AQUANTIA, AQ_DEVICE_ID_AQC113), },
 	{ PCI_VDEVICE(AQUANTIA, AQ_DEVICE_ID_AQC113C), },
 	{ PCI_VDEVICE(AQUANTIA, AQ_DEVICE_ID_AQC115C), },
+	{ PCI_VDEVICE(AQUANTIA, AQ_DEVICE_ID_AQC113CA), },
+	{ PCI_VDEVICE(AQUANTIA, AQ_DEVICE_ID_AQC116C), },
 
 	{}
 };
@@ -85,7 +87,10 @@ static const struct aq_board_revision_s hw_atl_boards[] = {
 	{ AQ_DEVICE_ID_AQC113CS,	AQ_HWREV_ANY,	&hw_atl2_ops, &hw_atl2_caps_aqc113, },
 	{ AQ_DEVICE_ID_AQC114CS,	AQ_HWREV_ANY,	&hw_atl2_ops, &hw_atl2_caps_aqc113, },
 	{ AQ_DEVICE_ID_AQC113C,		AQ_HWREV_ANY,	&hw_atl2_ops, &hw_atl2_caps_aqc113, },
-	{ AQ_DEVICE_ID_AQC115C,		AQ_HWREV_ANY,	&hw_atl2_ops, &hw_atl2_caps_aqc113, },
+	{ AQ_DEVICE_ID_AQC115C,		AQ_HWREV_ANY,	&hw_atl2_ops, &hw_atl2_caps_aqc115c, },
+	{ AQ_DEVICE_ID_AQC113CA,	AQ_HWREV_ANY,	&hw_atl2_ops, &hw_atl2_caps_aqc113, },
+	{ AQ_DEVICE_ID_AQC116C,		AQ_HWREV_ANY,	&hw_atl2_ops, &hw_atl2_caps_aqc116c, },
+
 };
 
 MODULE_DEVICE_TABLE(pci, aq_pci_tbl);
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
index 24122ccda614..77e76c9efd32 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
@@ -298,13 +298,14 @@ bool aq_ring_tx_clean(struct aq_ring_s *self)
 			}
 		}
 
-		if (unlikely(buff->is_eop)) {
+		if (unlikely(buff->is_eop && buff->skb)) {
 			u64_stats_update_begin(&self->stats.tx.syncp);
 			++self->stats.tx.packets;
 			self->stats.tx.bytes += buff->skb->len;
 			u64_stats_update_end(&self->stats.tx.syncp);
 
 			dev_kfree_skb_any(buff->skb);
+			buff->skb = NULL;
 		}
 		buff->pa = 0U;
 		buff->eop_index = 0xffffU;
@@ -365,6 +366,10 @@ int aq_ring_rx_clean(struct aq_ring_s *self,
 		if (!buff->is_eop) {
 			buff_ = buff;
 			do {
+				if (buff_->next >= self->size) {
+					err = -EIO;
+					goto err_exit;
+				}
 				next_ = buff_->next,
 				buff_ = &self->buff_ring[next_];
 				is_rsc_completed =
@@ -388,6 +393,10 @@ int aq_ring_rx_clean(struct aq_ring_s *self,
 			    (buff->is_lro && buff->is_cso_err)) {
 				buff_ = buff;
 				do {
+					if (buff_->next >= self->size) {
+						err = -EIO;
+						goto err_exit;
+					}
 					next_ = buff_->next,
 					buff_ = &self->buff_ring[next_];
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_vec.c b/drivers/net/ethernet/aquantia/atlantic/aq_vec.c
index d281322d7dd2..f4774cf051c9 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_vec.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_vec.c
@@ -362,9 +362,6 @@ unsigned int aq_vec_get_sw_stats(struct aq_vec_s *self, const unsigned int tc, u
 {
 	unsigned int count;
 
-	WARN_ONCE(!aq_vec_is_valid_tc(self, tc),
-		  "Invalid tc %u (#rx=%u, #tx=%u)\n",
-		  tc, self->rx_rings, self->tx_rings);
 	if (!aq_vec_is_valid_tc(self, tc))
 		return 0;
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
index fc0e66006644..7e88d7234b14 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
@@ -559,6 +559,11 @@ int hw_atl_utils_fw_rpc_wait(struct aq_hw_s *self,
 			goto err_exit;
 
 		if (fw.len == 0xFFFFU) {
+			if (sw.len > sizeof(self->rpc)) {
+				printk(KERN_INFO "Invalid sw len: %x\n", sw.len);
+				err = -EINVAL;
+				goto err_exit;
+			}
 			err = hw_atl_utils_fw_rpc_call(self, sw.len);
 			if (err < 0)
 				goto err_exit;
@@ -567,6 +572,11 @@ int hw_atl_utils_fw_rpc_wait(struct aq_hw_s *self,
 
 	if (rpc) {
 		if (fw.len) {
+			if (fw.len > sizeof(self->rpc)) {
+				printk(KERN_INFO "Invalid fw len: %x\n", fw.len);
+				err = -EINVAL;
+				goto err_exit;
+			}
 			err =
 			hw_atl_utils_fw_downld_dwords(self,
 						      self->rpc_addr,
@@ -857,12 +867,20 @@ static int hw_atl_fw1x_deinit(struct aq_hw_s *self)
 int hw_atl_utils_update_stats(struct aq_hw_s *self)
 {
 	struct aq_stats_s *cs = &self->curr_stats;
+	struct aq_stats_s curr_stats = *cs;
 	struct hw_atl_utils_mbox mbox;
+	bool corrupted_stats = false;
 
 	hw_atl_utils_mpi_read_stats(self, &mbox);
 
-#define AQ_SDELTA(_N_) (self->curr_stats._N_ += \
-			mbox.stats._N_ - self->last_stats._N_)
+#define AQ_SDELTA(_N_)  \
+do { \
+	if (!corrupted_stats && \
+	    ((s64)(mbox.stats._N_ - self->last_stats._N_)) >= 0) \
+		curr_stats._N_ += mbox.stats._N_ - self->last_stats._N_; \
+	else \
+		corrupted_stats = true; \
+} while (0)
 
 	if (self->aq_link_status.mbps) {
 		AQ_SDELTA(uprc);
@@ -882,6 +900,9 @@ int hw_atl_utils_update_stats(struct aq_hw_s *self)
 		AQ_SDELTA(bbrc);
 		AQ_SDELTA(bbtc);
 		AQ_SDELTA(dpc);
+
+		if (!corrupted_stats)
+			*cs = curr_stats;
 	}
 #undef AQ_SDELTA
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c
index eac631c45c56..4d4cfbc91e19 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c
@@ -132,9 +132,6 @@ static enum hw_atl_fw2x_rate link_speed_mask_2fw2x_ratemask(u32 speed)
 	if (speed & AQ_NIC_RATE_5G)
 		rate |= FW2X_RATE_5G;
 
-	if (speed & AQ_NIC_RATE_5GSR)
-		rate |= FW2X_RATE_5G;
-
 	if (speed & AQ_NIC_RATE_2G5)
 		rate |= FW2X_RATE_2G5;
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c
index c98708bb044c..5dfc751572ed 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c
@@ -65,11 +65,25 @@ const struct aq_hw_caps_s hw_atl2_caps_aqc113 = {
 			  AQ_NIC_RATE_5G  |
 			  AQ_NIC_RATE_2G5 |
 			  AQ_NIC_RATE_1G  |
-			  AQ_NIC_RATE_1G_HALF   |
 			  AQ_NIC_RATE_100M      |
-			  AQ_NIC_RATE_100M_HALF |
-			  AQ_NIC_RATE_10M       |
-			  AQ_NIC_RATE_10M_HALF,
+			  AQ_NIC_RATE_10M,
+};
+
+const struct aq_hw_caps_s hw_atl2_caps_aqc115c = {
+	DEFAULT_BOARD_BASIC_CAPABILITIES,
+	.media_type = AQ_HW_MEDIA_TYPE_TP,
+	.link_speed_msk = AQ_NIC_RATE_2G5 |
+			  AQ_NIC_RATE_1G  |
+			  AQ_NIC_RATE_100M      |
+			  AQ_NIC_RATE_10M,
+};
+
+const struct aq_hw_caps_s hw_atl2_caps_aqc116c = {
+	DEFAULT_BOARD_BASIC_CAPABILITIES,
+	.media_type = AQ_HW_MEDIA_TYPE_TP,
+	.link_speed_msk = AQ_NIC_RATE_1G  |
+			  AQ_NIC_RATE_100M      |
+			  AQ_NIC_RATE_10M,
 };
 
 static u32 hw_atl2_sem_act_rslvr_get(struct aq_hw_s *self)
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.h
index de8723f1c28a..346f0dc9912e 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.h
@@ -9,6 +9,8 @@
 #include "aq_common.h"
 
 extern const struct aq_hw_caps_s hw_atl2_caps_aqc113;
+extern const struct aq_hw_caps_s hw_atl2_caps_aqc115c;
+extern const struct aq_hw_caps_s hw_atl2_caps_aqc116c;
 extern const struct aq_hw_ops hw_atl2_ops;
 
 #endif /* HW_ATL2_H */
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils.h
index b66fa346581c..6bad64c77b87 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils.h
@@ -239,7 +239,8 @@ struct version_s {
 		u8 minor;
 		u16 build;
 	} phy;
-	u32 rsvd;
+	u32 drv_iface_ver:4;
+	u32 rsvd:28;
 };
 
 struct link_status_s {
@@ -424,7 +425,7 @@ struct cable_diag_status_s {
 	u16 rsvd2;
 };
 
-struct statistics_s {
+struct statistics_a0_s {
 	struct {
 		u32 link_up;
 		u32 link_down;
@@ -457,6 +458,33 @@ struct statistics_s {
 	u32 reserve_fw_gap;
 };
 
+struct __packed statistics_b0_s {
+	u64 rx_good_octets;
+	u64 rx_pause_frames;
+	u64 rx_good_frames;
+	u64 rx_errors;
+	u64 rx_unicast_frames;
+	u64 rx_multicast_frames;
+	u64 rx_broadcast_frames;
+
+	u64 tx_good_octets;
+	u64 tx_pause_frames;
+	u64 tx_good_frames;
+	u64 tx_errors;
+	u64 tx_unicast_frames;
+	u64 tx_multicast_frames;
+	u64 tx_broadcast_frames;
+
+	u32 main_loop_cycles;
+};
+
+struct __packed statistics_s {
+	union __packed {
+		struct statistics_a0_s a0;
+		struct statistics_b0_s b0;
+	};
+};
+
 struct filter_caps_s {
 	u8 l2_filters_base_index:6;
 	u8 flexible_filter_mask:2;
@@ -545,7 +573,7 @@ struct management_status_s {
 	u32 rsvd5;
 };
 
-struct fw_interface_out {
+struct __packed fw_interface_out {
 	struct transaction_counter_s transaction_id;
 	struct version_s version;
 	struct link_status_s link_status;
@@ -569,7 +597,6 @@ struct fw_interface_out {
 	struct core_dump_s core_dump;
 	u32 rsvd11;
 	struct statistics_s stats;
-	u32 rsvd12;
 	struct filter_caps_s filter_caps;
 	struct device_caps_s device_caps;
 	u32 rsvd13;
@@ -592,6 +619,9 @@ struct fw_interface_out {
 #define  AQ_HOST_MODE_LOW_POWER    3U
 #define  AQ_HOST_MODE_SHUTDOWN     4U
 
+#define  AQ_A2_FW_INTERFACE_A0     0
+#define  AQ_A2_FW_INTERFACE_B0     1
+
 int hw_atl2_utils_initfw(struct aq_hw_s *self, const struct aq_fw_ops **fw_ops);
 
 int hw_atl2_utils_soft_reset(struct aq_hw_s *self);
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils_fw.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils_fw.c
index dd259c8f2f4f..58d426dda3ed 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils_fw.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils_fw.c
@@ -84,7 +84,7 @@ static int hw_atl2_shared_buffer_read_block(struct aq_hw_s *self,
 			if (cnt > AQ_A2_FW_READ_TRY_MAX)
 				return -ETIME;
 			if (tid1.transaction_cnt_a != tid1.transaction_cnt_b)
-				udelay(1);
+				mdelay(1);
 		} while (tid1.transaction_cnt_a != tid1.transaction_cnt_b);
 
 		hw_atl2_mif_shared_buf_read(self, offset, (u32 *)data, dwords);
@@ -154,7 +154,7 @@ static void a2_link_speed_mask2fw(u32 speed,
 {
 	link_options->rate_10G = !!(speed & AQ_NIC_RATE_10G);
 	link_options->rate_5G = !!(speed & AQ_NIC_RATE_5G);
-	link_options->rate_N5G = !!(speed & AQ_NIC_RATE_5GSR);
+	link_options->rate_N5G = link_options->rate_5G;
 	link_options->rate_2P5G = !!(speed & AQ_NIC_RATE_2G5);
 	link_options->rate_N2P5G = link_options->rate_2P5G;
 	link_options->rate_1G = !!(speed & AQ_NIC_RATE_1G);
@@ -192,8 +192,6 @@ static u32 a2_fw_lkp_to_mask(struct lkp_link_caps_s *lkp_link_caps)
 		rate |= AQ_NIC_RATE_10G;
 	if (lkp_link_caps->rate_5G)
 		rate |= AQ_NIC_RATE_5G;
-	if (lkp_link_caps->rate_N5G)
-		rate |= AQ_NIC_RATE_5GSR;
 	if (lkp_link_caps->rate_2P5G)
 		rate |= AQ_NIC_RATE_2G5;
 	if (lkp_link_caps->rate_1G)
@@ -335,15 +333,22 @@ static int aq_a2_fw_get_mac_permanent(struct aq_hw_s *self, u8 *mac)
 	return 0;
 }
 
-static int aq_a2_fw_update_stats(struct aq_hw_s *self)
+static void aq_a2_fill_a0_stats(struct aq_hw_s *self,
+				struct statistics_s *stats)
 {
 	struct hw_atl2_priv *priv = (struct hw_atl2_priv *)self->priv;
-	struct statistics_s stats;
-
-	hw_atl2_shared_buffer_read_safe(self, stats, &stats);
-
-#define AQ_SDELTA(_N_, _F_) (self->curr_stats._N_ += \
-			stats.msm._F_ - priv->last_stats.msm._F_)
+	struct aq_stats_s *cs = &self->curr_stats;
+	struct aq_stats_s curr_stats = *cs;
+	bool corrupted_stats = false;
+
+#define AQ_SDELTA(_N, _F)  \
+do { \
+	if (!corrupted_stats && \
+	    ((s64)(stats->a0.msm._F - priv->last_stats.a0.msm._F)) >= 0) \
+		curr_stats._N += stats->a0.msm._F - priv->last_stats.a0.msm._F;\
+	else \
+		corrupted_stats = true; \
+} while (0)
 
 	if (self->aq_link_status.mbps) {
 		AQ_SDELTA(uprc, rx_unicast_frames);
@@ -362,17 +367,76 @@ static int aq_a2_fw_update_stats(struct aq_hw_s *self)
 		AQ_SDELTA(mbtc, tx_multicast_octets);
 		AQ_SDELTA(bbrc, rx_broadcast_octets);
 		AQ_SDELTA(bbtc, tx_broadcast_octets);
+
+		if (!corrupted_stats)
+			*cs = curr_stats;
 	}
 #undef AQ_SDELTA
-	self->curr_stats.dma_pkt_rc =
-		hw_atl_stats_rx_dma_good_pkt_counter_get(self);
-	self->curr_stats.dma_pkt_tc =
-		hw_atl_stats_tx_dma_good_pkt_counter_get(self);
-	self->curr_stats.dma_oct_rc =
-		hw_atl_stats_rx_dma_good_octet_counter_get(self);
-	self->curr_stats.dma_oct_tc =
-		hw_atl_stats_tx_dma_good_octet_counter_get(self);
-	self->curr_stats.dpc = hw_atl_rpb_rx_dma_drop_pkt_cnt_get(self);
+
+}
+
+static void aq_a2_fill_b0_stats(struct aq_hw_s *self,
+				struct statistics_s *stats)
+{
+	struct hw_atl2_priv *priv = (struct hw_atl2_priv *)self->priv;
+	struct aq_stats_s *cs = &self->curr_stats;
+	struct aq_stats_s curr_stats = *cs;
+	bool corrupted_stats = false;
+
+#define AQ_SDELTA(_N, _F)  \
+do { \
+	if (!corrupted_stats && \
+	    ((s64)(stats->b0._F - priv->last_stats.b0._F)) >= 0) \
+		curr_stats._N += stats->b0._F - priv->last_stats.b0._F; \
+	else \
+		corrupted_stats = true; \
+} while (0)
+
+	if (self->aq_link_status.mbps) {
+		AQ_SDELTA(uprc, rx_unicast_frames);
+		AQ_SDELTA(mprc, rx_multicast_frames);
+		AQ_SDELTA(bprc, rx_broadcast_frames);
+		AQ_SDELTA(erpr, rx_errors);
+		AQ_SDELTA(brc, rx_good_octets);
+
+		AQ_SDELTA(uptc, tx_unicast_frames);
+		AQ_SDELTA(mptc, tx_multicast_frames);
+		AQ_SDELTA(bptc, tx_broadcast_frames);
+		AQ_SDELTA(erpt, tx_errors);
+		AQ_SDELTA(btc, tx_good_octets);
+
+		if (!corrupted_stats)
+			*cs = curr_stats;
+	}
+#undef AQ_SDELTA
+}
+
+static int aq_a2_fw_update_stats(struct aq_hw_s *self)
+{
+	struct hw_atl2_priv *priv = (struct hw_atl2_priv *)self->priv;
+	struct aq_stats_s *cs = &self->curr_stats;
+	struct statistics_s stats;
+	struct version_s version;
+	int err;
+
+	err = hw_atl2_shared_buffer_read_safe(self, version, &version);
+	if (err)
+		return err;
+
+	err = hw_atl2_shared_buffer_read_safe(self, stats, &stats);
+	if (err)
+		return err;
+
+	if (version.drv_iface_ver == AQ_A2_FW_INTERFACE_A0)
+		aq_a2_fill_a0_stats(self, &stats);
+	else
+		aq_a2_fill_b0_stats(self, &stats);
+
+	cs->dma_pkt_rc = hw_atl_stats_rx_dma_good_pkt_counter_get(self);
+	cs->dma_pkt_tc = hw_atl_stats_tx_dma_good_pkt_counter_get(self);
+	cs->dma_oct_rc = hw_atl_stats_rx_dma_good_octet_counter_get(self);
+	cs->dma_oct_tc = hw_atl_stats_tx_dma_good_octet_counter_get(self);
+	cs->dpc = hw_atl_rpb_rx_dma_drop_pkt_cnt_get(self);
 
 	memcpy(&priv->last_stats, &stats, sizeof(stats));
 
@@ -499,9 +563,9 @@ u32 hw_atl2_utils_get_fw_version(struct aq_hw_s *self)
 	hw_atl2_shared_buffer_read_safe(self, version, &version);
 
 	/* A2 FW version is stored in reverse order */
-	return version.mac.major << 24 |
-	       version.mac.minor << 16 |
-	       version.mac.build;
+	return version.bundle.major << 24 |
+	       version.bundle.minor << 16 |
+	       version.bundle.build;
 }
 
 int hw_atl2_utils_get_action_resolve_table_caps(struct aq_hw_s *self,
diff --git a/drivers/net/ethernet/asix/ax88796c_main.h b/drivers/net/ethernet/asix/ax88796c_main.h
index 80263c3cef75..4a83c991dcbe 100644
--- a/drivers/net/ethernet/asix/ax88796c_main.h
+++ b/drivers/net/ethernet/asix/ax88796c_main.h
@@ -127,9 +127,9 @@ struct ax88796c_device {
 		#define AX_PRIV_FLAGS_MASK	(AX_CAP_COMP)
 
 	unsigned long		flags;
-		#define EVENT_INTR		BIT(0)
-		#define EVENT_TX		BIT(1)
-		#define EVENT_SET_MULTI		BIT(2)
+		#define EVENT_INTR		0
+		#define EVENT_TX		1
+		#define EVENT_SET_MULTI		2
 
 };
 
diff --git a/drivers/net/ethernet/asix/ax88796c_spi.c b/drivers/net/ethernet/asix/ax88796c_spi.c
index 94df4f96d2be..0710e716d682 100644
--- a/drivers/net/ethernet/asix/ax88796c_spi.c
+++ b/drivers/net/ethernet/asix/ax88796c_spi.c
@@ -34,7 +34,7 @@ int axspi_read_status(struct axspi_data *ax_spi, struct spi_status *status)
 
 	/* OP */
 	ax_spi->cmd_buf[0] = AX_SPICMD_READ_STATUS;
-	ret = spi_write_then_read(ax_spi->spi, ax_spi->cmd_buf, 1, (u8 *)&status, 3);
+	ret = spi_write_then_read(ax_spi->spi, ax_spi->cmd_buf, 1, (u8 *)status, 3);
 	if (ret)
 		dev_err(&ax_spi->spi->dev, "%s() failed: ret = %d\n", __func__, ret);
 	else
diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c
index 88d2ab748399..4579ddf9c427 100644
--- a/drivers/net/ethernet/atheros/ag71xx.c
+++ b/drivers/net/ethernet/atheros/ag71xx.c
@@ -1913,15 +1913,12 @@ static int ag71xx_probe(struct platform_device *pdev)
 	ag->mac_reset = devm_reset_control_get(&pdev->dev, "mac");
 	if (IS_ERR(ag->mac_reset)) {
 		netif_err(ag, probe, ndev, "missing mac reset\n");
-		err = PTR_ERR(ag->mac_reset);
-		goto err_free;
+		return PTR_ERR(ag->mac_reset);
 	}
 
 	ag->mac_base = devm_ioremap(&pdev->dev, res->start, resource_size(res));
-	if (!ag->mac_base) {
-		err = -ENOMEM;
-		goto err_free;
-	}
+	if (!ag->mac_base)
+		return -ENOMEM;
 
 	ndev->irq = platform_get_irq(pdev, 0);
 	err = devm_request_irq(&pdev->dev, ndev->irq, ag71xx_interrupt,
@@ -1929,7 +1926,7 @@ static int ag71xx_probe(struct platform_device *pdev)
 	if (err) {
 		netif_err(ag, probe, ndev, "unable to request IRQ %d\n",
 			  ndev->irq);
-		goto err_free;
+		return err;
 	}
 
 	ndev->netdev_ops = &ag71xx_netdev_ops;
@@ -1957,10 +1954,8 @@ static int ag71xx_probe(struct platform_device *pdev)
 	ag->stop_desc = dmam_alloc_coherent(&pdev->dev,
 					    sizeof(struct ag71xx_desc),
 					    &ag->stop_desc_dma, GFP_KERNEL);
-	if (!ag->stop_desc) {
-		err = -ENOMEM;
-		goto err_free;
-	}
+	if (!ag->stop_desc)
+		return -ENOMEM;
 
 	ag->stop_desc->data = 0;
 	ag->stop_desc->ctrl = 0;
@@ -1975,7 +1970,7 @@ static int ag71xx_probe(struct platform_device *pdev)
 	err = of_get_phy_mode(np, &ag->phy_if_mode);
 	if (err) {
 		netif_err(ag, probe, ndev, "missing phy-mode property in DT\n");
-		goto err_free;
+		return err;
 	}
 
 	netif_napi_add(ndev, &ag->napi, ag71xx_poll, AG71XX_NAPI_WEIGHT);
@@ -1983,7 +1978,7 @@ static int ag71xx_probe(struct platform_device *pdev)
 	err = clk_prepare_enable(ag->clk_eth);
 	if (err) {
 		netif_err(ag, probe, ndev, "Failed to enable eth clk.\n");
-		goto err_free;
+		return err;
 	}
 
 	ag71xx_wr(ag, AG71XX_REG_MAC_CFG1, 0);
@@ -2019,8 +2014,6 @@ err_mdio_remove:
 	ag71xx_mdio_remove(ag);
 err_put_clk:
 	clk_disable_unprepare(ag->clk_eth);
-err_free:
-	free_netdev(ndev);
 	return err;
 }
 
diff --git a/drivers/net/ethernet/broadcom/bcm4908_enet.c b/drivers/net/ethernet/broadcom/bcm4908_enet.c
index 7cc5213c575a..b07cb9bc5f2d 100644
--- a/drivers/net/ethernet/broadcom/bcm4908_enet.c
+++ b/drivers/net/ethernet/broadcom/bcm4908_enet.c
@@ -708,7 +708,9 @@ static int bcm4908_enet_probe(struct platform_device *pdev)
 
 	enet->irq_tx = platform_get_irq_byname(pdev, "tx");
 
-	dma_set_coherent_mask(dev, DMA_BIT_MASK(32));
+	err = dma_set_coherent_mask(dev, DMA_BIT_MASK(32));
+	if (err)
+		return err;
 
 	err = bcm4908_enet_dma_alloc(enet);
 	if (err)
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index 40933bf5a710..60dde29974bf 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -1309,11 +1309,11 @@ static netdev_tx_t bcm_sysport_xmit(struct sk_buff *skb,
 	struct bcm_sysport_priv *priv = netdev_priv(dev);
 	struct device *kdev = &priv->pdev->dev;
 	struct bcm_sysport_tx_ring *ring;
+	unsigned long flags, desc_flags;
 	struct bcm_sysport_cb *cb;
 	struct netdev_queue *txq;
 	u32 len_status, addr_lo;
 	unsigned int skb_len;
-	unsigned long flags;
 	dma_addr_t mapping;
 	u16 queue;
 	int ret;
@@ -1373,8 +1373,10 @@ static netdev_tx_t bcm_sysport_xmit(struct sk_buff *skb,
 	ring->desc_count--;
 
 	/* Ports are latched, so write upper address first */
+	spin_lock_irqsave(&priv->desc_lock, desc_flags);
 	tdma_writel(priv, len_status, TDMA_WRITE_PORT_HI(ring->index));
 	tdma_writel(priv, addr_lo, TDMA_WRITE_PORT_LO(ring->index));
+	spin_unlock_irqrestore(&priv->desc_lock, desc_flags);
 
 	/* Check ring space and update SW control flow */
 	if (ring->desc_count == 0)
@@ -2013,6 +2015,7 @@ static int bcm_sysport_open(struct net_device *dev)
 	}
 
 	/* Initialize both hardware and software ring */
+	spin_lock_init(&priv->desc_lock);
 	for (i = 0; i < dev->num_tx_queues; i++) {
 		ret = bcm_sysport_init_tx_ring(priv, i);
 		if (ret) {
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.h b/drivers/net/ethernet/broadcom/bcmsysport.h
index 984f76e74b43..16b73bb9acc7 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.h
+++ b/drivers/net/ethernet/broadcom/bcmsysport.h
@@ -711,6 +711,7 @@ struct bcm_sysport_priv {
 	int			wol_irq;
 
 	/* Transmit rings */
+	spinlock_t		desc_lock;
 	struct bcm_sysport_tx_ring *tx_rings;
 
 	/* Receive queue */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init_ops.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init_ops.h
index 1835d2e451c0..fc7fce642666 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init_ops.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init_ops.h
@@ -635,11 +635,13 @@ static int bnx2x_ilt_client_mem_op(struct bnx2x *bp, int cli_num,
 {
 	int i, rc;
 	struct bnx2x_ilt *ilt = BP_ILT(bp);
-	struct ilt_client_info *ilt_cli = &ilt->clients[cli_num];
+	struct ilt_client_info *ilt_cli;
 
 	if (!ilt || !ilt->lines)
 		return -1;
 
+	ilt_cli = &ilt->clients[cli_num];
+
 	if (ilt_cli->flags & (ILT_CLIENT_SKIP_INIT | ILT_CLIENT_SKIP_MEM))
 		return 0;
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index d0d5da9b78f8..4c9507d82fd0 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -2258,6 +2258,16 @@ static inline void bnxt_db_write(struct bnxt *bp, struct bnxt_db_info *db,
 	}
 }
 
+/* Must hold rtnl_lock */
+static inline bool bnxt_sriov_cfg(struct bnxt *bp)
+{
+#if defined(CONFIG_BNXT_SRIOV)
+	return BNXT_PF(bp) && (bp->pf.active_vfs || bp->sriov_cfg);
+#else
+	return false;
+#endif
+}
+
 extern const u16 bnxt_lhint_arr[];
 
 int bnxt_alloc_rx_data(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
index 5c464ea73576..951c4c569a9b 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
@@ -360,7 +360,7 @@ bnxt_dl_livepatch_report_err(struct bnxt *bp, struct netlink_ext_ack *extack,
 		NL_SET_ERR_MSG_MOD(extack, "Live patch already applied");
 		break;
 	default:
-		netdev_err(bp->dev, "Unexpected live patch error: %hhd\n", err);
+		netdev_err(bp->dev, "Unexpected live patch error: %d\n", err);
 		NL_SET_ERR_MSG_MOD(extack, "Failed to activate live patch");
 		break;
 	}
@@ -441,12 +441,13 @@ static int bnxt_dl_reload_down(struct devlink *dl, bool netns_change,
 
 	switch (action) {
 	case DEVLINK_RELOAD_ACTION_DRIVER_REINIT: {
-		if (BNXT_PF(bp) && bp->pf.active_vfs) {
+		rtnl_lock();
+		if (bnxt_sriov_cfg(bp)) {
 			NL_SET_ERR_MSG_MOD(extack,
-					   "reload is unsupported when VFs are allocated");
+					   "reload is unsupported while VFs are allocated or being configured");
+			rtnl_unlock();
 			return -EOPNOTSUPP;
 		}
-		rtnl_lock();
 		if (bp->dev->reg_state == NETREG_UNREGISTERED) {
 			rtnl_unlock();
 			return -ENODEV;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
index e6a4a768b10b..1471b6130a2b 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
@@ -1868,7 +1868,7 @@ static int bnxt_tc_setup_indr_block_cb(enum tc_setup_type type,
 	struct flow_cls_offload *flower = type_data;
 	struct bnxt *bp = priv->bp;
 
-	if (flower->common.chain_index)
+	if (!tc_cls_can_offload_and_chain0(bp->dev, type_data))
 		return -EOPNOTSUPP;
 
 	switch (type) {
diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c
index 5f259641437a..c888ddee1fc4 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmmii.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c
@@ -589,9 +589,9 @@ static int bcmgenet_mii_pd_init(struct bcmgenet_priv *priv)
 		 * Internal or external PHY with MDIO access
 		 */
 		phydev = phy_attach(priv->dev, phy_name, pd->phy_interface);
-		if (!phydev) {
+		if (IS_ERR(phydev)) {
 			dev_err(kdev, "failed to register PHY device\n");
-			return -ENODEV;
+			return PTR_ERR(phydev);
 		}
 	} else {
 		/*
diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
index 64479c464b4e..ae9cca768d74 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
@@ -3196,6 +3196,7 @@ static int cxgb4vf_pci_probe(struct pci_dev *pdev,
 	}
 	if (adapter->registered_device_map == 0) {
 		dev_err(&pdev->dev, "could not register any net devices\n");
+		err = -EINVAL;
 		goto err_disable_interrupts;
 	}
 
diff --git a/drivers/net/ethernet/dec/tulip/de4x5.c b/drivers/net/ethernet/dec/tulip/de4x5.c
index 13121c4dcfe6..71730ef4cd57 100644
--- a/drivers/net/ethernet/dec/tulip/de4x5.c
+++ b/drivers/net/ethernet/dec/tulip/de4x5.c
@@ -4709,6 +4709,10 @@ type3_infoblock(struct net_device *dev, u_char count, u_char *p)
         lp->ibn = 3;
         lp->active = *p++;
 	if (MOTO_SROM_BUG) lp->active = 0;
+	/* if (MOTO_SROM_BUG) statement indicates lp->active could
+	 * be 8 (i.e. the size of array lp->phy) */
+	if (WARN_ON(lp->active >= ARRAY_SIZE(lp->phy)))
+		return -EINVAL;
 	lp->phy[lp->active].gep = (*p ? p : NULL); p += (2 * (*p) + 1);
 	lp->phy[lp->active].rst = (*p ? p : NULL); p += (2 * (*p) + 1);
 	lp->phy[lp->active].mc  = get_unaligned_le16(p); p += 2;
@@ -5000,19 +5004,23 @@ mii_get_phy(struct net_device *dev)
 	}
 	if ((j == limit) && (i < DE4X5_MAX_MII)) {
 	    for (k=0; k < DE4X5_MAX_PHY && lp->phy[k].id; k++);
-	    lp->phy[k].addr = i;
-	    lp->phy[k].id = id;
-	    lp->phy[k].spd.reg = GENERIC_REG;      /* ANLPA register         */
-	    lp->phy[k].spd.mask = GENERIC_MASK;    /* 100Mb/s technologies   */
-	    lp->phy[k].spd.value = GENERIC_VALUE;  /* TX & T4, H/F Duplex    */
-	    lp->mii_cnt++;
-	    lp->active++;
-	    printk("%s: Using generic MII device control. If the board doesn't operate,\nplease mail the following dump to the author:\n", dev->name);
-	    j = de4x5_debug;
-	    de4x5_debug |= DEBUG_MII;
-	    de4x5_dbg_mii(dev, k);
-	    de4x5_debug = j;
-	    printk("\n");
+	    if (k < DE4X5_MAX_PHY) {
+		lp->phy[k].addr = i;
+		lp->phy[k].id = id;
+		lp->phy[k].spd.reg = GENERIC_REG;      /* ANLPA register         */
+		lp->phy[k].spd.mask = GENERIC_MASK;    /* 100Mb/s technologies   */
+		lp->phy[k].spd.value = GENERIC_VALUE;  /* TX & T4, H/F Duplex    */
+		lp->mii_cnt++;
+		lp->active++;
+		printk("%s: Using generic MII device control. If the board doesn't operate,\nplease mail the following dump to the author:\n", dev->name);
+		j = de4x5_debug;
+		de4x5_debug |= DEBUG_MII;
+		de4x5_dbg_mii(dev, k);
+		de4x5_debug = j;
+		printk("\n");
+	    } else {
+		goto purgatory;
+	    }
 	}
     }
   purgatory:
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index 714e961e7a77..8e643567abce 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -4550,10 +4550,12 @@ static int dpaa2_eth_remove(struct fsl_mc_device *ls_dev)
 
 	fsl_mc_portal_free(priv->mc_io);
 
-	free_netdev(net_dev);
+	destroy_workqueue(priv->dpaa2_ptp_wq);
 
 	dev_dbg(net_dev->dev.parent, "Removed interface %s\n", net_dev->name);
 
+	free_netdev(net_dev);
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
index 2085844227fe..e54e70ebdd05 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
@@ -388,6 +388,8 @@ struct dpaa2_eth_ch_stats {
 	__u64 bytes_per_cdan;
 };
 
+#define DPAA2_ETH_CH_STATS	7
+
 /* Maximum number of queues associated with a DPNI */
 #define DPAA2_ETH_MAX_TCS		8
 #define DPAA2_ETH_MAX_RX_QUEUES_PER_TC	16
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
index adb8ce5306ee..3fdbf87dccb1 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
@@ -278,7 +278,7 @@ static void dpaa2_eth_get_ethtool_stats(struct net_device *net_dev,
 	/* Per-channel stats */
 	for (k = 0; k < priv->num_channels; k++) {
 		ch_stats = &priv->channel[k]->stats;
-		for (j = 0; j < sizeof(*ch_stats) / sizeof(__u64) - 1; j++)
+		for (j = 0; j < DPAA2_ETH_CH_STATS; j++)
 			*((__u64 *)data + i + j) += *((__u64 *)ch_stats + j);
 	}
 	i += j;
diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h
index 7b4961daa254..ed7301b69169 100644
--- a/drivers/net/ethernet/freescale/fec.h
+++ b/drivers/net/ethernet/freescale/fec.h
@@ -377,6 +377,9 @@ struct bufdesc_ex {
 #define FEC_ENET_WAKEUP	((uint)0x00020000)	/* Wakeup request */
 #define FEC_ENET_TXF	(FEC_ENET_TXF_0 | FEC_ENET_TXF_1 | FEC_ENET_TXF_2)
 #define FEC_ENET_RXF	(FEC_ENET_RXF_0 | FEC_ENET_RXF_1 | FEC_ENET_RXF_2)
+#define FEC_ENET_RXF_GET(X)	(((X) == 0) ? FEC_ENET_RXF_0 :	\
+				(((X) == 1) ? FEC_ENET_RXF_1 :	\
+				FEC_ENET_RXF_2))
 #define FEC_ENET_TS_AVAIL       ((uint)0x00010000)
 #define FEC_ENET_TS_TIMER       ((uint)0x00008000)
 
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index bc418b910999..1b1f7f2a6130 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -1480,7 +1480,7 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id)
 			break;
 		pkt_received++;
 
-		writel(FEC_ENET_RXF, fep->hwp + FEC_IEVENT);
+		writel(FEC_ENET_RXF_GET(queue_id), fep->hwp + FEC_IEVENT);
 
 		/* Check for errors. */
 		status ^= BD_ENET_RX_LAST;
diff --git a/drivers/net/ethernet/freescale/fman/fman_port.c b/drivers/net/ethernet/freescale/fman/fman_port.c
index d9baac0dbc7d..4c9d05c45c03 100644
--- a/drivers/net/ethernet/freescale/fman/fman_port.c
+++ b/drivers/net/ethernet/freescale/fman/fman_port.c
@@ -1805,7 +1805,7 @@ static int fman_port_probe(struct platform_device *of_dev)
 	fman = dev_get_drvdata(&fm_pdev->dev);
 	if (!fman) {
 		err = -EINVAL;
-		goto return_err;
+		goto put_device;
 	}
 
 	err = of_property_read_u32(port_node, "cell-index", &val);
@@ -1813,7 +1813,7 @@ static int fman_port_probe(struct platform_device *of_dev)
 		dev_err(port->dev, "%s: reading cell-index for %pOF failed\n",
 			__func__, port_node);
 		err = -EINVAL;
-		goto return_err;
+		goto put_device;
 	}
 	port_id = (u8)val;
 	port->dts_params.id = port_id;
@@ -1847,7 +1847,7 @@ static int fman_port_probe(struct platform_device *of_dev)
 	}  else {
 		dev_err(port->dev, "%s: Illegal port type\n", __func__);
 		err = -EINVAL;
-		goto return_err;
+		goto put_device;
 	}
 
 	port->dts_params.type = port_type;
@@ -1861,7 +1861,7 @@ static int fman_port_probe(struct platform_device *of_dev)
 			dev_err(port->dev, "%s: incorrect qman-channel-id\n",
 				__func__);
 			err = -EINVAL;
-			goto return_err;
+			goto put_device;
 		}
 		port->dts_params.qman_channel_id = qman_channel_id;
 	}
@@ -1871,7 +1871,7 @@ static int fman_port_probe(struct platform_device *of_dev)
 		dev_err(port->dev, "%s: of_address_to_resource() failed\n",
 			__func__);
 		err = -ENOMEM;
-		goto return_err;
+		goto put_device;
 	}
 
 	port->dts_params.fman = fman;
@@ -1896,6 +1896,8 @@ static int fman_port_probe(struct platform_device *of_dev)
 
 	return 0;
 
+put_device:
+	put_device(&fm_pdev->dev);
 return_err:
 	of_node_put(port_node);
 free_port:
diff --git a/drivers/net/ethernet/freescale/xgmac_mdio.c b/drivers/net/ethernet/freescale/xgmac_mdio.c
index 0b68852379da..5b8b9bcf41a2 100644
--- a/drivers/net/ethernet/freescale/xgmac_mdio.c
+++ b/drivers/net/ethernet/freescale/xgmac_mdio.c
@@ -47,7 +47,6 @@ struct tgec_mdio_controller {
 #define MDIO_CTL_READ		BIT(15)
 
 #define MDIO_DATA(x)		(x & 0xffff)
-#define MDIO_DATA_BSY		BIT(31)
 
 struct mdio_fsl_priv {
 	struct	tgec_mdio_controller __iomem *mdio_base;
diff --git a/drivers/net/ethernet/google/gve/gve_adminq.c b/drivers/net/ethernet/google/gve/gve_adminq.c
index 83ae56c310d3..326b56b49216 100644
--- a/drivers/net/ethernet/google/gve/gve_adminq.c
+++ b/drivers/net/ethernet/google/gve/gve_adminq.c
@@ -738,10 +738,7 @@ int gve_adminq_describe_device(struct gve_priv *priv)
 	 * is not set to GqiRda, choose the queue format in a priority order:
 	 * DqoRda, GqiRda, GqiQpl. Use GqiQpl as default.
 	 */
-	if (priv->queue_format == GVE_GQI_RDA_FORMAT) {
-		dev_info(&priv->pdev->dev,
-			 "Driver is running with GQI RDA queue format.\n");
-	} else if (dev_op_dqo_rda) {
+	if (dev_op_dqo_rda) {
 		priv->queue_format = GVE_DQO_RDA_FORMAT;
 		dev_info(&priv->pdev->dev,
 			 "Driver is running with DQO RDA queue format.\n");
@@ -753,6 +750,9 @@ int gve_adminq_describe_device(struct gve_priv *priv)
 			 "Driver is running with GQI RDA queue format.\n");
 		supported_features_mask =
 			be32_to_cpu(dev_op_gqi_rda->supported_features_mask);
+	} else if (priv->queue_format == GVE_GQI_RDA_FORMAT) {
+		dev_info(&priv->pdev->dev,
+			 "Driver is running with GQI RDA queue format.\n");
 	} else {
 		priv->queue_format = GVE_GQI_QPL_FORMAT;
 		if (dev_op_gqi_qpl)
diff --git a/drivers/net/ethernet/google/gve/gve_utils.c b/drivers/net/ethernet/google/gve/gve_utils.c
index 88ca49cbc1e2..d57508bc4307 100644
--- a/drivers/net/ethernet/google/gve/gve_utils.c
+++ b/drivers/net/ethernet/google/gve/gve_utils.c
@@ -68,6 +68,9 @@ struct sk_buff *gve_rx_copy(struct net_device *dev, struct napi_struct *napi,
 		set_protocol = ctx->curr_frag_cnt == ctx->expected_frag_cnt - 1;
 	} else {
 		skb = napi_alloc_skb(napi, len);
+
+		if (unlikely(!skb))
+			return NULL;
 		set_protocol = true;
 	}
 	__skb_put(skb, len);
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c
index 23d9cbf262c3..740850b64aff 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c
@@ -400,6 +400,10 @@ static void hns_dsaf_ge_srst_by_port(struct dsaf_device *dsaf_dev, u32 port,
 		return;
 
 	if (!HNS_DSAF_IS_DEBUG(dsaf_dev)) {
+		/* DSAF_MAX_PORT_NUM is 6, but DSAF_GE_NUM is 8.
+		   We need check to prevent array overflow */
+		if (port >= DSAF_MAX_PORT_NUM)
+			return;
 		reg_val_1  = 0x1 << port;
 		port_rst_off = dsaf_dev->mac_cb[port]->port_rst_off;
 		/* there is difference between V1 and V2 in register.*/
diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index 3f7a9a4c59d5..63f5abcc6bf4 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -839,6 +839,8 @@ struct hnae3_handle {
 
 	u8 netdev_flags;
 	struct dentry *hnae3_dbgfs;
+	/* protects concurrent contention between debugfs commands */
+	struct mutex dbgfs_lock;
 
 	/* Network interface message level enabled bits */
 	u32 msg_enable;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
index 67364ab63a1f..c381f8af67f0 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
@@ -1081,7 +1081,8 @@ static void hns3_dump_page_pool_info(struct hns3_enet_ring *ring,
 	u32 j = 0;
 
 	sprintf(result[j++], "%u", index);
-	sprintf(result[j++], "%u", ring->page_pool->pages_state_hold_cnt);
+	sprintf(result[j++], "%u",
+		READ_ONCE(ring->page_pool->pages_state_hold_cnt));
 	sprintf(result[j++], "%u",
 		atomic_read(&ring->page_pool->pages_state_release_cnt));
 	sprintf(result[j++], "%u", ring->page_pool->p.pool_size);
@@ -1106,6 +1107,11 @@ hns3_dbg_page_pool_info(struct hnae3_handle *h, char *buf, int len)
 		return -EFAULT;
 	}
 
+	if (!priv->ring[h->kinfo.num_tqps].page_pool) {
+		dev_err(&h->pdev->dev, "page pool is not initialized\n");
+		return -EFAULT;
+	}
+
 	for (i = 0; i < ARRAY_SIZE(page_pool_info_items); i++)
 		result[i] = &data_str[i][0];
 
@@ -1220,6 +1226,7 @@ static ssize_t hns3_dbg_read(struct file *filp, char __user *buffer,
 	if (ret)
 		return ret;
 
+	mutex_lock(&handle->dbgfs_lock);
 	save_buf = &hns3_dbg_cmd[index].buf;
 
 	if (!test_bit(HNS3_NIC_STATE_INITED, &priv->state) ||
@@ -1232,15 +1239,15 @@ static ssize_t hns3_dbg_read(struct file *filp, char __user *buffer,
 		read_buf = *save_buf;
 	} else {
 		read_buf = kvzalloc(hns3_dbg_cmd[index].buf_len, GFP_KERNEL);
-		if (!read_buf)
-			return -ENOMEM;
+		if (!read_buf) {
+			ret = -ENOMEM;
+			goto out;
+		}
 
 		/* save the buffer addr until the last read operation */
 		*save_buf = read_buf;
-	}
 
-	/* get data ready for the first time to read */
-	if (!*ppos) {
+		/* get data ready for the first time to read */
 		ret = hns3_dbg_read_cmd(dbg_data, hns3_dbg_cmd[index].cmd,
 					read_buf, hns3_dbg_cmd[index].buf_len);
 		if (ret)
@@ -1249,8 +1256,10 @@ static ssize_t hns3_dbg_read(struct file *filp, char __user *buffer,
 
 	size = simple_read_from_buffer(buffer, count, ppos, read_buf,
 				       strlen(read_buf));
-	if (size > 0)
+	if (size > 0) {
+		mutex_unlock(&handle->dbgfs_lock);
 		return size;
+	}
 
 out:
 	/* free the buffer for the last read operation */
@@ -1259,6 +1268,7 @@ out:
 		*save_buf = NULL;
 	}
 
+	mutex_unlock(&handle->dbgfs_lock);
 	return ret;
 }
 
@@ -1331,6 +1341,8 @@ int hns3_dbg_init(struct hnae3_handle *handle)
 			debugfs_create_dir(hns3_dbg_dentry[i].name,
 					   handle->hnae3_dbgfs);
 
+	mutex_init(&handle->dbgfs_lock);
+
 	for (i = 0; i < ARRAY_SIZE(hns3_dbg_cmd); i++) {
 		if ((hns3_dbg_cmd[i].cmd == HNAE3_DBG_CMD_TM_NODES &&
 		     ae_dev->dev_version <= HNAE3_DEVICE_VERSION_V2) ||
@@ -1357,6 +1369,7 @@ int hns3_dbg_init(struct hnae3_handle *handle)
 	return 0;
 
 out:
+	mutex_destroy(&handle->dbgfs_lock);
 	debugfs_remove_recursive(handle->hnae3_dbgfs);
 	handle->hnae3_dbgfs = NULL;
 	return ret;
@@ -1372,6 +1385,7 @@ void hns3_dbg_uninit(struct hnae3_handle *handle)
 			hns3_dbg_cmd[i].buf = NULL;
 		}
 
+	mutex_destroy(&handle->dbgfs_lock);
 	debugfs_remove_recursive(handle->hnae3_dbgfs);
 	handle->hnae3_dbgfs = NULL;
 }
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
index c8442b86df94..c9b4568d7a8d 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
@@ -987,6 +987,7 @@ static int hns3_set_reset(struct net_device *netdev, u32 *flags)
 	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(h->pdev);
 	const struct hnae3_ae_ops *ops = h->ae_algo->ops;
 	const struct hns3_reset_type_map *rst_type_map;
+	enum ethtool_reset_flags rst_flags;
 	u32 i, size;
 
 	if (ops->ae_dev_resetting && ops->ae_dev_resetting(h))
@@ -1006,6 +1007,7 @@ static int hns3_set_reset(struct net_device *netdev, u32 *flags)
 	for (i = 0; i < size; i++) {
 		if (rst_type_map[i].rst_flags == *flags) {
 			rst_type = rst_type_map[i].rst_type;
+			rst_flags = rst_type_map[i].rst_flags;
 			break;
 		}
 	}
@@ -1021,6 +1023,8 @@ static int hns3_set_reset(struct net_device *netdev, u32 *flags)
 
 	ops->reset_event(h->pdev, h);
 
+	*flags &= ~rst_flags;
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 25c419d40066..41afaeea881b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -703,9 +703,9 @@ static int hclgevf_set_rss_tc_mode(struct hclgevf_dev *hdev,  u16 rss_size)
 	roundup_size = ilog2(roundup_size);
 
 	for (i = 0; i < HCLGEVF_MAX_TC_NUM; i++) {
-		tc_valid[i] = !!(hdev->hw_tc_map & BIT(i));
+		tc_valid[i] = 1;
 		tc_size[i] = roundup_size;
-		tc_offset[i] = rss_size * i;
+		tc_offset[i] = (hdev->hw_tc_map & BIT(i)) ? rss_size * i : 0;
 	}
 
 	hclgevf_cmd_setup_basic_desc(&desc, HCLGEVF_OPC_RSS_TC_MODE, false);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
index fdc66fae0960..c5ac6ecf36e1 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
@@ -114,7 +114,8 @@ int hclgevf_send_mbx_msg(struct hclgevf_dev *hdev,
 
 	memcpy(&req->msg, send_msg, sizeof(struct hclge_vf_to_pf_msg));
 
-	trace_hclge_vf_mbx_send(hdev, req);
+	if (test_bit(HCLGEVF_STATE_NIC_REGISTERED, &hdev->state))
+		trace_hclge_vf_mbx_send(hdev, req);
 
 	/* synchronous send */
 	if (need_resp) {
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_sriov.c b/drivers/net/ethernet/huawei/hinic/hinic_sriov.c
index a78c398bf5b2..01e7d3c0b68e 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_sriov.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_sriov.c
@@ -8,6 +8,7 @@
 #include <linux/interrupt.h>
 #include <linux/etherdevice.h>
 #include <linux/netdevice.h>
+#include <linux/module.h>
 
 #include "hinic_hw_dev.h"
 #include "hinic_dev.h"
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 3cca51735421..0bb3911dd014 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -628,17 +628,9 @@ static bool reuse_rx_pools(struct ibmvnic_adapter *adapter)
 	old_buff_size = adapter->prev_rx_buf_sz;
 	new_buff_size = adapter->cur_rx_buf_sz;
 
-	/* Require buff size to be exactly same for now */
-	if (old_buff_size != new_buff_size)
-		return false;
-
-	if (old_num_pools == new_num_pools && old_pool_size == new_pool_size)
-		return true;
-
-	if (old_num_pools < adapter->min_rx_queues ||
-	    old_num_pools > adapter->max_rx_queues ||
-	    old_pool_size < adapter->min_rx_add_entries_per_subcrq ||
-	    old_pool_size > adapter->max_rx_add_entries_per_subcrq)
+	if (old_buff_size != new_buff_size ||
+	    old_num_pools != new_num_pools ||
+	    old_pool_size != new_pool_size)
 		return false;
 
 	return true;
@@ -874,17 +866,9 @@ static bool reuse_tx_pools(struct ibmvnic_adapter *adapter)
 	old_mtu = adapter->prev_mtu;
 	new_mtu = adapter->req_mtu;
 
-	/* Require MTU to be exactly same to reuse pools for now */
-	if (old_mtu != new_mtu)
-		return false;
-
-	if (old_num_pools == new_num_pools && old_pool_size == new_pool_size)
-		return true;
-
-	if (old_num_pools < adapter->min_tx_queues ||
-	    old_num_pools > adapter->max_tx_queues ||
-	    old_pool_size < adapter->min_tx_entries_per_subcrq ||
-	    old_pool_size > adapter->max_tx_entries_per_subcrq)
+	if (old_mtu != new_mtu ||
+	    old_num_pools != new_num_pools ||
+	    old_pool_size != new_pool_size)
 		return false;
 
 	return true;
diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c
index 5039a2536951..0bf3d47bb90d 100644
--- a/drivers/net/ethernet/intel/e100.c
+++ b/drivers/net/ethernet/intel/e100.c
@@ -3003,9 +3003,10 @@ static void __e100_shutdown(struct pci_dev *pdev, bool *enable_wake)
 	struct net_device *netdev = pci_get_drvdata(pdev);
 	struct nic *nic = netdev_priv(netdev);
 
+	netif_device_detach(netdev);
+
 	if (netif_running(netdev))
 		e100_down(nic);
-	netif_device_detach(netdev);
 
 	if ((nic->flags & wol_magic) | e100_asf(nic)) {
 		/* enable reverse auto-negotiation */
@@ -3022,7 +3023,7 @@ static void __e100_shutdown(struct pci_dev *pdev, bool *enable_wake)
 		*enable_wake = false;
 	}
 
-	pci_clear_master(pdev);
+	pci_disable_device(pdev);
 }
 
 static int __e100_power_off(struct pci_dev *pdev, bool wake)
@@ -3042,8 +3043,6 @@ static int __maybe_unused e100_suspend(struct device *dev_d)
 
 	__e100_shutdown(to_pci_dev(dev_d), &wake);
 
-	device_wakeup_disable(dev_d);
-
 	return 0;
 }
 
@@ -3051,6 +3050,14 @@ static int __maybe_unused e100_resume(struct device *dev_d)
 {
 	struct net_device *netdev = dev_get_drvdata(dev_d);
 	struct nic *nic = netdev_priv(netdev);
+	int err;
+
+	err = pci_enable_device(to_pci_dev(dev_d));
+	if (err) {
+		netdev_err(netdev, "Resume cannot enable PCI device, aborting\n");
+		return err;
+	}
+	pci_set_master(to_pci_dev(dev_d));
 
 	/* disable reverse auto-negotiation */
 	if (nic->phy == phy_82552_v) {
@@ -3062,10 +3069,11 @@ static int __maybe_unused e100_resume(struct device *dev_d)
 		           smartspeed & ~(E100_82552_REV_ANEG));
 	}
 
-	netif_device_attach(netdev);
 	if (netif_running(netdev))
 		e100_up(nic);
 
+	netif_device_attach(netdev);
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index 3d528fba754b..4d939af0a626 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -161,6 +161,7 @@ enum i40e_vsi_state_t {
 	__I40E_VSI_OVERFLOW_PROMISC,
 	__I40E_VSI_REINIT_REQUESTED,
 	__I40E_VSI_DOWN_REQUESTED,
+	__I40E_VSI_RELEASING,
 	/* This must be last as it determines the size of the BITMAP */
 	__I40E_VSI_STATE_SIZE__,
 };
@@ -1247,6 +1248,7 @@ void i40e_ptp_restore_hw_time(struct i40e_pf *pf);
 void i40e_ptp_init(struct i40e_pf *pf);
 void i40e_ptp_stop(struct i40e_pf *pf);
 int i40e_ptp_alloc_pins(struct i40e_pf *pf);
+int i40e_update_adq_vsi_queues(struct i40e_vsi *vsi, int vsi_offset);
 int i40e_is_vsi_uplink_mode_veb(struct i40e_vsi *vsi);
 i40e_status i40e_get_partition_bw_setting(struct i40e_pf *pf);
 i40e_status i40e_set_partition_bw_setting(struct i40e_pf *pf);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
index 291e61ac3e44..2c1b1da1220e 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
@@ -553,6 +553,14 @@ static void i40e_dbg_dump_desc(int cnt, int vsi_seid, int ring_id, int desc_n,
 		dev_info(&pf->pdev->dev, "vsi %d not found\n", vsi_seid);
 		return;
 	}
+	if (vsi->type != I40E_VSI_MAIN &&
+	    vsi->type != I40E_VSI_FDIR &&
+	    vsi->type != I40E_VSI_VMDQ2) {
+		dev_info(&pf->pdev->dev,
+			 "vsi %d type %d descriptor rings not available\n",
+			 vsi_seid, vsi->type);
+		return;
+	}
 	if (type == RING_TYPE_XDP && !i40e_enabled_xdp_vsi(vsi)) {
 		dev_info(&pf->pdev->dev, "XDP not enabled on VSI %d\n", vsi_seid);
 		return;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index ba862131b9bd..e118cf9265c7 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -1790,6 +1790,7 @@ static void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi,
 				     bool is_add)
 {
 	struct i40e_pf *pf = vsi->back;
+	u16 num_tc_qps = 0;
 	u16 sections = 0;
 	u8 netdev_tc = 0;
 	u16 numtc = 1;
@@ -1797,13 +1798,33 @@ static void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi,
 	u8 offset;
 	u16 qmap;
 	int i;
-	u16 num_tc_qps = 0;
 
 	sections = I40E_AQ_VSI_PROP_QUEUE_MAP_VALID;
 	offset = 0;
+	/* zero out queue mapping, it will get updated on the end of the function */
+	memset(ctxt->info.queue_mapping, 0, sizeof(ctxt->info.queue_mapping));
+
+	if (vsi->type == I40E_VSI_MAIN) {
+		/* This code helps add more queue to the VSI if we have
+		 * more cores than RSS can support, the higher cores will
+		 * be served by ATR or other filters. Furthermore, the
+		 * non-zero req_queue_pairs says that user requested a new
+		 * queue count via ethtool's set_channels, so use this
+		 * value for queues distribution across traffic classes
+		 */
+		if (vsi->req_queue_pairs > 0)
+			vsi->num_queue_pairs = vsi->req_queue_pairs;
+		else if (pf->flags & I40E_FLAG_MSIX_ENABLED)
+			vsi->num_queue_pairs = pf->num_lan_msix;
+	}
 
 	/* Number of queues per enabled TC */
-	num_tc_qps = vsi->alloc_queue_pairs;
+	if (vsi->type == I40E_VSI_MAIN ||
+	    (vsi->type == I40E_VSI_SRIOV && vsi->num_queue_pairs != 0))
+		num_tc_qps = vsi->num_queue_pairs;
+	else
+		num_tc_qps = vsi->alloc_queue_pairs;
+
 	if (enabled_tc && (vsi->back->flags & I40E_FLAG_DCB_ENABLED)) {
 		/* Find numtc from enabled TC bitmap */
 		for (i = 0, numtc = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) {
@@ -1881,15 +1902,11 @@ static void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi,
 		}
 		ctxt->info.tc_mapping[i] = cpu_to_le16(qmap);
 	}
-
-	/* Set actual Tx/Rx queue pairs */
-	vsi->num_queue_pairs = offset;
-	if ((vsi->type == I40E_VSI_MAIN) && (numtc == 1)) {
-		if (vsi->req_queue_pairs > 0)
-			vsi->num_queue_pairs = vsi->req_queue_pairs;
-		else if (pf->flags & I40E_FLAG_MSIX_ENABLED)
-			vsi->num_queue_pairs = pf->num_lan_msix;
-	}
+	/* Do not change previously set num_queue_pairs for PFs and VFs*/
+	if ((vsi->type == I40E_VSI_MAIN && numtc != 1) ||
+	    (vsi->type == I40E_VSI_SRIOV && vsi->num_queue_pairs == 0) ||
+	    (vsi->type != I40E_VSI_MAIN && vsi->type != I40E_VSI_SRIOV))
+		vsi->num_queue_pairs = offset;
 
 	/* Scheduler section valid can only be set for ADD VSI */
 	if (is_add) {
@@ -2623,7 +2640,8 @@ static void i40e_sync_filters_subtask(struct i40e_pf *pf)
 
 	for (v = 0; v < pf->num_alloc_vsi; v++) {
 		if (pf->vsi[v] &&
-		    (pf->vsi[v]->flags & I40E_VSI_FLAG_FILTER_CHANGED)) {
+		    (pf->vsi[v]->flags & I40E_VSI_FLAG_FILTER_CHANGED) &&
+		    !test_bit(__I40E_VSI_RELEASING, pf->vsi[v]->state)) {
 			int ret = i40e_sync_vsi_filters(pf->vsi[v]);
 
 			if (ret) {
@@ -5427,6 +5445,58 @@ static void i40e_vsi_update_queue_map(struct i40e_vsi *vsi,
 }
 
 /**
+ * i40e_update_adq_vsi_queues - update queue mapping for ADq VSI
+ * @vsi: the VSI being reconfigured
+ * @vsi_offset: offset from main VF VSI
+ */
+int i40e_update_adq_vsi_queues(struct i40e_vsi *vsi, int vsi_offset)
+{
+	struct i40e_vsi_context ctxt = {};
+	struct i40e_pf *pf;
+	struct i40e_hw *hw;
+	int ret;
+
+	if (!vsi)
+		return I40E_ERR_PARAM;
+	pf = vsi->back;
+	hw = &pf->hw;
+
+	ctxt.seid = vsi->seid;
+	ctxt.pf_num = hw->pf_id;
+	ctxt.vf_num = vsi->vf_id + hw->func_caps.vf_base_id + vsi_offset;
+	ctxt.uplink_seid = vsi->uplink_seid;
+	ctxt.connection_type = I40E_AQ_VSI_CONN_TYPE_NORMAL;
+	ctxt.flags = I40E_AQ_VSI_TYPE_VF;
+	ctxt.info = vsi->info;
+
+	i40e_vsi_setup_queue_map(vsi, &ctxt, vsi->tc_config.enabled_tc,
+				 false);
+	if (vsi->reconfig_rss) {
+		vsi->rss_size = min_t(int, pf->alloc_rss_size,
+				      vsi->num_queue_pairs);
+		ret = i40e_vsi_config_rss(vsi);
+		if (ret) {
+			dev_info(&pf->pdev->dev, "Failed to reconfig rss for num_queues\n");
+			return ret;
+		}
+		vsi->reconfig_rss = false;
+	}
+
+	ret = i40e_aq_update_vsi_params(hw, &ctxt, NULL);
+	if (ret) {
+		dev_info(&pf->pdev->dev, "Update vsi config failed, err %s aq_err %s\n",
+			 i40e_stat_str(hw, ret),
+			 i40e_aq_str(hw, hw->aq.asq_last_status));
+		return ret;
+	}
+	/* update the local VSI info with updated queue map */
+	i40e_vsi_update_queue_map(vsi, &ctxt);
+	vsi->info.valid_sections = 0;
+
+	return ret;
+}
+
+/**
  * i40e_vsi_config_tc - Configure VSI Tx Scheduler for given TC map
  * @vsi: VSI to be configured
  * @enabled_tc: TC bitmap
@@ -5717,24 +5787,6 @@ static void i40e_remove_queue_channels(struct i40e_vsi *vsi)
 }
 
 /**
- * i40e_is_any_channel - channel exist or not
- * @vsi: ptr to VSI to which channels are associated with
- *
- * Returns true or false if channel(s) exist for associated VSI or not
- **/
-static bool i40e_is_any_channel(struct i40e_vsi *vsi)
-{
-	struct i40e_channel *ch, *ch_tmp;
-
-	list_for_each_entry_safe(ch, ch_tmp, &vsi->ch_list, list) {
-		if (ch->initialized)
-			return true;
-	}
-
-	return false;
-}
-
-/**
  * i40e_get_max_queues_for_channel
  * @vsi: ptr to VSI to which channels are associated with
  *
@@ -6240,26 +6292,15 @@ int i40e_create_queue_channel(struct i40e_vsi *vsi,
 	/* By default we are in VEPA mode, if this is the first VF/VMDq
 	 * VSI to be added switch to VEB mode.
 	 */
-	if ((!(pf->flags & I40E_FLAG_VEB_MODE_ENABLED)) ||
-	    (!i40e_is_any_channel(vsi))) {
-		if (!is_power_of_2(vsi->tc_config.tc_info[0].qcount)) {
-			dev_dbg(&pf->pdev->dev,
-				"Failed to create channel. Override queues (%u) not power of 2\n",
-				vsi->tc_config.tc_info[0].qcount);
-			return -EINVAL;
-		}
 
-		if (!(pf->flags & I40E_FLAG_VEB_MODE_ENABLED)) {
-			pf->flags |= I40E_FLAG_VEB_MODE_ENABLED;
+	if (!(pf->flags & I40E_FLAG_VEB_MODE_ENABLED)) {
+		pf->flags |= I40E_FLAG_VEB_MODE_ENABLED;
 
-			if (vsi->type == I40E_VSI_MAIN) {
-				if (pf->flags & I40E_FLAG_TC_MQPRIO)
-					i40e_do_reset(pf, I40E_PF_RESET_FLAG,
-						      true);
-				else
-					i40e_do_reset_safe(pf,
-							   I40E_PF_RESET_FLAG);
-			}
+		if (vsi->type == I40E_VSI_MAIN) {
+			if (pf->flags & I40E_FLAG_TC_MQPRIO)
+				i40e_do_reset(pf, I40E_PF_RESET_FLAG, true);
+			else
+				i40e_do_reset_safe(pf, I40E_PF_RESET_FLAG);
 		}
 		/* now onwards for main VSI, number of queues will be value
 		 * of TC0's queue count
@@ -7912,12 +7953,20 @@ config_tc:
 			    vsi->seid);
 		need_reset = true;
 		goto exit;
-	} else {
-		dev_info(&vsi->back->pdev->dev,
-			 "Setup channel (id:%u) utilizing num_queues %d\n",
-			 vsi->seid, vsi->tc_config.tc_info[0].qcount);
+	} else if (enabled_tc &&
+		   (!is_power_of_2(vsi->tc_config.tc_info[0].qcount))) {
+		netdev_info(netdev,
+			    "Failed to create channel. Override queues (%u) not power of 2\n",
+			    vsi->tc_config.tc_info[0].qcount);
+		ret = -EINVAL;
+		need_reset = true;
+		goto exit;
 	}
 
+	dev_info(&vsi->back->pdev->dev,
+		 "Setup channel (id:%u) utilizing num_queues %d\n",
+		 vsi->seid, vsi->tc_config.tc_info[0].qcount);
+
 	if (pf->flags & I40E_FLAG_TC_MQPRIO) {
 		if (vsi->mqprio_qopt.max_rate[0]) {
 			u64 max_tx_rate = vsi->mqprio_qopt.max_rate[0];
@@ -8482,9 +8531,8 @@ static int i40e_configure_clsflower(struct i40e_vsi *vsi,
 		err = i40e_add_del_cloud_filter(vsi, filter, true);
 
 	if (err) {
-		dev_err(&pf->pdev->dev,
-			"Failed to add cloud filter, err %s\n",
-			i40e_stat_str(&pf->hw, err));
+		dev_err(&pf->pdev->dev, "Failed to add cloud filter, err %d\n",
+			err);
 		goto err;
 	}
 
@@ -13771,7 +13819,7 @@ int i40e_vsi_release(struct i40e_vsi *vsi)
 		dev_info(&pf->pdev->dev, "Can't remove PF VSI\n");
 		return -ENODEV;
 	}
-
+	set_bit(__I40E_VSI_RELEASING, vsi->state);
 	uplink_seid = vsi->uplink_seid;
 	if (vsi->type != I40E_VSI_SRIOV) {
 		if (vsi->netdev_registered) {
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index 472f56b360b8..2ea4deb8fc44 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -183,17 +183,18 @@ void i40e_vc_notify_vf_reset(struct i40e_vf *vf)
 /***********************misc routines*****************************/
 
 /**
- * i40e_vc_disable_vf
+ * i40e_vc_reset_vf
  * @vf: pointer to the VF info
- *
- * Disable the VF through a SW reset.
+ * @notify_vf: notify vf about reset or not
+ * Reset VF handler.
  **/
-static inline void i40e_vc_disable_vf(struct i40e_vf *vf)
+static void i40e_vc_reset_vf(struct i40e_vf *vf, bool notify_vf)
 {
 	struct i40e_pf *pf = vf->pf;
 	int i;
 
-	i40e_vc_notify_vf_reset(vf);
+	if (notify_vf)
+		i40e_vc_notify_vf_reset(vf);
 
 	/* We want to ensure that an actual reset occurs initiated after this
 	 * function was called. However, we do not want to wait forever, so
@@ -211,9 +212,14 @@ static inline void i40e_vc_disable_vf(struct i40e_vf *vf)
 		usleep_range(10000, 20000);
 	}
 
-	dev_warn(&vf->pf->pdev->dev,
-		 "Failed to initiate reset for VF %d after 200 milliseconds\n",
-		 vf->vf_id);
+	if (notify_vf)
+		dev_warn(&vf->pf->pdev->dev,
+			 "Failed to initiate reset for VF %d after 200 milliseconds\n",
+			 vf->vf_id);
+	else
+		dev_dbg(&vf->pf->pdev->dev,
+			"Failed to initiate reset for VF %d after 200 milliseconds\n",
+			vf->vf_id);
 }
 
 /**
@@ -674,14 +680,13 @@ static int i40e_config_vsi_rx_queue(struct i40e_vf *vf, u16 vsi_id,
 				    u16 vsi_queue_id,
 				    struct virtchnl_rxq_info *info)
 {
+	u16 pf_queue_id = i40e_vc_get_pf_queue_id(vf, vsi_id, vsi_queue_id);
 	struct i40e_pf *pf = vf->pf;
+	struct i40e_vsi *vsi = pf->vsi[vf->lan_vsi_idx];
 	struct i40e_hw *hw = &pf->hw;
 	struct i40e_hmc_obj_rxq rx_ctx;
-	u16 pf_queue_id;
 	int ret = 0;
 
-	pf_queue_id = i40e_vc_get_pf_queue_id(vf, vsi_id, vsi_queue_id);
-
 	/* clear the context structure first */
 	memset(&rx_ctx, 0, sizeof(struct i40e_hmc_obj_rxq));
 
@@ -719,6 +724,10 @@ static int i40e_config_vsi_rx_queue(struct i40e_vf *vf, u16 vsi_id,
 	}
 	rx_ctx.rxmax = info->max_pkt_size;
 
+	/* if port VLAN is configured increase the max packet size */
+	if (vsi->info.pvid)
+		rx_ctx.rxmax += VLAN_HLEN;
+
 	/* enable 32bytes desc always */
 	rx_ctx.dsize = 1;
 
@@ -1940,6 +1949,32 @@ static int i40e_vc_send_resp_to_vf(struct i40e_vf *vf,
 }
 
 /**
+ * i40e_sync_vf_state
+ * @vf: pointer to the VF info
+ * @state: VF state
+ *
+ * Called from a VF message to synchronize the service with a potential
+ * VF reset state
+ **/
+static bool i40e_sync_vf_state(struct i40e_vf *vf, enum i40e_vf_states state)
+{
+	int i;
+
+	/* When handling some messages, it needs VF state to be set.
+	 * It is possible that this flag is cleared during VF reset,
+	 * so there is a need to wait until the end of the reset to
+	 * handle the request message correctly.
+	 */
+	for (i = 0; i < I40E_VF_STATE_WAIT_COUNT; i++) {
+		if (test_bit(state, &vf->vf_states))
+			return true;
+		usleep_range(10000, 20000);
+	}
+
+	return test_bit(state, &vf->vf_states);
+}
+
+/**
  * i40e_vc_get_version_msg
  * @vf: pointer to the VF info
  * @msg: pointer to the msg buffer
@@ -1999,7 +2034,7 @@ static int i40e_vc_get_vf_resources_msg(struct i40e_vf *vf, u8 *msg)
 	size_t len = 0;
 	int ret;
 
-	if (!test_bit(I40E_VF_STATE_INIT, &vf->vf_states)) {
+	if (!i40e_sync_vf_state(vf, I40E_VF_STATE_INIT)) {
 		aq_ret = I40E_ERR_PARAM;
 		goto err;
 	}
@@ -2106,20 +2141,6 @@ err:
 }
 
 /**
- * i40e_vc_reset_vf_msg
- * @vf: pointer to the VF info
- *
- * called from the VF to reset itself,
- * unlike other virtchnl messages, PF driver
- * doesn't send the response back to the VF
- **/
-static void i40e_vc_reset_vf_msg(struct i40e_vf *vf)
-{
-	if (test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states))
-		i40e_reset_vf(vf, false);
-}
-
-/**
  * i40e_vc_config_promiscuous_mode_msg
  * @vf: pointer to the VF info
  * @msg: pointer to the msg buffer
@@ -2136,7 +2157,7 @@ static int i40e_vc_config_promiscuous_mode_msg(struct i40e_vf *vf, u8 *msg)
 	bool allmulti = false;
 	bool alluni = false;
 
-	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) {
+	if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) {
 		aq_ret = I40E_ERR_PARAM;
 		goto err_out;
 	}
@@ -2217,13 +2238,14 @@ static int i40e_vc_config_queues_msg(struct i40e_vf *vf, u8 *msg)
 	struct virtchnl_vsi_queue_config_info *qci =
 	    (struct virtchnl_vsi_queue_config_info *)msg;
 	struct virtchnl_queue_pair_info *qpi;
-	struct i40e_pf *pf = vf->pf;
 	u16 vsi_id, vsi_queue_id = 0;
-	u16 num_qps_all = 0;
+	struct i40e_pf *pf = vf->pf;
 	i40e_status aq_ret = 0;
 	int i, j = 0, idx = 0;
+	struct i40e_vsi *vsi;
+	u16 num_qps_all = 0;
 
-	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) {
+	if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) {
 		aq_ret = I40E_ERR_PARAM;
 		goto error_param;
 	}
@@ -2310,9 +2332,15 @@ static int i40e_vc_config_queues_msg(struct i40e_vf *vf, u8 *msg)
 		pf->vsi[vf->lan_vsi_idx]->num_queue_pairs =
 			qci->num_queue_pairs;
 	} else {
-		for (i = 0; i < vf->num_tc; i++)
-			pf->vsi[vf->ch[i].vsi_idx]->num_queue_pairs =
-			       vf->ch[i].num_qps;
+		for (i = 0; i < vf->num_tc; i++) {
+			vsi = pf->vsi[vf->ch[i].vsi_idx];
+			vsi->num_queue_pairs = vf->ch[i].num_qps;
+
+			if (i40e_update_adq_vsi_queues(vsi, i)) {
+				aq_ret = I40E_ERR_CONFIG;
+				goto error_param;
+			}
+		}
 	}
 
 error_param:
@@ -2366,7 +2394,7 @@ static int i40e_vc_config_irq_map_msg(struct i40e_vf *vf, u8 *msg)
 	i40e_status aq_ret = 0;
 	int i;
 
-	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) {
+	if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) {
 		aq_ret = I40E_ERR_PARAM;
 		goto error_param;
 	}
@@ -2538,7 +2566,7 @@ static int i40e_vc_disable_queues_msg(struct i40e_vf *vf, u8 *msg)
 	struct i40e_pf *pf = vf->pf;
 	i40e_status aq_ret = 0;
 
-	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) {
+	if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) {
 		aq_ret = I40E_ERR_PARAM;
 		goto error_param;
 	}
@@ -2588,7 +2616,7 @@ static int i40e_vc_request_queues_msg(struct i40e_vf *vf, u8 *msg)
 	u8 cur_pairs = vf->num_queue_pairs;
 	struct i40e_pf *pf = vf->pf;
 
-	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states))
+	if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE))
 		return -EINVAL;
 
 	if (req_pairs > I40E_MAX_VF_QUEUES) {
@@ -2607,8 +2635,7 @@ static int i40e_vc_request_queues_msg(struct i40e_vf *vf, u8 *msg)
 	} else {
 		/* successful request */
 		vf->num_req_queues = req_pairs;
-		i40e_vc_notify_vf_reset(vf);
-		i40e_reset_vf(vf, false);
+		i40e_vc_reset_vf(vf, true);
 		return 0;
 	}
 
@@ -2634,7 +2661,7 @@ static int i40e_vc_get_stats_msg(struct i40e_vf *vf, u8 *msg)
 
 	memset(&stats, 0, sizeof(struct i40e_eth_stats));
 
-	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) {
+	if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) {
 		aq_ret = I40E_ERR_PARAM;
 		goto error_param;
 	}
@@ -2751,7 +2778,7 @@ static int i40e_vc_add_mac_addr_msg(struct i40e_vf *vf, u8 *msg)
 	i40e_status ret = 0;
 	int i;
 
-	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) ||
+	if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE) ||
 	    !i40e_vc_isvalid_vsi_id(vf, al->vsi_id)) {
 		ret = I40E_ERR_PARAM;
 		goto error_param;
@@ -2823,7 +2850,7 @@ static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg)
 	i40e_status ret = 0;
 	int i;
 
-	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) ||
+	if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE) ||
 	    !i40e_vc_isvalid_vsi_id(vf, al->vsi_id)) {
 		ret = I40E_ERR_PARAM;
 		goto error_param;
@@ -2967,7 +2994,7 @@ static int i40e_vc_remove_vlan_msg(struct i40e_vf *vf, u8 *msg)
 	i40e_status aq_ret = 0;
 	int i;
 
-	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) ||
+	if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE) ||
 	    !i40e_vc_isvalid_vsi_id(vf, vfl->vsi_id)) {
 		aq_ret = I40E_ERR_PARAM;
 		goto error_param;
@@ -3087,9 +3114,9 @@ static int i40e_vc_config_rss_key(struct i40e_vf *vf, u8 *msg)
 	struct i40e_vsi *vsi = NULL;
 	i40e_status aq_ret = 0;
 
-	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) ||
+	if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE) ||
 	    !i40e_vc_isvalid_vsi_id(vf, vrk->vsi_id) ||
-	    (vrk->key_len != I40E_HKEY_ARRAY_SIZE)) {
+	    vrk->key_len != I40E_HKEY_ARRAY_SIZE) {
 		aq_ret = I40E_ERR_PARAM;
 		goto err;
 	}
@@ -3118,9 +3145,9 @@ static int i40e_vc_config_rss_lut(struct i40e_vf *vf, u8 *msg)
 	i40e_status aq_ret = 0;
 	u16 i;
 
-	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) ||
+	if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE) ||
 	    !i40e_vc_isvalid_vsi_id(vf, vrl->vsi_id) ||
-	    (vrl->lut_entries != I40E_VF_HLUT_ARRAY_SIZE)) {
+	    vrl->lut_entries != I40E_VF_HLUT_ARRAY_SIZE) {
 		aq_ret = I40E_ERR_PARAM;
 		goto err;
 	}
@@ -3153,7 +3180,7 @@ static int i40e_vc_get_rss_hena(struct i40e_vf *vf, u8 *msg)
 	i40e_status aq_ret = 0;
 	int len = 0;
 
-	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) {
+	if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) {
 		aq_ret = I40E_ERR_PARAM;
 		goto err;
 	}
@@ -3189,7 +3216,7 @@ static int i40e_vc_set_rss_hena(struct i40e_vf *vf, u8 *msg)
 	struct i40e_hw *hw = &pf->hw;
 	i40e_status aq_ret = 0;
 
-	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) {
+	if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) {
 		aq_ret = I40E_ERR_PARAM;
 		goto err;
 	}
@@ -3214,7 +3241,7 @@ static int i40e_vc_enable_vlan_stripping(struct i40e_vf *vf, u8 *msg)
 	i40e_status aq_ret = 0;
 	struct i40e_vsi *vsi;
 
-	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) {
+	if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) {
 		aq_ret = I40E_ERR_PARAM;
 		goto err;
 	}
@@ -3240,7 +3267,7 @@ static int i40e_vc_disable_vlan_stripping(struct i40e_vf *vf, u8 *msg)
 	i40e_status aq_ret = 0;
 	struct i40e_vsi *vsi;
 
-	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) {
+	if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) {
 		aq_ret = I40E_ERR_PARAM;
 		goto err;
 	}
@@ -3467,7 +3494,7 @@ static int i40e_vc_del_cloud_filter(struct i40e_vf *vf, u8 *msg)
 	i40e_status aq_ret = 0;
 	int i, ret;
 
-	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) {
+	if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) {
 		aq_ret = I40E_ERR_PARAM;
 		goto err;
 	}
@@ -3598,7 +3625,7 @@ static int i40e_vc_add_cloud_filter(struct i40e_vf *vf, u8 *msg)
 	i40e_status aq_ret = 0;
 	int i, ret;
 
-	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) {
+	if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) {
 		aq_ret = I40E_ERR_PARAM;
 		goto err_out;
 	}
@@ -3707,7 +3734,7 @@ static int i40e_vc_add_qch_msg(struct i40e_vf *vf, u8 *msg)
 	i40e_status aq_ret = 0;
 	u64 speed = 0;
 
-	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) {
+	if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) {
 		aq_ret = I40E_ERR_PARAM;
 		goto err;
 	}
@@ -3796,15 +3823,9 @@ static int i40e_vc_add_qch_msg(struct i40e_vf *vf, u8 *msg)
 
 	/* set this flag only after making sure all inputs are sane */
 	vf->adq_enabled = true;
-	/* num_req_queues is set when user changes number of queues via ethtool
-	 * and this causes issue for default VSI(which depends on this variable)
-	 * when ADq is enabled, hence reset it.
-	 */
-	vf->num_req_queues = 0;
 
 	/* reset the VF in order to allocate resources */
-	i40e_vc_notify_vf_reset(vf);
-	i40e_reset_vf(vf, false);
+	i40e_vc_reset_vf(vf, true);
 
 	return I40E_SUCCESS;
 
@@ -3824,7 +3845,7 @@ static int i40e_vc_del_qch_msg(struct i40e_vf *vf, u8 *msg)
 	struct i40e_pf *pf = vf->pf;
 	i40e_status aq_ret = 0;
 
-	if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) {
+	if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) {
 		aq_ret = I40E_ERR_PARAM;
 		goto err;
 	}
@@ -3844,8 +3865,7 @@ static int i40e_vc_del_qch_msg(struct i40e_vf *vf, u8 *msg)
 	}
 
 	/* reset the VF in order to allocate resources */
-	i40e_vc_notify_vf_reset(vf);
-	i40e_reset_vf(vf, false);
+	i40e_vc_reset_vf(vf, true);
 
 	return I40E_SUCCESS;
 
@@ -3907,7 +3927,7 @@ int i40e_vc_process_vf_msg(struct i40e_pf *pf, s16 vf_id, u32 v_opcode,
 		i40e_vc_notify_vf_link_state(vf);
 		break;
 	case VIRTCHNL_OP_RESET_VF:
-		i40e_vc_reset_vf_msg(vf);
+		i40e_vc_reset_vf(vf, false);
 		ret = 0;
 		break;
 	case VIRTCHNL_OP_CONFIG_PROMISCUOUS_MODE:
@@ -4161,7 +4181,7 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac)
 	/* Force the VF interface down so it has to bring up with new MAC
 	 * address
 	 */
-	i40e_vc_disable_vf(vf);
+	i40e_vc_reset_vf(vf, true);
 	dev_info(&pf->pdev->dev, "Bring down and up the VF interface to make this change effective.\n");
 
 error_param:
@@ -4170,34 +4190,6 @@ error_param:
 }
 
 /**
- * i40e_vsi_has_vlans - True if VSI has configured VLANs
- * @vsi: pointer to the vsi
- *
- * Check if a VSI has configured any VLANs. False if we have a port VLAN or if
- * we have no configured VLANs. Do not call while holding the
- * mac_filter_hash_lock.
- */
-static bool i40e_vsi_has_vlans(struct i40e_vsi *vsi)
-{
-	bool have_vlans;
-
-	/* If we have a port VLAN, then the VSI cannot have any VLANs
-	 * configured, as all MAC/VLAN filters will be assigned to the PVID.
-	 */
-	if (vsi->info.pvid)
-		return false;
-
-	/* Since we don't have a PVID, we know that if the device is in VLAN
-	 * mode it must be because of a VLAN filter configured on this VSI.
-	 */
-	spin_lock_bh(&vsi->mac_filter_hash_lock);
-	have_vlans = i40e_is_vsi_in_vlan(vsi);
-	spin_unlock_bh(&vsi->mac_filter_hash_lock);
-
-	return have_vlans;
-}
-
-/**
  * i40e_ndo_set_vf_port_vlan
  * @netdev: network interface device structure
  * @vf_id: VF identifier
@@ -4253,19 +4245,9 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, int vf_id,
 		/* duplicate request, so just return success */
 		goto error_pvid;
 
-	if (i40e_vsi_has_vlans(vsi)) {
-		dev_err(&pf->pdev->dev,
-			"VF %d has already configured VLAN filters and the administrator is requesting a port VLAN override.\nPlease unload and reload the VF driver for this change to take effect.\n",
-			vf_id);
-		/* Administrator Error - knock the VF offline until he does
-		 * the right thing by reconfiguring his network correctly
-		 * and then reloading the VF driver.
-		 */
-		i40e_vc_disable_vf(vf);
-		/* During reset the VF got a new VSI, so refresh the pointer. */
-		vsi = pf->vsi[vf->lan_vsi_idx];
-	}
-
+	i40e_vc_reset_vf(vf, true);
+	/* During reset the VF got a new VSI, so refresh a pointer. */
+	vsi = pf->vsi[vf->lan_vsi_idx];
 	/* Locked once because multiple functions below iterate list */
 	spin_lock_bh(&vsi->mac_filter_hash_lock);
 
@@ -4641,7 +4623,7 @@ int i40e_ndo_set_vf_trust(struct net_device *netdev, int vf_id, bool setting)
 		goto out;
 
 	vf->trusted = setting;
-	i40e_vc_disable_vf(vf);
+	i40e_vc_reset_vf(vf, true);
 	dev_info(&pf->pdev->dev, "VF %u is now %strusted\n",
 		 vf_id, setting ? "" : "un");
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
index 091e32c1bb46..49575a640a84 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
@@ -18,6 +18,8 @@
 
 #define I40E_MAX_VF_PROMISC_FLAGS	3
 
+#define I40E_VF_STATE_WAIT_COUNT	20
+
 /* Various queue ctrls */
 enum i40e_queue_ctrl {
 	I40E_QUEUE_CTRL_UNKNOWN = 0,
diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h
index e6e7c1da47fb..3789269ce741 100644
--- a/drivers/net/ethernet/intel/iavf/iavf.h
+++ b/drivers/net/ethernet/intel/iavf/iavf.h
@@ -39,6 +39,7 @@
 #include "iavf_txrx.h"
 #include "iavf_fdir.h"
 #include "iavf_adv_rss.h"
+#include <linux/bitmap.h>
 
 #define DEFAULT_DEBUG_LEVEL_SHIFT 3
 #define PFX "iavf: "
@@ -304,6 +305,7 @@ struct iavf_adapter {
 #define IAVF_FLAG_AQ_DEL_FDIR_FILTER		BIT(26)
 #define IAVF_FLAG_AQ_ADD_ADV_RSS_CFG		BIT(27)
 #define IAVF_FLAG_AQ_DEL_ADV_RSS_CFG		BIT(28)
+#define IAVF_FLAG_AQ_REQUEST_STATS		BIT(29)
 
 	/* OS defined structs */
 	struct net_device *netdev;
@@ -443,6 +445,7 @@ int iavf_up(struct iavf_adapter *adapter);
 void iavf_down(struct iavf_adapter *adapter);
 int iavf_process_config(struct iavf_adapter *adapter);
 void iavf_schedule_reset(struct iavf_adapter *adapter);
+void iavf_schedule_request_stats(struct iavf_adapter *adapter);
 void iavf_reset(struct iavf_adapter *adapter);
 void iavf_set_ethtool_ops(struct net_device *netdev);
 void iavf_update_stats(struct iavf_adapter *adapter);
@@ -500,4 +503,5 @@ void iavf_add_adv_rss_cfg(struct iavf_adapter *adapter);
 void iavf_del_adv_rss_cfg(struct iavf_adapter *adapter);
 struct iavf_mac_filter *iavf_add_filter(struct iavf_adapter *adapter,
 					const u8 *macaddr);
+int iavf_lock_timeout(struct mutex *lock, unsigned int msecs);
 #endif /* _IAVF_H_ */
diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
index 5a359a0a20ec..461f5237a2f8 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
@@ -354,6 +354,9 @@ static void iavf_get_ethtool_stats(struct net_device *netdev,
 	struct iavf_adapter *adapter = netdev_priv(netdev);
 	unsigned int i;
 
+	/* Explicitly request stats refresh */
+	iavf_schedule_request_stats(adapter);
+
 	iavf_add_ethtool_stats(&data, adapter, iavf_gstrings_stats);
 
 	rcu_read_lock();
@@ -612,23 +615,44 @@ static int iavf_set_ringparam(struct net_device *netdev,
 	if ((ring->rx_mini_pending) || (ring->rx_jumbo_pending))
 		return -EINVAL;
 
-	new_tx_count = clamp_t(u32, ring->tx_pending,
-			       IAVF_MIN_TXD,
-			       IAVF_MAX_TXD);
-	new_tx_count = ALIGN(new_tx_count, IAVF_REQ_DESCRIPTOR_MULTIPLE);
+	if (ring->tx_pending > IAVF_MAX_TXD ||
+	    ring->tx_pending < IAVF_MIN_TXD ||
+	    ring->rx_pending > IAVF_MAX_RXD ||
+	    ring->rx_pending < IAVF_MIN_RXD) {
+		netdev_err(netdev, "Descriptors requested (Tx: %d / Rx: %d) out of range [%d-%d] (increment %d)\n",
+			   ring->tx_pending, ring->rx_pending, IAVF_MIN_TXD,
+			   IAVF_MAX_RXD, IAVF_REQ_DESCRIPTOR_MULTIPLE);
+		return -EINVAL;
+	}
+
+	new_tx_count = ALIGN(ring->tx_pending, IAVF_REQ_DESCRIPTOR_MULTIPLE);
+	if (new_tx_count != ring->tx_pending)
+		netdev_info(netdev, "Requested Tx descriptor count rounded up to %d\n",
+			    new_tx_count);
 
-	new_rx_count = clamp_t(u32, ring->rx_pending,
-			       IAVF_MIN_RXD,
-			       IAVF_MAX_RXD);
-	new_rx_count = ALIGN(new_rx_count, IAVF_REQ_DESCRIPTOR_MULTIPLE);
+	new_rx_count = ALIGN(ring->rx_pending, IAVF_REQ_DESCRIPTOR_MULTIPLE);
+	if (new_rx_count != ring->rx_pending)
+		netdev_info(netdev, "Requested Rx descriptor count rounded up to %d\n",
+			    new_rx_count);
 
 	/* if nothing to do return success */
 	if ((new_tx_count == adapter->tx_desc_count) &&
-	    (new_rx_count == adapter->rx_desc_count))
+	    (new_rx_count == adapter->rx_desc_count)) {
+		netdev_dbg(netdev, "Nothing to change, descriptor count is same as requested\n");
 		return 0;
+	}
+
+	if (new_tx_count != adapter->tx_desc_count) {
+		netdev_dbg(netdev, "Changing Tx descriptor count from %d to %d\n",
+			   adapter->tx_desc_count, new_tx_count);
+		adapter->tx_desc_count = new_tx_count;
+	}
 
-	adapter->tx_desc_count = new_tx_count;
-	adapter->rx_desc_count = new_rx_count;
+	if (new_rx_count != adapter->rx_desc_count) {
+		netdev_dbg(netdev, "Changing Rx descriptor count from %d to %d\n",
+			   adapter->rx_desc_count, new_rx_count);
+		adapter->rx_desc_count = new_rx_count;
+	}
 
 	if (netif_running(netdev)) {
 		adapter->flags |= IAVF_FLAG_RESET_NEEDED;
@@ -723,12 +747,31 @@ static int iavf_get_per_queue_coalesce(struct net_device *netdev, u32 queue,
  *
  * Change the ITR settings for a specific queue.
  **/
-static void iavf_set_itr_per_queue(struct iavf_adapter *adapter,
-				   struct ethtool_coalesce *ec, int queue)
+static int iavf_set_itr_per_queue(struct iavf_adapter *adapter,
+				  struct ethtool_coalesce *ec, int queue)
 {
 	struct iavf_ring *rx_ring = &adapter->rx_rings[queue];
 	struct iavf_ring *tx_ring = &adapter->tx_rings[queue];
 	struct iavf_q_vector *q_vector;
+	u16 itr_setting;
+
+	itr_setting = rx_ring->itr_setting & ~IAVF_ITR_DYNAMIC;
+
+	if (ec->rx_coalesce_usecs != itr_setting &&
+	    ec->use_adaptive_rx_coalesce) {
+		netif_info(adapter, drv, adapter->netdev,
+			   "Rx interrupt throttling cannot be changed if adaptive-rx is enabled\n");
+		return -EINVAL;
+	}
+
+	itr_setting = tx_ring->itr_setting & ~IAVF_ITR_DYNAMIC;
+
+	if (ec->tx_coalesce_usecs != itr_setting &&
+	    ec->use_adaptive_tx_coalesce) {
+		netif_info(adapter, drv, adapter->netdev,
+			   "Tx interrupt throttling cannot be changed if adaptive-tx is enabled\n");
+		return -EINVAL;
+	}
 
 	rx_ring->itr_setting = ITR_REG_ALIGN(ec->rx_coalesce_usecs);
 	tx_ring->itr_setting = ITR_REG_ALIGN(ec->tx_coalesce_usecs);
@@ -751,6 +794,7 @@ static void iavf_set_itr_per_queue(struct iavf_adapter *adapter,
 	 * the Tx and Rx ITR values based on the values we have entered
 	 * into the q_vector, no need to write the values now.
 	 */
+	return 0;
 }
 
 /**
@@ -792,9 +836,11 @@ static int __iavf_set_coalesce(struct net_device *netdev,
 	 */
 	if (queue < 0) {
 		for (i = 0; i < adapter->num_active_queues; i++)
-			iavf_set_itr_per_queue(adapter, ec, i);
+			if (iavf_set_itr_per_queue(adapter, ec, i))
+				return -EINVAL;
 	} else if (queue < adapter->num_active_queues) {
-		iavf_set_itr_per_queue(adapter, ec, queue);
+		if (iavf_set_itr_per_queue(adapter, ec, queue))
+			return -EINVAL;
 	} else {
 		netif_info(adapter, drv, netdev, "Invalid queue value, queue range is 0 - %d\n",
 			   adapter->num_active_queues - 1);
@@ -1776,6 +1822,7 @@ static int iavf_set_channels(struct net_device *netdev,
 {
 	struct iavf_adapter *adapter = netdev_priv(netdev);
 	u32 num_req = ch->combined_count;
+	int i;
 
 	if ((adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ) &&
 	    adapter->num_tc) {
@@ -1786,7 +1833,7 @@ static int iavf_set_channels(struct net_device *netdev,
 	/* All of these should have already been checked by ethtool before this
 	 * even gets to us, but just to be sure.
 	 */
-	if (num_req > adapter->vsi_res->num_queue_pairs)
+	if (num_req == 0 || num_req > adapter->vsi_res->num_queue_pairs)
 		return -EINVAL;
 
 	if (num_req == adapter->num_active_queues)
@@ -1798,6 +1845,20 @@ static int iavf_set_channels(struct net_device *netdev,
 	adapter->num_req_queues = num_req;
 	adapter->flags |= IAVF_FLAG_REINIT_ITR_NEEDED;
 	iavf_schedule_reset(adapter);
+
+	/* wait for the reset is done */
+	for (i = 0; i < IAVF_RESET_WAIT_COMPLETE_COUNT; i++) {
+		msleep(IAVF_RESET_WAIT_MS);
+		if (adapter->flags & IAVF_FLAG_RESET_PENDING)
+			continue;
+		break;
+	}
+	if (i == IAVF_RESET_WAIT_COMPLETE_COUNT) {
+		adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED;
+		adapter->num_active_queues = num_req;
+		return -EOPNOTSUPP;
+	}
+
 	return 0;
 }
 
@@ -1844,14 +1905,13 @@ static int iavf_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
 
 	if (hfunc)
 		*hfunc = ETH_RSS_HASH_TOP;
-	if (!indir)
-		return 0;
-
-	memcpy(key, adapter->rss_key, adapter->rss_key_size);
+	if (key)
+		memcpy(key, adapter->rss_key, adapter->rss_key_size);
 
-	/* Each 32 bits pointed by 'indir' is stored with a lut entry */
-	for (i = 0; i < adapter->rss_lut_size; i++)
-		indir[i] = (u32)adapter->rss_lut[i];
+	if (indir)
+		/* Each 32 bits pointed by 'indir' is stored with a lut entry */
+		for (i = 0; i < adapter->rss_lut_size; i++)
+			indir[i] = (u32)adapter->rss_lut[i];
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index 847d67e32a54..4e7c04047f91 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -147,7 +147,7 @@ enum iavf_status iavf_free_virt_mem_d(struct iavf_hw *hw,
  *
  * Returns 0 on success, negative on failure
  **/
-static int iavf_lock_timeout(struct mutex *lock, unsigned int msecs)
+int iavf_lock_timeout(struct mutex *lock, unsigned int msecs)
 {
 	unsigned int wait, delay = 10;
 
@@ -175,6 +175,19 @@ void iavf_schedule_reset(struct iavf_adapter *adapter)
 }
 
 /**
+ * iavf_schedule_request_stats - Set the flags and schedule statistics request
+ * @adapter: board private structure
+ *
+ * Sets IAVF_FLAG_AQ_REQUEST_STATS flag so iavf_watchdog_task() will explicitly
+ * request and refresh ethtool stats
+ **/
+void iavf_schedule_request_stats(struct iavf_adapter *adapter)
+{
+	adapter->aq_required |= IAVF_FLAG_AQ_REQUEST_STATS;
+	mod_delayed_work(iavf_wq, &adapter->watchdog_task, 0);
+}
+
+/**
  * iavf_tx_timeout - Respond to a Tx Hang
  * @netdev: network interface device structure
  * @txqueue: queue number that is timing out
@@ -697,6 +710,21 @@ static void iavf_del_vlan(struct iavf_adapter *adapter, u16 vlan)
 }
 
 /**
+ * iavf_restore_filters
+ * @adapter: board private structure
+ *
+ * Restore existing non MAC filters when VF netdev comes back up
+ **/
+static void iavf_restore_filters(struct iavf_adapter *adapter)
+{
+	u16 vid;
+
+	/* re-add all VLAN filters */
+	for_each_set_bit(vid, adapter->vsi.active_vlans, VLAN_N_VID)
+		iavf_add_vlan(adapter, vid);
+}
+
+/**
  * iavf_vlan_rx_add_vid - Add a VLAN filter to a device
  * @netdev: network device struct
  * @proto: unused protocol data
@@ -709,8 +737,11 @@ static int iavf_vlan_rx_add_vid(struct net_device *netdev,
 
 	if (!VLAN_ALLOWED(adapter))
 		return -EIO;
+
 	if (iavf_add_vlan(adapter, vid) == NULL)
 		return -ENOMEM;
+
+	set_bit(vid, adapter->vsi.active_vlans);
 	return 0;
 }
 
@@ -725,11 +756,10 @@ static int iavf_vlan_rx_kill_vid(struct net_device *netdev,
 {
 	struct iavf_adapter *adapter = netdev_priv(netdev);
 
-	if (VLAN_ALLOWED(adapter)) {
-		iavf_del_vlan(adapter, vid);
-		return 0;
-	}
-	return -EIO;
+	iavf_del_vlan(adapter, vid);
+	clear_bit(vid, adapter->vsi.active_vlans);
+
+	return 0;
 }
 
 /**
@@ -1639,8 +1669,7 @@ static int iavf_process_aq_command(struct iavf_adapter *adapter)
 		iavf_set_promiscuous(adapter, FLAG_VF_MULTICAST_PROMISC);
 		return 0;
 	}
-
-	if ((adapter->aq_required & IAVF_FLAG_AQ_RELEASE_PROMISC) &&
+	if ((adapter->aq_required & IAVF_FLAG_AQ_RELEASE_PROMISC) ||
 	    (adapter->aq_required & IAVF_FLAG_AQ_RELEASE_ALLMULTI)) {
 		iavf_set_promiscuous(adapter, 0);
 		return 0;
@@ -1688,6 +1717,11 @@ static int iavf_process_aq_command(struct iavf_adapter *adapter)
 		iavf_del_adv_rss_cfg(adapter);
 		return 0;
 	}
+	if (adapter->aq_required & IAVF_FLAG_AQ_REQUEST_STATS) {
+		iavf_request_stats(adapter);
+		return 0;
+	}
+
 	return -EAGAIN;
 }
 
@@ -2012,6 +2046,7 @@ static void iavf_watchdog_task(struct work_struct *work)
 		}
 		adapter->aq_required = 0;
 		adapter->current_op = VIRTCHNL_OP_UNKNOWN;
+		mutex_unlock(&adapter->crit_lock);
 		queue_delayed_work(iavf_wq,
 				   &adapter->watchdog_task,
 				   msecs_to_jiffies(10));
@@ -2042,16 +2077,14 @@ static void iavf_watchdog_task(struct work_struct *work)
 			iavf_detect_recover_hung(&adapter->vsi);
 		break;
 	case __IAVF_REMOVE:
-		mutex_unlock(&adapter->crit_lock);
-		return;
 	default:
+		mutex_unlock(&adapter->crit_lock);
 		return;
 	}
 
 	/* check for hw reset */
 	reg_val = rd32(hw, IAVF_VF_ARQLEN1) & IAVF_VF_ARQLEN1_ARQENABLE_MASK;
 	if (!reg_val) {
-		iavf_change_state(adapter, __IAVF_RESETTING);
 		adapter->flags |= IAVF_FLAG_RESET_PENDING;
 		adapter->aq_required = 0;
 		adapter->current_op = VIRTCHNL_OP_UNKNOWN;
@@ -2123,8 +2156,8 @@ static void iavf_disable_vf(struct iavf_adapter *adapter)
 
 	iavf_free_misc_irq(adapter);
 	iavf_reset_interrupt_capability(adapter);
-	iavf_free_queues(adapter);
 	iavf_free_q_vectors(adapter);
+	iavf_free_queues(adapter);
 	memset(adapter->vf_res, 0, IAVF_VIRTCHNL_VF_RESOURCE_SIZE);
 	iavf_shutdown_adminq(&adapter->hw);
 	adapter->netdev->flags &= ~IFF_UP;
@@ -2152,7 +2185,6 @@ static void iavf_reset_task(struct work_struct *work)
 	struct net_device *netdev = adapter->netdev;
 	struct iavf_hw *hw = &adapter->hw;
 	struct iavf_mac_filter *f, *ftmp;
-	struct iavf_vlan_filter *vlf;
 	struct iavf_cloud_filter *cf;
 	u32 reg_val;
 	int i = 0, err;
@@ -2215,6 +2247,7 @@ static void iavf_reset_task(struct work_struct *work)
 	}
 
 	pci_set_master(adapter->pdev);
+	pci_restore_msi_state(adapter->pdev);
 
 	if (i == IAVF_RESET_WAIT_COMPLETE_COUNT) {
 		dev_err(&adapter->pdev->dev, "Reset never finished (%x)\n",
@@ -2233,6 +2266,7 @@ continue_reset:
 		   (adapter->state == __IAVF_RESETTING));
 
 	if (running) {
+		netdev->flags &= ~IFF_UP;
 		netif_carrier_off(netdev);
 		netif_tx_stop_all_queues(netdev);
 		adapter->link_up = false;
@@ -2292,11 +2326,6 @@ continue_reset:
 	list_for_each_entry(f, &adapter->mac_filter_list, list) {
 		f->add = true;
 	}
-	/* re-add all VLAN filters */
-	list_for_each_entry(vlf, &adapter->vlan_filter_list, list) {
-		vlf->add = true;
-	}
-
 	spin_unlock_bh(&adapter->mac_vlan_list_lock);
 
 	/* check if TCs are running and re-add all cloud filters */
@@ -2310,7 +2339,6 @@ continue_reset:
 	spin_unlock_bh(&adapter->cloud_filter_list_lock);
 
 	adapter->aq_required |= IAVF_FLAG_AQ_ADD_MAC_FILTER;
-	adapter->aq_required |= IAVF_FLAG_AQ_ADD_VLAN_FILTER;
 	adapter->aq_required |= IAVF_FLAG_AQ_ADD_CLOUD_FILTER;
 	iavf_misc_irq_enable(adapter);
 
@@ -2344,7 +2372,7 @@ continue_reset:
 		 * to __IAVF_RUNNING
 		 */
 		iavf_up_complete(adapter);
-
+		netdev->flags |= IFF_UP;
 		iavf_irq_enable(adapter, true);
 	} else {
 		iavf_change_state(adapter, __IAVF_DOWN);
@@ -2357,8 +2385,10 @@ continue_reset:
 reset_err:
 	mutex_unlock(&adapter->client_lock);
 	mutex_unlock(&adapter->crit_lock);
-	if (running)
+	if (running) {
 		iavf_change_state(adapter, __IAVF_RUNNING);
+		netdev->flags |= IFF_UP;
+	}
 	dev_err(&adapter->pdev->dev, "failed to allocate resources during reinit\n");
 	iavf_close(netdev);
 }
@@ -2410,7 +2440,7 @@ static void iavf_adminq_task(struct work_struct *work)
 
 	/* check for error indications */
 	val = rd32(hw, hw->aq.arq.len);
-	if (val == 0xdeadbeef) /* indicates device in reset */
+	if (val == 0xdeadbeef || val == 0xffffffff) /* device in reset */
 		goto freedom;
 	oldval = val;
 	if (val & IAVF_VF_ARQLEN1_ARQVFE_MASK) {
@@ -3095,8 +3125,10 @@ static int iavf_configure_clsflower(struct iavf_adapter *adapter,
 		return -ENOMEM;
 
 	while (!mutex_trylock(&adapter->crit_lock)) {
-		if (--count == 0)
-			goto err;
+		if (--count == 0) {
+			kfree(filter);
+			return err;
+		}
 		udelay(1);
 	}
 
@@ -3107,11 +3139,11 @@ static int iavf_configure_clsflower(struct iavf_adapter *adapter,
 	/* start out with flow type and eth type IPv4 to begin with */
 	filter->f.flow_type = VIRTCHNL_TCP_V4_FLOW;
 	err = iavf_parse_cls_flower(adapter, cls_flower, filter);
-	if (err < 0)
+	if (err)
 		goto err;
 
 	err = iavf_handle_tclass(adapter, tc, filter);
-	if (err < 0)
+	if (err)
 		goto err;
 
 	/* add filter to the list */
@@ -3308,6 +3340,9 @@ static int iavf_open(struct net_device *netdev)
 
 	spin_unlock_bh(&adapter->mac_vlan_list_lock);
 
+	/* Restore VLAN filters that were removed with IFF_DOWN */
+	iavf_restore_filters(adapter);
+
 	iavf_configure(adapter);
 
 	iavf_up_complete(adapter);
@@ -3415,11 +3450,16 @@ static int iavf_set_features(struct net_device *netdev,
 {
 	struct iavf_adapter *adapter = netdev_priv(netdev);
 
-	/* Don't allow changing VLAN_RX flag when adapter is not capable
-	 * of VLAN offload
+	/* Don't allow enabling VLAN features when adapter is not capable
+	 * of VLAN offload/filtering
 	 */
 	if (!VLAN_ALLOWED(adapter)) {
-		if ((netdev->features ^ features) & NETIF_F_HW_VLAN_CTAG_RX)
+		netdev->hw_features &= ~(NETIF_F_HW_VLAN_CTAG_RX |
+					 NETIF_F_HW_VLAN_CTAG_TX |
+					 NETIF_F_HW_VLAN_CTAG_FILTER);
+		if (features & (NETIF_F_HW_VLAN_CTAG_RX |
+				NETIF_F_HW_VLAN_CTAG_TX |
+				NETIF_F_HW_VLAN_CTAG_FILTER))
 			return -EINVAL;
 	} else if ((netdev->features ^ features) & NETIF_F_HW_VLAN_CTAG_RX) {
 		if (features & NETIF_F_HW_VLAN_CTAG_RX)
@@ -3503,7 +3543,8 @@ static netdev_features_t iavf_fix_features(struct net_device *netdev,
 {
 	struct iavf_adapter *adapter = netdev_priv(netdev);
 
-	if (!(adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN))
+	if (adapter->vf_res &&
+	    !(adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN))
 		features &= ~(NETIF_F_HW_VLAN_CTAG_TX |
 			      NETIF_F_HW_VLAN_CTAG_RX |
 			      NETIF_F_HW_VLAN_CTAG_FILTER);
diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
index 8c3f0f77cb57..d60bf7c21200 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
@@ -607,7 +607,7 @@ void iavf_add_vlans(struct iavf_adapter *adapter)
 		if (f->add)
 			count++;
 	}
-	if (!count) {
+	if (!count || !VLAN_ALLOWED(adapter)) {
 		adapter->aq_required &= ~IAVF_FLAG_AQ_ADD_VLAN_FILTER;
 		spin_unlock_bh(&adapter->mac_vlan_list_lock);
 		return;
@@ -673,9 +673,19 @@ void iavf_del_vlans(struct iavf_adapter *adapter)
 
 	spin_lock_bh(&adapter->mac_vlan_list_lock);
 
-	list_for_each_entry(f, &adapter->vlan_filter_list, list) {
-		if (f->remove)
+	list_for_each_entry_safe(f, ftmp, &adapter->vlan_filter_list, list) {
+		/* since VLAN capabilities are not allowed, we dont want to send
+		 * a VLAN delete request because it will most likely fail and
+		 * create unnecessary errors/noise, so just free the VLAN
+		 * filters marked for removal to enable bailing out before
+		 * sending a virtchnl message
+		 */
+		if (f->remove && !VLAN_ALLOWED(adapter)) {
+			list_del(&f->list);
+			kfree(f);
+		} else if (f->remove) {
 			count++;
+		}
 	}
 	if (!count) {
 		adapter->aq_required &= ~IAVF_FLAG_AQ_DEL_VLAN_FILTER;
@@ -784,6 +794,8 @@ void iavf_request_stats(struct iavf_adapter *adapter)
 		/* no error message, this isn't crucial */
 		return;
 	}
+
+	adapter->aq_required &= ~IAVF_FLAG_AQ_REQUEST_STATS;
 	adapter->current_op = VIRTCHNL_OP_GET_STATS;
 	vqs.vsi_id = adapter->vsi_res->vsi_id;
 	/* queue maps are ignored for this message - only the vsi is used */
@@ -1722,8 +1734,37 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter,
 		}
 		spin_lock_bh(&adapter->mac_vlan_list_lock);
 		iavf_add_filter(adapter, adapter->hw.mac.addr);
+
+		if (VLAN_ALLOWED(adapter)) {
+			if (!list_empty(&adapter->vlan_filter_list)) {
+				struct iavf_vlan_filter *vlf;
+
+				/* re-add all VLAN filters over virtchnl */
+				list_for_each_entry(vlf,
+						    &adapter->vlan_filter_list,
+						    list)
+					vlf->add = true;
+
+				adapter->aq_required |=
+					IAVF_FLAG_AQ_ADD_VLAN_FILTER;
+			}
+		}
+
 		spin_unlock_bh(&adapter->mac_vlan_list_lock);
 		iavf_process_config(adapter);
+
+		/* unlock crit_lock before acquiring rtnl_lock as other
+		 * processes holding rtnl_lock could be waiting for the same
+		 * crit_lock
+		 */
+		mutex_unlock(&adapter->crit_lock);
+		rtnl_lock();
+		netdev_update_features(adapter->netdev);
+		rtnl_unlock();
+		if (iavf_lock_timeout(&adapter->crit_lock, 10000))
+			dev_warn(&adapter->pdev->dev, "failed to acquire crit_lock in %s\n",
+				 __FUNCTION__);
+
 		}
 		break;
 	case VIRTCHNL_OP_ENABLE_QUEUES:
diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index 1efc635cc0f5..fafe020e46ee 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -6,6 +6,18 @@
 #include "ice_lib.h"
 #include "ice_dcb_lib.h"
 
+static bool ice_alloc_rx_buf_zc(struct ice_rx_ring *rx_ring)
+{
+	rx_ring->xdp_buf = kcalloc(rx_ring->count, sizeof(*rx_ring->xdp_buf), GFP_KERNEL);
+	return !!rx_ring->xdp_buf;
+}
+
+static bool ice_alloc_rx_buf(struct ice_rx_ring *rx_ring)
+{
+	rx_ring->rx_buf = kcalloc(rx_ring->count, sizeof(*rx_ring->rx_buf), GFP_KERNEL);
+	return !!rx_ring->rx_buf;
+}
+
 /**
  * __ice_vsi_get_qs_contig - Assign a contiguous chunk of queues to VSI
  * @qs_cfg: gathered variables needed for PF->VSI queues assignment
@@ -492,8 +504,11 @@ int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
 			xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
 					 ring->q_index, ring->q_vector->napi.napi_id);
 
+		kfree(ring->rx_buf);
 		ring->xsk_pool = ice_xsk_pool(ring);
 		if (ring->xsk_pool) {
+			if (!ice_alloc_rx_buf_zc(ring))
+				return -ENOMEM;
 			xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq);
 
 			ring->rx_buf_len =
@@ -508,6 +523,8 @@ int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
 			dev_info(dev, "Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring %d\n",
 				 ring->q_index);
 		} else {
+			if (!ice_alloc_rx_buf(ring))
+				return -ENOMEM;
 			if (!xdp_rxq_info_is_reg(&ring->xdp_rxq))
 				/* coverity[check_return] */
 				xdp_rxq_info_reg(&ring->xdp_rxq,
diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_nl.c b/drivers/net/ethernet/intel/ice/ice_dcb_nl.c
index 7fdeb411b6df..3eb01731e496 100644
--- a/drivers/net/ethernet/intel/ice/ice_dcb_nl.c
+++ b/drivers/net/ethernet/intel/ice/ice_dcb_nl.c
@@ -97,6 +97,9 @@ static int ice_dcbnl_setets(struct net_device *netdev, struct ieee_ets *ets)
 
 	new_cfg->etscfg.maxtcs = pf->hw.func_caps.common_cap.maxtc;
 
+	if (!bwcfg)
+		new_cfg->etscfg.tcbwtable[0] = 100;
+
 	if (!bwrec)
 		new_cfg->etsrec.tcbwtable[0] = 100;
 
@@ -167,15 +170,18 @@ static u8 ice_dcbnl_setdcbx(struct net_device *netdev, u8 mode)
 	if (mode == pf->dcbx_cap)
 		return ICE_DCB_NO_HW_CHG;
 
-	pf->dcbx_cap = mode;
 	qos_cfg = &pf->hw.port_info->qos_cfg;
-	if (mode & DCB_CAP_DCBX_VER_CEE) {
-		if (qos_cfg->local_dcbx_cfg.pfc_mode == ICE_QOS_MODE_DSCP)
-			return ICE_DCB_NO_HW_CHG;
+
+	/* DSCP configuration is not DCBx negotiated */
+	if (qos_cfg->local_dcbx_cfg.pfc_mode == ICE_QOS_MODE_DSCP)
+		return ICE_DCB_NO_HW_CHG;
+
+	pf->dcbx_cap = mode;
+
+	if (mode & DCB_CAP_DCBX_VER_CEE)
 		qos_cfg->local_dcbx_cfg.dcbx_mode = ICE_DCBX_MODE_CEE;
-	} else {
+	else
 		qos_cfg->local_dcbx_cfg.dcbx_mode = ICE_DCBX_MODE_IEEE;
-	}
 
 	dev_info(ice_pf_to_dev(pf), "DCBx mode = 0x%x\n", mode);
 	return ICE_DCB_HW_CHG_RST;
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
index 38960bcc384c..b6e7f47c8c78 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
@@ -1268,7 +1268,7 @@ ice_fdir_write_all_fltr(struct ice_pf *pf, struct ice_fdir_fltr *input,
 		bool is_tun = tun == ICE_FD_HW_SEG_TUN;
 		int err;
 
-		if (is_tun && !ice_get_open_tunnel_port(&pf->hw, &port_num))
+		if (is_tun && !ice_get_open_tunnel_port(&pf->hw, &port_num, TNL_ALL))
 			continue;
 		err = ice_fdir_write_fltr(pf, input, add, is_tun);
 		if (err)
@@ -1652,7 +1652,7 @@ int ice_add_fdir_ethtool(struct ice_vsi *vsi, struct ethtool_rxnfc *cmd)
 	}
 
 	/* return error if not an update and no available filters */
-	fltrs_needed = ice_get_open_tunnel_port(hw, &tunnel_port) ? 2 : 1;
+	fltrs_needed = ice_get_open_tunnel_port(hw, &tunnel_port, TNL_ALL) ? 2 : 1;
 	if (!ice_fdir_find_fltr_by_idx(hw, fsp->location) &&
 	    ice_fdir_num_avail_fltr(hw, pf->vsi[vsi->idx]) < fltrs_needed) {
 		dev_err(dev, "Failed to add filter.  The maximum number of flow director filters has been reached.\n");
diff --git a/drivers/net/ethernet/intel/ice/ice_fdir.c b/drivers/net/ethernet/intel/ice/ice_fdir.c
index cbd8424631e3..4dca009bdd50 100644
--- a/drivers/net/ethernet/intel/ice/ice_fdir.c
+++ b/drivers/net/ethernet/intel/ice/ice_fdir.c
@@ -924,7 +924,7 @@ ice_fdir_get_gen_prgm_pkt(struct ice_hw *hw, struct ice_fdir_fltr *input,
 		memcpy(pkt, ice_fdir_pkt[idx].pkt, ice_fdir_pkt[idx].pkt_len);
 		loc = pkt;
 	} else {
-		if (!ice_get_open_tunnel_port(hw, &tnl_port))
+		if (!ice_get_open_tunnel_port(hw, &tnl_port, TNL_ALL))
 			return ICE_ERR_DOES_NOT_EXIST;
 		if (!ice_fdir_pkt[idx].tun_pkt)
 			return ICE_ERR_PARAM;
diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
index 23cfcceb1536..6ad1c2559724 100644
--- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
+++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
@@ -1899,9 +1899,11 @@ static struct ice_buf *ice_pkg_buf(struct ice_buf_build *bld)
  * ice_get_open_tunnel_port - retrieve an open tunnel port
  * @hw: pointer to the HW structure
  * @port: returns open port
+ * @type: type of tunnel, can be TNL_LAST if it doesn't matter
  */
 bool
-ice_get_open_tunnel_port(struct ice_hw *hw, u16 *port)
+ice_get_open_tunnel_port(struct ice_hw *hw, u16 *port,
+			 enum ice_tunnel_type type)
 {
 	bool res = false;
 	u16 i;
@@ -1909,7 +1911,8 @@ ice_get_open_tunnel_port(struct ice_hw *hw, u16 *port)
 	mutex_lock(&hw->tnl_lock);
 
 	for (i = 0; i < hw->tnl.count && i < ICE_TUNNEL_MAX_ENTRIES; i++)
-		if (hw->tnl.tbl[i].valid && hw->tnl.tbl[i].port) {
+		if (hw->tnl.tbl[i].valid && hw->tnl.tbl[i].port &&
+		    (type == TNL_LAST || type == hw->tnl.tbl[i].type)) {
 			*port = hw->tnl.tbl[i].port;
 			res = true;
 			break;
diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.h b/drivers/net/ethernet/intel/ice/ice_flex_pipe.h
index 344c2637facd..a2863f38fd1f 100644
--- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.h
+++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.h
@@ -33,7 +33,8 @@ enum ice_status
 ice_get_sw_fv_list(struct ice_hw *hw, u8 *prot_ids, u16 ids_cnt,
 		   unsigned long *bm, struct list_head *fv_list);
 bool
-ice_get_open_tunnel_port(struct ice_hw *hw, u16 *port);
+ice_get_open_tunnel_port(struct ice_hw *hw, u16 *port,
+			 enum ice_tunnel_type type);
 int ice_udp_tunnel_set_port(struct net_device *netdev, unsigned int table,
 			    unsigned int idx, struct udp_tunnel_info *ti);
 int ice_udp_tunnel_unset_port(struct net_device *netdev, unsigned int table,
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 40562600a8cf..09a3297cd63c 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -89,8 +89,13 @@ static int ice_vsi_alloc_arrays(struct ice_vsi *vsi)
 	if (!vsi->rx_rings)
 		goto err_rings;
 
-	/* XDP will have vsi->alloc_txq Tx queues as well, so double the size */
-	vsi->txq_map = devm_kcalloc(dev, (2 * vsi->alloc_txq),
+	/* txq_map needs to have enough space to track both Tx (stack) rings
+	 * and XDP rings; at this point vsi->num_xdp_txq might not be set,
+	 * so use num_possible_cpus() as we want to always provide XDP ring
+	 * per CPU, regardless of queue count settings from user that might
+	 * have come from ethtool's set_channels() callback;
+	 */
+	vsi->txq_map = devm_kcalloc(dev, (vsi->alloc_txq + num_possible_cpus()),
 				    sizeof(*vsi->txq_map), GFP_KERNEL);
 
 	if (!vsi->txq_map)
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index f099797f35e3..73c61cdb036f 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -2609,7 +2609,18 @@ int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog)
 			ice_stat_str(status));
 		goto clear_xdp_rings;
 	}
-	ice_vsi_assign_bpf_prog(vsi, prog);
+
+	/* assign the prog only when it's not already present on VSI;
+	 * this flow is a subject of both ethtool -L and ndo_bpf flows;
+	 * VSI rebuild that happens under ethtool -L can expose us to
+	 * the bpf_prog refcount issues as we would be swapping same
+	 * bpf_prog pointers from vsi->xdp_prog and calling bpf_prog_put
+	 * on it as it would be treated as an 'old_prog'; for ndo_bpf
+	 * this is not harmful as dev_xdp_install bumps the refcount
+	 * before calling the op exposed by the driver;
+	 */
+	if (!ice_is_xdp_ena_vsi(vsi))
+		ice_vsi_assign_bpf_prog(vsi, prog);
 
 	return 0;
 clear_xdp_rings:
@@ -2785,6 +2796,11 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog,
 		if (xdp_ring_err)
 			NL_SET_ERR_MSG_MOD(extack, "Freeing XDP Tx resources failed");
 	} else {
+		/* safe to call even when prog == vsi->xdp_prog as
+		 * dev_xdp_install in net/core/dev.c incremented prog's
+		 * refcount so corresponding bpf_prog_put won't cause
+		 * underflow
+		 */
 		ice_vsi_assign_bpf_prog(vsi, prog);
 	}
 
@@ -5865,6 +5881,9 @@ static int ice_up_complete(struct ice_vsi *vsi)
 		netif_carrier_on(vsi->netdev);
 	}
 
+	/* clear this now, and the first stats read will be used as baseline */
+	vsi->stat_offsets_loaded = false;
+
 	ice_service_task_schedule(pf);
 
 	return 0;
@@ -5911,14 +5930,15 @@ ice_fetch_u64_stats_per_ring(struct u64_stats_sync *syncp, struct ice_q_stats st
 /**
  * ice_update_vsi_tx_ring_stats - Update VSI Tx ring stats counters
  * @vsi: the VSI to be updated
+ * @vsi_stats: the stats struct to be updated
  * @rings: rings to work on
  * @count: number of rings
  */
 static void
-ice_update_vsi_tx_ring_stats(struct ice_vsi *vsi, struct ice_tx_ring **rings,
-			     u16 count)
+ice_update_vsi_tx_ring_stats(struct ice_vsi *vsi,
+			     struct rtnl_link_stats64 *vsi_stats,
+			     struct ice_tx_ring **rings, u16 count)
 {
-	struct rtnl_link_stats64 *vsi_stats = &vsi->net_stats;
 	u16 i;
 
 	for (i = 0; i < count; i++) {
@@ -5942,15 +5962,13 @@ ice_update_vsi_tx_ring_stats(struct ice_vsi *vsi, struct ice_tx_ring **rings,
  */
 static void ice_update_vsi_ring_stats(struct ice_vsi *vsi)
 {
-	struct rtnl_link_stats64 *vsi_stats = &vsi->net_stats;
+	struct rtnl_link_stats64 *vsi_stats;
 	u64 pkts, bytes;
 	int i;
 
-	/* reset netdev stats */
-	vsi_stats->tx_packets = 0;
-	vsi_stats->tx_bytes = 0;
-	vsi_stats->rx_packets = 0;
-	vsi_stats->rx_bytes = 0;
+	vsi_stats = kzalloc(sizeof(*vsi_stats), GFP_ATOMIC);
+	if (!vsi_stats)
+		return;
 
 	/* reset non-netdev (extended) stats */
 	vsi->tx_restart = 0;
@@ -5962,7 +5980,8 @@ static void ice_update_vsi_ring_stats(struct ice_vsi *vsi)
 	rcu_read_lock();
 
 	/* update Tx rings counters */
-	ice_update_vsi_tx_ring_stats(vsi, vsi->tx_rings, vsi->num_txq);
+	ice_update_vsi_tx_ring_stats(vsi, vsi_stats, vsi->tx_rings,
+				     vsi->num_txq);
 
 	/* update Rx rings counters */
 	ice_for_each_rxq(vsi, i) {
@@ -5977,10 +5996,17 @@ static void ice_update_vsi_ring_stats(struct ice_vsi *vsi)
 
 	/* update XDP Tx rings counters */
 	if (ice_is_xdp_ena_vsi(vsi))
-		ice_update_vsi_tx_ring_stats(vsi, vsi->xdp_rings,
+		ice_update_vsi_tx_ring_stats(vsi, vsi_stats, vsi->xdp_rings,
 					     vsi->num_xdp_txq);
 
 	rcu_read_unlock();
+
+	vsi->net_stats.tx_packets = vsi_stats->tx_packets;
+	vsi->net_stats.tx_bytes = vsi_stats->tx_bytes;
+	vsi->net_stats.rx_packets = vsi_stats->rx_packets;
+	vsi->net_stats.rx_bytes = vsi_stats->rx_bytes;
+
+	kfree(vsi_stats);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c
index bf7247c6f58e..442b031b0edc 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.c
@@ -705,7 +705,7 @@ static int ice_ptp_adjfine(struct ptp_clock_info *info, long scaled_ppm)
 		scaled_ppm = -scaled_ppm;
 	}
 
-	while ((u64)scaled_ppm > div_u64(U64_MAX, incval)) {
+	while ((u64)scaled_ppm > div64_u64(U64_MAX, incval)) {
 		/* handle overflow by scaling down the scaled_ppm and
 		 * the divisor, losing some precision
 		 */
@@ -1540,19 +1540,16 @@ static void ice_ptp_tx_tstamp_work(struct kthread_work *work)
 		if (err)
 			continue;
 
-		/* Check if the timestamp is valid */
-		if (!(raw_tstamp & ICE_PTP_TS_VALID))
+		/* Check if the timestamp is invalid or stale */
+		if (!(raw_tstamp & ICE_PTP_TS_VALID) ||
+		    raw_tstamp == tx->tstamps[idx].cached_tstamp)
 			continue;
 
-		/* clear the timestamp register, so that it won't show valid
-		 * again when re-used.
-		 */
-		ice_clear_phy_tstamp(hw, tx->quad, phy_idx);
-
 		/* The timestamp is valid, so we'll go ahead and clear this
 		 * index and then send the timestamp up to the stack.
 		 */
 		spin_lock(&tx->lock);
+		tx->tstamps[idx].cached_tstamp = raw_tstamp;
 		clear_bit(idx, tx->in_use);
 		skb = tx->tstamps[idx].skb;
 		tx->tstamps[idx].skb = NULL;
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.h b/drivers/net/ethernet/intel/ice/ice_ptp.h
index f71ad317d6c8..53c15fc9d996 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.h
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.h
@@ -55,15 +55,21 @@ struct ice_perout_channel {
  * struct ice_tx_tstamp - Tracking for a single Tx timestamp
  * @skb: pointer to the SKB for this timestamp request
  * @start: jiffies when the timestamp was first requested
+ * @cached_tstamp: last read timestamp
  *
  * This structure tracks a single timestamp request. The SKB pointer is
  * provided when initiating a request. The start time is used to ensure that
  * we discard old requests that were not fulfilled within a 2 second time
  * window.
+ * Timestamp values in the PHY are read only and do not get cleared except at
+ * hardware reset or when a new timestamp value is captured. The cached_tstamp
+ * field is used to detect the case where a new timestamp has not yet been
+ * captured, ensuring that we avoid sending stale timestamp data to the stack.
  */
 struct ice_tx_tstamp {
 	struct sk_buff *skb;
 	unsigned long start;
+	u64 cached_tstamp;
 };
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c
index 793f4a9fc2cd..183d93033890 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.c
+++ b/drivers/net/ethernet/intel/ice/ice_switch.c
@@ -3796,10 +3796,13 @@ static struct ice_protocol_entry ice_prot_id_tbl[ICE_PROTOCOL_LAST] = {
  * ice_find_recp - find a recipe
  * @hw: pointer to the hardware structure
  * @lkup_exts: extension sequence to match
+ * @tun_type: type of recipe tunnel
  *
  * Returns index of matching recipe, or ICE_MAX_NUM_RECIPES if not found.
  */
-static u16 ice_find_recp(struct ice_hw *hw, struct ice_prot_lkup_ext *lkup_exts)
+static u16
+ice_find_recp(struct ice_hw *hw, struct ice_prot_lkup_ext *lkup_exts,
+	      enum ice_sw_tunnel_type tun_type)
 {
 	bool refresh_required = true;
 	struct ice_sw_recipe *recp;
@@ -3860,8 +3863,9 @@ static u16 ice_find_recp(struct ice_hw *hw, struct ice_prot_lkup_ext *lkup_exts)
 			}
 			/* If for "i"th recipe the found was never set to false
 			 * then it means we found our match
+			 * Also tun type of recipe needs to be checked
 			 */
-			if (found)
+			if (found && recp[i].tun_type == tun_type)
 				return i; /* Return the recipe ID */
 		}
 	}
@@ -4651,11 +4655,12 @@ ice_add_adv_recipe(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups,
 	}
 
 	/* Look for a recipe which matches our requested fv / mask list */
-	*rid = ice_find_recp(hw, lkup_exts);
+	*rid = ice_find_recp(hw, lkup_exts, rinfo->tun_type);
 	if (*rid < ICE_MAX_NUM_RECIPES)
 		/* Success if found a recipe that match the existing criteria */
 		goto err_unroll;
 
+	rm->tun_type = rinfo->tun_type;
 	/* Recipe we need does not exist, add a recipe */
 	status = ice_add_sw_recipe(hw, rm, profiles);
 	if (status)
@@ -4958,11 +4963,13 @@ ice_fill_adv_packet_tun(struct ice_hw *hw, enum ice_sw_tunnel_type tun_type,
 
 	switch (tun_type) {
 	case ICE_SW_TUN_VXLAN:
+		if (!ice_get_open_tunnel_port(hw, &open_port, TNL_VXLAN))
+			return ICE_ERR_CFG;
+		break;
 	case ICE_SW_TUN_GENEVE:
-		if (!ice_get_open_tunnel_port(hw, &open_port))
+		if (!ice_get_open_tunnel_port(hw, &open_port, TNL_GENEVE))
 			return ICE_ERR_CFG;
 		break;
-
 	default:
 		/* Nothing needs to be done for this tunnel type */
 		return 0;
@@ -5555,7 +5562,7 @@ ice_rem_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups,
 	if (status)
 		return status;
 
-	rid = ice_find_recp(hw, &lkup_exts);
+	rid = ice_find_recp(hw, &lkup_exts, rinfo->tun_type);
 	/* If did not find a recipe that match the existing criteria */
 	if (rid == ICE_MAX_NUM_RECIPES)
 		return ICE_ERR_PARAM;
diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.c b/drivers/net/ethernet/intel/ice/ice_tc_lib.c
index e5d23feb6701..25cca5c4ae57 100644
--- a/drivers/net/ethernet/intel/ice/ice_tc_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.c
@@ -74,21 +74,13 @@ static enum ice_protocol_type ice_proto_type_from_ipv6(bool inner)
 	return inner ? ICE_IPV6_IL : ICE_IPV6_OFOS;
 }
 
-static enum ice_protocol_type
-ice_proto_type_from_l4_port(bool inner, u16 ip_proto)
+static enum ice_protocol_type ice_proto_type_from_l4_port(u16 ip_proto)
 {
-	if (inner) {
-		switch (ip_proto) {
-		case IPPROTO_UDP:
-			return ICE_UDP_ILOS;
-		}
-	} else {
-		switch (ip_proto) {
-		case IPPROTO_TCP:
-			return ICE_TCP_IL;
-		case IPPROTO_UDP:
-			return ICE_UDP_OF;
-		}
+	switch (ip_proto) {
+	case IPPROTO_TCP:
+		return ICE_TCP_IL;
+	case IPPROTO_UDP:
+		return ICE_UDP_ILOS;
 	}
 
 	return 0;
@@ -191,8 +183,9 @@ ice_tc_fill_tunnel_outer(u32 flags, struct ice_tc_flower_fltr *fltr,
 		i++;
 	}
 
-	if (flags & ICE_TC_FLWR_FIELD_ENC_DEST_L4_PORT) {
-		list[i].type = ice_proto_type_from_l4_port(false, hdr->l3_key.ip_proto);
+	if ((flags & ICE_TC_FLWR_FIELD_ENC_DEST_L4_PORT) &&
+	    hdr->l3_key.ip_proto == IPPROTO_UDP) {
+		list[i].type = ICE_UDP_OF;
 		list[i].h_u.l4_hdr.dst_port = hdr->l4_key.dst_port;
 		list[i].m_u.l4_hdr.dst_port = hdr->l4_mask.dst_port;
 		i++;
@@ -317,7 +310,7 @@ ice_tc_fill_rules(struct ice_hw *hw, u32 flags,
 		     ICE_TC_FLWR_FIELD_SRC_L4_PORT)) {
 		struct ice_tc_l4_hdr *l4_key, *l4_mask;
 
-		list[i].type = ice_proto_type_from_l4_port(inner, headers->l3_key.ip_proto);
+		list[i].type = ice_proto_type_from_l4_port(headers->l3_key.ip_proto);
 		l4_key = &headers->l4_key;
 		l4_mask = &headers->l4_mask;
 
@@ -802,7 +795,8 @@ ice_parse_tunnel_attr(struct net_device *dev, struct flow_rule *rule,
 		headers->l3_mask.ttl = match.mask->ttl;
 	}
 
-	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_PORTS)) {
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_PORTS) &&
+	    fltr->tunnel_type != TNL_VXLAN && fltr->tunnel_type != TNL_GENEVE) {
 		struct flow_match_ports match;
 
 		flow_rule_match_enc_ports(rule, &match);
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index bc3ba19dc88f..dccf09eefc75 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -419,7 +419,10 @@ void ice_clean_rx_ring(struct ice_rx_ring *rx_ring)
 	}
 
 rx_skip_free:
-	memset(rx_ring->rx_buf, 0, sizeof(*rx_ring->rx_buf) * rx_ring->count);
+	if (rx_ring->xsk_pool)
+		memset(rx_ring->xdp_buf, 0, array_size(rx_ring->count, sizeof(*rx_ring->xdp_buf)));
+	else
+		memset(rx_ring->rx_buf, 0, array_size(rx_ring->count, sizeof(*rx_ring->rx_buf)));
 
 	/* Zero out the descriptor ring */
 	size = ALIGN(rx_ring->count * sizeof(union ice_32byte_rx_desc),
@@ -446,8 +449,13 @@ void ice_free_rx_ring(struct ice_rx_ring *rx_ring)
 		if (xdp_rxq_info_is_reg(&rx_ring->xdp_rxq))
 			xdp_rxq_info_unreg(&rx_ring->xdp_rxq);
 	rx_ring->xdp_prog = NULL;
-	devm_kfree(rx_ring->dev, rx_ring->rx_buf);
-	rx_ring->rx_buf = NULL;
+	if (rx_ring->xsk_pool) {
+		kfree(rx_ring->xdp_buf);
+		rx_ring->xdp_buf = NULL;
+	} else {
+		kfree(rx_ring->rx_buf);
+		rx_ring->rx_buf = NULL;
+	}
 
 	if (rx_ring->desc) {
 		size = ALIGN(rx_ring->count * sizeof(union ice_32byte_rx_desc),
@@ -475,8 +483,7 @@ int ice_setup_rx_ring(struct ice_rx_ring *rx_ring)
 	/* warn if we are about to overwrite the pointer */
 	WARN_ON(rx_ring->rx_buf);
 	rx_ring->rx_buf =
-		devm_kcalloc(dev, sizeof(*rx_ring->rx_buf), rx_ring->count,
-			     GFP_KERNEL);
+		kcalloc(rx_ring->count, sizeof(*rx_ring->rx_buf), GFP_KERNEL);
 	if (!rx_ring->rx_buf)
 		return -ENOMEM;
 
@@ -505,7 +512,7 @@ int ice_setup_rx_ring(struct ice_rx_ring *rx_ring)
 	return 0;
 
 err:
-	devm_kfree(dev, rx_ring->rx_buf);
+	kfree(rx_ring->rx_buf);
 	rx_ring->rx_buf = NULL;
 	return -ENOMEM;
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h
index c56dd1749903..b7b3bd4816f0 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.h
@@ -24,7 +24,6 @@
 #define ICE_MAX_DATA_PER_TXD_ALIGNED \
 	(~(ICE_MAX_READ_REQ_SIZE - 1) & ICE_MAX_DATA_PER_TXD)
 
-#define ICE_RX_BUF_WRITE	16	/* Must be power of 2 */
 #define ICE_MAX_TXQ_PER_TXQG	128
 
 /* Attempt to maximize the headroom available for incoming frames. We use a 2K
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
index 217ff5e9a6f1..6427e7ec93de 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
@@ -1617,6 +1617,7 @@ bool ice_reset_all_vfs(struct ice_pf *pf, bool is_vflr)
 		ice_vc_set_default_allowlist(vf);
 
 		ice_vf_fdir_exit(vf);
+		ice_vf_fdir_init(vf);
 		/* clean VF control VSI when resetting VFs since it should be
 		 * setup only when VF creates its first FDIR rule.
 		 */
@@ -1747,6 +1748,7 @@ bool ice_reset_vf(struct ice_vf *vf, bool is_vflr)
 	}
 
 	ice_vf_fdir_exit(vf);
+	ice_vf_fdir_init(vf);
 	/* clean VF control VSI when resetting VF since it should be setup
 	 * only when VF creates its first FDIR rule.
 	 */
@@ -2021,6 +2023,10 @@ static int ice_ena_vfs(struct ice_pf *pf, u16 num_vfs)
 	if (ret)
 		goto err_unroll_sriov;
 
+	/* rearm global interrupts */
+	if (test_and_clear_bit(ICE_OICR_INTR_DIS, pf->state))
+		ice_irq_dynamic_ena(hw, NULL, NULL);
+
 	return 0;
 
 err_unroll_sriov:
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index ff55cb415b11..c895351b25e0 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -12,6 +12,11 @@
 #include "ice_txrx_lib.h"
 #include "ice_lib.h"
 
+static struct xdp_buff **ice_xdp_buf(struct ice_rx_ring *rx_ring, u32 idx)
+{
+	return &rx_ring->xdp_buf[idx];
+}
+
 /**
  * ice_qp_reset_stats - Resets all stats for rings of given index
  * @vsi: VSI that contains rings of interest
@@ -372,7 +377,7 @@ bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
 	dma_addr_t dma;
 
 	rx_desc = ICE_RX_DESC(rx_ring, ntu);
-	xdp = &rx_ring->xdp_buf[ntu];
+	xdp = ice_xdp_buf(rx_ring, ntu);
 
 	nb_buffs = min_t(u16, count, rx_ring->count - ntu);
 	nb_buffs = xsk_buff_alloc_batch(rx_ring->xsk_pool, xdp, nb_buffs);
@@ -383,20 +388,16 @@ bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
 	while (i--) {
 		dma = xsk_buff_xdp_get_dma(*xdp);
 		rx_desc->read.pkt_addr = cpu_to_le64(dma);
+		rx_desc->wb.status_error0 = 0;
 
 		rx_desc++;
 		xdp++;
 	}
 
 	ntu += nb_buffs;
-	if (ntu == rx_ring->count) {
-		rx_desc = ICE_RX_DESC(rx_ring, 0);
-		xdp = rx_ring->xdp_buf;
+	if (ntu == rx_ring->count)
 		ntu = 0;
-	}
 
-	/* clear the status bits for the next_to_use descriptor */
-	rx_desc->wb.status_error0 = 0;
 	ice_release_rx_desc(rx_ring, ntu);
 
 	return count == nb_buffs;
@@ -418,19 +419,18 @@ static void ice_bump_ntc(struct ice_rx_ring *rx_ring)
 /**
  * ice_construct_skb_zc - Create an sk_buff from zero-copy buffer
  * @rx_ring: Rx ring
- * @xdp_arr: Pointer to the SW ring of xdp_buff pointers
+ * @xdp: Pointer to XDP buffer
  *
  * This function allocates a new skb from a zero-copy Rx buffer.
  *
  * Returns the skb on success, NULL on failure.
  */
 static struct sk_buff *
-ice_construct_skb_zc(struct ice_rx_ring *rx_ring, struct xdp_buff **xdp_arr)
+ice_construct_skb_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp)
 {
-	struct xdp_buff *xdp = *xdp_arr;
+	unsigned int datasize_hard = xdp->data_end - xdp->data_hard_start;
 	unsigned int metasize = xdp->data - xdp->data_meta;
 	unsigned int datasize = xdp->data_end - xdp->data;
-	unsigned int datasize_hard = xdp->data_end - xdp->data_hard_start;
 	struct sk_buff *skb;
 
 	skb = __napi_alloc_skb(&rx_ring->q_vector->napi, datasize_hard,
@@ -444,7 +444,6 @@ ice_construct_skb_zc(struct ice_rx_ring *rx_ring, struct xdp_buff **xdp_arr)
 		skb_metadata_set(skb, metasize);
 
 	xsk_buff_free(xdp);
-	*xdp_arr = NULL;
 	return skb;
 }
 
@@ -506,7 +505,6 @@ out_failure:
 int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
 {
 	unsigned int total_rx_bytes = 0, total_rx_packets = 0;
-	u16 cleaned_count = ICE_DESC_UNUSED(rx_ring);
 	struct ice_tx_ring *xdp_ring;
 	unsigned int xdp_xmit = 0;
 	struct bpf_prog *xdp_prog;
@@ -521,7 +519,7 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
 	while (likely(total_rx_packets < (unsigned int)budget)) {
 		union ice_32b_rx_flex_desc *rx_desc;
 		unsigned int size, xdp_res = 0;
-		struct xdp_buff **xdp;
+		struct xdp_buff *xdp;
 		struct sk_buff *skb;
 		u16 stat_err_bits;
 		u16 vlan_tag = 0;
@@ -539,31 +537,35 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
 		 */
 		dma_rmb();
 
+		xdp = *ice_xdp_buf(rx_ring, rx_ring->next_to_clean);
+
 		size = le16_to_cpu(rx_desc->wb.pkt_len) &
 				   ICE_RX_FLX_DESC_PKT_LEN_M;
-		if (!size)
-			break;
+		if (!size) {
+			xdp->data = NULL;
+			xdp->data_end = NULL;
+			xdp->data_hard_start = NULL;
+			xdp->data_meta = NULL;
+			goto construct_skb;
+		}
 
-		xdp = &rx_ring->xdp_buf[rx_ring->next_to_clean];
-		xsk_buff_set_size(*xdp, size);
-		xsk_buff_dma_sync_for_cpu(*xdp, rx_ring->xsk_pool);
+		xsk_buff_set_size(xdp, size);
+		xsk_buff_dma_sync_for_cpu(xdp, rx_ring->xsk_pool);
 
-		xdp_res = ice_run_xdp_zc(rx_ring, *xdp, xdp_prog, xdp_ring);
+		xdp_res = ice_run_xdp_zc(rx_ring, xdp, xdp_prog, xdp_ring);
 		if (xdp_res) {
 			if (xdp_res & (ICE_XDP_TX | ICE_XDP_REDIR))
 				xdp_xmit |= xdp_res;
 			else
-				xsk_buff_free(*xdp);
+				xsk_buff_free(xdp);
 
-			*xdp = NULL;
 			total_rx_bytes += size;
 			total_rx_packets++;
-			cleaned_count++;
 
 			ice_bump_ntc(rx_ring);
 			continue;
 		}
-
+construct_skb:
 		/* XDP_PASS path */
 		skb = ice_construct_skb_zc(rx_ring, xdp);
 		if (!skb) {
@@ -571,7 +573,6 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
 			break;
 		}
 
-		cleaned_count++;
 		ice_bump_ntc(rx_ring);
 
 		if (eth_skb_pad(skb)) {
@@ -593,8 +594,7 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
 		ice_receive_skb(rx_ring, skb, vlan_tag);
 	}
 
-	if (cleaned_count >= ICE_RX_BUF_WRITE)
-		failure = !ice_alloc_rx_bufs_zc(rx_ring, cleaned_count);
+	failure = !ice_alloc_rx_bufs_zc(rx_ring, ICE_DESC_UNUSED(rx_ring));
 
 	ice_finalize_xdp_rx(xdp_ring, xdp_xmit);
 	ice_update_rx_ring_stats(rx_ring, total_rx_packets, total_rx_bytes);
@@ -810,15 +810,14 @@ bool ice_xsk_any_rx_ring_ena(struct ice_vsi *vsi)
  */
 void ice_xsk_clean_rx_ring(struct ice_rx_ring *rx_ring)
 {
-	u16 i;
-
-	for (i = 0; i < rx_ring->count; i++) {
-		struct xdp_buff **xdp = &rx_ring->xdp_buf[i];
+	u16 count_mask = rx_ring->count - 1;
+	u16 ntc = rx_ring->next_to_clean;
+	u16 ntu = rx_ring->next_to_use;
 
-		if (!xdp)
-			continue;
+	for ( ; ntc != ntu; ntc = (ntc + 1) & count_mask) {
+		struct xdp_buff *xdp = *ice_xdp_buf(rx_ring, ntc);
 
-		*xdp = NULL;
+		xsk_buff_free(xdp);
 	}
 }
 
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 836be0d3b291..446894dde182 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -7648,6 +7648,20 @@ static int igb_set_vf_mac_filter(struct igb_adapter *adapter, const int vf,
 	struct vf_mac_filter *entry = NULL;
 	int ret = 0;
 
+	if ((vf_data->flags & IGB_VF_FLAG_PF_SET_MAC) &&
+	    !vf_data->trusted) {
+		dev_warn(&pdev->dev,
+			 "VF %d requested MAC filter but is administratively denied\n",
+			  vf);
+		return -EINVAL;
+	}
+	if (!is_valid_ether_addr(addr)) {
+		dev_warn(&pdev->dev,
+			 "VF %d attempted to set invalid MAC filter\n",
+			  vf);
+		return -EINVAL;
+	}
+
 	switch (info) {
 	case E1000_VF_MAC_FILTER_CLR:
 		/* remove all unicast MAC filters related to the current VF */
@@ -7661,20 +7675,6 @@ static int igb_set_vf_mac_filter(struct igb_adapter *adapter, const int vf,
 		}
 		break;
 	case E1000_VF_MAC_FILTER_ADD:
-		if ((vf_data->flags & IGB_VF_FLAG_PF_SET_MAC) &&
-		    !vf_data->trusted) {
-			dev_warn(&pdev->dev,
-				 "VF %d requested MAC filter but is administratively denied\n",
-				 vf);
-			return -EINVAL;
-		}
-		if (!is_valid_ether_addr(addr)) {
-			dev_warn(&pdev->dev,
-				 "VF %d attempted to set invalid MAC filter\n",
-				 vf);
-			return -EINVAL;
-		}
-
 		/* try to find empty slot in the list */
 		list_for_each(pos, &adapter->vf_macs.l) {
 			entry = list_entry(pos, struct vf_mac_filter, l);
@@ -8026,7 +8026,7 @@ static int igb_poll(struct napi_struct *napi, int budget)
 	if (likely(napi_complete_done(napi, work_done)))
 		igb_ring_irq_enable(q_vector);
 
-	return min(work_done, budget - 1);
+	return work_done;
 }
 
 /**
@@ -9254,7 +9254,7 @@ static int __maybe_unused igb_suspend(struct device *dev)
 	return __igb_shutdown(to_pci_dev(dev), NULL, 0);
 }
 
-static int __maybe_unused igb_resume(struct device *dev)
+static int __maybe_unused __igb_resume(struct device *dev, bool rpm)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct net_device *netdev = pci_get_drvdata(pdev);
@@ -9297,17 +9297,24 @@ static int __maybe_unused igb_resume(struct device *dev)
 
 	wr32(E1000_WUS, ~0);
 
-	rtnl_lock();
+	if (!rpm)
+		rtnl_lock();
 	if (!err && netif_running(netdev))
 		err = __igb_open(netdev, true);
 
 	if (!err)
 		netif_device_attach(netdev);
-	rtnl_unlock();
+	if (!rpm)
+		rtnl_unlock();
 
 	return err;
 }
 
+static int __maybe_unused igb_resume(struct device *dev)
+{
+	return __igb_resume(dev, false);
+}
+
 static int __maybe_unused igb_runtime_idle(struct device *dev)
 {
 	struct net_device *netdev = dev_get_drvdata(dev);
@@ -9326,7 +9333,7 @@ static int __maybe_unused igb_runtime_suspend(struct device *dev)
 
 static int __maybe_unused igb_runtime_resume(struct device *dev)
 {
-	return igb_resume(dev);
+	return __igb_resume(dev, true);
 }
 
 static void igb_shutdown(struct pci_dev *pdev)
@@ -9442,7 +9449,7 @@ static pci_ers_result_t igb_io_error_detected(struct pci_dev *pdev,
  *  @pdev: Pointer to PCI device
  *
  *  Restart the card from scratch, as if from a cold-boot. Implementation
- *  resembles the first-half of the igb_resume routine.
+ *  resembles the first-half of the __igb_resume routine.
  **/
 static pci_ers_result_t igb_io_slot_reset(struct pci_dev *pdev)
 {
@@ -9482,7 +9489,7 @@ static pci_ers_result_t igb_io_slot_reset(struct pci_dev *pdev)
  *
  *  This callback is called when the error recovery driver tells us that
  *  its OK to resume normal operation. Implementation resembles the
- *  second-half of the igb_resume routine.
+ *  second-half of the __igb_resume routine.
  */
 static void igb_io_resume(struct pci_dev *pdev)
 {
diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c
index 74ccd622251a..4d988da68394 100644
--- a/drivers/net/ethernet/intel/igbvf/netdev.c
+++ b/drivers/net/ethernet/intel/igbvf/netdev.c
@@ -2859,6 +2859,7 @@ static int igbvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	return 0;
 
 err_hw_init:
+	netif_napi_del(&adapter->rx_ring->napi);
 	kfree(adapter->tx_ring);
 	kfree(adapter->rx_ring);
 err_sw_init:
diff --git a/drivers/net/ethernet/intel/igc/igc_i225.c b/drivers/net/ethernet/intel/igc/igc_i225.c
index b2ef9fde97b3..b6807e16eea9 100644
--- a/drivers/net/ethernet/intel/igc/igc_i225.c
+++ b/drivers/net/ethernet/intel/igc/igc_i225.c
@@ -636,7 +636,7 @@ s32 igc_set_ltr_i225(struct igc_hw *hw, bool link)
 		ltrv = rd32(IGC_LTRMAXV);
 		if (ltr_max != (ltrv & IGC_LTRMAXV_LTRV_MASK)) {
 			ltrv = IGC_LTRMAXV_LSNP_REQ | ltr_max |
-			       (scale_min << IGC_LTRMAXV_SCALE_SHIFT);
+			       (scale_max << IGC_LTRMAXV_SCALE_SHIFT);
 			wr32(IGC_LTRMAXV, ltrv);
 		}
 	}
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 8e448288ee26..d28a80a00953 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -5467,6 +5467,9 @@ static irqreturn_t igc_intr_msi(int irq, void *data)
 			mod_timer(&adapter->watchdog_timer, jiffies + 1);
 	}
 
+	if (icr & IGC_ICR_TS)
+		igc_tsync_interrupt(adapter);
+
 	napi_schedule(&q_vector->napi);
 
 	return IRQ_HANDLED;
@@ -5510,6 +5513,9 @@ static irqreturn_t igc_intr(int irq, void *data)
 			mod_timer(&adapter->watchdog_timer, jiffies + 1);
 	}
 
+	if (icr & IGC_ICR_TS)
+		igc_tsync_interrupt(adapter);
+
 	napi_schedule(&q_vector->napi);
 
 	return IRQ_HANDLED;
diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c
index 30568e3544cd..4f9245aa79a1 100644
--- a/drivers/net/ethernet/intel/igc/igc_ptp.c
+++ b/drivers/net/ethernet/intel/igc/igc_ptp.c
@@ -768,7 +768,20 @@ int igc_ptp_get_ts_config(struct net_device *netdev, struct ifreq *ifr)
  */
 static bool igc_is_crosststamp_supported(struct igc_adapter *adapter)
 {
-	return IS_ENABLED(CONFIG_X86_TSC) ? pcie_ptm_enabled(adapter->pdev) : false;
+	if (!IS_ENABLED(CONFIG_X86_TSC))
+		return false;
+
+	/* FIXME: it was noticed that enabling support for PCIe PTM in
+	 * some i225-V models could cause lockups when bringing the
+	 * interface up/down. There should be no downsides to
+	 * disabling crosstimestamping support for i225-V, as it
+	 * doesn't have any PTP support. That way we gain some time
+	 * while root causing the issue.
+	 */
+	if (adapter->pdev->device == IGC_DEV_ID_I225_V)
+		return false;
+
+	return pcie_ptm_enabled(adapter->pdev);
 }
 
 static struct system_counterval_t igc_device_tstamp_to_system(u64 tstamp)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 0f9f022260d7..45e2ec4d264d 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -5531,6 +5531,10 @@ static int ixgbe_non_sfp_link_config(struct ixgbe_hw *hw)
 	if (!speed && hw->mac.ops.get_link_capabilities) {
 		ret = hw->mac.ops.get_link_capabilities(hw, &speed,
 							&autoneg);
+		/* remove NBASE-T speeds from default autonegotiation
+		 * to accommodate broken network switches in the field
+		 * which cannot cope with advertised NBASE-T speeds
+		 */
 		speed &= ~(IXGBE_LINK_SPEED_5GB_FULL |
 			   IXGBE_LINK_SPEED_2_5GB_FULL);
 	}
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
index 9724ffb16518..e4b50c7781ff 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c
@@ -3405,6 +3405,9 @@ static s32 ixgbe_reset_hw_X550em(struct ixgbe_hw *hw)
 	/* flush pending Tx transactions */
 	ixgbe_clear_tx_pending(hw);
 
+	/* set MDIO speed before talking to the PHY in case it's the 1st time */
+	ixgbe_set_mdio_speed(hw);
+
 	/* PHY ops must be identified and initialized prior to reset */
 	status = hw->phy.ops.init(hw);
 	if (status == IXGBE_ERR_SFP_NOT_SUPPORTED ||
diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c
index 6433c909c6b2..072391c494ce 100644
--- a/drivers/net/ethernet/lantiq_etop.c
+++ b/drivers/net/ethernet/lantiq_etop.c
@@ -25,6 +25,7 @@
 #include <linux/io.h>
 #include <linux/dma-mapping.h>
 #include <linux/module.h>
+#include <linux/property.h>
 
 #include <asm/checksum.h>
 
@@ -239,6 +240,7 @@ ltq_etop_hw_init(struct net_device *dev)
 {
 	struct ltq_etop_priv *priv = netdev_priv(dev);
 	int i;
+	int err;
 
 	ltq_pmu_enable(PMU_PPE);
 
@@ -273,7 +275,13 @@ ltq_etop_hw_init(struct net_device *dev)
 
 		if (IS_TX(i)) {
 			ltq_dma_alloc_tx(&ch->dma);
-			request_irq(irq, ltq_etop_dma_irq, 0, "etop_tx", priv);
+			err = request_irq(irq, ltq_etop_dma_irq, 0, "etop_tx", priv);
+			if (err) {
+				netdev_err(dev,
+					   "Unable to get Tx DMA IRQ %d\n",
+					   irq);
+				return err;
+			}
 		} else if (IS_RX(i)) {
 			ltq_dma_alloc_rx(&ch->dma);
 			for (ch->dma.desc = 0; ch->dma.desc < LTQ_DESC_NUM;
@@ -281,7 +289,13 @@ ltq_etop_hw_init(struct net_device *dev)
 				if (ltq_etop_alloc_skb(ch))
 					return -ENOMEM;
 			ch->dma.desc = 0;
-			request_irq(irq, ltq_etop_dma_irq, 0, "etop_rx", priv);
+			err = request_irq(irq, ltq_etop_dma_irq, 0, "etop_rx", priv);
+			if (err) {
+				netdev_err(dev,
+					   "Unable to get Rx DMA IRQ %d\n",
+					   irq);
+				return err;
+			}
 		}
 		ch->dma.irq = irq;
 	}
@@ -726,7 +740,7 @@ static struct platform_driver ltq_mii_driver = {
 	},
 };
 
-int __init
+static int __init
 init_ltq_etop(void)
 {
 	int ret = platform_driver_probe(&ltq_mii_driver, ltq_etop_probe);
diff --git a/drivers/net/ethernet/lantiq_xrx200.c b/drivers/net/ethernet/lantiq_xrx200.c
index 0da09ea81980..80bfaf2fec92 100644
--- a/drivers/net/ethernet/lantiq_xrx200.c
+++ b/drivers/net/ethernet/lantiq_xrx200.c
@@ -71,6 +71,8 @@ struct xrx200_priv {
 	struct xrx200_chan chan_tx;
 	struct xrx200_chan chan_rx;
 
+	u16 rx_buf_size;
+
 	struct net_device *net_dev;
 	struct device *dev;
 
@@ -97,6 +99,16 @@ static void xrx200_pmac_mask(struct xrx200_priv *priv, u32 clear, u32 set,
 	xrx200_pmac_w32(priv, val, offset);
 }
 
+static int xrx200_max_frame_len(int mtu)
+{
+	return VLAN_ETH_HLEN + mtu;
+}
+
+static int xrx200_buffer_size(int mtu)
+{
+	return round_up(xrx200_max_frame_len(mtu), 4 * XRX200_DMA_BURST_LEN);
+}
+
 /* drop all the packets from the DMA ring */
 static void xrx200_flush_dma(struct xrx200_chan *ch)
 {
@@ -109,8 +121,7 @@ static void xrx200_flush_dma(struct xrx200_chan *ch)
 			break;
 
 		desc->ctl = LTQ_DMA_OWN | LTQ_DMA_RX_OFFSET(NET_IP_ALIGN) |
-			    (ch->priv->net_dev->mtu + VLAN_ETH_HLEN +
-			     ETH_FCS_LEN);
+			    ch->priv->rx_buf_size;
 		ch->dma.desc++;
 		ch->dma.desc %= LTQ_DESC_NUM;
 	}
@@ -158,21 +169,21 @@ static int xrx200_close(struct net_device *net_dev)
 
 static int xrx200_alloc_skb(struct xrx200_chan *ch)
 {
-	int len = ch->priv->net_dev->mtu + VLAN_ETH_HLEN + ETH_FCS_LEN;
 	struct sk_buff *skb = ch->skb[ch->dma.desc];
+	struct xrx200_priv *priv = ch->priv;
 	dma_addr_t mapping;
 	int ret = 0;
 
-	ch->skb[ch->dma.desc] = netdev_alloc_skb_ip_align(ch->priv->net_dev,
-							  len);
+	ch->skb[ch->dma.desc] = netdev_alloc_skb_ip_align(priv->net_dev,
+							  priv->rx_buf_size);
 	if (!ch->skb[ch->dma.desc]) {
 		ret = -ENOMEM;
 		goto skip;
 	}
 
-	mapping = dma_map_single(ch->priv->dev, ch->skb[ch->dma.desc]->data,
-				 len, DMA_FROM_DEVICE);
-	if (unlikely(dma_mapping_error(ch->priv->dev, mapping))) {
+	mapping = dma_map_single(priv->dev, ch->skb[ch->dma.desc]->data,
+				 priv->rx_buf_size, DMA_FROM_DEVICE);
+	if (unlikely(dma_mapping_error(priv->dev, mapping))) {
 		dev_kfree_skb_any(ch->skb[ch->dma.desc]);
 		ch->skb[ch->dma.desc] = skb;
 		ret = -ENOMEM;
@@ -184,7 +195,7 @@ static int xrx200_alloc_skb(struct xrx200_chan *ch)
 	wmb();
 skip:
 	ch->dma.desc_base[ch->dma.desc].ctl =
-		LTQ_DMA_OWN | LTQ_DMA_RX_OFFSET(NET_IP_ALIGN) | len;
+		LTQ_DMA_OWN | LTQ_DMA_RX_OFFSET(NET_IP_ALIGN) | priv->rx_buf_size;
 
 	return ret;
 }
@@ -213,7 +224,7 @@ static int xrx200_hw_receive(struct xrx200_chan *ch)
 	skb->protocol = eth_type_trans(skb, net_dev);
 	netif_receive_skb(skb);
 	net_dev->stats.rx_packets++;
-	net_dev->stats.rx_bytes += len - ETH_FCS_LEN;
+	net_dev->stats.rx_bytes += len;
 
 	return 0;
 }
@@ -356,6 +367,7 @@ xrx200_change_mtu(struct net_device *net_dev, int new_mtu)
 	int ret = 0;
 
 	net_dev->mtu = new_mtu;
+	priv->rx_buf_size = xrx200_buffer_size(new_mtu);
 
 	if (new_mtu <= old_mtu)
 		return ret;
@@ -375,6 +387,7 @@ xrx200_change_mtu(struct net_device *net_dev, int new_mtu)
 		ret = xrx200_alloc_skb(ch_rx);
 		if (ret) {
 			net_dev->mtu = old_mtu;
+			priv->rx_buf_size = xrx200_buffer_size(old_mtu);
 			break;
 		}
 		dev_kfree_skb_any(skb);
@@ -505,7 +518,8 @@ static int xrx200_probe(struct platform_device *pdev)
 	net_dev->netdev_ops = &xrx200_netdev_ops;
 	SET_NETDEV_DEV(net_dev, dev);
 	net_dev->min_mtu = ETH_ZLEN;
-	net_dev->max_mtu = XRX200_DMA_DATA_LEN - VLAN_ETH_HLEN - ETH_FCS_LEN;
+	net_dev->max_mtu = XRX200_DMA_DATA_LEN - xrx200_max_frame_len(0);
+	priv->rx_buf_size = xrx200_buffer_size(ETH_DATA_LEN);
 
 	/* load the memory ranges */
 	priv->pmac_reg = devm_platform_get_and_ioremap_resource(pdev, 0, NULL);
diff --git a/drivers/net/ethernet/marvell/mvmdio.c b/drivers/net/ethernet/marvell/mvmdio.c
index 62a97c46fba0..ef878973b859 100644
--- a/drivers/net/ethernet/marvell/mvmdio.c
+++ b/drivers/net/ethernet/marvell/mvmdio.c
@@ -429,12 +429,14 @@ static const struct of_device_id orion_mdio_match[] = {
 };
 MODULE_DEVICE_TABLE(of, orion_mdio_match);
 
+#ifdef CONFIG_ACPI
 static const struct acpi_device_id orion_mdio_acpi_match[] = {
 	{ "MRVL0100", BUS_TYPE_SMI },
 	{ "MRVL0101", BUS_TYPE_XSMI },
 	{ },
 };
 MODULE_DEVICE_TABLE(acpi, orion_mdio_acpi_match);
+#endif
 
 static struct platform_driver orion_mdio_driver = {
 	.probe = orion_mdio_probe,
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index 2b18d89d9756..6da8a595026b 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -2960,11 +2960,11 @@ static int mvpp2_rxq_init(struct mvpp2_port *port,
 	mvpp2_rxq_status_update(port, rxq->id, 0, rxq->size);
 
 	if (priv->percpu_pools) {
-		err = xdp_rxq_info_reg(&rxq->xdp_rxq_short, port->dev, rxq->id, 0);
+		err = xdp_rxq_info_reg(&rxq->xdp_rxq_short, port->dev, rxq->logic_rxq, 0);
 		if (err < 0)
 			goto err_free_dma;
 
-		err = xdp_rxq_info_reg(&rxq->xdp_rxq_long, port->dev, rxq->id, 0);
+		err = xdp_rxq_info_reg(&rxq->xdp_rxq_long, port->dev, rxq->logic_rxq, 0);
 		if (err < 0)
 			goto err_unregister_rxq_short;
 
@@ -5017,11 +5017,13 @@ static int mvpp2_change_mtu(struct net_device *dev, int mtu)
 		mtu = ALIGN(MVPP2_RX_PKT_SIZE(mtu), 8);
 	}
 
+	if (port->xdp_prog && mtu > MVPP2_MAX_RX_BUF_SIZE) {
+		netdev_err(dev, "Illegal MTU value %d (> %d) for XDP mode\n",
+			   mtu, (int)MVPP2_MAX_RX_BUF_SIZE);
+		return -EINVAL;
+	}
+
 	if (MVPP2_RX_PKT_SIZE(mtu) > MVPP2_BM_LONG_PKT_SIZE) {
-		if (port->xdp_prog) {
-			netdev_err(dev, "Jumbo frames are not supported with XDP\n");
-			return -EINVAL;
-		}
 		if (priv->percpu_pools) {
 			netdev_warn(dev, "mtu %d too high, switching to shared buffers", mtu);
 			mvpp2_bm_switch_buffers(priv, false);
@@ -5307,8 +5309,8 @@ static int mvpp2_xdp_setup(struct mvpp2_port *port, struct netdev_bpf *bpf)
 	bool running = netif_running(port->dev);
 	bool reset = !prog != !port->xdp_prog;
 
-	if (port->dev->mtu > ETH_DATA_LEN) {
-		NL_SET_ERR_MSG_MOD(bpf->extack, "XDP is not supported with jumbo frames enabled");
+	if (port->dev->mtu > MVPP2_MAX_RX_BUF_SIZE) {
+		NL_SET_ERR_MSG_MOD(bpf->extack, "MTU too large for XDP");
 		return -EOPNOTSUPP;
 	}
 
@@ -7456,7 +7458,7 @@ static int mvpp2_probe(struct platform_device *pdev)
 
 	shared = num_present_cpus() - priv->nthreads;
 	if (shared > 0)
-		bitmap_fill(&priv->lock_map,
+		bitmap_set(&priv->lock_map, 0,
 			    min_t(int, shared, MVPP2_MAX_THREADS));
 
 	for (i = 0; i < MVPP2_MAX_THREADS; i++) {
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
index cb56e171ddd4..3ca6b942ebe2 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
@@ -2341,7 +2341,7 @@ static int rvu_mbox_init(struct rvu *rvu, struct mbox_wq_info *mw,
 			goto free_regions;
 		break;
 	default:
-		return err;
+		goto free_regions;
 	}
 
 	mw->mbox_wq = alloc_workqueue(name,
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
index c7fd466a0efd..a09a507369ac 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
@@ -236,10 +236,11 @@ static ssize_t rvu_dbg_lmtst_map_table_display(struct file *filp,
 	u64 lmt_addr, val, tbl_base;
 	int pf, vf, num_vfs, hw_vfs;
 	void __iomem *lmt_map_base;
-	int index = 0, off = 0;
-	int bytes_not_copied;
 	int buf_size = 10240;
+	size_t off = 0;
+	int index = 0;
 	char *buf;
+	int ret;
 
 	/* don't allow partial reads */
 	if (*ppos != 0)
@@ -303,15 +304,17 @@ static ssize_t rvu_dbg_lmtst_map_table_display(struct file *filp,
 	}
 	off +=	scnprintf(&buf[off], buf_size - 1 - off, "\n");
 
-	bytes_not_copied = copy_to_user(buffer, buf, off);
+	ret = min(off, count);
+	if (copy_to_user(buffer, buf, ret))
+		ret = -EFAULT;
 	kfree(buf);
 
 	iounmap(lmt_map_base);
-	if (bytes_not_copied)
-		return -EFAULT;
+	if (ret < 0)
+		return ret;
 
-	*ppos = off;
-	return off;
+	*ppos = ret;
+	return ret;
 }
 
 RVU_DEBUG_FOPS(lmtst_map_table, lmtst_map_table_display, NULL);
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c
index 0ef68fdd1f26..61c20907315f 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c
@@ -5,6 +5,8 @@
  *
  */
 
+#include <linux/module.h>
+
 #include "otx2_common.h"
 #include "otx2_ptp.h"
 
diff --git a/drivers/net/ethernet/marvell/prestera/prestera_main.c b/drivers/net/ethernet/marvell/prestera/prestera_main.c
index 4369a3ffad45..c687dc9aa973 100644
--- a/drivers/net/ethernet/marvell/prestera/prestera_main.c
+++ b/drivers/net/ethernet/marvell/prestera/prestera_main.c
@@ -54,12 +54,14 @@ int prestera_port_pvid_set(struct prestera_port *port, u16 vid)
 struct prestera_port *prestera_port_find_by_hwid(struct prestera_switch *sw,
 						 u32 dev_id, u32 hw_id)
 {
-	struct prestera_port *port = NULL;
+	struct prestera_port *port = NULL, *tmp;
 
 	read_lock(&sw->port_list_lock);
-	list_for_each_entry(port, &sw->port_list, list) {
-		if (port->dev_id == dev_id && port->hw_id == hw_id)
+	list_for_each_entry(tmp, &sw->port_list, list) {
+		if (tmp->dev_id == dev_id && tmp->hw_id == hw_id) {
+			port = tmp;
 			break;
+		}
 	}
 	read_unlock(&sw->port_list_lock);
 
@@ -68,12 +70,14 @@ struct prestera_port *prestera_port_find_by_hwid(struct prestera_switch *sw,
 
 struct prestera_port *prestera_find_port(struct prestera_switch *sw, u32 id)
 {
-	struct prestera_port *port = NULL;
+	struct prestera_port *port = NULL, *tmp;
 
 	read_lock(&sw->port_list_lock);
-	list_for_each_entry(port, &sw->port_list, list) {
-		if (port->id == id)
+	list_for_each_entry(tmp, &sw->port_list, list) {
+		if (tmp->id == id) {
+			port = tmp;
 			break;
+		}
 	}
 	read_unlock(&sw->port_list_lock);
 
@@ -764,23 +768,27 @@ static int prestera_netdev_port_event(struct net_device *lower,
 				      struct net_device *dev,
 				      unsigned long event, void *ptr)
 {
-	struct netdev_notifier_changeupper_info *info = ptr;
+	struct netdev_notifier_info *info = ptr;
+	struct netdev_notifier_changeupper_info *cu_info;
 	struct prestera_port *port = netdev_priv(dev);
 	struct netlink_ext_ack *extack;
 	struct net_device *upper;
 
-	extack = netdev_notifier_info_to_extack(&info->info);
-	upper = info->upper_dev;
+	extack = netdev_notifier_info_to_extack(info);
+	cu_info = container_of(info,
+			       struct netdev_notifier_changeupper_info,
+			       info);
 
 	switch (event) {
 	case NETDEV_PRECHANGEUPPER:
+		upper = cu_info->upper_dev;
 		if (!netif_is_bridge_master(upper) &&
 		    !netif_is_lag_master(upper)) {
 			NL_SET_ERR_MSG_MOD(extack, "Unknown upper device type");
 			return -EINVAL;
 		}
 
-		if (!info->linking)
+		if (!cu_info->linking)
 			break;
 
 		if (netdev_has_any_upper_dev(upper)) {
@@ -789,7 +797,7 @@ static int prestera_netdev_port_event(struct net_device *lower,
 		}
 
 		if (netif_is_lag_master(upper) &&
-		    !prestera_lag_master_check(upper, info->upper_info, extack))
+		    !prestera_lag_master_check(upper, cu_info->upper_info, extack))
 			return -EOPNOTSUPP;
 		if (netif_is_lag_master(upper) && vlan_uses_dev(dev)) {
 			NL_SET_ERR_MSG_MOD(extack,
@@ -805,14 +813,15 @@ static int prestera_netdev_port_event(struct net_device *lower,
 		break;
 
 	case NETDEV_CHANGEUPPER:
+		upper = cu_info->upper_dev;
 		if (netif_is_bridge_master(upper)) {
-			if (info->linking)
+			if (cu_info->linking)
 				return prestera_bridge_port_join(upper, port,
 								 extack);
 			else
 				prestera_bridge_port_leave(upper, port);
 		} else if (netif_is_lag_master(upper)) {
-			if (info->linking)
+			if (cu_info->linking)
 				return prestera_lag_port_add(port, upper);
 			else
 				prestera_lag_port_del(port);
diff --git a/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c b/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c
index 3ce6ccd0f539..b4599fe4ca8d 100644
--- a/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c
+++ b/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c
@@ -497,8 +497,8 @@ int prestera_bridge_port_join(struct net_device *br_dev,
 
 	br_port = prestera_bridge_port_add(bridge, port->dev);
 	if (IS_ERR(br_port)) {
-		err = PTR_ERR(br_port);
-		goto err_brport_create;
+		prestera_bridge_put(bridge);
+		return PTR_ERR(br_port);
 	}
 
 	err = switchdev_bridge_port_offload(br_port->dev, port->dev, NULL,
@@ -519,8 +519,6 @@ err_port_join:
 	switchdev_bridge_port_unoffload(br_port->dev, NULL, NULL, NULL);
 err_switchdev_offload:
 	prestera_bridge_port_put(br_port);
-err_brport_create:
-	prestera_bridge_put(bridge);
 	return err;
 }
 
@@ -1124,7 +1122,7 @@ static int prestera_switchdev_blk_event(struct notifier_block *unused,
 						     prestera_port_obj_attr_set);
 		break;
 	default:
-		err = -EOPNOTSUPP;
+		return NOTIFY_DONE;
 	}
 
 	return notifier_from_errno(err);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index 066d79e4ecfc..10238bedd694 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -670,7 +670,7 @@ void __init mlx4_en_init_ptys2ethtool_map(void)
 	MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_1000BASE_T, SPEED_1000,
 				       ETHTOOL_LINK_MODE_1000baseT_Full_BIT);
 	MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_1000BASE_CX_SGMII, SPEED_1000,
-				       ETHTOOL_LINK_MODE_1000baseKX_Full_BIT);
+				       ETHTOOL_LINK_MODE_1000baseX_Full_BIT);
 	MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_1000BASE_KX, SPEED_1000,
 				       ETHTOOL_LINK_MODE_1000baseKX_Full_BIT);
 	MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_10GBASE_T, SPEED_10000,
@@ -682,9 +682,9 @@ void __init mlx4_en_init_ptys2ethtool_map(void)
 	MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_10GBASE_KR, SPEED_10000,
 				       ETHTOOL_LINK_MODE_10000baseKR_Full_BIT);
 	MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_10GBASE_CR, SPEED_10000,
-				       ETHTOOL_LINK_MODE_10000baseKR_Full_BIT);
+				       ETHTOOL_LINK_MODE_10000baseCR_Full_BIT);
 	MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_10GBASE_SR, SPEED_10000,
-				       ETHTOOL_LINK_MODE_10000baseKR_Full_BIT);
+				       ETHTOOL_LINK_MODE_10000baseSR_Full_BIT);
 	MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_20GBASE_KR2, SPEED_20000,
 				       ETHTOOL_LINK_MODE_20000baseMLD2_Full_BIT,
 				       ETHTOOL_LINK_MODE_20000baseKR2_Full_BIT);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 3f6d5c384637..f1c10f2bda78 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -2286,9 +2286,14 @@ int mlx4_en_try_alloc_resources(struct mlx4_en_priv *priv,
 				bool carry_xdp_prog)
 {
 	struct bpf_prog *xdp_prog;
-	int i, t;
+	int i, t, ret;
 
-	mlx4_en_copy_priv(tmp, priv, prof);
+	ret = mlx4_en_copy_priv(tmp, priv, prof);
+	if (ret) {
+		en_warn(priv, "%s: mlx4_en_copy_priv() failed, return\n",
+			__func__);
+		return ret;
+	}
 
 	if (mlx4_en_alloc_resources(tmp)) {
 		en_warn(priv,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index f71ec4d9d68e..a46284ca5172 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -339,6 +339,9 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_PAGE_FAULT_RESUME:
 	case MLX5_CMD_OP_QUERY_ESW_FUNCTIONS:
 	case MLX5_CMD_OP_DEALLOC_SF:
+	case MLX5_CMD_OP_DESTROY_UCTX:
+	case MLX5_CMD_OP_DESTROY_UMEM:
+	case MLX5_CMD_OP_MODIFY_RQT:
 		return MLX5_CMD_STAT_OK;
 
 	case MLX5_CMD_OP_QUERY_HCA_CAP:
@@ -444,7 +447,6 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_MODIFY_TIS:
 	case MLX5_CMD_OP_QUERY_TIS:
 	case MLX5_CMD_OP_CREATE_RQT:
-	case MLX5_CMD_OP_MODIFY_RQT:
 	case MLX5_CMD_OP_QUERY_RQT:
 
 	case MLX5_CMD_OP_CREATE_FLOW_TABLE:
@@ -464,9 +466,7 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_MODIFY_GENERAL_OBJECT:
 	case MLX5_CMD_OP_QUERY_GENERAL_OBJECT:
 	case MLX5_CMD_OP_CREATE_UCTX:
-	case MLX5_CMD_OP_DESTROY_UCTX:
 	case MLX5_CMD_OP_CREATE_UMEM:
-	case MLX5_CMD_OP_DESTROY_UMEM:
 	case MLX5_CMD_OP_ALLOC_MEMIC:
 	case MLX5_CMD_OP_MODIFY_XRQ:
 	case MLX5_CMD_OP_RELEASE_XRQ_ERROR:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cq.c b/drivers/net/ethernet/mellanox/mlx5/core/cq.c
index 02e77ffe5c3e..5371ad0a12eb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cq.c
@@ -164,13 +164,14 @@ int mlx5_core_destroy_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq)
 	MLX5_SET(destroy_cq_in, in, cqn, cq->cqn);
 	MLX5_SET(destroy_cq_in, in, uid, cq->uid);
 	err = mlx5_cmd_exec_in(dev, destroy_cq, in);
+	if (err)
+		return err;
 
 	synchronize_irq(cq->irqn);
-
 	mlx5_cq_put(cq);
 	wait_for_completion(&cq->free);
 
-	return err;
+	return 0;
 }
 EXPORT_SYMBOL(mlx5_core_destroy_cq);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
index 07c8d9811bc8..10d195042ab5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
@@ -507,6 +507,8 @@ void mlx5_debug_cq_remove(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq)
 	if (!mlx5_debugfs_root)
 		return;
 
-	if (cq->dbg)
+	if (cq->dbg) {
 		rem_res_tree(cq->dbg);
+		cq->dbg = NULL;
+	}
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index f0ac6b0d9653..b47a0d3ef22f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -783,6 +783,8 @@ struct mlx5e_channel {
 	DECLARE_BITMAP(state, MLX5E_CHANNEL_NUM_STATES);
 	int                        ix;
 	int                        cpu;
+	/* Sync between icosq recovery and XSK enable/disable. */
+	struct mutex               icosq_recovery_lock;
 };
 
 struct mlx5e_ptp;
@@ -1014,9 +1016,6 @@ int mlx5e_create_rq(struct mlx5e_rq *rq, struct mlx5e_rq_param *param);
 void mlx5e_destroy_rq(struct mlx5e_rq *rq);
 
 struct mlx5e_sq_param;
-int mlx5e_open_icosq(struct mlx5e_channel *c, struct mlx5e_params *params,
-		     struct mlx5e_sq_param *param, struct mlx5e_icosq *sq);
-void mlx5e_close_icosq(struct mlx5e_icosq *sq);
 int mlx5e_open_xdpsq(struct mlx5e_channel *c, struct mlx5e_params *params,
 		     struct mlx5e_sq_param *param, struct xsk_buff_pool *xsk_pool,
 		     struct mlx5e_xdpsq *sq, bool is_redirect);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/health.h b/drivers/net/ethernet/mellanox/mlx5/core/en/health.h
index d5b7110a4265..0107e4e73bb0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/health.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/health.h
@@ -30,6 +30,8 @@ void mlx5e_reporter_rx_destroy(struct mlx5e_priv *priv);
 void mlx5e_reporter_icosq_cqe_err(struct mlx5e_icosq *icosq);
 void mlx5e_reporter_rq_cqe_err(struct mlx5e_rq *rq);
 void mlx5e_reporter_rx_timeout(struct mlx5e_rq *rq);
+void mlx5e_reporter_icosq_suspend_recovery(struct mlx5e_channel *c);
+void mlx5e_reporter_icosq_resume_recovery(struct mlx5e_channel *c);
 
 #define MLX5E_REPORTER_PER_Q_MAX_LEN 256
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.h
index d6c7c81690eb..7c9dd3a75f8a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.h
@@ -66,7 +66,7 @@ mlx5e_rep_setup_tc(struct net_device *dev, enum tc_setup_type type,
 
 static inline void
 mlx5e_rep_tc_receive(struct mlx5_cqe64 *cqe, struct mlx5e_rq *rq,
-		     struct sk_buff *skb) {}
+		     struct sk_buff *skb) { napi_gro_receive(rq->cq.napi, skb); }
 
 #endif /* CONFIG_MLX5_CLS_ACT */
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
index 74086eb556ae..2684e9da9f41 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
@@ -62,6 +62,7 @@ static void mlx5e_reset_icosq_cc_pc(struct mlx5e_icosq *icosq)
 
 static int mlx5e_rx_reporter_err_icosq_cqe_recover(void *ctx)
 {
+	struct mlx5e_rq *xskrq = NULL;
 	struct mlx5_core_dev *mdev;
 	struct mlx5e_icosq *icosq;
 	struct net_device *dev;
@@ -70,7 +71,13 @@ static int mlx5e_rx_reporter_err_icosq_cqe_recover(void *ctx)
 	int err;
 
 	icosq = ctx;
+
+	mutex_lock(&icosq->channel->icosq_recovery_lock);
+
+	/* mlx5e_close_rq cancels this work before RQ and ICOSQ are killed. */
 	rq = &icosq->channel->rq;
+	if (test_bit(MLX5E_RQ_STATE_ENABLED, &icosq->channel->xskrq.state))
+		xskrq = &icosq->channel->xskrq;
 	mdev = icosq->channel->mdev;
 	dev = icosq->channel->netdev;
 	err = mlx5_core_query_sq_state(mdev, icosq->sqn, &state);
@@ -84,6 +91,9 @@ static int mlx5e_rx_reporter_err_icosq_cqe_recover(void *ctx)
 		goto out;
 
 	mlx5e_deactivate_rq(rq);
+	if (xskrq)
+		mlx5e_deactivate_rq(xskrq);
+
 	err = mlx5e_wait_for_icosq_flush(icosq);
 	if (err)
 		goto out;
@@ -97,15 +107,28 @@ static int mlx5e_rx_reporter_err_icosq_cqe_recover(void *ctx)
 		goto out;
 
 	mlx5e_reset_icosq_cc_pc(icosq);
+
 	mlx5e_free_rx_in_progress_descs(rq);
+	if (xskrq)
+		mlx5e_free_rx_in_progress_descs(xskrq);
+
 	clear_bit(MLX5E_SQ_STATE_RECOVERING, &icosq->state);
 	mlx5e_activate_icosq(icosq);
-	mlx5e_activate_rq(rq);
 
+	mlx5e_activate_rq(rq);
 	rq->stats->recover++;
+
+	if (xskrq) {
+		mlx5e_activate_rq(xskrq);
+		xskrq->stats->recover++;
+	}
+
+	mutex_unlock(&icosq->channel->icosq_recovery_lock);
+
 	return 0;
 out:
 	clear_bit(MLX5E_SQ_STATE_RECOVERING, &icosq->state);
+	mutex_unlock(&icosq->channel->icosq_recovery_lock);
 	return err;
 }
 
@@ -706,6 +729,16 @@ void mlx5e_reporter_icosq_cqe_err(struct mlx5e_icosq *icosq)
 	mlx5e_health_report(priv, priv->rx_reporter, err_str, &err_ctx);
 }
 
+void mlx5e_reporter_icosq_suspend_recovery(struct mlx5e_channel *c)
+{
+	mutex_lock(&c->icosq_recovery_lock);
+}
+
+void mlx5e_reporter_icosq_resume_recovery(struct mlx5e_channel *c)
+{
+	mutex_unlock(&c->icosq_recovery_lock);
+}
+
 static const struct devlink_health_reporter_ops mlx5_rx_reporter_ops = {
 	.name = "rx",
 	.recover = mlx5e_rx_reporter_recover,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
index 4f4bc8726ec4..614cd9477600 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
@@ -466,6 +466,14 @@ static int mlx5e_tx_reporter_dump_sq(struct mlx5e_priv *priv, struct devlink_fms
 	return mlx5e_health_fmsg_named_obj_nest_end(fmsg);
 }
 
+static int mlx5e_tx_reporter_timeout_dump(struct mlx5e_priv *priv, struct devlink_fmsg *fmsg,
+					  void *ctx)
+{
+	struct mlx5e_tx_timeout_ctx *to_ctx = ctx;
+
+	return mlx5e_tx_reporter_dump_sq(priv, fmsg, to_ctx->sq);
+}
+
 static int mlx5e_tx_reporter_dump_all_sqs(struct mlx5e_priv *priv,
 					  struct devlink_fmsg *fmsg)
 {
@@ -561,7 +569,7 @@ int mlx5e_reporter_tx_timeout(struct mlx5e_txqsq *sq)
 	to_ctx.sq = sq;
 	err_ctx.ctx = &to_ctx;
 	err_ctx.recover = mlx5e_tx_reporter_timeout_recover;
-	err_ctx.dump = mlx5e_tx_reporter_dump_sq;
+	err_ctx.dump = mlx5e_tx_reporter_timeout_dump;
 	snprintf(err_str, sizeof(err_str),
 		 "TX timeout on queue: %d, SQ: 0x%x, CQ: 0x%x, SQ Cons: 0x%x SQ Prod: 0x%x, usecs since last trans: %u",
 		 sq->ch_ix, sq->sqn, sq->cq.mcq.cqn, sq->cc, sq->pc,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c
index 142953847996..0015a81eb9a1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c
@@ -13,6 +13,9 @@ struct mlx5e_rx_res {
 	unsigned int max_nch;
 	u32 drop_rqn;
 
+	struct mlx5e_packet_merge_param pkt_merge_param;
+	struct rw_semaphore pkt_merge_param_sem;
+
 	struct mlx5e_rss *rss[MLX5E_MAX_NUM_RSS];
 	bool rss_active;
 	u32 rss_rqns[MLX5E_INDIR_RQT_SIZE];
@@ -392,6 +395,7 @@ static int mlx5e_rx_res_ptp_init(struct mlx5e_rx_res *res)
 	if (err)
 		goto out;
 
+	/* Separated from the channels RQs, does not share pkt_merge state with them */
 	mlx5e_tir_builder_build_rqt(builder, res->mdev->mlx5e_res.hw_objs.td.tdn,
 				    mlx5e_rqt_get_rqtn(&res->ptp.rqt),
 				    inner_ft_support);
@@ -447,6 +451,9 @@ int mlx5e_rx_res_init(struct mlx5e_rx_res *res, struct mlx5_core_dev *mdev,
 	res->max_nch = max_nch;
 	res->drop_rqn = drop_rqn;
 
+	res->pkt_merge_param = *init_pkt_merge_param;
+	init_rwsem(&res->pkt_merge_param_sem);
+
 	err = mlx5e_rx_res_rss_init_def(res, init_pkt_merge_param, init_nch);
 	if (err)
 		goto err_out;
@@ -513,7 +520,7 @@ u32 mlx5e_rx_res_get_tirn_ptp(struct mlx5e_rx_res *res)
 	return mlx5e_tir_get_tirn(&res->ptp.tir);
 }
 
-u32 mlx5e_rx_res_get_rqtn_direct(struct mlx5e_rx_res *res, unsigned int ix)
+static u32 mlx5e_rx_res_get_rqtn_direct(struct mlx5e_rx_res *res, unsigned int ix)
 {
 	return mlx5e_rqt_get_rqtn(&res->channels[ix].direct_rqt);
 }
@@ -656,6 +663,9 @@ int mlx5e_rx_res_packet_merge_set_param(struct mlx5e_rx_res *res,
 	if (!builder)
 		return -ENOMEM;
 
+	down_write(&res->pkt_merge_param_sem);
+	res->pkt_merge_param = *pkt_merge_param;
+
 	mlx5e_tir_builder_build_packet_merge(builder, pkt_merge_param);
 
 	final_err = 0;
@@ -681,6 +691,7 @@ int mlx5e_rx_res_packet_merge_set_param(struct mlx5e_rx_res *res,
 		}
 	}
 
+	up_write(&res->pkt_merge_param_sem);
 	mlx5e_tir_builder_free(builder);
 	return final_err;
 }
@@ -689,3 +700,31 @@ struct mlx5e_rss_params_hash mlx5e_rx_res_get_current_hash(struct mlx5e_rx_res *
 {
 	return mlx5e_rss_get_hash(res->rss[0]);
 }
+
+int mlx5e_rx_res_tls_tir_create(struct mlx5e_rx_res *res, unsigned int rxq,
+				struct mlx5e_tir *tir)
+{
+	bool inner_ft_support = res->features & MLX5E_RX_RES_FEATURE_INNER_FT;
+	struct mlx5e_tir_builder *builder;
+	u32 rqtn;
+	int err;
+
+	builder = mlx5e_tir_builder_alloc(false);
+	if (!builder)
+		return -ENOMEM;
+
+	rqtn = mlx5e_rx_res_get_rqtn_direct(res, rxq);
+
+	mlx5e_tir_builder_build_rqt(builder, res->mdev->mlx5e_res.hw_objs.td.tdn, rqtn,
+				    inner_ft_support);
+	mlx5e_tir_builder_build_direct(builder);
+	mlx5e_tir_builder_build_tls(builder);
+	down_read(&res->pkt_merge_param_sem);
+	mlx5e_tir_builder_build_packet_merge(builder, &res->pkt_merge_param);
+	err = mlx5e_tir_init(tir, builder, res->mdev, false);
+	up_read(&res->pkt_merge_param_sem);
+
+	mlx5e_tir_builder_free(builder);
+
+	return err;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h
index d09f7d174a51..b39b20a720e0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h
@@ -37,9 +37,6 @@ u32 mlx5e_rx_res_get_tirn_rss(struct mlx5e_rx_res *res, enum mlx5_traffic_types
 u32 mlx5e_rx_res_get_tirn_rss_inner(struct mlx5e_rx_res *res, enum mlx5_traffic_types tt);
 u32 mlx5e_rx_res_get_tirn_ptp(struct mlx5e_rx_res *res);
 
-/* RQTN getters for modules that create their own TIRs */
-u32 mlx5e_rx_res_get_rqtn_direct(struct mlx5e_rx_res *res, unsigned int ix);
-
 /* Activate/deactivate API */
 void mlx5e_rx_res_channels_activate(struct mlx5e_rx_res *res, struct mlx5e_channels *chs);
 void mlx5e_rx_res_channels_deactivate(struct mlx5e_rx_res *res);
@@ -69,4 +66,7 @@ struct mlx5e_rss *mlx5e_rx_res_rss_get(struct mlx5e_rx_res *res, u32 rss_idx);
 /* Workaround for hairpin */
 struct mlx5e_rss_params_hash mlx5e_rx_res_get_current_hash(struct mlx5e_rx_res *res);
 
+/* Accel TIRs */
+int mlx5e_rx_res_tls_tir_create(struct mlx5e_rx_res *res, unsigned int rxq,
+				struct mlx5e_tir *tir);
 #endif /* __MLX5_EN_RX_RES_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
index c1c6e74c79c4..2445e2ae3324 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
@@ -1356,9 +1356,13 @@ mlx5_tc_ct_match_add(struct mlx5_tc_ct_priv *priv,
 int
 mlx5_tc_ct_parse_action(struct mlx5_tc_ct_priv *priv,
 			struct mlx5_flow_attr *attr,
+			struct mlx5e_tc_mod_hdr_acts *mod_acts,
 			const struct flow_action_entry *act,
 			struct netlink_ext_ack *extack)
 {
+	bool clear_action = act->ct.action & TCA_CT_ACT_CLEAR;
+	int err;
+
 	if (!priv) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "offload of ct action isn't available");
@@ -1369,6 +1373,17 @@ mlx5_tc_ct_parse_action(struct mlx5_tc_ct_priv *priv,
 	attr->ct_attr.ct_action = act->ct.action;
 	attr->ct_attr.nf_ft = act->ct.flow_table;
 
+	if (!clear_action)
+		goto out;
+
+	err = mlx5_tc_ct_entry_set_registers(priv, mod_acts, 0, 0, 0, 0);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "Failed to set registers for ct clear");
+		return err;
+	}
+	attr->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
+
+out:
 	return 0;
 }
 
@@ -1898,23 +1913,16 @@ __mlx5_tc_ct_flow_offload_clear(struct mlx5_tc_ct_priv *ct_priv,
 
 	memcpy(pre_ct_attr, attr, attr_sz);
 
-	err = mlx5_tc_ct_entry_set_registers(ct_priv, mod_acts, 0, 0, 0, 0);
-	if (err) {
-		ct_dbg("Failed to set register for ct clear");
-		goto err_set_registers;
-	}
-
 	mod_hdr = mlx5_modify_header_alloc(priv->mdev, ct_priv->ns_type,
 					   mod_acts->num_actions,
 					   mod_acts->actions);
 	if (IS_ERR(mod_hdr)) {
 		err = PTR_ERR(mod_hdr);
 		ct_dbg("Failed to add create ct clear mod hdr");
-		goto err_set_registers;
+		goto err_mod_hdr;
 	}
 
 	pre_ct_attr->modify_hdr = mod_hdr;
-	pre_ct_attr->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
 
 	rule = mlx5_tc_rule_insert(priv, orig_spec, pre_ct_attr);
 	if (IS_ERR(rule)) {
@@ -1930,7 +1938,7 @@ __mlx5_tc_ct_flow_offload_clear(struct mlx5_tc_ct_priv *ct_priv,
 
 err_insert:
 	mlx5_modify_header_dealloc(priv->mdev, mod_hdr);
-err_set_registers:
+err_mod_hdr:
 	netdev_warn(priv->netdev,
 		    "Failed to offload ct clear flow, err %d\n", err);
 	kfree(pre_ct_attr);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h
index 363329f4aac6..99662af1e41a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h
@@ -110,6 +110,7 @@ int mlx5_tc_ct_add_no_trk_match(struct mlx5_flow_spec *spec);
 int
 mlx5_tc_ct_parse_action(struct mlx5_tc_ct_priv *priv,
 			struct mlx5_flow_attr *attr,
+			struct mlx5e_tc_mod_hdr_acts *mod_acts,
 			const struct flow_action_entry *act,
 			struct netlink_ext_ack *extack);
 
@@ -172,6 +173,7 @@ mlx5_tc_ct_add_no_trk_match(struct mlx5_flow_spec *spec)
 static inline int
 mlx5_tc_ct_parse_action(struct mlx5_tc_ct_priv *priv,
 			struct mlx5_flow_attr *attr,
+			struct mlx5e_tc_mod_hdr_acts *mod_acts,
 			const struct flow_action_entry *act,
 			struct netlink_ext_ack *extack)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h
index 8f64f2c8895a..b689701ac7d8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h
@@ -102,6 +102,7 @@ struct mlx5e_tc_flow {
 	refcount_t refcnt;
 	struct rcu_head rcu_head;
 	struct completion init_done;
+	struct completion del_hw_done;
 	int tunnel_id; /* the mapped tunnel id of this flow */
 	struct mlx5_flow_attr *attr;
 };
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c
index 660cca73c36c..042b1abe1437 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c
@@ -245,8 +245,14 @@ static void mlx5e_take_tmp_flow(struct mlx5e_tc_flow *flow,
 				struct list_head *flow_list,
 				int index)
 {
-	if (IS_ERR(mlx5e_flow_get(flow)))
+	if (IS_ERR(mlx5e_flow_get(flow))) {
+		/* Flow is being deleted concurrently. Wait for it to be
+		 * unoffloaded from hardware, otherwise deleting encap will
+		 * fail.
+		 */
+		wait_for_completion(&flow->del_hw_done);
 		return;
+	}
 	wait_for_completion(&flow->init_done);
 
 	flow->tmp_entry_index = index;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
index 538bc2419bd8..8526a5fbbf0b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
@@ -4,6 +4,7 @@
 #include "setup.h"
 #include "en/params.h"
 #include "en/txrx.h"
+#include "en/health.h"
 
 /* It matches XDP_UMEM_MIN_CHUNK_SIZE, but as this constant is private and may
  * change unexpectedly, and mlx5e has a minimum valid stride size for striding
@@ -170,7 +171,13 @@ void mlx5e_close_xsk(struct mlx5e_channel *c)
 
 void mlx5e_activate_xsk(struct mlx5e_channel *c)
 {
+	/* ICOSQ recovery deactivates RQs. Suspend the recovery to avoid
+	 * activating XSKRQ in the middle of recovery.
+	 */
+	mlx5e_reporter_icosq_suspend_recovery(c);
 	set_bit(MLX5E_RQ_STATE_ENABLED, &c->xskrq.state);
+	mlx5e_reporter_icosq_resume_recovery(c);
+
 	/* TX queue is created active. */
 
 	spin_lock_bh(&c->async_icosq_lock);
@@ -180,6 +187,13 @@ void mlx5e_activate_xsk(struct mlx5e_channel *c)
 
 void mlx5e_deactivate_xsk(struct mlx5e_channel *c)
 {
-	mlx5e_deactivate_rq(&c->xskrq);
+	/* ICOSQ recovery may reactivate XSKRQ if clear_bit is called in the
+	 * middle of recovery. Suspend the recovery to avoid it.
+	 */
+	mlx5e_reporter_icosq_suspend_recovery(c);
+	clear_bit(MLX5E_RQ_STATE_ENABLED, &c->xskrq.state);
+	mlx5e_reporter_icosq_resume_recovery(c);
+	synchronize_net(); /* Sync with NAPI to prevent mlx5e_post_rx_wqes. */
+
 	/* TX queue is disabled on close. */
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
index fb5397324aa4..2db9573a3fe6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
@@ -191,7 +191,7 @@ static void mlx5e_ipsec_set_swp(struct sk_buff *skb,
 			eseg->swp_inner_l3_offset = skb_inner_network_offset(skb) / 2;
 			eseg->swp_inner_l4_offset =
 				(skb->csum_start + skb->head - skb->data) / 2;
-			if (skb->protocol == htons(ETH_P_IPV6))
+			if (inner_ip_hdr(skb)->version == 6)
 				eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L3_IPV6;
 			break;
 		default:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
index 62abce008c7b..15711814d2d2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c
@@ -55,6 +55,7 @@ struct mlx5e_ktls_offload_context_rx {
 	DECLARE_BITMAP(flags, MLX5E_NUM_PRIV_RX_FLAGS);
 
 	/* resync */
+	spinlock_t lock; /* protects resync fields */
 	struct mlx5e_ktls_rx_resync_ctx resync;
 	struct list_head list;
 };
@@ -99,25 +100,6 @@ mlx5e_ktls_rx_resync_create_resp_list(void)
 	return resp_list;
 }
 
-static int mlx5e_ktls_create_tir(struct mlx5_core_dev *mdev, struct mlx5e_tir *tir, u32 rqtn)
-{
-	struct mlx5e_tir_builder *builder;
-	int err;
-
-	builder = mlx5e_tir_builder_alloc(false);
-	if (!builder)
-		return -ENOMEM;
-
-	mlx5e_tir_builder_build_rqt(builder, mdev->mlx5e_res.hw_objs.td.tdn, rqtn, false);
-	mlx5e_tir_builder_build_direct(builder);
-	mlx5e_tir_builder_build_tls(builder);
-	err = mlx5e_tir_init(tir, builder, mdev, false);
-
-	mlx5e_tir_builder_free(builder);
-
-	return err;
-}
-
 static void accel_rule_handle_work(struct work_struct *work)
 {
 	struct mlx5e_ktls_offload_context_rx *priv_rx;
@@ -386,14 +368,18 @@ static void resync_handle_seq_match(struct mlx5e_ktls_offload_context_rx *priv_r
 	struct mlx5e_icosq *sq;
 	bool trigger_poll;
 
-	memcpy(info->rec_seq, &priv_rx->resync.sw_rcd_sn_be, sizeof(info->rec_seq));
-
 	sq = &c->async_icosq;
 	ktls_resync = sq->ktls_resync;
+	trigger_poll = false;
 
 	spin_lock_bh(&ktls_resync->lock);
-	list_add_tail(&priv_rx->list, &ktls_resync->list);
-	trigger_poll = !test_and_set_bit(MLX5E_SQ_STATE_PENDING_TLS_RX_RESYNC, &sq->state);
+	spin_lock_bh(&priv_rx->lock);
+	memcpy(info->rec_seq, &priv_rx->resync.sw_rcd_sn_be, sizeof(info->rec_seq));
+	if (list_empty(&priv_rx->list)) {
+		list_add_tail(&priv_rx->list, &ktls_resync->list);
+		trigger_poll = !test_and_set_bit(MLX5E_SQ_STATE_PENDING_TLS_RX_RESYNC, &sq->state);
+	}
+	spin_unlock_bh(&priv_rx->lock);
 	spin_unlock_bh(&ktls_resync->lock);
 
 	if (!trigger_poll)
@@ -604,7 +590,6 @@ int mlx5e_ktls_add_rx(struct net_device *netdev, struct sock *sk,
 	struct mlx5_core_dev *mdev;
 	struct mlx5e_priv *priv;
 	int rxq, err;
-	u32 rqtn;
 
 	tls_ctx = tls_get_ctx(sk);
 	priv = netdev_priv(netdev);
@@ -617,6 +602,8 @@ int mlx5e_ktls_add_rx(struct net_device *netdev, struct sock *sk,
 	if (err)
 		goto err_create_key;
 
+	INIT_LIST_HEAD(&priv_rx->list);
+	spin_lock_init(&priv_rx->lock);
 	priv_rx->crypto_info  =
 		*(struct tls12_crypto_info_aes_gcm_128 *)crypto_info;
 
@@ -628,9 +615,7 @@ int mlx5e_ktls_add_rx(struct net_device *netdev, struct sock *sk,
 	priv_rx->sw_stats = &priv->tls->sw_stats;
 	mlx5e_set_ktls_rx_priv_ctx(tls_ctx, priv_rx);
 
-	rqtn = mlx5e_rx_res_get_rqtn_direct(priv->rx_res, rxq);
-
-	err = mlx5e_ktls_create_tir(mdev, &priv_rx->tir, rqtn);
+	err = mlx5e_rx_res_tls_tir_create(priv->rx_res, rxq, &priv_rx->tir);
 	if (err)
 		goto err_create_tir;
 
@@ -730,10 +715,14 @@ bool mlx5e_ktls_rx_handle_resync_list(struct mlx5e_channel *c, int budget)
 		priv_rx = list_first_entry(&local_list,
 					   struct mlx5e_ktls_offload_context_rx,
 					   list);
+		spin_lock(&priv_rx->lock);
 		cseg = post_static_params(sq, priv_rx);
-		if (IS_ERR(cseg))
+		if (IS_ERR(cseg)) {
+			spin_unlock(&priv_rx->lock);
 			break;
-		list_del(&priv_rx->list);
+		}
+		list_del_init(&priv_rx->list);
+		spin_unlock(&priv_rx->lock);
 		db_cseg = cseg;
 	}
 	if (db_cseg)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 65571593ec5c..41379844eee1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -1087,8 +1087,6 @@ void mlx5e_deactivate_rq(struct mlx5e_rq *rq)
 void mlx5e_close_rq(struct mlx5e_rq *rq)
 {
 	cancel_work_sync(&rq->dim.work);
-	if (rq->icosq)
-		cancel_work_sync(&rq->icosq->recover_work);
 	cancel_work_sync(&rq->recover_work);
 	mlx5e_destroy_rq(rq);
 	mlx5e_free_rx_descs(rq);
@@ -1216,9 +1214,20 @@ static void mlx5e_icosq_err_cqe_work(struct work_struct *recover_work)
 	mlx5e_reporter_icosq_cqe_err(sq);
 }
 
+static void mlx5e_async_icosq_err_cqe_work(struct work_struct *recover_work)
+{
+	struct mlx5e_icosq *sq = container_of(recover_work, struct mlx5e_icosq,
+					      recover_work);
+
+	/* Not implemented yet. */
+
+	netdev_warn(sq->channel->netdev, "async_icosq recovery is not implemented\n");
+}
+
 static int mlx5e_alloc_icosq(struct mlx5e_channel *c,
 			     struct mlx5e_sq_param *param,
-			     struct mlx5e_icosq *sq)
+			     struct mlx5e_icosq *sq,
+			     work_func_t recover_work_func)
 {
 	void *sqc_wq               = MLX5_ADDR_OF(sqc, param->sqc, wq);
 	struct mlx5_core_dev *mdev = c->mdev;
@@ -1239,7 +1248,7 @@ static int mlx5e_alloc_icosq(struct mlx5e_channel *c,
 	if (err)
 		goto err_sq_wq_destroy;
 
-	INIT_WORK(&sq->recover_work, mlx5e_icosq_err_cqe_work);
+	INIT_WORK(&sq->recover_work, recover_work_func);
 
 	return 0;
 
@@ -1575,13 +1584,14 @@ void mlx5e_tx_err_cqe_work(struct work_struct *recover_work)
 	mlx5e_reporter_tx_err_cqe(sq);
 }
 
-int mlx5e_open_icosq(struct mlx5e_channel *c, struct mlx5e_params *params,
-		     struct mlx5e_sq_param *param, struct mlx5e_icosq *sq)
+static int mlx5e_open_icosq(struct mlx5e_channel *c, struct mlx5e_params *params,
+			    struct mlx5e_sq_param *param, struct mlx5e_icosq *sq,
+			    work_func_t recover_work_func)
 {
 	struct mlx5e_create_sq_param csp = {};
 	int err;
 
-	err = mlx5e_alloc_icosq(c, param, sq);
+	err = mlx5e_alloc_icosq(c, param, sq, recover_work_func);
 	if (err)
 		return err;
 
@@ -1620,7 +1630,7 @@ void mlx5e_deactivate_icosq(struct mlx5e_icosq *icosq)
 	synchronize_net(); /* Sync with NAPI. */
 }
 
-void mlx5e_close_icosq(struct mlx5e_icosq *sq)
+static void mlx5e_close_icosq(struct mlx5e_icosq *sq)
 {
 	struct mlx5e_channel *c = sq->channel;
 
@@ -2084,11 +2094,15 @@ static int mlx5e_open_queues(struct mlx5e_channel *c,
 
 	spin_lock_init(&c->async_icosq_lock);
 
-	err = mlx5e_open_icosq(c, params, &cparam->async_icosq, &c->async_icosq);
+	err = mlx5e_open_icosq(c, params, &cparam->async_icosq, &c->async_icosq,
+			       mlx5e_async_icosq_err_cqe_work);
 	if (err)
 		goto err_close_xdpsq_cq;
 
-	err = mlx5e_open_icosq(c, params, &cparam->icosq, &c->icosq);
+	mutex_init(&c->icosq_recovery_lock);
+
+	err = mlx5e_open_icosq(c, params, &cparam->icosq, &c->icosq,
+			       mlx5e_icosq_err_cqe_work);
 	if (err)
 		goto err_close_async_icosq;
 
@@ -2156,9 +2170,12 @@ static void mlx5e_close_queues(struct mlx5e_channel *c)
 	mlx5e_close_xdpsq(&c->xdpsq);
 	if (c->xdp)
 		mlx5e_close_xdpsq(&c->rq_xdpsq);
+	/* The same ICOSQ is used for UMRs for both RQ and XSKRQ. */
+	cancel_work_sync(&c->icosq.recover_work);
 	mlx5e_close_rq(&c->rq);
 	mlx5e_close_sqs(c);
 	mlx5e_close_icosq(&c->icosq);
+	mutex_destroy(&c->icosq_recovery_lock);
 	mlx5e_close_icosq(&c->async_icosq);
 	if (c->xdp)
 		mlx5e_close_cq(&c->rq_xdpsq.cq);
@@ -3724,12 +3741,11 @@ static int set_feature_arfs(struct net_device *netdev, bool enable)
 
 static int mlx5e_handle_feature(struct net_device *netdev,
 				netdev_features_t *features,
-				netdev_features_t wanted_features,
 				netdev_features_t feature,
 				mlx5e_feature_handler feature_handler)
 {
-	netdev_features_t changes = wanted_features ^ netdev->features;
-	bool enable = !!(wanted_features & feature);
+	netdev_features_t changes = *features ^ netdev->features;
+	bool enable = !!(*features & feature);
 	int err;
 
 	if (!(changes & feature))
@@ -3737,22 +3753,22 @@ static int mlx5e_handle_feature(struct net_device *netdev,
 
 	err = feature_handler(netdev, enable);
 	if (err) {
+		MLX5E_SET_FEATURE(features, feature, !enable);
 		netdev_err(netdev, "%s feature %pNF failed, err %d\n",
 			   enable ? "Enable" : "Disable", &feature, err);
 		return err;
 	}
 
-	MLX5E_SET_FEATURE(features, feature, enable);
 	return 0;
 }
 
 int mlx5e_set_features(struct net_device *netdev, netdev_features_t features)
 {
-	netdev_features_t oper_features = netdev->features;
+	netdev_features_t oper_features = features;
 	int err = 0;
 
 #define MLX5E_HANDLE_FEATURE(feature, handler) \
-	mlx5e_handle_feature(netdev, &oper_features, features, feature, handler)
+	mlx5e_handle_feature(netdev, &oper_features, feature, handler)
 
 	err |= MLX5E_HANDLE_FEATURE(NETIF_F_LRO, set_feature_lro);
 	err |= MLX5E_HANDLE_FEATURE(NETIF_F_GRO_HW, set_feature_hw_gro);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index e58a9ec42553..48895d79796a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -1080,6 +1080,10 @@ static mlx5e_stats_grp_t mlx5e_ul_rep_stats_grps[] = {
 	&MLX5E_STATS_GRP(pme),
 	&MLX5E_STATS_GRP(channels),
 	&MLX5E_STATS_GRP(per_port_buff_congest),
+#ifdef CONFIG_MLX5_EN_IPSEC
+	&MLX5E_STATS_GRP(ipsec_sw),
+	&MLX5E_STATS_GRP(ipsec_hw),
+#endif
 };
 
 static unsigned int mlx5e_ul_rep_stats_grps_num(struct mlx5e_priv *priv)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 96967b0a2441..793511d5ee4c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -543,13 +543,13 @@ static int mlx5e_build_shampo_hd_umr(struct mlx5e_rq *rq,
 				     u16 klm_entries, u16 index)
 {
 	struct mlx5e_shampo_hd *shampo = rq->mpwqe.shampo;
-	u16 entries, pi, i, header_offset, err, wqe_bbs, new_entries;
+	u16 entries, pi, header_offset, err, wqe_bbs, new_entries;
 	u32 lkey = rq->mdev->mlx5e_res.hw_objs.mkey;
 	struct page *page = shampo->last_page;
 	u64 addr = shampo->last_addr;
 	struct mlx5e_dma_info *dma_info;
 	struct mlx5e_umr_wqe *umr_wqe;
-	int headroom;
+	int headroom, i;
 
 	headroom = rq->buff.headroom;
 	new_entries = klm_entries - (shampo->pi & (MLX5_UMR_KLM_ALIGNMENT - 1));
@@ -601,9 +601,7 @@ update_klm:
 
 err_unmap:
 	while (--i >= 0) {
-		if (--index < 0)
-			index = shampo->hd_per_wq - 1;
-		dma_info = &shampo->info[index];
+		dma_info = &shampo->info[--index];
 		if (!(i & (MLX5E_SHAMPO_WQ_HEADER_PER_PAGE - 1))) {
 			dma_info->addr = ALIGN_DOWN(dma_info->addr, PAGE_SIZE);
 			mlx5e_page_release(rq, dma_info, true);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 835caa1c7b74..5e454a14428f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1196,21 +1196,16 @@ void mlx5e_tc_unoffload_fdb_rules(struct mlx5_eswitch *esw,
 	if (attr->flags & MLX5_ESW_ATTR_FLAG_SLOW_PATH)
 		goto offload_rule_0;
 
-	if (flow_flag_test(flow, CT)) {
-		mlx5_tc_ct_delete_flow(get_ct_priv(flow->priv), flow, attr);
-		return;
-	}
-
-	if (flow_flag_test(flow, SAMPLE)) {
-		mlx5e_tc_sample_unoffload(get_sample_priv(flow->priv), flow->rule[0], attr);
-		return;
-	}
-
 	if (attr->esw_attr->split_count)
 		mlx5_eswitch_del_fwd_rule(esw, flow->rule[1], attr);
 
+	if (flow_flag_test(flow, CT))
+		mlx5_tc_ct_delete_flow(get_ct_priv(flow->priv), flow, attr);
+	else if (flow_flag_test(flow, SAMPLE))
+		mlx5e_tc_sample_unoffload(get_sample_priv(flow->priv), flow->rule[0], attr);
+	else
 offload_rule_0:
-	mlx5_eswitch_del_offloaded_rule(esw, flow->rule[0], attr);
+		mlx5_eswitch_del_offloaded_rule(esw, flow->rule[0], attr);
 }
 
 struct mlx5_flow_handle *
@@ -1445,7 +1440,9 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
 							MLX5_FLOW_NAMESPACE_FDB, VPORT_TO_REG,
 							metadata);
 			if (err)
-				return err;
+				goto err_out;
+
+			attr->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
 		}
 	}
 
@@ -1461,13 +1458,15 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
 		if (attr->chain) {
 			NL_SET_ERR_MSG_MOD(extack,
 					   "Internal port rule is only supported on chain 0");
-			return -EOPNOTSUPP;
+			err = -EOPNOTSUPP;
+			goto err_out;
 		}
 
 		if (attr->dest_chain) {
 			NL_SET_ERR_MSG_MOD(extack,
 					   "Internal port rule offload doesn't support goto action");
-			return -EOPNOTSUPP;
+			err = -EOPNOTSUPP;
+			goto err_out;
 		}
 
 		int_port = mlx5e_tc_int_port_get(mlx5e_get_int_port_priv(priv),
@@ -1475,8 +1474,10 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
 						 flow_flag_test(flow, EGRESS) ?
 						 MLX5E_TC_INT_PORT_EGRESS :
 						 MLX5E_TC_INT_PORT_INGRESS);
-		if (IS_ERR(int_port))
-			return PTR_ERR(int_port);
+		if (IS_ERR(int_port)) {
+			err = PTR_ERR(int_port);
+			goto err_out;
+		}
 
 		esw_attr->int_port = int_port;
 	}
@@ -1600,6 +1601,7 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv,
 		else
 			mlx5e_tc_unoffload_fdb_rules(esw, flow, attr);
 	}
+	complete_all(&flow->del_hw_done);
 
 	if (mlx5_flow_has_geneve_opt(flow))
 		mlx5_geneve_tlv_option_del(priv->mdev->geneve);
@@ -3607,7 +3609,9 @@ parse_tc_nic_actions(struct mlx5e_priv *priv,
 			attr->dest_chain = act->chain_index;
 			break;
 		case FLOW_ACTION_CT:
-			err = mlx5_tc_ct_parse_action(get_ct_priv(priv), attr, act, extack);
+			err = mlx5_tc_ct_parse_action(get_ct_priv(priv), attr,
+						      &parse_attr->mod_hdr_acts,
+						      act, extack);
 			if (err)
 				return err;
 
@@ -4276,7 +4280,9 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv,
 				NL_SET_ERR_MSG_MOD(extack, "Sample action with connection tracking is not supported");
 				return -EOPNOTSUPP;
 			}
-			err = mlx5_tc_ct_parse_action(get_ct_priv(priv), attr, act, extack);
+			err = mlx5_tc_ct_parse_action(get_ct_priv(priv), attr,
+						      &parse_attr->mod_hdr_acts,
+						      act, extack);
 			if (err)
 				return err;
 
@@ -4465,6 +4471,7 @@ mlx5e_alloc_flow(struct mlx5e_priv *priv, int attr_size,
 	INIT_LIST_HEAD(&flow->l3_to_l2_reformat);
 	refcount_set(&flow->refcnt, 1);
 	init_completion(&flow->init_done);
+	init_completion(&flow->del_hw_done);
 
 	*__flow = flow;
 	*__parse_attr = parse_attr;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
index c6cc67cb4f6a..d377ddc70fc7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
@@ -130,7 +130,7 @@ static u32 esw_qos_calculate_min_rate_divider(struct mlx5_eswitch *esw,
 	/* If vports min rate divider is 0 but their group has bw_share configured, then
 	 * need to set bw_share for vports to minimal value.
 	 */
-	if (!group_level && !max_guarantee && group->bw_share)
+	if (!group_level && !max_guarantee && group && group->bw_share)
 		return 1;
 	return 0;
 }
@@ -423,7 +423,7 @@ static int esw_qos_vport_update_group(struct mlx5_eswitch *esw,
 		return err;
 
 	/* Recalculate bw share weights of old and new groups */
-	if (vport->qos.bw_share) {
+	if (vport->qos.bw_share || new_group->bw_share) {
 		esw_qos_normalize_vports_min_rate(esw, curr_group, extack);
 		esw_qos_normalize_vports_min_rate(esw, new_group, extack);
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index ec136b499204..51a8cecc4a7c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1305,12 +1305,17 @@ abort:
  */
 int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int num_vfs)
 {
+	bool toggle_lag;
 	int ret;
 
 	if (!mlx5_esw_allowed(esw))
 		return 0;
 
-	mlx5_lag_disable_change(esw->dev);
+	toggle_lag = esw->mode == MLX5_ESWITCH_NONE;
+
+	if (toggle_lag)
+		mlx5_lag_disable_change(esw->dev);
+
 	down_write(&esw->mode_lock);
 	if (esw->mode == MLX5_ESWITCH_NONE) {
 		ret = mlx5_eswitch_enable_locked(esw, MLX5_ESWITCH_LEGACY, num_vfs);
@@ -1324,7 +1329,10 @@ int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int num_vfs)
 			esw->esw_funcs.num_vfs = num_vfs;
 	}
 	up_write(&esw->mode_lock);
-	mlx5_lag_enable_change(esw->dev);
+
+	if (toggle_lag)
+		mlx5_lag_enable_change(esw->dev);
+
 	return ret;
 }
 
@@ -1572,6 +1580,11 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev)
 	esw->enabled_vports = 0;
 	esw->mode = MLX5_ESWITCH_NONE;
 	esw->offloads.inline_mode = MLX5_INLINE_MODE_NONE;
+	if (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, reformat) &&
+	    MLX5_CAP_ESW_FLOWTABLE_FDB(dev, decap))
+		esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_BASIC;
+	else
+		esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE;
 
 	dev->priv.eswitch = esw;
 	BLOCKING_INIT_NOTIFIER_HEAD(&esw->n_head);
@@ -1934,7 +1947,7 @@ free_out:
 	return err;
 }
 
-u8 mlx5_eswitch_mode(struct mlx5_core_dev *dev)
+u8 mlx5_eswitch_mode(const struct mlx5_core_dev *dev)
 {
 	struct mlx5_eswitch *esw = dev->priv.eswitch;
 
@@ -1948,7 +1961,7 @@ mlx5_eswitch_get_encap_mode(const struct mlx5_core_dev *dev)
 	struct mlx5_eswitch *esw;
 
 	esw = dev->priv.eswitch;
-	return mlx5_esw_allowed(esw) ? esw->offloads.encap :
+	return (mlx5_eswitch_mode(dev) == MLX5_ESWITCH_OFFLOADS)  ? esw->offloads.encap :
 		DEVLINK_ESWITCH_ENCAP_MODE_NONE;
 }
 EXPORT_SYMBOL(mlx5_eswitch_get_encap_mode);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index f4eaa5893886..32bc08a39925 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -329,14 +329,25 @@ static bool
 esw_is_indir_table(struct mlx5_eswitch *esw, struct mlx5_flow_attr *attr)
 {
 	struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr;
+	bool result = false;
 	int i;
 
-	for (i = esw_attr->split_count; i < esw_attr->out_count; i++)
+	/* Indirect table is supported only for flows with in_port uplink
+	 * and the destination is vport on the same eswitch as the uplink,
+	 * return false in case at least one of destinations doesn't meet
+	 * this criteria.
+	 */
+	for (i = esw_attr->split_count; i < esw_attr->out_count; i++) {
 		if (esw_attr->dests[i].rep &&
 		    mlx5_esw_indir_table_needed(esw, attr, esw_attr->dests[i].rep->vport,
-						esw_attr->dests[i].mdev))
-			return true;
-	return false;
+						esw_attr->dests[i].mdev)) {
+			result = true;
+		} else {
+			result = false;
+			break;
+		}
+	}
+	return result;
 }
 
 static int
@@ -2512,6 +2523,7 @@ static int esw_set_master_egress_rule(struct mlx5_core_dev *master,
 	struct mlx5_eswitch *esw = master->priv.eswitch;
 	struct mlx5_flow_table_attr ft_attr = {
 		.max_fte = 1, .prio = 0, .level = 0,
+		.flags = MLX5_FLOW_TABLE_OTHER_VPORT,
 	};
 	struct mlx5_flow_namespace *egress_ns;
 	struct mlx5_flow_table *acl;
@@ -3183,12 +3195,6 @@ int esw_offloads_enable(struct mlx5_eswitch *esw)
 	u64 mapping_id;
 	int err;
 
-	if (MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, reformat) &&
-	    MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, decap))
-		esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_BASIC;
-	else
-		esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE;
-
 	mutex_init(&esw->offloads.termtbl_mutex);
 	mlx5_rdma_enable_roce(esw->dev);
 
@@ -3286,7 +3292,6 @@ void esw_offloads_disable(struct mlx5_eswitch *esw)
 	esw_offloads_metadata_uninit(esw);
 	mlx5_rdma_disable_roce(esw->dev);
 	mutex_destroy(&esw->offloads.termtbl_mutex);
-	esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE;
 }
 
 static int esw_mode_from_devlink(u16 mode, u16 *mlx5_mode)
@@ -3630,7 +3635,7 @@ int mlx5_devlink_eswitch_encap_mode_get(struct devlink *devlink,
 	*encap = esw->offloads.encap;
 unlock:
 	up_write(&esw->mode_lock);
-	return 0;
+	return err;
 }
 
 static bool
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
index 31c99d53faf7..7e0e04cf26f8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
@@ -40,7 +40,7 @@
 #define MLX5_FC_STATS_PERIOD msecs_to_jiffies(1000)
 /* Max number of counters to query in bulk read is 32K */
 #define MLX5_SW_MAX_COUNTERS_BULK BIT(15)
-#define MLX5_SF_NUM_COUNTERS_BULK 6
+#define MLX5_SF_NUM_COUNTERS_BULK 8
 #define MLX5_FC_POOL_MAX_THRESHOLD BIT(18)
 #define MLX5_FC_POOL_USED_BUFF_RATIO 10
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index 64f1abc4dc36..3ca998874c50 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -835,6 +835,9 @@ void mlx5_start_health_poll(struct mlx5_core_dev *dev)
 
 	health->timer.expires = jiffies + msecs_to_jiffies(poll_interval_ms);
 	add_timer(&health->timer);
+
+	if (mlx5_core_is_pf(dev) && MLX5_CAP_MCAM_REG(dev, mrtc))
+		queue_delayed_work(health->wq, &health->update_fw_log_ts_work, 0);
 }
 
 void mlx5_stop_health_poll(struct mlx5_core_dev *dev, bool disable_health)
@@ -902,8 +905,6 @@ int mlx5_health_init(struct mlx5_core_dev *dev)
 	INIT_WORK(&health->fatal_report_work, mlx5_fw_fatal_reporter_err_work);
 	INIT_WORK(&health->report_work, mlx5_fw_reporter_err_work);
 	INIT_DELAYED_WORK(&health->update_fw_log_ts_work, mlx5_health_log_ts_update);
-	if (mlx5_core_is_pf(dev))
-		queue_delayed_work(health->wq, &health->update_fw_log_ts_work, 0);
 
 	return 0;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
index 48d2ea690d7a..4ddf6b330a44 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
@@ -615,6 +615,7 @@ static int mlx5_handle_changeupper_event(struct mlx5_lag *ldev,
 	bool is_bonded, is_in_lag, mode_supported;
 	int bond_status = 0;
 	int num_slaves = 0;
+	int changed = 0;
 	int idx;
 
 	if (!netif_is_lag_master(upper))
@@ -653,27 +654,27 @@ static int mlx5_handle_changeupper_event(struct mlx5_lag *ldev,
 	 */
 	is_in_lag = num_slaves == MLX5_MAX_PORTS && bond_status == 0x3;
 
-	if (!mlx5_lag_is_ready(ldev) && is_in_lag) {
-		NL_SET_ERR_MSG_MOD(info->info.extack,
-				   "Can't activate LAG offload, PF is configured with more than 64 VFs");
-		return 0;
-	}
-
 	/* Lag mode must be activebackup or hash. */
 	mode_supported = tracker->tx_type == NETDEV_LAG_TX_TYPE_ACTIVEBACKUP ||
 			 tracker->tx_type == NETDEV_LAG_TX_TYPE_HASH;
 
-	if (is_in_lag && !mode_supported)
-		NL_SET_ERR_MSG_MOD(info->info.extack,
-				   "Can't activate LAG offload, TX type isn't supported");
-
 	is_bonded = is_in_lag && mode_supported;
 	if (tracker->is_bonded != is_bonded) {
 		tracker->is_bonded = is_bonded;
-		return 1;
+		changed = 1;
 	}
 
-	return 0;
+	if (!is_in_lag)
+		return changed;
+
+	if (!mlx5_lag_is_ready(ldev))
+		NL_SET_ERR_MSG_MOD(info->info.extack,
+				   "Can't activate LAG offload, PF is configured with more than 64 VFs");
+	else if (!mode_supported)
+		NL_SET_ERR_MSG_MOD(info->info.extack,
+				   "Can't activate LAG offload, TX type isn't supported");
+
+	return changed;
 }
 
 static int mlx5_handle_changelowerstate_event(struct mlx5_lag *ldev,
@@ -716,9 +717,6 @@ static int mlx5_lag_netdev_event(struct notifier_block *this,
 
 	ldev    = container_of(this, struct mlx5_lag, nb);
 
-	if (!mlx5_lag_is_ready(ldev) && event == NETDEV_CHANGELOWERSTATE)
-		return NOTIFY_DONE;
-
 	tracker = ldev->tracker;
 
 	switch (event) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c
index ad63dd45c8fb..a6592f9c3c05 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c
@@ -608,4 +608,5 @@ void mlx5_lag_port_sel_destroy(struct mlx5_lag *ldev)
 	if (port_sel->tunnel)
 		mlx5_destroy_ttc_table(port_sel->inner.ttc);
 	mlx5_lag_destroy_definers(ldev);
+	memset(port_sel, 0, sizeof(*port_sel));
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c
index 97e5845b4cfd..d5e47630e284 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c
@@ -121,6 +121,9 @@ u32 mlx5_chains_get_nf_ft_chain(struct mlx5_fs_chains *chains)
 
 u32 mlx5_chains_get_prio_range(struct mlx5_fs_chains *chains)
 {
+	if (!mlx5_chains_prios_supported(chains))
+		return 1;
+
 	if (mlx5_chains_ignore_flow_level_supported(chains))
 		return UINT_MAX;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.c
index 0dd96a6b140d..c1df0d3595d8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.c
@@ -31,11 +31,11 @@ static void tout_set(struct mlx5_core_dev *dev, u64 val, enum mlx5_timeouts_type
 	dev->timeouts->to[type] = val;
 }
 
-static void tout_set_def_val(struct mlx5_core_dev *dev)
+void mlx5_tout_set_def_val(struct mlx5_core_dev *dev)
 {
 	int i;
 
-	for (i = MLX5_TO_FW_PRE_INIT_TIMEOUT_MS; i < MAX_TIMEOUT_TYPES; i++)
+	for (i = 0; i < MAX_TIMEOUT_TYPES; i++)
 		tout_set(dev, tout_def_sw_val[i], i);
 }
 
@@ -45,7 +45,6 @@ int mlx5_tout_init(struct mlx5_core_dev *dev)
 	if (!dev->timeouts)
 		return -ENOMEM;
 
-	tout_set_def_val(dev);
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.h
index 31faa5c17aa9..1c42ead782fa 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.h
@@ -34,6 +34,7 @@ int mlx5_tout_init(struct mlx5_core_dev *dev);
 void mlx5_tout_cleanup(struct mlx5_core_dev *dev);
 void mlx5_tout_query_iseg(struct mlx5_core_dev *dev);
 int mlx5_tout_query_dtor(struct mlx5_core_dev *dev);
+void mlx5_tout_set_def_val(struct mlx5_core_dev *dev);
 u64 _mlx5_tout_ms(struct mlx5_core_dev *dev, enum mlx5_timeouts_types type);
 
 #define mlx5_tout_ms(dev, type) _mlx5_tout_ms(dev, MLX5_TO_##type##_MS)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index a92a92a52346..65083496f913 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -992,11 +992,7 @@ static int mlx5_function_setup(struct mlx5_core_dev *dev, bool boot)
 	if (mlx5_core_is_pf(dev))
 		pcie_print_link_status(dev->pdev);
 
-	err = mlx5_tout_init(dev);
-	if (err) {
-		mlx5_core_err(dev, "Failed initializing timeouts, aborting\n");
-		return err;
-	}
+	mlx5_tout_set_def_val(dev);
 
 	/* wait for firmware to accept initialization segments configurations
 	 */
@@ -1005,13 +1001,13 @@ static int mlx5_function_setup(struct mlx5_core_dev *dev, bool boot)
 	if (err) {
 		mlx5_core_err(dev, "Firmware over %llu MS in pre-initializing state, aborting\n",
 			      mlx5_tout_ms(dev, FW_PRE_INIT_TIMEOUT));
-		goto err_tout_cleanup;
+		return err;
 	}
 
 	err = mlx5_cmd_init(dev);
 	if (err) {
 		mlx5_core_err(dev, "Failed initializing command interface, aborting\n");
-		goto err_tout_cleanup;
+		return err;
 	}
 
 	mlx5_tout_query_iseg(dev);
@@ -1075,18 +1071,16 @@ static int mlx5_function_setup(struct mlx5_core_dev *dev, bool boot)
 
 	mlx5_set_driver_version(dev);
 
-	mlx5_start_health_poll(dev);
-
 	err = mlx5_query_hca_caps(dev);
 	if (err) {
 		mlx5_core_err(dev, "query hca failed\n");
-		goto stop_health;
+		goto reclaim_boot_pages;
 	}
 
+	mlx5_start_health_poll(dev);
+
 	return 0;
 
-stop_health:
-	mlx5_stop_health_poll(dev, boot);
 reclaim_boot_pages:
 	mlx5_reclaim_startup_pages(dev);
 err_disable_hca:
@@ -1094,8 +1088,6 @@ err_disable_hca:
 err_cmd_cleanup:
 	mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_DOWN);
 	mlx5_cmd_cleanup(dev);
-err_tout_cleanup:
-	mlx5_tout_cleanup(dev);
 
 	return err;
 }
@@ -1114,7 +1106,6 @@ static int mlx5_function_teardown(struct mlx5_core_dev *dev, bool boot)
 	mlx5_core_disable_hca(dev, 0);
 	mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_DOWN);
 	mlx5_cmd_cleanup(dev);
-	mlx5_tout_cleanup(dev);
 
 	return 0;
 }
@@ -1476,6 +1467,12 @@ int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx)
 					    mlx5_debugfs_root);
 	INIT_LIST_HEAD(&priv->traps);
 
+	err = mlx5_tout_init(dev);
+	if (err) {
+		mlx5_core_err(dev, "Failed initializing timeouts, aborting\n");
+		goto err_timeout_init;
+	}
+
 	err = mlx5_health_init(dev);
 	if (err)
 		goto err_health_init;
@@ -1501,6 +1498,8 @@ err_adev_init:
 err_pagealloc_init:
 	mlx5_health_cleanup(dev);
 err_health_init:
+	mlx5_tout_cleanup(dev);
+err_timeout_init:
 	debugfs_remove(dev->priv.dbg_root);
 	mutex_destroy(&priv->pgdir_mutex);
 	mutex_destroy(&priv->alloc_mutex);
@@ -1518,6 +1517,7 @@ void mlx5_mdev_uninit(struct mlx5_core_dev *dev)
 	mlx5_adev_cleanup(dev);
 	mlx5_pagealloc_cleanup(dev);
 	mlx5_health_cleanup(dev);
+	mlx5_tout_cleanup(dev);
 	debugfs_remove_recursive(dev->priv.dbg_root);
 	mutex_destroy(&priv->pgdir_mutex);
 	mutex_destroy(&priv->alloc_mutex);
@@ -1809,12 +1809,13 @@ void mlx5_disable_device(struct mlx5_core_dev *dev)
 
 int mlx5_recover_device(struct mlx5_core_dev *dev)
 {
-	int ret = -EIO;
+	if (!mlx5_core_is_sf(dev)) {
+		mlx5_pci_disable_device(dev);
+		if (mlx5_pci_slot_reset(dev->pdev) != PCI_ERS_RESULT_RECOVERED)
+			return -EIO;
+	}
 
-	mlx5_pci_disable_device(dev);
-	if (mlx5_pci_slot_reset(dev->pdev) == PCI_ERS_RESULT_RECOVERED)
-		ret = mlx5_load_one(dev);
-	return ret;
+	return mlx5_load_one(dev);
 }
 
 static struct pci_driver mlx5_core_driver = {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
index 830444f927d4..bcee30f5de0a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
@@ -356,8 +356,8 @@ static struct mlx5_irq *irq_pool_request_affinity(struct mlx5_irq_pool *pool,
 	new_irq = irq_pool_create_irq(pool, affinity);
 	if (IS_ERR(new_irq)) {
 		if (!least_loaded_irq) {
-			mlx5_core_err(pool->dev, "Didn't find IRQ for cpu = %u\n",
-				      cpumask_first(affinity));
+			mlx5_core_err(pool->dev, "Didn't find a matching IRQ. err = %ld\n",
+				      PTR_ERR(new_irq));
 			mutex_unlock(&pool->lock);
 			return new_irq;
 		}
@@ -398,7 +398,7 @@ irq_pool_request_vector(struct mlx5_irq_pool *pool, int vecidx,
 	cpumask_copy(irq->mask, affinity);
 	if (!irq_pool_is_sf_pool(pool) && !pool->xa_num_irqs.max &&
 	    cpumask_empty(irq->mask))
-		cpumask_set_cpu(0, irq->mask);
+		cpumask_set_cpu(cpumask_first(cpu_online_mask), irq->mask);
 	irq_set_affinity_hint(irq->irqn, irq->mask);
 unlock:
 	mutex_unlock(&pool->lock);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c
index 49089cbe897c..c54cc45f63dc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c
@@ -2,6 +2,7 @@
 /* Copyright (c) 2019 Mellanox Technologies. */
 
 #include <linux/mlx5/eswitch.h>
+#include <linux/err.h>
 #include "dr_types.h"
 
 #define DR_DOMAIN_SW_STEERING_SUPPORTED(dmn, dmn_type)	\
@@ -72,9 +73,9 @@ static int dr_domain_init_resources(struct mlx5dr_domain *dmn)
 	}
 
 	dmn->uar = mlx5_get_uars_page(dmn->mdev);
-	if (!dmn->uar) {
+	if (IS_ERR(dmn->uar)) {
 		mlx5dr_err(dmn, "Couldn't allocate UAR\n");
-		ret = -ENOMEM;
+		ret = PTR_ERR(dmn->uar);
 		goto clean_pd;
 	}
 
@@ -135,25 +136,14 @@ static void dr_domain_fill_uplink_caps(struct mlx5dr_domain *dmn,
 
 static int dr_domain_query_vport(struct mlx5dr_domain *dmn,
 				 u16 vport_number,
+				 bool other_vport,
 				 struct mlx5dr_cmd_vport_cap *vport_caps)
 {
-	u16 cmd_vport = vport_number;
-	bool other_vport = true;
 	int ret;
 
-	if (vport_number == MLX5_VPORT_UPLINK) {
-		dr_domain_fill_uplink_caps(dmn, vport_caps);
-		return 0;
-	}
-
-	if (dmn->info.caps.is_ecpf && vport_number == MLX5_VPORT_ECPF) {
-		other_vport = false;
-		cmd_vport = 0;
-	}
-
 	ret = mlx5dr_cmd_query_esw_vport_context(dmn->mdev,
 						 other_vport,
-						 cmd_vport,
+						 vport_number,
 						 &vport_caps->icm_address_rx,
 						 &vport_caps->icm_address_tx);
 	if (ret)
@@ -161,7 +151,7 @@ static int dr_domain_query_vport(struct mlx5dr_domain *dmn,
 
 	ret = mlx5dr_cmd_query_gvmi(dmn->mdev,
 				    other_vport,
-				    cmd_vport,
+				    vport_number,
 				    &vport_caps->vport_gvmi);
 	if (ret)
 		return ret;
@@ -174,11 +164,15 @@ static int dr_domain_query_vport(struct mlx5dr_domain *dmn,
 
 static int dr_domain_query_esw_mngr(struct mlx5dr_domain *dmn)
 {
-	return dr_domain_query_vport(dmn,
-				     dmn->info.caps.is_ecpf ? MLX5_VPORT_ECPF : 0,
+	return dr_domain_query_vport(dmn, 0, false,
 				     &dmn->info.caps.vports.esw_manager_caps);
 }
 
+static void dr_domain_query_uplink(struct mlx5dr_domain *dmn)
+{
+	dr_domain_fill_uplink_caps(dmn, &dmn->info.caps.vports.uplink_caps);
+}
+
 static struct mlx5dr_cmd_vport_cap *
 dr_domain_add_vport_cap(struct mlx5dr_domain *dmn, u16 vport)
 {
@@ -190,7 +184,7 @@ dr_domain_add_vport_cap(struct mlx5dr_domain *dmn, u16 vport)
 	if (!vport_caps)
 		return NULL;
 
-	ret = dr_domain_query_vport(dmn, vport, vport_caps);
+	ret = dr_domain_query_vport(dmn, vport, true, vport_caps);
 	if (ret) {
 		kvfree(vport_caps);
 		return NULL;
@@ -207,16 +201,26 @@ dr_domain_add_vport_cap(struct mlx5dr_domain *dmn, u16 vport)
 	return vport_caps;
 }
 
+static bool dr_domain_is_esw_mgr_vport(struct mlx5dr_domain *dmn, u16 vport)
+{
+	struct mlx5dr_cmd_caps *caps = &dmn->info.caps;
+
+	return (caps->is_ecpf && vport == MLX5_VPORT_ECPF) ||
+	       (!caps->is_ecpf && vport == 0);
+}
+
 struct mlx5dr_cmd_vport_cap *
 mlx5dr_domain_get_vport_cap(struct mlx5dr_domain *dmn, u16 vport)
 {
 	struct mlx5dr_cmd_caps *caps = &dmn->info.caps;
 	struct mlx5dr_cmd_vport_cap *vport_caps;
 
-	if ((caps->is_ecpf && vport == MLX5_VPORT_ECPF) ||
-	    (!caps->is_ecpf && vport == 0))
+	if (dr_domain_is_esw_mgr_vport(dmn, vport))
 		return &caps->vports.esw_manager_caps;
 
+	if (vport == MLX5_VPORT_UPLINK)
+		return &caps->vports.uplink_caps;
+
 vport_load:
 	vport_caps = xa_load(&caps->vports.vports_caps_xa, vport);
 	if (vport_caps)
@@ -241,17 +245,6 @@ static void dr_domain_clear_vports(struct mlx5dr_domain *dmn)
 	}
 }
 
-static int dr_domain_query_uplink(struct mlx5dr_domain *dmn)
-{
-	struct mlx5dr_cmd_vport_cap *vport_caps;
-
-	vport_caps = mlx5dr_domain_get_vport_cap(dmn, MLX5_VPORT_UPLINK);
-	if (!vport_caps)
-		return -EINVAL;
-
-	return 0;
-}
-
 static int dr_domain_query_fdb_caps(struct mlx5_core_dev *mdev,
 				    struct mlx5dr_domain *dmn)
 {
@@ -281,11 +274,7 @@ static int dr_domain_query_fdb_caps(struct mlx5_core_dev *mdev,
 		goto free_vports_caps_xa;
 	}
 
-	ret = dr_domain_query_uplink(dmn);
-	if (ret) {
-		mlx5dr_err(dmn, "Failed to query uplink vport caps (err: %d)", ret);
-		goto free_vports_caps_xa;
-	}
+	dr_domain_query_uplink(dmn);
 
 	return 0;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c
index 75c775bee351..793365242e85 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c
@@ -924,11 +924,12 @@ static int dr_matcher_init(struct mlx5dr_matcher *matcher,
 
 	/* Check that all mask data was consumed */
 	for (i = 0; i < consumed_mask.match_sz; i++) {
-		if (consumed_mask.match_buf[i]) {
-			mlx5dr_dbg(dmn, "Match param mask contains unsupported parameters\n");
-			ret = -EOPNOTSUPP;
-			goto free_consumed_mask;
-		}
+		if (!((u8 *)consumed_mask.match_buf)[i])
+			continue;
+
+		mlx5dr_dbg(dmn, "Match param mask contains unsupported parameters\n");
+		ret = -EOPNOTSUPP;
+		goto free_consumed_mask;
 	}
 
 	ret =  0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h
index 3028b776da00..2333c2439c28 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h
@@ -764,6 +764,7 @@ struct mlx5dr_roce_cap {
 
 struct mlx5dr_vports {
 	struct mlx5dr_cmd_vport_cap esw_manager_caps;
+	struct mlx5dr_cmd_vport_cap uplink_caps;
 	struct xarray vports_caps_xa;
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 5925db386b1b..03e5bad4e405 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -2153,7 +2153,7 @@ static void mlxsw_sp_pude_event_func(const struct mlxsw_reg_info *reg,
 	max_ports = mlxsw_core_max_ports(mlxsw_sp->core);
 	local_port = mlxsw_reg_pude_local_port_get(pude_pl);
 
-	if (WARN_ON_ONCE(local_port >= max_ports))
+	if (WARN_ON_ONCE(!local_port || local_port >= max_ports))
 		return;
 	mlxsw_sp_port = mlxsw_sp->ports[local_port];
 	if (!mlxsw_sp_port)
@@ -3290,10 +3290,10 @@ mlxsw_sp_resources_rif_mac_profile_register(struct mlxsw_core *mlxsw_core)
 	u8 max_rif_mac_profiles;
 
 	if (!MLXSW_CORE_RES_VALID(mlxsw_core, MAX_RIF_MAC_PROFILES))
-		return -EIO;
-
-	max_rif_mac_profiles = MLXSW_CORE_RES_GET(mlxsw_core,
-						  MAX_RIF_MAC_PROFILES);
+		max_rif_mac_profiles = 1;
+	else
+		max_rif_mac_profiles = MLXSW_CORE_RES_GET(mlxsw_core,
+							  MAX_RIF_MAC_PROFILES);
 	devlink_resource_size_params_init(&size_params, max_rif_mac_profiles,
 					  max_rif_mac_profiles, 1,
 					  DEVLINK_RESOURCE_UNIT_ENTRY);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 217e3b351dfe..c34833ff1dde 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -8494,7 +8494,8 @@ mlxsw_sp_rif_mac_profile_replace(struct mlxsw_sp *mlxsw_sp,
 	u8 mac_profile;
 	int err;
 
-	if (!mlxsw_sp_rif_mac_profile_is_shared(rif))
+	if (!mlxsw_sp_rif_mac_profile_is_shared(rif) &&
+	    !mlxsw_sp_rif_mac_profile_find(mlxsw_sp, new_mac))
 		return mlxsw_sp_rif_mac_profile_edit(rif, new_mac);
 
 	err = mlxsw_sp_rif_mac_profile_get(mlxsw_sp, new_mac,
diff --git a/drivers/net/ethernet/micrel/ks8851_par.c b/drivers/net/ethernet/micrel/ks8851_par.c
index 2e25798c610e..7f49042484bd 100644
--- a/drivers/net/ethernet/micrel/ks8851_par.c
+++ b/drivers/net/ethernet/micrel/ks8851_par.c
@@ -321,6 +321,8 @@ static int ks8851_probe_par(struct platform_device *pdev)
 		return ret;
 
 	netdev->irq = platform_get_irq(pdev, 0);
+	if (netdev->irq < 0)
+		return netdev->irq;
 
 	return ks8851_probe_common(netdev, dev, msg_enable);
 }
diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c
index 4fc97823bc84..7d7647481f70 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.c
+++ b/drivers/net/ethernet/microchip/lan743x_main.c
@@ -914,8 +914,7 @@ static int lan743x_phy_reset(struct lan743x_adapter *adapter)
 }
 
 static void lan743x_phy_update_flowcontrol(struct lan743x_adapter *adapter,
-					   u8 duplex, u16 local_adv,
-					   u16 remote_adv)
+					   u16 local_adv, u16 remote_adv)
 {
 	struct lan743x_phy *phy = &adapter->phy;
 	u8 cap;
@@ -943,7 +942,6 @@ static void lan743x_phy_link_status_change(struct net_device *netdev)
 
 	phy_print_status(phydev);
 	if (phydev->state == PHY_RUNNING) {
-		struct ethtool_link_ksettings ksettings;
 		int remote_advertisement = 0;
 		int local_advertisement = 0;
 
@@ -980,18 +978,14 @@ static void lan743x_phy_link_status_change(struct net_device *netdev)
 		}
 		lan743x_csr_write(adapter, MAC_CR, data);
 
-		memset(&ksettings, 0, sizeof(ksettings));
-		phy_ethtool_get_link_ksettings(netdev, &ksettings);
 		local_advertisement =
 			linkmode_adv_to_mii_adv_t(phydev->advertising);
 		remote_advertisement =
 			linkmode_adv_to_mii_adv_t(phydev->lp_advertising);
 
-		lan743x_phy_update_flowcontrol(adapter,
-					       ksettings.base.duplex,
-					       local_advertisement,
+		lan743x_phy_update_flowcontrol(adapter, local_advertisement,
 					       remote_advertisement);
-		lan743x_ptp_update_latency(adapter, ksettings.base.speed);
+		lan743x_ptp_update_latency(adapter, phydev->speed);
 	}
 }
 
diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.c b/drivers/net/ethernet/microsoft/mana/hw_channel.c
index 34b971ff8ef8..078d6a5a0768 100644
--- a/drivers/net/ethernet/microsoft/mana/hw_channel.c
+++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c
@@ -480,16 +480,16 @@ static int mana_hwc_create_wq(struct hw_channel_context *hwc,
 	if (err)
 		goto out;
 
-	err = mana_hwc_alloc_dma_buf(hwc, q_depth, max_msg_size,
-				     &hwc_wq->msg_buf);
-	if (err)
-		goto out;
-
 	hwc_wq->hwc = hwc;
 	hwc_wq->gdma_wq = queue;
 	hwc_wq->queue_depth = q_depth;
 	hwc_wq->hwc_cq = hwc_cq;
 
+	err = mana_hwc_alloc_dma_buf(hwc, q_depth, max_msg_size,
+				     &hwc_wq->msg_buf);
+	if (err)
+		goto out;
+
 	*hwc_wq_ptr = hwc_wq;
 	return 0;
 out:
diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index e6c18b598d5c..1e4ad953cffb 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -1278,6 +1278,225 @@ int ocelot_fdb_dump(struct ocelot *ocelot, int port,
 }
 EXPORT_SYMBOL(ocelot_fdb_dump);
 
+static void ocelot_populate_l2_ptp_trap_key(struct ocelot_vcap_filter *trap)
+{
+	trap->key_type = OCELOT_VCAP_KEY_ETYPE;
+	*(__be16 *)trap->key.etype.etype.value = htons(ETH_P_1588);
+	*(__be16 *)trap->key.etype.etype.mask = htons(0xffff);
+}
+
+static void
+ocelot_populate_ipv4_ptp_event_trap_key(struct ocelot_vcap_filter *trap)
+{
+	trap->key_type = OCELOT_VCAP_KEY_IPV4;
+	trap->key.ipv4.dport.value = PTP_EV_PORT;
+	trap->key.ipv4.dport.mask = 0xffff;
+}
+
+static void
+ocelot_populate_ipv6_ptp_event_trap_key(struct ocelot_vcap_filter *trap)
+{
+	trap->key_type = OCELOT_VCAP_KEY_IPV6;
+	trap->key.ipv6.dport.value = PTP_EV_PORT;
+	trap->key.ipv6.dport.mask = 0xffff;
+}
+
+static void
+ocelot_populate_ipv4_ptp_general_trap_key(struct ocelot_vcap_filter *trap)
+{
+	trap->key_type = OCELOT_VCAP_KEY_IPV4;
+	trap->key.ipv4.dport.value = PTP_GEN_PORT;
+	trap->key.ipv4.dport.mask = 0xffff;
+}
+
+static void
+ocelot_populate_ipv6_ptp_general_trap_key(struct ocelot_vcap_filter *trap)
+{
+	trap->key_type = OCELOT_VCAP_KEY_IPV6;
+	trap->key.ipv6.dport.value = PTP_GEN_PORT;
+	trap->key.ipv6.dport.mask = 0xffff;
+}
+
+static int ocelot_trap_add(struct ocelot *ocelot, int port,
+			   unsigned long cookie,
+			   void (*populate)(struct ocelot_vcap_filter *f))
+{
+	struct ocelot_vcap_block *block_vcap_is2;
+	struct ocelot_vcap_filter *trap;
+	bool new = false;
+	int err;
+
+	block_vcap_is2 = &ocelot->block[VCAP_IS2];
+
+	trap = ocelot_vcap_block_find_filter_by_id(block_vcap_is2, cookie,
+						   false);
+	if (!trap) {
+		trap = kzalloc(sizeof(*trap), GFP_KERNEL);
+		if (!trap)
+			return -ENOMEM;
+
+		populate(trap);
+		trap->prio = 1;
+		trap->id.cookie = cookie;
+		trap->id.tc_offload = false;
+		trap->block_id = VCAP_IS2;
+		trap->type = OCELOT_VCAP_FILTER_OFFLOAD;
+		trap->lookup = 0;
+		trap->action.cpu_copy_ena = true;
+		trap->action.mask_mode = OCELOT_MASK_MODE_PERMIT_DENY;
+		trap->action.port_mask = 0;
+		new = true;
+	}
+
+	trap->ingress_port_mask |= BIT(port);
+
+	if (new)
+		err = ocelot_vcap_filter_add(ocelot, trap, NULL);
+	else
+		err = ocelot_vcap_filter_replace(ocelot, trap);
+	if (err) {
+		trap->ingress_port_mask &= ~BIT(port);
+		if (!trap->ingress_port_mask)
+			kfree(trap);
+		return err;
+	}
+
+	return 0;
+}
+
+static int ocelot_trap_del(struct ocelot *ocelot, int port,
+			   unsigned long cookie)
+{
+	struct ocelot_vcap_block *block_vcap_is2;
+	struct ocelot_vcap_filter *trap;
+
+	block_vcap_is2 = &ocelot->block[VCAP_IS2];
+
+	trap = ocelot_vcap_block_find_filter_by_id(block_vcap_is2, cookie,
+						   false);
+	if (!trap)
+		return 0;
+
+	trap->ingress_port_mask &= ~BIT(port);
+	if (!trap->ingress_port_mask)
+		return ocelot_vcap_filter_del(ocelot, trap);
+
+	return ocelot_vcap_filter_replace(ocelot, trap);
+}
+
+static int ocelot_l2_ptp_trap_add(struct ocelot *ocelot, int port)
+{
+	unsigned long l2_cookie = ocelot->num_phys_ports + 1;
+
+	return ocelot_trap_add(ocelot, port, l2_cookie,
+			       ocelot_populate_l2_ptp_trap_key);
+}
+
+static int ocelot_l2_ptp_trap_del(struct ocelot *ocelot, int port)
+{
+	unsigned long l2_cookie = ocelot->num_phys_ports + 1;
+
+	return ocelot_trap_del(ocelot, port, l2_cookie);
+}
+
+static int ocelot_ipv4_ptp_trap_add(struct ocelot *ocelot, int port)
+{
+	unsigned long ipv4_gen_cookie = ocelot->num_phys_ports + 2;
+	unsigned long ipv4_ev_cookie = ocelot->num_phys_ports + 3;
+	int err;
+
+	err = ocelot_trap_add(ocelot, port, ipv4_ev_cookie,
+			      ocelot_populate_ipv4_ptp_event_trap_key);
+	if (err)
+		return err;
+
+	err = ocelot_trap_add(ocelot, port, ipv4_gen_cookie,
+			      ocelot_populate_ipv4_ptp_general_trap_key);
+	if (err)
+		ocelot_trap_del(ocelot, port, ipv4_ev_cookie);
+
+	return err;
+}
+
+static int ocelot_ipv4_ptp_trap_del(struct ocelot *ocelot, int port)
+{
+	unsigned long ipv4_gen_cookie = ocelot->num_phys_ports + 2;
+	unsigned long ipv4_ev_cookie = ocelot->num_phys_ports + 3;
+	int err;
+
+	err = ocelot_trap_del(ocelot, port, ipv4_ev_cookie);
+	err |= ocelot_trap_del(ocelot, port, ipv4_gen_cookie);
+	return err;
+}
+
+static int ocelot_ipv6_ptp_trap_add(struct ocelot *ocelot, int port)
+{
+	unsigned long ipv6_gen_cookie = ocelot->num_phys_ports + 4;
+	unsigned long ipv6_ev_cookie = ocelot->num_phys_ports + 5;
+	int err;
+
+	err = ocelot_trap_add(ocelot, port, ipv6_ev_cookie,
+			      ocelot_populate_ipv6_ptp_event_trap_key);
+	if (err)
+		return err;
+
+	err = ocelot_trap_add(ocelot, port, ipv6_gen_cookie,
+			      ocelot_populate_ipv6_ptp_general_trap_key);
+	if (err)
+		ocelot_trap_del(ocelot, port, ipv6_ev_cookie);
+
+	return err;
+}
+
+static int ocelot_ipv6_ptp_trap_del(struct ocelot *ocelot, int port)
+{
+	unsigned long ipv6_gen_cookie = ocelot->num_phys_ports + 4;
+	unsigned long ipv6_ev_cookie = ocelot->num_phys_ports + 5;
+	int err;
+
+	err = ocelot_trap_del(ocelot, port, ipv6_ev_cookie);
+	err |= ocelot_trap_del(ocelot, port, ipv6_gen_cookie);
+	return err;
+}
+
+static int ocelot_setup_ptp_traps(struct ocelot *ocelot, int port,
+				  bool l2, bool l4)
+{
+	int err;
+
+	if (l2)
+		err = ocelot_l2_ptp_trap_add(ocelot, port);
+	else
+		err = ocelot_l2_ptp_trap_del(ocelot, port);
+	if (err)
+		return err;
+
+	if (l4) {
+		err = ocelot_ipv4_ptp_trap_add(ocelot, port);
+		if (err)
+			goto err_ipv4;
+
+		err = ocelot_ipv6_ptp_trap_add(ocelot, port);
+		if (err)
+			goto err_ipv6;
+	} else {
+		err = ocelot_ipv4_ptp_trap_del(ocelot, port);
+
+		err |= ocelot_ipv6_ptp_trap_del(ocelot, port);
+	}
+	if (err)
+		return err;
+
+	return 0;
+
+err_ipv6:
+	ocelot_ipv4_ptp_trap_del(ocelot, port);
+err_ipv4:
+	if (l2)
+		ocelot_l2_ptp_trap_del(ocelot, port);
+	return err;
+}
+
 int ocelot_hwstamp_get(struct ocelot *ocelot, int port, struct ifreq *ifr)
 {
 	return copy_to_user(ifr->ifr_data, &ocelot->hwtstamp_config,
@@ -1288,7 +1507,9 @@ EXPORT_SYMBOL(ocelot_hwstamp_get);
 int ocelot_hwstamp_set(struct ocelot *ocelot, int port, struct ifreq *ifr)
 {
 	struct ocelot_port *ocelot_port = ocelot->ports[port];
+	bool l2 = false, l4 = false;
 	struct hwtstamp_config cfg;
+	int err;
 
 	if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg)))
 		return -EFAULT;
@@ -1320,28 +1541,42 @@ int ocelot_hwstamp_set(struct ocelot *ocelot, int port, struct ifreq *ifr)
 	switch (cfg.rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
 		break;
-	case HWTSTAMP_FILTER_ALL:
-	case HWTSTAMP_FILTER_SOME:
-	case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
-	case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
-	case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
-	case HWTSTAMP_FILTER_NTP_ALL:
 	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
 	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
+		l4 = true;
+		break;
 	case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
 	case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ:
+		l2 = true;
+		break;
 	case HWTSTAMP_FILTER_PTP_V2_EVENT:
 	case HWTSTAMP_FILTER_PTP_V2_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
-		cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
+		l2 = true;
+		l4 = true;
 		break;
 	default:
 		mutex_unlock(&ocelot->ptp_lock);
 		return -ERANGE;
 	}
 
+	err = ocelot_setup_ptp_traps(ocelot, port, l2, l4);
+	if (err) {
+		mutex_unlock(&ocelot->ptp_lock);
+		return err;
+	}
+
+	if (l2 && l4)
+		cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
+	else if (l2)
+		cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_EVENT;
+	else if (l4)
+		cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_L4_EVENT;
+	else
+		cfg.rx_filter = HWTSTAMP_FILTER_NONE;
+
 	/* Commit back the result & save it */
 	memcpy(&ocelot->hwtstamp_config, &cfg, sizeof(cfg));
 	mutex_unlock(&ocelot->ptp_lock);
@@ -1444,7 +1679,10 @@ int ocelot_get_ts_info(struct ocelot *ocelot, int port,
 				 SOF_TIMESTAMPING_RAW_HARDWARE;
 	info->tx_types = BIT(HWTSTAMP_TX_OFF) | BIT(HWTSTAMP_TX_ON) |
 			 BIT(HWTSTAMP_TX_ONESTEP_SYNC);
-	info->rx_filters = BIT(HWTSTAMP_FILTER_NONE) | BIT(HWTSTAMP_FILTER_ALL);
+	info->rx_filters = BIT(HWTSTAMP_FILTER_NONE) |
+			   BIT(HWTSTAMP_FILTER_PTP_V2_EVENT) |
+			   BIT(HWTSTAMP_FILTER_PTP_V2_L2_EVENT) |
+			   BIT(HWTSTAMP_FILTER_PTP_V2_L4_EVENT);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/mscc/ocelot_vcap.c b/drivers/net/ethernet/mscc/ocelot_vcap.c
index 99d7376a70a7..337cd08b1a54 100644
--- a/drivers/net/ethernet/mscc/ocelot_vcap.c
+++ b/drivers/net/ethernet/mscc/ocelot_vcap.c
@@ -1217,6 +1217,22 @@ int ocelot_vcap_filter_del(struct ocelot *ocelot,
 }
 EXPORT_SYMBOL(ocelot_vcap_filter_del);
 
+int ocelot_vcap_filter_replace(struct ocelot *ocelot,
+			       struct ocelot_vcap_filter *filter)
+{
+	struct ocelot_vcap_block *block = &ocelot->block[filter->block_id];
+	int index;
+
+	index = ocelot_vcap_block_get_filter_index(block, filter);
+	if (index < 0)
+		return index;
+
+	vcap_entry_set(ocelot, index, filter);
+
+	return 0;
+}
+EXPORT_SYMBOL(ocelot_vcap_filter_replace);
+
 int ocelot_vcap_filter_stats_update(struct ocelot *ocelot,
 				    struct ocelot_vcap_filter *filter)
 {
diff --git a/drivers/net/ethernet/natsemi/xtsonic.c b/drivers/net/ethernet/natsemi/xtsonic.c
index ca4686094701..0a02d8bd0a3e 100644
--- a/drivers/net/ethernet/natsemi/xtsonic.c
+++ b/drivers/net/ethernet/natsemi/xtsonic.c
@@ -120,7 +120,7 @@ static const struct net_device_ops xtsonic_netdev_ops = {
 	.ndo_set_mac_address	= eth_mac_addr,
 };
 
-static int __init sonic_probe1(struct net_device *dev)
+static int sonic_probe1(struct net_device *dev)
 {
 	unsigned int silicon_revision;
 	struct sonic_local *lp = netdev_priv(dev);
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h
index df203738511b..0b1865e9f0b5 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h
@@ -565,7 +565,6 @@ struct nfp_net_dp {
  * @exn_name:           Name for Exception interrupt
  * @shared_handler:     Handler for shared interrupts
  * @shared_name:        Name for shared interrupt
- * @me_freq_mhz:        ME clock_freq (MHz)
  * @reconfig_lock:	Protects @reconfig_posted, @reconfig_timer_active,
  *			@reconfig_sync_present and HW reconfiguration request
  *			regs/machinery from async requests (sync must take
@@ -650,8 +649,6 @@ struct nfp_net {
 	irq_handler_t shared_handler;
 	char shared_name[IFNAMSIZ + 8];
 
-	u32 me_freq_mhz;
-
 	bool link_up;
 	spinlock_t link_status_lock;
 
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
index 1de076f55740..cf7882933993 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
@@ -1344,7 +1344,7 @@ static int nfp_net_set_coalesce(struct net_device *netdev,
 	 * ME timestamp ticks.  There are 16 ME clock cycles for each timestamp
 	 * count.
 	 */
-	factor = nn->me_freq_mhz / 16;
+	factor = nn->tlv_caps.me_freq_mhz / 16;
 
 	/* Each pair of (usecs, max_frames) fields specifies that interrupts
 	 * should be coalesced until
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cppcore.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cppcore.c
index d7ac0307797f..34c0d2ddf9ef 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cppcore.c
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cppcore.c
@@ -803,8 +803,10 @@ int nfp_cpp_area_cache_add(struct nfp_cpp *cpp, size_t size)
 		return -ENOMEM;
 
 	cache = kzalloc(sizeof(*cache), GFP_KERNEL);
-	if (!cache)
+	if (!cache) {
+		nfp_cpp_area_free(area);
 		return -ENOMEM;
+	}
 
 	cache->id = 0;
 	cache->addr = 0;
diff --git a/drivers/net/ethernet/ni/nixge.c b/drivers/net/ethernet/ni/nixge.c
index cfeb7620ae20..07a00dd9cfe0 100644
--- a/drivers/net/ethernet/ni/nixge.c
+++ b/drivers/net/ethernet/ni/nixge.c
@@ -1209,7 +1209,7 @@ static void *nixge_get_nvmem_address(struct device *dev)
 
 	cell = nvmem_cell_get(dev, "address");
 	if (IS_ERR(cell))
-		return NULL;
+		return cell;
 
 	mac = nvmem_cell_read(cell, &cell_size);
 	nvmem_cell_put(cell);
@@ -1282,7 +1282,7 @@ static int nixge_probe(struct platform_device *pdev)
 	ndev->max_mtu = NIXGE_JUMBO_MTU;
 
 	mac_addr = nixge_get_nvmem_address(&pdev->dev);
-	if (mac_addr && is_valid_ether_addr(mac_addr)) {
+	if (!IS_ERR(mac_addr) && is_valid_ether_addr(mac_addr)) {
 		eth_hw_addr_set(ndev, mac_addr);
 		kfree(mac_addr);
 	} else {
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
index 63f8a8163b5f..2ff7be17e5af 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
@@ -3135,7 +3135,7 @@ int ionic_lif_init(struct ionic_lif *lif)
 		return -EINVAL;
 	}
 
-	lif->dbid_inuse = bitmap_alloc(lif->dbid_count, GFP_KERNEL);
+	lif->dbid_inuse = bitmap_zalloc(lif->dbid_count, GFP_KERNEL);
 	if (!lif->dbid_inuse) {
 		dev_err(dev, "Failed alloc doorbell id bitmap, aborting\n");
 		return -ENOMEM;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.c b/drivers/net/ethernet/qlogic/qed/qed_int.c
index a97f691839e0..6958adeca86d 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_int.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_int.c
@@ -1045,7 +1045,7 @@ static int qed_int_deassertion(struct qed_hwfn  *p_hwfn,
 		if (!parities)
 			continue;
 
-		for (j = 0, bit_idx = 0; bit_idx < 32; j++) {
+		for (j = 0, bit_idx = 0; bit_idx < 32 && j < 32; j++) {
 			struct aeu_invert_reg_bit *p_bit = &p_aeu->bits[j];
 
 			if (qed_int_is_parity_flag(p_hwfn, p_bit) &&
@@ -1083,7 +1083,7 @@ static int qed_int_deassertion(struct qed_hwfn  *p_hwfn,
 			 * to current group, making them responsible for the
 			 * previous assertion.
 			 */
-			for (j = 0, bit_idx = 0; bit_idx < 32; j++) {
+			for (j = 0, bit_idx = 0; bit_idx < 32 && j < 32; j++) {
 				long unsigned int bitmask;
 				u8 bit, bit_len;
 
@@ -1382,7 +1382,7 @@ static void qed_int_sb_attn_init(struct qed_hwfn *p_hwfn,
 	memset(sb_info->parity_mask, 0, sizeof(u32) * NUM_ATTN_REGS);
 	for (i = 0; i < NUM_ATTN_REGS; i++) {
 		/* j is array index, k is bit index */
-		for (j = 0, k = 0; k < 32; j++) {
+		for (j = 0, k = 0; k < 32 && j < 32; j++) {
 			struct aeu_invert_reg_bit *p_aeu;
 
 			p_aeu = &aeu_descs[i].bits[j];
diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c
index 065e9004598e..999abcfe3310 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_fp.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c
@@ -1643,6 +1643,13 @@ netdev_tx_t qede_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 			data_split = true;
 		}
 	} else {
+		if (unlikely(skb->len > ETH_TX_MAX_NON_LSO_PKT_LEN)) {
+			DP_ERR(edev, "Unexpected non LSO skb length = 0x%x\n", skb->len);
+			qede_free_failed_tx_pkt(txq, first_bd, 0, false);
+			qede_update_tx_producer(txq);
+			return NETDEV_TX_OK;
+		}
+
 		val |= ((skb->len & ETH_TX_DATA_1ST_BD_PKT_LEN_MASK) <<
 			 ETH_TX_DATA_1ST_BD_PKT_LEN_SHIFT);
 	}
diff --git a/drivers/net/ethernet/qlogic/qla3xxx.c b/drivers/net/ethernet/qlogic/qla3xxx.c
index 1e6d72adfe43..71523d747e93 100644
--- a/drivers/net/ethernet/qlogic/qla3xxx.c
+++ b/drivers/net/ethernet/qlogic/qla3xxx.c
@@ -3480,20 +3480,19 @@ static int ql_adapter_up(struct ql3_adapter *qdev)
 
 	spin_lock_irqsave(&qdev->hw_lock, hw_flags);
 
-	err = ql_wait_for_drvr_lock(qdev);
-	if (err) {
-		err = ql_adapter_initialize(qdev);
-		if (err) {
-			netdev_err(ndev, "Unable to initialize adapter\n");
-			goto err_init;
-		}
-		netdev_err(ndev, "Releasing driver lock\n");
-		ql_sem_unlock(qdev, QL_DRVR_SEM_MASK);
-	} else {
+	if (!ql_wait_for_drvr_lock(qdev)) {
 		netdev_err(ndev, "Could not acquire driver lock\n");
+		err = -ENODEV;
 		goto err_lock;
 	}
 
+	err = ql_adapter_initialize(qdev);
+	if (err) {
+		netdev_err(ndev, "Unable to initialize adapter\n");
+		goto err_init;
+	}
+	ql_sem_unlock(qdev, QL_DRVR_SEM_MASK);
+
 	spin_unlock_irqrestore(&qdev->hw_lock, hw_flags);
 
 	set_bit(QL_ADAPTER_UP, &qdev->flags);
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
index d51bac7ba5af..bd0607680329 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
@@ -1077,8 +1077,14 @@ static int qlcnic_83xx_add_rings(struct qlcnic_adapter *adapter)
 	sds_mbx_size = sizeof(struct qlcnic_sds_mbx);
 	context_id = recv_ctx->context_id;
 	num_sds = adapter->drv_sds_rings - QLCNIC_MAX_SDS_RINGS;
-	ahw->hw_ops->alloc_mbx_args(&cmd, adapter,
-				    QLCNIC_CMD_ADD_RCV_RINGS);
+	err = ahw->hw_ops->alloc_mbx_args(&cmd, adapter,
+					QLCNIC_CMD_ADD_RCV_RINGS);
+	if (err) {
+		dev_err(&adapter->pdev->dev,
+			"Failed to alloc mbx args %d\n", err);
+		return err;
+	}
+
 	cmd.req.arg[1] = 0 | (num_sds << 8) | (context_id << 16);
 
 	/* set up status rings, mbx 2-81 */
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov.h
index 7160b42f51dd..d0111cb3b40e 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov.h
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov.h
@@ -201,7 +201,7 @@ int qlcnic_sriov_get_vf_vport_info(struct qlcnic_adapter *,
 				   struct qlcnic_info *, u16);
 int qlcnic_sriov_cfg_vf_guest_vlan(struct qlcnic_adapter *, u16, u8);
 void qlcnic_sriov_free_vlans(struct qlcnic_adapter *);
-void qlcnic_sriov_alloc_vlans(struct qlcnic_adapter *);
+int qlcnic_sriov_alloc_vlans(struct qlcnic_adapter *);
 bool qlcnic_sriov_check_any_vlan(struct qlcnic_vf_info *);
 void qlcnic_sriov_del_vlan_id(struct qlcnic_sriov *,
 			      struct qlcnic_vf_info *, u16);
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c
index dd03be3fc82a..42a44c97572a 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c
@@ -432,7 +432,7 @@ static int qlcnic_sriov_set_guest_vlan_mode(struct qlcnic_adapter *adapter,
 					    struct qlcnic_cmd_args *cmd)
 {
 	struct qlcnic_sriov *sriov = adapter->ahw->sriov;
-	int i, num_vlans;
+	int i, num_vlans, ret;
 	u16 *vlans;
 
 	if (sriov->allowed_vlans)
@@ -443,7 +443,9 @@ static int qlcnic_sriov_set_guest_vlan_mode(struct qlcnic_adapter *adapter,
 	dev_info(&adapter->pdev->dev, "Number of allowed Guest VLANs = %d\n",
 		 sriov->num_allowed_vlans);
 
-	qlcnic_sriov_alloc_vlans(adapter);
+	ret = qlcnic_sriov_alloc_vlans(adapter);
+	if (ret)
+		return ret;
 
 	if (!sriov->any_vlan)
 		return 0;
@@ -2154,7 +2156,7 @@ static int qlcnic_sriov_vf_resume(struct qlcnic_adapter *adapter)
 	return err;
 }
 
-void qlcnic_sriov_alloc_vlans(struct qlcnic_adapter *adapter)
+int qlcnic_sriov_alloc_vlans(struct qlcnic_adapter *adapter)
 {
 	struct qlcnic_sriov *sriov = adapter->ahw->sriov;
 	struct qlcnic_vf_info *vf;
@@ -2164,7 +2166,11 @@ void qlcnic_sriov_alloc_vlans(struct qlcnic_adapter *adapter)
 		vf = &sriov->vf_info[i];
 		vf->sriov_vlans = kcalloc(sriov->num_allowed_vlans,
 					  sizeof(*vf->sriov_vlans), GFP_KERNEL);
+		if (!vf->sriov_vlans)
+			return -ENOMEM;
 	}
+
+	return 0;
 }
 
 void qlcnic_sriov_free_vlans(struct qlcnic_adapter *adapter)
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c
index 447720b93e5a..e90fa97c0ae6 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c
@@ -597,7 +597,9 @@ static int __qlcnic_pci_sriov_enable(struct qlcnic_adapter *adapter,
 	if (err)
 		goto del_flr_queue;
 
-	qlcnic_sriov_alloc_vlans(adapter);
+	err = qlcnic_sriov_alloc_vlans(adapter);
+	if (err)
+		goto del_flr_queue;
 
 	return err;
 
diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index bbe21db20417..86c44bc5f73f 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -5217,8 +5217,8 @@ static int rtl_get_ether_clk(struct rtl8169_private *tp)
 
 static void rtl_init_mac_address(struct rtl8169_private *tp)
 {
+	u8 mac_addr[ETH_ALEN] __aligned(2) = {};
 	struct net_device *dev = tp->dev;
-	u8 mac_addr[ETH_ALEN];
 	int rc;
 
 	rc = eth_platform_get_mac_address(tp_to_dev(tp), mac_addr);
@@ -5233,7 +5233,8 @@ static void rtl_init_mac_address(struct rtl8169_private *tp)
 	if (is_valid_ether_addr(mac_addr))
 		goto done;
 
-	eth_hw_addr_random(dev);
+	eth_random_addr(mac_addr);
+	dev->addr_assign_type = NET_ADDR_RANDOM;
 	dev_warn(tp_to_dev(tp), "can't read MAC address, setting random one\n");
 done:
 	eth_hw_addr_set(dev, mac_addr);
diff --git a/drivers/net/ethernet/sfc/ef100_nic.c b/drivers/net/ethernet/sfc/ef100_nic.c
index 6aa81229b68a..e77a5cb4e40d 100644
--- a/drivers/net/ethernet/sfc/ef100_nic.c
+++ b/drivers/net/ethernet/sfc/ef100_nic.c
@@ -609,6 +609,9 @@ static size_t ef100_update_stats(struct efx_nic *efx,
 	ef100_common_stat_mask(mask);
 	ef100_ethtool_stat_mask(mask);
 
+	if (!mc_stats)
+		return 0;
+
 	efx_nic_copy_stats(efx, mc_stats);
 	efx_nic_update_stats(ef100_stat_desc, EF100_STAT_COUNT, mask,
 			     stats, mc_stats, false);
diff --git a/drivers/net/ethernet/sfc/falcon/rx.c b/drivers/net/ethernet/sfc/falcon/rx.c
index 966f13e7475d..11a6aee852e9 100644
--- a/drivers/net/ethernet/sfc/falcon/rx.c
+++ b/drivers/net/ethernet/sfc/falcon/rx.c
@@ -728,7 +728,10 @@ static void ef4_init_rx_recycle_ring(struct ef4_nic *efx,
 					    efx->rx_bufs_per_page);
 	rx_queue->page_ring = kcalloc(page_ring_size,
 				      sizeof(*rx_queue->page_ring), GFP_KERNEL);
-	rx_queue->page_ptr_mask = page_ring_size - 1;
+	if (!rx_queue->page_ring)
+		rx_queue->page_ptr_mask = 0;
+	else
+		rx_queue->page_ptr_mask = page_ring_size - 1;
 }
 
 void ef4_init_rx_queue(struct ef4_rx_queue *rx_queue)
diff --git a/drivers/net/ethernet/sfc/rx_common.c b/drivers/net/ethernet/sfc/rx_common.c
index 68fc7d317693..0983abc0cc5f 100644
--- a/drivers/net/ethernet/sfc/rx_common.c
+++ b/drivers/net/ethernet/sfc/rx_common.c
@@ -150,7 +150,10 @@ static void efx_init_rx_recycle_ring(struct efx_rx_queue *rx_queue)
 					    efx->rx_bufs_per_page);
 	rx_queue->page_ring = kcalloc(page_ring_size,
 				      sizeof(*rx_queue->page_ring), GFP_KERNEL);
-	rx_queue->page_ptr_mask = page_ring_size - 1;
+	if (!rx_queue->page_ring)
+		rx_queue->page_ptr_mask = 0;
+	else
+		rx_queue->page_ptr_mask = page_ring_size - 1;
 }
 
 static void efx_fini_rx_recycle_ring(struct efx_rx_queue *rx_queue)
diff --git a/drivers/net/ethernet/sis/sis900.c b/drivers/net/ethernet/sis/sis900.c
index cc2d907c4c4b..23a336c5096e 100644
--- a/drivers/net/ethernet/sis/sis900.c
+++ b/drivers/net/ethernet/sis/sis900.c
@@ -392,7 +392,7 @@ static int sis96x_get_mac_addr(struct pci_dev *pci_dev,
 			/* get MAC address from EEPROM */
 			for (i = 0; i < 3; i++)
 			        addr[i] = read_eeprom(ioaddr, i + EEPROMMACAddr);
-			 eth_hw_addr_set(net_dev, (u8 *)addr);
+			eth_hw_addr_set(net_dev, (u8 *)addr);
 
 			rc = 1;
 			break;
diff --git a/drivers/net/ethernet/smsc/smc911x.c b/drivers/net/ethernet/smsc/smc911x.c
index 89381f796985..dd6f69ced4ee 100644
--- a/drivers/net/ethernet/smsc/smc911x.c
+++ b/drivers/net/ethernet/smsc/smc911x.c
@@ -2072,6 +2072,11 @@ static int smc911x_drv_probe(struct platform_device *pdev)
 
 	ndev->dma = (unsigned char)-1;
 	ndev->irq = platform_get_irq(pdev, 0);
+	if (ndev->irq < 0) {
+		ret = ndev->irq;
+		goto release_both;
+	}
+
 	lp = netdev_priv(ndev);
 	lp->netdev = ndev;
 #ifdef SMC_DYNAMIC_BUS_CONFIG
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
index 6924a6aacbd5..c469abc91fa1 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
@@ -33,6 +33,7 @@ struct rk_gmac_ops {
 	void (*set_rgmii_speed)(struct rk_priv_data *bsp_priv, int speed);
 	void (*set_rmii_speed)(struct rk_priv_data *bsp_priv, int speed);
 	void (*integrated_phy_powerup)(struct rk_priv_data *bsp_priv);
+	bool regs_valid;
 	u32 regs[];
 };
 
@@ -1092,6 +1093,7 @@ static const struct rk_gmac_ops rk3568_ops = {
 	.set_to_rmii = rk3568_set_to_rmii,
 	.set_rgmii_speed = rk3568_set_gmac_speed,
 	.set_rmii_speed = rk3568_set_gmac_speed,
+	.regs_valid = true,
 	.regs = {
 		0xfe2a0000, /* gmac0 */
 		0xfe010000, /* gmac1 */
@@ -1383,7 +1385,7 @@ static struct rk_priv_data *rk_gmac_setup(struct platform_device *pdev,
 	 * to be distinguished.
 	 */
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (res) {
+	if (res && ops->regs_valid) {
 		int i = 0;
 
 		while (ops->regs[i]) {
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c
index 85208128f135..b7c2579c963b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c
@@ -485,8 +485,28 @@ static int socfpga_dwmac_resume(struct device *dev)
 }
 #endif /* CONFIG_PM_SLEEP */
 
-static SIMPLE_DEV_PM_OPS(socfpga_dwmac_pm_ops, stmmac_suspend,
-					       socfpga_dwmac_resume);
+static int __maybe_unused socfpga_dwmac_runtime_suspend(struct device *dev)
+{
+	struct net_device *ndev = dev_get_drvdata(dev);
+	struct stmmac_priv *priv = netdev_priv(ndev);
+
+	stmmac_bus_clks_config(priv, false);
+
+	return 0;
+}
+
+static int __maybe_unused socfpga_dwmac_runtime_resume(struct device *dev)
+{
+	struct net_device *ndev = dev_get_drvdata(dev);
+	struct stmmac_priv *priv = netdev_priv(ndev);
+
+	return stmmac_bus_clks_config(priv, true);
+}
+
+static const struct dev_pm_ops socfpga_dwmac_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(stmmac_suspend, socfpga_dwmac_resume)
+	SET_RUNTIME_PM_OPS(socfpga_dwmac_runtime_suspend, socfpga_dwmac_runtime_resume, NULL)
+};
 
 static const struct socfpga_dwmac_ops socfpga_gen5_ops = {
 	.set_phy_mode = socfpga_gen5_set_phy_mode,
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c
index 66fc8be34bb7..e2e0f977875d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c
@@ -26,7 +26,7 @@
 #define ETHER_CLK_SEL_FREQ_SEL_125M	(BIT(9) | BIT(8))
 #define ETHER_CLK_SEL_FREQ_SEL_50M	BIT(9)
 #define ETHER_CLK_SEL_FREQ_SEL_25M	BIT(8)
-#define ETHER_CLK_SEL_FREQ_SEL_2P5M	BIT(0)
+#define ETHER_CLK_SEL_FREQ_SEL_2P5M	0
 #define ETHER_CLK_SEL_TX_CLK_EXT_SEL_IN BIT(0)
 #define ETHER_CLK_SEL_TX_CLK_EXT_SEL_TXC BIT(10)
 #define ETHER_CLK_SEL_TX_CLK_EXT_SEL_DIV BIT(11)
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index 43eead726886..873b9e3e5da2 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -172,6 +172,19 @@ struct stmmac_flow_entry {
 	int is_l4;
 };
 
+/* Rx Frame Steering */
+enum stmmac_rfs_type {
+	STMMAC_RFS_T_VLAN,
+	STMMAC_RFS_T_MAX,
+};
+
+struct stmmac_rfs_entry {
+	unsigned long cookie;
+	int in_use;
+	int type;
+	int tc;
+};
+
 struct stmmac_priv {
 	/* Frequently used values are kept adjacent for cache effect */
 	u32 tx_coal_frames[MTL_MAX_TX_QUEUES];
@@ -289,6 +302,10 @@ struct stmmac_priv {
 	struct stmmac_tc_entry *tc_entries;
 	unsigned int flow_entries_max;
 	struct stmmac_flow_entry *flow_entries;
+	unsigned int rfs_entries_max[STMMAC_RFS_T_MAX];
+	unsigned int rfs_entries_cnt[STMMAC_RFS_T_MAX];
+	unsigned int rfs_entries_total;
+	struct stmmac_rfs_entry *rfs_entries;
 
 	/* Pulse Per Second output */
 	struct stmmac_pps_cfg pps[STMMAC_PPS_MAX];
@@ -314,6 +331,7 @@ int stmmac_mdio_reset(struct mii_bus *mii);
 int stmmac_xpcs_setup(struct mii_bus *mii);
 void stmmac_set_ethtool_ops(struct net_device *netdev);
 
+int stmmac_init_tstamp_counter(struct stmmac_priv *priv, u32 systime_flags);
 void stmmac_ptp_register(struct stmmac_priv *priv);
 void stmmac_ptp_unregister(struct stmmac_priv *priv);
 int stmmac_open(struct net_device *dev);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index d3f350c25b9b..8ded4be08b00 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -50,6 +50,13 @@
 #include "dwxgmac2.h"
 #include "hwif.h"
 
+/* As long as the interface is active, we keep the timestamping counter enabled
+ * with fine resolution and binary rollover. This avoid non-monotonic behavior
+ * (clock jumps) when changing timestamping settings at runtime.
+ */
+#define STMMAC_HWTS_ACTIVE	(PTP_TCR_TSENA | PTP_TCR_TSCFUPDT | \
+				 PTP_TCR_TSCTRLSSR)
+
 #define	STMMAC_ALIGN(x)		ALIGN(ALIGN(x, SMP_CACHE_BYTES), 16)
 #define	TSO_MAX_BUFF_SIZE	(SZ_16K - 1)
 
@@ -511,6 +518,14 @@ bool stmmac_eee_init(struct stmmac_priv *priv)
 	return true;
 }
 
+static inline u32 stmmac_cdc_adjust(struct stmmac_priv *priv)
+{
+	/* Correct the clk domain crossing(CDC) error */
+	if (priv->plat->has_gmac4 && priv->plat->clk_ptp_rate)
+		return (2 * NSEC_PER_SEC) / priv->plat->clk_ptp_rate;
+	return 0;
+}
+
 /* stmmac_get_tx_hwtstamp - get HW TX timestamps
  * @priv: driver private structure
  * @p : descriptor pointer
@@ -524,7 +539,6 @@ static void stmmac_get_tx_hwtstamp(struct stmmac_priv *priv,
 {
 	struct skb_shared_hwtstamps shhwtstamp;
 	bool found = false;
-	s64 adjust = 0;
 	u64 ns = 0;
 
 	if (!priv->hwts_tx_en)
@@ -543,12 +557,7 @@ static void stmmac_get_tx_hwtstamp(struct stmmac_priv *priv,
 	}
 
 	if (found) {
-		/* Correct the clk domain crossing(CDC) error */
-		if (priv->plat->has_gmac4 && priv->plat->clk_ptp_rate) {
-			adjust += -(2 * (NSEC_PER_SEC /
-					 priv->plat->clk_ptp_rate));
-			ns += adjust;
-		}
+		ns -= stmmac_cdc_adjust(priv);
 
 		memset(&shhwtstamp, 0, sizeof(struct skb_shared_hwtstamps));
 		shhwtstamp.hwtstamp = ns_to_ktime(ns);
@@ -573,7 +582,6 @@ static void stmmac_get_rx_hwtstamp(struct stmmac_priv *priv, struct dma_desc *p,
 {
 	struct skb_shared_hwtstamps *shhwtstamp = NULL;
 	struct dma_desc *desc = p;
-	u64 adjust = 0;
 	u64 ns = 0;
 
 	if (!priv->hwts_rx_en)
@@ -586,11 +594,7 @@ static void stmmac_get_rx_hwtstamp(struct stmmac_priv *priv, struct dma_desc *p,
 	if (stmmac_get_rx_timestamp_status(priv, p, np, priv->adv_ts)) {
 		stmmac_get_timestamp(priv, desc, priv->adv_ts, &ns);
 
-		/* Correct the clk domain crossing(CDC) error */
-		if (priv->plat->has_gmac4 && priv->plat->clk_ptp_rate) {
-			adjust += 2 * (NSEC_PER_SEC / priv->plat->clk_ptp_rate);
-			ns -= adjust;
-		}
+		ns -= stmmac_cdc_adjust(priv);
 
 		netdev_dbg(priv->dev, "get valid RX hw timestamp %llu\n", ns);
 		shhwtstamp = skb_hwtstamps(skb);
@@ -616,8 +620,6 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
 	struct hwtstamp_config config;
-	struct timespec64 now;
-	u64 temp = 0;
 	u32 ptp_v2 = 0;
 	u32 tstamp_all = 0;
 	u32 ptp_over_ipv4_udp = 0;
@@ -626,11 +628,6 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 	u32 snap_type_sel = 0;
 	u32 ts_master_en = 0;
 	u32 ts_event_en = 0;
-	u32 sec_inc = 0;
-	u32 value = 0;
-	bool xmac;
-
-	xmac = priv->plat->has_gmac4 || priv->plat->has_xgmac;
 
 	if (!(priv->dma_cap.time_stamp || priv->adv_ts)) {
 		netdev_alert(priv->dev, "No support for HW time stamping\n");
@@ -792,42 +789,17 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 	priv->hwts_rx_en = ((config.rx_filter == HWTSTAMP_FILTER_NONE) ? 0 : 1);
 	priv->hwts_tx_en = config.tx_type == HWTSTAMP_TX_ON;
 
-	if (!priv->hwts_tx_en && !priv->hwts_rx_en)
-		stmmac_config_hw_tstamping(priv, priv->ptpaddr, 0);
-	else {
-		value = (PTP_TCR_TSENA | PTP_TCR_TSCFUPDT | PTP_TCR_TSCTRLSSR |
-			 tstamp_all | ptp_v2 | ptp_over_ethernet |
-			 ptp_over_ipv6_udp | ptp_over_ipv4_udp | ts_event_en |
-			 ts_master_en | snap_type_sel);
-		stmmac_config_hw_tstamping(priv, priv->ptpaddr, value);
-
-		/* program Sub Second Increment reg */
-		stmmac_config_sub_second_increment(priv,
-				priv->ptpaddr, priv->plat->clk_ptp_rate,
-				xmac, &sec_inc);
-		temp = div_u64(1000000000ULL, sec_inc);
-
-		/* Store sub second increment and flags for later use */
-		priv->sub_second_inc = sec_inc;
-		priv->systime_flags = value;
-
-		/* calculate default added value:
-		 * formula is :
-		 * addend = (2^32)/freq_div_ratio;
-		 * where, freq_div_ratio = 1e9ns/sec_inc
-		 */
-		temp = (u64)(temp << 32);
-		priv->default_addend = div_u64(temp, priv->plat->clk_ptp_rate);
-		stmmac_config_addend(priv, priv->ptpaddr, priv->default_addend);
-
-		/* initialize system time */
-		ktime_get_real_ts64(&now);
+	priv->systime_flags = STMMAC_HWTS_ACTIVE;
 
-		/* lower 32 bits of tv_sec are safe until y2106 */
-		stmmac_init_systime(priv, priv->ptpaddr,
-				(u32)now.tv_sec, now.tv_nsec);
+	if (priv->hwts_tx_en || priv->hwts_rx_en) {
+		priv->systime_flags |= tstamp_all | ptp_v2 |
+				       ptp_over_ethernet | ptp_over_ipv6_udp |
+				       ptp_over_ipv4_udp | ts_event_en |
+				       ts_master_en | snap_type_sel;
 	}
 
+	stmmac_config_hw_tstamping(priv, priv->ptpaddr, priv->systime_flags);
+
 	memcpy(&priv->tstamp_config, &config, sizeof(config));
 
 	return copy_to_user(ifr->ifr_data, &config,
@@ -856,6 +828,66 @@ static int stmmac_hwtstamp_get(struct net_device *dev, struct ifreq *ifr)
 }
 
 /**
+ * stmmac_init_tstamp_counter - init hardware timestamping counter
+ * @priv: driver private structure
+ * @systime_flags: timestamping flags
+ * Description:
+ * Initialize hardware counter for packet timestamping.
+ * This is valid as long as the interface is open and not suspended.
+ * Will be rerun after resuming from suspend, case in which the timestamping
+ * flags updated by stmmac_hwtstamp_set() also need to be restored.
+ */
+int stmmac_init_tstamp_counter(struct stmmac_priv *priv, u32 systime_flags)
+{
+	bool xmac = priv->plat->has_gmac4 || priv->plat->has_xgmac;
+	struct timespec64 now;
+	u32 sec_inc = 0;
+	u64 temp = 0;
+	int ret;
+
+	if (!(priv->dma_cap.time_stamp || priv->dma_cap.atime_stamp))
+		return -EOPNOTSUPP;
+
+	ret = clk_prepare_enable(priv->plat->clk_ptp_ref);
+	if (ret < 0) {
+		netdev_warn(priv->dev,
+			    "failed to enable PTP reference clock: %pe\n",
+			    ERR_PTR(ret));
+		return ret;
+	}
+
+	stmmac_config_hw_tstamping(priv, priv->ptpaddr, systime_flags);
+	priv->systime_flags = systime_flags;
+
+	/* program Sub Second Increment reg */
+	stmmac_config_sub_second_increment(priv, priv->ptpaddr,
+					   priv->plat->clk_ptp_rate,
+					   xmac, &sec_inc);
+	temp = div_u64(1000000000ULL, sec_inc);
+
+	/* Store sub second increment for later use */
+	priv->sub_second_inc = sec_inc;
+
+	/* calculate default added value:
+	 * formula is :
+	 * addend = (2^32)/freq_div_ratio;
+	 * where, freq_div_ratio = 1e9ns/sec_inc
+	 */
+	temp = (u64)(temp << 32);
+	priv->default_addend = div_u64(temp, priv->plat->clk_ptp_rate);
+	stmmac_config_addend(priv, priv->ptpaddr, priv->default_addend);
+
+	/* initialize system time */
+	ktime_get_real_ts64(&now);
+
+	/* lower 32 bits of tv_sec are safe until y2106 */
+	stmmac_init_systime(priv, priv->ptpaddr, (u32)now.tv_sec, now.tv_nsec);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(stmmac_init_tstamp_counter);
+
+/**
  * stmmac_init_ptp - init PTP
  * @priv: driver private structure
  * Description: this is to verify if the HW supports the PTPv1 or PTPv2.
@@ -865,9 +897,11 @@ static int stmmac_hwtstamp_get(struct net_device *dev, struct ifreq *ifr)
 static int stmmac_init_ptp(struct stmmac_priv *priv)
 {
 	bool xmac = priv->plat->has_gmac4 || priv->plat->has_xgmac;
+	int ret;
 
-	if (!(priv->dma_cap.time_stamp || priv->dma_cap.atime_stamp))
-		return -EOPNOTSUPP;
+	ret = stmmac_init_tstamp_counter(priv, STMMAC_HWTS_ACTIVE);
+	if (ret)
+		return ret;
 
 	priv->adv_ts = 0;
 	/* Check if adv_ts can be enabled for dwmac 4.x / xgmac core */
@@ -1427,16 +1461,20 @@ static int stmmac_init_rx_buffers(struct stmmac_priv *priv, struct dma_desc *p,
 {
 	struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
 	struct stmmac_rx_buffer *buf = &rx_q->buf_pool[i];
+	gfp_t gfp = (GFP_ATOMIC | __GFP_NOWARN);
+
+	if (priv->dma_cap.addr64 <= 32)
+		gfp |= GFP_DMA32;
 
 	if (!buf->page) {
-		buf->page = page_pool_dev_alloc_pages(rx_q->page_pool);
+		buf->page = page_pool_alloc_pages(rx_q->page_pool, gfp);
 		if (!buf->page)
 			return -ENOMEM;
 		buf->page_offset = stmmac_rx_offset(priv);
 	}
 
 	if (priv->sph && !buf->sec_page) {
-		buf->sec_page = page_pool_dev_alloc_pages(rx_q->page_pool);
+		buf->sec_page = page_pool_alloc_pages(rx_q->page_pool, gfp);
 		if (!buf->sec_page)
 			return -ENOMEM;
 
@@ -3275,10 +3313,6 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp)
 	stmmac_mmc_setup(priv);
 
 	if (init_ptp) {
-		ret = clk_prepare_enable(priv->plat->clk_ptp_ref);
-		if (ret < 0)
-			netdev_warn(priv->dev, "failed to enable PTP reference clock: %d\n", ret);
-
 		ret = stmmac_init_ptp(priv);
 		if (ret == -EOPNOTSUPP)
 			netdev_warn(priv->dev, "PTP not supported by HW\n");
@@ -3772,6 +3806,8 @@ int stmmac_release(struct net_device *dev)
 	struct stmmac_priv *priv = netdev_priv(dev);
 	u32 chan;
 
+	netif_tx_disable(dev);
+
 	if (device_may_wakeup(priv->device))
 		phylink_speed_down(priv->phylink, false);
 	/* Stop and disconnect the PHY */
@@ -4450,6 +4486,10 @@ static inline void stmmac_rx_refill(struct stmmac_priv *priv, u32 queue)
 	struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
 	int dirty = stmmac_rx_dirty(priv, queue);
 	unsigned int entry = rx_q->dirty_rx;
+	gfp_t gfp = (GFP_ATOMIC | __GFP_NOWARN);
+
+	if (priv->dma_cap.addr64 <= 32)
+		gfp |= GFP_DMA32;
 
 	while (dirty-- > 0) {
 		struct stmmac_rx_buffer *buf = &rx_q->buf_pool[entry];
@@ -4462,13 +4502,13 @@ static inline void stmmac_rx_refill(struct stmmac_priv *priv, u32 queue)
 			p = rx_q->dma_rx + entry;
 
 		if (!buf->page) {
-			buf->page = page_pool_dev_alloc_pages(rx_q->page_pool);
+			buf->page = page_pool_alloc_pages(rx_q->page_pool, gfp);
 			if (!buf->page)
 				break;
 		}
 
 		if (priv->sph && !buf->sec_page) {
-			buf->sec_page = page_pool_dev_alloc_pages(rx_q->page_pool);
+			buf->sec_page = page_pool_alloc_pages(rx_q->page_pool, gfp);
 			if (!buf->sec_page)
 				break;
 
@@ -5164,12 +5204,13 @@ read_again:
 		if (likely(!(status & rx_not_ls)) &&
 		    (likely(priv->synopsys_id >= DWMAC_CORE_4_00) ||
 		     unlikely(status != llc_snap))) {
-			if (buf2_len)
+			if (buf2_len) {
 				buf2_len -= ETH_FCS_LEN;
-			else
+				len -= ETH_FCS_LEN;
+			} else if (buf1_len) {
 				buf1_len -= ETH_FCS_LEN;
-
-			len -= ETH_FCS_LEN;
+				len -= ETH_FCS_LEN;
+			}
 		}
 
 		if (!skb) {
@@ -5507,8 +5548,6 @@ static int stmmac_set_features(struct net_device *netdev,
 			       netdev_features_t features)
 {
 	struct stmmac_priv *priv = netdev_priv(netdev);
-	bool sph_en;
-	u32 chan;
 
 	/* Keep the COE Type in case of csum is supporting */
 	if (features & NETIF_F_RXCSUM)
@@ -5520,10 +5559,13 @@ static int stmmac_set_features(struct net_device *netdev,
 	 */
 	stmmac_rx_ipc(priv, priv->hw);
 
-	sph_en = (priv->hw->rx_csum > 0) && priv->sph;
+	if (priv->sph_cap) {
+		bool sph_en = (priv->hw->rx_csum > 0) && priv->sph;
+		u32 chan;
 
-	for (chan = 0; chan < priv->plat->rx_queues_to_use; chan++)
-		stmmac_enable_sph(priv, priv->ioaddr, sph_en, chan);
+		for (chan = 0; chan < priv->plat->rx_queues_to_use; chan++)
+			stmmac_enable_sph(priv, priv->ioaddr, sph_en, chan);
+	}
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index 232ac98943cd..5d29f336315b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -816,7 +816,7 @@ static int __maybe_unused stmmac_pltfr_noirq_resume(struct device *dev)
 		if (ret)
 			return ret;
 
-		clk_prepare_enable(priv->plat->clk_ptp_ref);
+		stmmac_init_tstamp_counter(priv, priv->systime_flags);
 	}
 
 	return 0;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
index 580cc035536b..be9b58b2abf9 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
@@ -102,7 +102,7 @@ static int stmmac_adjust_time(struct ptp_clock_info *ptp, s64 delta)
 		time.tv_nsec = priv->plat->est->btr_reserve[0];
 		time.tv_sec = priv->plat->est->btr_reserve[1];
 		basetime = timespec64_to_ktime(time);
-		cycle_time = priv->plat->est->ctr[1] * NSEC_PER_SEC +
+		cycle_time = (u64)priv->plat->est->ctr[1] * NSEC_PER_SEC +
 			     priv->plat->est->ctr[0];
 		time = stmmac_calc_tas_basetime(basetime,
 						current_time_ns,
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
index 1c4ea0b1b845..d0a2b289f460 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
@@ -232,11 +232,33 @@ static int tc_setup_cls_u32(struct stmmac_priv *priv,
 	}
 }
 
+static int tc_rfs_init(struct stmmac_priv *priv)
+{
+	int i;
+
+	priv->rfs_entries_max[STMMAC_RFS_T_VLAN] = 8;
+
+	for (i = 0; i < STMMAC_RFS_T_MAX; i++)
+		priv->rfs_entries_total += priv->rfs_entries_max[i];
+
+	priv->rfs_entries = devm_kcalloc(priv->device,
+					 priv->rfs_entries_total,
+					 sizeof(*priv->rfs_entries),
+					 GFP_KERNEL);
+	if (!priv->rfs_entries)
+		return -ENOMEM;
+
+	dev_info(priv->device, "Enabled RFS Flow TC (entries=%d)\n",
+		 priv->rfs_entries_total);
+
+	return 0;
+}
+
 static int tc_init(struct stmmac_priv *priv)
 {
 	struct dma_features *dma_cap = &priv->dma_cap;
 	unsigned int count;
-	int i;
+	int ret, i;
 
 	if (dma_cap->l3l4fnum) {
 		priv->flow_entries_max = dma_cap->l3l4fnum;
@@ -250,10 +272,14 @@ static int tc_init(struct stmmac_priv *priv)
 		for (i = 0; i < priv->flow_entries_max; i++)
 			priv->flow_entries[i].idx = i;
 
-		dev_info(priv->device, "Enabled Flow TC (entries=%d)\n",
+		dev_info(priv->device, "Enabled L3L4 Flow TC (entries=%d)\n",
 			 priv->flow_entries_max);
 	}
 
+	ret = tc_rfs_init(priv);
+	if (ret)
+		return -ENOMEM;
+
 	if (!priv->plat->fpe_cfg) {
 		priv->plat->fpe_cfg = devm_kzalloc(priv->device,
 						   sizeof(*priv->plat->fpe_cfg),
@@ -607,16 +633,45 @@ static int tc_del_flow(struct stmmac_priv *priv,
 	return ret;
 }
 
+static struct stmmac_rfs_entry *tc_find_rfs(struct stmmac_priv *priv,
+					    struct flow_cls_offload *cls,
+					    bool get_free)
+{
+	int i;
+
+	for (i = 0; i < priv->rfs_entries_total; i++) {
+		struct stmmac_rfs_entry *entry = &priv->rfs_entries[i];
+
+		if (entry->cookie == cls->cookie)
+			return entry;
+		if (get_free && entry->in_use == false)
+			return entry;
+	}
+
+	return NULL;
+}
+
 #define VLAN_PRIO_FULL_MASK (0x07)
 
 static int tc_add_vlan_flow(struct stmmac_priv *priv,
 			    struct flow_cls_offload *cls)
 {
+	struct stmmac_rfs_entry *entry = tc_find_rfs(priv, cls, false);
 	struct flow_rule *rule = flow_cls_offload_flow_rule(cls);
 	struct flow_dissector *dissector = rule->match.dissector;
 	int tc = tc_classid_to_hwtc(priv->dev, cls->classid);
 	struct flow_match_vlan match;
 
+	if (!entry) {
+		entry = tc_find_rfs(priv, cls, true);
+		if (!entry)
+			return -ENOENT;
+	}
+
+	if (priv->rfs_entries_cnt[STMMAC_RFS_T_VLAN] >=
+	    priv->rfs_entries_max[STMMAC_RFS_T_VLAN])
+		return -ENOENT;
+
 	/* Nothing to do here */
 	if (!dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_VLAN))
 		return -EINVAL;
@@ -638,6 +693,12 @@ static int tc_add_vlan_flow(struct stmmac_priv *priv,
 
 		prio = BIT(match.key->vlan_priority);
 		stmmac_rx_queue_prio(priv, priv->hw, prio, tc);
+
+		entry->in_use = true;
+		entry->cookie = cls->cookie;
+		entry->tc = tc;
+		entry->type = STMMAC_RFS_T_VLAN;
+		priv->rfs_entries_cnt[STMMAC_RFS_T_VLAN]++;
 	}
 
 	return 0;
@@ -646,20 +707,19 @@ static int tc_add_vlan_flow(struct stmmac_priv *priv,
 static int tc_del_vlan_flow(struct stmmac_priv *priv,
 			    struct flow_cls_offload *cls)
 {
-	struct flow_rule *rule = flow_cls_offload_flow_rule(cls);
-	struct flow_dissector *dissector = rule->match.dissector;
-	int tc = tc_classid_to_hwtc(priv->dev, cls->classid);
+	struct stmmac_rfs_entry *entry = tc_find_rfs(priv, cls, false);
 
-	/* Nothing to do here */
-	if (!dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_VLAN))
-		return -EINVAL;
+	if (!entry || !entry->in_use || entry->type != STMMAC_RFS_T_VLAN)
+		return -ENOENT;
 
-	if (tc < 0) {
-		netdev_err(priv->dev, "Invalid traffic class\n");
-		return -EINVAL;
-	}
+	stmmac_rx_queue_prio(priv, priv->hw, 0, entry->tc);
+
+	entry->in_use = false;
+	entry->cookie = 0;
+	entry->tc = 0;
+	entry->type = 0;
 
-	stmmac_rx_queue_prio(priv, priv->hw, 0, tc);
+	priv->rfs_entries_cnt[STMMAC_RFS_T_VLAN]--;
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
index c092cb61416a..ffbbda8f4d41 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
@@ -1844,13 +1844,14 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common)
 		if (ret < 0) {
 			dev_err(dev, "%pOF error reading port_id %d\n",
 				port_np, ret);
-			return ret;
+			goto of_node_put;
 		}
 
 		if (!port_id || port_id > common->port_num) {
 			dev_err(dev, "%pOF has invalid port_id %u %s\n",
 				port_np, port_id, port_np->name);
-			return -EINVAL;
+			ret = -EINVAL;
+			goto of_node_put;
 		}
 
 		port = am65_common_get_port(common, port_id);
@@ -1866,8 +1867,10 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common)
 				(AM65_CPSW_NU_FRAM_PORT_OFFSET * (port_id - 1));
 
 		port->slave.mac_sl = cpsw_sl_get("am65", dev, port->port_base);
-		if (IS_ERR(port->slave.mac_sl))
-			return PTR_ERR(port->slave.mac_sl);
+		if (IS_ERR(port->slave.mac_sl)) {
+			ret = PTR_ERR(port->slave.mac_sl);
+			goto of_node_put;
+		}
 
 		port->disabled = !of_device_is_available(port_np);
 		if (port->disabled) {
@@ -1880,7 +1883,7 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common)
 			ret = PTR_ERR(port->slave.ifphy);
 			dev_err(dev, "%pOF error retrieving port phy: %d\n",
 				port_np, ret);
-			return ret;
+			goto of_node_put;
 		}
 
 		port->slave.mac_only =
@@ -1889,10 +1892,12 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common)
 		/* get phy/link info */
 		if (of_phy_is_fixed_link(port_np)) {
 			ret = of_phy_register_fixed_link(port_np);
-			if (ret)
-				return dev_err_probe(dev, ret,
+			if (ret) {
+				ret = dev_err_probe(dev, ret,
 						     "failed to register fixed-link phy %pOF\n",
 						     port_np);
+				goto of_node_put;
+			}
 			port->slave.phy_node = of_node_get(port_np);
 		} else {
 			port->slave.phy_node =
@@ -1902,14 +1907,15 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common)
 		if (!port->slave.phy_node) {
 			dev_err(dev,
 				"slave[%d] no phy found\n", port_id);
-			return -ENODEV;
+			ret = -ENODEV;
+			goto of_node_put;
 		}
 
 		ret = of_get_phy_mode(port_np, &port->slave.phy_if);
 		if (ret) {
 			dev_err(dev, "%pOF read phy-mode err %d\n",
 				port_np, ret);
-			return ret;
+			goto of_node_put;
 		}
 
 		ret = of_get_mac_address(port_np, port->slave.mac_addr);
@@ -1932,6 +1938,11 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common)
 	}
 
 	return 0;
+
+of_node_put:
+	of_node_put(port_np);
+	of_node_put(node);
+	return ret;
 }
 
 static void am65_cpsw_pcpu_stats_free(void *data)
diff --git a/drivers/net/fjes/fjes_main.c b/drivers/net/fjes/fjes_main.c
index b06c17ac8d4e..ebd287039a54 100644
--- a/drivers/net/fjes/fjes_main.c
+++ b/drivers/net/fjes/fjes_main.c
@@ -1262,6 +1262,11 @@ static int fjes_probe(struct platform_device *plat_dev)
 	hw->hw_res.start = res->start;
 	hw->hw_res.size = resource_size(res);
 	hw->hw_res.irq = platform_get_irq(plat_dev, 0);
+	if (hw->hw_res.irq < 0) {
+		err = hw->hw_res.irq;
+		goto err_free_control_wq;
+	}
+
 	err = fjes_hw_init(&adapter->hw);
 	if (err)
 		goto err_free_control_wq;
diff --git a/drivers/net/hamradio/6pack.c b/drivers/net/hamradio/6pack.c
index bfdf89e54752..8a19a06b505d 100644
--- a/drivers/net/hamradio/6pack.c
+++ b/drivers/net/hamradio/6pack.c
@@ -306,7 +306,6 @@ static void sp_setup(struct net_device *dev)
 {
 	/* Finish setting up the DEVICE info. */
 	dev->netdev_ops		= &sp_netdev_ops;
-	dev->needs_free_netdev	= true;
 	dev->mtu		= SIXP_MTU;
 	dev->hard_header_len	= AX25_MAX_HEADER_LEN;
 	dev->header_ops 	= &ax25_header_ops;
diff --git a/drivers/net/hamradio/mkiss.c b/drivers/net/hamradio/mkiss.c
index e2b332b54f06..edde9c3ae12b 100644
--- a/drivers/net/hamradio/mkiss.c
+++ b/drivers/net/hamradio/mkiss.c
@@ -31,6 +31,8 @@
 
 #define AX_MTU		236
 
+/* some arch define END as assembly function ending, just undef it */
+#undef	END
 /* SLIP/KISS protocol characters. */
 #define END             0300		/* indicates end of frame	*/
 #define ESC             0333		/* indicates byte stuffing	*/
@@ -792,14 +794,14 @@ static void mkiss_close(struct tty_struct *tty)
 	 */
 	netif_stop_queue(ax->dev);
 
-	ax->tty = NULL;
-
 	unregister_netdev(ax->dev);
 
 	/* Free all AX25 frame buffers after unreg. */
 	kfree(ax->rbuff);
 	kfree(ax->xbuff);
 
+	ax->tty = NULL;
+
 	free_netdev(ax->dev);
 }
 
diff --git a/drivers/net/ipa/ipa_cmd.c b/drivers/net/ipa/ipa_cmd.c
index cff51731195a..d57472ea077f 100644
--- a/drivers/net/ipa/ipa_cmd.c
+++ b/drivers/net/ipa/ipa_cmd.c
@@ -661,22 +661,6 @@ void ipa_cmd_pipeline_clear_wait(struct ipa *ipa)
 	wait_for_completion(&ipa->completion);
 }
 
-void ipa_cmd_pipeline_clear(struct ipa *ipa)
-{
-	u32 count = ipa_cmd_pipeline_clear_count();
-	struct gsi_trans *trans;
-
-	trans = ipa_cmd_trans_alloc(ipa, count);
-	if (trans) {
-		ipa_cmd_pipeline_clear_add(trans);
-		gsi_trans_commit_wait(trans);
-		ipa_cmd_pipeline_clear_wait(ipa);
-	} else {
-		dev_err(&ipa->pdev->dev,
-			"error allocating %u entry tag transaction\n", count);
-	}
-}
-
 static struct ipa_cmd_info *
 ipa_cmd_info_alloc(struct ipa_endpoint *endpoint, u32 tre_count)
 {
diff --git a/drivers/net/ipa/ipa_cmd.h b/drivers/net/ipa/ipa_cmd.h
index 69cd085d427d..05ed7e42e184 100644
--- a/drivers/net/ipa/ipa_cmd.h
+++ b/drivers/net/ipa/ipa_cmd.h
@@ -164,12 +164,6 @@ u32 ipa_cmd_pipeline_clear_count(void);
 void ipa_cmd_pipeline_clear_wait(struct ipa *ipa);
 
 /**
- * ipa_cmd_pipeline_clear() - Clear the hardware pipeline
- * @ipa:	- IPA pointer
- */
-void ipa_cmd_pipeline_clear(struct ipa *ipa);
-
-/**
  * ipa_cmd_trans_alloc() - Allocate a transaction for the command TX endpoint
  * @ipa:	IPA pointer
  * @tre_count:	Number of elements in the transaction
diff --git a/drivers/net/ipa/ipa_endpoint.c b/drivers/net/ipa/ipa_endpoint.c
index 5528d97110d5..03a170993420 100644
--- a/drivers/net/ipa/ipa_endpoint.c
+++ b/drivers/net/ipa/ipa_endpoint.c
@@ -853,6 +853,7 @@ static void ipa_endpoint_init_hol_block_timer(struct ipa_endpoint *endpoint,
 	u32 offset;
 	u32 val;
 
+	/* This should only be changed when HOL_BLOCK_EN is disabled */
 	offset = IPA_REG_ENDP_INIT_HOL_BLOCK_TIMER_N_OFFSET(endpoint_id);
 	val = hol_block_timer_val(ipa, microseconds);
 	iowrite32(val, ipa->reg_virt + offset);
@@ -868,6 +869,9 @@ ipa_endpoint_init_hol_block_enable(struct ipa_endpoint *endpoint, bool enable)
 	val = enable ? HOL_BLOCK_EN_FMASK : 0;
 	offset = IPA_REG_ENDP_INIT_HOL_BLOCK_EN_N_OFFSET(endpoint_id);
 	iowrite32(val, endpoint->ipa->reg_virt + offset);
+	/* When enabling, the register must be written twice for IPA v4.5+ */
+	if (enable && endpoint->ipa->version >= IPA_VERSION_4_5)
+		iowrite32(val, endpoint->ipa->reg_virt + offset);
 }
 
 void ipa_endpoint_modem_hol_block_clear_all(struct ipa *ipa)
@@ -880,6 +884,7 @@ void ipa_endpoint_modem_hol_block_clear_all(struct ipa *ipa)
 		if (endpoint->toward_ipa || endpoint->ee_id != GSI_EE_MODEM)
 			continue;
 
+		ipa_endpoint_init_hol_block_enable(endpoint, false);
 		ipa_endpoint_init_hol_block_timer(endpoint, 0);
 		ipa_endpoint_init_hol_block_enable(endpoint, true);
 	}
@@ -1631,8 +1636,6 @@ void ipa_endpoint_suspend(struct ipa *ipa)
 	if (ipa->modem_netdev)
 		ipa_modem_suspend(ipa->modem_netdev);
 
-	ipa_cmd_pipeline_clear(ipa);
-
 	ipa_endpoint_suspend_one(ipa->name_map[IPA_ENDPOINT_AP_LAN_RX]);
 	ipa_endpoint_suspend_one(ipa->name_map[IPA_ENDPOINT_AP_COMMAND_TX]);
 }
diff --git a/drivers/net/ipa/ipa_main.c b/drivers/net/ipa/ipa_main.c
index cdfa98a76e1f..a448ec198bee 100644
--- a/drivers/net/ipa/ipa_main.c
+++ b/drivers/net/ipa/ipa_main.c
@@ -28,6 +28,7 @@
 #include "ipa_reg.h"
 #include "ipa_mem.h"
 #include "ipa_table.h"
+#include "ipa_smp2p.h"
 #include "ipa_modem.h"
 #include "ipa_uc.h"
 #include "ipa_interrupt.h"
@@ -801,6 +802,11 @@ static int ipa_remove(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	int ret;
 
+	/* Prevent the modem from triggering a call to ipa_setup().  This
+	 * also ensures a modem-initiated setup that's underway completes.
+	 */
+	ipa_smp2p_irq_disable_setup(ipa);
+
 	ret = pm_runtime_get_sync(dev);
 	if (WARN_ON(ret < 0))
 		goto out_power_put;
diff --git a/drivers/net/ipa/ipa_modem.c b/drivers/net/ipa/ipa_modem.c
index ad116bcc0580..d0ab4d70c303 100644
--- a/drivers/net/ipa/ipa_modem.c
+++ b/drivers/net/ipa/ipa_modem.c
@@ -339,9 +339,6 @@ int ipa_modem_stop(struct ipa *ipa)
 	if (state != IPA_MODEM_STATE_RUNNING)
 		return -EBUSY;
 
-	/* Prevent the modem from triggering a call to ipa_setup() */
-	ipa_smp2p_disable(ipa);
-
 	/* Clean up the netdev and endpoints if it was started */
 	if (netdev) {
 		struct ipa_priv *priv = netdev_priv(netdev);
@@ -369,6 +366,9 @@ static void ipa_modem_crashed(struct ipa *ipa)
 	struct device *dev = &ipa->pdev->dev;
 	int ret;
 
+	/* Prevent the modem from triggering a call to ipa_setup() */
+	ipa_smp2p_irq_disable_setup(ipa);
+
 	ret = pm_runtime_get_sync(dev);
 	if (ret < 0) {
 		dev_err(dev, "error %d getting power to handle crash\n", ret);
diff --git a/drivers/net/ipa/ipa_resource.c b/drivers/net/ipa/ipa_resource.c
index e3da95d69409..06cec7199382 100644
--- a/drivers/net/ipa/ipa_resource.c
+++ b/drivers/net/ipa/ipa_resource.c
@@ -52,7 +52,7 @@ static bool ipa_resource_limits_valid(struct ipa *ipa,
 				return false;
 	}
 
-	group_count = data->rsrc_group_src_count;
+	group_count = data->rsrc_group_dst_count;
 	if (!group_count || group_count > IPA_RESOURCE_GROUP_MAX)
 		return false;
 
diff --git a/drivers/net/ipa/ipa_smp2p.c b/drivers/net/ipa/ipa_smp2p.c
index df7639c39d71..211233612039 100644
--- a/drivers/net/ipa/ipa_smp2p.c
+++ b/drivers/net/ipa/ipa_smp2p.c
@@ -53,7 +53,7 @@
  * @setup_ready_irq:	IPA interrupt triggered by modem to signal GSI ready
  * @power_on:		Whether IPA power is on
  * @notified:		Whether modem has been notified of power state
- * @disabled:		Whether setup ready interrupt handling is disabled
+ * @setup_disabled:	Whether setup ready interrupt handler is disabled
  * @mutex:		Mutex protecting ready-interrupt/shutdown interlock
  * @panic_notifier:	Panic notifier structure
 */
@@ -67,7 +67,7 @@ struct ipa_smp2p {
 	u32 setup_ready_irq;
 	bool power_on;
 	bool notified;
-	bool disabled;
+	bool setup_disabled;
 	struct mutex mutex;
 	struct notifier_block panic_notifier;
 };
@@ -155,11 +155,9 @@ static irqreturn_t ipa_smp2p_modem_setup_ready_isr(int irq, void *dev_id)
 	struct device *dev;
 	int ret;
 
-	mutex_lock(&smp2p->mutex);
-
-	if (smp2p->disabled)
-		goto out_mutex_unlock;
-	smp2p->disabled = true;		/* If any others arrive, ignore them */
+	/* Ignore any (spurious) interrupts received after the first */
+	if (smp2p->ipa->setup_complete)
+		return IRQ_HANDLED;
 
 	/* Power needs to be active for setup */
 	dev = &smp2p->ipa->pdev->dev;
@@ -176,8 +174,6 @@ static irqreturn_t ipa_smp2p_modem_setup_ready_isr(int irq, void *dev_id)
 out_power_put:
 	pm_runtime_mark_last_busy(dev);
 	(void)pm_runtime_put_autosuspend(dev);
-out_mutex_unlock:
-	mutex_unlock(&smp2p->mutex);
 
 	return IRQ_HANDLED;
 }
@@ -313,7 +309,7 @@ void ipa_smp2p_exit(struct ipa *ipa)
 	kfree(smp2p);
 }
 
-void ipa_smp2p_disable(struct ipa *ipa)
+void ipa_smp2p_irq_disable_setup(struct ipa *ipa)
 {
 	struct ipa_smp2p *smp2p = ipa->smp2p;
 
@@ -322,7 +318,10 @@ void ipa_smp2p_disable(struct ipa *ipa)
 
 	mutex_lock(&smp2p->mutex);
 
-	smp2p->disabled = true;
+	if (!smp2p->setup_disabled) {
+		disable_irq(smp2p->setup_ready_irq);
+		smp2p->setup_disabled = true;
+	}
 
 	mutex_unlock(&smp2p->mutex);
 }
diff --git a/drivers/net/ipa/ipa_smp2p.h b/drivers/net/ipa/ipa_smp2p.h
index 99a956789638..59cee31a7383 100644
--- a/drivers/net/ipa/ipa_smp2p.h
+++ b/drivers/net/ipa/ipa_smp2p.h
@@ -27,13 +27,12 @@ int ipa_smp2p_init(struct ipa *ipa, bool modem_init);
 void ipa_smp2p_exit(struct ipa *ipa);
 
 /**
- * ipa_smp2p_disable() - Prevent "ipa-setup-ready" interrupt handling
+ * ipa_smp2p_irq_disable_setup() - Disable the "setup ready" interrupt
  * @ipa:	IPA pointer
  *
- * Prevent handling of the "setup ready" interrupt from the modem.
- * This is used before initiating shutdown of the driver.
+ * Disable the "ipa-setup-ready" interrupt from the modem.
  */
-void ipa_smp2p_disable(struct ipa *ipa);
+void ipa_smp2p_irq_disable_setup(struct ipa *ipa);
 
 /**
  * ipa_smp2p_notify_reset() - Reset modem notification state
diff --git a/drivers/net/mdio/mdio-aspeed.c b/drivers/net/mdio/mdio-aspeed.c
index cad820568f75..966c3b4ad59d 100644
--- a/drivers/net/mdio/mdio-aspeed.c
+++ b/drivers/net/mdio/mdio-aspeed.c
@@ -61,6 +61,13 @@ static int aspeed_mdio_read(struct mii_bus *bus, int addr, int regnum)
 
 	iowrite32(ctrl, ctx->base + ASPEED_MDIO_CTRL);
 
+	rc = readl_poll_timeout(ctx->base + ASPEED_MDIO_CTRL, ctrl,
+				!(ctrl & ASPEED_MDIO_CTRL_FIRE),
+				ASPEED_MDIO_INTERVAL_US,
+				ASPEED_MDIO_TIMEOUT_US);
+	if (rc < 0)
+		return rc;
+
 	rc = readl_poll_timeout(ctx->base + ASPEED_MDIO_DATA, data,
 				data & ASPEED_MDIO_DATA_IDLE,
 				ASPEED_MDIO_INTERVAL_US,
diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c
index 90aafb56f140..a43820212932 100644
--- a/drivers/net/netdevsim/bpf.c
+++ b/drivers/net/netdevsim/bpf.c
@@ -514,6 +514,7 @@ nsim_bpf_map_alloc(struct netdevsim *ns, struct bpf_offloaded_map *offmap)
 				goto err_free;
 			key = nmap->entry[i].key;
 			*key = i;
+			memset(nmap->entry[i].value, 0, offmap->map.value_size);
 		}
 	}
 
diff --git a/drivers/net/netdevsim/ethtool.c b/drivers/net/netdevsim/ethtool.c
index 0ab6a40be611..a6a713b31aad 100644
--- a/drivers/net/netdevsim/ethtool.c
+++ b/drivers/net/netdevsim/ethtool.c
@@ -77,7 +77,10 @@ static int nsim_set_ringparam(struct net_device *dev,
 {
 	struct netdevsim *ns = netdev_priv(dev);
 
-	memcpy(&ns->ethtool.ring, ring, sizeof(ns->ethtool.ring));
+	ns->ethtool.ring.rx_pending = ring->rx_pending;
+	ns->ethtool.ring.rx_jumbo_pending = ring->rx_jumbo_pending;
+	ns->ethtool.ring.rx_mini_pending = ring->rx_mini_pending;
+	ns->ethtool.ring.tx_pending = ring->tx_pending;
 	return 0;
 }
 
diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c
index c204067f1890..c198722e4871 100644
--- a/drivers/net/phy/mdio_bus.c
+++ b/drivers/net/phy/mdio_bus.c
@@ -460,6 +460,9 @@ static void of_mdiobus_link_mdiodev(struct mii_bus *bus,
 
 		if (addr == mdiodev->addr) {
 			device_set_node(dev, of_fwnode_handle(child));
+			/* The refcount on "child" is passed to the mdio
+			 * device. Do _not_ use of_node_put(child) here.
+			 */
 			return;
 		}
 	}
diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index 3ad7397b8119..ea82ea5660e7 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -710,6 +710,7 @@ static void phylink_resolve(struct work_struct *w)
 	struct phylink_link_state link_state;
 	struct net_device *ndev = pl->netdev;
 	bool mac_config = false;
+	bool retrigger = false;
 	bool cur_link_state;
 
 	mutex_lock(&pl->state_mutex);
@@ -723,6 +724,7 @@ static void phylink_resolve(struct work_struct *w)
 		link_state.link = false;
 	} else if (pl->mac_link_dropped) {
 		link_state.link = false;
+		retrigger = true;
 	} else {
 		switch (pl->cur_link_an_mode) {
 		case MLO_AN_PHY:
@@ -739,6 +741,19 @@ static void phylink_resolve(struct work_struct *w)
 		case MLO_AN_INBAND:
 			phylink_mac_pcs_get_state(pl, &link_state);
 
+			/* The PCS may have a latching link-fail indicator.
+			 * If the link was up, bring the link down and
+			 * re-trigger the resolve. Otherwise, re-read the
+			 * PCS state to get the current status of the link.
+			 */
+			if (!link_state.link) {
+				if (cur_link_state)
+					retrigger = true;
+				else
+					phylink_mac_pcs_get_state(pl,
+								  &link_state);
+			}
+
 			/* If we have a phy, the "up" state is the union of
 			 * both the PHY and the MAC
 			 */
@@ -747,6 +762,15 @@ static void phylink_resolve(struct work_struct *w)
 
 			/* Only update if the PHY link is up */
 			if (pl->phydev && pl->phy_state.link) {
+				/* If the interface has changed, force a
+				 * link down event if the link isn't already
+				 * down, and re-resolve.
+				 */
+				if (link_state.interface !=
+				    pl->phy_state.interface) {
+					retrigger = true;
+					link_state.link = false;
+				}
 				link_state.interface = pl->phy_state.interface;
 
 				/* If we have a PHY, we need to update with
@@ -789,7 +813,7 @@ static void phylink_resolve(struct work_struct *w)
 		else
 			phylink_link_up(pl, link_state);
 	}
-	if (!link_state.link && pl->mac_link_dropped) {
+	if (!link_state.link && retrigger) {
 		pl->mac_link_dropped = false;
 		queue_work(system_power_efficient_wq, &pl->resolve);
 	}
@@ -1364,6 +1388,7 @@ EXPORT_SYMBOL_GPL(phylink_stop);
  * @mac_wol: true if the MAC needs to receive packets for Wake-on-Lan
  *
  * Handle a network device suspend event. There are several cases:
+ *
  * - If Wake-on-Lan is not active, we can bring down the link between
  *   the MAC and PHY by calling phylink_stop().
  * - If Wake-on-Lan is active, and being handled only by the PHY, we
diff --git a/drivers/net/slip/slip.h b/drivers/net/slip/slip.h
index c420e5948522..3d7f88b330c1 100644
--- a/drivers/net/slip/slip.h
+++ b/drivers/net/slip/slip.h
@@ -40,6 +40,8 @@
 					   insmod -oslip_maxdev=nnn	*/
 #define SL_MTU		296		/* 296; I am used to 600- FvK	*/
 
+/* some arch define END as assembly function ending, just undef it */
+#undef	END
 /* SLIP protocol characters. */
 #define END             0300		/* indicates end of frame	*/
 #define ESC             0333		/* indicates byte stuffing	*/
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index fecc9a1d293a..45a67e72a02c 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -209,6 +209,9 @@ struct tun_struct {
 	struct tun_prog __rcu *steering_prog;
 	struct tun_prog __rcu *filter_prog;
 	struct ethtool_link_ksettings link_ksettings;
+	/* init args */
+	struct file *file;
+	struct ifreq *ifr;
 };
 
 struct veth {
@@ -216,6 +219,9 @@ struct veth {
 	__be16 h_vlan_TCI;
 };
 
+static void tun_flow_init(struct tun_struct *tun);
+static void tun_flow_uninit(struct tun_struct *tun);
+
 static int tun_napi_receive(struct napi_struct *napi, int budget)
 {
 	struct tun_file *tfile = container_of(napi, struct tun_file, napi);
@@ -953,6 +959,49 @@ static int check_filter(struct tap_filter *filter, const struct sk_buff *skb)
 
 static const struct ethtool_ops tun_ethtool_ops;
 
+static int tun_net_init(struct net_device *dev)
+{
+	struct tun_struct *tun = netdev_priv(dev);
+	struct ifreq *ifr = tun->ifr;
+	int err;
+
+	dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
+	if (!dev->tstats)
+		return -ENOMEM;
+
+	spin_lock_init(&tun->lock);
+
+	err = security_tun_dev_alloc_security(&tun->security);
+	if (err < 0) {
+		free_percpu(dev->tstats);
+		return err;
+	}
+
+	tun_flow_init(tun);
+
+	dev->hw_features = NETIF_F_SG | NETIF_F_FRAGLIST |
+			   TUN_USER_FEATURES | NETIF_F_HW_VLAN_CTAG_TX |
+			   NETIF_F_HW_VLAN_STAG_TX;
+	dev->features = dev->hw_features | NETIF_F_LLTX;
+	dev->vlan_features = dev->features &
+			     ~(NETIF_F_HW_VLAN_CTAG_TX |
+			       NETIF_F_HW_VLAN_STAG_TX);
+
+	tun->flags = (tun->flags & ~TUN_FEATURES) |
+		      (ifr->ifr_flags & TUN_FEATURES);
+
+	INIT_LIST_HEAD(&tun->disabled);
+	err = tun_attach(tun, tun->file, false, ifr->ifr_flags & IFF_NAPI,
+			 ifr->ifr_flags & IFF_NAPI_FRAGS, false);
+	if (err < 0) {
+		tun_flow_uninit(tun);
+		security_tun_dev_free_security(tun->security);
+		free_percpu(dev->tstats);
+		return err;
+	}
+	return 0;
+}
+
 /* Net device detach from fd. */
 static void tun_net_uninit(struct net_device *dev)
 {
@@ -1010,6 +1059,7 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct tun_struct *tun = netdev_priv(dev);
 	int txq = skb->queue_mapping;
+	struct netdev_queue *queue;
 	struct tun_file *tfile;
 	int len = skb->len;
 
@@ -1054,6 +1104,10 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (ptr_ring_produce(&tfile->tx_ring, skb))
 		goto drop;
 
+	/* NETIF_F_LLTX requires to do our own update of trans_start */
+	queue = netdev_get_tx_queue(dev, txq);
+	queue->trans_start = jiffies;
+
 	/* Notify and wake up reader process */
 	if (tfile->flags & TUN_FASYNC)
 		kill_fasync(&tfile->fasync, SIGIO, POLL_IN);
@@ -1164,6 +1218,7 @@ static int tun_net_change_carrier(struct net_device *dev, bool new_carrier)
 }
 
 static const struct net_device_ops tun_netdev_ops = {
+	.ndo_init		= tun_net_init,
 	.ndo_uninit		= tun_net_uninit,
 	.ndo_open		= tun_net_open,
 	.ndo_stop		= tun_net_close,
@@ -1247,6 +1302,7 @@ static int tun_xdp_tx(struct net_device *dev, struct xdp_buff *xdp)
 }
 
 static const struct net_device_ops tap_netdev_ops = {
+	.ndo_init		= tun_net_init,
 	.ndo_uninit		= tun_net_uninit,
 	.ndo_open		= tun_net_open,
 	.ndo_stop		= tun_net_close,
@@ -1287,7 +1343,7 @@ static void tun_flow_uninit(struct tun_struct *tun)
 #define MAX_MTU 65535
 
 /* Initialize net device. */
-static void tun_net_init(struct net_device *dev)
+static void tun_net_initialize(struct net_device *dev)
 {
 	struct tun_struct *tun = netdev_priv(dev);
 
@@ -2201,11 +2257,6 @@ static void tun_free_netdev(struct net_device *dev)
 	BUG_ON(!(list_empty(&tun->disabled)));
 
 	free_percpu(dev->tstats);
-	/* We clear tstats so that tun_set_iff() can tell if
-	 * tun_free_netdev() has been called from register_netdevice().
-	 */
-	dev->tstats = NULL;
-
 	tun_flow_uninit(tun);
 	security_tun_dev_free_security(tun->security);
 	__tun_set_ebpf(tun, &tun->steering_prog, NULL);
@@ -2711,41 +2762,16 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
 		tun->rx_batched = 0;
 		RCU_INIT_POINTER(tun->steering_prog, NULL);
 
-		dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
-		if (!dev->tstats) {
-			err = -ENOMEM;
-			goto err_free_dev;
-		}
+		tun->ifr = ifr;
+		tun->file = file;
 
-		spin_lock_init(&tun->lock);
-
-		err = security_tun_dev_alloc_security(&tun->security);
-		if (err < 0)
-			goto err_free_stat;
-
-		tun_net_init(dev);
-		tun_flow_init(tun);
-
-		dev->hw_features = NETIF_F_SG | NETIF_F_FRAGLIST |
-				   TUN_USER_FEATURES | NETIF_F_HW_VLAN_CTAG_TX |
-				   NETIF_F_HW_VLAN_STAG_TX;
-		dev->features = dev->hw_features | NETIF_F_LLTX;
-		dev->vlan_features = dev->features &
-				     ~(NETIF_F_HW_VLAN_CTAG_TX |
-				       NETIF_F_HW_VLAN_STAG_TX);
-
-		tun->flags = (tun->flags & ~TUN_FEATURES) |
-			      (ifr->ifr_flags & TUN_FEATURES);
-
-		INIT_LIST_HEAD(&tun->disabled);
-		err = tun_attach(tun, file, false, ifr->ifr_flags & IFF_NAPI,
-				 ifr->ifr_flags & IFF_NAPI_FRAGS, false);
-		if (err < 0)
-			goto err_free_flow;
+		tun_net_initialize(dev);
 
 		err = register_netdevice(tun->dev);
-		if (err < 0)
-			goto err_detach;
+		if (err < 0) {
+			free_netdev(dev);
+			return err;
+		}
 		/* free_netdev() won't check refcnt, to avoid race
 		 * with dev_put() we need publish tun after registration.
 		 */
@@ -2762,24 +2788,6 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
 
 	strcpy(ifr->ifr_name, tun->dev->name);
 	return 0;
-
-err_detach:
-	tun_detach_all(dev);
-	/* We are here because register_netdevice() has failed.
-	 * If register_netdevice() already called tun_free_netdev()
-	 * while dealing with the error, dev->stats has been cleared.
-	 */
-	if (!dev->tstats)
-		goto err_free_dev;
-
-err_free_flow:
-	tun_flow_uninit(tun);
-	security_tun_dev_free_security(tun->security);
-err_free_stat:
-	free_percpu(dev->tstats);
-err_free_dev:
-	free_netdev(dev);
-	return err;
 }
 
 static void tun_get_iff(struct tun_struct *tun, struct ifreq *ifr)
diff --git a/drivers/net/usb/asix_common.c b/drivers/net/usb/asix_common.c
index 42ba4af68090..71682970be58 100644
--- a/drivers/net/usb/asix_common.c
+++ b/drivers/net/usb/asix_common.c
@@ -9,6 +9,8 @@
 
 #include "asix.h"
 
+#define AX_HOST_EN_RETRIES	30
+
 int asix_read_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index,
 		  u16 size, void *data, int in_pm)
 {
@@ -68,7 +70,7 @@ static int asix_check_host_enable(struct usbnet *dev, int in_pm)
 	int i, ret;
 	u8 smsr;
 
-	for (i = 0; i < 30; ++i) {
+	for (i = 0; i < AX_HOST_EN_RETRIES; ++i) {
 		ret = asix_set_sw_mii(dev, in_pm);
 		if (ret == -ENODEV || ret == -ETIMEDOUT)
 			break;
@@ -77,13 +79,13 @@ static int asix_check_host_enable(struct usbnet *dev, int in_pm)
 				    0, 0, 1, &smsr, in_pm);
 		if (ret == -ENODEV)
 			break;
-		else if (ret < 0)
+		else if (ret < sizeof(smsr))
 			continue;
 		else if (smsr & AX_HOST_EN)
 			break;
 	}
 
-	return ret;
+	return i >= AX_HOST_EN_RETRIES ? -ETIMEDOUT : ret;
 }
 
 static void reset_asix_rx_fixup_info(struct asix_rx_fixup_info *rx)
diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index 24753a4da7e6..e303b522efb5 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -181,6 +181,8 @@ static u32 cdc_ncm_check_tx_max(struct usbnet *dev, u32 new_tx)
 		min = ctx->max_datagram_size + ctx->max_ndp_size + sizeof(struct usb_cdc_ncm_nth32);
 
 	max = min_t(u32, CDC_NCM_NTB_MAX_SIZE_TX, le32_to_cpu(ctx->ncm_parm.dwNtbOutMaxSize));
+	if (max == 0)
+		max = CDC_NCM_NTB_MAX_SIZE_TX; /* dwNtbOutMaxSize not set */
 
 	/* some devices set dwNtbOutMaxSize too low for the above default */
 	min = min(min, max);
diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index f20376c1ef3f..075f8abde5cd 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -76,6 +76,8 @@
 #define LAN7801_USB_PRODUCT_ID		(0x7801)
 #define LAN78XX_EEPROM_MAGIC		(0x78A5)
 #define LAN78XX_OTP_MAGIC		(0x78F3)
+#define AT29M2AF_USB_VENDOR_ID		(0x07C9)
+#define AT29M2AF_USB_PRODUCT_ID	(0x0012)
 
 #define	MII_READ			1
 #define	MII_WRITE			0
@@ -2228,7 +2230,7 @@ static int lan78xx_phy_init(struct lan78xx_net *dev)
 	if (dev->domain_data.phyirq > 0)
 		phydev->irq = dev->domain_data.phyirq;
 	else
-		phydev->irq = 0;
+		phydev->irq = PHY_POLL;
 	netdev_dbg(dev->net, "phydev->irq = %d\n", phydev->irq);
 
 	/* set to AUTOMDIX */
@@ -4734,6 +4736,10 @@ static const struct usb_device_id products[] = {
 	/* LAN7801 USB Gigabit Ethernet Device */
 	USB_DEVICE(LAN78XX_USB_VENDOR_ID, LAN7801_USB_PRODUCT_ID),
 	},
+	{
+	/* ATM2-AF USB Gigabit Ethernet Device */
+	USB_DEVICE(AT29M2AF_USB_VENDOR_ID, AT29M2AF_USB_PRODUCT_ID),
+	},
 	{},
 };
 MODULE_DEVICE_TABLE(usb, products);
diff --git a/drivers/net/usb/pegasus.c b/drivers/net/usb/pegasus.c
index c4cd40b090fd..feb247e355f7 100644
--- a/drivers/net/usb/pegasus.c
+++ b/drivers/net/usb/pegasus.c
@@ -493,11 +493,11 @@ static void read_bulk_callback(struct urb *urb)
 		goto goon;
 
 	rx_status = buf[count - 2];
-	if (rx_status & 0x1e) {
+	if (rx_status & 0x1c) {
 		netif_dbg(pegasus, rx_err, net,
 			  "RX packet error %x\n", rx_status);
 		net->stats.rx_errors++;
-		if (rx_status & 0x06)	/* long or runt	*/
+		if (rx_status & 0x04)	/* runt	*/
 			net->stats.rx_length_errors++;
 		if (rx_status & 0x08)
 			net->stats.rx_crc_errors++;
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 86b814e99224..f510e8219470 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1358,6 +1358,7 @@ static const struct usb_device_id products[] = {
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1040, 2)},	/* Telit LE922A */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1050, 2)},	/* Telit FN980 */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1060, 2)},	/* Telit LN920 */
+	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1070, 2)},	/* Telit FN990 */
 	{QMI_FIXED_INTF(0x1bc7, 0x1100, 3)},	/* Telit ME910 */
 	{QMI_FIXED_INTF(0x1bc7, 0x1101, 3)},	/* Telit ME910 dual modem */
 	{QMI_FIXED_INTF(0x1bc7, 0x1200, 5)},	/* Telit LE920 */
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 4a02f33f0643..3085e8118d7f 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -32,7 +32,7 @@
 #define NETNEXT_VERSION		"12"
 
 /* Information for net */
-#define NET_VERSION		"11"
+#define NET_VERSION		"12"
 
 #define DRIVER_VERSION		"v1." NETNEXT_VERSION "." NET_VERSION
 #define DRIVER_AUTHOR "Realtek linux nic maintainers <nic_swsd@realtek.com>"
@@ -4016,6 +4016,11 @@ static void rtl_clear_bp(struct r8152 *tp, u16 type)
 	ocp_write_word(tp, type, PLA_BP_BA, 0);
 }
 
+static inline void rtl_reset_ocp_base(struct r8152 *tp)
+{
+	tp->ocp_base = -1;
+}
+
 static int rtl_phy_patch_request(struct r8152 *tp, bool request, bool wait)
 {
 	u16 data, check;
@@ -4087,8 +4092,6 @@ static int rtl_post_ram_code(struct r8152 *tp, u16 key_addr, bool wait)
 
 	rtl_phy_patch_request(tp, false, wait);
 
-	ocp_write_word(tp, MCU_TYPE_PLA, PLA_OCP_GPHY_BASE, tp->ocp_base);
-
 	return 0;
 }
 
@@ -4800,6 +4803,8 @@ static void rtl_ram_code_speed_up(struct r8152 *tp, struct fw_phy_speed_up *phy,
 	u32 len;
 	u8 *data;
 
+	rtl_reset_ocp_base(tp);
+
 	if (sram_read(tp, SRAM_GPHY_FW_VER) >= __le16_to_cpu(phy->version)) {
 		dev_dbg(&tp->intf->dev, "PHY firmware has been the newest\n");
 		return;
@@ -4845,7 +4850,8 @@ static void rtl_ram_code_speed_up(struct r8152 *tp, struct fw_phy_speed_up *phy,
 		}
 	}
 
-	ocp_write_word(tp, MCU_TYPE_PLA, PLA_OCP_GPHY_BASE, tp->ocp_base);
+	rtl_reset_ocp_base(tp);
+
 	rtl_phy_patch_request(tp, false, wait);
 
 	if (sram_read(tp, SRAM_GPHY_FW_VER) == __le16_to_cpu(phy->version))
@@ -4861,6 +4867,8 @@ static int rtl8152_fw_phy_ver(struct r8152 *tp, struct fw_phy_ver *phy_ver)
 	ver_addr = __le16_to_cpu(phy_ver->ver.addr);
 	ver = __le16_to_cpu(phy_ver->ver.data);
 
+	rtl_reset_ocp_base(tp);
+
 	if (sram_read(tp, ver_addr) >= ver) {
 		dev_dbg(&tp->intf->dev, "PHY firmware has been the newest\n");
 		return 0;
@@ -4877,6 +4885,8 @@ static void rtl8152_fw_phy_fixup(struct r8152 *tp, struct fw_phy_fixup *fix)
 {
 	u16 addr, data;
 
+	rtl_reset_ocp_base(tp);
+
 	addr = __le16_to_cpu(fix->setting.addr);
 	data = ocp_reg_read(tp, addr);
 
@@ -4908,6 +4918,8 @@ static void rtl8152_fw_phy_union_apply(struct r8152 *tp, struct fw_phy_union *ph
 	u32 length;
 	int i, num;
 
+	rtl_reset_ocp_base(tp);
+
 	num = phy->pre_num;
 	for (i = 0; i < num; i++)
 		sram_write(tp, __le16_to_cpu(phy->pre_set[i].addr),
@@ -4938,6 +4950,8 @@ static void rtl8152_fw_phy_nc_apply(struct r8152 *tp, struct fw_phy_nc *phy)
 	u32 length, i, num;
 	__le16 *data;
 
+	rtl_reset_ocp_base(tp);
+
 	mode_reg = __le16_to_cpu(phy->mode_reg);
 	sram_write(tp, mode_reg, __le16_to_cpu(phy->mode_pre));
 	sram_write(tp, __le16_to_cpu(phy->ba_reg),
@@ -5107,6 +5121,7 @@ post_fw:
 	if (rtl_fw->post_fw)
 		rtl_fw->post_fw(tp);
 
+	rtl_reset_ocp_base(tp);
 	strscpy(rtl_fw->version, fw_hdr->version, RTL_VER_SIZE);
 	dev_info(&tp->intf->dev, "load %s successfully\n", rtl_fw->version);
 }
@@ -6584,6 +6599,21 @@ static bool rtl8153_in_nway(struct r8152 *tp)
 		return true;
 }
 
+static void r8156_mdio_force_mode(struct r8152 *tp)
+{
+	u16 data;
+
+	/* Select force mode through 0xa5b4 bit 15
+	 * 0: MDIO force mode
+	 * 1: MMD force mode
+	 */
+	data = ocp_reg_read(tp, 0xa5b4);
+	if (data & BIT(15)) {
+		data &= ~BIT(15);
+		ocp_reg_write(tp, 0xa5b4, data);
+	}
+}
+
 static void set_carrier(struct r8152 *tp)
 {
 	struct net_device *netdev = tp->netdev;
@@ -8016,6 +8046,7 @@ static void r8156_init(struct r8152 *tp)
 	ocp_data |= ACT_ODMA;
 	ocp_write_byte(tp, MCU_TYPE_USB, USB_BMU_CONFIG, ocp_data);
 
+	r8156_mdio_force_mode(tp);
 	rtl_tally_reset(tp);
 
 	tp->coalesce = 15000;	/* 15 us */
@@ -8145,6 +8176,7 @@ static void r8156b_init(struct r8152 *tp)
 	ocp_data &= ~(RX_AGG_DISABLE | RX_ZERO_EN);
 	ocp_write_word(tp, MCU_TYPE_USB, USB_USB_CTRL, ocp_data);
 
+	r8156_mdio_force_mode(tp);
 	rtl_tally_reset(tp);
 
 	tp->coalesce = 15000;	/* 15 us */
@@ -8467,6 +8499,8 @@ static int rtl8152_resume(struct usb_interface *intf)
 
 	mutex_lock(&tp->control);
 
+	rtl_reset_ocp_base(tp);
+
 	if (test_bit(SELECTIVE_SUSPEND, &tp->flags))
 		ret = rtl8152_runtime_resume(tp);
 	else
@@ -8482,6 +8516,7 @@ static int rtl8152_reset_resume(struct usb_interface *intf)
 	struct r8152 *tp = usb_get_intfdata(intf);
 
 	clear_bit(SELECTIVE_SUSPEND, &tp->flags);
+	rtl_reset_ocp_base(tp);
 	tp->rtl_ops.init(tp);
 	queue_delayed_work(system_long_wq, &tp->hw_phy_work, 0);
 	set_ethernet_addr(tp, true);
@@ -9603,12 +9638,9 @@ static int rtl8152_probe(struct usb_interface *intf,
 		netdev->hw_features &= ~NETIF_F_RXCSUM;
 	}
 
-	if (le16_to_cpu(udev->descriptor.idVendor) == VENDOR_ID_LENOVO) {
-		switch (le16_to_cpu(udev->descriptor.idProduct)) {
-		case DEVICE_ID_THINKPAD_THUNDERBOLT3_DOCK_GEN2:
-		case DEVICE_ID_THINKPAD_USB_C_DOCK_GEN2:
-			tp->lenovo_macpassthru = 1;
-		}
+	if (udev->parent &&
+			le16_to_cpu(udev->parent->descriptor.idVendor) == VENDOR_ID_LENOVO) {
+		tp->lenovo_macpassthru = 1;
 	}
 
 	if (le16_to_cpu(udev->descriptor.bcdDevice) == 0x3011 && udev->serial &&
diff --git a/drivers/net/usb/rndis_host.c b/drivers/net/usb/rndis_host.c
index 4a84f90e377c..247f58cb0f84 100644
--- a/drivers/net/usb/rndis_host.c
+++ b/drivers/net/usb/rndis_host.c
@@ -609,6 +609,11 @@ static const struct usb_device_id	products [] = {
 				      USB_CLASS_COMM, 2 /* ACM */, 0x0ff),
 	.driver_info = (unsigned long) &rndis_poll_status_info,
 }, {
+	/* Hytera Communications DMR radios' "Radio to PC Network" */
+	USB_VENDOR_AND_INTERFACE_INFO(0x238b,
+				      USB_CLASS_COMM, 2 /* ACM */, 0x0ff),
+	.driver_info = (unsigned long)&rndis_info,
+}, {
 	/* RNDIS is MSFT's un-official variant of CDC ACM */
 	USB_INTERFACE_INFO(USB_CLASS_COMM, 2 /* ACM */, 0x0ff),
 	.driver_info = (unsigned long) &rndis_info,
diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c
index 20fe4cd8f784..abe0149ed917 100644
--- a/drivers/net/usb/smsc95xx.c
+++ b/drivers/net/usb/smsc95xx.c
@@ -1050,6 +1050,14 @@ static const struct net_device_ops smsc95xx_netdev_ops = {
 	.ndo_set_features	= smsc95xx_set_features,
 };
 
+static void smsc95xx_handle_link_change(struct net_device *net)
+{
+	struct usbnet *dev = netdev_priv(net);
+
+	phy_print_status(net->phydev);
+	usbnet_defer_kevent(dev, EVENT_LINK_CHANGE);
+}
+
 static int smsc95xx_bind(struct usbnet *dev, struct usb_interface *intf)
 {
 	struct smsc95xx_priv *pdata;
@@ -1154,6 +1162,17 @@ static int smsc95xx_bind(struct usbnet *dev, struct usb_interface *intf)
 	dev->net->min_mtu = ETH_MIN_MTU;
 	dev->net->max_mtu = ETH_DATA_LEN;
 	dev->hard_mtu = dev->net->mtu + dev->net->hard_header_len;
+
+	ret = phy_connect_direct(dev->net, pdata->phydev,
+				 &smsc95xx_handle_link_change,
+				 PHY_INTERFACE_MODE_MII);
+	if (ret) {
+		netdev_err(dev->net, "can't attach PHY to %s\n", pdata->mdiobus->id);
+		goto unregister_mdio;
+	}
+
+	phy_attached_info(dev->net->phydev);
+
 	return 0;
 
 unregister_mdio:
@@ -1171,47 +1190,25 @@ static void smsc95xx_unbind(struct usbnet *dev, struct usb_interface *intf)
 {
 	struct smsc95xx_priv *pdata = dev->driver_priv;
 
+	phy_disconnect(dev->net->phydev);
 	mdiobus_unregister(pdata->mdiobus);
 	mdiobus_free(pdata->mdiobus);
 	netif_dbg(dev, ifdown, dev->net, "free pdata\n");
 	kfree(pdata);
 }
 
-static void smsc95xx_handle_link_change(struct net_device *net)
-{
-	struct usbnet *dev = netdev_priv(net);
-
-	phy_print_status(net->phydev);
-	usbnet_defer_kevent(dev, EVENT_LINK_CHANGE);
-}
-
 static int smsc95xx_start_phy(struct usbnet *dev)
 {
-	struct smsc95xx_priv *pdata = dev->driver_priv;
-	struct net_device *net = dev->net;
-	int ret;
+	phy_start(dev->net->phydev);
 
-	ret = smsc95xx_reset(dev);
-	if (ret < 0)
-		return ret;
-
-	ret = phy_connect_direct(net, pdata->phydev,
-				 &smsc95xx_handle_link_change,
-				 PHY_INTERFACE_MODE_MII);
-	if (ret) {
-		netdev_err(net, "can't attach PHY to %s\n", pdata->mdiobus->id);
-		return ret;
-	}
-
-	phy_attached_info(net->phydev);
-	phy_start(net->phydev);
 	return 0;
 }
 
-static int smsc95xx_disconnect_phy(struct usbnet *dev)
+static int smsc95xx_stop(struct usbnet *dev)
 {
-	phy_stop(dev->net->phydev);
-	phy_disconnect(dev->net->phydev);
+	if (dev->net->phydev)
+		phy_stop(dev->net->phydev);
+
 	return 0;
 }
 
@@ -1966,7 +1963,7 @@ static const struct driver_info smsc95xx_info = {
 	.unbind		= smsc95xx_unbind,
 	.link_reset	= smsc95xx_link_reset,
 	.reset		= smsc95xx_start_phy,
-	.stop		= smsc95xx_disconnect_phy,
+	.stop		= smsc95xx_stop,
 	.rx_fixup	= smsc95xx_rx_fixup,
 	.tx_fixup	= smsc95xx_tx_fixup,
 	.status		= smsc95xx_status,
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 50eb43e5bf45..2acdb8ad6c71 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -879,8 +879,12 @@ static int veth_xdp_rcv(struct veth_rq *rq, int budget,
 
 			stats->xdp_bytes += skb->len;
 			skb = veth_xdp_rcv_skb(rq, skb, bq, stats);
-			if (skb)
-				napi_gro_receive(&rq->xdp_napi, skb);
+			if (skb) {
+				if (skb_shared(skb) || skb_unclone(skb, GFP_ATOMIC))
+					netif_receive_skb(skb);
+				else
+					napi_gro_receive(&rq->xdp_napi, skb);
+			}
 		}
 		done++;
 	}
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 1771d6e5224f..b107835242ad 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -733,7 +733,7 @@ static struct sk_buff *receive_small(struct net_device *dev,
 		pr_debug("%s: rx error: len %u exceeds max size %d\n",
 			 dev->name, len, GOOD_PACKET_LEN);
 		dev->stats.rx_length_errors++;
-		goto err_len;
+		goto err;
 	}
 
 	if (likely(!vi->xdp_enabled)) {
@@ -825,10 +825,8 @@ static struct sk_buff *receive_small(struct net_device *dev,
 
 skip_xdp:
 	skb = build_skb(buf, buflen);
-	if (!skb) {
-		put_page(page);
+	if (!skb)
 		goto err;
-	}
 	skb_reserve(skb, headroom - delta);
 	skb_put(skb, len);
 	if (!xdp_prog) {
@@ -839,13 +837,12 @@ skip_xdp:
 	if (metasize)
 		skb_metadata_set(skb, metasize);
 
-err:
 	return skb;
 
 err_xdp:
 	rcu_read_unlock();
 	stats->xdp_drops++;
-err_len:
+err:
 	stats->drops++;
 	put_page(page);
 xdp_xmit:
@@ -3423,7 +3420,6 @@ static struct virtio_driver virtio_net_driver = {
 	.feature_table_size = ARRAY_SIZE(features),
 	.feature_table_legacy = features_legacy,
 	.feature_table_size_legacy = ARRAY_SIZE(features_legacy),
-	.suppress_used_validation = true,
 	.driver.name =	KBUILD_MODNAME,
 	.driver.owner =	THIS_MODULE,
 	.id_table =	id_table,
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index 14fae317bc70..fd407c0e2856 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -3261,7 +3261,7 @@ vmxnet3_alloc_intr_resources(struct vmxnet3_adapter *adapter)
 
 #ifdef CONFIG_PCI_MSI
 	if (adapter->intr.type == VMXNET3_IT_MSIX) {
-		int i, nvec;
+		int i, nvec, nvec_allocated;
 
 		nvec  = adapter->share_intr == VMXNET3_INTR_TXSHARE ?
 			1 : adapter->num_tx_queues;
@@ -3274,14 +3274,15 @@ vmxnet3_alloc_intr_resources(struct vmxnet3_adapter *adapter)
 		for (i = 0; i < nvec; i++)
 			adapter->intr.msix_entries[i].entry = i;
 
-		nvec = vmxnet3_acquire_msix_vectors(adapter, nvec);
-		if (nvec < 0)
+		nvec_allocated = vmxnet3_acquire_msix_vectors(adapter, nvec);
+		if (nvec_allocated < 0)
 			goto msix_err;
 
 		/* If we cannot allocate one MSIx vector per queue
 		 * then limit the number of rx queues to 1
 		 */
-		if (nvec == VMXNET3_LINUX_MIN_MSIX_VECT) {
+		if (nvec_allocated == VMXNET3_LINUX_MIN_MSIX_VECT &&
+		    nvec != VMXNET3_LINUX_MIN_MSIX_VECT) {
 			if (adapter->share_intr != VMXNET3_INTR_BUDDYSHARE
 			    || adapter->num_rx_queues != 1) {
 				adapter->share_intr = VMXNET3_INTR_TXSHARE;
@@ -3291,14 +3292,14 @@ vmxnet3_alloc_intr_resources(struct vmxnet3_adapter *adapter)
 			}
 		}
 
-		adapter->intr.num_intrs = nvec;
+		adapter->intr.num_intrs = nvec_allocated;
 		return;
 
 msix_err:
 		/* If we cannot allocate MSIx vectors use only one rx queue */
 		dev_info(&adapter->pdev->dev,
 			 "Failed to enable MSI-X, error %d. "
-			 "Limiting #rx queues to 1, try MSI.\n", nvec);
+			 "Limiting #rx queues to 1, try MSI.\n", nvec_allocated);
 
 		adapter->intr.type = VMXNET3_IT_MSI;
 	}
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index ccf677015d5b..b2242a082431 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -497,6 +497,7 @@ static netdev_tx_t vrf_process_v6_outbound(struct sk_buff *skb,
 	/* strip the ethernet header added for pass through VRF device */
 	__skb_pull(skb, skb_network_offset(skb));
 
+	memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
 	ret = vrf_ip6_local_out(net, skb->sk, skb);
 	if (unlikely(net_xmit_eval(ret)))
 		dev->stats.tx_errors++;
@@ -579,6 +580,7 @@ static netdev_tx_t vrf_process_v4_outbound(struct sk_buff *skb,
 					       RT_SCOPE_LINK);
 	}
 
+	memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
 	ret = vrf_ip_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb);
 	if (unlikely(net_xmit_eval(ret)))
 		vrf_dev->stats.tx_errors++;
@@ -768,8 +770,6 @@ static struct sk_buff *vrf_ip6_out_direct(struct net_device *vrf_dev,
 
 	skb->dev = vrf_dev;
 
-	vrf_nf_set_untracked(skb);
-
 	err = nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk,
 		      skb, NULL, vrf_dev, vrf_ip6_out_direct_finish);
 
@@ -790,6 +790,8 @@ static struct sk_buff *vrf_ip6_out(struct net_device *vrf_dev,
 	if (rt6_need_strict(&ipv6_hdr(skb)->daddr))
 		return skb;
 
+	vrf_nf_set_untracked(skb);
+
 	if (qdisc_tx_is_default(vrf_dev) ||
 	    IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED)
 		return vrf_ip6_out_direct(vrf_dev, sk, skb);
@@ -998,8 +1000,6 @@ static struct sk_buff *vrf_ip_out_direct(struct net_device *vrf_dev,
 
 	skb->dev = vrf_dev;
 
-	vrf_nf_set_untracked(skb);
-
 	err = nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, net, sk,
 		      skb, NULL, vrf_dev, vrf_ip_out_direct_finish);
 
@@ -1021,6 +1021,8 @@ static struct sk_buff *vrf_ip_out(struct net_device *vrf_dev,
 	    ipv4_is_lbcast(ip_hdr(skb)->daddr))
 		return skb;
 
+	vrf_nf_set_untracked(skb);
+
 	if (qdisc_tx_is_default(vrf_dev) ||
 	    IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED)
 		return vrf_ip_out_direct(vrf_dev, sk, skb);
diff --git a/drivers/net/wireguard/allowedips.c b/drivers/net/wireguard/allowedips.c
index b7197e80f226..9a4c8ff32d9d 100644
--- a/drivers/net/wireguard/allowedips.c
+++ b/drivers/net/wireguard/allowedips.c
@@ -163,7 +163,7 @@ static bool node_placement(struct allowedips_node __rcu *trie, const u8 *key,
 	return exact;
 }
 
-static inline void connect_node(struct allowedips_node **parent, u8 bit, struct allowedips_node *node)
+static inline void connect_node(struct allowedips_node __rcu **parent, u8 bit, struct allowedips_node *node)
 {
 	node->parent_bit_packed = (unsigned long)parent | bit;
 	rcu_assign_pointer(*parent, node);
diff --git a/drivers/net/wireguard/device.c b/drivers/net/wireguard/device.c
index 551ddaaaf540..a46067c38bf5 100644
--- a/drivers/net/wireguard/device.c
+++ b/drivers/net/wireguard/device.c
@@ -98,6 +98,7 @@ static int wg_stop(struct net_device *dev)
 {
 	struct wg_device *wg = netdev_priv(dev);
 	struct wg_peer *peer;
+	struct sk_buff *skb;
 
 	mutex_lock(&wg->device_update_lock);
 	list_for_each_entry(peer, &wg->peer_list, peer_list) {
@@ -108,7 +109,9 @@ static int wg_stop(struct net_device *dev)
 		wg_noise_reset_last_sent_handshake(&peer->last_sent_handshake);
 	}
 	mutex_unlock(&wg->device_update_lock);
-	skb_queue_purge(&wg->incoming_handshakes);
+	while ((skb = ptr_ring_consume(&wg->handshake_queue.ring)) != NULL)
+		kfree_skb(skb);
+	atomic_set(&wg->handshake_queue_len, 0);
 	wg_socket_reinit(wg, NULL, NULL);
 	return 0;
 }
@@ -235,14 +238,13 @@ static void wg_destruct(struct net_device *dev)
 	destroy_workqueue(wg->handshake_receive_wq);
 	destroy_workqueue(wg->handshake_send_wq);
 	destroy_workqueue(wg->packet_crypt_wq);
-	wg_packet_queue_free(&wg->decrypt_queue);
-	wg_packet_queue_free(&wg->encrypt_queue);
+	wg_packet_queue_free(&wg->handshake_queue, true);
+	wg_packet_queue_free(&wg->decrypt_queue, false);
+	wg_packet_queue_free(&wg->encrypt_queue, false);
 	rcu_barrier(); /* Wait for all the peers to be actually freed. */
 	wg_ratelimiter_uninit();
 	memzero_explicit(&wg->static_identity, sizeof(wg->static_identity));
-	skb_queue_purge(&wg->incoming_handshakes);
 	free_percpu(dev->tstats);
-	free_percpu(wg->incoming_handshakes_worker);
 	kvfree(wg->index_hashtable);
 	kvfree(wg->peer_hashtable);
 	mutex_unlock(&wg->device_update_lock);
@@ -298,7 +300,6 @@ static int wg_newlink(struct net *src_net, struct net_device *dev,
 	init_rwsem(&wg->static_identity.lock);
 	mutex_init(&wg->socket_update_lock);
 	mutex_init(&wg->device_update_lock);
-	skb_queue_head_init(&wg->incoming_handshakes);
 	wg_allowedips_init(&wg->peer_allowedips);
 	wg_cookie_checker_init(&wg->cookie_checker, wg);
 	INIT_LIST_HEAD(&wg->peer_list);
@@ -316,16 +317,10 @@ static int wg_newlink(struct net *src_net, struct net_device *dev,
 	if (!dev->tstats)
 		goto err_free_index_hashtable;
 
-	wg->incoming_handshakes_worker =
-		wg_packet_percpu_multicore_worker_alloc(
-				wg_packet_handshake_receive_worker, wg);
-	if (!wg->incoming_handshakes_worker)
-		goto err_free_tstats;
-
 	wg->handshake_receive_wq = alloc_workqueue("wg-kex-%s",
 			WQ_CPU_INTENSIVE | WQ_FREEZABLE, 0, dev->name);
 	if (!wg->handshake_receive_wq)
-		goto err_free_incoming_handshakes;
+		goto err_free_tstats;
 
 	wg->handshake_send_wq = alloc_workqueue("wg-kex-%s",
 			WQ_UNBOUND | WQ_FREEZABLE, 0, dev->name);
@@ -347,10 +342,15 @@ static int wg_newlink(struct net *src_net, struct net_device *dev,
 	if (ret < 0)
 		goto err_free_encrypt_queue;
 
-	ret = wg_ratelimiter_init();
+	ret = wg_packet_queue_init(&wg->handshake_queue, wg_packet_handshake_receive_worker,
+				   MAX_QUEUED_INCOMING_HANDSHAKES);
 	if (ret < 0)
 		goto err_free_decrypt_queue;
 
+	ret = wg_ratelimiter_init();
+	if (ret < 0)
+		goto err_free_handshake_queue;
+
 	ret = register_netdevice(dev);
 	if (ret < 0)
 		goto err_uninit_ratelimiter;
@@ -367,18 +367,18 @@ static int wg_newlink(struct net *src_net, struct net_device *dev,
 
 err_uninit_ratelimiter:
 	wg_ratelimiter_uninit();
+err_free_handshake_queue:
+	wg_packet_queue_free(&wg->handshake_queue, false);
 err_free_decrypt_queue:
-	wg_packet_queue_free(&wg->decrypt_queue);
+	wg_packet_queue_free(&wg->decrypt_queue, false);
 err_free_encrypt_queue:
-	wg_packet_queue_free(&wg->encrypt_queue);
+	wg_packet_queue_free(&wg->encrypt_queue, false);
 err_destroy_packet_crypt:
 	destroy_workqueue(wg->packet_crypt_wq);
 err_destroy_handshake_send:
 	destroy_workqueue(wg->handshake_send_wq);
 err_destroy_handshake_receive:
 	destroy_workqueue(wg->handshake_receive_wq);
-err_free_incoming_handshakes:
-	free_percpu(wg->incoming_handshakes_worker);
 err_free_tstats:
 	free_percpu(dev->tstats);
 err_free_index_hashtable:
@@ -398,6 +398,7 @@ static struct rtnl_link_ops link_ops __read_mostly = {
 static void wg_netns_pre_exit(struct net *net)
 {
 	struct wg_device *wg;
+	struct wg_peer *peer;
 
 	rtnl_lock();
 	list_for_each_entry(wg, &device_list, device_list) {
@@ -407,6 +408,8 @@ static void wg_netns_pre_exit(struct net *net)
 			mutex_lock(&wg->device_update_lock);
 			rcu_assign_pointer(wg->creating_net, NULL);
 			wg_socket_reinit(wg, NULL, NULL);
+			list_for_each_entry(peer, &wg->peer_list, peer_list)
+				wg_socket_clear_peer_endpoint_src(peer);
 			mutex_unlock(&wg->device_update_lock);
 		}
 	}
diff --git a/drivers/net/wireguard/device.h b/drivers/net/wireguard/device.h
index 854bc3d97150..43c7cebbf50b 100644
--- a/drivers/net/wireguard/device.h
+++ b/drivers/net/wireguard/device.h
@@ -39,21 +39,18 @@ struct prev_queue {
 
 struct wg_device {
 	struct net_device *dev;
-	struct crypt_queue encrypt_queue, decrypt_queue;
+	struct crypt_queue encrypt_queue, decrypt_queue, handshake_queue;
 	struct sock __rcu *sock4, *sock6;
 	struct net __rcu *creating_net;
 	struct noise_static_identity static_identity;
-	struct workqueue_struct *handshake_receive_wq, *handshake_send_wq;
-	struct workqueue_struct *packet_crypt_wq;
-	struct sk_buff_head incoming_handshakes;
-	int incoming_handshake_cpu;
-	struct multicore_worker __percpu *incoming_handshakes_worker;
+	struct workqueue_struct *packet_crypt_wq,*handshake_receive_wq, *handshake_send_wq;
 	struct cookie_checker cookie_checker;
 	struct pubkey_hashtable *peer_hashtable;
 	struct index_hashtable *index_hashtable;
 	struct allowedips peer_allowedips;
 	struct mutex device_update_lock, socket_update_lock;
 	struct list_head device_list, peer_list;
+	atomic_t handshake_queue_len;
 	unsigned int num_peers, device_update_gen;
 	u32 fwmark;
 	u16 incoming_port;
diff --git a/drivers/net/wireguard/main.c b/drivers/net/wireguard/main.c
index 75dbe77b0b4b..ee4da9ab8013 100644
--- a/drivers/net/wireguard/main.c
+++ b/drivers/net/wireguard/main.c
@@ -17,7 +17,7 @@
 #include <linux/genetlink.h>
 #include <net/rtnetlink.h>
 
-static int __init mod_init(void)
+static int __init wg_mod_init(void)
 {
 	int ret;
 
@@ -60,7 +60,7 @@ err_allowedips:
 	return ret;
 }
 
-static void __exit mod_exit(void)
+static void __exit wg_mod_exit(void)
 {
 	wg_genetlink_uninit();
 	wg_device_uninit();
@@ -68,8 +68,8 @@ static void __exit mod_exit(void)
 	wg_allowedips_slab_uninit();
 }
 
-module_init(mod_init);
-module_exit(mod_exit);
+module_init(wg_mod_init);
+module_exit(wg_mod_exit);
 MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("WireGuard secure network tunnel");
 MODULE_AUTHOR("Jason A. Donenfeld <Jason@zx2c4.com>");
diff --git a/drivers/net/wireguard/queueing.c b/drivers/net/wireguard/queueing.c
index 48e7b982a307..1de413b19e34 100644
--- a/drivers/net/wireguard/queueing.c
+++ b/drivers/net/wireguard/queueing.c
@@ -38,11 +38,11 @@ int wg_packet_queue_init(struct crypt_queue *queue, work_func_t function,
 	return 0;
 }
 
-void wg_packet_queue_free(struct crypt_queue *queue)
+void wg_packet_queue_free(struct crypt_queue *queue, bool purge)
 {
 	free_percpu(queue->worker);
-	WARN_ON(!__ptr_ring_empty(&queue->ring));
-	ptr_ring_cleanup(&queue->ring, NULL);
+	WARN_ON(!purge && !__ptr_ring_empty(&queue->ring));
+	ptr_ring_cleanup(&queue->ring, purge ? (void(*)(void*))kfree_skb : NULL);
 }
 
 #define NEXT(skb) ((skb)->prev)
diff --git a/drivers/net/wireguard/queueing.h b/drivers/net/wireguard/queueing.h
index 4ef2944a68bc..e2388107f7fd 100644
--- a/drivers/net/wireguard/queueing.h
+++ b/drivers/net/wireguard/queueing.h
@@ -23,7 +23,7 @@ struct sk_buff;
 /* queueing.c APIs: */
 int wg_packet_queue_init(struct crypt_queue *queue, work_func_t function,
 			 unsigned int len);
-void wg_packet_queue_free(struct crypt_queue *queue);
+void wg_packet_queue_free(struct crypt_queue *queue, bool purge);
 struct multicore_worker __percpu *
 wg_packet_percpu_multicore_worker_alloc(work_func_t function, void *ptr);
 
diff --git a/drivers/net/wireguard/ratelimiter.c b/drivers/net/wireguard/ratelimiter.c
index 3fedd1d21f5e..dd55e5c26f46 100644
--- a/drivers/net/wireguard/ratelimiter.c
+++ b/drivers/net/wireguard/ratelimiter.c
@@ -176,12 +176,12 @@ int wg_ratelimiter_init(void)
 			(1U << 14) / sizeof(struct hlist_head)));
 	max_entries = table_size * 8;
 
-	table_v4 = kvzalloc(table_size * sizeof(*table_v4), GFP_KERNEL);
+	table_v4 = kvcalloc(table_size, sizeof(*table_v4), GFP_KERNEL);
 	if (unlikely(!table_v4))
 		goto err_kmemcache;
 
 #if IS_ENABLED(CONFIG_IPV6)
-	table_v6 = kvzalloc(table_size * sizeof(*table_v6), GFP_KERNEL);
+	table_v6 = kvcalloc(table_size, sizeof(*table_v6), GFP_KERNEL);
 	if (unlikely(!table_v6)) {
 		kvfree(table_v4);
 		goto err_kmemcache;
diff --git a/drivers/net/wireguard/receive.c b/drivers/net/wireguard/receive.c
index 7dc84bcca261..7b8df406c773 100644
--- a/drivers/net/wireguard/receive.c
+++ b/drivers/net/wireguard/receive.c
@@ -116,8 +116,8 @@ static void wg_receive_handshake_packet(struct wg_device *wg,
 		return;
 	}
 
-	under_load = skb_queue_len(&wg->incoming_handshakes) >=
-		     MAX_QUEUED_INCOMING_HANDSHAKES / 8;
+	under_load = atomic_read(&wg->handshake_queue_len) >=
+			MAX_QUEUED_INCOMING_HANDSHAKES / 8;
 	if (under_load) {
 		last_under_load = ktime_get_coarse_boottime_ns();
 	} else if (last_under_load) {
@@ -212,13 +212,14 @@ static void wg_receive_handshake_packet(struct wg_device *wg,
 
 void wg_packet_handshake_receive_worker(struct work_struct *work)
 {
-	struct wg_device *wg = container_of(work, struct multicore_worker,
-					    work)->ptr;
+	struct crypt_queue *queue = container_of(work, struct multicore_worker, work)->ptr;
+	struct wg_device *wg = container_of(queue, struct wg_device, handshake_queue);
 	struct sk_buff *skb;
 
-	while ((skb = skb_dequeue(&wg->incoming_handshakes)) != NULL) {
+	while ((skb = ptr_ring_consume_bh(&queue->ring)) != NULL) {
 		wg_receive_handshake_packet(wg, skb);
 		dev_kfree_skb(skb);
+		atomic_dec(&wg->handshake_queue_len);
 		cond_resched();
 	}
 }
@@ -553,22 +554,28 @@ void wg_packet_receive(struct wg_device *wg, struct sk_buff *skb)
 	case cpu_to_le32(MESSAGE_HANDSHAKE_INITIATION):
 	case cpu_to_le32(MESSAGE_HANDSHAKE_RESPONSE):
 	case cpu_to_le32(MESSAGE_HANDSHAKE_COOKIE): {
-		int cpu;
-
-		if (skb_queue_len(&wg->incoming_handshakes) >
-			    MAX_QUEUED_INCOMING_HANDSHAKES ||
-		    unlikely(!rng_is_initialized())) {
+		int cpu, ret = -EBUSY;
+
+		if (unlikely(!rng_is_initialized()))
+			goto drop;
+		if (atomic_read(&wg->handshake_queue_len) > MAX_QUEUED_INCOMING_HANDSHAKES / 2) {
+			if (spin_trylock_bh(&wg->handshake_queue.ring.producer_lock)) {
+				ret = __ptr_ring_produce(&wg->handshake_queue.ring, skb);
+				spin_unlock_bh(&wg->handshake_queue.ring.producer_lock);
+			}
+		} else
+			ret = ptr_ring_produce_bh(&wg->handshake_queue.ring, skb);
+		if (ret) {
+	drop:
 			net_dbg_skb_ratelimited("%s: Dropping handshake packet from %pISpfsc\n",
 						wg->dev->name, skb);
 			goto err;
 		}
-		skb_queue_tail(&wg->incoming_handshakes, skb);
-		/* Queues up a call to packet_process_queued_handshake_
-		 * packets(skb):
-		 */
-		cpu = wg_cpumask_next_online(&wg->incoming_handshake_cpu);
+		atomic_inc(&wg->handshake_queue_len);
+		cpu = wg_cpumask_next_online(&wg->handshake_queue.last_cpu);
+		/* Queues up a call to packet_process_queued_handshake_packets(skb): */
 		queue_work_on(cpu, wg->handshake_receive_wq,
-			&per_cpu_ptr(wg->incoming_handshakes_worker, cpu)->work);
+			      &per_cpu_ptr(wg->handshake_queue.worker, cpu)->work);
 		break;
 	}
 	case cpu_to_le32(MESSAGE_DATA):
diff --git a/drivers/net/wireguard/socket.c b/drivers/net/wireguard/socket.c
index 8c496b747108..6f07b949cb81 100644
--- a/drivers/net/wireguard/socket.c
+++ b/drivers/net/wireguard/socket.c
@@ -308,7 +308,7 @@ void wg_socket_clear_peer_endpoint_src(struct wg_peer *peer)
 {
 	write_lock_bh(&peer->endpoint_lock);
 	memset(&peer->endpoint.src6, 0, sizeof(peer->endpoint.src6));
-	dst_cache_reset(&peer->endpoint_cache);
+	dst_cache_reset_now(&peer->endpoint_cache);
 	write_unlock_bh(&peer->endpoint_lock);
 }
 
diff --git a/drivers/net/wireless/ath/ath11k/mhi.c b/drivers/net/wireless/ath/ath11k/mhi.c
index 26c7ae242db6..49c0b1ad40a0 100644
--- a/drivers/net/wireless/ath/ath11k/mhi.c
+++ b/drivers/net/wireless/ath/ath11k/mhi.c
@@ -533,7 +533,11 @@ static int ath11k_mhi_set_state(struct ath11k_pci *ab_pci,
 		ret = mhi_pm_suspend(ab_pci->mhi_ctrl);
 		break;
 	case ATH11K_MHI_RESUME:
-		ret = mhi_pm_resume(ab_pci->mhi_ctrl);
+		/* Do force MHI resume as some devices like QCA6390, WCN6855
+		 * are not in M3 state but they are functional. So just ignore
+		 * the MHI state while resuming.
+		 */
+		ret = mhi_pm_resume_force(ab_pci->mhi_ctrl);
 		break;
 	case ATH11K_MHI_TRIGGER_RDDM:
 		ret = mhi_force_rddm_mode(ab_pci->mhi_ctrl);
diff --git a/drivers/net/wireless/broadcom/brcm80211/Kconfig b/drivers/net/wireless/broadcom/brcm80211/Kconfig
index 5bf2318763c5..3a1a35b5672f 100644
--- a/drivers/net/wireless/broadcom/brcm80211/Kconfig
+++ b/drivers/net/wireless/broadcom/brcm80211/Kconfig
@@ -7,16 +7,20 @@ config BRCMSMAC
 	depends on MAC80211
 	depends on BCMA_POSSIBLE
 	select BCMA
-	select NEW_LEDS if BCMA_DRIVER_GPIO
-	select LEDS_CLASS if BCMA_DRIVER_GPIO
 	select BRCMUTIL
 	select FW_LOADER
 	select CORDIC
 	help
 	  This module adds support for PCIe wireless adapters based on Broadcom
-	  IEEE802.11n SoftMAC chipsets. It also has WLAN led support, which will
-	  be available if you select BCMA_DRIVER_GPIO. If you choose to build a
-	  module, the driver will be called brcmsmac.ko.
+	  IEEE802.11n SoftMAC chipsets. If you choose to build a module, the
+	  driver will be called brcmsmac.ko.
+
+config BRCMSMAC_LEDS
+	def_bool BRCMSMAC && BCMA_DRIVER_GPIO && MAC80211_LEDS
+	help
+	  The brcmsmac LED support depends on the presence of the
+	  BCMA_DRIVER_GPIO driver, and it only works if LED support
+	  is enabled and reachable from the driver module.
 
 source "drivers/net/wireless/broadcom/brcm80211/brcmfmac/Kconfig"
 
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/Makefile b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/Makefile
index 482d7737764d..090757730ba6 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/Makefile
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/Makefile
@@ -42,6 +42,6 @@ brcmsmac-y := \
 	brcms_trace_events.o \
 	debug.o
 
-brcmsmac-$(CONFIG_BCMA_DRIVER_GPIO) += led.o
+brcmsmac-$(CONFIG_BRCMSMAC_LEDS) += led.o
 
 obj-$(CONFIG_BRCMSMAC)	+= brcmsmac.o
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/led.h b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/led.h
index d65f5c268fd7..2a5cbeb9e783 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/led.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/led.h
@@ -24,7 +24,7 @@ struct brcms_led {
 	struct gpio_desc *gpiod;
 };
 
-#ifdef CONFIG_BCMA_DRIVER_GPIO
+#ifdef CONFIG_BRCMSMAC_LEDS
 void brcms_led_unregister(struct brcms_info *wl);
 int brcms_led_register(struct brcms_info *wl);
 #else
diff --git a/drivers/net/wireless/intel/iwlegacy/Kconfig b/drivers/net/wireless/intel/iwlegacy/Kconfig
index 24fe3f63c321..7eacc8e58ee1 100644
--- a/drivers/net/wireless/intel/iwlegacy/Kconfig
+++ b/drivers/net/wireless/intel/iwlegacy/Kconfig
@@ -2,14 +2,13 @@
 config IWLEGACY
 	tristate
 	select FW_LOADER
-	select NEW_LEDS
-	select LEDS_CLASS
 	select LEDS_TRIGGERS
 	select MAC80211_LEDS
 
 config IWL4965
 	tristate "Intel Wireless WiFi 4965AGN (iwl4965)"
 	depends on PCI && MAC80211
+	depends on LEDS_CLASS=y || LEDS_CLASS=MAC80211
 	select IWLEGACY
 	help
 	  This option enables support for
@@ -38,6 +37,7 @@ config IWL4965
 config IWL3945
 	tristate "Intel PRO/Wireless 3945ABG/BG Network Connection (iwl3945)"
 	depends on PCI && MAC80211
+	depends on LEDS_CLASS=y || LEDS_CLASS=MAC80211
 	select IWLEGACY
 	help
 	  Select to build the driver supporting the:
diff --git a/drivers/net/wireless/intel/iwlwifi/Kconfig b/drivers/net/wireless/intel/iwlwifi/Kconfig
index 1085afbefba8..418ae4f870ab 100644
--- a/drivers/net/wireless/intel/iwlwifi/Kconfig
+++ b/drivers/net/wireless/intel/iwlwifi/Kconfig
@@ -47,7 +47,7 @@ if IWLWIFI
 
 config IWLWIFI_LEDS
 	bool
-	depends on LEDS_CLASS=y || LEDS_CLASS=IWLWIFI
+	depends on LEDS_CLASS=y || LEDS_CLASS=MAC80211
 	depends on IWLMVM || IWLDVM
 	select LEDS_TRIGGERS
 	select MAC80211_LEDS
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/uefi.c b/drivers/net/wireless/intel/iwlwifi/fw/uefi.c
index c875bf35533c..009dd4be597b 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/uefi.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/uefi.c
@@ -86,6 +86,7 @@ static void *iwl_uefi_reduce_power_section(struct iwl_trans *trans,
 		if (len < tlv_len) {
 			IWL_ERR(trans, "invalid TLV len: %zd/%u\n",
 				len, tlv_len);
+			kfree(reduce_power_data);
 			reduce_power_data = ERR_PTR(-EINVAL);
 			goto out;
 		}
@@ -105,6 +106,7 @@ static void *iwl_uefi_reduce_power_section(struct iwl_trans *trans,
 				IWL_DEBUG_FW(trans,
 					     "Couldn't allocate (more) reduce_power_data\n");
 
+				kfree(reduce_power_data);
 				reduce_power_data = ERR_PTR(-ENOMEM);
 				goto out;
 			}
@@ -134,6 +136,10 @@ static void *iwl_uefi_reduce_power_section(struct iwl_trans *trans,
 done:
 	if (!size) {
 		IWL_DEBUG_FW(trans, "Empty REDUCE_POWER, skipping.\n");
+		/* Better safe than sorry, but 'reduce_power_data' should
+		 * always be NULL if !size.
+		 */
+		kfree(reduce_power_data);
 		reduce_power_data = ERR_PTR(-ENOENT);
 		goto out;
 	}
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
index 36196e07b1a0..5cec467b995b 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
@@ -1313,23 +1313,31 @@ _iwl_op_mode_start(struct iwl_drv *drv, struct iwlwifi_opmode_table *op)
 	const struct iwl_op_mode_ops *ops = op->ops;
 	struct dentry *dbgfs_dir = NULL;
 	struct iwl_op_mode *op_mode = NULL;
+	int retry, max_retry = !!iwlwifi_mod_params.fw_restart * IWL_MAX_INIT_RETRY;
+
+	for (retry = 0; retry <= max_retry; retry++) {
 
 #ifdef CONFIG_IWLWIFI_DEBUGFS
-	drv->dbgfs_op_mode = debugfs_create_dir(op->name,
-						drv->dbgfs_drv);
-	dbgfs_dir = drv->dbgfs_op_mode;
+		drv->dbgfs_op_mode = debugfs_create_dir(op->name,
+							drv->dbgfs_drv);
+		dbgfs_dir = drv->dbgfs_op_mode;
 #endif
 
-	op_mode = ops->start(drv->trans, drv->trans->cfg, &drv->fw, dbgfs_dir);
+		op_mode = ops->start(drv->trans, drv->trans->cfg,
+				     &drv->fw, dbgfs_dir);
+
+		if (op_mode)
+			return op_mode;
+
+		IWL_ERR(drv, "retry init count %d\n", retry);
 
 #ifdef CONFIG_IWLWIFI_DEBUGFS
-	if (!op_mode) {
 		debugfs_remove_recursive(drv->dbgfs_op_mode);
 		drv->dbgfs_op_mode = NULL;
-	}
 #endif
+	}
 
-	return op_mode;
+	return NULL;
 }
 
 static void _iwl_op_mode_stop(struct iwl_drv *drv)
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.h b/drivers/net/wireless/intel/iwlwifi/iwl-drv.h
index 2e2d60a58692..0fd009e6d685 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.h
@@ -89,4 +89,7 @@ void iwl_drv_stop(struct iwl_drv *drv);
 #define IWL_EXPORT_SYMBOL(sym)
 #endif
 
+/* max retry for init flow */
+#define IWL_MAX_INIT_RETRY 2
+
 #endif /* __iwl_drv_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index 9fb9c7dad314..897e3b91ddb2 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -16,6 +16,7 @@
 #include <net/ieee80211_radiotap.h>
 #include <net/tcp.h>
 
+#include "iwl-drv.h"
 #include "iwl-op-mode.h"
 #include "iwl-io.h"
 #include "mvm.h"
@@ -1117,9 +1118,30 @@ static int iwl_mvm_mac_start(struct ieee80211_hw *hw)
 {
 	struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
 	int ret;
+	int retry, max_retry = 0;
 
 	mutex_lock(&mvm->mutex);
-	ret = __iwl_mvm_mac_start(mvm);
+
+	/* we are starting the mac not in error flow, and restart is enabled */
+	if (!test_bit(IWL_MVM_STATUS_HW_RESTART_REQUESTED, &mvm->status) &&
+	    iwlwifi_mod_params.fw_restart) {
+		max_retry = IWL_MAX_INIT_RETRY;
+		/*
+		 * This will prevent mac80211 recovery flows to trigger during
+		 * init failures
+		 */
+		set_bit(IWL_MVM_STATUS_STARTING, &mvm->status);
+	}
+
+	for (retry = 0; retry <= max_retry; retry++) {
+		ret = __iwl_mvm_mac_start(mvm);
+		if (!ret)
+			break;
+
+		IWL_ERR(mvm, "mac start retry %d\n", retry);
+	}
+	clear_bit(IWL_MVM_STATUS_STARTING, &mvm->status);
+
 	mutex_unlock(&mvm->mutex);
 
 	return ret;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
index 2b1dcd60e00f..a72d85086fe3 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
@@ -1123,6 +1123,8 @@ struct iwl_mvm {
  * @IWL_MVM_STATUS_FIRMWARE_RUNNING: firmware is running
  * @IWL_MVM_STATUS_NEED_FLUSH_P2P: need to flush P2P bcast STA
  * @IWL_MVM_STATUS_IN_D3: in D3 (or at least about to go into it)
+ * @IWL_MVM_STATUS_STARTING: starting mac,
+ *	used to disable restart flow while in STARTING state
  */
 enum iwl_mvm_status {
 	IWL_MVM_STATUS_HW_RFKILL,
@@ -1134,6 +1136,7 @@ enum iwl_mvm_status {
 	IWL_MVM_STATUS_FIRMWARE_RUNNING,
 	IWL_MVM_STATUS_NEED_FLUSH_P2P,
 	IWL_MVM_STATUS_IN_D3,
+	IWL_MVM_STATUS_STARTING,
 };
 
 /* Keep track of completed init configuration */
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
index 232ad531d612..cd08e289cd9a 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
@@ -686,6 +686,7 @@ static int iwl_mvm_start_get_nvm(struct iwl_mvm *mvm)
 	int ret;
 
 	rtnl_lock();
+	wiphy_lock(mvm->hw->wiphy);
 	mutex_lock(&mvm->mutex);
 
 	ret = iwl_run_init_mvm_ucode(mvm);
@@ -701,6 +702,7 @@ static int iwl_mvm_start_get_nvm(struct iwl_mvm *mvm)
 		iwl_mvm_stop_device(mvm);
 
 	mutex_unlock(&mvm->mutex);
+	wiphy_unlock(mvm->hw->wiphy);
 	rtnl_unlock();
 
 	if (ret < 0)
@@ -1600,6 +1602,9 @@ void iwl_mvm_nic_restart(struct iwl_mvm *mvm, bool fw_error)
 	 */
 	if (!mvm->fw_restart && fw_error) {
 		iwl_fw_error_collect(&mvm->fwrt, false);
+	} else if (test_bit(IWL_MVM_STATUS_STARTING,
+			    &mvm->status)) {
+		IWL_ERR(mvm, "Starting mac, retry will be triggered anyway\n");
 	} else if (test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status)) {
 		struct iwl_mvm_reprobe *reprobe;
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
index bdd4ee432548..76e0b7b45980 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
@@ -269,17 +269,18 @@ static u32 iwl_mvm_get_tx_rate(struct iwl_mvm *mvm,
 	u8 rate_plcp;
 	u32 rate_flags = 0;
 	bool is_cck;
-	struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta);
 
 	/* info->control is only relevant for non HW rate control */
 	if (!ieee80211_hw_check(mvm->hw, HAS_RATE_CONTROL)) {
+		struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta);
+
 		/* HT rate doesn't make sense for a non data frame */
 		WARN_ONCE(info->control.rates[0].flags & IEEE80211_TX_RC_MCS &&
 			  !ieee80211_is_data(fc),
 			  "Got a HT rate (flags:0x%x/mcs:%d/fc:0x%x/state:%d) for a non data frame\n",
 			  info->control.rates[0].flags,
 			  info->control.rates[0].idx,
-			  le16_to_cpu(fc), mvmsta->sta_state);
+			  le16_to_cpu(fc), sta ? mvmsta->sta_state : -1);
 
 		rate_idx = info->control.rates[0].idx;
 	}
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
index c574f041f096..5ce07f28e7c3 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
@@ -1339,9 +1339,13 @@ iwl_pci_find_dev_info(u16 device, u16 subsystem_device,
 		      u16 mac_type, u8 mac_step,
 		      u16 rf_type, u8 cdb, u8 rf_id, u8 no_160, u8 cores)
 {
+	int num_devices = ARRAY_SIZE(iwl_dev_info_table);
 	int i;
 
-	for (i = ARRAY_SIZE(iwl_dev_info_table) - 1; i >= 0; i--) {
+	if (!num_devices)
+		return NULL;
+
+	for (i = num_devices - 1; i >= 0; i--) {
 		const struct iwl_dev_info *dev_info = &iwl_dev_info_table[i];
 
 		if (dev_info->device != (u16)IWL_CFG_ANY &&
@@ -1442,8 +1446,10 @@ static int iwl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	 */
 	if (iwl_trans->trans_cfg->rf_id &&
 	    iwl_trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_9000 &&
-	    !CSR_HW_RFID_TYPE(iwl_trans->hw_rf_id) && get_crf_id(iwl_trans))
+	    !CSR_HW_RFID_TYPE(iwl_trans->hw_rf_id) && get_crf_id(iwl_trans)) {
+		ret = -EINVAL;
 		goto out_free_trans;
+	}
 
 	dev_info = iwl_pci_find_dev_info(pdev->device, pdev->subsystem_device,
 					 CSR_HW_REV_TYPE(iwl_trans->hw_rev),
diff --git a/drivers/net/wireless/mediatek/mt76/Makefile b/drivers/net/wireless/mediatek/mt76/Makefile
index 79ab850a45a2..c78ae4b89761 100644
--- a/drivers/net/wireless/mediatek/mt76/Makefile
+++ b/drivers/net/wireless/mediatek/mt76/Makefile
@@ -34,4 +34,4 @@ obj-$(CONFIG_MT76x2_COMMON) += mt76x2/
 obj-$(CONFIG_MT7603E) += mt7603/
 obj-$(CONFIG_MT7615_COMMON) += mt7615/
 obj-$(CONFIG_MT7915E) += mt7915/
-obj-$(CONFIG_MT7921E) += mt7921/
+obj-$(CONFIG_MT7921_COMMON) += mt7921/
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/pci_mac.c b/drivers/net/wireless/mediatek/mt76/mt7615/pci_mac.c
index 5ee52cd70a4b..d1806f198aed 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/pci_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/pci_mac.c
@@ -143,8 +143,6 @@ int mt7615_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr,
 	if (!wcid)
 		wcid = &dev->mt76.global_wcid;
 
-	pid = mt76_tx_status_skb_add(mdev, wcid, tx_info->skb);
-
 	if ((info->flags & IEEE80211_TX_CTL_RATE_CTRL_PROBE) && msta) {
 		struct mt7615_phy *phy = &dev->phy;
 
@@ -164,6 +162,7 @@ int mt7615_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr,
 	if (id < 0)
 		return id;
 
+	pid = mt76_tx_status_skb_add(mdev, wcid, tx_info->skb);
 	mt7615_mac_write_txwi(dev, txwi_ptr, tx_info->skb, wcid, sta,
 			      pid, key, false);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/usb_sdio.c b/drivers/net/wireless/mediatek/mt76/mt7615/usb_sdio.c
index bd2939ebcbf4..5a6d7829c6e0 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/usb_sdio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/usb_sdio.c
@@ -43,19 +43,11 @@ EXPORT_SYMBOL_GPL(mt7663_usb_sdio_reg_map);
 static void
 mt7663_usb_sdio_write_txwi(struct mt7615_dev *dev, struct mt76_wcid *wcid,
 			   enum mt76_txq_id qid, struct ieee80211_sta *sta,
+			   struct ieee80211_key_conf *key, int pid,
 			   struct sk_buff *skb)
 {
-	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
-	struct ieee80211_key_conf *key = info->control.hw_key;
-	__le32 *txwi;
-	int pid;
-
-	if (!wcid)
-		wcid = &dev->mt76.global_wcid;
-
-	pid = mt76_tx_status_skb_add(&dev->mt76, wcid, skb);
+	__le32 *txwi = (__le32 *)(skb->data - MT_USB_TXD_SIZE);
 
-	txwi = (__le32 *)(skb->data - MT_USB_TXD_SIZE);
 	memset(txwi, 0, MT_USB_TXD_SIZE);
 	mt7615_mac_write_txwi(dev, txwi, skb, wcid, sta, pid, key, false);
 	skb_push(skb, MT_USB_TXD_SIZE);
@@ -194,10 +186,14 @@ int mt7663_usb_sdio_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr,
 	struct mt7615_dev *dev = container_of(mdev, struct mt7615_dev, mt76);
 	struct sk_buff *skb = tx_info->skb;
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+	struct ieee80211_key_conf *key = info->control.hw_key;
 	struct mt7615_sta *msta;
-	int pad;
+	int pad, err, pktid;
 
 	msta = wcid ? container_of(wcid, struct mt7615_sta, wcid) : NULL;
+	if (!wcid)
+		wcid = &dev->mt76.global_wcid;
+
 	if ((info->flags & IEEE80211_TX_CTL_RATE_CTRL_PROBE) &&
 	    msta && !msta->rate_probe) {
 		/* request to configure sampling rate */
@@ -207,7 +203,8 @@ int mt7663_usb_sdio_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr,
 		spin_unlock_bh(&dev->mt76.lock);
 	}
 
-	mt7663_usb_sdio_write_txwi(dev, wcid, qid, sta, skb);
+	pktid = mt76_tx_status_skb_add(&dev->mt76, wcid, skb);
+	mt7663_usb_sdio_write_txwi(dev, wcid, qid, sta, key, pktid, skb);
 	if (mt76_is_usb(mdev)) {
 		u32 len = skb->len;
 
@@ -217,7 +214,12 @@ int mt7663_usb_sdio_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr,
 		pad = round_up(skb->len, 4) - skb->len;
 	}
 
-	return mt76_skb_adjust_pad(skb, pad);
+	err = mt76_skb_adjust_pad(skb, pad);
+	if (err)
+		/* Release pktid in case of error. */
+		idr_remove(&wcid->pktid, pktid);
+
+	return err;
 }
 EXPORT_SYMBOL_GPL(mt7663_usb_sdio_tx_prepare_skb);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_usb_core.c b/drivers/net/wireless/mediatek/mt76/mt76x02_usb_core.c
index efd70ddc2fd1..2c6c03809b20 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_usb_core.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_usb_core.c
@@ -72,6 +72,7 @@ int mt76x02u_tx_prepare_skb(struct mt76_dev *mdev, void *data,
 	bool ampdu = IEEE80211_SKB_CB(tx_info->skb)->flags & IEEE80211_TX_CTL_AMPDU;
 	enum mt76_qsel qsel;
 	u32 flags;
+	int err;
 
 	mt76_insert_hdr_pad(tx_info->skb);
 
@@ -106,7 +107,12 @@ int mt76x02u_tx_prepare_skb(struct mt76_dev *mdev, void *data,
 		ewma_pktlen_add(&msta->pktlen, tx_info->skb->len);
 	}
 
-	return mt76x02u_skb_dma_info(tx_info->skb, WLAN_PORT, flags);
+	err = mt76x02u_skb_dma_info(tx_info->skb, WLAN_PORT, flags);
+	if (err && wcid)
+		/* Release pktid in case of error. */
+		idr_remove(&wcid->pktid, pid);
+
+	return err;
 }
 EXPORT_SYMBOL_GPL(mt76x02u_tx_prepare_skb);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
index 5fcf35f2d9fb..809dc18e5083 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
@@ -1151,8 +1151,14 @@ int mt7915_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr,
 		}
 	}
 
-	pid = mt76_tx_status_skb_add(mdev, wcid, tx_info->skb);
+	t = (struct mt76_txwi_cache *)(txwi + mdev->drv->txwi_size);
+	t->skb = tx_info->skb;
+
+	id = mt76_token_consume(mdev, &t);
+	if (id < 0)
+		return id;
 
+	pid = mt76_tx_status_skb_add(mdev, wcid, tx_info->skb);
 	mt7915_mac_write_txwi(dev, txwi_ptr, tx_info->skb, wcid, pid, key,
 			      false);
 
@@ -1178,13 +1184,6 @@ int mt7915_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr,
 		txp->bss_idx = mvif->idx;
 	}
 
-	t = (struct mt76_txwi_cache *)(txwi + mdev->drv->txwi_size);
-	t->skb = tx_info->skb;
-
-	id = mt76_token_consume(mdev, &t);
-	if (id < 0)
-		return id;
-
 	txp->token = cpu_to_le16(id);
 	if (test_bit(MT_WCID_FLAG_4ADDR, &wcid->flags))
 		txp->rept_wds_wcid = cpu_to_le16(wcid->idx);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
index 899957b9d0f1..852d5d97c70b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
@@ -176,7 +176,7 @@ mt7915_get_phy_mode(struct ieee80211_vif *vif, struct ieee80211_sta *sta)
 		if (ht_cap->ht_supported)
 			mode |= PHY_MODE_GN;
 
-		if (he_cap->has_he)
+		if (he_cap && he_cap->has_he)
 			mode |= PHY_MODE_AX_24G;
 	} else if (band == NL80211_BAND_5GHZ) {
 		mode |= PHY_MODE_A;
@@ -187,7 +187,7 @@ mt7915_get_phy_mode(struct ieee80211_vif *vif, struct ieee80211_sta *sta)
 		if (vht_cap->vht_supported)
 			mode |= PHY_MODE_AC;
 
-		if (he_cap->has_he)
+		if (he_cap && he_cap->has_he)
 			mode |= PHY_MODE_AX_5G;
 	}
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/sdio_mac.c b/drivers/net/wireless/mediatek/mt76/mt7921/sdio_mac.c
index 137f86a6dbf8..bdec508b6b9f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/sdio_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/sdio_mac.c
@@ -142,15 +142,11 @@ out:
 static void
 mt7921s_write_txwi(struct mt7921_dev *dev, struct mt76_wcid *wcid,
 		   enum mt76_txq_id qid, struct ieee80211_sta *sta,
+		   struct ieee80211_key_conf *key, int pid,
 		   struct sk_buff *skb)
 {
-	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
-	struct ieee80211_key_conf *key = info->control.hw_key;
-	__le32 *txwi;
-	int pid;
+	__le32 *txwi = (__le32 *)(skb->data - MT_SDIO_TXD_SIZE);
 
-	pid = mt76_tx_status_skb_add(&dev->mt76, wcid, skb);
-	txwi = (__le32 *)(skb->data - MT_SDIO_TXD_SIZE);
 	memset(txwi, 0, MT_SDIO_TXD_SIZE);
 	mt7921_mac_write_txwi(dev, txwi, skb, wcid, key, pid, false);
 	skb_push(skb, MT_SDIO_TXD_SIZE);
@@ -163,8 +159,9 @@ int mt7921s_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr,
 {
 	struct mt7921_dev *dev = container_of(mdev, struct mt7921_dev, mt76);
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx_info->skb);
+	struct ieee80211_key_conf *key = info->control.hw_key;
 	struct sk_buff *skb = tx_info->skb;
-	int pad;
+	int err, pad, pktid;
 
 	if (unlikely(tx_info->skb->len <= ETH_HLEN))
 		return -EINVAL;
@@ -181,12 +178,18 @@ int mt7921s_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr,
 		}
 	}
 
-	mt7921s_write_txwi(dev, wcid, qid, sta, skb);
+	pktid = mt76_tx_status_skb_add(&dev->mt76, wcid, skb);
+	mt7921s_write_txwi(dev, wcid, qid, sta, key, pktid, skb);
 
 	mt7921_skb_add_sdio_hdr(skb, MT7921_SDIO_DATA);
 	pad = round_up(skb->len, 4) - skb->len;
 
-	return mt76_skb_adjust_pad(skb, pad);
+	err = mt76_skb_adjust_pad(skb, pad);
+	if (err)
+		/* Release pktid in case of error. */
+		idr_remove(&wcid->pktid, pktid);
+
+	return err;
 }
 
 void mt7921s_tx_complete_skb(struct mt76_dev *mdev, struct mt76_queue_entry *e)
diff --git a/drivers/net/wireless/mediatek/mt76/tx.c b/drivers/net/wireless/mediatek/mt76/tx.c
index 11719ef034d8..6b8c9dc80542 100644
--- a/drivers/net/wireless/mediatek/mt76/tx.c
+++ b/drivers/net/wireless/mediatek/mt76/tx.c
@@ -173,7 +173,7 @@ mt76_tx_status_skb_get(struct mt76_dev *dev, struct mt76_wcid *wcid, int pktid,
 			if (!(cb->flags & MT_TX_CB_DMA_DONE))
 				continue;
 
-			if (!time_is_after_jiffies(cb->jiffies +
+			if (time_is_after_jiffies(cb->jiffies +
 						   MT_TX_STATUS_SKB_TIMEOUT))
 				continue;
 		}
diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00usb.c b/drivers/net/wireless/ralink/rt2x00/rt2x00usb.c
index e4473a551241..74c3d8cb3100 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2x00usb.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt2x00usb.c
@@ -25,6 +25,9 @@ static bool rt2x00usb_check_usb_error(struct rt2x00_dev *rt2x00dev, int status)
 	if (status == -ENODEV || status == -ENOENT)
 		return true;
 
+	if (!test_bit(DEVICE_STATE_STARTED, &rt2x00dev->flags))
+		return false;
+
 	if (status == -EPROTO || status == -ETIMEDOUT)
 		rt2x00dev->num_proto_errs++;
 	else
diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index 212aaf577d3c..65ef3dc9d061 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -91,7 +91,6 @@ static int rtw89_fw_hdr_parser(struct rtw89_dev *rtwdev, const u8 *fw, u32 len,
 	info->section_num = GET_FW_HDR_SEC_NUM(fw);
 	info->hdr_len = RTW89_FW_HDR_SIZE +
 			info->section_num * RTW89_FW_SECTION_HDR_SIZE;
-	SET_FW_HDR_PART_SIZE(fw, FWDL_SECTION_PER_PKT_LEN);
 
 	bin = fw + info->hdr_len;
 
@@ -275,6 +274,7 @@ static int __rtw89_fw_download_hdr(struct rtw89_dev *rtwdev, const u8 *fw, u32 l
 	}
 
 	skb_put_data(skb, fw, len);
+	SET_FW_HDR_PART_SIZE(skb->data, FWDL_SECTION_PER_PKT_LEN);
 	rtw89_h2c_pkt_set_hdr_fwdl(rtwdev, skb, FWCMD_TYPE_H2C,
 				   H2C_CAT_MAC, H2C_CL_MAC_FWDL,
 				   H2C_FUNC_MAC_FWHDR_DL, len);
diff --git a/drivers/net/wireless/realtek/rtw89/fw.h b/drivers/net/wireless/realtek/rtw89/fw.h
index 7ee0d9323310..36e8d0da6c1e 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.h
+++ b/drivers/net/wireless/realtek/rtw89/fw.h
@@ -282,8 +282,10 @@ struct rtw89_h2creg_sch_tx_en {
 	le32_get_bits(*((__le32 *)(fwhdr) + 6), GENMASK(15, 8))
 #define GET_FW_HDR_CMD_VERSERION(fwhdr)	\
 	le32_get_bits(*((__le32 *)(fwhdr) + 7), GENMASK(31, 24))
-#define SET_FW_HDR_PART_SIZE(fwhdr, val)	\
-	le32p_replace_bits((__le32 *)(fwhdr) + 7, val, GENMASK(15, 0))
+static inline void SET_FW_HDR_PART_SIZE(void *fwhdr, u32 val)
+{
+	le32p_replace_bits((__le32 *)fwhdr + 7, val, GENMASK(15, 0));
+}
 
 #define SET_CTRL_INFO_MACID(table, val) \
 	le32p_replace_bits((__le32 *)(table) + 0, val, GENMASK(6, 0))
diff --git a/drivers/net/wwan/iosm/iosm_ipc_imem.c b/drivers/net/wwan/iosm/iosm_ipc_imem.c
index cff3b43ca4d7..12c03dacb5dd 100644
--- a/drivers/net/wwan/iosm/iosm_ipc_imem.c
+++ b/drivers/net/wwan/iosm/iosm_ipc_imem.c
@@ -181,9 +181,9 @@ void ipc_imem_hrtimer_stop(struct hrtimer *hr_timer)
 bool ipc_imem_ul_write_td(struct iosm_imem *ipc_imem)
 {
 	struct ipc_mem_channel *channel;
+	bool hpda_ctrl_pending = false;
 	struct sk_buff_head *ul_list;
 	bool hpda_pending = false;
-	bool forced_hpdu = false;
 	struct ipc_pipe *pipe;
 	int i;
 
@@ -200,15 +200,19 @@ bool ipc_imem_ul_write_td(struct iosm_imem *ipc_imem)
 		ul_list = &channel->ul_list;
 
 		/* Fill the transfer descriptor with the uplink buffer info. */
-		hpda_pending |= ipc_protocol_ul_td_send(ipc_imem->ipc_protocol,
+		if (!ipc_imem_check_wwan_ips(channel)) {
+			hpda_ctrl_pending |=
+				ipc_protocol_ul_td_send(ipc_imem->ipc_protocol,
 							pipe, ul_list);
-
-		/* forced HP update needed for non data channels */
-		if (hpda_pending && !ipc_imem_check_wwan_ips(channel))
-			forced_hpdu = true;
+		} else {
+			hpda_pending |=
+				ipc_protocol_ul_td_send(ipc_imem->ipc_protocol,
+							pipe, ul_list);
+		}
 	}
 
-	if (forced_hpdu) {
+	/* forced HP update needed for non data channels */
+	if (hpda_ctrl_pending) {
 		hpda_pending = false;
 		ipc_protocol_doorbell_trigger(ipc_imem->ipc_protocol,
 					      IPC_HP_UL_WRITE_TD);
@@ -527,6 +531,9 @@ static void ipc_imem_run_state_worker(struct work_struct *instance)
 		return;
 	}
 
+	if (test_and_clear_bit(IOSM_DEVLINK_INIT, &ipc_imem->flag))
+		ipc_devlink_deinit(ipc_imem->ipc_devlink);
+
 	if (!ipc_imem_setup_cp_mux_cap_init(ipc_imem, &mux_cfg))
 		ipc_imem->mux = ipc_mux_init(&mux_cfg, ipc_imem);
 
@@ -1167,7 +1174,7 @@ void ipc_imem_cleanup(struct iosm_imem *ipc_imem)
 		ipc_port_deinit(ipc_imem->ipc_port);
 	}
 
-	if (ipc_imem->ipc_devlink)
+	if (test_and_clear_bit(IOSM_DEVLINK_INIT, &ipc_imem->flag))
 		ipc_devlink_deinit(ipc_imem->ipc_devlink);
 
 	ipc_imem_device_ipc_uninit(ipc_imem);
@@ -1263,7 +1270,6 @@ struct iosm_imem *ipc_imem_init(struct iosm_pcie *pcie, unsigned int device_id,
 
 	ipc_imem->pci_device_id = device_id;
 
-	ipc_imem->ev_cdev_write_pending = false;
 	ipc_imem->cp_version = 0;
 	ipc_imem->device_sleep = IPC_HOST_SLEEP_ENTER_SLEEP;
 
@@ -1331,6 +1337,8 @@ struct iosm_imem *ipc_imem_init(struct iosm_pcie *pcie, unsigned int device_id,
 
 		if (ipc_flash_link_establish(ipc_imem))
 			goto devlink_channel_fail;
+
+		set_bit(IOSM_DEVLINK_INIT, &ipc_imem->flag);
 	}
 	return ipc_imem;
 devlink_channel_fail:
diff --git a/drivers/net/wwan/iosm/iosm_ipc_imem.h b/drivers/net/wwan/iosm/iosm_ipc_imem.h
index 6be6708b4eec..6b8a837faef2 100644
--- a/drivers/net/wwan/iosm/iosm_ipc_imem.h
+++ b/drivers/net/wwan/iosm/iosm_ipc_imem.h
@@ -101,6 +101,7 @@ struct ipc_chnl_cfg;
 #define IOSM_CHIP_INFO_SIZE_MAX 100
 
 #define FULLY_FUNCTIONAL 0
+#define IOSM_DEVLINK_INIT 1
 
 /* List of the supported UL/DL pipes. */
 enum ipc_mem_pipes {
@@ -335,8 +336,6 @@ enum ipc_phase {
  *				process the irq actions.
  * @flag:			Flag to monitor the state of driver
  * @td_update_timer_suspended:	if true then td update timer suspend
- * @ev_cdev_write_pending:	0 means inform the IPC tasklet to pass
- *				the accumulated uplink buffers to CP.
  * @ev_mux_net_transmit_pending:0 means inform the IPC tasklet to pass
  * @reset_det_n:		Reset detect flag
  * @pcie_wake_n:		Pcie wake flag
@@ -374,7 +373,6 @@ struct iosm_imem {
 	u8 ev_irq_pending[IPC_IRQ_VECTORS];
 	unsigned long flag;
 	u8 td_update_timer_suspended:1,
-	   ev_cdev_write_pending:1,
 	   ev_mux_net_transmit_pending:1,
 	   reset_det_n:1,
 	   pcie_wake_n:1;
diff --git a/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c b/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c
index 825e8e5ffb2a..831cdae28e8a 100644
--- a/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c
+++ b/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c
@@ -41,7 +41,6 @@ void ipc_imem_sys_wwan_close(struct iosm_imem *ipc_imem, int if_id,
 static int ipc_imem_tq_cdev_write(struct iosm_imem *ipc_imem, int arg,
 				  void *msg, size_t size)
 {
-	ipc_imem->ev_cdev_write_pending = false;
 	ipc_imem_ul_send(ipc_imem);
 
 	return 0;
@@ -50,11 +49,6 @@ static int ipc_imem_tq_cdev_write(struct iosm_imem *ipc_imem, int arg,
 /* Through tasklet to do sio write. */
 static int ipc_imem_call_cdev_write(struct iosm_imem *ipc_imem)
 {
-	if (ipc_imem->ev_cdev_write_pending)
-		return -1;
-
-	ipc_imem->ev_cdev_write_pending = true;
-
 	return ipc_task_queue_send_task(ipc_imem, ipc_imem_tq_cdev_write, 0,
 					NULL, 0, false);
 }
@@ -450,6 +444,7 @@ void ipc_imem_sys_devlink_close(struct iosm_devlink *ipc_devlink)
 	/* Release the pipe resources */
 	ipc_imem_pipe_cleanup(ipc_imem, &channel->ul_pipe);
 	ipc_imem_pipe_cleanup(ipc_imem, &channel->dl_pipe);
+	ipc_imem->nr_of_channels--;
 }
 
 void ipc_imem_sys_devlink_notify_rx(struct iosm_devlink *ipc_devlink,
diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h
index 4a16d6e33c09..d9dea4829c86 100644
--- a/drivers/net/xen-netback/common.h
+++ b/drivers/net/xen-netback/common.h
@@ -203,6 +203,7 @@ struct xenvif_queue { /* Per-queue data for xenvif */
 	unsigned int rx_queue_max;
 	unsigned int rx_queue_len;
 	unsigned long last_rx_time;
+	unsigned int rx_slots_needed;
 	bool stalled;
 
 	struct xenvif_copy_state rx_copy;
diff --git a/drivers/net/xen-netback/rx.c b/drivers/net/xen-netback/rx.c
index accc991d153f..dbac4c03d21a 100644
--- a/drivers/net/xen-netback/rx.c
+++ b/drivers/net/xen-netback/rx.c
@@ -33,28 +33,36 @@
 #include <xen/xen.h>
 #include <xen/events.h>
 
-static bool xenvif_rx_ring_slots_available(struct xenvif_queue *queue)
+/*
+ * Update the needed ring page slots for the first SKB queued.
+ * Note that any call sequence outside the RX thread calling this function
+ * needs to wake up the RX thread via a call of xenvif_kick_thread()
+ * afterwards in order to avoid a race with putting the thread to sleep.
+ */
+static void xenvif_update_needed_slots(struct xenvif_queue *queue,
+				       const struct sk_buff *skb)
 {
-	RING_IDX prod, cons;
-	struct sk_buff *skb;
-	int needed;
-	unsigned long flags;
-
-	spin_lock_irqsave(&queue->rx_queue.lock, flags);
+	unsigned int needed = 0;
 
-	skb = skb_peek(&queue->rx_queue);
-	if (!skb) {
-		spin_unlock_irqrestore(&queue->rx_queue.lock, flags);
-		return false;
+	if (skb) {
+		needed = DIV_ROUND_UP(skb->len, XEN_PAGE_SIZE);
+		if (skb_is_gso(skb))
+			needed++;
+		if (skb->sw_hash)
+			needed++;
 	}
 
-	needed = DIV_ROUND_UP(skb->len, XEN_PAGE_SIZE);
-	if (skb_is_gso(skb))
-		needed++;
-	if (skb->sw_hash)
-		needed++;
+	WRITE_ONCE(queue->rx_slots_needed, needed);
+}
 
-	spin_unlock_irqrestore(&queue->rx_queue.lock, flags);
+static bool xenvif_rx_ring_slots_available(struct xenvif_queue *queue)
+{
+	RING_IDX prod, cons;
+	unsigned int needed;
+
+	needed = READ_ONCE(queue->rx_slots_needed);
+	if (!needed)
+		return false;
 
 	do {
 		prod = queue->rx.sring->req_prod;
@@ -80,13 +88,19 @@ void xenvif_rx_queue_tail(struct xenvif_queue *queue, struct sk_buff *skb)
 
 	spin_lock_irqsave(&queue->rx_queue.lock, flags);
 
-	__skb_queue_tail(&queue->rx_queue, skb);
-
-	queue->rx_queue_len += skb->len;
-	if (queue->rx_queue_len > queue->rx_queue_max) {
+	if (queue->rx_queue_len >= queue->rx_queue_max) {
 		struct net_device *dev = queue->vif->dev;
 
 		netif_tx_stop_queue(netdev_get_tx_queue(dev, queue->id));
+		kfree_skb(skb);
+		queue->vif->dev->stats.rx_dropped++;
+	} else {
+		if (skb_queue_empty(&queue->rx_queue))
+			xenvif_update_needed_slots(queue, skb);
+
+		__skb_queue_tail(&queue->rx_queue, skb);
+
+		queue->rx_queue_len += skb->len;
 	}
 
 	spin_unlock_irqrestore(&queue->rx_queue.lock, flags);
@@ -100,6 +114,8 @@ static struct sk_buff *xenvif_rx_dequeue(struct xenvif_queue *queue)
 
 	skb = __skb_dequeue(&queue->rx_queue);
 	if (skb) {
+		xenvif_update_needed_slots(queue, skb_peek(&queue->rx_queue));
+
 		queue->rx_queue_len -= skb->len;
 		if (queue->rx_queue_len < queue->rx_queue_max) {
 			struct netdev_queue *txq;
@@ -134,6 +150,7 @@ static void xenvif_rx_queue_drop_expired(struct xenvif_queue *queue)
 			break;
 		xenvif_rx_dequeue(queue);
 		kfree_skb(skb);
+		queue->vif->dev->stats.rx_dropped++;
 	}
 }
 
@@ -487,27 +504,31 @@ void xenvif_rx_action(struct xenvif_queue *queue)
 	xenvif_rx_copy_flush(queue);
 }
 
-static bool xenvif_rx_queue_stalled(struct xenvif_queue *queue)
+static RING_IDX xenvif_rx_queue_slots(const struct xenvif_queue *queue)
 {
 	RING_IDX prod, cons;
 
 	prod = queue->rx.sring->req_prod;
 	cons = queue->rx.req_cons;
 
+	return prod - cons;
+}
+
+static bool xenvif_rx_queue_stalled(const struct xenvif_queue *queue)
+{
+	unsigned int needed = READ_ONCE(queue->rx_slots_needed);
+
 	return !queue->stalled &&
-		prod - cons < 1 &&
+		xenvif_rx_queue_slots(queue) < needed &&
 		time_after(jiffies,
 			   queue->last_rx_time + queue->vif->stall_timeout);
 }
 
 static bool xenvif_rx_queue_ready(struct xenvif_queue *queue)
 {
-	RING_IDX prod, cons;
-
-	prod = queue->rx.sring->req_prod;
-	cons = queue->rx.req_cons;
+	unsigned int needed = READ_ONCE(queue->rx_slots_needed);
 
-	return queue->stalled && prod - cons >= 1;
+	return queue->stalled && xenvif_rx_queue_slots(queue) >= needed;
 }
 
 bool xenvif_have_rx_work(struct xenvif_queue *queue, bool test_kthread)
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index 911f43986a8c..d514d96027a6 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -148,6 +148,9 @@ struct netfront_queue {
 	grant_ref_t gref_rx_head;
 	grant_ref_t grant_rx_ref[NET_RX_RING_SIZE];
 
+	unsigned int rx_rsp_unconsumed;
+	spinlock_t rx_cons_lock;
+
 	struct page_pool *page_pool;
 	struct xdp_rxq_info xdp_rxq;
 };
@@ -376,12 +379,13 @@ static int xennet_open(struct net_device *dev)
 	return 0;
 }
 
-static void xennet_tx_buf_gc(struct netfront_queue *queue)
+static bool xennet_tx_buf_gc(struct netfront_queue *queue)
 {
 	RING_IDX cons, prod;
 	unsigned short id;
 	struct sk_buff *skb;
 	bool more_to_do;
+	bool work_done = false;
 	const struct device *dev = &queue->info->netdev->dev;
 
 	BUG_ON(!netif_carrier_ok(queue->info->netdev));
@@ -398,6 +402,8 @@ static void xennet_tx_buf_gc(struct netfront_queue *queue)
 		for (cons = queue->tx.rsp_cons; cons != prod; cons++) {
 			struct xen_netif_tx_response txrsp;
 
+			work_done = true;
+
 			RING_COPY_RESPONSE(&queue->tx, cons, &txrsp);
 			if (txrsp.status == XEN_NETIF_RSP_NULL)
 				continue;
@@ -441,11 +447,13 @@ static void xennet_tx_buf_gc(struct netfront_queue *queue)
 
 	xennet_maybe_wake_tx(queue);
 
-	return;
+	return work_done;
 
  err:
 	queue->info->broken = true;
 	dev_alert(dev, "Disabled for further use\n");
+
+	return work_done;
 }
 
 struct xennet_gnttab_make_txreq {
@@ -834,6 +842,16 @@ static int xennet_close(struct net_device *dev)
 	return 0;
 }
 
+static void xennet_set_rx_rsp_cons(struct netfront_queue *queue, RING_IDX val)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&queue->rx_cons_lock, flags);
+	queue->rx.rsp_cons = val;
+	queue->rx_rsp_unconsumed = RING_HAS_UNCONSUMED_RESPONSES(&queue->rx);
+	spin_unlock_irqrestore(&queue->rx_cons_lock, flags);
+}
+
 static void xennet_move_rx_slot(struct netfront_queue *queue, struct sk_buff *skb,
 				grant_ref_t ref)
 {
@@ -885,7 +903,7 @@ static int xennet_get_extras(struct netfront_queue *queue,
 		xennet_move_rx_slot(queue, skb, ref);
 	} while (extra.flags & XEN_NETIF_EXTRA_FLAG_MORE);
 
-	queue->rx.rsp_cons = cons;
+	xennet_set_rx_rsp_cons(queue, cons);
 	return err;
 }
 
@@ -1039,7 +1057,7 @@ next:
 	}
 
 	if (unlikely(err))
-		queue->rx.rsp_cons = cons + slots;
+		xennet_set_rx_rsp_cons(queue, cons + slots);
 
 	return err;
 }
@@ -1093,7 +1111,8 @@ static int xennet_fill_frags(struct netfront_queue *queue,
 			__pskb_pull_tail(skb, pull_to - skb_headlen(skb));
 		}
 		if (unlikely(skb_shinfo(skb)->nr_frags >= MAX_SKB_FRAGS)) {
-			queue->rx.rsp_cons = ++cons + skb_queue_len(list);
+			xennet_set_rx_rsp_cons(queue,
+					       ++cons + skb_queue_len(list));
 			kfree_skb(nskb);
 			return -ENOENT;
 		}
@@ -1106,7 +1125,7 @@ static int xennet_fill_frags(struct netfront_queue *queue,
 		kfree_skb(nskb);
 	}
 
-	queue->rx.rsp_cons = cons;
+	xennet_set_rx_rsp_cons(queue, cons);
 
 	return 0;
 }
@@ -1229,7 +1248,9 @@ err:
 
 			if (unlikely(xennet_set_skb_gso(skb, gso))) {
 				__skb_queue_head(&tmpq, skb);
-				queue->rx.rsp_cons += skb_queue_len(&tmpq);
+				xennet_set_rx_rsp_cons(queue,
+						       queue->rx.rsp_cons +
+						       skb_queue_len(&tmpq));
 				goto err;
 			}
 		}
@@ -1253,7 +1274,8 @@ err:
 
 		__skb_queue_tail(&rxq, skb);
 
-		i = ++queue->rx.rsp_cons;
+		i = queue->rx.rsp_cons + 1;
+		xennet_set_rx_rsp_cons(queue, i);
 		work_done++;
 	}
 	if (need_xdp_flush)
@@ -1417,40 +1439,79 @@ static int xennet_set_features(struct net_device *dev,
 	return 0;
 }
 
-static irqreturn_t xennet_tx_interrupt(int irq, void *dev_id)
+static bool xennet_handle_tx(struct netfront_queue *queue, unsigned int *eoi)
 {
-	struct netfront_queue *queue = dev_id;
 	unsigned long flags;
 
-	if (queue->info->broken)
-		return IRQ_HANDLED;
+	if (unlikely(queue->info->broken))
+		return false;
 
 	spin_lock_irqsave(&queue->tx_lock, flags);
-	xennet_tx_buf_gc(queue);
+	if (xennet_tx_buf_gc(queue))
+		*eoi = 0;
 	spin_unlock_irqrestore(&queue->tx_lock, flags);
 
+	return true;
+}
+
+static irqreturn_t xennet_tx_interrupt(int irq, void *dev_id)
+{
+	unsigned int eoiflag = XEN_EOI_FLAG_SPURIOUS;
+
+	if (likely(xennet_handle_tx(dev_id, &eoiflag)))
+		xen_irq_lateeoi(irq, eoiflag);
+
 	return IRQ_HANDLED;
 }
 
-static irqreturn_t xennet_rx_interrupt(int irq, void *dev_id)
+static bool xennet_handle_rx(struct netfront_queue *queue, unsigned int *eoi)
 {
-	struct netfront_queue *queue = dev_id;
-	struct net_device *dev = queue->info->netdev;
+	unsigned int work_queued;
+	unsigned long flags;
 
-	if (queue->info->broken)
-		return IRQ_HANDLED;
+	if (unlikely(queue->info->broken))
+		return false;
+
+	spin_lock_irqsave(&queue->rx_cons_lock, flags);
+	work_queued = RING_HAS_UNCONSUMED_RESPONSES(&queue->rx);
+	if (work_queued > queue->rx_rsp_unconsumed) {
+		queue->rx_rsp_unconsumed = work_queued;
+		*eoi = 0;
+	} else if (unlikely(work_queued < queue->rx_rsp_unconsumed)) {
+		const struct device *dev = &queue->info->netdev->dev;
+
+		spin_unlock_irqrestore(&queue->rx_cons_lock, flags);
+		dev_alert(dev, "RX producer index going backwards\n");
+		dev_alert(dev, "Disabled for further use\n");
+		queue->info->broken = true;
+		return false;
+	}
+	spin_unlock_irqrestore(&queue->rx_cons_lock, flags);
 
-	if (likely(netif_carrier_ok(dev) &&
-		   RING_HAS_UNCONSUMED_RESPONSES(&queue->rx)))
+	if (likely(netif_carrier_ok(queue->info->netdev) && work_queued))
 		napi_schedule(&queue->napi);
 
+	return true;
+}
+
+static irqreturn_t xennet_rx_interrupt(int irq, void *dev_id)
+{
+	unsigned int eoiflag = XEN_EOI_FLAG_SPURIOUS;
+
+	if (likely(xennet_handle_rx(dev_id, &eoiflag)))
+		xen_irq_lateeoi(irq, eoiflag);
+
 	return IRQ_HANDLED;
 }
 
 static irqreturn_t xennet_interrupt(int irq, void *dev_id)
 {
-	xennet_tx_interrupt(irq, dev_id);
-	xennet_rx_interrupt(irq, dev_id);
+	unsigned int eoiflag = XEN_EOI_FLAG_SPURIOUS;
+
+	if (xennet_handle_tx(dev_id, &eoiflag) &&
+	    xennet_handle_rx(dev_id, &eoiflag))
+		xen_irq_lateeoi(irq, eoiflag);
+
 	return IRQ_HANDLED;
 }
 
@@ -1768,9 +1829,10 @@ static int setup_netfront_single(struct netfront_queue *queue)
 	if (err < 0)
 		goto fail;
 
-	err = bind_evtchn_to_irqhandler(queue->tx_evtchn,
-					xennet_interrupt,
-					0, queue->info->netdev->name, queue);
+	err = bind_evtchn_to_irqhandler_lateeoi(queue->tx_evtchn,
+						xennet_interrupt, 0,
+						queue->info->netdev->name,
+						queue);
 	if (err < 0)
 		goto bind_fail;
 	queue->rx_evtchn = queue->tx_evtchn;
@@ -1798,18 +1860,18 @@ static int setup_netfront_split(struct netfront_queue *queue)
 
 	snprintf(queue->tx_irq_name, sizeof(queue->tx_irq_name),
 		 "%s-tx", queue->name);
-	err = bind_evtchn_to_irqhandler(queue->tx_evtchn,
-					xennet_tx_interrupt,
-					0, queue->tx_irq_name, queue);
+	err = bind_evtchn_to_irqhandler_lateeoi(queue->tx_evtchn,
+						xennet_tx_interrupt, 0,
+						queue->tx_irq_name, queue);
 	if (err < 0)
 		goto bind_tx_fail;
 	queue->tx_irq = err;
 
 	snprintf(queue->rx_irq_name, sizeof(queue->rx_irq_name),
 		 "%s-rx", queue->name);
-	err = bind_evtchn_to_irqhandler(queue->rx_evtchn,
-					xennet_rx_interrupt,
-					0, queue->rx_irq_name, queue);
+	err = bind_evtchn_to_irqhandler_lateeoi(queue->rx_evtchn,
+						xennet_rx_interrupt, 0,
+						queue->rx_irq_name, queue);
 	if (err < 0)
 		goto bind_rx_fail;
 	queue->rx_irq = err;
@@ -1911,6 +1973,7 @@ static int xennet_init_queue(struct netfront_queue *queue)
 
 	spin_lock_init(&queue->tx_lock);
 	spin_lock_init(&queue->rx_lock);
+	spin_lock_init(&queue->rx_cons_lock);
 
 	timer_setup(&queue->rx_refill_timer, rx_refill_timeout, 0);
 
diff --git a/drivers/nfc/st21nfca/i2c.c b/drivers/nfc/st21nfca/i2c.c
index f126ce96a7df..35b32fb90906 100644
--- a/drivers/nfc/st21nfca/i2c.c
+++ b/drivers/nfc/st21nfca/i2c.c
@@ -524,7 +524,8 @@ static int st21nfca_hci_i2c_probe(struct i2c_client *client,
 	phy->gpiod_ena = devm_gpiod_get(dev, "enable", GPIOD_OUT_LOW);
 	if (IS_ERR(phy->gpiod_ena)) {
 		nfc_err(dev, "Unable to get ENABLE GPIO\n");
-		return PTR_ERR(phy->gpiod_ena);
+		r = PTR_ERR(phy->gpiod_ena);
+		goto out_free;
 	}
 
 	phy->se_status.is_ese_present =
@@ -535,7 +536,7 @@ static int st21nfca_hci_i2c_probe(struct i2c_client *client,
 	r = st21nfca_hci_platform_init(phy);
 	if (r < 0) {
 		nfc_err(&client->dev, "Unable to reboot st21nfca\n");
-		return r;
+		goto out_free;
 	}
 
 	r = devm_request_threaded_irq(&client->dev, client->irq, NULL,
@@ -544,15 +545,23 @@ static int st21nfca_hci_i2c_probe(struct i2c_client *client,
 				ST21NFCA_HCI_DRIVER_NAME, phy);
 	if (r < 0) {
 		nfc_err(&client->dev, "Unable to register IRQ handler\n");
-		return r;
+		goto out_free;
 	}
 
-	return st21nfca_hci_probe(phy, &i2c_phy_ops, LLC_SHDLC_NAME,
-					ST21NFCA_FRAME_HEADROOM,
-					ST21NFCA_FRAME_TAILROOM,
-					ST21NFCA_HCI_LLC_MAX_PAYLOAD,
-					&phy->hdev,
-					&phy->se_status);
+	r = st21nfca_hci_probe(phy, &i2c_phy_ops, LLC_SHDLC_NAME,
+			       ST21NFCA_FRAME_HEADROOM,
+			       ST21NFCA_FRAME_TAILROOM,
+			       ST21NFCA_HCI_LLC_MAX_PAYLOAD,
+			       &phy->hdev,
+			       &phy->se_status);
+	if (r)
+		goto out_free;
+
+	return 0;
+
+out_free:
+	kfree_skb(phy->pending_skb);
+	return r;
 }
 
 static int st21nfca_hci_i2c_remove(struct i2c_client *client)
@@ -563,6 +572,8 @@ static int st21nfca_hci_i2c_remove(struct i2c_client *client)
 
 	if (phy->powered)
 		st21nfca_hci_i2c_disable(phy);
+	if (phy->pending_skb)
+		kfree_skb(phy->pending_skb);
 
 	return 0;
 }
diff --git a/drivers/nfc/virtual_ncidev.c b/drivers/nfc/virtual_ncidev.c
index 221fa3bb8705..f577449e4935 100644
--- a/drivers/nfc/virtual_ncidev.c
+++ b/drivers/nfc/virtual_ncidev.c
@@ -202,7 +202,7 @@ static int __init virtual_ncidev_init(void)
 	miscdev.minor = MISC_DYNAMIC_MINOR;
 	miscdev.name = "virtual_nci";
 	miscdev.fops = &virtual_ncidev_fops;
-	miscdev.mode = S_IALLUGO;
+	miscdev.mode = 0600;
 
 	return misc_register(&miscdev);
 }
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 4b5de8f5435a..1af8a4513708 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -666,6 +666,7 @@ blk_status_t nvme_fail_nonready_command(struct nvme_ctrl *ctrl,
 		struct request *rq)
 {
 	if (ctrl->state != NVME_CTRL_DELETING_NOIO &&
+	    ctrl->state != NVME_CTRL_DELETING &&
 	    ctrl->state != NVME_CTRL_DEAD &&
 	    !test_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags) &&
 	    !blk_noretry_request(rq) && !(rq->cmd_flags & REQ_NVME_MPATH))
@@ -895,10 +896,19 @@ static inline blk_status_t nvme_setup_write_zeroes(struct nvme_ns *ns,
 		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);
-	if (nvme_ns_has_pi(ns))
+
+	if (nvme_ns_has_pi(ns)) {
 		cmnd->write_zeroes.control = cpu_to_le16(NVME_RW_PRINFO_PRACT);
-	else
-		cmnd->write_zeroes.control = 0;
+
+		switch (ns->pi_type) {
+		case NVME_NS_DPS_PI_TYPE1:
+		case NVME_NS_DPS_PI_TYPE2:
+			cmnd->write_zeroes.reftag =
+				cpu_to_le32(t10_pi_ref_tag(req));
+			break;
+		}
+	}
+
 	return BLK_STS_OK;
 }
 
@@ -1740,9 +1750,20 @@ static int nvme_configure_metadata(struct nvme_ns *ns, struct nvme_id_ns *id)
 		 */
 		if (WARN_ON_ONCE(!(id->flbas & NVME_NS_FLBAS_META_EXT)))
 			return -EINVAL;
-		if (ctrl->max_integrity_segments)
-			ns->features |=
-				(NVME_NS_METADATA_SUPPORTED | NVME_NS_EXT_LBAS);
+
+		ns->features |= NVME_NS_EXT_LBAS;
+
+		/*
+		 * The current fabrics transport drivers support namespace
+		 * metadata formats only if nvme_ns_has_pi() returns true.
+		 * Suppress support for all other formats so the namespace will
+		 * have a 0 capacity and not be usable through the block stack.
+		 *
+		 * Note, this check will need to be modified if any drivers
+		 * gain the ability to use other metadata formats.
+		 */
+		if (ctrl->max_integrity_segments && nvme_ns_has_pi(ns))
+			ns->features |= NVME_NS_METADATA_SUPPORTED;
 	} else {
 		/*
 		 * For PCIe controllers, we can't easily remap the separate
@@ -2469,6 +2490,20 @@ static const struct nvme_core_quirk_entry core_quirks[] = {
 		.vid = 0x14a4,
 		.fr = "22301111",
 		.quirks = NVME_QUIRK_SIMPLE_SUSPEND,
+	},
+	{
+		/*
+		 * This Kioxia CD6-V Series / HPE PE8030 device times out and
+		 * aborts I/O during any load, but more easily reproducible
+		 * with discards (fstrim).
+		 *
+		 * The device is left in a state where it is also not possible
+		 * to use "nvme set-feature" to disable APST, but booting with
+		 * nvme_core.default_ps_max_latency=0 works.
+		 */
+		.vid = 0x1e0f,
+		.mn = "KCD6XVUL6T40",
+		.quirks = NVME_QUIRK_NO_APST,
 	}
 };
 
@@ -2673,8 +2708,9 @@ static bool nvme_validate_cntlid(struct nvme_subsystem *subsys,
 
 		if (tmp->cntlid == ctrl->cntlid) {
 			dev_err(ctrl->device,
-				"Duplicate cntlid %u with %s, rejecting\n",
-				ctrl->cntlid, dev_name(tmp->device));
+				"Duplicate cntlid %u with %s, subsys %s, rejecting\n",
+				ctrl->cntlid, dev_name(tmp->device),
+				subsys->subnqn);
 			return false;
 		}
 
diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
index c5a2b71c5268..282d54117e0a 100644
--- a/drivers/nvme/host/fabrics.c
+++ b/drivers/nvme/host/fabrics.c
@@ -698,6 +698,9 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
 			if (token >= 0)
 				pr_warn("I/O fail on reconnect controller after %d sec\n",
 					token);
+			else
+				token = -1;
+
 			opts->fast_io_fail_tmo = token;
 			break;
 		case NVMF_OPT_HOSTNQN:
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 7f2071f2460c..13e5d503ed07 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -866,7 +866,7 @@ int nvme_mpath_init_identify(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
 	}
 	if (ana_log_size > ctrl->ana_log_size) {
 		nvme_mpath_stop(ctrl);
-		kfree(ctrl->ana_log_buf);
+		nvme_mpath_uninit(ctrl);
 		ctrl->ana_log_buf = kmalloc(ana_log_size, GFP_KERNEL);
 		if (!ctrl->ana_log_buf)
 			return -ENOMEM;
@@ -886,4 +886,5 @@ void nvme_mpath_uninit(struct nvme_ctrl *ctrl)
 {
 	kfree(ctrl->ana_log_buf);
 	ctrl->ana_log_buf = NULL;
+	ctrl->ana_log_size = 0;
 }
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index b334af8aa264..9b095ee01364 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -709,7 +709,7 @@ static inline bool nvme_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
 		return true;
 	if (ctrl->ops->flags & NVME_F_FABRICS &&
 	    ctrl->state == NVME_CTRL_DELETING)
-		return true;
+		return queue_live;
 	return __nvme_check_ready(ctrl, rq, queue_live);
 }
 int nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 33bc83d8d992..4ceb28675fdf 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -572,7 +572,7 @@ static int nvme_tcp_handle_comp(struct nvme_tcp_queue *queue,
 	return ret;
 }
 
-static int nvme_tcp_setup_h2c_data_pdu(struct nvme_tcp_request *req,
+static void nvme_tcp_setup_h2c_data_pdu(struct nvme_tcp_request *req,
 		struct nvme_tcp_r2t_pdu *pdu)
 {
 	struct nvme_tcp_data_pdu *data = req->pdu;
@@ -581,32 +581,11 @@ static int nvme_tcp_setup_h2c_data_pdu(struct nvme_tcp_request *req,
 	u8 hdgst = nvme_tcp_hdgst_len(queue);
 	u8 ddgst = nvme_tcp_ddgst_len(queue);
 
+	req->state = NVME_TCP_SEND_H2C_PDU;
+	req->offset = 0;
 	req->pdu_len = le32_to_cpu(pdu->r2t_length);
 	req->pdu_sent = 0;
 
-	if (unlikely(!req->pdu_len)) {
-		dev_err(queue->ctrl->ctrl.device,
-			"req %d r2t len is %u, probably a bug...\n",
-			rq->tag, req->pdu_len);
-		return -EPROTO;
-	}
-
-	if (unlikely(req->data_sent + req->pdu_len > req->data_len)) {
-		dev_err(queue->ctrl->ctrl.device,
-			"req %d r2t len %u exceeded data len %u (%zu sent)\n",
-			rq->tag, req->pdu_len, req->data_len,
-			req->data_sent);
-		return -EPROTO;
-	}
-
-	if (unlikely(le32_to_cpu(pdu->r2t_offset) < req->data_sent)) {
-		dev_err(queue->ctrl->ctrl.device,
-			"req %d unexpected r2t offset %u (expected %zu)\n",
-			rq->tag, le32_to_cpu(pdu->r2t_offset),
-			req->data_sent);
-		return -EPROTO;
-	}
-
 	memset(data, 0, sizeof(*data));
 	data->hdr.type = nvme_tcp_h2c_data;
 	data->hdr.flags = NVME_TCP_F_DATA_LAST;
@@ -622,7 +601,6 @@ static int nvme_tcp_setup_h2c_data_pdu(struct nvme_tcp_request *req,
 	data->command_id = nvme_cid(rq);
 	data->data_offset = pdu->r2t_offset;
 	data->data_length = cpu_to_le32(req->pdu_len);
-	return 0;
 }
 
 static int nvme_tcp_handle_r2t(struct nvme_tcp_queue *queue,
@@ -630,7 +608,7 @@ static int nvme_tcp_handle_r2t(struct nvme_tcp_queue *queue,
 {
 	struct nvme_tcp_request *req;
 	struct request *rq;
-	int ret;
+	u32 r2t_length = le32_to_cpu(pdu->r2t_length);
 
 	rq = nvme_find_rq(nvme_tcp_tagset(queue), pdu->command_id);
 	if (!rq) {
@@ -641,13 +619,28 @@ static int nvme_tcp_handle_r2t(struct nvme_tcp_queue *queue,
 	}
 	req = blk_mq_rq_to_pdu(rq);
 
-	ret = nvme_tcp_setup_h2c_data_pdu(req, pdu);
-	if (unlikely(ret))
-		return ret;
+	if (unlikely(!r2t_length)) {
+		dev_err(queue->ctrl->ctrl.device,
+			"req %d r2t len is %u, probably a bug...\n",
+			rq->tag, r2t_length);
+		return -EPROTO;
+	}
 
-	req->state = NVME_TCP_SEND_H2C_PDU;
-	req->offset = 0;
+	if (unlikely(req->data_sent + r2t_length > req->data_len)) {
+		dev_err(queue->ctrl->ctrl.device,
+			"req %d r2t len %u exceeded data len %u (%zu sent)\n",
+			rq->tag, r2t_length, req->data_len, req->data_sent);
+		return -EPROTO;
+	}
 
+	if (unlikely(le32_to_cpu(pdu->r2t_offset) < req->data_sent)) {
+		dev_err(queue->ctrl->ctrl.device,
+			"req %d unexpected r2t offset %u (expected %zu)\n",
+			rq->tag, le32_to_cpu(pdu->r2t_offset), req->data_sent);
+		return -EPROTO;
+	}
+
+	nvme_tcp_setup_h2c_data_pdu(req, pdu);
 	nvme_tcp_queue_request(req, false, true);
 
 	return 0;
@@ -1232,6 +1225,7 @@ static int nvme_tcp_alloc_async_req(struct nvme_tcp_ctrl *ctrl)
 
 static void nvme_tcp_free_queue(struct nvme_ctrl *nctrl, int qid)
 {
+	struct page *page;
 	struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl);
 	struct nvme_tcp_queue *queue = &ctrl->queues[qid];
 
@@ -1241,6 +1235,11 @@ static void nvme_tcp_free_queue(struct nvme_ctrl *nctrl, int qid)
 	if (queue->hdr_digest || queue->data_digest)
 		nvme_tcp_free_crypto(queue);
 
+	if (queue->pf_cache.va) {
+		page = virt_to_head_page(queue->pf_cache.va);
+		__page_frag_cache_drain(page, queue->pf_cache.pagecnt_bias);
+		queue->pf_cache.va = NULL;
+	}
 	sock_release(queue->sock);
 	kfree(queue->pdu);
 	mutex_destroy(&queue->send_mutex);
diff --git a/drivers/nvme/host/zns.c b/drivers/nvme/host/zns.c
index bfc259e0d7b8..9f81beb4df4e 100644
--- a/drivers/nvme/host/zns.c
+++ b/drivers/nvme/host/zns.c
@@ -166,7 +166,10 @@ static int nvme_zone_parse_entry(struct nvme_ns *ns,
 	zone.len = ns->zsze;
 	zone.capacity = nvme_lba_to_sect(ns, le64_to_cpu(entry->zcap));
 	zone.start = nvme_lba_to_sect(ns, le64_to_cpu(entry->zslba));
-	zone.wp = nvme_lba_to_sect(ns, le64_to_cpu(entry->wp));
+	if (zone.cond == BLK_ZONE_COND_FULL)
+		zone.wp = zone.start + zone.len;
+	else
+		zone.wp = nvme_lba_to_sect(ns, le64_to_cpu(entry->wp));
 
 	return cb(&zone, idx, data);
 }
diff --git a/drivers/nvme/target/io-cmd-file.c b/drivers/nvme/target/io-cmd-file.c
index 6aa30f30b572..6be6e59d273b 100644
--- a/drivers/nvme/target/io-cmd-file.c
+++ b/drivers/nvme/target/io-cmd-file.c
@@ -8,6 +8,7 @@
 #include <linux/uio.h>
 #include <linux/falloc.h>
 #include <linux/file.h>
+#include <linux/fs.h>
 #include "nvmet.h"
 
 #define NVMET_MAX_MPOOL_BVEC		16
@@ -266,7 +267,8 @@ static void nvmet_file_execute_rw(struct nvmet_req *req)
 
 	if (req->ns->buffered_io) {
 		if (likely(!req->f.mpool_alloc) &&
-				nvmet_file_execute_io(req, IOCB_NOWAIT))
+		    (req->ns->file->f_mode & FMODE_NOWAIT) &&
+		    nvmet_file_execute_io(req, IOCB_NOWAIT))
 			return;
 		nvmet_file_submit_buffered_io(req);
 	} else
diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index 84c387e4bf43..7c1c43ce466b 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -166,6 +166,8 @@ static struct workqueue_struct *nvmet_tcp_wq;
 static const struct nvmet_fabrics_ops nvmet_tcp_ops;
 static void nvmet_tcp_free_cmd(struct nvmet_tcp_cmd *c);
 static void nvmet_tcp_finish_cmd(struct nvmet_tcp_cmd *cmd);
+static void nvmet_tcp_free_cmd_buffers(struct nvmet_tcp_cmd *cmd);
+static void nvmet_tcp_unmap_pdu_iovec(struct nvmet_tcp_cmd *cmd);
 
 static inline u16 nvmet_tcp_cmd_tag(struct nvmet_tcp_queue *queue,
 		struct nvmet_tcp_cmd *cmd)
@@ -297,6 +299,16 @@ static int nvmet_tcp_check_ddgst(struct nvmet_tcp_queue *queue, void *pdu)
 	return 0;
 }
 
+static void nvmet_tcp_free_cmd_buffers(struct nvmet_tcp_cmd *cmd)
+{
+	WARN_ON(unlikely(cmd->nr_mapped > 0));
+
+	kfree(cmd->iov);
+	sgl_free(cmd->req.sg);
+	cmd->iov = NULL;
+	cmd->req.sg = NULL;
+}
+
 static void nvmet_tcp_unmap_pdu_iovec(struct nvmet_tcp_cmd *cmd)
 {
 	struct scatterlist *sg;
@@ -306,6 +318,8 @@ static void nvmet_tcp_unmap_pdu_iovec(struct nvmet_tcp_cmd *cmd)
 
 	for (i = 0; i < cmd->nr_mapped; i++)
 		kunmap(sg_page(&sg[i]));
+
+	cmd->nr_mapped = 0;
 }
 
 static void nvmet_tcp_map_pdu_iovec(struct nvmet_tcp_cmd *cmd)
@@ -387,7 +401,7 @@ static int nvmet_tcp_map_data(struct nvmet_tcp_cmd *cmd)
 
 	return 0;
 err:
-	sgl_free(cmd->req.sg);
+	nvmet_tcp_free_cmd_buffers(cmd);
 	return NVME_SC_INTERNAL;
 }
 
@@ -632,10 +646,8 @@ static int nvmet_try_send_data(struct nvmet_tcp_cmd *cmd, bool last_in_batch)
 		}
 	}
 
-	if (queue->nvme_sq.sqhd_disabled) {
-		kfree(cmd->iov);
-		sgl_free(cmd->req.sg);
-	}
+	if (queue->nvme_sq.sqhd_disabled)
+		nvmet_tcp_free_cmd_buffers(cmd);
 
 	return 1;
 
@@ -664,8 +676,7 @@ static int nvmet_try_send_response(struct nvmet_tcp_cmd *cmd,
 	if (left)
 		return -EAGAIN;
 
-	kfree(cmd->iov);
-	sgl_free(cmd->req.sg);
+	nvmet_tcp_free_cmd_buffers(cmd);
 	cmd->queue->snd_cmd = NULL;
 	nvmet_tcp_put_cmd(cmd);
 	return 1;
@@ -700,10 +711,11 @@ static int nvmet_try_send_r2t(struct nvmet_tcp_cmd *cmd, bool last_in_batch)
 static int nvmet_try_send_ddgst(struct nvmet_tcp_cmd *cmd, bool last_in_batch)
 {
 	struct nvmet_tcp_queue *queue = cmd->queue;
+	int left = NVME_TCP_DIGEST_LENGTH - cmd->offset;
 	struct msghdr msg = { .msg_flags = MSG_DONTWAIT };
 	struct kvec iov = {
 		.iov_base = (u8 *)&cmd->exp_ddgst + cmd->offset,
-		.iov_len = NVME_TCP_DIGEST_LENGTH - cmd->offset
+		.iov_len = left
 	};
 	int ret;
 
@@ -717,6 +729,10 @@ static int nvmet_try_send_ddgst(struct nvmet_tcp_cmd *cmd, bool last_in_batch)
 		return ret;
 
 	cmd->offset += ret;
+	left -= ret;
+
+	if (left)
+		return -EAGAIN;
 
 	if (queue->nvme_sq.sqhd_disabled) {
 		cmd->queue->snd_cmd = NULL;
@@ -906,7 +922,14 @@ static void nvmet_tcp_handle_req_failure(struct nvmet_tcp_queue *queue,
 	size_t data_len = le32_to_cpu(req->cmd->common.dptr.sgl.length);
 	int ret;
 
-	if (!nvme_is_write(cmd->req.cmd) ||
+	/*
+	 * This command has not been processed yet, hence we are trying to
+	 * figure out if there is still pending data left to receive. If
+	 * we don't, we can simply prepare for the next pdu and bail out,
+	 * otherwise we will need to prepare a buffer and receive the
+	 * stale data before continuing forward.
+	 */
+	if (!nvme_is_write(cmd->req.cmd) || !data_len ||
 	    data_len > cmd->req.port->inline_data_size) {
 		nvmet_prepare_receive_pdu(queue);
 		return;
@@ -1406,8 +1429,7 @@ static void nvmet_tcp_finish_cmd(struct nvmet_tcp_cmd *cmd)
 {
 	nvmet_req_uninit(&cmd->req);
 	nvmet_tcp_unmap_pdu_iovec(cmd);
-	kfree(cmd->iov);
-	sgl_free(cmd->req.sg);
+	nvmet_tcp_free_cmd_buffers(cmd);
 }
 
 static void nvmet_tcp_uninit_data_in_cmds(struct nvmet_tcp_queue *queue)
@@ -1417,7 +1439,10 @@ static void nvmet_tcp_uninit_data_in_cmds(struct nvmet_tcp_queue *queue)
 
 	for (i = 0; i < queue->nr_cmds; i++, cmd++) {
 		if (nvmet_tcp_need_data_in(cmd))
-			nvmet_tcp_finish_cmd(cmd);
+			nvmet_req_uninit(&cmd->req);
+
+		nvmet_tcp_unmap_pdu_iovec(cmd);
+		nvmet_tcp_free_cmd_buffers(cmd);
 	}
 
 	if (!queue->nr_cmds && nvmet_tcp_need_data_in(&queue->connect)) {
@@ -1437,7 +1462,9 @@ static void nvmet_tcp_release_queue_work(struct work_struct *w)
 	mutex_unlock(&nvmet_tcp_queue_mutex);
 
 	nvmet_tcp_restore_socket_callbacks(queue);
-	flush_work(&queue->io_work);
+	cancel_work_sync(&queue->io_work);
+	/* stop accepting incoming data */
+	queue->rcv_state = NVMET_TCP_RECV_ERR;
 
 	nvmet_tcp_uninit_data_in_cmds(queue);
 	nvmet_sq_destroy(&queue->nvme_sq);
diff --git a/drivers/of/irq.c b/drivers/of/irq.c
index 32be5a03951f..2b07677a386b 100644
--- a/drivers/of/irq.c
+++ b/drivers/of/irq.c
@@ -76,6 +76,26 @@ struct device_node *of_irq_find_parent(struct device_node *child)
 }
 EXPORT_SYMBOL_GPL(of_irq_find_parent);
 
+/*
+ * These interrupt controllers abuse interrupt-map for unspeakable
+ * reasons and rely on the core code to *ignore* it (the drivers do
+ * their own parsing of the property).
+ *
+ * If you think of adding to the list for something *new*, think
+ * again. There is a high chance that you will be sent back to the
+ * drawing board.
+ */
+static const char * const of_irq_imap_abusers[] = {
+	"CBEA,platform-spider-pic",
+	"sti,platform-spider-pic",
+	"realtek,rtl-intc",
+	"fsl,ls1021a-extirq",
+	"fsl,ls1043a-extirq",
+	"fsl,ls1088a-extirq",
+	"renesas,rza1-irqc",
+	NULL,
+};
+
 /**
  * of_irq_parse_raw - Low level interrupt tree parsing
  * @addr:	address specifier (start of "reg" property of the device) in be32 format
@@ -159,11 +179,15 @@ int of_irq_parse_raw(const __be32 *addr, struct of_phandle_args *out_irq)
 		/*
 		 * Now check if cursor is an interrupt-controller and
 		 * if it is then we are done, unless there is an
-		 * interrupt-map which takes precedence.
+		 * interrupt-map which takes precedence except on one
+		 * of these broken platforms that want to parse
+		 * interrupt-map themselves for $reason.
 		 */
+		bool intc = of_property_read_bool(ipar, "interrupt-controller");
+
 		imap = of_get_property(ipar, "interrupt-map", &imaplen);
-		if (imap == NULL &&
-		    of_property_read_bool(ipar, "interrupt-controller")) {
+		if (intc &&
+		    (!imap || of_device_compatible_match(ipar, of_irq_imap_abusers))) {
 			pr_debug(" -> got it !\n");
 			return 0;
 		}
@@ -244,8 +268,20 @@ int of_irq_parse_raw(const __be32 *addr, struct of_phandle_args *out_irq)
 
 			pr_debug(" -> imaplen=%d\n", imaplen);
 		}
-		if (!match)
+		if (!match) {
+			if (intc) {
+				/*
+				 * The PASEMI Nemo is a known offender, so
+				 * let's only warn for anyone else.
+				 */
+				WARN(!IS_ENABLED(CONFIG_PPC_PASEMI),
+				     "%pOF interrupt-map failed, using interrupt-controller\n",
+				     ipar);
+				return 0;
+			}
+
 			goto fail;
+		}
 
 		/*
 		 * Successfully parsed an interrrupt-map translation; copy new
diff --git a/drivers/of/platform.c b/drivers/of/platform.c
index 07813fb1ef37..b3faf89744aa 100644
--- a/drivers/of/platform.c
+++ b/drivers/of/platform.c
@@ -76,6 +76,7 @@ static void of_device_make_bus_id(struct device *dev)
 	struct device_node *node = dev->of_node;
 	const __be32 *reg;
 	u64 addr;
+	u32 mask;
 
 	/* Construct the name, using parent nodes if necessary to ensure uniqueness */
 	while (node->parent) {
@@ -85,8 +86,13 @@ static void of_device_make_bus_id(struct device *dev)
 		 */
 		reg = of_get_property(node, "reg", NULL);
 		if (reg && (addr = of_translate_address(node, reg)) != OF_BAD_ADDR) {
-			dev_set_name(dev, dev_name(dev) ? "%llx.%pOFn:%s" : "%llx.%pOFn",
-				     addr, node, dev_name(dev));
+			if (!of_property_read_u32(node, "mask", &mask))
+				dev_set_name(dev, dev_name(dev) ? "%llx.%x.%pOFn:%s" : "%llx.%x.%pOFn",
+					     addr, ffs(mask) - 1, node, dev_name(dev));
+
+			else
+				dev_set_name(dev, dev_name(dev) ? "%llx.%pOFn:%s" : "%llx.%pOFn",
+					     addr, node, dev_name(dev));
 			return;
 		}
 
diff --git a/drivers/pci/controller/Kconfig b/drivers/pci/controller/Kconfig
index e917bb3652bb..7fc5135ffbbf 100644
--- a/drivers/pci/controller/Kconfig
+++ b/drivers/pci/controller/Kconfig
@@ -270,7 +270,8 @@ config VMD
 
 config PCIE_BRCMSTB
 	tristate "Broadcom Brcmstb PCIe host controller"
-	depends on ARCH_BRCMSTB || ARCH_BCM2835 || ARCH_BCM4908 || COMPILE_TEST
+	depends on ARCH_BRCMSTB || ARCH_BCM2835 || ARCH_BCM4908 || \
+		   BMIPS_GENERIC || COMPILE_TEST
 	depends on OF
 	depends on PCI_MSI_IRQ_DOMAIN
 	default ARCH_BRCMSTB
@@ -331,8 +332,8 @@ config PCIE_APPLE
 	  If unsure, say Y if you have an Apple Silicon system.
 
 config PCIE_MT7621
-	tristate "MediaTek MT7621 PCIe Controller"
-	depends on (RALINK && SOC_MT7621) || (MIPS && COMPILE_TEST)
+	bool "MediaTek MT7621 PCIe Controller"
+	depends on SOC_MT7621 || (MIPS && COMPILE_TEST)
 	select PHY_MT7621_PCI
 	default SOC_MT7621
 	help
diff --git a/drivers/pci/controller/dwc/pci-exynos.c b/drivers/pci/controller/dwc/pci-exynos.c
index c24dab383654..722dacdd5a17 100644
--- a/drivers/pci/controller/dwc/pci-exynos.c
+++ b/drivers/pci/controller/dwc/pci-exynos.c
@@ -19,6 +19,7 @@
 #include <linux/platform_device.h>
 #include <linux/phy/phy.h>
 #include <linux/regulator/consumer.h>
+#include <linux/module.h>
 
 #include "pcie-designware.h"
 
diff --git a/drivers/pci/controller/dwc/pcie-qcom-ep.c b/drivers/pci/controller/dwc/pcie-qcom-ep.c
index 7b17da2f9b3f..cfe66bf04c1d 100644
--- a/drivers/pci/controller/dwc/pcie-qcom-ep.c
+++ b/drivers/pci/controller/dwc/pcie-qcom-ep.c
@@ -18,6 +18,7 @@
 #include <linux/pm_domain.h>
 #include <linux/regmap.h>
 #include <linux/reset.h>
+#include <linux/module.h>
 
 #include "pcie-designware.h"
 
diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c
index c5300d49807a..c3b725afa11f 100644
--- a/drivers/pci/controller/pci-aardvark.c
+++ b/drivers/pci/controller/pci-aardvark.c
@@ -32,7 +32,6 @@
 #define PCIE_CORE_DEV_ID_REG					0x0
 #define PCIE_CORE_CMD_STATUS_REG				0x4
 #define PCIE_CORE_DEV_REV_REG					0x8
-#define PCIE_CORE_EXP_ROM_BAR_REG				0x30
 #define PCIE_CORE_PCIEXP_CAP					0xc0
 #define PCIE_CORE_ERR_CAPCTL_REG				0x118
 #define     PCIE_CORE_ERR_CAPCTL_ECRC_CHK_TX			BIT(5)
@@ -774,10 +773,6 @@ advk_pci_bridge_emul_base_conf_read(struct pci_bridge_emul *bridge,
 		*value = advk_readl(pcie, PCIE_CORE_CMD_STATUS_REG);
 		return PCI_BRIDGE_EMUL_HANDLED;
 
-	case PCI_ROM_ADDRESS1:
-		*value = advk_readl(pcie, PCIE_CORE_EXP_ROM_BAR_REG);
-		return PCI_BRIDGE_EMUL_HANDLED;
-
 	case PCI_INTERRUPT_LINE: {
 		/*
 		 * From the whole 32bit register we support reading from HW only
@@ -810,10 +805,6 @@ advk_pci_bridge_emul_base_conf_write(struct pci_bridge_emul *bridge,
 		advk_writel(pcie, new, PCIE_CORE_CMD_STATUS_REG);
 		break;
 
-	case PCI_ROM_ADDRESS1:
-		advk_writel(pcie, new, PCIE_CORE_EXP_ROM_BAR_REG);
-		break;
-
 	case PCI_INTERRUPT_LINE:
 		if (mask & (PCI_BRIDGE_CTL_BUS_RESET << 16)) {
 			u32 val = advk_readl(pcie, PCIE_CORE_CTRL1_REG);
diff --git a/drivers/pci/controller/pcie-apple.c b/drivers/pci/controller/pcie-apple.c
index 1bf4d75b61be..b090924b41fe 100644
--- a/drivers/pci/controller/pcie-apple.c
+++ b/drivers/pci/controller/pcie-apple.c
@@ -516,7 +516,7 @@ static int apple_pcie_setup_port(struct apple_pcie *pcie,
 	int ret, i;
 
 	reset = gpiod_get_from_of_node(np, "reset-gpios", 0,
-				       GPIOD_OUT_LOW, "#PERST");
+				       GPIOD_OUT_LOW, "PERST#");
 	if (IS_ERR(reset))
 		return PTR_ERR(reset);
 
@@ -539,12 +539,22 @@ static int apple_pcie_setup_port(struct apple_pcie *pcie,
 
 	rmw_set(PORT_APPCLK_EN, port->base + PORT_APPCLK);
 
+	/* Assert PERST# before setting up the clock */
+	gpiod_set_value(reset, 1);
+
 	ret = apple_pcie_setup_refclk(pcie, port);
 	if (ret < 0)
 		return ret;
 
+	/* The minimal Tperst-clk value is 100us (PCIe CEM r5.0, 2.9.2) */
+	usleep_range(100, 200);
+
+	/* Deassert PERST# */
 	rmw_set(PORT_PERST_OFF, port->base + PORT_PERST);
-	gpiod_set_value(reset, 1);
+	gpiod_set_value(reset, 0);
+
+	/* Wait for 100ms after PERST# deassertion (PCIe r5.0, 6.6.1) */
+	msleep(100);
 
 	ret = readl_relaxed_poll_timeout(port->base + PORT_STATUS, stat,
 					 stat & PORT_STATUS_READY, 100, 250000);
diff --git a/drivers/pci/hotplug/s390_pci_hpc.c b/drivers/pci/hotplug/s390_pci_hpc.c
index dcefdb42ac46..a89b7de72dcf 100644
--- a/drivers/pci/hotplug/s390_pci_hpc.c
+++ b/drivers/pci/hotplug/s390_pci_hpc.c
@@ -57,6 +57,29 @@ static int disable_slot(struct hotplug_slot *hotplug_slot)
 	return zpci_deconfigure_device(zdev);
 }
 
+static int reset_slot(struct hotplug_slot *hotplug_slot, bool probe)
+{
+	struct zpci_dev *zdev = container_of(hotplug_slot, struct zpci_dev,
+					     hotplug_slot);
+
+	if (zdev->state != ZPCI_FN_STATE_CONFIGURED)
+		return -EIO;
+	/*
+	 * We can't take the zdev->lock as reset_slot may be called during
+	 * probing and/or device removal which already happens under the
+	 * zdev->lock. Instead the user should use the higher level
+	 * pci_reset_function() or pci_bus_reset() which hold the PCI device
+	 * lock preventing concurrent removal. If not using these functions
+	 * holding the PCI device lock is required.
+	 */
+
+	/* As long as the function is configured we can reset */
+	if (probe)
+		return 0;
+
+	return zpci_hot_reset_device(zdev);
+}
+
 static int get_power_status(struct hotplug_slot *hotplug_slot, u8 *value)
 {
 	struct zpci_dev *zdev = container_of(hotplug_slot, struct zpci_dev,
@@ -76,6 +99,7 @@ static int get_adapter_status(struct hotplug_slot *hotplug_slot, u8 *value)
 static const struct hotplug_slot_ops s390_hotplug_slot_ops = {
 	.enable_slot =		enable_slot,
 	.disable_slot =		disable_slot,
+	.reset_slot =		reset_slot,
 	.get_power_status =	get_power_status,
 	.get_adapter_status =	get_adapter_status,
 };
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 12e296d634eb..d84cf30bb279 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -148,6 +148,9 @@ static noinline void pci_msi_update_mask(struct msi_desc *desc, u32 clear, u32 s
 	raw_spinlock_t *lock = &desc->dev->msi_lock;
 	unsigned long flags;
 
+	if (!desc->msi_attrib.can_mask)
+		return;
+
 	raw_spin_lock_irqsave(lock, flags);
 	desc->msi_mask &= ~clear;
 	desc->msi_mask |= set;
@@ -181,7 +184,8 @@ static void pci_msix_write_vector_ctrl(struct msi_desc *desc, u32 ctrl)
 {
 	void __iomem *desc_addr = pci_msix_desc_addr(desc);
 
-	writel(ctrl, desc_addr + PCI_MSIX_ENTRY_VECTOR_CTRL);
+	if (desc->msi_attrib.can_mask)
+		writel(ctrl, desc_addr + PCI_MSIX_ENTRY_VECTOR_CTRL);
 }
 
 static inline void pci_msix_mask(struct msi_desc *desc)
@@ -200,23 +204,17 @@ static inline void pci_msix_unmask(struct msi_desc *desc)
 
 static void __pci_msi_mask_desc(struct msi_desc *desc, u32 mask)
 {
-	if (pci_msi_ignore_mask || desc->msi_attrib.is_virtual)
-		return;
-
 	if (desc->msi_attrib.is_msix)
 		pci_msix_mask(desc);
-	else if (desc->msi_attrib.maskbit)
+	else
 		pci_msi_mask(desc, mask);
 }
 
 static void __pci_msi_unmask_desc(struct msi_desc *desc, u32 mask)
 {
-	if (pci_msi_ignore_mask || desc->msi_attrib.is_virtual)
-		return;
-
 	if (desc->msi_attrib.is_msix)
 		pci_msix_unmask(desc);
-	else if (desc->msi_attrib.maskbit)
+	else
 		pci_msi_unmask(desc, mask);
 }
 
@@ -370,6 +368,11 @@ static void free_msi_irqs(struct pci_dev *dev)
 			for (i = 0; i < entry->nvec_used; i++)
 				BUG_ON(irq_has_action(entry->irq + i));
 
+	if (dev->msi_irq_groups) {
+		msi_destroy_sysfs(&dev->dev, dev->msi_irq_groups);
+		dev->msi_irq_groups = NULL;
+	}
+
 	pci_msi_teardown_msi_irqs(dev);
 
 	list_for_each_entry_safe(entry, tmp, msi_list, list) {
@@ -381,11 +384,6 @@ static void free_msi_irqs(struct pci_dev *dev)
 		list_del(&entry->list);
 		free_msi_entry(entry);
 	}
-
-	if (dev->msi_irq_groups) {
-		msi_destroy_sysfs(&dev->dev, dev->msi_irq_groups);
-		dev->msi_irq_groups = NULL;
-	}
 }
 
 static void pci_intx_for_msi(struct pci_dev *dev, int enable)
@@ -479,12 +477,16 @@ msi_setup_entry(struct pci_dev *dev, int nvec, struct irq_affinity *affd)
 		goto out;
 
 	pci_read_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, &control);
+	/* Lies, damned lies, and MSIs */
+	if (dev->dev_flags & PCI_DEV_FLAGS_HAS_MSI_MASKING)
+		control |= PCI_MSI_FLAGS_MASKBIT;
 
 	entry->msi_attrib.is_msix	= 0;
 	entry->msi_attrib.is_64		= !!(control & PCI_MSI_FLAGS_64BIT);
 	entry->msi_attrib.is_virtual    = 0;
 	entry->msi_attrib.entry_nr	= 0;
-	entry->msi_attrib.maskbit	= !!(control & PCI_MSI_FLAGS_MASKBIT);
+	entry->msi_attrib.can_mask	= !pci_msi_ignore_mask &&
+					  !!(control & PCI_MSI_FLAGS_MASKBIT);
 	entry->msi_attrib.default_irq	= dev->irq;	/* Save IOAPIC IRQ */
 	entry->msi_attrib.multi_cap	= (control & PCI_MSI_FLAGS_QMASK) >> 1;
 	entry->msi_attrib.multiple	= ilog2(__roundup_pow_of_two(nvec));
@@ -495,7 +497,7 @@ msi_setup_entry(struct pci_dev *dev, int nvec, struct irq_affinity *affd)
 		entry->mask_pos = dev->msi_cap + PCI_MSI_MASK_32;
 
 	/* Save the initial mask status */
-	if (entry->msi_attrib.maskbit)
+	if (entry->msi_attrib.can_mask)
 		pci_read_config_dword(dev, entry->mask_pos, &entry->msi_mask);
 
 out:
@@ -639,10 +641,13 @@ static int msix_setup_entries(struct pci_dev *dev, void __iomem *base,
 		entry->msi_attrib.is_virtual =
 			entry->msi_attrib.entry_nr >= vec_count;
 
+		entry->msi_attrib.can_mask	= !pci_msi_ignore_mask &&
+						  !entry->msi_attrib.is_virtual;
+
 		entry->msi_attrib.default_irq	= dev->irq;
 		entry->mask_base		= base;
 
-		if (!entry->msi_attrib.is_virtual) {
+		if (entry->msi_attrib.can_mask) {
 			addr = pci_msix_desc_addr(entry);
 			entry->msix_ctrl = readl(addr + PCI_MSIX_ENTRY_VECTOR_CTRL);
 		}
@@ -717,9 +722,6 @@ static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries,
 		goto out_disable;
 	}
 
-	/* Ensure that all table entries are masked. */
-	msix_mask_all(base, tsize);
-
 	ret = msix_setup_entries(dev, base, entries, nvec, affd);
 	if (ret)
 		goto out_disable;
@@ -746,6 +748,16 @@ static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries,
 	/* Set MSI-X enabled bits and unmask the function */
 	pci_intx_for_msi(dev, 0);
 	dev->msix_enabled = 1;
+
+	/*
+	 * Ensure that all table entries are masked to prevent
+	 * stale entries from firing in a crash kernel.
+	 *
+	 * Done late to deal with a broken Marvell NVME device
+	 * which takes the MSI-X mask bits into account even
+	 * when MSI-X is disabled, which prevents MSI delivery.
+	 */
+	msix_mask_all(base, tsize);
 	pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_MASKALL, 0);
 
 	pcibios_free_irq(dev);
@@ -772,7 +784,7 @@ out_free:
 	free_msi_irqs(dev);
 
 out_disable:
-	pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_ENABLE, 0);
+	pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_MASKALL | PCI_MSIX_FLAGS_ENABLE, 0);
 
 	return ret;
 }
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 1579a3724eb4..3d2fb394986a 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -5106,12 +5106,13 @@ static int pci_reset_bus_function(struct pci_dev *dev, bool probe)
 	return pci_parent_bus_reset(dev, probe);
 }
 
-static void pci_dev_lock(struct pci_dev *dev)
+void pci_dev_lock(struct pci_dev *dev)
 {
 	pci_cfg_access_lock(dev);
 	/* block PM suspend, driver probe, etc. */
 	device_lock(&dev->dev);
 }
+EXPORT_SYMBOL_GPL(pci_dev_lock);
 
 /* Return 1 on successful lock, 0 on contention */
 int pci_dev_trylock(struct pci_dev *dev)
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index aedb78c86ddc..003950c738d2 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -5851,3 +5851,9 @@ DECLARE_PCI_FIXUP_ENABLE(PCI_VENDOR_ID_PERICOM, 0x2303,
 			 pci_fixup_pericom_acs_store_forward);
 DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_PERICOM, 0x2303,
 			 pci_fixup_pericom_acs_store_forward);
+
+static void nvidia_ion_ahci_fixup(struct pci_dev *pdev)
+{
+	pdev->dev_flags |= PCI_DEV_FLAGS_HAS_MSI_MASKING;
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_NVIDIA, 0x0ab8, nvidia_ion_ahci_fixup);
diff --git a/drivers/phy/hisilicon/phy-hi3670-pcie.c b/drivers/phy/hisilicon/phy-hi3670-pcie.c
index c64c6679b1b9..0ac9634b398d 100644
--- a/drivers/phy/hisilicon/phy-hi3670-pcie.c
+++ b/drivers/phy/hisilicon/phy-hi3670-pcie.c
@@ -757,8 +757,8 @@ static int hi3670_pcie_phy_get_resources(struct hi3670_pcie_phy *phy,
 		return PTR_ERR(phy->sysctrl);
 
 	phy->pmctrl = syscon_regmap_lookup_by_compatible("hisilicon,hi3670-pmctrl");
-	if (IS_ERR(phy->sysctrl))
-		return PTR_ERR(phy->sysctrl);
+	if (IS_ERR(phy->pmctrl))
+		return PTR_ERR(phy->pmctrl);
 
 	/* clocks */
 	phy->phy_ref_clk = devm_clk_get(dev, "phy_ref");
diff --git a/drivers/phy/marvell/phy-mvebu-cp110-utmi.c b/drivers/phy/marvell/phy-mvebu-cp110-utmi.c
index 08d178a4dc13..aa27c7994610 100644
--- a/drivers/phy/marvell/phy-mvebu-cp110-utmi.c
+++ b/drivers/phy/marvell/phy-mvebu-cp110-utmi.c
@@ -82,9 +82,9 @@
  * struct mvebu_cp110_utmi - PHY driver data
  *
  * @regs: PHY registers
- * @syscom: Regmap with system controller registers
+ * @syscon: Regmap with system controller registers
  * @dev: device driver handle
- * @caps: PHY capabilities
+ * @ops: phy ops
  */
 struct mvebu_cp110_utmi {
 	void __iomem *regs;
diff --git a/drivers/phy/qualcomm/phy-qcom-ipq806x-usb.c b/drivers/phy/qualcomm/phy-qcom-ipq806x-usb.c
index bfff0c8c9130..fec1da470d26 100644
--- a/drivers/phy/qualcomm/phy-qcom-ipq806x-usb.c
+++ b/drivers/phy/qualcomm/phy-qcom-ipq806x-usb.c
@@ -127,12 +127,13 @@ struct phy_drvdata {
 };
 
 /**
- * Write register and read back masked value to confirm it is written
+ * usb_phy_write_readback() - Write register and read back masked value to
+ * confirm it is written
  *
- * @base - QCOM DWC3 PHY base virtual address.
- * @offset - register offset.
- * @mask - register bitmask specifying what should be updated
- * @val - value to write.
+ * @phy_dwc3: QCOM DWC3 phy context
+ * @offset: register offset.
+ * @mask: register bitmask specifying what should be updated
+ * @val: value to write.
  */
 static inline void usb_phy_write_readback(struct usb_phy *phy_dwc3,
 					  u32 offset,
@@ -171,11 +172,11 @@ static int wait_for_latch(void __iomem *addr)
 }
 
 /**
- * Write SSPHY register
+ * usb_ss_write_phycreg() - Write SSPHY register
  *
- * @base - QCOM DWC3 PHY base virtual address.
- * @addr - SSPHY address to write.
- * @val - value to write.
+ * @phy_dwc3: QCOM DWC3 phy context
+ * @addr: SSPHY address to write.
+ * @val: value to write.
  */
 static int usb_ss_write_phycreg(struct usb_phy *phy_dwc3,
 				u32 addr, u32 val)
@@ -209,10 +210,11 @@ err_wait:
 }
 
 /**
- * Read SSPHY register.
+ * usb_ss_read_phycreg() - Read SSPHY register.
  *
- * @base - QCOM DWC3 PHY base virtual address.
- * @addr - SSPHY address to read.
+ * @phy_dwc3: QCOM DWC3 phy context
+ * @addr: SSPHY address to read.
+ * @val: pointer in which read is store.
  */
 static int usb_ss_read_phycreg(struct usb_phy *phy_dwc3,
 			       u32 addr, u32 *val)
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp.c b/drivers/phy/qualcomm/phy-qcom-qmp.c
index 456a59d8c7d0..c96639d5f581 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp.c
+++ b/drivers/phy/qualcomm/phy-qcom-qmp.c
@@ -2973,6 +2973,9 @@ struct qmp_phy_combo_cfg {
  * @qmp: QMP phy to which this lane belongs
  * @lane_rst: lane's reset controller
  * @mode: current PHY mode
+ * @dp_aux_cfg: Display port aux config
+ * @dp_opts: Display port optional config
+ * @dp_clks: Display port clocks
  */
 struct qmp_phy {
 	struct phy *phy;
diff --git a/drivers/phy/qualcomm/phy-qcom-usb-hsic.c b/drivers/phy/qualcomm/phy-qcom-usb-hsic.c
index 04d18d52f700..716a77748ed8 100644
--- a/drivers/phy/qualcomm/phy-qcom-usb-hsic.c
+++ b/drivers/phy/qualcomm/phy-qcom-usb-hsic.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0-only
-/**
+/*
  * Copyright (C) 2016 Linaro Ltd
  */
 #include <linux/module.h>
diff --git a/drivers/phy/st/phy-stm32-usbphyc.c b/drivers/phy/st/phy-stm32-usbphyc.c
index 7df6a63ad37b..e4f4a9be5132 100644
--- a/drivers/phy/st/phy-stm32-usbphyc.c
+++ b/drivers/phy/st/phy-stm32-usbphyc.c
@@ -478,7 +478,7 @@ static void stm32_usbphyc_phy_tuning(struct stm32_usbphyc *usbphyc,
 	if (!of_property_read_bool(np, "st,no-lsfs-fb-cap"))
 		usbphyc_phy->tune |= LFSCAPEN;
 
-	if (of_property_read_bool(np, "st,slow-hs-slew-rate"))
+	if (of_property_read_bool(np, "st,decrease-hs-slew-rate"))
 		usbphyc_phy->tune |= HSDRVSLEW;
 
 	ret = of_property_read_u32(np, "st,tune-hs-dc-level", &val);
diff --git a/drivers/phy/ti/phy-am654-serdes.c b/drivers/phy/ti/phy-am654-serdes.c
index 2ff56ce77b30..c1211c4f863c 100644
--- a/drivers/phy/ti/phy-am654-serdes.c
+++ b/drivers/phy/ti/phy-am654-serdes.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/**
+/*
  * PCIe SERDES driver for AM654x SoC
  *
  * Copyright (C) 2018 - 2019 Texas Instruments Incorporated - http://www.ti.com/
diff --git a/drivers/phy/ti/phy-j721e-wiz.c b/drivers/phy/ti/phy-j721e-wiz.c
index 126f5b8735cc..b3384c31637a 100644
--- a/drivers/phy/ti/phy-j721e-wiz.c
+++ b/drivers/phy/ti/phy-j721e-wiz.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/**
+/*
  * Wrapper driver for SERDES used in J721E
  *
  * Copyright (C) 2019 Texas Instruments Incorporated - http://www.ti.com/
diff --git a/drivers/phy/ti/phy-omap-usb2.c b/drivers/phy/ti/phy-omap-usb2.c
index ebceb1520ce8..3a505fe5715a 100644
--- a/drivers/phy/ti/phy-omap-usb2.c
+++ b/drivers/phy/ti/phy-omap-usb2.c
@@ -89,9 +89,9 @@ static inline void omap_usb_writel(void __iomem *addr, unsigned int offset,
 }
 
 /**
- * omap_usb2_set_comparator - links the comparator present in the system with
- *	this phy
- * @comparator - the companion phy(comparator) for this phy
+ * omap_usb2_set_comparator() - links the comparator present in the system with this phy
+ *
+ * @comparator:  the companion phy(comparator) for this phy
  *
  * The phy companion driver should call this API passing the phy_companion
  * filled with set_vbus and start_srp to be used by usb phy.
diff --git a/drivers/phy/ti/phy-tusb1210.c b/drivers/phy/ti/phy-tusb1210.c
index a63213f5972a..15c1c79e5c29 100644
--- a/drivers/phy/ti/phy-tusb1210.c
+++ b/drivers/phy/ti/phy-tusb1210.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0-only
-/**
+/*
  * tusb1210.c - TUSB1210 USB ULPI PHY driver
  *
  * Copyright (C) 2015 Intel Corporation
diff --git a/drivers/pinctrl/bcm/pinctrl-bcm2835.c b/drivers/pinctrl/bcm/pinctrl-bcm2835.c
index 2abcc6ce4eba..b607d10e4cbd 100644
--- a/drivers/pinctrl/bcm/pinctrl-bcm2835.c
+++ b/drivers/pinctrl/bcm/pinctrl-bcm2835.c
@@ -1244,6 +1244,18 @@ static int bcm2835_pinctrl_probe(struct platform_device *pdev)
 		raw_spin_lock_init(&pc->irq_lock[i]);
 	}
 
+	pc->pctl_desc = *pdata->pctl_desc;
+	pc->pctl_dev = devm_pinctrl_register(dev, &pc->pctl_desc, pc);
+	if (IS_ERR(pc->pctl_dev)) {
+		gpiochip_remove(&pc->gpio_chip);
+		return PTR_ERR(pc->pctl_dev);
+	}
+
+	pc->gpio_range = *pdata->gpio_range;
+	pc->gpio_range.base = pc->gpio_chip.base;
+	pc->gpio_range.gc = &pc->gpio_chip;
+	pinctrl_add_gpio_range(pc->pctl_dev, &pc->gpio_range);
+
 	girq = &pc->gpio_chip.irq;
 	girq->chip = &bcm2835_gpio_irq_chip;
 	girq->parent_handler = bcm2835_gpio_irq_handler;
@@ -1251,8 +1263,10 @@ static int bcm2835_pinctrl_probe(struct platform_device *pdev)
 	girq->parents = devm_kcalloc(dev, BCM2835_NUM_IRQS,
 				     sizeof(*girq->parents),
 				     GFP_KERNEL);
-	if (!girq->parents)
+	if (!girq->parents) {
+		pinctrl_remove_gpio_range(pc->pctl_dev, &pc->gpio_range);
 		return -ENOMEM;
+	}
 
 	if (is_7211) {
 		pc->wake_irq = devm_kcalloc(dev, BCM2835_NUM_IRQS,
@@ -1307,21 +1321,10 @@ static int bcm2835_pinctrl_probe(struct platform_device *pdev)
 	err = gpiochip_add_data(&pc->gpio_chip, pc);
 	if (err) {
 		dev_err(dev, "could not add GPIO chip\n");
+		pinctrl_remove_gpio_range(pc->pctl_dev, &pc->gpio_range);
 		return err;
 	}
 
-	pc->pctl_desc = *pdata->pctl_desc;
-	pc->pctl_dev = devm_pinctrl_register(dev, &pc->pctl_desc, pc);
-	if (IS_ERR(pc->pctl_dev)) {
-		gpiochip_remove(&pc->gpio_chip);
-		return PTR_ERR(pc->pctl_dev);
-	}
-
-	pc->gpio_range = *pdata->gpio_range;
-	pc->gpio_range.base = pc->gpio_chip.base;
-	pc->gpio_range.gc = &pc->gpio_chip;
-	pinctrl_add_gpio_range(pc->pctl_dev, &pc->gpio_range);
-
 	return 0;
 }
 
diff --git a/drivers/pinctrl/mediatek/pinctrl-mtk-common-v2.c b/drivers/pinctrl/mediatek/pinctrl-mtk-common-v2.c
index 91553b2fc160..53779822348d 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mtk-common-v2.c
+++ b/drivers/pinctrl/mediatek/pinctrl-mtk-common-v2.c
@@ -285,8 +285,12 @@ static int mtk_xt_get_gpio_n(void *data, unsigned long eint_n,
 	desc = (const struct mtk_pin_desc *)hw->soc->pins;
 	*gpio_chip = &hw->chip;
 
-	/* Be greedy to guess first gpio_n is equal to eint_n */
-	if (desc[eint_n].eint.eint_n == eint_n)
+	/*
+	 * Be greedy to guess first gpio_n is equal to eint_n.
+	 * Only eint virtual eint number is greater than gpio number.
+	 */
+	if (hw->soc->npins > eint_n &&
+	    desc[eint_n].eint.eint_n == eint_n)
 		*gpio_n = eint_n;
 	else
 		*gpio_n = mtk_xt_find_eint_num(hw, eint_n);
diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c
index bae9d429b813..ecab9064a845 100644
--- a/drivers/pinctrl/pinctrl-amd.c
+++ b/drivers/pinctrl/pinctrl-amd.c
@@ -598,14 +598,14 @@ static struct irq_chip amd_gpio_irqchip = {
 
 #define PIN_IRQ_PENDING	(BIT(INTERRUPT_STS_OFF) | BIT(WAKE_STS_OFF))
 
-static irqreturn_t amd_gpio_irq_handler(int irq, void *dev_id)
+static bool do_amd_gpio_irq_handler(int irq, void *dev_id)
 {
 	struct amd_gpio *gpio_dev = dev_id;
 	struct gpio_chip *gc = &gpio_dev->gc;
-	irqreturn_t ret = IRQ_NONE;
 	unsigned int i, irqnr;
 	unsigned long flags;
 	u32 __iomem *regs;
+	bool ret = false;
 	u32  regval;
 	u64 status, mask;
 
@@ -627,6 +627,14 @@ static irqreturn_t amd_gpio_irq_handler(int irq, void *dev_id)
 		/* Each status bit covers four pins */
 		for (i = 0; i < 4; i++) {
 			regval = readl(regs + i);
+			/* caused wake on resume context for shared IRQ */
+			if (irq < 0 && (regval & BIT(WAKE_STS_OFF))) {
+				dev_dbg(&gpio_dev->pdev->dev,
+					"Waking due to GPIO %d: 0x%x",
+					irqnr + i, regval);
+				return true;
+			}
+
 			if (!(regval & PIN_IRQ_PENDING) ||
 			    !(regval & BIT(INTERRUPT_MASK_OFF)))
 				continue;
@@ -650,9 +658,12 @@ static irqreturn_t amd_gpio_irq_handler(int irq, void *dev_id)
 			}
 			writel(regval, regs + i);
 			raw_spin_unlock_irqrestore(&gpio_dev->lock, flags);
-			ret = IRQ_HANDLED;
+			ret = true;
 		}
 	}
+	/* did not cause wake on resume context for shared IRQ */
+	if (irq < 0)
+		return false;
 
 	/* Signal EOI to the GPIO unit */
 	raw_spin_lock_irqsave(&gpio_dev->lock, flags);
@@ -664,6 +675,16 @@ static irqreturn_t amd_gpio_irq_handler(int irq, void *dev_id)
 	return ret;
 }
 
+static irqreturn_t amd_gpio_irq_handler(int irq, void *dev_id)
+{
+	return IRQ_RETVAL(do_amd_gpio_irq_handler(irq, dev_id));
+}
+
+static bool __maybe_unused amd_gpio_check_wake(void *dev_id)
+{
+	return do_amd_gpio_irq_handler(-1, dev_id);
+}
+
 static int amd_get_groups_count(struct pinctrl_dev *pctldev)
 {
 	struct amd_gpio *gpio_dev = pinctrl_dev_get_drvdata(pctldev);
@@ -1033,6 +1054,7 @@ static int amd_gpio_probe(struct platform_device *pdev)
 		goto out2;
 
 	platform_set_drvdata(pdev, gpio_dev);
+	acpi_register_wakeup_handler(gpio_dev->irq, amd_gpio_check_wake, gpio_dev);
 
 	dev_dbg(&pdev->dev, "amd gpio driver loaded\n");
 	return ret;
@@ -1050,6 +1072,7 @@ static int amd_gpio_remove(struct platform_device *pdev)
 	gpio_dev = platform_get_drvdata(pdev);
 
 	gpiochip_remove(&gpio_dev->gc);
+	acpi_unregister_wakeup_handler(amd_gpio_check_wake, gpio_dev);
 
 	return 0;
 }
diff --git a/drivers/pinctrl/pinctrl-apple-gpio.c b/drivers/pinctrl/pinctrl-apple-gpio.c
index 0cc346bfc4c3..a7861079a650 100644
--- a/drivers/pinctrl/pinctrl-apple-gpio.c
+++ b/drivers/pinctrl/pinctrl-apple-gpio.c
@@ -258,7 +258,7 @@ static void apple_gpio_irq_ack(struct irq_data *data)
 	       pctl->base + REG_IRQ(irqgrp, data->hwirq));
 }
 
-static int apple_gpio_irq_type(unsigned int type)
+static unsigned int apple_gpio_irq_type(unsigned int type)
 {
 	switch (type & IRQ_TYPE_SENSE_MASK) {
 	case IRQ_TYPE_EDGE_RISING:
@@ -272,7 +272,7 @@ static int apple_gpio_irq_type(unsigned int type)
 	case IRQ_TYPE_LEVEL_LOW:
 		return REG_GPIOx_IN_IRQ_LO;
 	default:
-		return -EINVAL;
+		return REG_GPIOx_IN_IRQ_OFF;
 	}
 }
 
@@ -288,7 +288,7 @@ static void apple_gpio_irq_unmask(struct irq_data *data)
 {
 	struct apple_gpio_pinctrl *pctl =
 		gpiochip_get_data(irq_data_get_irq_chip_data(data));
-	int irqtype = apple_gpio_irq_type(irqd_get_trigger_type(data));
+	unsigned int irqtype = apple_gpio_irq_type(irqd_get_trigger_type(data));
 
 	apple_gpio_set_reg(pctl, data->hwirq, REG_GPIOx_MODE,
 			   FIELD_PREP(REG_GPIOx_MODE, irqtype));
@@ -313,10 +313,10 @@ static int apple_gpio_irq_set_type(struct irq_data *data,
 {
 	struct apple_gpio_pinctrl *pctl =
 		gpiochip_get_data(irq_data_get_irq_chip_data(data));
-	int irqtype = apple_gpio_irq_type(type);
+	unsigned int irqtype = apple_gpio_irq_type(type);
 
-	if (irqtype < 0)
-		return irqtype;
+	if (irqtype == REG_GPIOx_IN_IRQ_OFF)
+		return -EINVAL;
 
 	apple_gpio_set_reg(pctl, data->hwirq, REG_GPIOx_MODE,
 			   FIELD_PREP(REG_GPIOx_MODE, irqtype));
diff --git a/drivers/pinctrl/qcom/Kconfig b/drivers/pinctrl/qcom/Kconfig
index b9191f1abb1c..3e0c00766f59 100644
--- a/drivers/pinctrl/qcom/Kconfig
+++ b/drivers/pinctrl/qcom/Kconfig
@@ -197,6 +197,7 @@ config PINCTRL_QCOM_SPMI_PMIC
 	select PINMUX
 	select PINCONF
 	select GENERIC_PINCONF
+  select GPIOLIB
 	select GPIOLIB_IRQCHIP
 	select IRQ_DOMAIN_HIERARCHY
 	help
@@ -211,6 +212,7 @@ config PINCTRL_QCOM_SSBI_PMIC
 	select PINMUX
 	select PINCONF
 	select GENERIC_PINCONF
+  select GPIOLIB
 	select GPIOLIB_IRQCHIP
 	select IRQ_DOMAIN_HIERARCHY
 	help
diff --git a/drivers/pinctrl/qcom/pinctrl-sdm845.c b/drivers/pinctrl/qcom/pinctrl-sdm845.c
index c51793f6546f..fdfd7b8f3a76 100644
--- a/drivers/pinctrl/qcom/pinctrl-sdm845.c
+++ b/drivers/pinctrl/qcom/pinctrl-sdm845.c
@@ -1310,6 +1310,7 @@ static const struct msm_pinctrl_soc_data sdm845_pinctrl = {
 	.ngpios = 151,
 	.wakeirq_map = sdm845_pdc_map,
 	.nwakeirq_map = ARRAY_SIZE(sdm845_pdc_map),
+	.wakeirq_dual_edge_errata = true,
 };
 
 static const struct msm_pinctrl_soc_data sdm845_acpi_pinctrl = {
diff --git a/drivers/pinctrl/qcom/pinctrl-sm8350.c b/drivers/pinctrl/qcom/pinctrl-sm8350.c
index 4d8f8636c2b3..1c042d39380c 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm8350.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm8350.c
@@ -1597,10 +1597,10 @@ static const struct msm_pingroup sm8350_groups[] = {
 	[200] = PINGROUP(200, qdss_gpio, _, _, _, _, _, _, _, _),
 	[201] = PINGROUP(201, _, _, _, _, _, _, _, _, _),
 	[202] = PINGROUP(202, _, _, _, _, _, _, _, _, _),
-	[203] = UFS_RESET(ufs_reset, 0x1d8000),
-	[204] = SDC_PINGROUP(sdc2_clk, 0x1cf000, 14, 6),
-	[205] = SDC_PINGROUP(sdc2_cmd, 0x1cf000, 11, 3),
-	[206] = SDC_PINGROUP(sdc2_data, 0x1cf000, 9, 0),
+	[203] = UFS_RESET(ufs_reset, 0xd8000),
+	[204] = SDC_PINGROUP(sdc2_clk, 0xcf000, 14, 6),
+	[205] = SDC_PINGROUP(sdc2_cmd, 0xcf000, 11, 3),
+	[206] = SDC_PINGROUP(sdc2_data, 0xcf000, 9, 0),
 };
 
 static const struct msm_gpio_wakeirq_map sm8350_pdc_map[] = {
diff --git a/drivers/pinctrl/ralink/pinctrl-mt7620.c b/drivers/pinctrl/ralink/pinctrl-mt7620.c
index 425d55a2ee19..6853b5b8b0fe 100644
--- a/drivers/pinctrl/ralink/pinctrl-mt7620.c
+++ b/drivers/pinctrl/ralink/pinctrl-mt7620.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 
+#include <asm/mach-ralink/ralink_regs.h>
 #include <asm/mach-ralink/mt7620.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
diff --git a/drivers/pinctrl/stm32/pinctrl-stm32.c b/drivers/pinctrl/stm32/pinctrl-stm32.c
index 24764ebcc936..9ed764731570 100644
--- a/drivers/pinctrl/stm32/pinctrl-stm32.c
+++ b/drivers/pinctrl/stm32/pinctrl-stm32.c
@@ -1251,10 +1251,10 @@ static int stm32_gpiolib_register_bank(struct stm32_pinctrl *pctl,
 		bank_nr = args.args[1] / STM32_GPIO_PINS_PER_BANK;
 		bank->gpio_chip.base = args.args[1];
 
-		npins = args.args[2];
-		while (!of_parse_phandle_with_fixed_args(np, "gpio-ranges", 3,
-							 ++i, &args))
-			npins += args.args[2];
+		/* get the last defined gpio line (offset + nb of pins) */
+		npins = args.args[0] + args.args[2];
+		while (!of_parse_phandle_with_fixed_args(np, "gpio-ranges", 3, ++i, &args))
+			npins = max(npins, (int)(args.args[0] + args.args[2]));
 	} else {
 		bank_nr = pctl->nbanks;
 		bank->gpio_chip.base = bank_nr * STM32_GPIO_PINS_PER_BANK;
diff --git a/drivers/pinctrl/tegra/pinctrl-tegra.c b/drivers/pinctrl/tegra/pinctrl-tegra.c
index 8d734bfc33d2..50bd26a30ac0 100644
--- a/drivers/pinctrl/tegra/pinctrl-tegra.c
+++ b/drivers/pinctrl/tegra/pinctrl-tegra.c
@@ -275,7 +275,7 @@ static int tegra_pinctrl_set_mux(struct pinctrl_dev *pctldev,
 	return 0;
 }
 
-static struct tegra_pingroup *tegra_pinctrl_get_group(struct pinctrl_dev *pctldev,
+static const struct tegra_pingroup *tegra_pinctrl_get_group(struct pinctrl_dev *pctldev,
 					unsigned int offset)
 {
 	struct tegra_pmx *pmx = pinctrl_dev_get_drvdata(pctldev);
@@ -289,7 +289,7 @@ static struct tegra_pingroup *tegra_pinctrl_get_group(struct pinctrl_dev *pctlde
 			continue;
 		for (j = 0; j < num_pins; j++) {
 			if (offset == pins[j])
-				return (struct tegra_pingroup *)&pmx->soc->groups[group];
+				return &pmx->soc->groups[group];
 		}
 	}
 
diff --git a/drivers/pinctrl/tegra/pinctrl-tegra194.c b/drivers/pinctrl/tegra/pinctrl-tegra194.c
index b4fef9185d88..5c1dfcb46749 100644
--- a/drivers/pinctrl/tegra/pinctrl-tegra194.c
+++ b/drivers/pinctrl/tegra/pinctrl-tegra194.c
@@ -1387,7 +1387,6 @@ static struct tegra_function tegra194_functions[] = {
 		.schmitt_bit = schmitt_b,			\
 		.drvtype_bit = 13,				\
 		.lpdr_bit = e_lpdr,				\
-		.drv_reg = -1,					\
 
 #define drive_touch_clk_pcc4            DRV_PINGROUP_ENTRY_Y(0x2004,	12,	5,	20,	5,	-1,	-1,	-1,	-1,	1)
 #define drive_uart3_rx_pcc6             DRV_PINGROUP_ENTRY_Y(0x200c,	12,	5,	20,	5,	-1,	-1,	-1,	-1,	1)
diff --git a/drivers/platform/chrome/cros_ec_ishtp.c b/drivers/platform/chrome/cros_ec_ishtp.c
index 9d1e7e03628e..4020b8354bae 100644
--- a/drivers/platform/chrome/cros_ec_ishtp.c
+++ b/drivers/platform/chrome/cros_ec_ishtp.c
@@ -41,9 +41,12 @@ enum cros_ec_ish_channel {
 #define ISHTP_SEND_TIMEOUT			(3 * HZ)
 
 /* ISH Transport CrOS EC ISH client unique GUID */
-static const guid_t cros_ish_guid =
-	GUID_INIT(0x7b7154d0, 0x56f4, 0x4bdc,
-		  0xb0, 0xd8, 0x9e, 0x7c, 0xda,	0xe0, 0xd6, 0xa0);
+static const struct ishtp_device_id cros_ec_ishtp_id_table[] = {
+	{ .guid = GUID_INIT(0x7b7154d0, 0x56f4, 0x4bdc,
+		  0xb0, 0xd8, 0x9e, 0x7c, 0xda,	0xe0, 0xd6, 0xa0), },
+	{ }
+};
+MODULE_DEVICE_TABLE(ishtp, cros_ec_ishtp_id_table);
 
 struct header {
 	u8 channel;
@@ -389,7 +392,7 @@ static int cros_ish_init(struct ishtp_cl *cros_ish_cl)
 	ishtp_set_tx_ring_size(cros_ish_cl, CROS_ISH_CL_TX_RING_SIZE);
 	ishtp_set_rx_ring_size(cros_ish_cl, CROS_ISH_CL_RX_RING_SIZE);
 
-	fw_client = ishtp_fw_cl_get_client(dev, &cros_ish_guid);
+	fw_client = ishtp_fw_cl_get_client(dev, &cros_ec_ishtp_id_table[0].guid);
 	if (!fw_client) {
 		dev_err(cl_data_to_dev(client_data),
 			"ish client uuid not found\n");
@@ -765,7 +768,7 @@ static SIMPLE_DEV_PM_OPS(cros_ec_ishtp_pm_ops, cros_ec_ishtp_suspend,
 
 static struct ishtp_cl_driver	cros_ec_ishtp_driver = {
 	.name = "cros_ec_ishtp",
-	.guid = &cros_ish_guid,
+	.id = cros_ec_ishtp_id_table,
 	.probe = cros_ec_ishtp_probe,
 	.remove = cros_ec_ishtp_remove,
 	.reset = cros_ec_ishtp_reset,
@@ -791,4 +794,3 @@ MODULE_DESCRIPTION("ChromeOS EC ISHTP Client Driver");
 MODULE_AUTHOR("Rushikesh S Kadam <rushikesh.s.kadam@intel.com>");
 
 MODULE_LICENSE("GPL v2");
-MODULE_ALIAS("ishtp:*");
diff --git a/drivers/platform/mellanox/mlxbf-pmc.c b/drivers/platform/mellanox/mlxbf-pmc.c
index 04bc3b50aa7a..65b4a819f1bd 100644
--- a/drivers/platform/mellanox/mlxbf-pmc.c
+++ b/drivers/platform/mellanox/mlxbf-pmc.c
@@ -1374,8 +1374,8 @@ static int mlxbf_pmc_map_counters(struct device *dev)
 		pmc->block[i].counters = info[2];
 		pmc->block[i].type = info[3];
 
-		if (IS_ERR(pmc->block[i].mmio_base))
-			return PTR_ERR(pmc->block[i].mmio_base);
+		if (!pmc->block[i].mmio_base)
+			return -ENOMEM;
 
 		ret = mlxbf_pmc_create_groups(dev, i);
 		if (ret)
diff --git a/drivers/platform/mellanox/mlxreg-lc.c b/drivers/platform/mellanox/mlxreg-lc.c
index 0b7f58feb701..c897a2f15840 100644
--- a/drivers/platform/mellanox/mlxreg-lc.c
+++ b/drivers/platform/mellanox/mlxreg-lc.c
@@ -413,7 +413,7 @@ mlxreg_lc_create_static_devices(struct mlxreg_lc *mlxreg_lc, struct mlxreg_hotpl
 				int size)
 {
 	struct mlxreg_hotplug_device *dev = devs;
-	int i;
+	int i, ret;
 
 	/* Create static I2C device feeding by auxiliary or main power. */
 	for (i = 0; i < size; i++, dev++) {
@@ -423,6 +423,7 @@ mlxreg_lc_create_static_devices(struct mlxreg_lc *mlxreg_lc, struct mlxreg_hotpl
 				dev->brdinfo->type, dev->nr, dev->brdinfo->addr);
 
 			dev->adapter = NULL;
+			ret = PTR_ERR(dev->client);
 			goto fail_create_static_devices;
 		}
 	}
@@ -435,7 +436,7 @@ fail_create_static_devices:
 		i2c_unregister_device(dev->client);
 		dev->client = NULL;
 	}
-	return IS_ERR(dev->client);
+	return ret;
 }
 
 static void
diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig
index d4c079f4afc6..7400bc5da5be 100644
--- a/drivers/platform/x86/Kconfig
+++ b/drivers/platform/x86/Kconfig
@@ -185,7 +185,7 @@ config ACER_WMI
 
 config AMD_PMC
 	tristate "AMD SoC PMC driver"
-	depends on ACPI && PCI
+	depends on ACPI && PCI && RTC_CLASS
 	help
 	  The driver provides support for AMD Power Management Controller
 	  primarily responsible for S2Idle transactions that are driven from
diff --git a/drivers/platform/x86/Makefile b/drivers/platform/x86/Makefile
index 219478061683..253a096b5dd8 100644
--- a/drivers/platform/x86/Makefile
+++ b/drivers/platform/x86/Makefile
@@ -68,7 +68,7 @@ obj-$(CONFIG_THINKPAD_ACPI)	+= thinkpad_acpi.o
 obj-$(CONFIG_THINKPAD_LMI)	+= think-lmi.o
 
 # Intel
-obj-$(CONFIG_X86_PLATFORM_DRIVERS_INTEL)		+= intel/
+obj-y				+= intel/
 
 # MSI
 obj-$(CONFIG_MSI_LAPTOP)	+= msi-laptop.o
diff --git a/drivers/platform/x86/amd-pmc.c b/drivers/platform/x86/amd-pmc.c
index b7e50ed050a8..230593ae5d6d 100644
--- a/drivers/platform/x86/amd-pmc.c
+++ b/drivers/platform/x86/amd-pmc.c
@@ -76,7 +76,7 @@
 #define AMD_CPU_ID_CZN			AMD_CPU_ID_RN
 #define AMD_CPU_ID_YC			0x14B5
 
-#define PMC_MSG_DELAY_MIN_US		100
+#define PMC_MSG_DELAY_MIN_US		50
 #define RESPONSE_REGISTER_LOOP_MAX	20000
 
 #define SOC_SUBSYSTEM_IP_MAX	12
@@ -508,7 +508,8 @@ static int __maybe_unused amd_pmc_resume(struct device *dev)
 }
 
 static const struct dev_pm_ops amd_pmc_pm_ops = {
-	SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(amd_pmc_suspend, amd_pmc_resume)
+	.suspend_noirq = amd_pmc_suspend,
+	.resume_noirq = amd_pmc_resume,
 };
 
 static const struct pci_device_id pmc_pci_ids[] = {
diff --git a/drivers/platform/x86/apple-gmux.c b/drivers/platform/x86/apple-gmux.c
index 9aae45a45200..57553f9b4d1d 100644
--- a/drivers/platform/x86/apple-gmux.c
+++ b/drivers/platform/x86/apple-gmux.c
@@ -625,7 +625,7 @@ static int gmux_probe(struct pnp_dev *pnp, const struct pnp_device_id *id)
 	}
 
 	gmux_data->iostart = res->start;
-	gmux_data->iolen = res->end - res->start;
+	gmux_data->iolen = resource_size(res);
 
 	if (gmux_data->iolen < GMUX_MIN_IO_LEN) {
 		pr_err("gmux I/O region too small (%lu < %u)\n",
diff --git a/drivers/platform/x86/dell/Kconfig b/drivers/platform/x86/dell/Kconfig
index 2fffa57e596e..fe224a54f24c 100644
--- a/drivers/platform/x86/dell/Kconfig
+++ b/drivers/platform/x86/dell/Kconfig
@@ -187,7 +187,7 @@ config DELL_WMI_AIO
 
 config DELL_WMI_DESCRIPTOR
 	tristate
-	default m
+	default n
 	depends on ACPI_WMI
 
 config DELL_WMI_LED
diff --git a/drivers/platform/x86/hp_accel.c b/drivers/platform/x86/hp_accel.c
index b183967ecfb7..435a91fe2568 100644
--- a/drivers/platform/x86/hp_accel.c
+++ b/drivers/platform/x86/hp_accel.c
@@ -331,9 +331,11 @@ static int lis3lv02d_probe(struct platform_device *device)
 	INIT_WORK(&hpled_led.work, delayed_set_status_worker);
 	ret = led_classdev_register(NULL, &hpled_led.led_classdev);
 	if (ret) {
+		i8042_remove_filter(hp_accel_i8042_filter);
 		lis3lv02d_joystick_disable(&lis3_dev);
 		lis3lv02d_poweroff(&lis3_dev);
 		flush_work(&hpled_led.work);
+		lis3lv02d_remove_fs(&lis3_dev);
 		return ret;
 	}
 
diff --git a/drivers/platform/x86/intel/Kconfig b/drivers/platform/x86/intel/Kconfig
index 38ce3e344589..40096b25994a 100644
--- a/drivers/platform/x86/intel/Kconfig
+++ b/drivers/platform/x86/intel/Kconfig
@@ -3,19 +3,6 @@
 # Intel x86 Platform Specific Drivers
 #
 
-menuconfig X86_PLATFORM_DRIVERS_INTEL
-	bool "Intel x86 Platform Specific Device Drivers"
-	default y
-	help
-	  Say Y here to get to see options for device drivers for
-	  various Intel x86 platforms, including vendor-specific
-	  drivers. This option alone does not add any kernel code.
-
-	  If you say N, all options in this submenu will be skipped
-	  and disabled.
-
-if X86_PLATFORM_DRIVERS_INTEL
-
 source "drivers/platform/x86/intel/atomisp2/Kconfig"
 source "drivers/platform/x86/intel/int1092/Kconfig"
 source "drivers/platform/x86/intel/int33fe/Kconfig"
@@ -183,5 +170,3 @@ config INTEL_UNCORE_FREQ_CONTROL
 
 	  To compile this driver as a module, choose M here: the module
 	  will be called intel-uncore-frequency.
-
-endif # X86_PLATFORM_DRIVERS_INTEL
diff --git a/drivers/platform/x86/intel/hid.c b/drivers/platform/x86/intel/hid.c
index 08598942a6d7..13f8cf70b9ae 100644
--- a/drivers/platform/x86/intel/hid.c
+++ b/drivers/platform/x86/intel/hid.c
@@ -99,6 +99,13 @@ static const struct dmi_system_id button_array_table[] = {
 			DMI_MATCH(DMI_PRODUCT_FAMILY, "ThinkPad X1 Tablet Gen 2"),
 		},
 	},
+	{
+		.ident = "Microsoft Surface Go 3",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Microsoft Corporation"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Surface Go 3"),
+		},
+	},
 	{ }
 };
 
diff --git a/drivers/platform/x86/intel/ishtp_eclite.c b/drivers/platform/x86/intel/ishtp_eclite.c
index 12fc98a48657..93ac8b2dbf38 100644
--- a/drivers/platform/x86/intel/ishtp_eclite.c
+++ b/drivers/platform/x86/intel/ishtp_eclite.c
@@ -93,9 +93,12 @@ struct ishtp_opregion_dev {
 };
 
 /* eclite ishtp client UUID: 6a19cc4b-d760-4de3-b14d-f25ebd0fbcd9 */
-static const guid_t ecl_ishtp_guid =
-	GUID_INIT(0x6a19cc4b, 0xd760, 0x4de3,
-		  0xb1, 0x4d, 0xf2, 0x5e, 0xbd, 0xf, 0xbc, 0xd9);
+static const struct ishtp_device_id ecl_ishtp_id_table[] = {
+	{ .guid = GUID_INIT(0x6a19cc4b, 0xd760, 0x4de3,
+		  0xb1, 0x4d, 0xf2, 0x5e, 0xbd, 0xf, 0xbc, 0xd9), },
+	{ }
+};
+MODULE_DEVICE_TABLE(ishtp, ecl_ishtp_id_table);
 
 /* ACPI DSM UUID: 91d936a7-1f01-49c6-a6b4-72f00ad8d8a5 */
 static const guid_t ecl_acpi_guid =
@@ -462,7 +465,7 @@ static int ecl_ishtp_cl_init(struct ishtp_cl *ecl_ishtp_cl)
 	ishtp_set_tx_ring_size(ecl_ishtp_cl, ECL_CL_TX_RING_SIZE);
 	ishtp_set_rx_ring_size(ecl_ishtp_cl, ECL_CL_RX_RING_SIZE);
 
-	fw_client = ishtp_fw_cl_get_client(dev, &ecl_ishtp_guid);
+	fw_client = ishtp_fw_cl_get_client(dev, &ecl_ishtp_id_table[0].guid);
 	if (!fw_client) {
 		dev_err(cl_data_to_dev(opr_dev), "fw client not found\n");
 		return -ENOENT;
@@ -674,7 +677,7 @@ static const struct dev_pm_ops ecl_ishtp_pm_ops = {
 
 static struct ishtp_cl_driver ecl_ishtp_cl_driver = {
 	.name = "ishtp-eclite",
-	.guid = &ecl_ishtp_guid,
+	.id = ecl_ishtp_id_table,
 	.probe = ecl_ishtp_cl_probe,
 	.remove = ecl_ishtp_cl_remove,
 	.reset = ecl_ishtp_cl_reset,
@@ -698,4 +701,3 @@ MODULE_DESCRIPTION("ISH ISHTP eclite client opregion driver");
 MODULE_AUTHOR("K Naduvalath, Sumesh <sumesh.k.naduvalath@intel.com>");
 
 MODULE_LICENSE("GPL v2");
-MODULE_ALIAS("ishtp:*");
diff --git a/drivers/platform/x86/intel/pmc/pltdrv.c b/drivers/platform/x86/intel/pmc/pltdrv.c
index 73797680b895..15ca8afdd973 100644
--- a/drivers/platform/x86/intel/pmc/pltdrv.c
+++ b/drivers/platform/x86/intel/pmc/pltdrv.c
@@ -65,7 +65,7 @@ static int __init pmc_core_platform_init(void)
 
 	retval = platform_device_register(pmc_core_device);
 	if (retval)
-		kfree(pmc_core_device);
+		platform_device_put(pmc_core_device);
 
 	return retval;
 }
diff --git a/drivers/platform/x86/lg-laptop.c b/drivers/platform/x86/lg-laptop.c
index ae9293024c77..a91847a551a7 100644
--- a/drivers/platform/x86/lg-laptop.c
+++ b/drivers/platform/x86/lg-laptop.c
@@ -657,6 +657,18 @@ static int acpi_add(struct acpi_device *device)
 	if (product && strlen(product) > 4)
 		switch (product[4]) {
 		case '5':
+			if (strlen(product) > 5)
+				switch (product[5]) {
+				case 'N':
+					year = 2021;
+					break;
+				case '0':
+					year = 2016;
+					break;
+				default:
+					year = 2022;
+				}
+			break;
 		case '6':
 			year = 2016;
 			break;
diff --git a/drivers/platform/x86/samsung-laptop.c b/drivers/platform/x86/samsung-laptop.c
index 7ee010aa740a..c1d9ed9b7b67 100644
--- a/drivers/platform/x86/samsung-laptop.c
+++ b/drivers/platform/x86/samsung-laptop.c
@@ -152,7 +152,7 @@ struct sabi_config {
 
 static const struct sabi_config sabi_configs[] = {
 	{
-		/* I don't know if it is really 2, but it it is
+		/* I don't know if it is really 2, but it is
 		 * less than 3 anyway */
 		.sabi_version = 2,
 
diff --git a/drivers/platform/x86/system76_acpi.c b/drivers/platform/x86/system76_acpi.c
index 8b292ee95a14..7299ad08c838 100644
--- a/drivers/platform/x86/system76_acpi.c
+++ b/drivers/platform/x86/system76_acpi.c
@@ -35,6 +35,7 @@ struct system76_data {
 	union acpi_object *nfan;
 	union acpi_object *ntmp;
 	struct input_dev *input;
+	bool has_open_ec;
 };
 
 static const struct acpi_device_id device_ids[] = {
@@ -279,20 +280,12 @@ static struct acpi_battery_hook system76_battery_hook = {
 
 static void system76_battery_init(void)
 {
-	acpi_handle handle;
-
-	handle = ec_get_handle();
-	if (handle && acpi_has_method(handle, "GBCT"))
-		battery_hook_register(&system76_battery_hook);
+	battery_hook_register(&system76_battery_hook);
 }
 
 static void system76_battery_exit(void)
 {
-	acpi_handle handle;
-
-	handle = ec_get_handle();
-	if (handle && acpi_has_method(handle, "GBCT"))
-		battery_hook_unregister(&system76_battery_hook);
+	battery_hook_unregister(&system76_battery_hook);
 }
 
 // Get the airplane mode LED brightness
@@ -673,6 +666,10 @@ static int system76_add(struct acpi_device *acpi_dev)
 	acpi_dev->driver_data = data;
 	data->acpi_dev = acpi_dev;
 
+	// Some models do not run open EC firmware. Check for an ACPI method
+	// that only exists on open EC to guard functionality specific to it.
+	data->has_open_ec = acpi_has_method(acpi_device_handle(data->acpi_dev), "NFAN");
+
 	err = system76_get(data, "INIT");
 	if (err)
 		return err;
@@ -718,27 +715,31 @@ static int system76_add(struct acpi_device *acpi_dev)
 	if (err)
 		goto error;
 
-	err = system76_get_object(data, "NFAN", &data->nfan);
-	if (err)
-		goto error;
+	if (data->has_open_ec) {
+		err = system76_get_object(data, "NFAN", &data->nfan);
+		if (err)
+			goto error;
 
-	err = system76_get_object(data, "NTMP", &data->ntmp);
-	if (err)
-		goto error;
+		err = system76_get_object(data, "NTMP", &data->ntmp);
+		if (err)
+			goto error;
 
-	data->therm = devm_hwmon_device_register_with_info(&acpi_dev->dev,
-		"system76_acpi", data, &thermal_chip_info, NULL);
-	err = PTR_ERR_OR_ZERO(data->therm);
-	if (err)
-		goto error;
+		data->therm = devm_hwmon_device_register_with_info(&acpi_dev->dev,
+			"system76_acpi", data, &thermal_chip_info, NULL);
+		err = PTR_ERR_OR_ZERO(data->therm);
+		if (err)
+			goto error;
 
-	system76_battery_init();
+		system76_battery_init();
+	}
 
 	return 0;
 
 error:
-	kfree(data->ntmp);
-	kfree(data->nfan);
+	if (data->has_open_ec) {
+		kfree(data->ntmp);
+		kfree(data->nfan);
+	}
 	return err;
 }
 
@@ -749,14 +750,15 @@ static int system76_remove(struct acpi_device *acpi_dev)
 
 	data = acpi_driver_data(acpi_dev);
 
-	system76_battery_exit();
+	if (data->has_open_ec) {
+		system76_battery_exit();
+		kfree(data->nfan);
+		kfree(data->ntmp);
+	}
 
 	devm_led_classdev_unregister(&acpi_dev->dev, &data->ap_led);
 	devm_led_classdev_unregister(&acpi_dev->dev, &data->kb_led);
 
-	kfree(data->nfan);
-	kfree(data->ntmp);
-
 	system76_get(data, "FINI");
 
 	return 0;
diff --git a/drivers/platform/x86/think-lmi.c b/drivers/platform/x86/think-lmi.c
index 9472aae72df2..c4d9c45350f7 100644
--- a/drivers/platform/x86/think-lmi.c
+++ b/drivers/platform/x86/think-lmi.c
@@ -888,8 +888,10 @@ static int tlmi_analyze(void)
 			break;
 		if (!item)
 			break;
-		if (!*item)
+		if (!*item) {
+			kfree(item);
 			continue;
+		}
 
 		/* It is not allowed to have '/' for file name. Convert it into '\'. */
 		strreplace(item, '/', '\\');
@@ -902,6 +904,7 @@ static int tlmi_analyze(void)
 		setting = kzalloc(sizeof(*setting), GFP_KERNEL);
 		if (!setting) {
 			ret = -ENOMEM;
+			kfree(item);
 			goto fail_clear_attr;
 		}
 		setting->index = i;
@@ -916,7 +919,6 @@ static int tlmi_analyze(void)
 		}
 		kobject_init(&setting->kobj, &tlmi_attr_setting_ktype);
 		tlmi_priv.setting[i] = setting;
-		tlmi_priv.settings_count++;
 		kfree(item);
 	}
 
@@ -983,7 +985,12 @@ static void tlmi_remove(struct wmi_device *wdev)
 
 static int tlmi_probe(struct wmi_device *wdev, const void *context)
 {
-	tlmi_analyze();
+	int ret;
+
+	ret = tlmi_analyze();
+	if (ret)
+		return ret;
+
 	return tlmi_sysfs_init();
 }
 
diff --git a/drivers/platform/x86/think-lmi.h b/drivers/platform/x86/think-lmi.h
index f8e26823075f..2ce5086a5af2 100644
--- a/drivers/platform/x86/think-lmi.h
+++ b/drivers/platform/x86/think-lmi.h
@@ -55,7 +55,6 @@ struct tlmi_attr_setting {
 struct think_lmi {
 	struct wmi_device *wmi_device;
 
-	int settings_count;
 	bool can_set_bios_settings;
 	bool can_get_bios_selections;
 	bool can_set_bios_password;
diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c
index 9c632df734bb..bb1abb947e1e 100644
--- a/drivers/platform/x86/thinkpad_acpi.c
+++ b/drivers/platform/x86/thinkpad_acpi.c
@@ -1105,15 +1105,6 @@ static int tpacpi_rfk_update_swstate(const struct tpacpi_rfk *tp_rfk)
 	return status;
 }
 
-/* Query FW and update rfkill sw state for all rfkill switches */
-static void tpacpi_rfk_update_swstate_all(void)
-{
-	unsigned int i;
-
-	for (i = 0; i < TPACPI_RFK_SW_MAX; i++)
-		tpacpi_rfk_update_swstate(tpacpi_rfkill_switches[i]);
-}
-
 /*
  * Sync the HW-blocking state of all rfkill switches,
  * do notice it causes the rfkill core to schedule uevents
@@ -3024,6 +3015,8 @@ static struct attribute *hotkey_attributes[] = {
 	&dev_attr_hotkey_all_mask.attr,
 	&dev_attr_hotkey_adaptive_all_mask.attr,
 	&dev_attr_hotkey_recommended_mask.attr,
+	&dev_attr_hotkey_tablet_mode.attr,
+	&dev_attr_hotkey_radio_sw.attr,
 #ifdef CONFIG_THINKPAD_ACPI_HOTKEY_POLL
 	&dev_attr_hotkey_source_mask.attr,
 	&dev_attr_hotkey_poll_freq.attr,
@@ -3074,9 +3067,6 @@ static void tpacpi_send_radiosw_update(void)
 	if (wlsw == TPACPI_RFK_RADIO_OFF)
 		tpacpi_rfk_update_hwblock_state(true);
 
-	/* Sync sw blocking state */
-	tpacpi_rfk_update_swstate_all();
-
 	/* Sync hw blocking state last if it is hw-unblocked */
 	if (wlsw == TPACPI_RFK_RADIO_ON)
 		tpacpi_rfk_update_hwblock_state(false);
@@ -5738,11 +5728,11 @@ static const char * const tpacpi_led_names[TPACPI_LED_NUMLEDS] = {
 	"tpacpi::standby",
 	"tpacpi::dock_status1",
 	"tpacpi::dock_status2",
-	"tpacpi::unknown_led2",
+	"tpacpi::lid_logo_dot",
 	"tpacpi::unknown_led3",
 	"tpacpi::thinkvantage",
 };
-#define TPACPI_SAFE_LEDS	0x1081U
+#define TPACPI_SAFE_LEDS	0x1481U
 
 static inline bool tpacpi_is_led_restricted(const unsigned int led)
 {
@@ -8766,6 +8756,7 @@ static const struct tpacpi_quirk fan_quirk_table[] __initconst = {
 	TPACPI_Q_LNV3('N', '2', 'E', TPACPI_FAN_2CTL),	/* P1 / X1 Extreme (1st gen) */
 	TPACPI_Q_LNV3('N', '2', 'O', TPACPI_FAN_2CTL),	/* P1 / X1 Extreme (2nd gen) */
 	TPACPI_Q_LNV3('N', '2', 'V', TPACPI_FAN_2CTL),	/* P1 / X1 Extreme (3nd gen) */
+	TPACPI_Q_LNV3('N', '4', '0', TPACPI_FAN_2CTL),	/* P1 / X1 Extreme (4nd gen) */
 	TPACPI_Q_LNV3('N', '3', '0', TPACPI_FAN_2CTL),	/* P15 (1st gen) / P15v (1st gen) */
 	TPACPI_Q_LNV3('N', '3', '2', TPACPI_FAN_2CTL),	/* X1 Carbon (9th gen) */
 };
diff --git a/drivers/platform/x86/touchscreen_dmi.c b/drivers/platform/x86/touchscreen_dmi.c
index fa8812039b82..17dd54d4b783 100644
--- a/drivers/platform/x86/touchscreen_dmi.c
+++ b/drivers/platform/x86/touchscreen_dmi.c
@@ -905,6 +905,16 @@ static const struct ts_dmi_data trekstor_primetab_t13b_data = {
 	.properties = trekstor_primetab_t13b_props,
 };
 
+static const struct property_entry trekstor_surftab_duo_w1_props[] = {
+	PROPERTY_ENTRY_BOOL("touchscreen-inverted-x"),
+	{ }
+};
+
+static const struct ts_dmi_data trekstor_surftab_duo_w1_data = {
+	.acpi_name	= "GDIX1001:00",
+	.properties	= trekstor_surftab_duo_w1_props,
+};
+
 static const struct property_entry trekstor_surftab_twin_10_1_props[] = {
 	PROPERTY_ENTRY_U32("touchscreen-min-x", 20),
 	PROPERTY_ENTRY_U32("touchscreen-min-y", 0),
@@ -1503,6 +1513,14 @@ const struct dmi_system_id touchscreen_dmi_table[] = {
 		},
 	},
 	{
+		/* TrekStor SurfTab duo W1 10.1 ST10432-10b */
+		.driver_data = (void *)&trekstor_surftab_duo_w1_data,
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "TrekStor"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "SurfTab duo W1 10.1 (VT4)"),
+		},
+	},
+	{
 		/* TrekStor SurfTab twin 10.1 ST10432-8 */
 		.driver_data = (void *)&trekstor_surftab_twin_10_1_data,
 		.matches = {
diff --git a/drivers/powercap/dtpm.c b/drivers/powercap/dtpm.c
index b9fac786246a..2a5c1829aab7 100644
--- a/drivers/powercap/dtpm.c
+++ b/drivers/powercap/dtpm.c
@@ -463,17 +463,12 @@ int dtpm_register(const char *name, struct dtpm *dtpm, struct dtpm *parent)
 
 static int __init init_dtpm(void)
 {
-	struct dtpm_descr *dtpm_descr;
-
 	pct = powercap_register_control_type(NULL, "dtpm", NULL);
 	if (IS_ERR(pct)) {
 		pr_err("Failed to register control type\n");
 		return PTR_ERR(pct);
 	}
 
-	for_each_dtpm_table(dtpm_descr)
-		dtpm_descr->init();
-
 	return 0;
 }
 late_initcall(init_dtpm);
diff --git a/drivers/powercap/dtpm_cpu.c b/drivers/powercap/dtpm_cpu.c
index 44faa3a74db6..b740866b228d 100644
--- a/drivers/powercap/dtpm_cpu.c
+++ b/drivers/powercap/dtpm_cpu.c
@@ -166,16 +166,13 @@ static struct dtpm_ops dtpm_ops = {
 
 static int cpuhp_dtpm_cpu_offline(unsigned int cpu)
 {
-	struct em_perf_domain *pd;
 	struct dtpm_cpu *dtpm_cpu;
 
-	pd = em_cpu_get(cpu);
-	if (!pd)
-		return -EINVAL;
-
 	dtpm_cpu = per_cpu(dtpm_per_cpu, cpu);
+	if (dtpm_cpu)
+		dtpm_update_power(&dtpm_cpu->dtpm);
 
-	return dtpm_update_power(&dtpm_cpu->dtpm);
+	return 0;
 }
 
 static int cpuhp_dtpm_cpu_online(unsigned int cpu)
diff --git a/drivers/ptp/ptp_clockmatrix.c b/drivers/ptp/ptp_clockmatrix.c
index 6bc5791a7ec5..08e429a06922 100644
--- a/drivers/ptp/ptp_clockmatrix.c
+++ b/drivers/ptp/ptp_clockmatrix.c
@@ -1699,12 +1699,9 @@ static int initialize_dco_operating_mode(struct idtcm_channel *channel)
 
 /* PTP Hardware Clock interface */
 
-/**
+/*
  * Maximum absolute value for write phase offset in picoseconds
  *
- * @channel:  channel
- * @delta_ns: delta in nanoseconds
- *
  * Destination signed register is 32-bit register in resolution of 50ps
  *
  * 0x7fffffff * 50 =  2147483647 * 50 = 107374182350
diff --git a/drivers/ptp/ptp_ocp.c b/drivers/ptp/ptp_ocp.c
index 34f943c8c9fd..0f1b5a7d2a89 100644
--- a/drivers/ptp/ptp_ocp.c
+++ b/drivers/ptp/ptp_ocp.c
@@ -1304,10 +1304,11 @@ ptp_ocp_register_ext(struct ptp_ocp *bp, struct ocp_resource *r)
 	if (!ext)
 		return -ENOMEM;
 
-	err = -EINVAL;
 	ext->mem = ptp_ocp_get_mem(bp, r);
-	if (!ext->mem)
+	if (IS_ERR(ext->mem)) {
+		err = PTR_ERR(ext->mem);
 		goto out;
+	}
 
 	ext->bp = bp;
 	ext->info = r->extra;
@@ -1371,8 +1372,8 @@ ptp_ocp_register_mem(struct ptp_ocp *bp, struct ocp_resource *r)
 	void __iomem *mem;
 
 	mem = ptp_ocp_get_mem(bp, r);
-	if (!mem)
-		return -EINVAL;
+	if (IS_ERR(mem))
+		return PTR_ERR(mem);
 
 	bp_assign_entry(bp, r, mem);
 
diff --git a/drivers/reset/tegra/reset-bpmp.c b/drivers/reset/tegra/reset-bpmp.c
index 4c5bba52b105..24d3395964cc 100644
--- a/drivers/reset/tegra/reset-bpmp.c
+++ b/drivers/reset/tegra/reset-bpmp.c
@@ -20,7 +20,6 @@ static int tegra_bpmp_reset_common(struct reset_controller_dev *rstc,
 	struct tegra_bpmp *bpmp = to_tegra_bpmp(rstc);
 	struct mrq_reset_request request;
 	struct tegra_bpmp_message msg;
-	int err;
 
 	memset(&request, 0, sizeof(request));
 	request.cmd = command;
@@ -31,13 +30,7 @@ static int tegra_bpmp_reset_common(struct reset_controller_dev *rstc,
 	msg.tx.data = &request;
 	msg.tx.size = sizeof(request);
 
-	err = tegra_bpmp_transfer(bpmp, &msg);
-	if (err)
-		return err;
-	if (msg.rx.ret)
-		return -EINVAL;
-
-	return 0;
+	return tegra_bpmp_transfer(bpmp, &msg);
 }
 
 static int tegra_bpmp_reset_module(struct reset_controller_dev *rstc,
diff --git a/drivers/s390/block/dasd_devmap.c b/drivers/s390/block/dasd_devmap.c
index 2c40fe15da55..6043c832d09e 100644
--- a/drivers/s390/block/dasd_devmap.c
+++ b/drivers/s390/block/dasd_devmap.c
@@ -731,7 +731,7 @@ static ssize_t dasd_ff_show(struct device *dev, struct device_attribute *attr,
 		ff_flag = (devmap->features & DASD_FEATURE_FAILFAST) != 0;
 	else
 		ff_flag = (DASD_FEATURE_DEFAULT & DASD_FEATURE_FAILFAST) != 0;
-	return snprintf(buf, PAGE_SIZE, ff_flag ? "1\n" : "0\n");
+	return sysfs_emit(buf, ff_flag ? "1\n" : "0\n");
 }
 
 static ssize_t dasd_ff_store(struct device *dev, struct device_attribute *attr,
@@ -773,7 +773,7 @@ dasd_ro_show(struct device *dev, struct device_attribute *attr, char *buf)
 	spin_unlock(&dasd_devmap_lock);
 
 out:
-	return snprintf(buf, PAGE_SIZE, ro_flag ? "1\n" : "0\n");
+	return sysfs_emit(buf, ro_flag ? "1\n" : "0\n");
 }
 
 static ssize_t
@@ -834,7 +834,7 @@ dasd_erplog_show(struct device *dev, struct device_attribute *attr, char *buf)
 		erplog = (devmap->features & DASD_FEATURE_ERPLOG) != 0;
 	else
 		erplog = (DASD_FEATURE_DEFAULT & DASD_FEATURE_ERPLOG) != 0;
-	return snprintf(buf, PAGE_SIZE, erplog ? "1\n" : "0\n");
+	return sysfs_emit(buf, erplog ? "1\n" : "0\n");
 }
 
 static ssize_t
@@ -1033,13 +1033,13 @@ dasd_discipline_show(struct device *dev, struct device_attribute *attr,
 		dasd_put_device(device);
 		goto out;
 	} else {
-		len = snprintf(buf, PAGE_SIZE, "%s\n",
-			       device->discipline->name);
+		len = sysfs_emit(buf, "%s\n",
+				 device->discipline->name);
 		dasd_put_device(device);
 		return len;
 	}
 out:
-	len = snprintf(buf, PAGE_SIZE, "none\n");
+	len = sysfs_emit(buf, "none\n");
 	return len;
 }
 
@@ -1056,30 +1056,30 @@ dasd_device_status_show(struct device *dev, struct device_attribute *attr,
 	if (!IS_ERR(device)) {
 		switch (device->state) {
 		case DASD_STATE_NEW:
-			len = snprintf(buf, PAGE_SIZE, "new\n");
+			len = sysfs_emit(buf, "new\n");
 			break;
 		case DASD_STATE_KNOWN:
-			len = snprintf(buf, PAGE_SIZE, "detected\n");
+			len = sysfs_emit(buf, "detected\n");
 			break;
 		case DASD_STATE_BASIC:
-			len = snprintf(buf, PAGE_SIZE, "basic\n");
+			len = sysfs_emit(buf, "basic\n");
 			break;
 		case DASD_STATE_UNFMT:
-			len = snprintf(buf, PAGE_SIZE, "unformatted\n");
+			len = sysfs_emit(buf, "unformatted\n");
 			break;
 		case DASD_STATE_READY:
-			len = snprintf(buf, PAGE_SIZE, "ready\n");
+			len = sysfs_emit(buf, "ready\n");
 			break;
 		case DASD_STATE_ONLINE:
-			len = snprintf(buf, PAGE_SIZE, "online\n");
+			len = sysfs_emit(buf, "online\n");
 			break;
 		default:
-			len = snprintf(buf, PAGE_SIZE, "no stat\n");
+			len = sysfs_emit(buf, "no stat\n");
 			break;
 		}
 		dasd_put_device(device);
 	} else
-		len = snprintf(buf, PAGE_SIZE, "unknown\n");
+		len = sysfs_emit(buf, "unknown\n");
 	return len;
 }
 
@@ -1120,7 +1120,7 @@ static ssize_t dasd_vendor_show(struct device *dev,
 	device = dasd_device_from_cdev(to_ccwdev(dev));
 	vendor = "";
 	if (IS_ERR(device))
-		return snprintf(buf, PAGE_SIZE, "%s\n", vendor);
+		return sysfs_emit(buf, "%s\n", vendor);
 
 	if (device->discipline && device->discipline->get_uid &&
 	    !device->discipline->get_uid(device, &uid))
@@ -1128,7 +1128,7 @@ static ssize_t dasd_vendor_show(struct device *dev,
 
 	dasd_put_device(device);
 
-	return snprintf(buf, PAGE_SIZE, "%s\n", vendor);
+	return sysfs_emit(buf, "%s\n", vendor);
 }
 
 static DEVICE_ATTR(vendor, 0444, dasd_vendor_show, NULL);
@@ -1148,7 +1148,7 @@ dasd_uid_show(struct device *dev, struct device_attribute *attr, char *buf)
 	device = dasd_device_from_cdev(to_ccwdev(dev));
 	uid_string[0] = 0;
 	if (IS_ERR(device))
-		return snprintf(buf, PAGE_SIZE, "%s\n", uid_string);
+		return sysfs_emit(buf, "%s\n", uid_string);
 
 	if (device->discipline && device->discipline->get_uid &&
 	    !device->discipline->get_uid(device, &uid)) {
@@ -1183,7 +1183,7 @@ dasd_uid_show(struct device *dev, struct device_attribute *attr, char *buf)
 	}
 	dasd_put_device(device);
 
-	return snprintf(buf, PAGE_SIZE, "%s\n", uid_string);
+	return sysfs_emit(buf, "%s\n", uid_string);
 }
 static DEVICE_ATTR(uid, 0444, dasd_uid_show, NULL);
 
@@ -1201,7 +1201,7 @@ dasd_eer_show(struct device *dev, struct device_attribute *attr, char *buf)
 		eer_flag = dasd_eer_enabled(devmap->device);
 	else
 		eer_flag = 0;
-	return snprintf(buf, PAGE_SIZE, eer_flag ? "1\n" : "0\n");
+	return sysfs_emit(buf, eer_flag ? "1\n" : "0\n");
 }
 
 static ssize_t
@@ -1243,7 +1243,7 @@ dasd_expires_show(struct device *dev, struct device_attribute *attr, char *buf)
 	device = dasd_device_from_cdev(to_ccwdev(dev));
 	if (IS_ERR(device))
 		return -ENODEV;
-	len = snprintf(buf, PAGE_SIZE, "%lu\n", device->default_expires);
+	len = sysfs_emit(buf, "%lu\n", device->default_expires);
 	dasd_put_device(device);
 	return len;
 }
@@ -1283,7 +1283,7 @@ dasd_retries_show(struct device *dev, struct device_attribute *attr, char *buf)
 	device = dasd_device_from_cdev(to_ccwdev(dev));
 	if (IS_ERR(device))
 		return -ENODEV;
-	len = snprintf(buf, PAGE_SIZE, "%lu\n", device->default_retries);
+	len = sysfs_emit(buf, "%lu\n", device->default_retries);
 	dasd_put_device(device);
 	return len;
 }
@@ -1324,7 +1324,7 @@ dasd_timeout_show(struct device *dev, struct device_attribute *attr,
 	device = dasd_device_from_cdev(to_ccwdev(dev));
 	if (IS_ERR(device))
 		return -ENODEV;
-	len = snprintf(buf, PAGE_SIZE, "%lu\n", device->blk_timeout);
+	len = sysfs_emit(buf, "%lu\n", device->blk_timeout);
 	dasd_put_device(device);
 	return len;
 }
@@ -1398,11 +1398,11 @@ static ssize_t dasd_hpf_show(struct device *dev, struct device_attribute *attr,
 		return -ENODEV;
 	if (!device->discipline || !device->discipline->hpf_enabled) {
 		dasd_put_device(device);
-		return snprintf(buf, PAGE_SIZE, "%d\n", dasd_nofcx);
+		return sysfs_emit(buf, "%d\n", dasd_nofcx);
 	}
 	hpf = device->discipline->hpf_enabled(device);
 	dasd_put_device(device);
-	return snprintf(buf, PAGE_SIZE, "%d\n", hpf);
+	return sysfs_emit(buf, "%d\n", hpf);
 }
 
 static DEVICE_ATTR(hpf, 0444, dasd_hpf_show, NULL);
@@ -1416,13 +1416,13 @@ static ssize_t dasd_reservation_policy_show(struct device *dev,
 
 	devmap = dasd_find_busid(dev_name(dev));
 	if (IS_ERR(devmap)) {
-		rc = snprintf(buf, PAGE_SIZE, "ignore\n");
+		rc = sysfs_emit(buf, "ignore\n");
 	} else {
 		spin_lock(&dasd_devmap_lock);
 		if (devmap->features & DASD_FEATURE_FAILONSLCK)
-			rc = snprintf(buf, PAGE_SIZE, "fail\n");
+			rc = sysfs_emit(buf, "fail\n");
 		else
-			rc = snprintf(buf, PAGE_SIZE, "ignore\n");
+			rc = sysfs_emit(buf, "ignore\n");
 		spin_unlock(&dasd_devmap_lock);
 	}
 	return rc;
@@ -1457,14 +1457,14 @@ static ssize_t dasd_reservation_state_show(struct device *dev,
 
 	device = dasd_device_from_cdev(to_ccwdev(dev));
 	if (IS_ERR(device))
-		return snprintf(buf, PAGE_SIZE, "none\n");
+		return sysfs_emit(buf, "none\n");
 
 	if (test_bit(DASD_FLAG_IS_RESERVED, &device->flags))
-		rc = snprintf(buf, PAGE_SIZE, "reserved\n");
+		rc = sysfs_emit(buf, "reserved\n");
 	else if (test_bit(DASD_FLAG_LOCK_STOLEN, &device->flags))
-		rc = snprintf(buf, PAGE_SIZE, "lost\n");
+		rc = sysfs_emit(buf, "lost\n");
 	else
-		rc = snprintf(buf, PAGE_SIZE, "none\n");
+		rc = sysfs_emit(buf, "none\n");
 	dasd_put_device(device);
 	return rc;
 }
@@ -1531,7 +1531,7 @@ dasd_path_threshold_show(struct device *dev,
 	device = dasd_device_from_cdev(to_ccwdev(dev));
 	if (IS_ERR(device))
 		return -ENODEV;
-	len = snprintf(buf, PAGE_SIZE, "%lu\n", device->path_thrhld);
+	len = sysfs_emit(buf, "%lu\n", device->path_thrhld);
 	dasd_put_device(device);
 	return len;
 }
@@ -1578,7 +1578,7 @@ dasd_path_autodisable_show(struct device *dev,
 	else
 		flag = (DASD_FEATURE_DEFAULT &
 			DASD_FEATURE_PATH_AUTODISABLE) != 0;
-	return snprintf(buf, PAGE_SIZE, flag ? "1\n" : "0\n");
+	return sysfs_emit(buf, flag ? "1\n" : "0\n");
 }
 
 static ssize_t
@@ -1616,7 +1616,7 @@ dasd_path_interval_show(struct device *dev,
 	device = dasd_device_from_cdev(to_ccwdev(dev));
 	if (IS_ERR(device))
 		return -ENODEV;
-	len = snprintf(buf, PAGE_SIZE, "%lu\n", device->path_interval);
+	len = sysfs_emit(buf, "%lu\n", device->path_interval);
 	dasd_put_device(device);
 	return len;
 }
@@ -1662,9 +1662,9 @@ dasd_device_fcs_show(struct device *dev, struct device_attribute *attr,
 		return -ENODEV;
 	fc_sec = dasd_path_get_fcs_device(device);
 	if (fc_sec == -EINVAL)
-		rc = snprintf(buf, PAGE_SIZE, "Inconsistent\n");
+		rc = sysfs_emit(buf, "Inconsistent\n");
 	else
-		rc = snprintf(buf, PAGE_SIZE, "%s\n", dasd_path_get_fcs_str(fc_sec));
+		rc = sysfs_emit(buf, "%s\n", dasd_path_get_fcs_str(fc_sec));
 	dasd_put_device(device);
 
 	return rc;
@@ -1677,7 +1677,7 @@ dasd_path_fcs_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf)
 	struct dasd_path *path = to_dasd_path(kobj);
 	unsigned int fc_sec = path->fc_security;
 
-	return snprintf(buf, PAGE_SIZE, "%s\n", dasd_path_get_fcs_str(fc_sec));
+	return sysfs_emit(buf, "%s\n", dasd_path_get_fcs_str(fc_sec));
 }
 
 static struct kobj_attribute path_fcs_attribute =
@@ -1698,7 +1698,7 @@ static ssize_t dasd_##_name##_show(struct device *dev,			\
 		val = _func(device);					\
 	dasd_put_device(device);					\
 									\
-	return snprintf(buf, PAGE_SIZE, "%d\n", val);			\
+	return sysfs_emit(buf, "%d\n", val);			\
 }									\
 static DEVICE_ATTR(_name, 0444, dasd_##_name##_show, NULL);		\
 
diff --git a/drivers/s390/char/raw3270.c b/drivers/s390/char/raw3270.c
index 646ec796bb83..dfde0d941c3c 100644
--- a/drivers/s390/char/raw3270.c
+++ b/drivers/s390/char/raw3270.c
@@ -1047,24 +1047,24 @@ raw3270_probe (struct ccw_device *cdev)
 static ssize_t
 raw3270_model_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
-	return snprintf(buf, PAGE_SIZE, "%i\n",
-			((struct raw3270 *) dev_get_drvdata(dev))->model);
+	return sysfs_emit(buf, "%i\n",
+			  ((struct raw3270 *)dev_get_drvdata(dev))->model);
 }
 static DEVICE_ATTR(model, 0444, raw3270_model_show, NULL);
 
 static ssize_t
 raw3270_rows_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
-	return snprintf(buf, PAGE_SIZE, "%i\n",
-			((struct raw3270 *) dev_get_drvdata(dev))->rows);
+	return sysfs_emit(buf, "%i\n",
+			  ((struct raw3270 *)dev_get_drvdata(dev))->rows);
 }
 static DEVICE_ATTR(rows, 0444, raw3270_rows_show, NULL);
 
 static ssize_t
 raw3270_columns_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
-	return snprintf(buf, PAGE_SIZE, "%i\n",
-			((struct raw3270 *) dev_get_drvdata(dev))->cols);
+	return sysfs_emit(buf, "%i\n",
+			  ((struct raw3270 *)dev_get_drvdata(dev))->cols);
 }
 static DEVICE_ATTR(columns, 0444, raw3270_columns_show, NULL);
 
diff --git a/drivers/s390/char/tape_std.c b/drivers/s390/char/tape_std.c
index 1f5fab617b67..f7e75d9fedf6 100644
--- a/drivers/s390/char/tape_std.c
+++ b/drivers/s390/char/tape_std.c
@@ -53,7 +53,6 @@ int
 tape_std_assign(struct tape_device *device)
 {
 	int                  rc;
-	struct timer_list    timeout;
 	struct tape_request *request;
 
 	request = tape_alloc_request(2, 11);
@@ -70,7 +69,7 @@ tape_std_assign(struct tape_device *device)
 	 * So we set up a timeout for this call.
 	 */
 	timer_setup(&request->timer, tape_std_assign_timeout, 0);
-	mod_timer(&timeout, jiffies + 2 * HZ);
+	mod_timer(&request->timer, jiffies + msecs_to_jiffies(2000));
 
 	rc = tape_do_io_interruptible(device, request);
 
diff --git a/drivers/s390/cio/chp.c b/drivers/s390/cio/chp.c
index 1097e76982a5..5440f285f349 100644
--- a/drivers/s390/cio/chp.c
+++ b/drivers/s390/cio/chp.c
@@ -285,7 +285,7 @@ static ssize_t chp_configure_show(struct device *dev,
 	if (status < 0)
 		return status;
 
-	return snprintf(buf, PAGE_SIZE, "%d\n", status);
+	return sysfs_emit(buf, "%d\n", status);
 }
 
 static int cfg_wait_idle(void);
diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c
index 2bc55ccf3f23..ce9e7517430f 100644
--- a/drivers/s390/cio/css.c
+++ b/drivers/s390/cio/css.c
@@ -437,8 +437,8 @@ static ssize_t dev_busid_show(struct device *dev,
 	struct subchannel *sch = to_subchannel(dev);
 	struct pmcw *pmcw = &sch->schib.pmcw;
 
-	if ((pmcw->st == SUBCHANNEL_TYPE_IO ||
-	     pmcw->st == SUBCHANNEL_TYPE_MSG) && pmcw->dnv)
+	if ((pmcw->st == SUBCHANNEL_TYPE_IO && pmcw->dnv) ||
+	    (pmcw->st == SUBCHANNEL_TYPE_MSG && pmcw->w))
 		return sysfs_emit(buf, "0.%x.%04x\n", sch->schid.ssid,
 				  pmcw->dev);
 	else
diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c
index b940e0268f96..e83453bea2ae 100644
--- a/drivers/scsi/lpfc/lpfc_els.c
+++ b/drivers/scsi/lpfc/lpfc_els.c
@@ -5095,14 +5095,9 @@ lpfc_cmpl_els_logo_acc(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 		/* NPort Recovery mode or node is just allocated */
 		if (!lpfc_nlp_not_used(ndlp)) {
 			/* A LOGO is completing and the node is in NPR state.
-			 * If this a fabric node that cleared its transport
-			 * registration, release the rpi.
+			 * Just unregister the RPI because the node is still
+			 * required.
 			 */
-			spin_lock_irq(&ndlp->lock);
-			ndlp->nlp_flag &= ~NLP_NPR_2B_DISC;
-			if (phba->sli_rev == LPFC_SLI_REV4)
-				ndlp->nlp_flag |= NLP_RELEASE_RPI;
-			spin_unlock_irq(&ndlp->lock);
 			lpfc_unreg_rpi(vport, ndlp);
 		} else {
 			/* Indicate the node has already released, should
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index 27eb652b564f..81dab9b82f79 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -639,8 +639,8 @@ static void _base_sync_drv_fw_timestamp(struct MPT3SAS_ADAPTER *ioc)
 	mpi_request->IOCParameter = MPI26_SET_IOC_PARAMETER_SYNC_TIMESTAMP;
 	current_time = ktime_get_real();
 	TimeStamp = ktime_to_ms(current_time);
-	mpi_request->Reserved7 = cpu_to_le32(TimeStamp & 0xFFFFFFFF);
-	mpi_request->IOCParameterValue = cpu_to_le32(TimeStamp >> 32);
+	mpi_request->Reserved7 = cpu_to_le32(TimeStamp >> 32);
+	mpi_request->IOCParameterValue = cpu_to_le32(TimeStamp & 0xFFFFFFFF);
 	init_completion(&ioc->scsih_cmds.done);
 	ioc->put_smid_default(ioc, smid);
 	dinitprintk(ioc, ioc_info(ioc,
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.h b/drivers/scsi/mpt3sas/mpt3sas_base.h
index db6a759de1e9..a0af986633d2 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.h
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.h
@@ -142,6 +142,8 @@
 
 #define MPT_MAX_CALLBACKS		32
 
+#define MPT_MAX_HBA_NUM_PHYS		32
+
 #define INTERNAL_CMDS_COUNT		10	/* reserved cmds */
 /* reserved for issuing internally framed scsi io cmds */
 #define INTERNAL_SCSIIO_CMDS_COUNT	3
@@ -798,6 +800,7 @@ struct _sas_phy {
  * @enclosure_handle: handle for this a member of an enclosure
  * @device_info: bitwise defining capabilities of this sas_host/expander
  * @responding: used in _scsih_expander_device_mark_responding
+ * @nr_phys_allocated: Allocated memory for this many count phys
  * @phy: a list of phys that make up this sas_host/expander
  * @sas_port_list: list of ports attached to this sas_host/expander
  * @port: hba port entry containing node's port number info
@@ -813,6 +816,7 @@ struct _sas_node {
 	u16	enclosure_handle;
 	u64	enclosure_logical_id;
 	u8	responding;
+	u8	nr_phys_allocated;
 	struct hba_port *port;
 	struct	_sas_phy *phy;
 	struct list_head sas_port_list;
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index cee7170beae8..00792767c620 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -3869,7 +3869,7 @@ _scsih_ublock_io_device(struct MPT3SAS_ADAPTER *ioc,
 
 	shost_for_each_device(sdev, ioc->shost) {
 		sas_device_priv_data = sdev->hostdata;
-		if (!sas_device_priv_data)
+		if (!sas_device_priv_data || !sas_device_priv_data->sas_target)
 			continue;
 		if (sas_device_priv_data->sas_target->sas_address
 		    != sas_address)
@@ -6406,11 +6406,26 @@ _scsih_sas_port_refresh(struct MPT3SAS_ADAPTER *ioc)
 	int i, j, count = 0, lcount = 0;
 	int ret;
 	u64 sas_addr;
+	u8 num_phys;
 
 	drsprintk(ioc, ioc_info(ioc,
 	    "updating ports for sas_host(0x%016llx)\n",
 	    (unsigned long long)ioc->sas_hba.sas_address));
 
+	mpt3sas_config_get_number_hba_phys(ioc, &num_phys);
+	if (!num_phys) {
+		ioc_err(ioc, "failure at %s:%d/%s()!\n",
+		    __FILE__, __LINE__, __func__);
+		return;
+	}
+
+	if (num_phys > ioc->sas_hba.nr_phys_allocated) {
+		ioc_err(ioc, "failure at %s:%d/%s()!\n",
+		   __FILE__, __LINE__, __func__);
+		return;
+	}
+	ioc->sas_hba.num_phys = num_phys;
+
 	port_table = kcalloc(ioc->sas_hba.num_phys,
 	    sizeof(struct hba_port), GFP_KERNEL);
 	if (!port_table)
@@ -6611,6 +6626,30 @@ _scsih_sas_host_refresh(struct MPT3SAS_ADAPTER *ioc)
 			ioc->sas_hba.phy[i].hba_vphy = 1;
 		}
 
+		/*
+		 * Add new HBA phys to STL if these new phys got added as part
+		 * of HBA Firmware upgrade/downgrade operation.
+		 */
+		if (!ioc->sas_hba.phy[i].phy) {
+			if ((mpt3sas_config_get_phy_pg0(ioc, &mpi_reply,
+							&phy_pg0, i))) {
+				ioc_err(ioc, "failure at %s:%d/%s()!\n",
+					__FILE__, __LINE__, __func__);
+				continue;
+			}
+			ioc_status = le16_to_cpu(mpi_reply.IOCStatus) &
+				MPI2_IOCSTATUS_MASK;
+			if (ioc_status != MPI2_IOCSTATUS_SUCCESS) {
+				ioc_err(ioc, "failure at %s:%d/%s()!\n",
+					__FILE__, __LINE__, __func__);
+				continue;
+			}
+			ioc->sas_hba.phy[i].phy_id = i;
+			mpt3sas_transport_add_host_phy(ioc,
+				&ioc->sas_hba.phy[i], phy_pg0,
+				ioc->sas_hba.parent_dev);
+			continue;
+		}
 		ioc->sas_hba.phy[i].handle = ioc->sas_hba.handle;
 		attached_handle = le16_to_cpu(sas_iounit_pg0->PhyData[i].
 		    AttachedDevHandle);
@@ -6622,6 +6661,19 @@ _scsih_sas_host_refresh(struct MPT3SAS_ADAPTER *ioc)
 		    attached_handle, i, link_rate,
 		    ioc->sas_hba.phy[i].port);
 	}
+	/*
+	 * Clear the phy details if this phy got disabled as part of
+	 * HBA Firmware upgrade/downgrade operation.
+	 */
+	for (i = ioc->sas_hba.num_phys;
+	     i < ioc->sas_hba.nr_phys_allocated; i++) {
+		if (ioc->sas_hba.phy[i].phy &&
+		    ioc->sas_hba.phy[i].phy->negotiated_linkrate >=
+		    SAS_LINK_RATE_1_5_GBPS)
+			mpt3sas_transport_update_links(ioc,
+				ioc->sas_hba.sas_address, 0, i,
+				MPI2_SAS_NEG_LINK_RATE_PHY_DISABLED, NULL);
+	}
  out:
 	kfree(sas_iounit_pg0);
 }
@@ -6654,7 +6706,10 @@ _scsih_sas_host_add(struct MPT3SAS_ADAPTER *ioc)
 			__FILE__, __LINE__, __func__);
 		return;
 	}
-	ioc->sas_hba.phy = kcalloc(num_phys,
+
+	ioc->sas_hba.nr_phys_allocated = max_t(u8,
+	    MPT_MAX_HBA_NUM_PHYS, num_phys);
+	ioc->sas_hba.phy = kcalloc(ioc->sas_hba.nr_phys_allocated,
 	    sizeof(struct _sas_phy), GFP_KERNEL);
 	if (!ioc->sas_hba.phy) {
 		ioc_err(ioc, "failure at %s:%d/%s()!\n",
diff --git a/drivers/scsi/pm8001/pm8001_init.c b/drivers/scsi/pm8001/pm8001_init.c
index bed8cc125544..fbfeb0b046dd 100644
--- a/drivers/scsi/pm8001/pm8001_init.c
+++ b/drivers/scsi/pm8001/pm8001_init.c
@@ -282,12 +282,12 @@ static int pm8001_alloc(struct pm8001_hba_info *pm8001_ha,
 	if (rc) {
 		pm8001_dbg(pm8001_ha, FAIL,
 			   "pm8001_setup_irq failed [ret: %d]\n", rc);
-		goto err_out_shost;
+		goto err_out;
 	}
 	/* Request Interrupt */
 	rc = pm8001_request_irq(pm8001_ha);
 	if (rc)
-		goto err_out_shost;
+		goto err_out;
 
 	count = pm8001_ha->max_q_num;
 	/* Queues are chosen based on the number of cores/msix availability */
@@ -423,8 +423,6 @@ static int pm8001_alloc(struct pm8001_hba_info *pm8001_ha,
 	pm8001_tag_init(pm8001_ha);
 	return 0;
 
-err_out_shost:
-	scsi_remove_host(pm8001_ha->shost);
 err_out_nodev:
 	for (i = 0; i < pm8001_ha->max_memcnt; i++) {
 		if (pm8001_ha->memoryMap.region[i].virt_ptr != NULL) {
diff --git a/drivers/scsi/pm8001/pm80xx_hwi.c b/drivers/scsi/pm8001/pm80xx_hwi.c
index b9f6d83ff380..2101fc5761c3 100644
--- a/drivers/scsi/pm8001/pm80xx_hwi.c
+++ b/drivers/scsi/pm8001/pm80xx_hwi.c
@@ -3053,7 +3053,6 @@ mpi_smp_completion(struct pm8001_hba_info *pm8001_ha, void *piomb)
 	struct smp_completion_resp *psmpPayload;
 	struct task_status_struct *ts;
 	struct pm8001_device *pm8001_dev;
-	char *pdma_respaddr = NULL;
 
 	psmpPayload = (struct smp_completion_resp *)(piomb + 4);
 	status = le32_to_cpu(psmpPayload->status);
@@ -3080,19 +3079,23 @@ mpi_smp_completion(struct pm8001_hba_info *pm8001_ha, void *piomb)
 		if (pm8001_dev)
 			atomic_dec(&pm8001_dev->running_req);
 		if (pm8001_ha->smp_exp_mode == SMP_DIRECT) {
+			struct scatterlist *sg_resp = &t->smp_task.smp_resp;
+			u8 *payload;
+			void *to;
+
 			pm8001_dbg(pm8001_ha, IO,
 				   "DIRECT RESPONSE Length:%d\n",
 				   param);
-			pdma_respaddr = (char *)(phys_to_virt(cpu_to_le64
-						((u64)sg_dma_address
-						(&t->smp_task.smp_resp))));
+			to = kmap_atomic(sg_page(sg_resp));
+			payload = to + sg_resp->offset;
 			for (i = 0; i < param; i++) {
-				*(pdma_respaddr+i) = psmpPayload->_r_a[i];
+				*(payload + i) = psmpPayload->_r_a[i];
 				pm8001_dbg(pm8001_ha, IO,
 					   "SMP Byte%d DMA data 0x%x psmp 0x%x\n",
-					   i, *(pdma_respaddr + i),
+					   i, *(payload + i),
 					   psmpPayload->_r_a[i]);
 			}
+			kunmap_atomic(to);
 		}
 		break;
 	case IO_ABORTED:
@@ -4236,14 +4239,14 @@ static int pm80xx_chip_smp_req(struct pm8001_hba_info *pm8001_ha,
 	struct sas_task *task = ccb->task;
 	struct domain_device *dev = task->dev;
 	struct pm8001_device *pm8001_dev = dev->lldd_dev;
-	struct scatterlist *sg_req, *sg_resp;
+	struct scatterlist *sg_req, *sg_resp, *smp_req;
 	u32 req_len, resp_len;
 	struct smp_req smp_cmd;
 	u32 opc;
 	struct inbound_queue_table *circularQ;
-	char *preq_dma_addr = NULL;
-	__le64 tmp_addr;
 	u32 i, length;
+	u8 *payload;
+	u8 *to;
 
 	memset(&smp_cmd, 0, sizeof(smp_cmd));
 	/*
@@ -4280,8 +4283,9 @@ static int pm80xx_chip_smp_req(struct pm8001_hba_info *pm8001_ha,
 		pm8001_ha->smp_exp_mode = SMP_INDIRECT;
 
 
-	tmp_addr = cpu_to_le64((u64)sg_dma_address(&task->smp_task.smp_req));
-	preq_dma_addr = (char *)phys_to_virt(tmp_addr);
+	smp_req = &task->smp_task.smp_req;
+	to = kmap_atomic(sg_page(smp_req));
+	payload = to + smp_req->offset;
 
 	/* INDIRECT MODE command settings. Use DMA */
 	if (pm8001_ha->smp_exp_mode == SMP_INDIRECT) {
@@ -4289,7 +4293,7 @@ static int pm80xx_chip_smp_req(struct pm8001_hba_info *pm8001_ha,
 		/* for SPCv indirect mode. Place the top 4 bytes of
 		 * SMP Request header here. */
 		for (i = 0; i < 4; i++)
-			smp_cmd.smp_req16[i] = *(preq_dma_addr + i);
+			smp_cmd.smp_req16[i] = *(payload + i);
 		/* exclude top 4 bytes for SMP req header */
 		smp_cmd.long_smp_req.long_req_addr =
 			cpu_to_le64((u64)sg_dma_address
@@ -4320,20 +4324,20 @@ static int pm80xx_chip_smp_req(struct pm8001_hba_info *pm8001_ha,
 		pm8001_dbg(pm8001_ha, IO, "SMP REQUEST DIRECT MODE\n");
 		for (i = 0; i < length; i++)
 			if (i < 16) {
-				smp_cmd.smp_req16[i] = *(preq_dma_addr+i);
+				smp_cmd.smp_req16[i] = *(payload + i);
 				pm8001_dbg(pm8001_ha, IO,
 					   "Byte[%d]:%x (DMA data:%x)\n",
 					   i, smp_cmd.smp_req16[i],
-					   *(preq_dma_addr));
+					   *(payload));
 			} else {
-				smp_cmd.smp_req[i] = *(preq_dma_addr+i);
+				smp_cmd.smp_req[i] = *(payload + i);
 				pm8001_dbg(pm8001_ha, IO,
 					   "Byte[%d]:%x (DMA data:%x)\n",
 					   i, smp_cmd.smp_req[i],
-					   *(preq_dma_addr));
+					   *(payload));
 			}
 	}
-
+	kunmap_atomic(to);
 	build_smp_cmd(pm8001_dev->device_id, smp_cmd.tag,
 				&smp_cmd, pm8001_ha->smp_exp_mode, length);
 	rc = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &smp_cmd,
diff --git a/drivers/scsi/qedi/qedi_fw.c b/drivers/scsi/qedi/qedi_fw.c
index 84a4204a2cb4..5916ed7662d5 100644
--- a/drivers/scsi/qedi/qedi_fw.c
+++ b/drivers/scsi/qedi/qedi_fw.c
@@ -732,7 +732,6 @@ static void qedi_process_cmd_cleanup_resp(struct qedi_ctx *qedi,
 {
 	struct qedi_work_map *work, *work_tmp;
 	u32 proto_itt = cqe->itid;
-	itt_t protoitt = 0;
 	int found = 0;
 	struct qedi_cmd *qedi_cmd = NULL;
 	u32 iscsi_cid;
@@ -812,16 +811,12 @@ unlock:
 	return;
 
 check_cleanup_reqs:
-	if (qedi_conn->cmd_cleanup_req > 0) {
-		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_TID,
+	if (atomic_inc_return(&qedi_conn->cmd_cleanup_cmpl) ==
+	    qedi_conn->cmd_cleanup_req) {
+		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_SCSI_TM,
 			  "Freeing tid=0x%x for cid=0x%x\n",
 			  cqe->itid, qedi_conn->iscsi_conn_id);
-		qedi_conn->cmd_cleanup_cmpl++;
 		wake_up(&qedi_conn->wait_queue);
-	} else {
-		QEDI_ERR(&qedi->dbg_ctx,
-			 "Delayed or untracked cleanup response, itt=0x%x, tid=0x%x, cid=0x%x\n",
-			 protoitt, cqe->itid, qedi_conn->iscsi_conn_id);
 	}
 }
 
@@ -1163,7 +1158,7 @@ int qedi_cleanup_all_io(struct qedi_ctx *qedi, struct qedi_conn *qedi_conn,
 	}
 
 	qedi_conn->cmd_cleanup_req = 0;
-	qedi_conn->cmd_cleanup_cmpl = 0;
+	atomic_set(&qedi_conn->cmd_cleanup_cmpl, 0);
 
 	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_SCSI_TM,
 		  "active_cmd_count=%d, cid=0x%x, in_recovery=%d, lun_reset=%d\n",
@@ -1215,16 +1210,15 @@ int qedi_cleanup_all_io(struct qedi_ctx *qedi, struct qedi_conn *qedi_conn,
 		  qedi_conn->iscsi_conn_id);
 
 	rval  = wait_event_interruptible_timeout(qedi_conn->wait_queue,
-						 ((qedi_conn->cmd_cleanup_req ==
-						 qedi_conn->cmd_cleanup_cmpl) ||
-						 test_bit(QEDI_IN_RECOVERY,
-							  &qedi->flags)),
-						 5 * HZ);
+				(qedi_conn->cmd_cleanup_req ==
+				 atomic_read(&qedi_conn->cmd_cleanup_cmpl)) ||
+				test_bit(QEDI_IN_RECOVERY, &qedi->flags),
+				5 * HZ);
 	if (rval) {
 		QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_SCSI_TM,
 			  "i/o cmd_cleanup_req=%d, equal to cmd_cleanup_cmpl=%d, cid=0x%x\n",
 			  qedi_conn->cmd_cleanup_req,
-			  qedi_conn->cmd_cleanup_cmpl,
+			  atomic_read(&qedi_conn->cmd_cleanup_cmpl),
 			  qedi_conn->iscsi_conn_id);
 
 		return 0;
@@ -1233,7 +1227,7 @@ int qedi_cleanup_all_io(struct qedi_ctx *qedi, struct qedi_conn *qedi_conn,
 	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_SCSI_TM,
 		  "i/o cmd_cleanup_req=%d, not equal to cmd_cleanup_cmpl=%d, cid=0x%x\n",
 		  qedi_conn->cmd_cleanup_req,
-		  qedi_conn->cmd_cleanup_cmpl,
+		  atomic_read(&qedi_conn->cmd_cleanup_cmpl),
 		  qedi_conn->iscsi_conn_id);
 
 	iscsi_host_for_each_session(qedi->shost,
@@ -1242,11 +1236,10 @@ int qedi_cleanup_all_io(struct qedi_ctx *qedi, struct qedi_conn *qedi_conn,
 
 	/* Enable IOs for all other sessions except current.*/
 	if (!wait_event_interruptible_timeout(qedi_conn->wait_queue,
-					      (qedi_conn->cmd_cleanup_req ==
-					       qedi_conn->cmd_cleanup_cmpl) ||
-					       test_bit(QEDI_IN_RECOVERY,
-							&qedi->flags),
-					      5 * HZ)) {
+				(qedi_conn->cmd_cleanup_req ==
+				 atomic_read(&qedi_conn->cmd_cleanup_cmpl)) ||
+				test_bit(QEDI_IN_RECOVERY, &qedi->flags),
+				5 * HZ)) {
 		iscsi_host_for_each_session(qedi->shost,
 					    qedi_mark_device_available);
 		return -1;
@@ -1266,7 +1259,7 @@ void qedi_clearsq(struct qedi_ctx *qedi, struct qedi_conn *qedi_conn,
 
 	qedi_ep = qedi_conn->ep;
 	qedi_conn->cmd_cleanup_req = 0;
-	qedi_conn->cmd_cleanup_cmpl = 0;
+	atomic_set(&qedi_conn->cmd_cleanup_cmpl, 0);
 
 	if (!qedi_ep) {
 		QEDI_WARN(&qedi->dbg_ctx,
diff --git a/drivers/scsi/qedi/qedi_iscsi.c b/drivers/scsi/qedi/qedi_iscsi.c
index 88aa7d8b11c9..282ecb4e39bb 100644
--- a/drivers/scsi/qedi/qedi_iscsi.c
+++ b/drivers/scsi/qedi/qedi_iscsi.c
@@ -412,7 +412,7 @@ static int qedi_conn_bind(struct iscsi_cls_session *cls_session,
 	qedi_conn->iscsi_conn_id = qedi_ep->iscsi_cid;
 	qedi_conn->fw_cid = qedi_ep->fw_cid;
 	qedi_conn->cmd_cleanup_req = 0;
-	qedi_conn->cmd_cleanup_cmpl = 0;
+	atomic_set(&qedi_conn->cmd_cleanup_cmpl, 0);
 
 	if (qedi_bind_conn_to_iscsi_cid(qedi, qedi_conn)) {
 		rc = -EINVAL;
diff --git a/drivers/scsi/qedi/qedi_iscsi.h b/drivers/scsi/qedi/qedi_iscsi.h
index a282860da0aa..9b9f2e44fdde 100644
--- a/drivers/scsi/qedi/qedi_iscsi.h
+++ b/drivers/scsi/qedi/qedi_iscsi.h
@@ -155,7 +155,7 @@ struct qedi_conn {
 	spinlock_t list_lock;		/* internal conn lock */
 	u32 active_cmd_count;
 	u32 cmd_cleanup_req;
-	u32 cmd_cleanup_cmpl;
+	atomic_t cmd_cleanup_cmpl;
 
 	u32 iscsi_conn_id;
 	int itt;
diff --git a/drivers/scsi/qla2xxx/qla_dbg.c b/drivers/scsi/qla2xxx/qla_dbg.c
index 25549a8a2d72..7cf1f78cbaee 100644
--- a/drivers/scsi/qla2xxx/qla_dbg.c
+++ b/drivers/scsi/qla2xxx/qla_dbg.c
@@ -2491,6 +2491,9 @@ ql_dbg(uint level, scsi_qla_host_t *vha, uint id, const char *fmt, ...)
 	struct va_format vaf;
 	char pbuf[64];
 
+	if (!ql_mask_match(level) && !trace_ql_dbg_log_enabled())
+		return;
+
 	va_start(va, fmt);
 
 	vaf.fmt = fmt;
diff --git a/drivers/scsi/qla2xxx/qla_edif.c b/drivers/scsi/qla2xxx/qla_edif.c
index 2e37b189cb75..53d2b8562027 100644
--- a/drivers/scsi/qla2xxx/qla_edif.c
+++ b/drivers/scsi/qla2xxx/qla_edif.c
@@ -865,7 +865,7 @@ qla_edif_app_getfcinfo(scsi_qla_host_t *vha, struct bsg_job *bsg_job)
 			    "APP request entry - portid=%06x.\n", tdid.b24);
 
 			/* Ran out of space */
-			if (pcnt > app_req.num_ports)
+			if (pcnt >= app_req.num_ports)
 				break;
 
 			if (tdid.b24 != 0 && tdid.b24 != fcport->d_id.b24)
diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c
index 73a353153d33..10d2655ef676 100644
--- a/drivers/scsi/qla2xxx/qla_mbx.c
+++ b/drivers/scsi/qla2xxx/qla_mbx.c
@@ -1695,10 +1695,8 @@ qla2x00_get_adapter_id(scsi_qla_host_t *vha, uint16_t *id, uint8_t *al_pa,
 		mcp->in_mb |= MBX_13|MBX_12|MBX_11|MBX_10;
 	if (IS_FWI2_CAPABLE(vha->hw))
 		mcp->in_mb |= MBX_19|MBX_18|MBX_17|MBX_16;
-	if (IS_QLA27XX(vha->hw) || IS_QLA28XX(vha->hw)) {
-		mcp->in_mb |= MBX_15;
-		mcp->out_mb |= MBX_7|MBX_21|MBX_22|MBX_23;
-	}
+	if (IS_QLA27XX(vha->hw) || IS_QLA28XX(vha->hw))
+		mcp->in_mb |= MBX_15|MBX_21|MBX_22|MBX_23;
 
 	mcp->tov = MBX_TOV_SECONDS;
 	mcp->flags = 0;
diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c
index 1d0278da9041..2104973a35cd 100644
--- a/drivers/scsi/scsi_debug.c
+++ b/drivers/scsi/scsi_debug.c
@@ -1189,7 +1189,7 @@ static int p_fill_from_dev_buffer(struct scsi_cmnd *scp, const void *arr,
 		 __func__, off_dst, scsi_bufflen(scp), act_len,
 		 scsi_get_resid(scp));
 	n = scsi_bufflen(scp) - (off_dst + act_len);
-	scsi_set_resid(scp, min_t(int, scsi_get_resid(scp), n));
+	scsi_set_resid(scp, min_t(u32, scsi_get_resid(scp), n));
 	return 0;
 }
 
@@ -1562,7 +1562,8 @@ static int resp_inquiry(struct scsi_cmnd *scp, struct sdebug_dev_info *devip)
 	unsigned char pq_pdt;
 	unsigned char *arr;
 	unsigned char *cmd = scp->cmnd;
-	int alloc_len, n, ret;
+	u32 alloc_len, n;
+	int ret;
 	bool have_wlun, is_disk, is_zbc, is_disk_zbc;
 
 	alloc_len = get_unaligned_be16(cmd + 3);
@@ -1585,7 +1586,8 @@ static int resp_inquiry(struct scsi_cmnd *scp, struct sdebug_dev_info *devip)
 		kfree(arr);
 		return check_condition_result;
 	} else if (0x1 & cmd[1]) {  /* EVPD bit set */
-		int lu_id_num, port_group_id, target_dev_id, len;
+		int lu_id_num, port_group_id, target_dev_id;
+		u32 len;
 		char lu_id_str[6];
 		int host_no = devip->sdbg_host->shost->host_no;
 		
@@ -1676,9 +1678,9 @@ static int resp_inquiry(struct scsi_cmnd *scp, struct sdebug_dev_info *devip)
 			kfree(arr);
 			return check_condition_result;
 		}
-		len = min(get_unaligned_be16(arr + 2) + 4, alloc_len);
+		len = min_t(u32, get_unaligned_be16(arr + 2) + 4, alloc_len);
 		ret = fill_from_dev_buffer(scp, arr,
-			    min(len, SDEBUG_MAX_INQ_ARR_SZ));
+			    min_t(u32, len, SDEBUG_MAX_INQ_ARR_SZ));
 		kfree(arr);
 		return ret;
 	}
@@ -1714,7 +1716,7 @@ static int resp_inquiry(struct scsi_cmnd *scp, struct sdebug_dev_info *devip)
 	}
 	put_unaligned_be16(0x2100, arr + n);	/* SPL-4 no version claimed */
 	ret = fill_from_dev_buffer(scp, arr,
-			    min_t(int, alloc_len, SDEBUG_LONG_INQ_SZ));
+			    min_t(u32, alloc_len, SDEBUG_LONG_INQ_SZ));
 	kfree(arr);
 	return ret;
 }
@@ -1729,8 +1731,8 @@ static int resp_requests(struct scsi_cmnd *scp,
 	unsigned char *cmd = scp->cmnd;
 	unsigned char arr[SCSI_SENSE_BUFFERSIZE];	/* assume >= 18 bytes */
 	bool dsense = !!(cmd[1] & 1);
-	int alloc_len = cmd[4];
-	int len = 18;
+	u32 alloc_len = cmd[4];
+	u32 len = 18;
 	int stopped_state = atomic_read(&devip->stopped);
 
 	memset(arr, 0, sizeof(arr));
@@ -1774,7 +1776,7 @@ static int resp_requests(struct scsi_cmnd *scp,
 			arr[7] = 0xa;
 		}
 	}
-	return fill_from_dev_buffer(scp, arr, min_t(int, len, alloc_len));
+	return fill_from_dev_buffer(scp, arr, min_t(u32, len, alloc_len));
 }
 
 static int resp_start_stop(struct scsi_cmnd *scp, struct sdebug_dev_info *devip)
@@ -2312,7 +2314,8 @@ static int resp_mode_sense(struct scsi_cmnd *scp,
 {
 	int pcontrol, pcode, subpcode, bd_len;
 	unsigned char dev_spec;
-	int alloc_len, offset, len, target_dev_id;
+	u32 alloc_len, offset, len;
+	int target_dev_id;
 	int target = scp->device->id;
 	unsigned char *ap;
 	unsigned char arr[SDEBUG_MAX_MSENSE_SZ];
@@ -2468,7 +2471,7 @@ static int resp_mode_sense(struct scsi_cmnd *scp,
 		arr[0] = offset - 1;
 	else
 		put_unaligned_be16((offset - 2), arr + 0);
-	return fill_from_dev_buffer(scp, arr, min_t(int, alloc_len, offset));
+	return fill_from_dev_buffer(scp, arr, min_t(u32, alloc_len, offset));
 }
 
 #define SDEBUG_MAX_MSELECT_SZ 512
@@ -2499,11 +2502,11 @@ static int resp_mode_select(struct scsi_cmnd *scp,
 			    __func__, param_len, res);
 	md_len = mselect6 ? (arr[0] + 1) : (get_unaligned_be16(arr + 0) + 2);
 	bd_len = mselect6 ? arr[3] : get_unaligned_be16(arr + 6);
-	if (md_len > 2) {
+	off = bd_len + (mselect6 ? 4 : 8);
+	if (md_len > 2 || off >= res) {
 		mk_sense_invalid_fld(scp, SDEB_IN_DATA, 0, -1);
 		return check_condition_result;
 	}
-	off = bd_len + (mselect6 ? 4 : 8);
 	mpage = arr[off] & 0x3f;
 	ps = !!(arr[off] & 0x80);
 	if (ps) {
@@ -2583,7 +2586,8 @@ static int resp_ie_l_pg(unsigned char *arr)
 static int resp_log_sense(struct scsi_cmnd *scp,
 			  struct sdebug_dev_info *devip)
 {
-	int ppc, sp, pcode, subpcode, alloc_len, len, n;
+	int ppc, sp, pcode, subpcode;
+	u32 alloc_len, len, n;
 	unsigned char arr[SDEBUG_MAX_LSENSE_SZ];
 	unsigned char *cmd = scp->cmnd;
 
@@ -2653,9 +2657,9 @@ static int resp_log_sense(struct scsi_cmnd *scp,
 		mk_sense_invalid_fld(scp, SDEB_IN_CDB, 3, -1);
 		return check_condition_result;
 	}
-	len = min_t(int, get_unaligned_be16(arr + 2) + 4, alloc_len);
+	len = min_t(u32, get_unaligned_be16(arr + 2) + 4, alloc_len);
 	return fill_from_dev_buffer(scp, arr,
-		    min_t(int, len, SDEBUG_MAX_INQ_ARR_SZ));
+		    min_t(u32, len, SDEBUG_MAX_INQ_ARR_SZ));
 }
 
 static inline bool sdebug_dev_is_zoned(struct sdebug_dev_info *devip)
@@ -4338,7 +4342,7 @@ static int resp_report_zones(struct scsi_cmnd *scp,
 	rep_max_zones = min((alloc_len - 64) >> ilog2(RZONES_DESC_HD),
 			    max_zones);
 
-	arr = kcalloc(RZONES_DESC_HD, alloc_len, GFP_ATOMIC);
+	arr = kzalloc(alloc_len, GFP_ATOMIC);
 	if (!arr) {
 		mk_sense_buffer(scp, ILLEGAL_REQUEST, INSUFF_RES_ASC,
 				INSUFF_RES_ASCQ);
@@ -4430,7 +4434,7 @@ static int resp_report_zones(struct scsi_cmnd *scp,
 	put_unaligned_be64(sdebug_capacity - 1, arr + 8);
 
 	rep_len = (unsigned long)desc - (unsigned long)arr;
-	ret = fill_from_dev_buffer(scp, arr, min_t(int, alloc_len, rep_len));
+	ret = fill_from_dev_buffer(scp, arr, min_t(u32, alloc_len, rep_len));
 
 fini:
 	read_unlock(macc_lckp);
@@ -4653,6 +4657,7 @@ static void zbc_rwp_zone(struct sdebug_dev_info *devip,
 			 struct sdeb_zone_state *zsp)
 {
 	enum sdebug_z_cond zc;
+	struct sdeb_store_info *sip = devip2sip(devip, false);
 
 	if (zbc_zone_is_conv(zsp))
 		return;
@@ -4664,6 +4669,10 @@ static void zbc_rwp_zone(struct sdebug_dev_info *devip,
 	if (zsp->z_cond == ZC4_CLOSED)
 		devip->nr_closed--;
 
+	if (zsp->z_wp > zsp->z_start)
+		memset(sip->storep + zsp->z_start * sdebug_sector_size, 0,
+		       (zsp->z_wp - zsp->z_start) * sdebug_sector_size);
+
 	zsp->z_non_seq_resource = false;
 	zsp->z_wp = zsp->z_start;
 	zsp->z_cond = ZC1_EMPTY;
diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c
index 55addd78fde4..d4edce930a4a 100644
--- a/drivers/scsi/scsi_sysfs.c
+++ b/drivers/scsi/scsi_sysfs.c
@@ -792,6 +792,7 @@ store_state_field(struct device *dev, struct device_attribute *attr,
 	int i, ret;
 	struct scsi_device *sdev = to_scsi_device(dev);
 	enum scsi_device_state state = 0;
+	bool rescan_dev = false;
 
 	for (i = 0; i < ARRAY_SIZE(sdev_states); i++) {
 		const int len = strlen(sdev_states[i].name);
@@ -810,20 +811,27 @@ store_state_field(struct device *dev, struct device_attribute *attr,
 	}
 
 	mutex_lock(&sdev->state_mutex);
-	ret = scsi_device_set_state(sdev, state);
-	/*
-	 * If the device state changes to SDEV_RUNNING, we need to
-	 * run the queue to avoid I/O hang, and rescan the device
-	 * to revalidate it. Running the queue first is necessary
-	 * because another thread may be waiting inside
-	 * blk_mq_freeze_queue_wait() and because that call may be
-	 * waiting for pending I/O to finish.
-	 */
-	if (ret == 0 && state == SDEV_RUNNING) {
+	if (sdev->sdev_state == SDEV_RUNNING && state == SDEV_RUNNING) {
+		ret = 0;
+	} else {
+		ret = scsi_device_set_state(sdev, state);
+		if (ret == 0 && state == SDEV_RUNNING)
+			rescan_dev = true;
+	}
+	mutex_unlock(&sdev->state_mutex);
+
+	if (rescan_dev) {
+		/*
+		 * If the device state changes to SDEV_RUNNING, we need to
+		 * run the queue to avoid I/O hang, and rescan the device
+		 * to revalidate it. Running the queue first is necessary
+		 * because another thread may be waiting inside
+		 * blk_mq_freeze_queue_wait() and because that call may be
+		 * waiting for pending I/O to finish.
+		 */
 		blk_mq_run_hw_queues(sdev->request_queue, true);
 		scsi_rescan_device(dev);
 	}
-	mutex_unlock(&sdev->state_mutex);
 
 	return ret == 0 ? count : -EINVAL;
 }
diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c
index 78343d3f9385..554b6f784223 100644
--- a/drivers/scsi/scsi_transport_iscsi.c
+++ b/drivers/scsi/scsi_transport_iscsi.c
@@ -1899,12 +1899,12 @@ static void session_recovery_timedout(struct work_struct *work)
 	}
 	spin_unlock_irqrestore(&session->lock, flags);
 
-	if (session->transport->session_recovery_timedout)
-		session->transport->session_recovery_timedout(session);
-
 	ISCSI_DBG_TRANS_SESSION(session, "Unblocking SCSI target\n");
 	scsi_target_unblock(&session->dev, SDEV_TRANSPORT_OFFLINE);
 	ISCSI_DBG_TRANS_SESSION(session, "Completed unblocking SCSI target\n");
+
+	if (session->transport->session_recovery_timedout)
+		session->transport->session_recovery_timedout(session);
 }
 
 static void __iscsi_unblock_session(struct work_struct *work)
diff --git a/drivers/scsi/ufs/ufs-mediatek.c b/drivers/scsi/ufs/ufs-mediatek.c
index fc5b214347b3..5393b5c9dd9c 100644
--- a/drivers/scsi/ufs/ufs-mediatek.c
+++ b/drivers/scsi/ufs/ufs-mediatek.c
@@ -1189,6 +1189,7 @@ static int ufs_mtk_probe(struct platform_device *pdev)
 	}
 	link = device_link_add(dev, &reset_pdev->dev,
 		DL_FLAG_AUTOPROBE_CONSUMER);
+	put_device(&reset_pdev->dev);
 	if (!link) {
 		dev_notice(dev, "add reset device_link fail\n");
 		goto skip_reset;
diff --git a/drivers/scsi/ufs/ufshcd-pci.c b/drivers/scsi/ufs/ufshcd-pci.c
index 51424557810d..f725248ba57f 100644
--- a/drivers/scsi/ufs/ufshcd-pci.c
+++ b/drivers/scsi/ufs/ufshcd-pci.c
@@ -421,6 +421,13 @@ static int ufs_intel_lkf_init(struct ufs_hba *hba)
 	return err;
 }
 
+static int ufs_intel_adl_init(struct ufs_hba *hba)
+{
+	hba->nop_out_timeout = 200;
+	hba->quirks |= UFSHCD_QUIRK_BROKEN_AUTO_HIBERN8;
+	return ufs_intel_common_init(hba);
+}
+
 static struct ufs_hba_variant_ops ufs_intel_cnl_hba_vops = {
 	.name                   = "intel-pci",
 	.init			= ufs_intel_common_init,
@@ -449,6 +456,15 @@ static struct ufs_hba_variant_ops ufs_intel_lkf_hba_vops = {
 	.device_reset		= ufs_intel_device_reset,
 };
 
+static struct ufs_hba_variant_ops ufs_intel_adl_hba_vops = {
+	.name			= "intel-pci",
+	.init			= ufs_intel_adl_init,
+	.exit			= ufs_intel_common_exit,
+	.link_startup_notify	= ufs_intel_link_startup_notify,
+	.resume			= ufs_intel_resume,
+	.device_reset		= ufs_intel_device_reset,
+};
+
 #ifdef CONFIG_PM_SLEEP
 static int ufshcd_pci_restore(struct device *dev)
 {
@@ -563,6 +579,8 @@ static const struct pci_device_id ufshcd_pci_tbl[] = {
 	{ PCI_VDEVICE(INTEL, 0x4B41), (kernel_ulong_t)&ufs_intel_ehl_hba_vops },
 	{ PCI_VDEVICE(INTEL, 0x4B43), (kernel_ulong_t)&ufs_intel_ehl_hba_vops },
 	{ PCI_VDEVICE(INTEL, 0x98FA), (kernel_ulong_t)&ufs_intel_lkf_hba_vops },
+	{ PCI_VDEVICE(INTEL, 0x51FF), (kernel_ulong_t)&ufs_intel_adl_hba_vops },
+	{ PCI_VDEVICE(INTEL, 0x54FF), (kernel_ulong_t)&ufs_intel_adl_hba_vops },
 	{ }	/* terminate list */
 };
 
diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index afd38142b1c0..13c09dbd99b9 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -6453,9 +6453,8 @@ static irqreturn_t ufshcd_tmc_handler(struct ufs_hba *hba)
 	irqreturn_t ret = IRQ_NONE;
 	int tag;
 
-	pending = ufshcd_readl(hba, REG_UTP_TASK_REQ_DOOR_BELL);
-
 	spin_lock_irqsave(hba->host->host_lock, flags);
+	pending = ufshcd_readl(hba, REG_UTP_TASK_REQ_DOOR_BELL);
 	issued = hba->outstanding_tasks & ~pending;
 	for_each_set_bit(tag, &issued, hba->nutmrs) {
 		struct request *req = hba->tmf_rqs[tag];
@@ -6616,11 +6615,6 @@ static int __ufshcd_issue_tm_cmd(struct ufs_hba *hba,
 	err = wait_for_completion_io_timeout(&wait,
 			msecs_to_jiffies(TM_CMD_TIMEOUT));
 	if (!err) {
-		/*
-		 * Make sure that ufshcd_compl_tm() does not trigger a
-		 * use-after-free.
-		 */
-		req->end_io_data = NULL;
 		ufshcd_add_tm_upiu_trace(hba, task_tag, UFS_TM_ERR);
 		dev_err(hba->dev, "%s: task management cmd 0x%.2x timed-out\n",
 				__func__, tm_function);
@@ -7116,6 +7110,7 @@ static int ufshcd_abort(struct scsi_cmnd *cmd)
 		goto release;
 	}
 
+	lrbp->cmd = NULL;
 	err = SUCCESS;
 
 release:
diff --git a/drivers/scsi/ufs/ufshpb.c b/drivers/scsi/ufs/ufshpb.c
index 2e31e1413826..ded5ba9b1466 100644
--- a/drivers/scsi/ufs/ufshpb.c
+++ b/drivers/scsi/ufs/ufshpb.c
@@ -331,7 +331,7 @@ ufshpb_set_hpb_read_to_upiu(struct ufs_hba *hba, struct ufshcd_lrb *lrbp,
 	cdb[0] = UFSHPB_READ;
 
 	if (hba->dev_quirks & UFS_DEVICE_QUIRK_SWAP_L2P_ENTRY_FOR_HPB_READ)
-		ppn_tmp = swab64(ppn);
+		ppn_tmp = (__force __be64)swab64((__force u64)ppn);
 
 	/* ppn value is stored as big-endian in the host memory */
 	memcpy(&cdb[6], &ppn_tmp, sizeof(__be64));
diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c
index 19f7d7b90625..28e1d98ae102 100644
--- a/drivers/scsi/virtio_scsi.c
+++ b/drivers/scsi/virtio_scsi.c
@@ -977,7 +977,6 @@ static unsigned int features[] = {
 static struct virtio_driver virtio_scsi_driver = {
 	.feature_table = features,
 	.feature_table_size = ARRAY_SIZE(features),
-	.suppress_used_validation = true,
 	.driver.name = KBUILD_MODNAME,
 	.driver.owner = THIS_MODULE,
 	.id_table = id_table,
diff --git a/drivers/sh/maple/maple.c b/drivers/sh/maple/maple.c
index bd0fbcdbdefe..e24e220e56ee 100644
--- a/drivers/sh/maple/maple.c
+++ b/drivers/sh/maple/maple.c
@@ -834,8 +834,10 @@ static int __init maple_bus_init(void)
 
 	maple_queue_cache = KMEM_CACHE(maple_buffer, SLAB_HWCACHE_ALIGN);
 
-	if (!maple_queue_cache)
+	if (!maple_queue_cache) {
+		retval = -ENOMEM;
 		goto cleanup_bothirqs;
+	}
 
 	INIT_LIST_HEAD(&maple_waitq);
 	INIT_LIST_HEAD(&maple_sentq);
@@ -848,6 +850,7 @@ static int __init maple_bus_init(void)
 		if (!mdev[i]) {
 			while (i-- > 0)
 				maple_free_dev(mdev[i]);
+			retval = -ENOMEM;
 			goto cleanup_cache;
 		}
 		baseunits[i] = mdev[i];
diff --git a/drivers/soc/imx/imx8m-blk-ctrl.c b/drivers/soc/imx/imx8m-blk-ctrl.c
index 519b3651d1d9..c2f076b56e24 100644
--- a/drivers/soc/imx/imx8m-blk-ctrl.c
+++ b/drivers/soc/imx/imx8m-blk-ctrl.c
@@ -17,6 +17,7 @@
 
 #define BLK_SFT_RSTN	0x0
 #define BLK_CLK_EN	0x4
+#define BLK_MIPI_RESET_DIV	0x8 /* Mini/Nano DISPLAY_BLK_CTRL only */
 
 struct imx8m_blk_ctrl_domain;
 
@@ -36,6 +37,15 @@ struct imx8m_blk_ctrl_domain_data {
 	const char *gpc_name;
 	u32 rst_mask;
 	u32 clk_mask;
+
+	/*
+	 * i.MX8M Mini and Nano have a third DISPLAY_BLK_CTRL register
+	 * which is used to control the reset for the MIPI Phy.
+	 * Since it's only present in certain circumstances,
+	 * an if-statement should be used before setting and clearing this
+	 * register.
+	 */
+	u32 mipi_phy_rst_mask;
 };
 
 #define DOMAIN_MAX_CLKS 3
@@ -78,6 +88,8 @@ static int imx8m_blk_ctrl_power_on(struct generic_pm_domain *genpd)
 
 	/* put devices into reset */
 	regmap_clear_bits(bc->regmap, BLK_SFT_RSTN, data->rst_mask);
+	if (data->mipi_phy_rst_mask)
+		regmap_clear_bits(bc->regmap, BLK_MIPI_RESET_DIV, data->mipi_phy_rst_mask);
 
 	/* enable upstream and blk-ctrl clocks to allow reset to propagate */
 	ret = clk_bulk_prepare_enable(data->num_clks, domain->clks);
@@ -99,6 +111,8 @@ static int imx8m_blk_ctrl_power_on(struct generic_pm_domain *genpd)
 
 	/* release reset */
 	regmap_set_bits(bc->regmap, BLK_SFT_RSTN, data->rst_mask);
+	if (data->mipi_phy_rst_mask)
+		regmap_set_bits(bc->regmap, BLK_MIPI_RESET_DIV, data->mipi_phy_rst_mask);
 
 	/* disable upstream clocks */
 	clk_bulk_disable_unprepare(data->num_clks, domain->clks);
@@ -120,6 +134,9 @@ static int imx8m_blk_ctrl_power_off(struct generic_pm_domain *genpd)
 	struct imx8m_blk_ctrl *bc = domain->bc;
 
 	/* put devices into reset and disable clocks */
+	if (data->mipi_phy_rst_mask)
+		regmap_clear_bits(bc->regmap, BLK_MIPI_RESET_DIV, data->mipi_phy_rst_mask);
+
 	regmap_clear_bits(bc->regmap, BLK_SFT_RSTN, data->rst_mask);
 	regmap_clear_bits(bc->regmap, BLK_CLK_EN, data->clk_mask);
 
@@ -480,6 +497,7 @@ static const struct imx8m_blk_ctrl_domain_data imx8mm_disp_blk_ctl_domain_data[]
 		.gpc_name = "mipi-dsi",
 		.rst_mask = BIT(5),
 		.clk_mask = BIT(8) | BIT(9),
+		.mipi_phy_rst_mask = BIT(17),
 	},
 	[IMX8MM_DISPBLK_PD_MIPI_CSI] = {
 		.name = "dispblk-mipi-csi",
@@ -488,6 +506,7 @@ static const struct imx8m_blk_ctrl_domain_data imx8mm_disp_blk_ctl_domain_data[]
 		.gpc_name = "mipi-csi",
 		.rst_mask = BIT(3) | BIT(4),
 		.clk_mask = BIT(10) | BIT(11),
+		.mipi_phy_rst_mask = BIT(16),
 	},
 };
 
diff --git a/drivers/soc/imx/soc-imx.c b/drivers/soc/imx/soc-imx.c
index ac6d856ba228..77bc12039c3d 100644
--- a/drivers/soc/imx/soc-imx.c
+++ b/drivers/soc/imx/soc-imx.c
@@ -36,6 +36,10 @@ static int __init imx_soc_device_init(void)
 	int ret;
 	int i;
 
+	/* Return early if this is running on devices with different SoCs */
+	if (!__mxc_cpu_type)
+		return 0;
+
 	if (of_machine_is_compatible("fsl,ls1021a"))
 		return 0;
 
diff --git a/drivers/soc/tegra/fuse/fuse-tegra.c b/drivers/soc/tegra/fuse/fuse-tegra.c
index f2151815db58..e714ed3b61bc 100644
--- a/drivers/soc/tegra/fuse/fuse-tegra.c
+++ b/drivers/soc/tegra/fuse/fuse-tegra.c
@@ -320,7 +320,7 @@ static struct platform_driver tegra_fuse_driver = {
 };
 builtin_platform_driver(tegra_fuse_driver);
 
-bool __init tegra_fuse_read_spare(unsigned int spare)
+u32 __init tegra_fuse_read_spare(unsigned int spare)
 {
 	unsigned int offset = fuse->soc->info->spare + spare * 4;
 
diff --git a/drivers/soc/tegra/fuse/fuse.h b/drivers/soc/tegra/fuse/fuse.h
index de58feba0435..ecff0c08e959 100644
--- a/drivers/soc/tegra/fuse/fuse.h
+++ b/drivers/soc/tegra/fuse/fuse.h
@@ -65,7 +65,7 @@ struct tegra_fuse {
 void tegra_init_revision(void);
 void tegra_init_apbmisc(void);
 
-bool __init tegra_fuse_read_spare(unsigned int spare);
+u32 __init tegra_fuse_read_spare(unsigned int spare);
 u32 __init tegra_fuse_read_early(unsigned int offset);
 
 u8 tegra_get_major_rev(void);
diff --git a/drivers/spi/spi-armada-3700.c b/drivers/spi/spi-armada-3700.c
index 46feafe4e201..d8cc4b270644 100644
--- a/drivers/spi/spi-armada-3700.c
+++ b/drivers/spi/spi-armada-3700.c
@@ -901,7 +901,7 @@ static int a3700_spi_probe(struct platform_device *pdev)
 	return 0;
 
 error_clk:
-	clk_disable_unprepare(spi->clk);
+	clk_unprepare(spi->clk);
 error:
 	spi_master_put(master);
 out:
diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c
index 8b3d268ac63c..b808c94641fa 100644
--- a/drivers/spi/spi-cadence-quadspi.c
+++ b/drivers/spi/spi-cadence-quadspi.c
@@ -37,6 +37,7 @@
 #define CQSPI_NEEDS_WR_DELAY		BIT(0)
 #define CQSPI_DISABLE_DAC_MODE		BIT(1)
 #define CQSPI_SUPPORT_EXTERNAL_DMA	BIT(2)
+#define CQSPI_NO_SUPPORT_WR_COMPLETION	BIT(3)
 
 /* Capabilities */
 #define CQSPI_SUPPORTS_OCTAL		BIT(0)
@@ -86,6 +87,7 @@ struct cqspi_st {
 	struct cqspi_flash_pdata f_pdata[CQSPI_MAX_CHIPSELECT];
 	bool			use_dma_read;
 	u32			pd_dev_id;
+	bool			wr_completion;
 };
 
 struct cqspi_driver_platdata {
@@ -996,9 +998,11 @@ static int cqspi_write_setup(struct cqspi_flash_pdata *f_pdata,
 	 * polling on the controller's side. spinand and spi-nor will take
 	 * care of polling the status register.
 	 */
-	reg = readl(reg_base + CQSPI_REG_WR_COMPLETION_CTRL);
-	reg |= CQSPI_REG_WR_DISABLE_AUTO_POLL;
-	writel(reg, reg_base + CQSPI_REG_WR_COMPLETION_CTRL);
+	if (cqspi->wr_completion) {
+		reg = readl(reg_base + CQSPI_REG_WR_COMPLETION_CTRL);
+		reg |= CQSPI_REG_WR_DISABLE_AUTO_POLL;
+		writel(reg, reg_base + CQSPI_REG_WR_COMPLETION_CTRL);
+	}
 
 	reg = readl(reg_base + CQSPI_REG_SIZE);
 	reg &= ~CQSPI_REG_SIZE_ADDRESS_MASK;
@@ -1736,6 +1740,10 @@ static int cqspi_probe(struct platform_device *pdev)
 
 	cqspi->master_ref_clk_hz = clk_get_rate(cqspi->clk);
 	master->max_speed_hz = cqspi->master_ref_clk_hz;
+
+	/* write completion is supported by default */
+	cqspi->wr_completion = true;
+
 	ddata  = of_device_get_match_data(dev);
 	if (ddata) {
 		if (ddata->quirks & CQSPI_NEEDS_WR_DELAY)
@@ -1747,6 +1755,8 @@ static int cqspi_probe(struct platform_device *pdev)
 			cqspi->use_direct_mode = true;
 		if (ddata->quirks & CQSPI_SUPPORT_EXTERNAL_DMA)
 			cqspi->use_dma_read = true;
+		if (ddata->quirks & CQSPI_NO_SUPPORT_WR_COMPLETION)
+			cqspi->wr_completion = false;
 
 		if (of_device_is_compatible(pdev->dev.of_node,
 					    "xlnx,versal-ospi-1.0"))
@@ -1859,6 +1869,10 @@ static const struct cqspi_driver_platdata intel_lgm_qspi = {
 	.quirks = CQSPI_DISABLE_DAC_MODE,
 };
 
+static const struct cqspi_driver_platdata socfpga_qspi = {
+	.quirks = CQSPI_NO_SUPPORT_WR_COMPLETION,
+};
+
 static const struct cqspi_driver_platdata versal_ospi = {
 	.hwcaps_mask = CQSPI_SUPPORTS_OCTAL,
 	.quirks = CQSPI_DISABLE_DAC_MODE | CQSPI_SUPPORT_EXTERNAL_DMA,
@@ -1887,6 +1901,10 @@ static const struct of_device_id cqspi_dt_ids[] = {
 		.compatible = "xlnx,versal-ospi-1.0",
 		.data = (void *)&versal_ospi,
 	},
+	{
+		.compatible = "intel,socfpga-qspi",
+		.data = (void *)&socfpga_qspi,
+	},
 	{ /* end of table */ }
 };
 
diff --git a/drivers/spi/spi-fsl-lpspi.c b/drivers/spi/spi-fsl-lpspi.c
index 5d98611dd999..c72e501c270f 100644
--- a/drivers/spi/spi-fsl-lpspi.c
+++ b/drivers/spi/spi-fsl-lpspi.c
@@ -912,7 +912,7 @@ static int fsl_lpspi_probe(struct platform_device *pdev)
 
 	ret = devm_spi_register_controller(&pdev->dev, controller);
 	if (ret < 0) {
-		dev_err(&pdev->dev, "spi_register_controller error.\n");
+		dev_err_probe(&pdev->dev, ret, "spi_register_controller error: %i\n", ret);
 		goto out_pm_get;
 	}
 
diff --git a/drivers/spi/spi-geni-qcom.c b/drivers/spi/spi-geni-qcom.c
index 27a446faf143..e2affaee4e76 100644
--- a/drivers/spi/spi-geni-qcom.c
+++ b/drivers/spi/spi-geni-qcom.c
@@ -491,22 +491,26 @@ static int spi_geni_grab_gpi_chan(struct spi_geni_master *mas)
 	int ret;
 
 	mas->tx = dma_request_chan(mas->dev, "tx");
-	ret = dev_err_probe(mas->dev, IS_ERR(mas->tx), "Failed to get tx DMA ch\n");
-	if (ret < 0)
+	if (IS_ERR(mas->tx)) {
+		ret = dev_err_probe(mas->dev, PTR_ERR(mas->tx),
+				    "Failed to get tx DMA ch\n");
 		goto err_tx;
+	}
 
 	mas->rx = dma_request_chan(mas->dev, "rx");
-	ret = dev_err_probe(mas->dev, IS_ERR(mas->rx), "Failed to get rx DMA ch\n");
-	if (ret < 0)
+	if (IS_ERR(mas->rx)) {
+		ret = dev_err_probe(mas->dev, PTR_ERR(mas->rx),
+				    "Failed to get rx DMA ch\n");
 		goto err_rx;
+	}
 
 	return 0;
 
 err_rx:
+	mas->rx = NULL;
 	dma_release_channel(mas->tx);
-	mas->tx = NULL;
 err_tx:
-	mas->rx = NULL;
+	mas->tx = NULL;
 	return ret;
 }
 
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index b23e675953e1..fdd530b150a7 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -3099,12 +3099,6 @@ void spi_unregister_controller(struct spi_controller *ctlr)
 
 	device_del(&ctlr->dev);
 
-	/* Release the last reference on the controller if its driver
-	 * has not yet been converted to devm_spi_alloc_master/slave().
-	 */
-	if (!ctlr->devm_allocated)
-		put_device(&ctlr->dev);
-
 	/* free bus id */
 	mutex_lock(&board_lock);
 	if (found == ctlr)
@@ -3113,6 +3107,12 @@ void spi_unregister_controller(struct spi_controller *ctlr)
 
 	if (IS_ENABLED(CONFIG_SPI_DYNAMIC))
 		mutex_unlock(&ctlr->add_lock);
+
+	/* Release the last reference on the controller if its driver
+	 * has not yet been converted to devm_spi_alloc_master/slave().
+	 */
+	if (!ctlr->devm_allocated)
+		put_device(&ctlr->dev);
 }
 EXPORT_SYMBOL_GPL(spi_unregister_controller);
 
diff --git a/drivers/staging/Kconfig b/drivers/staging/Kconfig
index 59af251e7576..7fec86946131 100644
--- a/drivers/staging/Kconfig
+++ b/drivers/staging/Kconfig
@@ -66,8 +66,6 @@ source "drivers/staging/gdm724x/Kconfig"
 
 source "drivers/staging/fwserial/Kconfig"
 
-source "drivers/staging/netlogic/Kconfig"
-
 source "drivers/staging/gs_fpgaboot/Kconfig"
 
 source "drivers/staging/unisys/Kconfig"
diff --git a/drivers/staging/Makefile b/drivers/staging/Makefile
index 76f413470bc8..e66e19c45425 100644
--- a/drivers/staging/Makefile
+++ b/drivers/staging/Makefile
@@ -10,7 +10,6 @@ obj-$(CONFIG_RTL8723BS)		+= rtl8723bs/
 obj-$(CONFIG_R8712U)		+= rtl8712/
 obj-$(CONFIG_R8188EU)		+= r8188eu/
 obj-$(CONFIG_RTS5208)		+= rts5208/
-obj-$(CONFIG_NETLOGIC_XLR_NET)	+= netlogic/
 obj-$(CONFIG_OCTEON_ETHERNET)	+= octeon/
 obj-$(CONFIG_OCTEON_USB)	+= octeon-usb/
 obj-$(CONFIG_VT6655)		+= vt6655/
diff --git a/drivers/staging/fbtft/fb_ssd1351.c b/drivers/staging/fbtft/fb_ssd1351.c
index cf263a58a148..6fd549a424d5 100644
--- a/drivers/staging/fbtft/fb_ssd1351.c
+++ b/drivers/staging/fbtft/fb_ssd1351.c
@@ -187,7 +187,6 @@ static struct fbtft_display display = {
 	},
 };
 
-#ifdef CONFIG_FB_BACKLIGHT
 static int update_onboard_backlight(struct backlight_device *bd)
 {
 	struct fbtft_par *par = bl_get_data(bd);
@@ -231,9 +230,6 @@ static void register_onboard_backlight(struct fbtft_par *par)
 	if (!par->fbtftops.unregister_backlight)
 		par->fbtftops.unregister_backlight = fbtft_unregister_backlight;
 }
-#else
-static void register_onboard_backlight(struct fbtft_par *par) { };
-#endif
 
 FBTFT_REGISTER_DRIVER(DRVNAME, "solomon,ssd1351", &display);
 
diff --git a/drivers/staging/fbtft/fbtft-core.c b/drivers/staging/fbtft/fbtft-core.c
index ecb5f75f6dd5..f2684d2d6851 100644
--- a/drivers/staging/fbtft/fbtft-core.c
+++ b/drivers/staging/fbtft/fbtft-core.c
@@ -128,7 +128,6 @@ static int fbtft_request_gpios(struct fbtft_par *par)
 	return 0;
 }
 
-#ifdef CONFIG_FB_BACKLIGHT
 static int fbtft_backlight_update_status(struct backlight_device *bd)
 {
 	struct fbtft_par *par = bl_get_data(bd);
@@ -161,6 +160,7 @@ void fbtft_unregister_backlight(struct fbtft_par *par)
 		par->info->bl_dev = NULL;
 	}
 }
+EXPORT_SYMBOL(fbtft_unregister_backlight);
 
 static const struct backlight_ops fbtft_bl_ops = {
 	.get_brightness	= fbtft_backlight_get_brightness,
@@ -198,12 +198,7 @@ void fbtft_register_backlight(struct fbtft_par *par)
 	if (!par->fbtftops.unregister_backlight)
 		par->fbtftops.unregister_backlight = fbtft_unregister_backlight;
 }
-#else
-void fbtft_register_backlight(struct fbtft_par *par) { };
-void fbtft_unregister_backlight(struct fbtft_par *par) { };
-#endif
 EXPORT_SYMBOL(fbtft_register_backlight);
-EXPORT_SYMBOL(fbtft_unregister_backlight);
 
 static void fbtft_set_addr_win(struct fbtft_par *par, int xs, int ys, int xe,
 			       int ye)
@@ -853,13 +848,11 @@ int fbtft_register_framebuffer(struct fb_info *fb_info)
 		 fb_info->fix.smem_len >> 10, text1,
 		 HZ / fb_info->fbdefio->delay, text2);
 
-#ifdef CONFIG_FB_BACKLIGHT
 	/* Turn on backlight if available */
 	if (fb_info->bl_dev) {
 		fb_info->bl_dev->props.power = FB_BLANK_UNBLANK;
 		fb_info->bl_dev->ops->update_status(fb_info->bl_dev);
 	}
-#endif
 
 	return 0;
 
diff --git a/drivers/staging/greybus/audio_helper.c b/drivers/staging/greybus/audio_helper.c
index 1ed4772d2771..843760675876 100644
--- a/drivers/staging/greybus/audio_helper.c
+++ b/drivers/staging/greybus/audio_helper.c
@@ -192,7 +192,11 @@ int gbaudio_remove_component_controls(struct snd_soc_component *component,
 				      unsigned int num_controls)
 {
 	struct snd_card *card = component->card->snd_card;
+	int err;
 
-	return gbaudio_remove_controls(card, component->dev, controls,
-				       num_controls, component->name_prefix);
+	down_write(&card->controls_rwsem);
+	err = gbaudio_remove_controls(card, component->dev, controls,
+				      num_controls, component->name_prefix);
+	up_write(&card->controls_rwsem);
+	return err;
 }
diff --git a/drivers/staging/netlogic/Kconfig b/drivers/staging/netlogic/Kconfig
deleted file mode 100644
index e1712606ee3c..000000000000
--- a/drivers/staging/netlogic/Kconfig
+++ /dev/null
@@ -1,9 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-config NETLOGIC_XLR_NET
-	tristate "Netlogic XLR/XLS network device"
-	depends on CPU_XLR
-	depends on NETDEVICES
-	select PHYLIB
-	help
-	This driver support Netlogic XLR/XLS on chip gigabit
-	Ethernet.
diff --git a/drivers/staging/netlogic/Makefile b/drivers/staging/netlogic/Makefile
deleted file mode 100644
index 7e2902af26a3..000000000000
--- a/drivers/staging/netlogic/Makefile
+++ /dev/null
@@ -1,2 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-obj-$(CONFIG_NETLOGIC_XLR_NET) += xlr_net.o platform_net.o
diff --git a/drivers/staging/netlogic/TODO b/drivers/staging/netlogic/TODO
deleted file mode 100644
index 20e22ecb9903..000000000000
--- a/drivers/staging/netlogic/TODO
+++ /dev/null
@@ -1,11 +0,0 @@
-* Implementing 64bit stat counter in software
-* All memory allocation should be changed to DMA allocations
-* Changing comments into linux standard format
-
-Please send patches
-To:
-Ganesan Ramalingam <ganesanr@broadcom.com>
-Greg Kroah-Hartman <gregkh@linuxfoundation.org>
-Cc:
-Jayachandran Chandrashekaran Nair <jchandra@broadcom.com>
-
diff --git a/drivers/staging/netlogic/platform_net.c b/drivers/staging/netlogic/platform_net.c
deleted file mode 100644
index 8be9d0b0c22c..000000000000
--- a/drivers/staging/netlogic/platform_net.c
+++ /dev/null
@@ -1,219 +0,0 @@
-// SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
-/*
- * Copyright (c) 2003-2012 Broadcom Corporation
- * All Rights Reserved
- */
-
-#include <linux/device.h>
-#include <linux/platform_device.h>
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/io.h>
-#include <linux/delay.h>
-#include <linux/ioport.h>
-#include <linux/resource.h>
-#include <linux/phy.h>
-
-#include <asm/netlogic/haldefs.h>
-#include <asm/netlogic/common.h>
-#include <asm/netlogic/xlr/fmn.h>
-#include <asm/netlogic/xlr/xlr.h>
-#include <asm/netlogic/psb-bootinfo.h>
-#include <asm/netlogic/xlr/pic.h>
-#include <asm/netlogic/xlr/iomap.h>
-
-#include "platform_net.h"
-
-/* Linux Net */
-#define MAX_NUM_GMAC		8
-#define MAX_NUM_XLS_GMAC	8
-#define MAX_NUM_XLR_GMAC	4
-
-static u32 xlr_gmac_offsets[] = {
-	NETLOGIC_IO_GMAC_0_OFFSET, NETLOGIC_IO_GMAC_1_OFFSET,
-	NETLOGIC_IO_GMAC_2_OFFSET, NETLOGIC_IO_GMAC_3_OFFSET,
-	NETLOGIC_IO_GMAC_4_OFFSET, NETLOGIC_IO_GMAC_5_OFFSET,
-	NETLOGIC_IO_GMAC_6_OFFSET, NETLOGIC_IO_GMAC_7_OFFSET
-};
-
-static u32 xlr_gmac_irqs[] = { PIC_GMAC_0_IRQ, PIC_GMAC_1_IRQ,
-	PIC_GMAC_2_IRQ, PIC_GMAC_3_IRQ,
-	PIC_GMAC_4_IRQ, PIC_GMAC_5_IRQ,
-	PIC_GMAC_6_IRQ, PIC_GMAC_7_IRQ
-};
-
-static struct resource xlr_net0_res[8];
-static struct resource xlr_net1_res[8];
-static u32 __iomem *gmac4_addr;
-static u32 __iomem *gpio_addr;
-
-static void xlr_resource_init(struct resource *res, int offset, int irq)
-{
-	res->name = "gmac";
-
-	res->start = CPHYSADDR(nlm_mmio_base(offset));
-	res->end = res->start + 0xfff;
-	res->flags = IORESOURCE_MEM;
-
-	res++;
-	res->name = "gmac";
-	res->start = irq;
-	res->end = irq;
-	res->flags = IORESOURCE_IRQ;
-}
-
-static struct platform_device *gmac_controller2_init(void *gmac0_addr)
-{
-	int mac;
-	static struct xlr_net_data ndata1 = {
-		.phy_interface	= PHY_INTERFACE_MODE_SGMII,
-		.rfr_station	= FMN_STNID_GMAC1_FR_0,
-		.bucket_size	= xlr_board_fmn_config.bucket_size,
-		.gmac_fmn_info	= &xlr_board_fmn_config.gmac[1],
-	};
-
-	static struct platform_device xlr_net_dev1 = {
-		.name		= "xlr-net",
-		.id		= 1,
-		.dev.platform_data = &ndata1,
-	};
-
-	gmac4_addr =
-		ioremap(CPHYSADDR(nlm_mmio_base(NETLOGIC_IO_GMAC_4_OFFSET)),
-			0xfff);
-	ndata1.serdes_addr = gmac4_addr;
-	ndata1.pcs_addr	= gmac4_addr;
-	ndata1.mii_addr	= gmac0_addr;
-	ndata1.gpio_addr = gpio_addr;
-	ndata1.cpu_mask = nlm_current_node()->coremask;
-
-	xlr_net_dev1.resource = xlr_net1_res;
-
-	for (mac = 0; mac < 4; mac++) {
-		ndata1.tx_stnid[mac] = FMN_STNID_GMAC1_TX0 + mac;
-		ndata1.phy_addr[mac] = mac + 4 + 0x10;
-
-		xlr_resource_init(&xlr_net1_res[mac * 2],
-				  xlr_gmac_offsets[mac + 4],
-				  xlr_gmac_irqs[mac + 4]);
-	}
-	xlr_net_dev1.num_resources = 8;
-
-	return &xlr_net_dev1;
-}
-
-static void xls_gmac_init(void)
-{
-	int mac;
-	struct platform_device *xlr_net_dev1;
-	void __iomem *gmac0_addr =
-		ioremap(CPHYSADDR(nlm_mmio_base(NETLOGIC_IO_GMAC_0_OFFSET)),
-			0xfff);
-
-	static struct xlr_net_data ndata0 = {
-		.rfr_station	= FMN_STNID_GMACRFR_0,
-		.bucket_size	= xlr_board_fmn_config.bucket_size,
-		.gmac_fmn_info	= &xlr_board_fmn_config.gmac[0],
-	};
-
-	static struct platform_device xlr_net_dev0 = {
-		.name		= "xlr-net",
-		.id		= 0,
-	};
-	xlr_net_dev0.dev.platform_data = &ndata0;
-	ndata0.serdes_addr = gmac0_addr;
-	ndata0.pcs_addr	= gmac0_addr;
-	ndata0.mii_addr	= gmac0_addr;
-
-	/* Passing GPIO base for serdes init. Only needed on sgmii ports */
-	gpio_addr =
-		ioremap(CPHYSADDR(nlm_mmio_base(NETLOGIC_IO_GPIO_OFFSET)),
-			0xfff);
-	ndata0.gpio_addr = gpio_addr;
-	ndata0.cpu_mask = nlm_current_node()->coremask;
-
-	xlr_net_dev0.resource = xlr_net0_res;
-
-	switch (nlm_prom_info.board_major_version) {
-	case 12:
-		/* first block RGMII or XAUI, use RGMII */
-		ndata0.phy_interface = PHY_INTERFACE_MODE_RGMII;
-		ndata0.tx_stnid[0] = FMN_STNID_GMAC0_TX0;
-		ndata0.phy_addr[0] = 0;
-
-		xlr_net_dev0.num_resources = 2;
-
-		xlr_resource_init(&xlr_net0_res[0], xlr_gmac_offsets[0],
-				  xlr_gmac_irqs[0]);
-		platform_device_register(&xlr_net_dev0);
-
-		/* second block is XAUI, not supported yet */
-		break;
-	default:
-		/* default XLS config, all ports SGMII */
-		ndata0.phy_interface = PHY_INTERFACE_MODE_SGMII;
-		for (mac = 0; mac < 4; mac++) {
-			ndata0.tx_stnid[mac] = FMN_STNID_GMAC0_TX0 + mac;
-			ndata0.phy_addr[mac] = mac + 0x10;
-
-			xlr_resource_init(&xlr_net0_res[mac * 2],
-					  xlr_gmac_offsets[mac],
-					xlr_gmac_irqs[mac]);
-		}
-		xlr_net_dev0.num_resources = 8;
-		platform_device_register(&xlr_net_dev0);
-
-		xlr_net_dev1 = gmac_controller2_init(gmac0_addr);
-		platform_device_register(xlr_net_dev1);
-	}
-}
-
-static void xlr_gmac_init(void)
-{
-	int mac;
-
-	/* assume all GMACs for now */
-	static struct xlr_net_data ndata0 = {
-		.phy_interface	= PHY_INTERFACE_MODE_RGMII,
-		.serdes_addr	= NULL,
-		.pcs_addr	= NULL,
-		.rfr_station	= FMN_STNID_GMACRFR_0,
-		.bucket_size	= xlr_board_fmn_config.bucket_size,
-		.gmac_fmn_info	= &xlr_board_fmn_config.gmac[0],
-		.gpio_addr	= NULL,
-	};
-
-	static struct platform_device xlr_net_dev0 = {
-		.name		= "xlr-net",
-		.id		= 0,
-		.dev.platform_data = &ndata0,
-	};
-	ndata0.mii_addr =
-		ioremap(CPHYSADDR(nlm_mmio_base(NETLOGIC_IO_GMAC_0_OFFSET)),
-			0xfff);
-
-	ndata0.cpu_mask = nlm_current_node()->coremask;
-
-	for (mac = 0; mac < MAX_NUM_XLR_GMAC; mac++) {
-		ndata0.tx_stnid[mac] = FMN_STNID_GMAC0_TX0 + mac;
-		ndata0.phy_addr[mac] = mac;
-		xlr_resource_init(&xlr_net0_res[mac * 2], xlr_gmac_offsets[mac],
-				  xlr_gmac_irqs[mac]);
-	}
-	xlr_net_dev0.num_resources = 8;
-	xlr_net_dev0.resource = xlr_net0_res;
-
-	platform_device_register(&xlr_net_dev0);
-}
-
-static int __init xlr_net_init(void)
-{
-	if (nlm_chip_is_xls())
-		xls_gmac_init();
-	else
-		xlr_gmac_init();
-
-	return 0;
-}
-
-arch_initcall(xlr_net_init);
diff --git a/drivers/staging/netlogic/platform_net.h b/drivers/staging/netlogic/platform_net.h
deleted file mode 100644
index c8d4c13424c6..000000000000
--- a/drivers/staging/netlogic/platform_net.h
+++ /dev/null
@@ -1,21 +0,0 @@
-/* SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) */
-/*
- * Copyright (c) 2003-2012 Broadcom Corporation
- * All Rights Reserved
- */
-
-#define PORTS_PER_CONTROLLER		4
-
-struct xlr_net_data {
-	int cpu_mask;
-	u32 __iomem *mii_addr;
-	u32 __iomem *serdes_addr;
-	u32 __iomem *pcs_addr;
-	u32 __iomem *gpio_addr;
-	int phy_interface;
-	int rfr_station;
-	int tx_stnid[PORTS_PER_CONTROLLER];
-	int *bucket_size;
-	int phy_addr[PORTS_PER_CONTROLLER];
-	struct xlr_fmn_info *gmac_fmn_info;
-};
diff --git a/drivers/staging/netlogic/xlr_net.c b/drivers/staging/netlogic/xlr_net.c
deleted file mode 100644
index 69ea61faf8fa..000000000000
--- a/drivers/staging/netlogic/xlr_net.c
+++ /dev/null
@@ -1,1080 +0,0 @@
-// SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
-/*
- * Copyright (c) 2003-2012 Broadcom Corporation
- * All Rights Reserved
- */
-
-#include <linux/phy.h>
-#include <linux/delay.h>
-#include <linux/netdevice.h>
-#include <linux/smp.h>
-#include <linux/ethtool.h>
-#include <linux/module.h>
-#include <linux/etherdevice.h>
-#include <linux/skbuff.h>
-#include <linux/jiffies.h>
-#include <linux/interrupt.h>
-#include <linux/platform_device.h>
-
-#include <asm/mipsregs.h>
-/*
- * fmn.h - For FMN credit configuration and registering fmn_handler.
- * FMN is communication mechanism that allows processing agents within
- * XLR/XLS to communicate each other.
- */
-#include <asm/netlogic/xlr/fmn.h>
-
-#include "platform_net.h"
-#include "xlr_net.h"
-
-/*
- * The readl/writel implementation byteswaps on XLR/XLS, so
- * we need to use __raw_ IO to read the NAE registers
- * because they are in the big-endian MMIO area on the SoC.
- */
-static inline void xlr_nae_wreg(u32 __iomem *base, unsigned int reg, u32 val)
-{
-	__raw_writel(val, base + reg);
-}
-
-static inline u32 xlr_nae_rdreg(u32 __iomem *base, unsigned int reg)
-{
-	return __raw_readl(base + reg);
-}
-
-static inline void xlr_reg_update(u32 *base_addr, u32 off, u32 val, u32 mask)
-{
-	u32 tmp;
-
-	tmp = xlr_nae_rdreg(base_addr, off);
-	xlr_nae_wreg(base_addr, off, (tmp & ~mask) | (val & mask));
-}
-
-#define MAC_SKB_BACK_PTR_SIZE SMP_CACHE_BYTES
-
-static int send_to_rfr_fifo(struct xlr_net_priv *priv, void *addr)
-{
-	struct nlm_fmn_msg msg;
-	int ret = 0, num_try = 0, stnid;
-	unsigned long paddr, mflags;
-
-	paddr = virt_to_bus(addr);
-	msg.msg0 = (u64)paddr & 0xffffffffe0ULL;
-	msg.msg1 = 0;
-	msg.msg2 = 0;
-	msg.msg3 = 0;
-	stnid = priv->nd->rfr_station;
-	do {
-		mflags = nlm_cop2_enable_irqsave();
-		ret = nlm_fmn_send(1, 0, stnid, &msg);
-		nlm_cop2_disable_irqrestore(mflags);
-		if (ret == 0)
-			return 0;
-	} while (++num_try < 10000);
-
-	netdev_err(priv->ndev, "Send to RFR failed in RX path\n");
-	return ret;
-}
-
-static inline unsigned char *xlr_alloc_skb(void)
-{
-	struct sk_buff *skb;
-	int buf_len = sizeof(struct sk_buff *);
-	unsigned char *skb_data;
-
-	/* skb->data is cache aligned */
-	skb = alloc_skb(XLR_RX_BUF_SIZE, GFP_ATOMIC);
-	if (!skb)
-		return NULL;
-	skb_data = skb->data;
-	skb_reserve(skb, MAC_SKB_BACK_PTR_SIZE);
-	memcpy(skb_data, &skb, buf_len);
-
-	return skb->data;
-}
-
-static void xlr_net_fmn_handler(int bkt, int src_stnid, int size, int code,
-				struct nlm_fmn_msg *msg, void *arg)
-{
-	struct sk_buff *skb;
-	void *skb_data = NULL;
-	struct net_device *ndev;
-	struct xlr_net_priv *priv;
-	u32 port, length;
-	unsigned char *addr;
-	struct xlr_adapter *adapter = arg;
-
-	length = (msg->msg0 >> 40) & 0x3fff;
-	if (length == 0) {
-		addr = bus_to_virt(msg->msg0 & 0xffffffffffULL);
-		addr = addr - MAC_SKB_BACK_PTR_SIZE;
-		skb = (struct sk_buff *)(*(unsigned long *)addr);
-		dev_kfree_skb_any((struct sk_buff *)addr);
-	} else {
-		addr = (unsigned char *)
-			bus_to_virt(msg->msg0 & 0xffffffffe0ULL);
-		length = length - BYTE_OFFSET - MAC_CRC_LEN;
-		port = ((int)msg->msg0) & 0x0f;
-		addr = addr - MAC_SKB_BACK_PTR_SIZE;
-		skb = (struct sk_buff *)(*(unsigned long *)addr);
-		skb->dev = adapter->netdev[port];
-		if (!skb->dev)
-			return;
-		ndev = skb->dev;
-		priv = netdev_priv(ndev);
-
-		/* 16 byte IP header align */
-		skb_reserve(skb, BYTE_OFFSET);
-		skb_put(skb, length);
-		skb->protocol = eth_type_trans(skb, skb->dev);
-		netif_rx(skb);
-		/* Fill rx ring */
-		skb_data = xlr_alloc_skb();
-		if (skb_data)
-			send_to_rfr_fifo(priv, skb_data);
-	}
-}
-
-static struct phy_device *xlr_get_phydev(struct xlr_net_priv *priv)
-{
-	return mdiobus_get_phy(priv->mii_bus, priv->phy_addr);
-}
-
-/*
- * Ethtool operation
- */
-static int xlr_get_link_ksettings(struct net_device *ndev,
-				  struct ethtool_link_ksettings *ecmd)
-{
-	struct xlr_net_priv *priv = netdev_priv(ndev);
-	struct phy_device *phydev = xlr_get_phydev(priv);
-
-	if (!phydev)
-		return -ENODEV;
-
-	phy_ethtool_ksettings_get(phydev, ecmd);
-
-	return 0;
-}
-
-static int xlr_set_link_ksettings(struct net_device *ndev,
-				  const struct ethtool_link_ksettings *ecmd)
-{
-	struct xlr_net_priv *priv = netdev_priv(ndev);
-	struct phy_device *phydev = xlr_get_phydev(priv);
-
-	if (!phydev)
-		return -ENODEV;
-	return phy_ethtool_ksettings_set(phydev, ecmd);
-}
-
-static const struct ethtool_ops xlr_ethtool_ops = {
-	.get_link_ksettings = xlr_get_link_ksettings,
-	.set_link_ksettings = xlr_set_link_ksettings,
-};
-
-/*
- * Net operations
- */
-static int xlr_net_fill_rx_ring(struct net_device *ndev)
-{
-	void *skb_data;
-	struct xlr_net_priv *priv = netdev_priv(ndev);
-	int i;
-
-	for (i = 0; i < MAX_FRIN_SPILL / 4; i++) {
-		skb_data = xlr_alloc_skb();
-		if (!skb_data)
-			return -ENOMEM;
-		send_to_rfr_fifo(priv, skb_data);
-	}
-	netdev_info(ndev, "Rx ring setup done\n");
-	return 0;
-}
-
-static int xlr_net_open(struct net_device *ndev)
-{
-	u32 err;
-	struct xlr_net_priv *priv = netdev_priv(ndev);
-	struct phy_device *phydev = xlr_get_phydev(priv);
-
-	/* schedule a link state check */
-	phy_start(phydev);
-
-	err = phy_start_aneg(phydev);
-	if (err) {
-		pr_err("Autoneg failed\n");
-		return err;
-	}
-	/* Setup the speed from PHY to internal reg*/
-	xlr_set_gmac_speed(priv);
-
-	netif_tx_start_all_queues(ndev);
-
-	return 0;
-}
-
-static int xlr_net_stop(struct net_device *ndev)
-{
-	struct xlr_net_priv *priv = netdev_priv(ndev);
-	struct phy_device *phydev = xlr_get_phydev(priv);
-
-	phy_stop(phydev);
-	netif_tx_stop_all_queues(ndev);
-	return 0;
-}
-
-static void xlr_make_tx_desc(struct nlm_fmn_msg *msg, unsigned long addr,
-			     struct sk_buff *skb)
-{
-	unsigned long physkb = virt_to_phys(skb);
-	int cpu_core = nlm_core_id();
-	int fr_stn_id = cpu_core * 8 + XLR_FB_STN;	/* FB to 6th bucket */
-
-	msg->msg0 = (((u64)1 << 63)	|	/* End of packet descriptor */
-		((u64)127 << 54)	|	/* No Free back */
-		(u64)skb->len << 40	|	/* Length of data */
-		((u64)addr));
-	msg->msg1 = (((u64)1 << 63)	|
-		((u64)fr_stn_id << 54)	|	/* Free back id */
-		(u64)0 << 40		|	/* Set len to 0 */
-		((u64)physkb  & 0xffffffff));	/* 32bit address */
-	msg->msg2 = 0;
-	msg->msg3 = 0;
-}
-
-static netdev_tx_t xlr_net_start_xmit(struct sk_buff *skb,
-				      struct net_device *ndev)
-{
-	struct nlm_fmn_msg msg;
-	struct xlr_net_priv *priv = netdev_priv(ndev);
-	int ret;
-	u32 flags;
-
-	xlr_make_tx_desc(&msg, virt_to_phys(skb->data), skb);
-	flags = nlm_cop2_enable_irqsave();
-	ret = nlm_fmn_send(2, 0, priv->tx_stnid, &msg);
-	nlm_cop2_disable_irqrestore(flags);
-	if (ret)
-		dev_kfree_skb_any(skb);
-	return NETDEV_TX_OK;
-}
-
-static void xlr_hw_set_mac_addr(struct net_device *ndev)
-{
-	struct xlr_net_priv *priv = netdev_priv(ndev);
-
-	/* set mac station address */
-	xlr_nae_wreg(priv->base_addr, R_MAC_ADDR0,
-		     ((ndev->dev_addr[5] << 24) | (ndev->dev_addr[4] << 16) |
-		     (ndev->dev_addr[3] << 8) | (ndev->dev_addr[2])));
-	xlr_nae_wreg(priv->base_addr, R_MAC_ADDR0 + 1,
-		     ((ndev->dev_addr[1] << 24) | (ndev->dev_addr[0] << 16)));
-
-	xlr_nae_wreg(priv->base_addr, R_MAC_ADDR_MASK2, 0xffffffff);
-	xlr_nae_wreg(priv->base_addr, R_MAC_ADDR_MASK2 + 1, 0xffffffff);
-	xlr_nae_wreg(priv->base_addr, R_MAC_ADDR_MASK3, 0xffffffff);
-	xlr_nae_wreg(priv->base_addr, R_MAC_ADDR_MASK3 + 1, 0xffffffff);
-
-	xlr_nae_wreg(priv->base_addr, R_MAC_FILTER_CONFIG,
-		     (1 << O_MAC_FILTER_CONFIG__BROADCAST_EN) |
-		     (1 << O_MAC_FILTER_CONFIG__ALL_MCAST_EN) |
-		     (1 << O_MAC_FILTER_CONFIG__MAC_ADDR0_VALID));
-
-	if (priv->nd->phy_interface == PHY_INTERFACE_MODE_RGMII ||
-	    priv->nd->phy_interface == PHY_INTERFACE_MODE_SGMII)
-		xlr_reg_update(priv->base_addr, R_IPG_IFG, MAC_B2B_IPG, 0x7f);
-}
-
-static int xlr_net_set_mac_addr(struct net_device *ndev, void *data)
-{
-	int err;
-
-	err = eth_mac_addr(ndev, data);
-	if (err)
-		return err;
-	xlr_hw_set_mac_addr(ndev);
-	return 0;
-}
-
-static void xlr_set_rx_mode(struct net_device *ndev)
-{
-	struct xlr_net_priv *priv = netdev_priv(ndev);
-	u32 regval;
-
-	regval = xlr_nae_rdreg(priv->base_addr, R_MAC_FILTER_CONFIG);
-
-	if (ndev->flags & IFF_PROMISC) {
-		regval |= (1 << O_MAC_FILTER_CONFIG__BROADCAST_EN) |
-		(1 << O_MAC_FILTER_CONFIG__PAUSE_FRAME_EN) |
-		(1 << O_MAC_FILTER_CONFIG__ALL_MCAST_EN) |
-		(1 << O_MAC_FILTER_CONFIG__ALL_UCAST_EN);
-	} else {
-		regval &= ~((1 << O_MAC_FILTER_CONFIG__PAUSE_FRAME_EN) |
-		(1 << O_MAC_FILTER_CONFIG__ALL_UCAST_EN));
-	}
-
-	xlr_nae_wreg(priv->base_addr, R_MAC_FILTER_CONFIG, regval);
-}
-
-static void xlr_stats(struct net_device *ndev, struct rtnl_link_stats64 *stats)
-{
-	struct xlr_net_priv *priv = netdev_priv(ndev);
-
-	stats->rx_packets = xlr_nae_rdreg(priv->base_addr, RX_PACKET_COUNTER);
-	stats->tx_packets = xlr_nae_rdreg(priv->base_addr, TX_PACKET_COUNTER);
-	stats->rx_bytes = xlr_nae_rdreg(priv->base_addr, RX_BYTE_COUNTER);
-	stats->tx_bytes = xlr_nae_rdreg(priv->base_addr, TX_BYTE_COUNTER);
-	stats->tx_errors = xlr_nae_rdreg(priv->base_addr, TX_FCS_ERROR_COUNTER);
-	stats->rx_dropped = xlr_nae_rdreg(priv->base_addr,
-					  RX_DROP_PACKET_COUNTER);
-	stats->tx_dropped = xlr_nae_rdreg(priv->base_addr,
-					  TX_DROP_FRAME_COUNTER);
-
-	stats->multicast = xlr_nae_rdreg(priv->base_addr,
-					 RX_MULTICAST_PACKET_COUNTER);
-	stats->collisions = xlr_nae_rdreg(priv->base_addr,
-					  TX_TOTAL_COLLISION_COUNTER);
-
-	stats->rx_length_errors = xlr_nae_rdreg(priv->base_addr,
-						RX_FRAME_LENGTH_ERROR_COUNTER);
-	stats->rx_over_errors = xlr_nae_rdreg(priv->base_addr,
-					      RX_DROP_PACKET_COUNTER);
-	stats->rx_crc_errors = xlr_nae_rdreg(priv->base_addr,
-					     RX_FCS_ERROR_COUNTER);
-	stats->rx_frame_errors = xlr_nae_rdreg(priv->base_addr,
-					       RX_ALIGNMENT_ERROR_COUNTER);
-
-	stats->rx_fifo_errors = xlr_nae_rdreg(priv->base_addr,
-					      RX_DROP_PACKET_COUNTER);
-	stats->rx_missed_errors = xlr_nae_rdreg(priv->base_addr,
-						RX_CARRIER_SENSE_ERROR_COUNTER);
-
-	stats->rx_errors = (stats->rx_over_errors + stats->rx_crc_errors +
-			    stats->rx_frame_errors + stats->rx_fifo_errors +
-			    stats->rx_missed_errors);
-
-	stats->tx_aborted_errors = xlr_nae_rdreg(priv->base_addr,
-						 TX_EXCESSIVE_COLLISION_PACKET_COUNTER);
-	stats->tx_carrier_errors = xlr_nae_rdreg(priv->base_addr,
-						 TX_DROP_FRAME_COUNTER);
-	stats->tx_fifo_errors = xlr_nae_rdreg(priv->base_addr,
-					      TX_DROP_FRAME_COUNTER);
-}
-
-static const struct net_device_ops xlr_netdev_ops = {
-	.ndo_open = xlr_net_open,
-	.ndo_stop = xlr_net_stop,
-	.ndo_start_xmit = xlr_net_start_xmit,
-	.ndo_select_queue = dev_pick_tx_cpu_id,
-	.ndo_set_mac_address = xlr_net_set_mac_addr,
-	.ndo_set_rx_mode = xlr_set_rx_mode,
-	.ndo_get_stats64 = xlr_stats,
-};
-
-/*
- * Gmac init
- */
-static void *xlr_config_spill(struct xlr_net_priv *priv, int reg_start_0,
-			      int reg_start_1, int reg_size, int size)
-{
-	void *spill;
-	u32 *base;
-	unsigned long phys_addr;
-	u32 spill_size;
-
-	base = priv->base_addr;
-	spill_size = size;
-	spill = kmalloc(spill_size + SMP_CACHE_BYTES, GFP_KERNEL);
-	if (!spill)
-		return ZERO_SIZE_PTR;
-
-	spill = PTR_ALIGN(spill, SMP_CACHE_BYTES);
-	phys_addr = virt_to_phys(spill);
-	dev_dbg(&priv->ndev->dev, "Allocated spill %d bytes at %lx\n",
-		size, phys_addr);
-	xlr_nae_wreg(base, reg_start_0, (phys_addr >> 5) & 0xffffffff);
-	xlr_nae_wreg(base, reg_start_1, ((u64)phys_addr >> 37) & 0x07);
-	xlr_nae_wreg(base, reg_size, spill_size);
-
-	return spill;
-}
-
-/*
- * Configure the 6 FIFO's that are used by the network accelarator to
- * communicate with the rest of the XLx device. 4 of the FIFO's are for
- * packets from NA --> cpu (called Class FIFO's) and 2 are for feeding
- * the NA with free descriptors.
- */
-static void xlr_config_fifo_spill_area(struct xlr_net_priv *priv)
-{
-	priv->frin_spill = xlr_config_spill(priv,
-					    R_REG_FRIN_SPILL_MEM_START_0,
-					    R_REG_FRIN_SPILL_MEM_START_1,
-					    R_REG_FRIN_SPILL_MEM_SIZE,
-					    MAX_FRIN_SPILL * sizeof(u64));
-	priv->frout_spill = xlr_config_spill(priv,
-					     R_FROUT_SPILL_MEM_START_0,
-					     R_FROUT_SPILL_MEM_START_1,
-					     R_FROUT_SPILL_MEM_SIZE,
-					     MAX_FROUT_SPILL * sizeof(u64));
-	priv->class_0_spill = xlr_config_spill(priv,
-					       R_CLASS0_SPILL_MEM_START_0,
-					       R_CLASS0_SPILL_MEM_START_1,
-					       R_CLASS0_SPILL_MEM_SIZE,
-					       MAX_CLASS_0_SPILL * sizeof(u64));
-	priv->class_1_spill = xlr_config_spill(priv,
-					       R_CLASS1_SPILL_MEM_START_0,
-					       R_CLASS1_SPILL_MEM_START_1,
-					       R_CLASS1_SPILL_MEM_SIZE,
-					       MAX_CLASS_1_SPILL * sizeof(u64));
-	priv->class_2_spill = xlr_config_spill(priv,
-					       R_CLASS2_SPILL_MEM_START_0,
-					       R_CLASS2_SPILL_MEM_START_1,
-					       R_CLASS2_SPILL_MEM_SIZE,
-					       MAX_CLASS_2_SPILL * sizeof(u64));
-	priv->class_3_spill = xlr_config_spill(priv,
-					       R_CLASS3_SPILL_MEM_START_0,
-					       R_CLASS3_SPILL_MEM_START_1,
-					       R_CLASS3_SPILL_MEM_SIZE,
-					       MAX_CLASS_3_SPILL * sizeof(u64));
-}
-
-/*
- * Configure PDE to Round-Robin distribution of packets to the
- * available cpu
- */
-static void xlr_config_pde(struct xlr_net_priv *priv)
-{
-	int i = 0;
-	u64 bkt_map = 0;
-
-	/* Each core has 8 buckets(station) */
-	for (i = 0; i < hweight32(priv->nd->cpu_mask); i++)
-		bkt_map |= (0xff << (i * 8));
-
-	xlr_nae_wreg(priv->base_addr, R_PDE_CLASS_0, (bkt_map & 0xffffffff));
-	xlr_nae_wreg(priv->base_addr, R_PDE_CLASS_0 + 1,
-		     ((bkt_map >> 32) & 0xffffffff));
-
-	xlr_nae_wreg(priv->base_addr, R_PDE_CLASS_1, (bkt_map & 0xffffffff));
-	xlr_nae_wreg(priv->base_addr, R_PDE_CLASS_1 + 1,
-		     ((bkt_map >> 32) & 0xffffffff));
-
-	xlr_nae_wreg(priv->base_addr, R_PDE_CLASS_2, (bkt_map & 0xffffffff));
-	xlr_nae_wreg(priv->base_addr, R_PDE_CLASS_2 + 1,
-		     ((bkt_map >> 32) & 0xffffffff));
-
-	xlr_nae_wreg(priv->base_addr, R_PDE_CLASS_3, (bkt_map & 0xffffffff));
-	xlr_nae_wreg(priv->base_addr, R_PDE_CLASS_3 + 1,
-		     ((bkt_map >> 32) & 0xffffffff));
-}
-
-/*
- * Setup the Message ring credits, bucket size and other
- * common configuration
- */
-static int xlr_config_common(struct xlr_net_priv *priv)
-{
-	struct xlr_fmn_info *gmac = priv->nd->gmac_fmn_info;
-	int start_stn_id = gmac->start_stn_id;
-	int end_stn_id = gmac->end_stn_id;
-	int *bucket_size = priv->nd->bucket_size;
-	int i, j, err;
-
-	/* Setting non-core MsgBktSize(0x321 - 0x325) */
-	for (i = start_stn_id; i <= end_stn_id; i++) {
-		xlr_nae_wreg(priv->base_addr,
-			     R_GMAC_RFR0_BUCKET_SIZE + i - start_stn_id,
-			     bucket_size[i]);
-	}
-
-	/*
-	 * Setting non-core Credit counter register
-	 * Distributing Gmac's credit to CPU's
-	 */
-	for (i = 0; i < 8; i++) {
-		for (j = 0; j < 8; j++)
-			xlr_nae_wreg(priv->base_addr,
-				     (R_CC_CPU0_0 + (i * 8)) + j,
-				     gmac->credit_config[(i * 8) + j]);
-	}
-
-	xlr_nae_wreg(priv->base_addr, R_MSG_TX_THRESHOLD, 3);
-	xlr_nae_wreg(priv->base_addr, R_DMACR0, 0xffffffff);
-	xlr_nae_wreg(priv->base_addr, R_DMACR1, 0xffffffff);
-	xlr_nae_wreg(priv->base_addr, R_DMACR2, 0xffffffff);
-	xlr_nae_wreg(priv->base_addr, R_DMACR3, 0xffffffff);
-	xlr_nae_wreg(priv->base_addr, R_FREEQCARVE, 0);
-
-	err = xlr_net_fill_rx_ring(priv->ndev);
-	if (err)
-		return err;
-	nlm_register_fmn_handler(start_stn_id, end_stn_id, xlr_net_fmn_handler,
-				 priv->adapter);
-	return 0;
-}
-
-static void xlr_config_translate_table(struct xlr_net_priv *priv)
-{
-	u32 cpu_mask;
-	u32 val;
-	int bkts[32]; /* one bucket is assumed for each cpu */
-	int b1, b2, c1, c2, i, j, k;
-	int use_bkt;
-
-	use_bkt = 0;
-	cpu_mask = priv->nd->cpu_mask;
-
-	pr_info("Using %s-based distribution\n",
-		(use_bkt) ? "bucket" : "class");
-	j = 0;
-	for (i = 0; i < 32; i++) {
-		if ((1 << i) & cpu_mask) {
-			/* for each cpu, mark the 4+threadid bucket */
-			bkts[j] = ((i / 4) * 8) + (i % 4);
-			j++;
-		}
-	}
-
-	/*configure the 128 * 9 Translation table to send to available buckets*/
-	k = 0;
-	c1 = 3;
-	c2 = 0;
-	for (i = 0; i < 64; i++) {
-		/*
-		 * On use_bkt set the b0, b1 are used, else
-		 * the 4 classes are used, here implemented
-		 * a logic to distribute the packets to the
-		 * buckets equally or based on the class
-		 */
-		c1 = (c1 + 1) & 3;
-		c2 = (c1 + 1) & 3;
-		b1 = bkts[k];
-		k = (k + 1) % j;
-		b2 = bkts[k];
-		k = (k + 1) % j;
-
-		val = ((c1 << 23) | (b1 << 17) | (use_bkt << 16) |
-				(c2 << 7) | (b2 << 1) | (use_bkt << 0));
-		dev_dbg(&priv->ndev->dev, "Table[%d] b1=%d b2=%d c1=%d c2=%d\n",
-			i, b1, b2, c1, c2);
-		xlr_nae_wreg(priv->base_addr, R_TRANSLATETABLE + i, val);
-		c1 = c2;
-	}
-}
-
-static void xlr_config_parser(struct xlr_net_priv *priv)
-{
-	u32 val;
-
-	/* Mark it as ETHERNET type */
-	xlr_nae_wreg(priv->base_addr, R_L2TYPE_0, 0x01);
-
-	/* Use 7bit CRChash for flow classification with 127 as CRC polynomial*/
-	xlr_nae_wreg(priv->base_addr, R_PARSERCONFIGREG,
-		     ((0x7f << 8) | (1 << 1)));
-
-	/* configure the parser : L2 Type is configured in the bootloader */
-	/* extract IP: src, dest protocol */
-	xlr_nae_wreg(priv->base_addr, R_L3CTABLE,
-		     (9 << 20) | (1 << 19) | (1 << 18) | (0x01 << 16) |
-		     (0x0800 << 0));
-	xlr_nae_wreg(priv->base_addr, R_L3CTABLE + 1,
-		     (9 << 25) | (1 << 21) | (12 << 14) | (4 << 10) |
-		     (16 << 4) | 4);
-
-	/* Configure to extract SRC port and Dest port for TCP and UDP pkts */
-	xlr_nae_wreg(priv->base_addr, R_L4CTABLE, 6);
-	xlr_nae_wreg(priv->base_addr, R_L4CTABLE + 2, 17);
-	val = ((0 << 21) | (2 << 17) | (2 << 11) | (2 << 7));
-	xlr_nae_wreg(priv->base_addr, R_L4CTABLE + 1, val);
-	xlr_nae_wreg(priv->base_addr, R_L4CTABLE + 3, val);
-
-	xlr_config_translate_table(priv);
-}
-
-static int xlr_phy_write(u32 *base_addr, int phy_addr, int regnum, u16 val)
-{
-	unsigned long timeout, stoptime, checktime;
-	int timedout;
-
-	/* 100ms timeout*/
-	timeout = msecs_to_jiffies(100);
-	stoptime = jiffies + timeout;
-	timedout = 0;
-
-	xlr_nae_wreg(base_addr, R_MII_MGMT_ADDRESS, (phy_addr << 8) | regnum);
-
-	/* Write the data which starts the write cycle */
-	xlr_nae_wreg(base_addr, R_MII_MGMT_WRITE_DATA, (u32)val);
-
-	/* poll for the read cycle to complete */
-	while (!timedout) {
-		checktime = jiffies;
-		if (xlr_nae_rdreg(base_addr, R_MII_MGMT_INDICATORS) == 0)
-			break;
-		timedout = time_after(checktime, stoptime);
-	}
-	if (timedout) {
-		pr_info("Phy device write err: device busy");
-		return -EBUSY;
-	}
-
-	return 0;
-}
-
-static int xlr_phy_read(u32 *base_addr, int phy_addr, int regnum)
-{
-	unsigned long timeout, stoptime, checktime;
-	int timedout;
-
-	/* 100ms timeout*/
-	timeout = msecs_to_jiffies(100);
-	stoptime = jiffies + timeout;
-	timedout = 0;
-
-	/* setup the phy reg to be used */
-	xlr_nae_wreg(base_addr, R_MII_MGMT_ADDRESS,
-		     (phy_addr << 8) | (regnum << 0));
-
-	/* Issue the read command */
-	xlr_nae_wreg(base_addr, R_MII_MGMT_COMMAND,
-		     (1 << O_MII_MGMT_COMMAND__rstat));
-
-	/* poll for the read cycle to complete */
-	while (!timedout) {
-		checktime = jiffies;
-		if (xlr_nae_rdreg(base_addr, R_MII_MGMT_INDICATORS) == 0)
-			break;
-		timedout = time_after(checktime, stoptime);
-	}
-	if (timedout) {
-		pr_info("Phy device read err: device busy");
-		return -EBUSY;
-	}
-
-	/* clear the read cycle */
-	xlr_nae_wreg(base_addr, R_MII_MGMT_COMMAND, 0);
-
-	/* Read the data */
-	return xlr_nae_rdreg(base_addr, R_MII_MGMT_STATUS);
-}
-
-static int xlr_mii_write(struct mii_bus *bus, int phy_addr, int regnum, u16 val)
-{
-	struct xlr_net_priv *priv = bus->priv;
-	int ret;
-
-	ret = xlr_phy_write(priv->mii_addr, phy_addr, regnum, val);
-	dev_dbg(&priv->ndev->dev, "mii_write phy %d : %d <- %x [%x]\n",
-		phy_addr, regnum, val, ret);
-	return ret;
-}
-
-static int xlr_mii_read(struct mii_bus *bus, int phy_addr, int regnum)
-{
-	struct xlr_net_priv *priv = bus->priv;
-	int ret;
-
-	ret =  xlr_phy_read(priv->mii_addr, phy_addr, regnum);
-	dev_dbg(&priv->ndev->dev, "mii_read phy %d : %d [%x]\n",
-		phy_addr, regnum, ret);
-	return ret;
-}
-
-/*
- * XLR ports are RGMII. XLS ports are SGMII mostly except the port0,
- * which can be configured either SGMII or RGMII, considered SGMII
- * by default, if board setup to RGMII the port_type need to set
- * accordingly.Serdes and PCS layer need to configured for SGMII
- */
-static void xlr_sgmii_init(struct xlr_net_priv *priv)
-{
-	int phy;
-
-	xlr_phy_write(priv->serdes_addr, 26, 0, 0x6DB0);
-	xlr_phy_write(priv->serdes_addr, 26, 1, 0xFFFF);
-	xlr_phy_write(priv->serdes_addr, 26, 2, 0xB6D0);
-	xlr_phy_write(priv->serdes_addr, 26, 3, 0x00FF);
-	xlr_phy_write(priv->serdes_addr, 26, 4, 0x0000);
-	xlr_phy_write(priv->serdes_addr, 26, 5, 0x0000);
-	xlr_phy_write(priv->serdes_addr, 26, 6, 0x0005);
-	xlr_phy_write(priv->serdes_addr, 26, 7, 0x0001);
-	xlr_phy_write(priv->serdes_addr, 26, 8, 0x0000);
-	xlr_phy_write(priv->serdes_addr, 26, 9, 0x0000);
-	xlr_phy_write(priv->serdes_addr, 26, 10, 0x0000);
-
-	/* program  GPIO values for serdes init parameters */
-	xlr_nae_wreg(priv->gpio_addr, 0x20, 0x7e6802);
-	xlr_nae_wreg(priv->gpio_addr, 0x10, 0x7104);
-
-	xlr_nae_wreg(priv->gpio_addr, 0x22, 0x7e6802);
-	xlr_nae_wreg(priv->gpio_addr, 0x21, 0x7104);
-
-	/* enable autoneg - more magic */
-	phy = priv->phy_addr % 4 + 27;
-	xlr_phy_write(priv->pcs_addr, phy, 0, 0x1000);
-	xlr_phy_write(priv->pcs_addr, phy, 0, 0x0200);
-}
-
-void xlr_set_gmac_speed(struct xlr_net_priv *priv)
-{
-	struct phy_device *phydev = xlr_get_phydev(priv);
-	int speed;
-
-	if (phydev->interface == PHY_INTERFACE_MODE_SGMII)
-		xlr_sgmii_init(priv);
-
-	if (phydev->speed != priv->phy_speed) {
-		speed = phydev->speed;
-		if (speed == SPEED_1000) {
-			/* Set interface to Byte mode */
-			xlr_nae_wreg(priv->base_addr, R_MAC_CONFIG_2, 0x7217);
-			priv->phy_speed = speed;
-		} else if (speed == SPEED_100 || speed == SPEED_10) {
-			/* Set interface to Nibble mode */
-			xlr_nae_wreg(priv->base_addr, R_MAC_CONFIG_2, 0x7117);
-			priv->phy_speed = speed;
-		}
-		/* Set SGMII speed in Interface control reg */
-		if (phydev->interface == PHY_INTERFACE_MODE_SGMII) {
-			if (speed == SPEED_10)
-				xlr_nae_wreg(priv->base_addr,
-					     R_INTERFACE_CONTROL,
-					     SGMII_SPEED_10);
-			if (speed == SPEED_100)
-				xlr_nae_wreg(priv->base_addr,
-					     R_INTERFACE_CONTROL,
-					     SGMII_SPEED_100);
-			if (speed == SPEED_1000)
-				xlr_nae_wreg(priv->base_addr,
-					     R_INTERFACE_CONTROL,
-					     SGMII_SPEED_1000);
-		}
-		if (speed == SPEED_10)
-			xlr_nae_wreg(priv->base_addr, R_CORECONTROL, 0x2);
-		if (speed == SPEED_100)
-			xlr_nae_wreg(priv->base_addr, R_CORECONTROL, 0x1);
-		if (speed == SPEED_1000)
-			xlr_nae_wreg(priv->base_addr, R_CORECONTROL, 0x0);
-	}
-	pr_info("gmac%d : %dMbps\n", priv->port_id, priv->phy_speed);
-}
-
-static void xlr_gmac_link_adjust(struct net_device *ndev)
-{
-	struct xlr_net_priv *priv = netdev_priv(ndev);
-	struct phy_device *phydev = xlr_get_phydev(priv);
-	u32 intreg;
-
-	intreg = xlr_nae_rdreg(priv->base_addr, R_INTREG);
-	if (phydev->link) {
-		if (phydev->speed != priv->phy_speed) {
-			xlr_set_gmac_speed(priv);
-			pr_info("gmac%d : Link up\n", priv->port_id);
-		}
-	} else {
-		xlr_set_gmac_speed(priv);
-		pr_info("gmac%d : Link down\n", priv->port_id);
-	}
-}
-
-static int xlr_mii_probe(struct xlr_net_priv *priv)
-{
-	struct phy_device *phydev = xlr_get_phydev(priv);
-
-	if (!phydev) {
-		pr_err("no PHY found on phy_addr %d\n", priv->phy_addr);
-		return -ENODEV;
-	}
-
-	/* Attach MAC to PHY */
-	phydev = phy_connect(priv->ndev, phydev_name(phydev),
-			     xlr_gmac_link_adjust, priv->nd->phy_interface);
-
-	if (IS_ERR(phydev)) {
-		pr_err("could not attach PHY\n");
-		return PTR_ERR(phydev);
-	}
-	phydev->supported &= (ADVERTISED_10baseT_Full
-				| ADVERTISED_10baseT_Half
-				| ADVERTISED_100baseT_Full
-				| ADVERTISED_100baseT_Half
-				| ADVERTISED_1000baseT_Full
-				| ADVERTISED_Autoneg
-				| ADVERTISED_MII);
-
-	phydev->advertising = phydev->supported;
-	phy_attached_info(phydev);
-	return 0;
-}
-
-static int xlr_setup_mdio(struct xlr_net_priv *priv,
-			  struct platform_device *pdev)
-{
-	int err;
-
-	priv->mii_bus = mdiobus_alloc();
-	if (!priv->mii_bus) {
-		pr_err("mdiobus alloc failed\n");
-		return -ENOMEM;
-	}
-
-	priv->mii_bus->priv = priv;
-	priv->mii_bus->name = "xlr-mdio";
-	snprintf(priv->mii_bus->id, MII_BUS_ID_SIZE, "%s-%d",
-		 priv->mii_bus->name, priv->port_id);
-	priv->mii_bus->read = xlr_mii_read;
-	priv->mii_bus->write = xlr_mii_write;
-	priv->mii_bus->parent = &pdev->dev;
-
-	/* Scan only the enabled address */
-	priv->mii_bus->phy_mask = ~(1 << priv->phy_addr);
-
-	/* setting clock divisor to 54 */
-	xlr_nae_wreg(priv->base_addr, R_MII_MGMT_CONFIG, 0x7);
-
-	err = mdiobus_register(priv->mii_bus);
-	if (err) {
-		mdiobus_free(priv->mii_bus);
-		pr_err("mdio bus registration failed\n");
-		return err;
-	}
-
-	pr_info("Registered mdio bus id : %s\n", priv->mii_bus->id);
-	err = xlr_mii_probe(priv);
-	if (err) {
-		mdiobus_free(priv->mii_bus);
-		return err;
-	}
-	return 0;
-}
-
-static void xlr_port_enable(struct xlr_net_priv *priv)
-{
-	u32 prid = (read_c0_prid() & 0xf000);
-
-	/* Setup MAC_CONFIG reg if (xls & rgmii) */
-	if ((prid == 0x8000 || prid == 0x4000 || prid == 0xc000) &&
-	    priv->nd->phy_interface == PHY_INTERFACE_MODE_RGMII)
-		xlr_reg_update(priv->base_addr, R_RX_CONTROL,
-			       (1 << O_RX_CONTROL__RGMII),
-			       (1 << O_RX_CONTROL__RGMII));
-
-	/* Rx Tx enable */
-	xlr_reg_update(priv->base_addr, R_MAC_CONFIG_1,
-		       ((1 << O_MAC_CONFIG_1__rxen) |
-			(1 << O_MAC_CONFIG_1__txen) |
-			(1 << O_MAC_CONFIG_1__rxfc) |
-			(1 << O_MAC_CONFIG_1__txfc)),
-		       ((1 << O_MAC_CONFIG_1__rxen) |
-			(1 << O_MAC_CONFIG_1__txen) |
-			(1 << O_MAC_CONFIG_1__rxfc) |
-			(1 << O_MAC_CONFIG_1__txfc)));
-
-	/* Setup tx control reg */
-	xlr_reg_update(priv->base_addr, R_TX_CONTROL,
-		       ((1 << O_TX_CONTROL__TXENABLE) |
-		       (512 << O_TX_CONTROL__TXTHRESHOLD)), 0x3fff);
-
-	/* Setup rx control reg */
-	xlr_reg_update(priv->base_addr, R_RX_CONTROL,
-		       1 << O_RX_CONTROL__RXENABLE,
-		       1 << O_RX_CONTROL__RXENABLE);
-}
-
-static void xlr_port_disable(struct xlr_net_priv *priv)
-{
-	/* Setup MAC_CONFIG reg */
-	/* Rx Tx disable*/
-	xlr_reg_update(priv->base_addr, R_MAC_CONFIG_1,
-		       ((1 << O_MAC_CONFIG_1__rxen) |
-			(1 << O_MAC_CONFIG_1__txen) |
-			(1 << O_MAC_CONFIG_1__rxfc) |
-			(1 << O_MAC_CONFIG_1__txfc)), 0x0);
-
-	/* Setup tx control reg */
-	xlr_reg_update(priv->base_addr, R_TX_CONTROL,
-		       ((1 << O_TX_CONTROL__TXENABLE) |
-		       (512 << O_TX_CONTROL__TXTHRESHOLD)), 0);
-
-	/* Setup rx control reg */
-	xlr_reg_update(priv->base_addr, R_RX_CONTROL,
-		       1 << O_RX_CONTROL__RXENABLE, 0);
-}
-
-/*
- * Initialization of gmac
- */
-static int xlr_gmac_init(struct xlr_net_priv *priv,
-			 struct platform_device *pdev)
-{
-	int ret;
-
-	pr_info("Initializing the gmac%d\n", priv->port_id);
-
-	xlr_port_disable(priv);
-
-	xlr_nae_wreg(priv->base_addr, R_DESC_PACK_CTRL,
-		     (1 << O_DESC_PACK_CTRL__MAXENTRY) |
-		     (BYTE_OFFSET << O_DESC_PACK_CTRL__BYTEOFFSET) |
-		     (1600 << O_DESC_PACK_CTRL__REGULARSIZE));
-
-	ret = xlr_setup_mdio(priv, pdev);
-	if (ret)
-		return ret;
-	xlr_port_enable(priv);
-
-	/* Enable Full-duplex/1000Mbps/CRC */
-	xlr_nae_wreg(priv->base_addr, R_MAC_CONFIG_2, 0x7217);
-	/* speed 2.5Mhz */
-	xlr_nae_wreg(priv->base_addr, R_CORECONTROL, 0x02);
-	/* Setup Interrupt mask reg */
-	xlr_nae_wreg(priv->base_addr, R_INTMASK, (1 << O_INTMASK__TXILLEGAL) |
-		     (1 << O_INTMASK__MDINT) | (1 << O_INTMASK__TXFETCHERROR) |
-		     (1 << O_INTMASK__P2PSPILLECC) | (1 << O_INTMASK__TAGFULL) |
-		     (1 << O_INTMASK__UNDERRUN) | (1 << O_INTMASK__ABORT));
-
-	/* Clear all stats */
-	xlr_reg_update(priv->base_addr, R_STATCTRL, 0, 1 << O_STATCTRL__CLRCNT);
-	xlr_reg_update(priv->base_addr, R_STATCTRL, 1 << 2, 1 << 2);
-	return 0;
-}
-
-static int xlr_net_probe(struct platform_device *pdev)
-{
-	struct xlr_net_priv *priv = NULL;
-	struct net_device *ndev;
-	struct resource *res;
-	struct xlr_adapter *adapter;
-	int err, port;
-
-	pr_info("XLR/XLS Ethernet Driver controller %d\n", pdev->id);
-	/*
-	 * Allocate our adapter data structure and attach it to the device.
-	 */
-	adapter = devm_kzalloc(&pdev->dev, sizeof(*adapter), GFP_KERNEL);
-	if (!adapter)
-		return -ENOMEM;
-
-	/*
-	 * XLR and XLS have 1 and 2 NAE controller respectively
-	 * Each controller has 4 gmac ports, mapping each controller
-	 * under one parent device, 4 gmac ports under one device.
-	 */
-	for (port = 0; port < pdev->num_resources / 2; port++) {
-		ndev = alloc_etherdev_mq(sizeof(struct xlr_net_priv), 32);
-		if (!ndev) {
-			dev_err(&pdev->dev,
-				"Allocation of Ethernet device failed\n");
-			return -ENOMEM;
-		}
-
-		priv = netdev_priv(ndev);
-		priv->pdev = pdev;
-		priv->ndev = ndev;
-		priv->port_id = (pdev->id * 4) + port;
-		priv->nd = (struct xlr_net_data *)pdev->dev.platform_data;
-		priv->base_addr = devm_platform_ioremap_resource(pdev, port);
-		if (IS_ERR(priv->base_addr)) {
-			err = PTR_ERR(priv->base_addr);
-			goto err_gmac;
-		}
-		priv->adapter = adapter;
-		adapter->netdev[port] = ndev;
-
-		res = platform_get_resource(pdev, IORESOURCE_IRQ, port);
-		if (!res) {
-			dev_err(&pdev->dev, "No irq resource for MAC %d\n",
-				priv->port_id);
-			err = -ENODEV;
-			goto err_gmac;
-		}
-
-		ndev->irq = res->start;
-
-		priv->phy_addr = priv->nd->phy_addr[port];
-		priv->tx_stnid = priv->nd->tx_stnid[port];
-		priv->mii_addr = priv->nd->mii_addr;
-		priv->serdes_addr = priv->nd->serdes_addr;
-		priv->pcs_addr = priv->nd->pcs_addr;
-		priv->gpio_addr = priv->nd->gpio_addr;
-
-		ndev->netdev_ops = &xlr_netdev_ops;
-		ndev->watchdog_timeo = HZ;
-
-		/* Setup Mac address and Rx mode */
-		eth_hw_addr_random(ndev);
-		xlr_hw_set_mac_addr(ndev);
-		xlr_set_rx_mode(ndev);
-
-		priv->num_rx_desc += MAX_NUM_DESC_SPILL;
-		ndev->ethtool_ops = &xlr_ethtool_ops;
-		SET_NETDEV_DEV(ndev, &pdev->dev);
-
-		xlr_config_fifo_spill_area(priv);
-		/* Configure PDE to Round-Robin pkt distribution */
-		xlr_config_pde(priv);
-		xlr_config_parser(priv);
-
-		/* Call init with respect to port */
-		if (strcmp(res->name, "gmac") == 0) {
-			err = xlr_gmac_init(priv, pdev);
-			if (err) {
-				dev_err(&pdev->dev, "gmac%d init failed\n",
-					priv->port_id);
-				goto err_gmac;
-			}
-		}
-
-		if (priv->port_id == 0 || priv->port_id == 4) {
-			err = xlr_config_common(priv);
-			if (err)
-				goto err_netdev;
-		}
-
-		err = register_netdev(ndev);
-		if (err) {
-			dev_err(&pdev->dev,
-				"Registering netdev failed for gmac%d\n",
-				priv->port_id);
-			goto err_netdev;
-		}
-		platform_set_drvdata(pdev, priv);
-	}
-
-	return 0;
-
-err_netdev:
-	mdiobus_free(priv->mii_bus);
-err_gmac:
-	free_netdev(ndev);
-	return err;
-}
-
-static int xlr_net_remove(struct platform_device *pdev)
-{
-	struct xlr_net_priv *priv = platform_get_drvdata(pdev);
-
-	unregister_netdev(priv->ndev);
-	mdiobus_unregister(priv->mii_bus);
-	mdiobus_free(priv->mii_bus);
-	free_netdev(priv->ndev);
-	return 0;
-}
-
-static struct platform_driver xlr_net_driver = {
-	.probe		= xlr_net_probe,
-	.remove		= xlr_net_remove,
-	.driver		= {
-		.name	= "xlr-net",
-	},
-};
-
-module_platform_driver(xlr_net_driver);
-
-MODULE_AUTHOR("Ganesan Ramalingam <ganesanr@broadcom.com>");
-MODULE_DESCRIPTION("Ethernet driver for Netlogic XLR/XLS");
-MODULE_LICENSE("Dual BSD/GPL");
-MODULE_ALIAS("platform:xlr-net");
diff --git a/drivers/staging/netlogic/xlr_net.h b/drivers/staging/netlogic/xlr_net.h
deleted file mode 100644
index 8365b744f9b3..000000000000
--- a/drivers/staging/netlogic/xlr_net.h
+++ /dev/null
@@ -1,1079 +0,0 @@
-/* SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) */
-/*
- * Copyright (c) 2003-2012 Broadcom Corporation
- * All Rights Reserved
- */
-
-/* #define MAC_SPLIT_MODE */
-
-#define MAC_SPACING                 0x400
-#define XGMAC_SPACING               0x400
-
-/* PE-MCXMAC register and bit field definitions */
-#define R_MAC_CONFIG_1                                              0x00
-#define   O_MAC_CONFIG_1__srst                                      31
-#define   O_MAC_CONFIG_1__simr                                      30
-#define   O_MAC_CONFIG_1__hrrmc                                     18
-#define   W_MAC_CONFIG_1__hrtmc                                      2
-#define   O_MAC_CONFIG_1__hrrfn                                     16
-#define   W_MAC_CONFIG_1__hrtfn                                      2
-#define   O_MAC_CONFIG_1__intlb                                      8
-#define   O_MAC_CONFIG_1__rxfc                                       5
-#define   O_MAC_CONFIG_1__txfc                                       4
-#define   O_MAC_CONFIG_1__srxen                                      3
-#define   O_MAC_CONFIG_1__rxen                                       2
-#define   O_MAC_CONFIG_1__stxen                                      1
-#define   O_MAC_CONFIG_1__txen                                       0
-#define R_MAC_CONFIG_2                                              0x01
-#define   O_MAC_CONFIG_2__prlen                                     12
-#define   W_MAC_CONFIG_2__prlen                                      4
-#define   O_MAC_CONFIG_2__speed                                      8
-#define   W_MAC_CONFIG_2__speed                                      2
-#define   O_MAC_CONFIG_2__hugen                                      5
-#define   O_MAC_CONFIG_2__flchk                                      4
-#define   O_MAC_CONFIG_2__crce                                       1
-#define   O_MAC_CONFIG_2__fulld                                      0
-#define R_IPG_IFG                                                   0x02
-#define   O_IPG_IFG__ipgr1                                          24
-#define   W_IPG_IFG__ipgr1                                           7
-#define   O_IPG_IFG__ipgr2                                          16
-#define   W_IPG_IFG__ipgr2                                           7
-#define   O_IPG_IFG__mifg                                            8
-#define   W_IPG_IFG__mifg                                            8
-#define   O_IPG_IFG__ipgt                                            0
-#define   W_IPG_IFG__ipgt                                            7
-#define R_HALF_DUPLEX                                               0x03
-#define   O_HALF_DUPLEX__abebt                                      24
-#define   W_HALF_DUPLEX__abebt                                       4
-#define   O_HALF_DUPLEX__abebe                                      19
-#define   O_HALF_DUPLEX__bpnb                                       18
-#define   O_HALF_DUPLEX__nobo                                       17
-#define   O_HALF_DUPLEX__edxsdfr                                    16
-#define   O_HALF_DUPLEX__retry                                      12
-#define   W_HALF_DUPLEX__retry                                       4
-#define   O_HALF_DUPLEX__lcol                                        0
-#define   W_HALF_DUPLEX__lcol                                       10
-#define R_MAXIMUM_FRAME_LENGTH                                      0x04
-#define   O_MAXIMUM_FRAME_LENGTH__maxf                               0
-#define   W_MAXIMUM_FRAME_LENGTH__maxf                              16
-#define R_TEST                                                      0x07
-#define   O_TEST__mbof                                               3
-#define   O_TEST__rthdf                                              2
-#define   O_TEST__tpause                                             1
-#define   O_TEST__sstct                                              0
-#define R_MII_MGMT_CONFIG                                           0x08
-#define   O_MII_MGMT_CONFIG__scinc                                   5
-#define   O_MII_MGMT_CONFIG__spre                                    4
-#define   O_MII_MGMT_CONFIG__clks                                    3
-#define   W_MII_MGMT_CONFIG__clks                                    3
-#define R_MII_MGMT_COMMAND                                          0x09
-#define   O_MII_MGMT_COMMAND__scan                                   1
-#define   O_MII_MGMT_COMMAND__rstat                                  0
-#define R_MII_MGMT_ADDRESS                                          0x0A
-#define   O_MII_MGMT_ADDRESS__fiad                                   8
-#define   W_MII_MGMT_ADDRESS__fiad                                   5
-#define   O_MII_MGMT_ADDRESS__fgad                                   5
-#define   W_MII_MGMT_ADDRESS__fgad                                   0
-#define R_MII_MGMT_WRITE_DATA                                       0x0B
-#define   O_MII_MGMT_WRITE_DATA__ctld                                0
-#define   W_MII_MGMT_WRITE_DATA__ctld                               16
-#define R_MII_MGMT_STATUS                                           0x0C
-#define R_MII_MGMT_INDICATORS                                       0x0D
-#define   O_MII_MGMT_INDICATORS__nvalid                              2
-#define   O_MII_MGMT_INDICATORS__scan                                1
-#define   O_MII_MGMT_INDICATORS__busy                                0
-#define R_INTERFACE_CONTROL                                         0x0E
-#define   O_INTERFACE_CONTROL__hrstint                              31
-#define   O_INTERFACE_CONTROL__tbimode                              27
-#define   O_INTERFACE_CONTROL__ghdmode                              26
-#define   O_INTERFACE_CONTROL__lhdmode                              25
-#define   O_INTERFACE_CONTROL__phymod                               24
-#define   O_INTERFACE_CONTROL__hrrmi                                23
-#define   O_INTERFACE_CONTROL__rspd                                 16
-#define   O_INTERFACE_CONTROL__hr100                                15
-#define   O_INTERFACE_CONTROL__frcq                                 10
-#define   O_INTERFACE_CONTROL__nocfr                                 9
-#define   O_INTERFACE_CONTROL__dlfct                                 8
-#define   O_INTERFACE_CONTROL__enjab                                 0
-#define R_INTERFACE_STATUS                                         0x0F
-#define   O_INTERFACE_STATUS__xsdfr                                  9
-#define   O_INTERFACE_STATUS__ssrr                                   8
-#define   W_INTERFACE_STATUS__ssrr                                   5
-#define   O_INTERFACE_STATUS__miilf                                  3
-#define   O_INTERFACE_STATUS__locar                                  2
-#define   O_INTERFACE_STATUS__sqerr                                  1
-#define   O_INTERFACE_STATUS__jabber                                 0
-#define R_STATION_ADDRESS_LS                                       0x10
-#define R_STATION_ADDRESS_MS                                       0x11
-
-/* A-XGMAC register and bit field definitions */
-#define R_XGMAC_CONFIG_0    0x00
-#define   O_XGMAC_CONFIG_0__hstmacrst               31
-#define   O_XGMAC_CONFIG_0__hstrstrctl              23
-#define   O_XGMAC_CONFIG_0__hstrstrfn               22
-#define   O_XGMAC_CONFIG_0__hstrsttctl              18
-#define   O_XGMAC_CONFIG_0__hstrsttfn               17
-#define   O_XGMAC_CONFIG_0__hstrstmiim              16
-#define   O_XGMAC_CONFIG_0__hstloopback             8
-#define R_XGMAC_CONFIG_1    0x01
-#define   O_XGMAC_CONFIG_1__hsttctlen               31
-#define   O_XGMAC_CONFIG_1__hsttfen                 30
-#define   O_XGMAC_CONFIG_1__hstrctlen               29
-#define   O_XGMAC_CONFIG_1__hstrfen                 28
-#define   O_XGMAC_CONFIG_1__tfen                    26
-#define   O_XGMAC_CONFIG_1__rfen                    24
-#define   O_XGMAC_CONFIG_1__hstrctlshrtp            12
-#define   O_XGMAC_CONFIG_1__hstdlyfcstx             10
-#define   W_XGMAC_CONFIG_1__hstdlyfcstx              2
-#define   O_XGMAC_CONFIG_1__hstdlyfcsrx              8
-#define   W_XGMAC_CONFIG_1__hstdlyfcsrx              2
-#define   O_XGMAC_CONFIG_1__hstppen                  7
-#define   O_XGMAC_CONFIG_1__hstbytswp                6
-#define   O_XGMAC_CONFIG_1__hstdrplt64               5
-#define   O_XGMAC_CONFIG_1__hstprmscrx               4
-#define   O_XGMAC_CONFIG_1__hstlenchk                3
-#define   O_XGMAC_CONFIG_1__hstgenfcs                2
-#define   O_XGMAC_CONFIG_1__hstpadmode               0
-#define   W_XGMAC_CONFIG_1__hstpadmode               2
-#define R_XGMAC_CONFIG_2    0x02
-#define   O_XGMAC_CONFIG_2__hsttctlfrcp             31
-#define   O_XGMAC_CONFIG_2__hstmlnkflth             27
-#define   O_XGMAC_CONFIG_2__hstalnkflth             26
-#define   O_XGMAC_CONFIG_2__rflnkflt                24
-#define   W_XGMAC_CONFIG_2__rflnkflt                 2
-#define   O_XGMAC_CONFIG_2__hstipgextmod            16
-#define   W_XGMAC_CONFIG_2__hstipgextmod             5
-#define   O_XGMAC_CONFIG_2__hstrctlfrcp             15
-#define   O_XGMAC_CONFIG_2__hstipgexten              5
-#define   O_XGMAC_CONFIG_2__hstmipgext               0
-#define   W_XGMAC_CONFIG_2__hstmipgext               5
-#define R_XGMAC_CONFIG_3    0x03
-#define   O_XGMAC_CONFIG_3__hstfltrfrm              31
-#define   W_XGMAC_CONFIG_3__hstfltrfrm              16
-#define   O_XGMAC_CONFIG_3__hstfltrfrmdc            15
-#define   W_XGMAC_CONFIG_3__hstfltrfrmdc            16
-#define R_XGMAC_STATION_ADDRESS_LS      0x04
-#define   O_XGMAC_STATION_ADDRESS_LS__hstmacadr0    0
-#define   W_XGMAC_STATION_ADDRESS_LS__hstmacadr0    32
-#define R_XGMAC_STATION_ADDRESS_MS      0x05
-#define R_XGMAC_MAX_FRAME_LEN           0x08
-#define   O_XGMAC_MAX_FRAME_LEN__hstmxfrmwctx       16
-#define   W_XGMAC_MAX_FRAME_LEN__hstmxfrmwctx       14
-#define   O_XGMAC_MAX_FRAME_LEN__hstmxfrmbcrx        0
-#define   W_XGMAC_MAX_FRAME_LEN__hstmxfrmbcrx       16
-#define R_XGMAC_REV_LEVEL               0x0B
-#define   O_XGMAC_REV_LEVEL__revlvl                  0
-#define   W_XGMAC_REV_LEVEL__revlvl                 15
-#define R_XGMAC_MIIM_COMMAND            0x10
-#define   O_XGMAC_MIIM_COMMAND__hstldcmd             3
-#define   O_XGMAC_MIIM_COMMAND__hstmiimcmd           0
-#define   W_XGMAC_MIIM_COMMAND__hstmiimcmd           3
-#define R_XGMAC_MIIM_FILED              0x11
-#define   O_XGMAC_MIIM_FILED__hststfield            30
-#define   W_XGMAC_MIIM_FILED__hststfield             2
-#define   O_XGMAC_MIIM_FILED__hstopfield            28
-#define   W_XGMAC_MIIM_FILED__hstopfield             2
-#define   O_XGMAC_MIIM_FILED__hstphyadx             23
-#define   W_XGMAC_MIIM_FILED__hstphyadx              5
-#define   O_XGMAC_MIIM_FILED__hstregadx             18
-#define   W_XGMAC_MIIM_FILED__hstregadx              5
-#define   O_XGMAC_MIIM_FILED__hsttafield            16
-#define   W_XGMAC_MIIM_FILED__hsttafield             2
-#define   O_XGMAC_MIIM_FILED__miimrddat              0
-#define   W_XGMAC_MIIM_FILED__miimrddat             16
-#define R_XGMAC_MIIM_CONFIG             0x12
-#define   O_XGMAC_MIIM_CONFIG__hstnopram             7
-#define   O_XGMAC_MIIM_CONFIG__hstclkdiv             0
-#define   W_XGMAC_MIIM_CONFIG__hstclkdiv             7
-#define R_XGMAC_MIIM_LINK_FAIL_VECTOR   0x13
-#define   O_XGMAC_MIIM_LINK_FAIL_VECTOR__miimlfvec   0
-#define   W_XGMAC_MIIM_LINK_FAIL_VECTOR__miimlfvec  32
-#define R_XGMAC_MIIM_INDICATOR          0x14
-#define   O_XGMAC_MIIM_INDICATOR__miimphylf          4
-#define   O_XGMAC_MIIM_INDICATOR__miimmoncplt        3
-#define   O_XGMAC_MIIM_INDICATOR__miimmonvld         2
-#define   O_XGMAC_MIIM_INDICATOR__miimmon            1
-#define   O_XGMAC_MIIM_INDICATOR__miimbusy           0
-
-/* GMAC stats registers */
-#define R_RBYT							    0x27
-#define R_RPKT							    0x28
-#define R_RFCS							    0x29
-#define R_RMCA							    0x2A
-#define R_RBCA							    0x2B
-#define R_RXCF							    0x2C
-#define R_RXPF							    0x2D
-#define R_RXUO							    0x2E
-#define R_RALN							    0x2F
-#define R_RFLR							    0x30
-#define R_RCDE							    0x31
-#define R_RCSE							    0x32
-#define R_RUND							    0x33
-#define R_ROVR							    0x34
-#define R_TBYT							    0x38
-#define R_TPKT							    0x39
-#define R_TMCA							    0x3A
-#define R_TBCA							    0x3B
-#define R_TXPF							    0x3C
-#define R_TDFR							    0x3D
-#define R_TEDF							    0x3E
-#define R_TSCL							    0x3F
-#define R_TMCL							    0x40
-#define R_TLCL							    0x41
-#define R_TXCL							    0x42
-#define R_TNCL							    0x43
-#define R_TJBR							    0x46
-#define R_TFCS							    0x47
-#define R_TXCF							    0x48
-#define R_TOVR							    0x49
-#define R_TUND							    0x4A
-#define R_TFRG							    0x4B
-
-/* Glue logic register and bit field definitions */
-#define R_MAC_ADDR0                                                 0x50
-#define R_MAC_ADDR1                                                 0x52
-#define R_MAC_ADDR2                                                 0x54
-#define R_MAC_ADDR3                                                 0x56
-#define R_MAC_ADDR_MASK2                                            0x58
-#define R_MAC_ADDR_MASK3                                            0x5A
-#define R_MAC_FILTER_CONFIG                                         0x5C
-#define   O_MAC_FILTER_CONFIG__BROADCAST_EN                         10
-#define   O_MAC_FILTER_CONFIG__PAUSE_FRAME_EN                       9
-#define   O_MAC_FILTER_CONFIG__ALL_MCAST_EN                         8
-#define   O_MAC_FILTER_CONFIG__ALL_UCAST_EN                         7
-#define   O_MAC_FILTER_CONFIG__HASH_MCAST_EN                        6
-#define   O_MAC_FILTER_CONFIG__HASH_UCAST_EN                        5
-#define   O_MAC_FILTER_CONFIG__ADDR_MATCH_DISC                      4
-#define   O_MAC_FILTER_CONFIG__MAC_ADDR3_VALID                      3
-#define   O_MAC_FILTER_CONFIG__MAC_ADDR2_VALID                      2
-#define   O_MAC_FILTER_CONFIG__MAC_ADDR1_VALID                      1
-#define   O_MAC_FILTER_CONFIG__MAC_ADDR0_VALID                      0
-#define R_HASH_TABLE_VECTOR                                         0x30
-#define R_TX_CONTROL                                                 0x0A0
-#define   O_TX_CONTROL__TX15HALT                                     31
-#define   O_TX_CONTROL__TX14HALT                                     30
-#define   O_TX_CONTROL__TX13HALT                                     29
-#define   O_TX_CONTROL__TX12HALT                                     28
-#define   O_TX_CONTROL__TX11HALT                                     27
-#define   O_TX_CONTROL__TX10HALT                                     26
-#define   O_TX_CONTROL__TX9HALT                                      25
-#define   O_TX_CONTROL__TX8HALT                                      24
-#define   O_TX_CONTROL__TX7HALT                                      23
-#define   O_TX_CONTROL__TX6HALT                                      22
-#define   O_TX_CONTROL__TX5HALT                                      21
-#define   O_TX_CONTROL__TX4HALT                                      20
-#define   O_TX_CONTROL__TX3HALT                                      19
-#define   O_TX_CONTROL__TX2HALT                                      18
-#define   O_TX_CONTROL__TX1HALT                                      17
-#define   O_TX_CONTROL__TX0HALT                                      16
-#define   O_TX_CONTROL__TXIDLE                                       15
-#define   O_TX_CONTROL__TXENABLE                                     14
-#define   O_TX_CONTROL__TXTHRESHOLD                                  0
-#define   W_TX_CONTROL__TXTHRESHOLD                                  14
-#define R_RX_CONTROL                                                 0x0A1
-#define   O_RX_CONTROL__RGMII                                        10
-#define   O_RX_CONTROL__SOFTRESET			             2
-#define   O_RX_CONTROL__RXHALT                                       1
-#define   O_RX_CONTROL__RXENABLE                                     0
-#define R_DESC_PACK_CTRL                                            0x0A2
-#define   O_DESC_PACK_CTRL__BYTEOFFSET                              17
-#define   W_DESC_PACK_CTRL__BYTEOFFSET                              3
-#define   O_DESC_PACK_CTRL__PREPADENABLE                            16
-#define   O_DESC_PACK_CTRL__MAXENTRY                                14
-#define   W_DESC_PACK_CTRL__MAXENTRY                                2
-#define   O_DESC_PACK_CTRL__REGULARSIZE                             0
-#define   W_DESC_PACK_CTRL__REGULARSIZE                             14
-#define R_STATCTRL                                                  0x0A3
-#define   O_STATCTRL__OVERFLOWEN                                    4
-#define   O_STATCTRL__GIG                                           3
-#define   O_STATCTRL__STEN                                          2
-#define   O_STATCTRL__CLRCNT                                        1
-#define   O_STATCTRL__AUTOZ                                         0
-#define R_L2ALLOCCTRL                                               0x0A4
-#define   O_L2ALLOCCTRL__TXL2ALLOCATE                               9
-#define   W_L2ALLOCCTRL__TXL2ALLOCATE                               9
-#define   O_L2ALLOCCTRL__RXL2ALLOCATE                               0
-#define   W_L2ALLOCCTRL__RXL2ALLOCATE                               9
-#define R_INTMASK                                                   0x0A5
-#define   O_INTMASK__SPI4TXERROR                                     28
-#define   O_INTMASK__SPI4RXERROR                                     27
-#define   O_INTMASK__RGMIIHALFDUPCOLLISION                           27
-#define   O_INTMASK__ABORT                                           26
-#define   O_INTMASK__UNDERRUN                                        25
-#define   O_INTMASK__DISCARDPACKET                                   24
-#define   O_INTMASK__ASYNCFIFOFULL                                   23
-#define   O_INTMASK__TAGFULL                                         22
-#define   O_INTMASK__CLASS3FULL                                      21
-#define   O_INTMASK__C3EARLYFULL                                     20
-#define   O_INTMASK__CLASS2FULL                                      19
-#define   O_INTMASK__C2EARLYFULL                                     18
-#define   O_INTMASK__CLASS1FULL                                      17
-#define   O_INTMASK__C1EARLYFULL                                     16
-#define   O_INTMASK__CLASS0FULL                                      15
-#define   O_INTMASK__C0EARLYFULL                                     14
-#define   O_INTMASK__RXDATAFULL                                      13
-#define   O_INTMASK__RXEARLYFULL                                     12
-#define   O_INTMASK__RFREEEMPTY                                      9
-#define   O_INTMASK__RFEARLYEMPTY                                    8
-#define   O_INTMASK__P2PSPILLECC                                     7
-#define   O_INTMASK__FREEDESCFULL                                    5
-#define   O_INTMASK__FREEEARLYFULL                                   4
-#define   O_INTMASK__TXFETCHERROR                                    3
-#define   O_INTMASK__STATCARRY                                       2
-#define   O_INTMASK__MDINT                                           1
-#define   O_INTMASK__TXILLEGAL                                       0
-#define R_INTREG                                                    0x0A6
-#define   O_INTREG__SPI4TXERROR                                     28
-#define   O_INTREG__SPI4RXERROR                                     27
-#define   O_INTREG__RGMIIHALFDUPCOLLISION                           27
-#define   O_INTREG__ABORT                                           26
-#define   O_INTREG__UNDERRUN                                        25
-#define   O_INTREG__DISCARDPACKET                                   24
-#define   O_INTREG__ASYNCFIFOFULL                                   23
-#define   O_INTREG__TAGFULL                                         22
-#define   O_INTREG__CLASS3FULL                                      21
-#define   O_INTREG__C3EARLYFULL                                     20
-#define   O_INTREG__CLASS2FULL                                      19
-#define   O_INTREG__C2EARLYFULL                                     18
-#define   O_INTREG__CLASS1FULL                                      17
-#define   O_INTREG__C1EARLYFULL                                     16
-#define   O_INTREG__CLASS0FULL                                      15
-#define   O_INTREG__C0EARLYFULL                                     14
-#define   O_INTREG__RXDATAFULL                                      13
-#define   O_INTREG__RXEARLYFULL                                     12
-#define   O_INTREG__RFREEEMPTY                                      9
-#define   O_INTREG__RFEARLYEMPTY                                    8
-#define   O_INTREG__P2PSPILLECC                                     7
-#define   O_INTREG__FREEDESCFULL                                    5
-#define   O_INTREG__FREEEARLYFULL                                   4
-#define   O_INTREG__TXFETCHERROR                                    3
-#define   O_INTREG__STATCARRY                                       2
-#define   O_INTREG__MDINT                                           1
-#define   O_INTREG__TXILLEGAL                                       0
-#define R_TXRETRY                                                   0x0A7
-#define   O_TXRETRY__COLLISIONRETRY                                 6
-#define   O_TXRETRY__BUSERRORRETRY                                  5
-#define   O_TXRETRY__UNDERRUNRETRY                                  4
-#define   O_TXRETRY__RETRIES                                        0
-#define   W_TXRETRY__RETRIES                                        4
-#define R_CORECONTROL                                               0x0A8
-#define   O_CORECONTROL__ERRORTHREAD                                4
-#define   W_CORECONTROL__ERRORTHREAD                                7
-#define   O_CORECONTROL__SHUTDOWN                                   2
-#define   O_CORECONTROL__SPEED                                      0
-#define   W_CORECONTROL__SPEED                                      2
-#define R_BYTEOFFSET0                                               0x0A9
-#define R_BYTEOFFSET1                                               0x0AA
-#define R_L2TYPE_0                                                  0x0F0
-#define   O_L2TYPE__EXTRAHDRPROTOSIZE                               26
-#define   W_L2TYPE__EXTRAHDRPROTOSIZE                               5
-#define   O_L2TYPE__EXTRAHDRPROTOOFFSET                             20
-#define   W_L2TYPE__EXTRAHDRPROTOOFFSET                             6
-#define   O_L2TYPE__EXTRAHEADERSIZE                                 14
-#define   W_L2TYPE__EXTRAHEADERSIZE                                 6
-#define   O_L2TYPE__PROTOOFFSET                                     8
-#define   W_L2TYPE__PROTOOFFSET                                     6
-#define   O_L2TYPE__L2HDROFFSET                                     2
-#define   W_L2TYPE__L2HDROFFSET                                     6
-#define   O_L2TYPE__L2PROTO                                         0
-#define   W_L2TYPE__L2PROTO                                         2
-#define R_L2TYPE_1                                                  0xF0
-#define R_L2TYPE_2                                                  0xF0
-#define R_L2TYPE_3                                                  0xF0
-#define R_PARSERCONFIGREG                                           0x100
-#define   O_PARSERCONFIGREG__CRCHASHPOLY                            8
-#define   W_PARSERCONFIGREG__CRCHASHPOLY                            7
-#define   O_PARSERCONFIGREG__PREPADOFFSET                           4
-#define   W_PARSERCONFIGREG__PREPADOFFSET                           4
-#define   O_PARSERCONFIGREG__USECAM                                 2
-#define   O_PARSERCONFIGREG__USEHASH                                1
-#define   O_PARSERCONFIGREG__USEPROTO                               0
-#define R_L3CTABLE                                                  0x140
-#define   O_L3CTABLE__OFFSET0                                       25
-#define   W_L3CTABLE__OFFSET0                                       7
-#define   O_L3CTABLE__LEN0                                          21
-#define   W_L3CTABLE__LEN0                                          4
-#define   O_L3CTABLE__OFFSET1                                       14
-#define   W_L3CTABLE__OFFSET1                                       7
-#define   O_L3CTABLE__LEN1                                          10
-#define   W_L3CTABLE__LEN1                                          4
-#define   O_L3CTABLE__OFFSET2                                       4
-#define   W_L3CTABLE__OFFSET2                                       6
-#define   O_L3CTABLE__LEN2                                          0
-#define   W_L3CTABLE__LEN2                                          4
-#define   O_L3CTABLE__L3HDROFFSET                                   26
-#define   W_L3CTABLE__L3HDROFFSET                                   6
-#define   O_L3CTABLE__L4PROTOOFFSET                                 20
-#define   W_L3CTABLE__L4PROTOOFFSET                                 6
-#define   O_L3CTABLE__IPCHKSUMCOMPUTE                               19
-#define   O_L3CTABLE__L4CLASSIFY                                    18
-#define   O_L3CTABLE__L2PROTO                                       16
-#define   W_L3CTABLE__L2PROTO                                       2
-#define   O_L3CTABLE__L3PROTOKEY                                    0
-#define   W_L3CTABLE__L3PROTOKEY                                    16
-#define R_L4CTABLE                                                  0x160
-#define   O_L4CTABLE__OFFSET0                                       21
-#define   W_L4CTABLE__OFFSET0                                       6
-#define   O_L4CTABLE__LEN0                                          17
-#define   W_L4CTABLE__LEN0                                          4
-#define   O_L4CTABLE__OFFSET1                                       11
-#define   W_L4CTABLE__OFFSET1                                       6
-#define   O_L4CTABLE__LEN1                                          7
-#define   W_L4CTABLE__LEN1                                          4
-#define   O_L4CTABLE__TCPCHKSUMENABLE                               0
-#define R_CAM4X128TABLE                                             0x172
-#define   O_CAM4X128TABLE__CLASSID                                  7
-#define   W_CAM4X128TABLE__CLASSID                                  2
-#define   O_CAM4X128TABLE__BUCKETID                                 1
-#define   W_CAM4X128TABLE__BUCKETID                                 6
-#define   O_CAM4X128TABLE__USEBUCKET                                0
-#define R_CAM4X128KEY                                               0x180
-#define R_TRANSLATETABLE                                            0x1A0
-#define R_DMACR0                                                    0x200
-#define   O_DMACR0__DATA0WRMAXCR                                    27
-#define   W_DMACR0__DATA0WRMAXCR                                    3
-#define   O_DMACR0__DATA0RDMAXCR                                    24
-#define   W_DMACR0__DATA0RDMAXCR                                    3
-#define   O_DMACR0__DATA1WRMAXCR                                    21
-#define   W_DMACR0__DATA1WRMAXCR                                    3
-#define   O_DMACR0__DATA1RDMAXCR                                    18
-#define   W_DMACR0__DATA1RDMAXCR                                    3
-#define   O_DMACR0__DATA2WRMAXCR                                    15
-#define   W_DMACR0__DATA2WRMAXCR                                    3
-#define   O_DMACR0__DATA2RDMAXCR                                    12
-#define   W_DMACR0__DATA2RDMAXCR                                    3
-#define   O_DMACR0__DATA3WRMAXCR                                    9
-#define   W_DMACR0__DATA3WRMAXCR                                    3
-#define   O_DMACR0__DATA3RDMAXCR                                    6
-#define   W_DMACR0__DATA3RDMAXCR                                    3
-#define   O_DMACR0__DATA4WRMAXCR                                    3
-#define   W_DMACR0__DATA4WRMAXCR                                    3
-#define   O_DMACR0__DATA4RDMAXCR                                    0
-#define   W_DMACR0__DATA4RDMAXCR                                    3
-#define R_DMACR1                                                    0x201
-#define   O_DMACR1__DATA5WRMAXCR                                    27
-#define   W_DMACR1__DATA5WRMAXCR                                    3
-#define   O_DMACR1__DATA5RDMAXCR                                    24
-#define   W_DMACR1__DATA5RDMAXCR                                    3
-#define   O_DMACR1__DATA6WRMAXCR                                    21
-#define   W_DMACR1__DATA6WRMAXCR                                    3
-#define   O_DMACR1__DATA6RDMAXCR                                    18
-#define   W_DMACR1__DATA6RDMAXCR                                    3
-#define   O_DMACR1__DATA7WRMAXCR                                    15
-#define   W_DMACR1__DATA7WRMAXCR                                    3
-#define   O_DMACR1__DATA7RDMAXCR                                    12
-#define   W_DMACR1__DATA7RDMAXCR                                    3
-#define   O_DMACR1__DATA8WRMAXCR                                    9
-#define   W_DMACR1__DATA8WRMAXCR                                    3
-#define   O_DMACR1__DATA8RDMAXCR                                    6
-#define   W_DMACR1__DATA8RDMAXCR                                    3
-#define   O_DMACR1__DATA9WRMAXCR                                    3
-#define   W_DMACR1__DATA9WRMAXCR                                    3
-#define   O_DMACR1__DATA9RDMAXCR                                    0
-#define   W_DMACR1__DATA9RDMAXCR                                    3
-#define R_DMACR2                                                    0x202
-#define   O_DMACR2__DATA10WRMAXCR                                   27
-#define   W_DMACR2__DATA10WRMAXCR                                   3
-#define   O_DMACR2__DATA10RDMAXCR                                   24
-#define   W_DMACR2__DATA10RDMAXCR                                   3
-#define   O_DMACR2__DATA11WRMAXCR                                   21
-#define   W_DMACR2__DATA11WRMAXCR                                   3
-#define   O_DMACR2__DATA11RDMAXCR                                   18
-#define   W_DMACR2__DATA11RDMAXCR                                   3
-#define   O_DMACR2__DATA12WRMAXCR                                   15
-#define   W_DMACR2__DATA12WRMAXCR                                   3
-#define   O_DMACR2__DATA12RDMAXCR                                   12
-#define   W_DMACR2__DATA12RDMAXCR                                   3
-#define   O_DMACR2__DATA13WRMAXCR                                   9
-#define   W_DMACR2__DATA13WRMAXCR                                   3
-#define   O_DMACR2__DATA13RDMAXCR                                   6
-#define   W_DMACR2__DATA13RDMAXCR                                   3
-#define   O_DMACR2__DATA14WRMAXCR                                   3
-#define   W_DMACR2__DATA14WRMAXCR                                   3
-#define   O_DMACR2__DATA14RDMAXCR                                   0
-#define   W_DMACR2__DATA14RDMAXCR                                   3
-#define R_DMACR3                                                    0x203
-#define   O_DMACR3__DATA15WRMAXCR                                   27
-#define   W_DMACR3__DATA15WRMAXCR                                   3
-#define   O_DMACR3__DATA15RDMAXCR                                   24
-#define   W_DMACR3__DATA15RDMAXCR                                   3
-#define   O_DMACR3__SPCLASSWRMAXCR                                  21
-#define   W_DMACR3__SPCLASSWRMAXCR                                  3
-#define   O_DMACR3__SPCLASSRDMAXCR                                  18
-#define   W_DMACR3__SPCLASSRDMAXCR                                  3
-#define   O_DMACR3__JUMFRINWRMAXCR                                  15
-#define   W_DMACR3__JUMFRINWRMAXCR                                  3
-#define   O_DMACR3__JUMFRINRDMAXCR                                  12
-#define   W_DMACR3__JUMFRINRDMAXCR                                  3
-#define   O_DMACR3__REGFRINWRMAXCR                                  9
-#define   W_DMACR3__REGFRINWRMAXCR                                  3
-#define   O_DMACR3__REGFRINRDMAXCR                                  6
-#define   W_DMACR3__REGFRINRDMAXCR                                  3
-#define   O_DMACR3__FROUTWRMAXCR                                    3
-#define   W_DMACR3__FROUTWRMAXCR                                    3
-#define   O_DMACR3__FROUTRDMAXCR                                    0
-#define   W_DMACR3__FROUTRDMAXCR                                    3
-#define R_REG_FRIN_SPILL_MEM_START_0                                0x204
-#define   O_REG_FRIN_SPILL_MEM_START_0__REGFRINSPILLMEMSTART0        0
-#define   W_REG_FRIN_SPILL_MEM_START_0__REGFRINSPILLMEMSTART0       32
-#define R_REG_FRIN_SPILL_MEM_START_1                                0x205
-#define   O_REG_FRIN_SPILL_MEM_START_1__REGFRINSPILLMEMSTART1        0
-#define   W_REG_FRIN_SPILL_MEM_START_1__REGFRINSPILLMEMSTART1        3
-#define R_REG_FRIN_SPILL_MEM_SIZE                                   0x206
-#define   O_REG_FRIN_SPILL_MEM_SIZE__REGFRINSPILLMEMSIZE             0
-#define   W_REG_FRIN_SPILL_MEM_SIZE__REGFRINSPILLMEMSIZE            32
-#define R_FROUT_SPILL_MEM_START_0                                   0x207
-#define   O_FROUT_SPILL_MEM_START_0__FROUTSPILLMEMSTART0             0
-#define   W_FROUT_SPILL_MEM_START_0__FROUTSPILLMEMSTART0            32
-#define R_FROUT_SPILL_MEM_START_1                                   0x208
-#define   O_FROUT_SPILL_MEM_START_1__FROUTSPILLMEMSTART1             0
-#define   W_FROUT_SPILL_MEM_START_1__FROUTSPILLMEMSTART1             3
-#define R_FROUT_SPILL_MEM_SIZE                                      0x209
-#define   O_FROUT_SPILL_MEM_SIZE__FROUTSPILLMEMSIZE                  0
-#define   W_FROUT_SPILL_MEM_SIZE__FROUTSPILLMEMSIZE                 32
-#define R_CLASS0_SPILL_MEM_START_0                                  0x20A
-#define   O_CLASS0_SPILL_MEM_START_0__CLASS0SPILLMEMSTART0           0
-#define   W_CLASS0_SPILL_MEM_START_0__CLASS0SPILLMEMSTART0          32
-#define R_CLASS0_SPILL_MEM_START_1                                  0x20B
-#define   O_CLASS0_SPILL_MEM_START_1__CLASS0SPILLMEMSTART1           0
-#define   W_CLASS0_SPILL_MEM_START_1__CLASS0SPILLMEMSTART1           3
-#define R_CLASS0_SPILL_MEM_SIZE                                     0x20C
-#define   O_CLASS0_SPILL_MEM_SIZE__CLASS0SPILLMEMSIZE                0
-#define   W_CLASS0_SPILL_MEM_SIZE__CLASS0SPILLMEMSIZE               32
-#define R_JUMFRIN_SPILL_MEM_START_0                                 0x20D
-#define   O_JUMFRIN_SPILL_MEM_START_0__JUMFRINSPILLMEMSTART0          0
-#define   W_JUMFRIN_SPILL_MEM_START_0__JUMFRINSPILLMEMSTART0         32
-#define R_JUMFRIN_SPILL_MEM_START_1                                 0x20E
-#define   O_JUMFRIN_SPILL_MEM_START_1__JUMFRINSPILLMEMSTART1         0
-#define   W_JUMFRIN_SPILL_MEM_START_1__JUMFRINSPILLMEMSTART1         3
-#define R_JUMFRIN_SPILL_MEM_SIZE                                    0x20F
-#define   O_JUMFRIN_SPILL_MEM_SIZE__JUMFRINSPILLMEMSIZE              0
-#define   W_JUMFRIN_SPILL_MEM_SIZE__JUMFRINSPILLMEMSIZE             32
-#define R_CLASS1_SPILL_MEM_START_0                                  0x210
-#define   O_CLASS1_SPILL_MEM_START_0__CLASS1SPILLMEMSTART0           0
-#define   W_CLASS1_SPILL_MEM_START_0__CLASS1SPILLMEMSTART0          32
-#define R_CLASS1_SPILL_MEM_START_1                                  0x211
-#define   O_CLASS1_SPILL_MEM_START_1__CLASS1SPILLMEMSTART1           0
-#define   W_CLASS1_SPILL_MEM_START_1__CLASS1SPILLMEMSTART1           3
-#define R_CLASS1_SPILL_MEM_SIZE                                     0x212
-#define   O_CLASS1_SPILL_MEM_SIZE__CLASS1SPILLMEMSIZE                0
-#define   W_CLASS1_SPILL_MEM_SIZE__CLASS1SPILLMEMSIZE               32
-#define R_CLASS2_SPILL_MEM_START_0                                  0x213
-#define   O_CLASS2_SPILL_MEM_START_0__CLASS2SPILLMEMSTART0           0
-#define   W_CLASS2_SPILL_MEM_START_0__CLASS2SPILLMEMSTART0          32
-#define R_CLASS2_SPILL_MEM_START_1                                  0x214
-#define   O_CLASS2_SPILL_MEM_START_1__CLASS2SPILLMEMSTART1           0
-#define   W_CLASS2_SPILL_MEM_START_1__CLASS2SPILLMEMSTART1           3
-#define R_CLASS2_SPILL_MEM_SIZE                                     0x215
-#define   O_CLASS2_SPILL_MEM_SIZE__CLASS2SPILLMEMSIZE                0
-#define   W_CLASS2_SPILL_MEM_SIZE__CLASS2SPILLMEMSIZE               32
-#define R_CLASS3_SPILL_MEM_START_0                                  0x216
-#define   O_CLASS3_SPILL_MEM_START_0__CLASS3SPILLMEMSTART0           0
-#define   W_CLASS3_SPILL_MEM_START_0__CLASS3SPILLMEMSTART0          32
-#define R_CLASS3_SPILL_MEM_START_1                                  0x217
-#define   O_CLASS3_SPILL_MEM_START_1__CLASS3SPILLMEMSTART1           0
-#define   W_CLASS3_SPILL_MEM_START_1__CLASS3SPILLMEMSTART1           3
-#define R_CLASS3_SPILL_MEM_SIZE                                     0x218
-#define   O_CLASS3_SPILL_MEM_SIZE__CLASS3SPILLMEMSIZE                0
-#define   W_CLASS3_SPILL_MEM_SIZE__CLASS3SPILLMEMSIZE               32
-#define R_REG_FRIN1_SPILL_MEM_START_0                               0x219
-#define R_REG_FRIN1_SPILL_MEM_START_1                               0x21a
-#define R_REG_FRIN1_SPILL_MEM_SIZE                                  0x21b
-#define R_SPIHNGY0                                                  0x219
-#define   O_SPIHNGY0__EG_HNGY_THRESH_0                              24
-#define   W_SPIHNGY0__EG_HNGY_THRESH_0                              7
-#define   O_SPIHNGY0__EG_HNGY_THRESH_1                              16
-#define   W_SPIHNGY0__EG_HNGY_THRESH_1                              7
-#define   O_SPIHNGY0__EG_HNGY_THRESH_2                              8
-#define   W_SPIHNGY0__EG_HNGY_THRESH_2                              7
-#define   O_SPIHNGY0__EG_HNGY_THRESH_3                              0
-#define   W_SPIHNGY0__EG_HNGY_THRESH_3                              7
-#define R_SPIHNGY1                                                  0x21A
-#define   O_SPIHNGY1__EG_HNGY_THRESH_4                              24
-#define   W_SPIHNGY1__EG_HNGY_THRESH_4                              7
-#define   O_SPIHNGY1__EG_HNGY_THRESH_5                              16
-#define   W_SPIHNGY1__EG_HNGY_THRESH_5                              7
-#define   O_SPIHNGY1__EG_HNGY_THRESH_6                              8
-#define   W_SPIHNGY1__EG_HNGY_THRESH_6                              7
-#define   O_SPIHNGY1__EG_HNGY_THRESH_7                              0
-#define   W_SPIHNGY1__EG_HNGY_THRESH_7                              7
-#define R_SPIHNGY2                                                  0x21B
-#define   O_SPIHNGY2__EG_HNGY_THRESH_8                              24
-#define   W_SPIHNGY2__EG_HNGY_THRESH_8                              7
-#define   O_SPIHNGY2__EG_HNGY_THRESH_9                              16
-#define   W_SPIHNGY2__EG_HNGY_THRESH_9                              7
-#define   O_SPIHNGY2__EG_HNGY_THRESH_10                             8
-#define   W_SPIHNGY2__EG_HNGY_THRESH_10                             7
-#define   O_SPIHNGY2__EG_HNGY_THRESH_11                             0
-#define   W_SPIHNGY2__EG_HNGY_THRESH_11                             7
-#define R_SPIHNGY3                                                  0x21C
-#define   O_SPIHNGY3__EG_HNGY_THRESH_12                             24
-#define   W_SPIHNGY3__EG_HNGY_THRESH_12                             7
-#define   O_SPIHNGY3__EG_HNGY_THRESH_13                             16
-#define   W_SPIHNGY3__EG_HNGY_THRESH_13                             7
-#define   O_SPIHNGY3__EG_HNGY_THRESH_14                             8
-#define   W_SPIHNGY3__EG_HNGY_THRESH_14                             7
-#define   O_SPIHNGY3__EG_HNGY_THRESH_15                             0
-#define   W_SPIHNGY3__EG_HNGY_THRESH_15                             7
-#define R_SPISTRV0                                                  0x21D
-#define   O_SPISTRV0__EG_STRV_THRESH_0                              24
-#define   W_SPISTRV0__EG_STRV_THRESH_0                              7
-#define   O_SPISTRV0__EG_STRV_THRESH_1                              16
-#define   W_SPISTRV0__EG_STRV_THRESH_1                              7
-#define   O_SPISTRV0__EG_STRV_THRESH_2                              8
-#define   W_SPISTRV0__EG_STRV_THRESH_2                              7
-#define   O_SPISTRV0__EG_STRV_THRESH_3                              0
-#define   W_SPISTRV0__EG_STRV_THRESH_3                              7
-#define R_SPISTRV1                                                  0x21E
-#define   O_SPISTRV1__EG_STRV_THRESH_4                              24
-#define   W_SPISTRV1__EG_STRV_THRESH_4                              7
-#define   O_SPISTRV1__EG_STRV_THRESH_5                              16
-#define   W_SPISTRV1__EG_STRV_THRESH_5                              7
-#define   O_SPISTRV1__EG_STRV_THRESH_6                              8
-#define   W_SPISTRV1__EG_STRV_THRESH_6                              7
-#define   O_SPISTRV1__EG_STRV_THRESH_7                              0
-#define   W_SPISTRV1__EG_STRV_THRESH_7                              7
-#define R_SPISTRV2                                                  0x21F
-#define   O_SPISTRV2__EG_STRV_THRESH_8                              24
-#define   W_SPISTRV2__EG_STRV_THRESH_8                              7
-#define   O_SPISTRV2__EG_STRV_THRESH_9                              16
-#define   W_SPISTRV2__EG_STRV_THRESH_9                              7
-#define   O_SPISTRV2__EG_STRV_THRESH_10                             8
-#define   W_SPISTRV2__EG_STRV_THRESH_10                             7
-#define   O_SPISTRV2__EG_STRV_THRESH_11                             0
-#define   W_SPISTRV2__EG_STRV_THRESH_11                             7
-#define R_SPISTRV3                                                  0x220
-#define   O_SPISTRV3__EG_STRV_THRESH_12                             24
-#define   W_SPISTRV3__EG_STRV_THRESH_12                             7
-#define   O_SPISTRV3__EG_STRV_THRESH_13                             16
-#define   W_SPISTRV3__EG_STRV_THRESH_13                             7
-#define   O_SPISTRV3__EG_STRV_THRESH_14                             8
-#define   W_SPISTRV3__EG_STRV_THRESH_14                             7
-#define   O_SPISTRV3__EG_STRV_THRESH_15                             0
-#define   W_SPISTRV3__EG_STRV_THRESH_15                             7
-#define R_TXDATAFIFO0                                               0x221
-#define   O_TXDATAFIFO0__TX0DATAFIFOSTART                           24
-#define   W_TXDATAFIFO0__TX0DATAFIFOSTART                           7
-#define   O_TXDATAFIFO0__TX0DATAFIFOSIZE                            16
-#define   W_TXDATAFIFO0__TX0DATAFIFOSIZE                            7
-#define   O_TXDATAFIFO0__TX1DATAFIFOSTART                           8
-#define   W_TXDATAFIFO0__TX1DATAFIFOSTART                           7
-#define   O_TXDATAFIFO0__TX1DATAFIFOSIZE                            0
-#define   W_TXDATAFIFO0__TX1DATAFIFOSIZE                            7
-#define R_TXDATAFIFO1                                               0x222
-#define   O_TXDATAFIFO1__TX2DATAFIFOSTART                           24
-#define   W_TXDATAFIFO1__TX2DATAFIFOSTART                           7
-#define   O_TXDATAFIFO1__TX2DATAFIFOSIZE                            16
-#define   W_TXDATAFIFO1__TX2DATAFIFOSIZE                            7
-#define   O_TXDATAFIFO1__TX3DATAFIFOSTART                           8
-#define   W_TXDATAFIFO1__TX3DATAFIFOSTART                           7
-#define   O_TXDATAFIFO1__TX3DATAFIFOSIZE                            0
-#define   W_TXDATAFIFO1__TX3DATAFIFOSIZE                            7
-#define R_TXDATAFIFO2                                               0x223
-#define   O_TXDATAFIFO2__TX4DATAFIFOSTART                           24
-#define   W_TXDATAFIFO2__TX4DATAFIFOSTART                           7
-#define   O_TXDATAFIFO2__TX4DATAFIFOSIZE                            16
-#define   W_TXDATAFIFO2__TX4DATAFIFOSIZE                            7
-#define   O_TXDATAFIFO2__TX5DATAFIFOSTART                           8
-#define   W_TXDATAFIFO2__TX5DATAFIFOSTART                           7
-#define   O_TXDATAFIFO2__TX5DATAFIFOSIZE                            0
-#define   W_TXDATAFIFO2__TX5DATAFIFOSIZE                            7
-#define R_TXDATAFIFO3                                               0x224
-#define   O_TXDATAFIFO3__TX6DATAFIFOSTART                           24
-#define   W_TXDATAFIFO3__TX6DATAFIFOSTART                           7
-#define   O_TXDATAFIFO3__TX6DATAFIFOSIZE                            16
-#define   W_TXDATAFIFO3__TX6DATAFIFOSIZE                            7
-#define   O_TXDATAFIFO3__TX7DATAFIFOSTART                           8
-#define   W_TXDATAFIFO3__TX7DATAFIFOSTART                           7
-#define   O_TXDATAFIFO3__TX7DATAFIFOSIZE                            0
-#define   W_TXDATAFIFO3__TX7DATAFIFOSIZE                            7
-#define R_TXDATAFIFO4                                               0x225
-#define   O_TXDATAFIFO4__TX8DATAFIFOSTART                           24
-#define   W_TXDATAFIFO4__TX8DATAFIFOSTART                           7
-#define   O_TXDATAFIFO4__TX8DATAFIFOSIZE                            16
-#define   W_TXDATAFIFO4__TX8DATAFIFOSIZE                            7
-#define   O_TXDATAFIFO4__TX9DATAFIFOSTART                           8
-#define   W_TXDATAFIFO4__TX9DATAFIFOSTART                           7
-#define   O_TXDATAFIFO4__TX9DATAFIFOSIZE                            0
-#define   W_TXDATAFIFO4__TX9DATAFIFOSIZE                            7
-#define R_TXDATAFIFO5                                               0x226
-#define   O_TXDATAFIFO5__TX10DATAFIFOSTART                          24
-#define   W_TXDATAFIFO5__TX10DATAFIFOSTART                          7
-#define   O_TXDATAFIFO5__TX10DATAFIFOSIZE                           16
-#define   W_TXDATAFIFO5__TX10DATAFIFOSIZE                           7
-#define   O_TXDATAFIFO5__TX11DATAFIFOSTART                          8
-#define   W_TXDATAFIFO5__TX11DATAFIFOSTART                          7
-#define   O_TXDATAFIFO5__TX11DATAFIFOSIZE                           0
-#define   W_TXDATAFIFO5__TX11DATAFIFOSIZE                           7
-#define R_TXDATAFIFO6                                               0x227
-#define   O_TXDATAFIFO6__TX12DATAFIFOSTART                          24
-#define   W_TXDATAFIFO6__TX12DATAFIFOSTART                          7
-#define   O_TXDATAFIFO6__TX12DATAFIFOSIZE                           16
-#define   W_TXDATAFIFO6__TX12DATAFIFOSIZE                           7
-#define   O_TXDATAFIFO6__TX13DATAFIFOSTART                          8
-#define   W_TXDATAFIFO6__TX13DATAFIFOSTART                          7
-#define   O_TXDATAFIFO6__TX13DATAFIFOSIZE                           0
-#define   W_TXDATAFIFO6__TX13DATAFIFOSIZE                           7
-#define R_TXDATAFIFO7                                               0x228
-#define   O_TXDATAFIFO7__TX14DATAFIFOSTART                          24
-#define   W_TXDATAFIFO7__TX14DATAFIFOSTART                          7
-#define   O_TXDATAFIFO7__TX14DATAFIFOSIZE                           16
-#define   W_TXDATAFIFO7__TX14DATAFIFOSIZE                           7
-#define   O_TXDATAFIFO7__TX15DATAFIFOSTART                          8
-#define   W_TXDATAFIFO7__TX15DATAFIFOSTART                          7
-#define   O_TXDATAFIFO7__TX15DATAFIFOSIZE                           0
-#define   W_TXDATAFIFO7__TX15DATAFIFOSIZE                           7
-#define R_RXDATAFIFO0                                               0x229
-#define   O_RXDATAFIFO0__RX0DATAFIFOSTART                           24
-#define   W_RXDATAFIFO0__RX0DATAFIFOSTART                           7
-#define   O_RXDATAFIFO0__RX0DATAFIFOSIZE                            16
-#define   W_RXDATAFIFO0__RX0DATAFIFOSIZE                            7
-#define   O_RXDATAFIFO0__RX1DATAFIFOSTART                           8
-#define   W_RXDATAFIFO0__RX1DATAFIFOSTART                           7
-#define   O_RXDATAFIFO0__RX1DATAFIFOSIZE                            0
-#define   W_RXDATAFIFO0__RX1DATAFIFOSIZE                            7
-#define R_RXDATAFIFO1                                               0x22A
-#define   O_RXDATAFIFO1__RX2DATAFIFOSTART                           24
-#define   W_RXDATAFIFO1__RX2DATAFIFOSTART                           7
-#define   O_RXDATAFIFO1__RX2DATAFIFOSIZE                            16
-#define   W_RXDATAFIFO1__RX2DATAFIFOSIZE                            7
-#define   O_RXDATAFIFO1__RX3DATAFIFOSTART                           8
-#define   W_RXDATAFIFO1__RX3DATAFIFOSTART                           7
-#define   O_RXDATAFIFO1__RX3DATAFIFOSIZE                            0
-#define   W_RXDATAFIFO1__RX3DATAFIFOSIZE                            7
-#define R_RXDATAFIFO2                                               0x22B
-#define   O_RXDATAFIFO2__RX4DATAFIFOSTART                           24
-#define   W_RXDATAFIFO2__RX4DATAFIFOSTART                           7
-#define   O_RXDATAFIFO2__RX4DATAFIFOSIZE                            16
-#define   W_RXDATAFIFO2__RX4DATAFIFOSIZE                            7
-#define   O_RXDATAFIFO2__RX5DATAFIFOSTART                           8
-#define   W_RXDATAFIFO2__RX5DATAFIFOSTART                           7
-#define   O_RXDATAFIFO2__RX5DATAFIFOSIZE                            0
-#define   W_RXDATAFIFO2__RX5DATAFIFOSIZE                            7
-#define R_RXDATAFIFO3                                               0x22C
-#define   O_RXDATAFIFO3__RX6DATAFIFOSTART                           24
-#define   W_RXDATAFIFO3__RX6DATAFIFOSTART                           7
-#define   O_RXDATAFIFO3__RX6DATAFIFOSIZE                            16
-#define   W_RXDATAFIFO3__RX6DATAFIFOSIZE                            7
-#define   O_RXDATAFIFO3__RX7DATAFIFOSTART                           8
-#define   W_RXDATAFIFO3__RX7DATAFIFOSTART                           7
-#define   O_RXDATAFIFO3__RX7DATAFIFOSIZE                            0
-#define   W_RXDATAFIFO3__RX7DATAFIFOSIZE                            7
-#define R_RXDATAFIFO4                                               0x22D
-#define   O_RXDATAFIFO4__RX8DATAFIFOSTART                           24
-#define   W_RXDATAFIFO4__RX8DATAFIFOSTART                           7
-#define   O_RXDATAFIFO4__RX8DATAFIFOSIZE                            16
-#define   W_RXDATAFIFO4__RX8DATAFIFOSIZE                            7
-#define   O_RXDATAFIFO4__RX9DATAFIFOSTART                           8
-#define   W_RXDATAFIFO4__RX9DATAFIFOSTART                           7
-#define   O_RXDATAFIFO4__RX9DATAFIFOSIZE                            0
-#define   W_RXDATAFIFO4__RX9DATAFIFOSIZE                            7
-#define R_RXDATAFIFO5                                               0x22E
-#define   O_RXDATAFIFO5__RX10DATAFIFOSTART                          24
-#define   W_RXDATAFIFO5__RX10DATAFIFOSTART                          7
-#define   O_RXDATAFIFO5__RX10DATAFIFOSIZE                           16
-#define   W_RXDATAFIFO5__RX10DATAFIFOSIZE                           7
-#define   O_RXDATAFIFO5__RX11DATAFIFOSTART                          8
-#define   W_RXDATAFIFO5__RX11DATAFIFOSTART                          7
-#define   O_RXDATAFIFO5__RX11DATAFIFOSIZE                           0
-#define   W_RXDATAFIFO5__RX11DATAFIFOSIZE                           7
-#define R_RXDATAFIFO6                                               0x22F
-#define   O_RXDATAFIFO6__RX12DATAFIFOSTART                          24
-#define   W_RXDATAFIFO6__RX12DATAFIFOSTART                          7
-#define   O_RXDATAFIFO6__RX12DATAFIFOSIZE                           16
-#define   W_RXDATAFIFO6__RX12DATAFIFOSIZE                           7
-#define   O_RXDATAFIFO6__RX13DATAFIFOSTART                          8
-#define   W_RXDATAFIFO6__RX13DATAFIFOSTART                          7
-#define   O_RXDATAFIFO6__RX13DATAFIFOSIZE                           0
-#define   W_RXDATAFIFO6__RX13DATAFIFOSIZE                           7
-#define R_RXDATAFIFO7                                               0x230
-#define   O_RXDATAFIFO7__RX14DATAFIFOSTART                          24
-#define   W_RXDATAFIFO7__RX14DATAFIFOSTART                          7
-#define   O_RXDATAFIFO7__RX14DATAFIFOSIZE                           16
-#define   W_RXDATAFIFO7__RX14DATAFIFOSIZE                           7
-#define   O_RXDATAFIFO7__RX15DATAFIFOSTART                          8
-#define   W_RXDATAFIFO7__RX15DATAFIFOSTART                          7
-#define   O_RXDATAFIFO7__RX15DATAFIFOSIZE                           0
-#define   W_RXDATAFIFO7__RX15DATAFIFOSIZE                           7
-#define R_XGMACPADCALIBRATION                                       0x231
-#define R_FREEQCARVE                                                0x233
-#define R_SPI4STATICDELAY0                                          0x240
-#define   O_SPI4STATICDELAY0__DATALINE7                             28
-#define   W_SPI4STATICDELAY0__DATALINE7                             4
-#define   O_SPI4STATICDELAY0__DATALINE6                             24
-#define   W_SPI4STATICDELAY0__DATALINE6                             4
-#define   O_SPI4STATICDELAY0__DATALINE5                             20
-#define   W_SPI4STATICDELAY0__DATALINE5                             4
-#define   O_SPI4STATICDELAY0__DATALINE4                             16
-#define   W_SPI4STATICDELAY0__DATALINE4                             4
-#define   O_SPI4STATICDELAY0__DATALINE3                             12
-#define   W_SPI4STATICDELAY0__DATALINE3                             4
-#define   O_SPI4STATICDELAY0__DATALINE2                             8
-#define   W_SPI4STATICDELAY0__DATALINE2                             4
-#define   O_SPI4STATICDELAY0__DATALINE1                             4
-#define   W_SPI4STATICDELAY0__DATALINE1                             4
-#define   O_SPI4STATICDELAY0__DATALINE0                             0
-#define   W_SPI4STATICDELAY0__DATALINE0                             4
-#define R_SPI4STATICDELAY1                                          0x241
-#define   O_SPI4STATICDELAY1__DATALINE15                            28
-#define   W_SPI4STATICDELAY1__DATALINE15                            4
-#define   O_SPI4STATICDELAY1__DATALINE14                            24
-#define   W_SPI4STATICDELAY1__DATALINE14                            4
-#define   O_SPI4STATICDELAY1__DATALINE13                            20
-#define   W_SPI4STATICDELAY1__DATALINE13                            4
-#define   O_SPI4STATICDELAY1__DATALINE12                            16
-#define   W_SPI4STATICDELAY1__DATALINE12                            4
-#define   O_SPI4STATICDELAY1__DATALINE11                            12
-#define   W_SPI4STATICDELAY1__DATALINE11                            4
-#define   O_SPI4STATICDELAY1__DATALINE10                            8
-#define   W_SPI4STATICDELAY1__DATALINE10                            4
-#define   O_SPI4STATICDELAY1__DATALINE9                             4
-#define   W_SPI4STATICDELAY1__DATALINE9                             4
-#define   O_SPI4STATICDELAY1__DATALINE8                             0
-#define   W_SPI4STATICDELAY1__DATALINE8                             4
-#define R_SPI4STATICDELAY2                                          0x242
-#define   O_SPI4STATICDELAY0__TXSTAT1                               8
-#define   W_SPI4STATICDELAY0__TXSTAT1                               4
-#define   O_SPI4STATICDELAY0__TXSTAT0                               4
-#define   W_SPI4STATICDELAY0__TXSTAT0                               4
-#define   O_SPI4STATICDELAY0__RXCONTROL                             0
-#define   W_SPI4STATICDELAY0__RXCONTROL                             4
-#define R_SPI4CONTROL                                               0x243
-#define   O_SPI4CONTROL__STATICDELAY                                2
-#define   O_SPI4CONTROL__LVDS_LVTTL                                 1
-#define   O_SPI4CONTROL__SPI4ENABLE                                 0
-#define R_CLASSWATERMARKS                                           0x244
-#define   O_CLASSWATERMARKS__CLASS0WATERMARK                        24
-#define   W_CLASSWATERMARKS__CLASS0WATERMARK                        5
-#define   O_CLASSWATERMARKS__CLASS1WATERMARK                        16
-#define   W_CLASSWATERMARKS__CLASS1WATERMARK                        5
-#define   O_CLASSWATERMARKS__CLASS3WATERMARK                        0
-#define   W_CLASSWATERMARKS__CLASS3WATERMARK                        5
-#define R_RXWATERMARKS1                                              0x245
-#define   O_RXWATERMARKS__RX0DATAWATERMARK                          24
-#define   W_RXWATERMARKS__RX0DATAWATERMARK                          7
-#define   O_RXWATERMARKS__RX1DATAWATERMARK                          16
-#define   W_RXWATERMARKS__RX1DATAWATERMARK                          7
-#define   O_RXWATERMARKS__RX3DATAWATERMARK                          0
-#define   W_RXWATERMARKS__RX3DATAWATERMARK                          7
-#define R_RXWATERMARKS2                                              0x246
-#define   O_RXWATERMARKS__RX4DATAWATERMARK                          24
-#define   W_RXWATERMARKS__RX4DATAWATERMARK                          7
-#define   O_RXWATERMARKS__RX5DATAWATERMARK                          16
-#define   W_RXWATERMARKS__RX5DATAWATERMARK                          7
-#define   O_RXWATERMARKS__RX6DATAWATERMARK                          8
-#define   W_RXWATERMARKS__RX6DATAWATERMARK                          7
-#define   O_RXWATERMARKS__RX7DATAWATERMARK                          0
-#define   W_RXWATERMARKS__RX7DATAWATERMARK                          7
-#define R_RXWATERMARKS3                                              0x247
-#define   O_RXWATERMARKS__RX8DATAWATERMARK                          24
-#define   W_RXWATERMARKS__RX8DATAWATERMARK                          7
-#define   O_RXWATERMARKS__RX9DATAWATERMARK                          16
-#define   W_RXWATERMARKS__RX9DATAWATERMARK                          7
-#define   O_RXWATERMARKS__RX10DATAWATERMARK                         8
-#define   W_RXWATERMARKS__RX10DATAWATERMARK                         7
-#define   O_RXWATERMARKS__RX11DATAWATERMARK                         0
-#define   W_RXWATERMARKS__RX11DATAWATERMARK                         7
-#define R_RXWATERMARKS4                                              0x248
-#define   O_RXWATERMARKS__RX12DATAWATERMARK                         24
-#define   W_RXWATERMARKS__RX12DATAWATERMARK                         7
-#define   O_RXWATERMARKS__RX13DATAWATERMARK                         16
-#define   W_RXWATERMARKS__RX13DATAWATERMARK                         7
-#define   O_RXWATERMARKS__RX14DATAWATERMARK                         8
-#define   W_RXWATERMARKS__RX14DATAWATERMARK                         7
-#define   O_RXWATERMARKS__RX15DATAWATERMARK                         0
-#define   W_RXWATERMARKS__RX15DATAWATERMARK                         7
-#define R_FREEWATERMARKS                                            0x249
-#define   O_FREEWATERMARKS__FREEOUTWATERMARK                        16
-#define   W_FREEWATERMARKS__FREEOUTWATERMARK                        16
-#define   O_FREEWATERMARKS__JUMFRWATERMARK                          8
-#define   W_FREEWATERMARKS__JUMFRWATERMARK                          7
-#define   O_FREEWATERMARKS__REGFRWATERMARK                          0
-#define   W_FREEWATERMARKS__REGFRWATERMARK                          7
-#define R_EGRESSFIFOCARVINGSLOTS                                    0x24a
-
-#define CTRL_RES0           0
-#define CTRL_RES1           1
-#define CTRL_REG_FREE       2
-#define CTRL_JUMBO_FREE     3
-#define CTRL_CONT           4
-#define CTRL_EOP            5
-#define CTRL_START          6
-#define CTRL_SNGL           7
-
-#define CTRL_B0_NOT_EOP     0
-#define CTRL_B0_EOP         1
-
-#define R_ROUND_ROBIN_TABLE                 0
-#define R_PDE_CLASS_0                       0x300
-#define R_PDE_CLASS_1                       0x302
-#define R_PDE_CLASS_2                       0x304
-#define R_PDE_CLASS_3                       0x306
-
-#define R_MSG_TX_THRESHOLD                  0x308
-
-#define R_GMAC_JFR0_BUCKET_SIZE              0x320
-#define R_GMAC_RFR0_BUCKET_SIZE              0x321
-#define R_GMAC_TX0_BUCKET_SIZE              0x322
-#define R_GMAC_TX1_BUCKET_SIZE              0x323
-#define R_GMAC_TX2_BUCKET_SIZE              0x324
-#define R_GMAC_TX3_BUCKET_SIZE              0x325
-#define R_GMAC_JFR1_BUCKET_SIZE              0x326
-#define R_GMAC_RFR1_BUCKET_SIZE              0x327
-
-#define R_XGS_TX0_BUCKET_SIZE               0x320
-#define R_XGS_TX1_BUCKET_SIZE               0x321
-#define R_XGS_TX2_BUCKET_SIZE               0x322
-#define R_XGS_TX3_BUCKET_SIZE               0x323
-#define R_XGS_TX4_BUCKET_SIZE               0x324
-#define R_XGS_TX5_BUCKET_SIZE               0x325
-#define R_XGS_TX6_BUCKET_SIZE               0x326
-#define R_XGS_TX7_BUCKET_SIZE               0x327
-#define R_XGS_TX8_BUCKET_SIZE               0x328
-#define R_XGS_TX9_BUCKET_SIZE               0x329
-#define R_XGS_TX10_BUCKET_SIZE              0x32A
-#define R_XGS_TX11_BUCKET_SIZE              0x32B
-#define R_XGS_TX12_BUCKET_SIZE              0x32C
-#define R_XGS_TX13_BUCKET_SIZE              0x32D
-#define R_XGS_TX14_BUCKET_SIZE              0x32E
-#define R_XGS_TX15_BUCKET_SIZE              0x32F
-#define R_XGS_JFR_BUCKET_SIZE               0x330
-#define R_XGS_RFR_BUCKET_SIZE               0x331
-
-#define R_CC_CPU0_0                         0x380
-#define R_CC_CPU1_0                         0x388
-#define R_CC_CPU2_0                         0x390
-#define R_CC_CPU3_0                         0x398
-#define R_CC_CPU4_0                         0x3a0
-#define R_CC_CPU5_0                         0x3a8
-#define R_CC_CPU6_0                         0x3b0
-#define R_CC_CPU7_0                         0x3b8
-
-#define XLR_GMAC_BLK_SZ		            (XLR_IO_GMAC_1_OFFSET - \
-		XLR_IO_GMAC_0_OFFSET)
-
-/* Constants used for configuring the devices */
-
-#define XLR_FB_STN			6 /* Bucket used for Tx freeback */
-
-#define MAC_B2B_IPG                     88
-
-#define	XLR_NET_PREPAD_LEN		32
-
-/* frame sizes need to be cacheline aligned */
-#define MAX_FRAME_SIZE                  (1536 + XLR_NET_PREPAD_LEN)
-#define MAX_FRAME_SIZE_JUMBO            9216
-
-#define MAC_SKB_BACK_PTR_SIZE           SMP_CACHE_BYTES
-#define MAC_PREPAD                      0
-#define BYTE_OFFSET                     2
-#define XLR_RX_BUF_SIZE                 (MAX_FRAME_SIZE + BYTE_OFFSET + \
-		MAC_PREPAD + MAC_SKB_BACK_PTR_SIZE + SMP_CACHE_BYTES)
-#define MAC_CRC_LEN                     4
-#define MAX_NUM_MSGRNG_STN_CC           128
-#define MAX_MSG_SND_ATTEMPTS		100	/* 13 stns x 4 entry msg/stn +
-						 * headroom
-						 */
-
-#define MAC_FRIN_TO_BE_SENT_THRESHOLD   16
-
-#define MAX_NUM_DESC_SPILL		1024
-#define MAX_FRIN_SPILL                  (MAX_NUM_DESC_SPILL << 2)
-#define MAX_FROUT_SPILL                 (MAX_NUM_DESC_SPILL << 2)
-#define MAX_CLASS_0_SPILL               (MAX_NUM_DESC_SPILL << 2)
-#define MAX_CLASS_1_SPILL               (MAX_NUM_DESC_SPILL << 2)
-#define MAX_CLASS_2_SPILL               (MAX_NUM_DESC_SPILL << 2)
-#define MAX_CLASS_3_SPILL               (MAX_NUM_DESC_SPILL << 2)
-
-enum {
-	SGMII_SPEED_10 = 0x00000000,
-	SGMII_SPEED_100 = 0x02000000,
-	SGMII_SPEED_1000 = 0x04000000,
-};
-
-enum tsv_rsv_reg {
-	TX_RX_64_BYTE_FRAME = 0x20,
-	TX_RX_64_127_BYTE_FRAME,
-	TX_RX_128_255_BYTE_FRAME,
-	TX_RX_256_511_BYTE_FRAME,
-	TX_RX_512_1023_BYTE_FRAME,
-	TX_RX_1024_1518_BYTE_FRAME,
-	TX_RX_1519_1522_VLAN_BYTE_FRAME,
-
-	RX_BYTE_COUNTER = 0x27,
-	RX_PACKET_COUNTER,
-	RX_FCS_ERROR_COUNTER,
-	RX_MULTICAST_PACKET_COUNTER,
-	RX_BROADCAST_PACKET_COUNTER,
-	RX_CONTROL_FRAME_PACKET_COUNTER,
-	RX_PAUSE_FRAME_PACKET_COUNTER,
-	RX_UNKNOWN_OP_CODE_COUNTER,
-	RX_ALIGNMENT_ERROR_COUNTER,
-	RX_FRAME_LENGTH_ERROR_COUNTER,
-	RX_CODE_ERROR_COUNTER,
-	RX_CARRIER_SENSE_ERROR_COUNTER,
-	RX_UNDERSIZE_PACKET_COUNTER,
-	RX_OVERSIZE_PACKET_COUNTER,
-	RX_FRAGMENTS_COUNTER,
-	RX_JABBER_COUNTER,
-	RX_DROP_PACKET_COUNTER,
-
-	TX_BYTE_COUNTER   = 0x38,
-	TX_PACKET_COUNTER,
-	TX_MULTICAST_PACKET_COUNTER,
-	TX_BROADCAST_PACKET_COUNTER,
-	TX_PAUSE_CONTROL_FRAME_COUNTER,
-	TX_DEFERRAL_PACKET_COUNTER,
-	TX_EXCESSIVE_DEFERRAL_PACKET_COUNTER,
-	TX_SINGLE_COLLISION_PACKET_COUNTER,
-	TX_MULTI_COLLISION_PACKET_COUNTER,
-	TX_LATE_COLLISION_PACKET_COUNTER,
-	TX_EXCESSIVE_COLLISION_PACKET_COUNTER,
-	TX_TOTAL_COLLISION_COUNTER,
-	TX_PAUSE_FRAME_HONERED_COUNTER,
-	TX_DROP_FRAME_COUNTER,
-	TX_JABBER_FRAME_COUNTER,
-	TX_FCS_ERROR_COUNTER,
-	TX_CONTROL_FRAME_COUNTER,
-	TX_OVERSIZE_FRAME_COUNTER,
-	TX_UNDERSIZE_FRAME_COUNTER,
-	TX_FRAGMENT_FRAME_COUNTER,
-
-	CARRY_REG_1 = 0x4c,
-	CARRY_REG_2 = 0x4d,
-};
-
-struct xlr_adapter {
-	struct net_device *netdev[4];
-};
-
-struct xlr_net_priv {
-	u32 __iomem *base_addr;
-	struct net_device *ndev;
-	struct xlr_adapter *adapter;
-	struct mii_bus *mii_bus;
-	int num_rx_desc;
-	int phy_addr;	/* PHY addr on MDIO bus */
-	int pcs_id;	/* PCS id on MDIO bus */
-	int port_id;	/* Port(gmac/xgmac) number, i.e 0-7 */
-	int tx_stnid;
-	u32 __iomem *mii_addr;
-	u32 __iomem *serdes_addr;
-	u32 __iomem *pcs_addr;
-	u32 __iomem *gpio_addr;
-	int phy_speed;
-	int port_type;
-	struct timer_list queue_timer;
-	int wakeup_q;
-	struct platform_device *pdev;
-	struct xlr_net_data *nd;
-
-	u64 *frin_spill;
-	u64 *frout_spill;
-	u64 *class_0_spill;
-	u64 *class_1_spill;
-	u64 *class_2_spill;
-	u64 *class_3_spill;
-};
-
-void xlr_set_gmac_speed(struct xlr_net_priv *priv);
diff --git a/drivers/staging/r8188eu/core/rtw_mlme_ext.c b/drivers/staging/r8188eu/core/rtw_mlme_ext.c
index 55c3d4a6faeb..b4820ad2cee7 100644
--- a/drivers/staging/r8188eu/core/rtw_mlme_ext.c
+++ b/drivers/staging/r8188eu/core/rtw_mlme_ext.c
@@ -107,6 +107,7 @@ static struct rt_channel_plan_map	RTW_ChannelPlanMap[RT_CHANNEL_DOMAIN_MAX] = {
 	{0x01},	/* 0x10, RT_CHANNEL_DOMAIN_JAPAN */
 	{0x02},	/* 0x11, RT_CHANNEL_DOMAIN_FCC_NO_DFS */
 	{0x01},	/* 0x12, RT_CHANNEL_DOMAIN_JAPAN_NO_DFS */
+	{0x00}, /* 0x13 */
 	{0x02},	/* 0x14, RT_CHANNEL_DOMAIN_TAIWAN_NO_DFS */
 	{0x00},	/* 0x15, RT_CHANNEL_DOMAIN_ETSI_NO_DFS */
 	{0x00},	/* 0x16, RT_CHANNEL_DOMAIN_KOREA_NO_DFS */
@@ -118,6 +119,7 @@ static struct rt_channel_plan_map	RTW_ChannelPlanMap[RT_CHANNEL_DOMAIN_MAX] = {
 	{0x00},	/* 0x1C, */
 	{0x00},	/* 0x1D, */
 	{0x00},	/* 0x1E, */
+	{0x00},	/* 0x1F, */
 	/*  0x20 ~ 0x7F , New Define ===== */
 	{0x00},	/* 0x20, RT_CHANNEL_DOMAIN_WORLD_NULL */
 	{0x01},	/* 0x21, RT_CHANNEL_DOMAIN_ETSI1_NULL */
@@ -6845,12 +6847,12 @@ void report_del_sta_event(struct adapter *padapter, unsigned char *MacAddr, unsi
 	struct mlme_ext_priv		*pmlmeext = &padapter->mlmeextpriv;
 	struct cmd_priv *pcmdpriv = &padapter->cmdpriv;
 
-	pcmd_obj = kzalloc(sizeof(struct cmd_obj), GFP_KERNEL);
+	pcmd_obj = kzalloc(sizeof(*pcmd_obj), GFP_ATOMIC);
 	if (!pcmd_obj)
 		return;
 
 	cmdsz = (sizeof(struct stadel_event) + sizeof(struct C2HEvent_Header));
-	pevtcmd = kzalloc(cmdsz, GFP_KERNEL);
+	pevtcmd = kzalloc(cmdsz, GFP_ATOMIC);
 	if (!pevtcmd) {
 		kfree(pcmd_obj);
 		return;
diff --git a/drivers/staging/r8188eu/os_dep/ioctl_linux.c b/drivers/staging/r8188eu/os_dep/ioctl_linux.c
index 52d42e576443..9404355726d0 100644
--- a/drivers/staging/r8188eu/os_dep/ioctl_linux.c
+++ b/drivers/staging/r8188eu/os_dep/ioctl_linux.c
@@ -1980,6 +1980,7 @@ static int rtw_wx_read32(struct net_device *dev,
 	u32 data32;
 	u32 bytes;
 	u8 *ptmp;
+	int ret;
 
 	padapter = (struct adapter *)rtw_netdev_priv(dev);
 	p = &wrqu->data;
@@ -2007,12 +2008,17 @@ static int rtw_wx_read32(struct net_device *dev,
 		break;
 	default:
 		DBG_88E(KERN_INFO "%s: usage> read [bytes],[address(hex)]\n", __func__);
-		return -EINVAL;
+		ret = -EINVAL;
+		goto err_free_ptmp;
 	}
 	DBG_88E(KERN_INFO "%s: addr = 0x%08X data =%s\n", __func__, addr, extra);
 
 	kfree(ptmp);
 	return 0;
+
+err_free_ptmp:
+	kfree(ptmp);
+	return ret;
 }
 
 static int rtw_wx_write32(struct net_device *dev,
diff --git a/drivers/staging/r8188eu/os_dep/mlme_linux.c b/drivers/staging/r8188eu/os_dep/mlme_linux.c
index a9b6ffdbf31a..f7ce724ebf87 100644
--- a/drivers/staging/r8188eu/os_dep/mlme_linux.c
+++ b/drivers/staging/r8188eu/os_dep/mlme_linux.c
@@ -112,7 +112,7 @@ void rtw_report_sec_ie(struct adapter *adapter, u8 authmode, u8 *sec_ie)
 
 	buff = NULL;
 	if (authmode == _WPA_IE_ID_) {
-		buff = kzalloc(IW_CUSTOM_MAX, GFP_KERNEL);
+		buff = kzalloc(IW_CUSTOM_MAX, GFP_ATOMIC);
 		if (!buff)
 			return;
 		p = buff;
diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c
index d2e9df60e9ba..b9ce71848023 100644
--- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c
+++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c
@@ -2549,13 +2549,14 @@ static void _rtl92e_pci_disconnect(struct pci_dev *pdev)
 			free_irq(dev->irq, dev);
 			priv->irq = 0;
 		}
-		free_rtllib(dev);
 
 		if (dev->mem_start != 0) {
 			iounmap((void __iomem *)dev->mem_start);
 			release_mem_region(pci_resource_start(pdev, 1),
 					pci_resource_len(pdev, 1));
 		}
+
+		free_rtllib(dev);
 	}
 
 	pci_disable_device(pdev);
diff --git a/drivers/target/target_core_fabric_configfs.c b/drivers/target/target_core_fabric_configfs.c
index 0b65de9f2df1..95a88f6224cd 100644
--- a/drivers/target/target_core_fabric_configfs.c
+++ b/drivers/target/target_core_fabric_configfs.c
@@ -520,7 +520,7 @@ static ssize_t target_fabric_port_alua_tg_pt_gp_show(struct config_item *item,
 {
 	struct se_lun *lun = item_to_lun(item);
 
-	if (!lun || !lun->lun_se_dev)
+	if (!lun->lun_se_dev)
 		return -ENODEV;
 
 	return core_alua_show_tg_pt_gp_info(lun, page);
@@ -531,7 +531,7 @@ static ssize_t target_fabric_port_alua_tg_pt_gp_store(struct config_item *item,
 {
 	struct se_lun *lun = item_to_lun(item);
 
-	if (!lun || !lun->lun_se_dev)
+	if (!lun->lun_se_dev)
 		return -ENODEV;
 
 	return core_alua_store_tg_pt_gp_info(lun, page, count);
@@ -542,7 +542,7 @@ static ssize_t target_fabric_port_alua_tg_pt_offline_show(
 {
 	struct se_lun *lun = item_to_lun(item);
 
-	if (!lun || !lun->lun_se_dev)
+	if (!lun->lun_se_dev)
 		return -ENODEV;
 
 	return core_alua_show_offline_bit(lun, page);
@@ -553,7 +553,7 @@ static ssize_t target_fabric_port_alua_tg_pt_offline_store(
 {
 	struct se_lun *lun = item_to_lun(item);
 
-	if (!lun || !lun->lun_se_dev)
+	if (!lun->lun_se_dev)
 		return -ENODEV;
 
 	return core_alua_store_offline_bit(lun, page, count);
@@ -564,7 +564,7 @@ static ssize_t target_fabric_port_alua_tg_pt_status_show(
 {
 	struct se_lun *lun = item_to_lun(item);
 
-	if (!lun || !lun->lun_se_dev)
+	if (!lun->lun_se_dev)
 		return -ENODEV;
 
 	return core_alua_show_secondary_status(lun, page);
@@ -575,7 +575,7 @@ static ssize_t target_fabric_port_alua_tg_pt_status_store(
 {
 	struct se_lun *lun = item_to_lun(item);
 
-	if (!lun || !lun->lun_se_dev)
+	if (!lun->lun_se_dev)
 		return -ENODEV;
 
 	return core_alua_store_secondary_status(lun, page, count);
@@ -586,7 +586,7 @@ static ssize_t target_fabric_port_alua_tg_pt_write_md_show(
 {
 	struct se_lun *lun = item_to_lun(item);
 
-	if (!lun || !lun->lun_se_dev)
+	if (!lun->lun_se_dev)
 		return -ENODEV;
 
 	return core_alua_show_secondary_write_metadata(lun, page);
@@ -597,7 +597,7 @@ static ssize_t target_fabric_port_alua_tg_pt_write_md_store(
 {
 	struct se_lun *lun = item_to_lun(item);
 
-	if (!lun || !lun->lun_se_dev)
+	if (!lun->lun_se_dev)
 		return -ENODEV;
 
 	return core_alua_store_secondary_write_metadata(lun, page, count);
diff --git a/drivers/target/target_core_spc.c b/drivers/target/target_core_spc.c
index 22703a0dbd07..4c76498d3fb0 100644
--- a/drivers/target/target_core_spc.c
+++ b/drivers/target/target_core_spc.c
@@ -40,11 +40,11 @@ static void spc_fill_alua_data(struct se_lun *lun, unsigned char *buf)
 	 *
 	 * See spc4r17 section 6.4.2 Table 135
 	 */
-	spin_lock(&lun->lun_tg_pt_gp_lock);
-	tg_pt_gp = lun->lun_tg_pt_gp;
+	rcu_read_lock();
+	tg_pt_gp = rcu_dereference(lun->lun_tg_pt_gp);
 	if (tg_pt_gp)
 		buf[5] |= tg_pt_gp->tg_pt_gp_alua_access_type;
-	spin_unlock(&lun->lun_tg_pt_gp_lock);
+	rcu_read_unlock();
 }
 
 static u16
@@ -325,14 +325,14 @@ check_t10_vend_desc:
 		 * Get the PROTOCOL IDENTIFIER as defined by spc4r17
 		 * section 7.5.1 Table 362
 		 */
-		spin_lock(&lun->lun_tg_pt_gp_lock);
-		tg_pt_gp = lun->lun_tg_pt_gp;
+		rcu_read_lock();
+		tg_pt_gp = rcu_dereference(lun->lun_tg_pt_gp);
 		if (!tg_pt_gp) {
-			spin_unlock(&lun->lun_tg_pt_gp_lock);
+			rcu_read_unlock();
 			goto check_lu_gp;
 		}
 		tg_pt_gp_id = tg_pt_gp->tg_pt_gp_id;
-		spin_unlock(&lun->lun_tg_pt_gp_lock);
+		rcu_read_unlock();
 
 		buf[off] = tpg->proto_id << 4;
 		buf[off++] |= 0x1; /* CODE SET == Binary */
diff --git a/drivers/tee/amdtee/core.c b/drivers/tee/amdtee/core.c
index da6b88e80dc0..297dc62bca29 100644
--- a/drivers/tee/amdtee/core.c
+++ b/drivers/tee/amdtee/core.c
@@ -203,9 +203,8 @@ static int copy_ta_binary(struct tee_context *ctx, void *ptr, void **ta,
 
 	*ta_size = roundup(fw->size, PAGE_SIZE);
 	*ta = (void *)__get_free_pages(GFP_KERNEL, get_order(*ta_size));
-	if (IS_ERR(*ta)) {
-		pr_err("%s: get_free_pages failed 0x%llx\n", __func__,
-		       (u64)*ta);
+	if (!*ta) {
+		pr_err("%s: get_free_pages failed\n", __func__);
 		rc = -ENOMEM;
 		goto rel_fw;
 	}
diff --git a/drivers/tee/optee/core.c b/drivers/tee/optee/core.c
index ab2edfcc6c70..2a66a5203d2f 100644
--- a/drivers/tee/optee/core.c
+++ b/drivers/tee/optee/core.c
@@ -48,10 +48,8 @@ int optee_pool_op_alloc_helper(struct tee_shm_pool_mgr *poolm,
 			goto err;
 		}
 
-		for (i = 0; i < nr_pages; i++) {
-			pages[i] = page;
-			page++;
-		}
+		for (i = 0; i < nr_pages; i++)
+			pages[i] = page + i;
 
 		shm->flags |= TEE_SHM_REGISTER;
 		rc = shm_register(shm->ctx, shm, pages, nr_pages,
diff --git a/drivers/tee/optee/ffa_abi.c b/drivers/tee/optee/ffa_abi.c
index 45424824e0f9..d8c8683863aa 100644
--- a/drivers/tee/optee/ffa_abi.c
+++ b/drivers/tee/optee/ffa_abi.c
@@ -810,10 +810,9 @@ static int optee_ffa_probe(struct ffa_device *ffa_dev)
 		return -EINVAL;
 
 	optee = kzalloc(sizeof(*optee), GFP_KERNEL);
-	if (!optee) {
-		rc = -ENOMEM;
-		goto err;
-	}
+	if (!optee)
+		return -ENOMEM;
+
 	optee->pool = optee_ffa_config_dyn_shm();
 	if (IS_ERR(optee->pool)) {
 		rc = PTR_ERR(optee->pool);
diff --git a/drivers/tee/optee/smc_abi.c b/drivers/tee/optee/smc_abi.c
index 6196d7c3888f..cf2e3293567d 100644
--- a/drivers/tee/optee/smc_abi.c
+++ b/drivers/tee/optee/smc_abi.c
@@ -23,6 +23,7 @@
 #include "optee_private.h"
 #include "optee_smc.h"
 #include "optee_rpc_cmd.h"
+#include <linux/kmemleak.h>
 #define CREATE_TRACE_POINTS
 #include "optee_trace.h"
 
@@ -783,6 +784,7 @@ static void optee_handle_rpc(struct tee_context *ctx,
 			param->a4 = 0;
 			param->a5 = 0;
 		}
+		kmemleak_not_leak(shm);
 		break;
 	case OPTEE_SMC_RPC_FUNC_FREE:
 		shm = reg_pair_to_ptr(param->a1, param->a2);
diff --git a/drivers/tee/tee_shm.c b/drivers/tee/tee_shm.c
index 8a8deb95e918..499fccba3d74 100644
--- a/drivers/tee/tee_shm.c
+++ b/drivers/tee/tee_shm.c
@@ -1,20 +1,17 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (c) 2015-2016, Linaro Limited
+ * Copyright (c) 2015-2017, 2019-2021 Linaro Limited
  */
+#include <linux/anon_inodes.h>
 #include <linux/device.h>
-#include <linux/dma-buf.h>
-#include <linux/fdtable.h>
 #include <linux/idr.h>
+#include <linux/mm.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/tee_drv.h>
 #include <linux/uio.h>
-#include <linux/module.h>
 #include "tee_private.h"
 
-MODULE_IMPORT_NS(DMA_BUF);
-
 static void release_registered_pages(struct tee_shm *shm)
 {
 	if (shm->pages) {
@@ -31,16 +28,8 @@ static void release_registered_pages(struct tee_shm *shm)
 	}
 }
 
-static void tee_shm_release(struct tee_shm *shm)
+static void tee_shm_release(struct tee_device *teedev, struct tee_shm *shm)
 {
-	struct tee_device *teedev = shm->ctx->teedev;
-
-	if (shm->flags & TEE_SHM_DMA_BUF) {
-		mutex_lock(&teedev->mutex);
-		idr_remove(&teedev->idr, shm->id);
-		mutex_unlock(&teedev->mutex);
-	}
-
 	if (shm->flags & TEE_SHM_POOL) {
 		struct tee_shm_pool_mgr *poolm;
 
@@ -67,45 +56,6 @@ static void tee_shm_release(struct tee_shm *shm)
 	tee_device_put(teedev);
 }
 
-static struct sg_table *tee_shm_op_map_dma_buf(struct dma_buf_attachment
-			*attach, enum dma_data_direction dir)
-{
-	return NULL;
-}
-
-static void tee_shm_op_unmap_dma_buf(struct dma_buf_attachment *attach,
-				     struct sg_table *table,
-				     enum dma_data_direction dir)
-{
-}
-
-static void tee_shm_op_release(struct dma_buf *dmabuf)
-{
-	struct tee_shm *shm = dmabuf->priv;
-
-	tee_shm_release(shm);
-}
-
-static int tee_shm_op_mmap(struct dma_buf *dmabuf, struct vm_area_struct *vma)
-{
-	struct tee_shm *shm = dmabuf->priv;
-	size_t size = vma->vm_end - vma->vm_start;
-
-	/* Refuse sharing shared memory provided by application */
-	if (shm->flags & TEE_SHM_USER_MAPPED)
-		return -EINVAL;
-
-	return remap_pfn_range(vma, vma->vm_start, shm->paddr >> PAGE_SHIFT,
-			       size, vma->vm_page_prot);
-}
-
-static const struct dma_buf_ops tee_shm_dma_buf_ops = {
-	.map_dma_buf = tee_shm_op_map_dma_buf,
-	.unmap_dma_buf = tee_shm_op_unmap_dma_buf,
-	.release = tee_shm_op_release,
-	.mmap = tee_shm_op_mmap,
-};
-
 struct tee_shm *tee_shm_alloc(struct tee_context *ctx, size_t size, u32 flags)
 {
 	struct tee_device *teedev = ctx->teedev;
@@ -140,6 +90,7 @@ struct tee_shm *tee_shm_alloc(struct tee_context *ctx, size_t size, u32 flags)
 		goto err_dev_put;
 	}
 
+	refcount_set(&shm->refcount, 1);
 	shm->flags = flags | TEE_SHM_POOL;
 	shm->ctx = ctx;
 	if (flags & TEE_SHM_DMA_BUF)
@@ -153,10 +104,7 @@ struct tee_shm *tee_shm_alloc(struct tee_context *ctx, size_t size, u32 flags)
 		goto err_kfree;
 	}
 
-
 	if (flags & TEE_SHM_DMA_BUF) {
-		DEFINE_DMA_BUF_EXPORT_INFO(exp_info);
-
 		mutex_lock(&teedev->mutex);
 		shm->id = idr_alloc(&teedev->idr, shm, 1, 0, GFP_KERNEL);
 		mutex_unlock(&teedev->mutex);
@@ -164,28 +112,11 @@ struct tee_shm *tee_shm_alloc(struct tee_context *ctx, size_t size, u32 flags)
 			ret = ERR_PTR(shm->id);
 			goto err_pool_free;
 		}
-
-		exp_info.ops = &tee_shm_dma_buf_ops;
-		exp_info.size = shm->size;
-		exp_info.flags = O_RDWR;
-		exp_info.priv = shm;
-
-		shm->dmabuf = dma_buf_export(&exp_info);
-		if (IS_ERR(shm->dmabuf)) {
-			ret = ERR_CAST(shm->dmabuf);
-			goto err_rem;
-		}
 	}
 
 	teedev_ctx_get(ctx);
 
 	return shm;
-err_rem:
-	if (flags & TEE_SHM_DMA_BUF) {
-		mutex_lock(&teedev->mutex);
-		idr_remove(&teedev->idr, shm->id);
-		mutex_unlock(&teedev->mutex);
-	}
 err_pool_free:
 	poolm->ops->free(poolm, shm);
 err_kfree:
@@ -246,6 +177,7 @@ struct tee_shm *tee_shm_register(struct tee_context *ctx, unsigned long addr,
 		goto err;
 	}
 
+	refcount_set(&shm->refcount, 1);
 	shm->flags = flags | TEE_SHM_REGISTER;
 	shm->ctx = ctx;
 	shm->id = -1;
@@ -306,22 +238,6 @@ struct tee_shm *tee_shm_register(struct tee_context *ctx, unsigned long addr,
 		goto err;
 	}
 
-	if (flags & TEE_SHM_DMA_BUF) {
-		DEFINE_DMA_BUF_EXPORT_INFO(exp_info);
-
-		exp_info.ops = &tee_shm_dma_buf_ops;
-		exp_info.size = shm->size;
-		exp_info.flags = O_RDWR;
-		exp_info.priv = shm;
-
-		shm->dmabuf = dma_buf_export(&exp_info);
-		if (IS_ERR(shm->dmabuf)) {
-			ret = ERR_CAST(shm->dmabuf);
-			teedev->desc->ops->shm_unregister(ctx, shm);
-			goto err;
-		}
-	}
-
 	return shm;
 err:
 	if (shm) {
@@ -339,6 +255,35 @@ err:
 }
 EXPORT_SYMBOL_GPL(tee_shm_register);
 
+static int tee_shm_fop_release(struct inode *inode, struct file *filp)
+{
+	tee_shm_put(filp->private_data);
+	return 0;
+}
+
+static int tee_shm_fop_mmap(struct file *filp, struct vm_area_struct *vma)
+{
+	struct tee_shm *shm = filp->private_data;
+	size_t size = vma->vm_end - vma->vm_start;
+
+	/* Refuse sharing shared memory provided by application */
+	if (shm->flags & TEE_SHM_USER_MAPPED)
+		return -EINVAL;
+
+	/* check for overflowing the buffer's size */
+	if (vma->vm_pgoff + vma_pages(vma) > shm->size >> PAGE_SHIFT)
+		return -EINVAL;
+
+	return remap_pfn_range(vma, vma->vm_start, shm->paddr >> PAGE_SHIFT,
+			       size, vma->vm_page_prot);
+}
+
+static const struct file_operations tee_shm_fops = {
+	.owner = THIS_MODULE,
+	.release = tee_shm_fop_release,
+	.mmap = tee_shm_fop_mmap,
+};
+
 /**
  * tee_shm_get_fd() - Increase reference count and return file descriptor
  * @shm:	Shared memory handle
@@ -351,10 +296,11 @@ int tee_shm_get_fd(struct tee_shm *shm)
 	if (!(shm->flags & TEE_SHM_DMA_BUF))
 		return -EINVAL;
 
-	get_dma_buf(shm->dmabuf);
-	fd = dma_buf_fd(shm->dmabuf, O_CLOEXEC);
+	/* matched by tee_shm_put() in tee_shm_op_release() */
+	refcount_inc(&shm->refcount);
+	fd = anon_inode_getfd("tee_shm", &tee_shm_fops, shm, O_RDWR);
 	if (fd < 0)
-		dma_buf_put(shm->dmabuf);
+		tee_shm_put(shm);
 	return fd;
 }
 
@@ -364,17 +310,7 @@ int tee_shm_get_fd(struct tee_shm *shm)
  */
 void tee_shm_free(struct tee_shm *shm)
 {
-	/*
-	 * dma_buf_put() decreases the dmabuf reference counter and will
-	 * call tee_shm_release() when the last reference is gone.
-	 *
-	 * In the case of driver private memory we call tee_shm_release
-	 * directly instead as it doesn't have a reference counter.
-	 */
-	if (shm->flags & TEE_SHM_DMA_BUF)
-		dma_buf_put(shm->dmabuf);
-	else
-		tee_shm_release(shm);
+	tee_shm_put(shm);
 }
 EXPORT_SYMBOL_GPL(tee_shm_free);
 
@@ -481,10 +417,15 @@ struct tee_shm *tee_shm_get_from_id(struct tee_context *ctx, int id)
 	teedev = ctx->teedev;
 	mutex_lock(&teedev->mutex);
 	shm = idr_find(&teedev->idr, id);
+	/*
+	 * If the tee_shm was found in the IDR it must have a refcount
+	 * larger than 0 due to the guarantee in tee_shm_put() below. So
+	 * it's safe to use refcount_inc().
+	 */
 	if (!shm || shm->ctx != ctx)
 		shm = ERR_PTR(-EINVAL);
-	else if (shm->flags & TEE_SHM_DMA_BUF)
-		get_dma_buf(shm->dmabuf);
+	else
+		refcount_inc(&shm->refcount);
 	mutex_unlock(&teedev->mutex);
 	return shm;
 }
@@ -496,7 +437,24 @@ EXPORT_SYMBOL_GPL(tee_shm_get_from_id);
  */
 void tee_shm_put(struct tee_shm *shm)
 {
-	if (shm->flags & TEE_SHM_DMA_BUF)
-		dma_buf_put(shm->dmabuf);
+	struct tee_device *teedev = shm->ctx->teedev;
+	bool do_release = false;
+
+	mutex_lock(&teedev->mutex);
+	if (refcount_dec_and_test(&shm->refcount)) {
+		/*
+		 * refcount has reached 0, we must now remove it from the
+		 * IDR before releasing the mutex. This will guarantee that
+		 * the refcount_inc() in tee_shm_get_from_id() never starts
+		 * from 0.
+		 */
+		if (shm->flags & TEE_SHM_DMA_BUF)
+			idr_remove(&teedev->idr, shm->id);
+		do_release = true;
+	}
+	mutex_unlock(&teedev->mutex);
+
+	if (do_release)
+		tee_shm_release(teedev, shm);
 }
 EXPORT_SYMBOL_GPL(tee_shm_put);
diff --git a/drivers/thermal/intel/int340x_thermal/Kconfig b/drivers/thermal/intel/int340x_thermal/Kconfig
index 45c31f3d6054..5d046de96a5d 100644
--- a/drivers/thermal/intel/int340x_thermal/Kconfig
+++ b/drivers/thermal/intel/int340x_thermal/Kconfig
@@ -5,12 +5,12 @@
 
 config INT340X_THERMAL
 	tristate "ACPI INT340X thermal drivers"
-	depends on X86 && ACPI && PCI
+	depends on X86_64 && ACPI && PCI
 	select THERMAL_GOV_USER_SPACE
 	select ACPI_THERMAL_REL
 	select ACPI_FAN
 	select INTEL_SOC_DTS_IOSF_CORE
-	select PROC_THERMAL_MMIO_RAPL if X86_64 && POWERCAP
+	select PROC_THERMAL_MMIO_RAPL if POWERCAP
 	help
 	  Newer laptops and tablets that use ACPI may have thermal sensors and
 	  other devices with thermal control capabilities outside the core
diff --git a/drivers/thermal/intel/int340x_thermal/processor_thermal_rfim.c b/drivers/thermal/intel/int340x_thermal/processor_thermal_rfim.c
index b25b54d4bac1..e693ec8234fb 100644
--- a/drivers/thermal/intel/int340x_thermal/processor_thermal_rfim.c
+++ b/drivers/thermal/intel/int340x_thermal/processor_thermal_rfim.c
@@ -29,7 +29,7 @@ static const char * const fivr_strings[] = {
 };
 
 static const struct mmio_reg tgl_fivr_mmio_regs[] = {
-	{ 0, 0x5A18, 3, 0x7, 12}, /* vco_ref_code_lo */
+	{ 0, 0x5A18, 3, 0x7, 11}, /* vco_ref_code_lo */
 	{ 0, 0x5A18, 8, 0xFF, 16}, /* vco_ref_code_hi */
 	{ 0, 0x5A08, 8, 0xFF, 0}, /* spread_spectrum_pct */
 	{ 0, 0x5A08, 1, 0x1, 8}, /* spread_spectrum_clk_enable */
diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index 648829ab79ff..82654dc8382b 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -421,6 +421,8 @@ static void thermal_zone_device_init(struct thermal_zone_device *tz)
 {
 	struct thermal_instance *pos;
 	tz->temperature = THERMAL_TEMP_INVALID;
+	tz->prev_low_trip = -INT_MAX;
+	tz->prev_high_trip = INT_MAX;
 	list_for_each_entry(pos, &tz->thermal_instances, tz_node)
 		pos->initialized = false;
 }
diff --git a/drivers/tty/hvc/hvc_xen.c b/drivers/tty/hvc/hvc_xen.c
index f0bf01ea069a..ebaf7500f48f 100644
--- a/drivers/tty/hvc/hvc_xen.c
+++ b/drivers/tty/hvc/hvc_xen.c
@@ -37,6 +37,8 @@ struct xencons_info {
 	struct xenbus_device *xbdev;
 	struct xencons_interface *intf;
 	unsigned int evtchn;
+	XENCONS_RING_IDX out_cons;
+	unsigned int out_cons_same;
 	struct hvc_struct *hvc;
 	int irq;
 	int vtermno;
@@ -138,6 +140,8 @@ static int domU_read_console(uint32_t vtermno, char *buf, int len)
 	XENCONS_RING_IDX cons, prod;
 	int recv = 0;
 	struct xencons_info *xencons = vtermno_to_xencons(vtermno);
+	unsigned int eoiflag = 0;
+
 	if (xencons == NULL)
 		return -EINVAL;
 	intf = xencons->intf;
@@ -157,7 +161,27 @@ static int domU_read_console(uint32_t vtermno, char *buf, int len)
 	mb();			/* read ring before consuming */
 	intf->in_cons = cons;
 
-	notify_daemon(xencons);
+	/*
+	 * When to mark interrupt having been spurious:
+	 * - there was no new data to be read, and
+	 * - the backend did not consume some output bytes, and
+	 * - the previous round with no read data didn't see consumed bytes
+	 *   (we might have a race with an interrupt being in flight while
+	 *   updating xencons->out_cons, so account for that by allowing one
+	 *   round without any visible reason)
+	 */
+	if (intf->out_cons != xencons->out_cons) {
+		xencons->out_cons = intf->out_cons;
+		xencons->out_cons_same = 0;
+	}
+	if (recv) {
+		notify_daemon(xencons);
+	} else if (xencons->out_cons_same++ > 1) {
+		eoiflag = XEN_EOI_FLAG_SPURIOUS;
+	}
+
+	xen_irq_lateeoi(xencons->irq, eoiflag);
+
 	return recv;
 }
 
@@ -386,7 +410,7 @@ static int xencons_connect_backend(struct xenbus_device *dev,
 	if (ret)
 		return ret;
 	info->evtchn = evtchn;
-	irq = bind_evtchn_to_irq(evtchn);
+	irq = bind_interdomain_evtchn_to_irq_lateeoi(dev, evtchn);
 	if (irq < 0)
 		return irq;
 	info->irq = irq;
@@ -522,6 +546,7 @@ static struct xenbus_driver xencons_driver = {
 	.remove = xencons_remove,
 	.resume = xencons_resume,
 	.otherend_changed = xencons_backend_changed,
+	.not_essential = true,
 };
 #endif /* CONFIG_HVC_XEN_FRONTEND */
 
@@ -550,7 +575,7 @@ static int __init xen_hvc_init(void)
 			return r;
 
 		info = vtermno_to_xencons(HVC_COOKIE);
-		info->irq = bind_evtchn_to_irq(info->evtchn);
+		info->irq = bind_evtchn_to_irq_lateeoi(info->evtchn);
 	}
 	if (info->irq < 0)
 		info->irq = 0; /* NO_IRQ */
diff --git a/drivers/tty/n_hdlc.c b/drivers/tty/n_hdlc.c
index 7e0884ecc74f..23ba1fc99df8 100644
--- a/drivers/tty/n_hdlc.c
+++ b/drivers/tty/n_hdlc.c
@@ -140,6 +140,8 @@ struct n_hdlc {
 	struct n_hdlc_buf_list	rx_buf_list;
 	struct n_hdlc_buf_list	tx_free_buf_list;
 	struct n_hdlc_buf_list	rx_free_buf_list;
+	struct work_struct	write_work;
+	struct tty_struct	*tty_for_write_work;
 };
 
 /*
@@ -154,6 +156,7 @@ static struct n_hdlc_buf *n_hdlc_buf_get(struct n_hdlc_buf_list *list);
 /* Local functions */
 
 static struct n_hdlc *n_hdlc_alloc(void);
+static void n_hdlc_tty_write_work(struct work_struct *work);
 
 /* max frame size for memory allocations */
 static int maxframe = 4096;
@@ -210,6 +213,8 @@ static void n_hdlc_tty_close(struct tty_struct *tty)
 	wake_up_interruptible(&tty->read_wait);
 	wake_up_interruptible(&tty->write_wait);
 
+	cancel_work_sync(&n_hdlc->write_work);
+
 	n_hdlc_free_buf_list(&n_hdlc->rx_free_buf_list);
 	n_hdlc_free_buf_list(&n_hdlc->tx_free_buf_list);
 	n_hdlc_free_buf_list(&n_hdlc->rx_buf_list);
@@ -241,6 +246,8 @@ static int n_hdlc_tty_open(struct tty_struct *tty)
 		return -ENFILE;
 	}
 
+	INIT_WORK(&n_hdlc->write_work, n_hdlc_tty_write_work);
+	n_hdlc->tty_for_write_work = tty;
 	tty->disc_data = n_hdlc;
 	tty->receive_room = 65536;
 
@@ -335,6 +342,20 @@ check_again:
 }	/* end of n_hdlc_send_frames() */
 
 /**
+ * n_hdlc_tty_write_work - Asynchronous callback for transmit wakeup
+ * @work: pointer to work_struct
+ *
+ * Called when low level device driver can accept more send data.
+ */
+static void n_hdlc_tty_write_work(struct work_struct *work)
+{
+	struct n_hdlc *n_hdlc = container_of(work, struct n_hdlc, write_work);
+	struct tty_struct *tty = n_hdlc->tty_for_write_work;
+
+	n_hdlc_send_frames(n_hdlc, tty);
+}	/* end of n_hdlc_tty_write_work() */
+
+/**
  * n_hdlc_tty_wakeup - Callback for transmit wakeup
  * @tty: pointer to associated tty instance data
  *
@@ -344,7 +365,7 @@ static void n_hdlc_tty_wakeup(struct tty_struct *tty)
 {
 	struct n_hdlc *n_hdlc = tty->disc_data;
 
-	n_hdlc_send_frames(n_hdlc, tty);
+	schedule_work(&n_hdlc->write_work);
 }	/* end of n_hdlc_tty_wakeup() */
 
 /**
diff --git a/drivers/tty/serial/8250/8250_bcm7271.c b/drivers/tty/serial/8250/8250_bcm7271.c
index 7f656fac503f..5163d60756b7 100644
--- a/drivers/tty/serial/8250/8250_bcm7271.c
+++ b/drivers/tty/serial/8250/8250_bcm7271.c
@@ -237,6 +237,7 @@ struct brcmuart_priv {
 	u32		rx_err;
 	u32		rx_timeout;
 	u32		rx_abort;
+	u32		saved_mctrl;
 };
 
 static struct dentry *brcmuart_debugfs_root;
@@ -1133,16 +1134,27 @@ static int brcmuart_remove(struct platform_device *pdev)
 static int __maybe_unused brcmuart_suspend(struct device *dev)
 {
 	struct brcmuart_priv *priv = dev_get_drvdata(dev);
+	struct uart_8250_port *up = serial8250_get_port(priv->line);
+	struct uart_port *port = &up->port;
 
 	serial8250_suspend_port(priv->line);
 	clk_disable_unprepare(priv->baud_mux_clk);
 
+	/*
+	 * This will prevent resume from enabling RTS before the
+	 *  baud rate has been resored.
+	 */
+	priv->saved_mctrl = port->mctrl;
+	port->mctrl = 0;
+
 	return 0;
 }
 
 static int __maybe_unused brcmuart_resume(struct device *dev)
 {
 	struct brcmuart_priv *priv = dev_get_drvdata(dev);
+	struct uart_8250_port *up = serial8250_get_port(priv->line);
+	struct uart_port *port = &up->port;
 	int ret;
 
 	ret = clk_prepare_enable(priv->baud_mux_clk);
@@ -1165,6 +1177,7 @@ static int __maybe_unused brcmuart_resume(struct device *dev)
 		start_rx_dma(serial8250_get_port(priv->line));
 	}
 	serial8250_resume_port(priv->line);
+	port->mctrl = priv->saved_mctrl;
 	return 0;
 }
 
diff --git a/drivers/tty/serial/8250/8250_fintek.c b/drivers/tty/serial/8250/8250_fintek.c
index 31c9e83ea3cb..251f0018ae8c 100644
--- a/drivers/tty/serial/8250/8250_fintek.c
+++ b/drivers/tty/serial/8250/8250_fintek.c
@@ -290,25 +290,6 @@ static void fintek_8250_set_max_fifo(struct fintek_8250 *pdata)
 	}
 }
 
-static void fintek_8250_goto_highspeed(struct uart_8250_port *uart,
-			      struct fintek_8250 *pdata)
-{
-	sio_write_reg(pdata, LDN, pdata->index);
-
-	switch (pdata->pid) {
-	case CHIP_ID_F81966:
-	case CHIP_ID_F81866: /* set uart clock for high speed serial mode */
-		sio_write_mask_reg(pdata, F81866_UART_CLK,
-			F81866_UART_CLK_MASK,
-			F81866_UART_CLK_14_769MHZ);
-
-		uart->port.uartclk = 921600 * 16;
-		break;
-	default: /* leave clock speed untouched */
-		break;
-	}
-}
-
 static void fintek_8250_set_termios(struct uart_port *port,
 				    struct ktermios *termios,
 				    struct ktermios *old)
@@ -430,7 +411,6 @@ static int probe_setup_port(struct fintek_8250 *pdata,
 
 				fintek_8250_set_irq_mode(pdata, level_mode);
 				fintek_8250_set_max_fifo(pdata);
-				fintek_8250_goto_highspeed(uart, pdata);
 
 				fintek_8250_exit_key(addr[i]);
 
diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c
index 5d43de143f33..60f8fffdfd77 100644
--- a/drivers/tty/serial/8250/8250_pci.c
+++ b/drivers/tty/serial/8250/8250_pci.c
@@ -1324,29 +1324,33 @@ pericom_do_set_divisor(struct uart_port *port, unsigned int baud,
 {
 	int scr;
 	int lcr;
-	int actual_baud;
-	int tolerance;
 
-	for (scr = 5 ; scr <= 15 ; scr++) {
-		actual_baud = 921600 * 16 / scr;
-		tolerance = actual_baud / 50;
+	for (scr = 16; scr > 4; scr--) {
+		unsigned int maxrate = port->uartclk / scr;
+		unsigned int divisor = max(maxrate / baud, 1U);
+		int delta = maxrate / divisor - baud;
 
-		if ((baud < actual_baud + tolerance) &&
-			(baud > actual_baud - tolerance)) {
+		if (baud > maxrate + baud / 50)
+			continue;
 
+		if (delta > baud / 50)
+			divisor++;
+
+		if (divisor > 0xffff)
+			continue;
+
+		/* Update delta due to possible divisor change */
+		delta = maxrate / divisor - baud;
+		if (abs(delta) < baud / 50) {
 			lcr = serial_port_in(port, UART_LCR);
 			serial_port_out(port, UART_LCR, lcr | 0x80);
-
-			serial_port_out(port, UART_DLL, 1);
-			serial_port_out(port, UART_DLM, 0);
+			serial_port_out(port, UART_DLL, divisor & 0xff);
+			serial_port_out(port, UART_DLM, divisor >> 8 & 0xff);
 			serial_port_out(port, 2, 16 - scr);
 			serial_port_out(port, UART_LCR, lcr);
 			return;
-		} else if (baud > actual_baud) {
-			break;
 		}
 	}
-	serial8250_do_set_divisor(port, baud, quot, quot_frac);
 }
 static int pci_pericom_setup(struct serial_private *priv,
 		  const struct pciserial_board *board,
@@ -2291,7 +2295,7 @@ static struct pci_serial_quirk pci_serial_quirks[] = {
 		.setup      = pci_pericom_setup_four_at_eight,
 	},
 	{
-		.vendor     = PCI_DEVICE_ID_ACCESIO_PCIE_ICM_4S,
+		.vendor     = PCI_VENDOR_ID_ACCESIO,
 		.device     = PCI_DEVICE_ID_ACCESIO_PCIE_ICM232_4,
 		.subvendor  = PCI_ANY_ID,
 		.subdevice  = PCI_ANY_ID,
@@ -2299,6 +2303,13 @@ static struct pci_serial_quirk pci_serial_quirks[] = {
 	},
 	{
 		.vendor     = PCI_VENDOR_ID_ACCESIO,
+		.device     = PCI_DEVICE_ID_ACCESIO_PCIE_ICM_4S,
+		.subvendor  = PCI_ANY_ID,
+		.subdevice  = PCI_ANY_ID,
+		.setup      = pci_pericom_setup_four_at_eight,
+	},
+	{
+		.vendor     = PCI_VENDOR_ID_ACCESIO,
 		.device     = PCI_DEVICE_ID_ACCESIO_MPCIE_ICM232_4,
 		.subvendor  = PCI_ANY_ID,
 		.subdevice  = PCI_ANY_ID,
diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c
index 5775cbff8f6e..46e2079ad1aa 100644
--- a/drivers/tty/serial/8250/8250_port.c
+++ b/drivers/tty/serial/8250/8250_port.c
@@ -2024,13 +2024,6 @@ void serial8250_do_set_mctrl(struct uart_port *port, unsigned int mctrl)
 	struct uart_8250_port *up = up_to_u8250p(port);
 	unsigned char mcr;
 
-	if (port->rs485.flags & SER_RS485_ENABLED) {
-		if (serial8250_in_MCR(up) & UART_MCR_RTS)
-			mctrl |= TIOCM_RTS;
-		else
-			mctrl &= ~TIOCM_RTS;
-	}
-
 	mcr = serial8250_TIOCM_to_MCR(mctrl);
 
 	mcr = (mcr & up->mcr_mask) | up->mcr_force | up->mcr;
diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig
index 6ff94cfcd9db..fc543ac97c13 100644
--- a/drivers/tty/serial/Kconfig
+++ b/drivers/tty/serial/Kconfig
@@ -1533,7 +1533,7 @@ config SERIAL_LITEUART
 	tristate "LiteUART serial port support"
 	depends on HAS_IOMEM
 	depends on OF || COMPILE_TEST
-	depends on LITEX
+	depends on LITEX || COMPILE_TEST
 	select SERIAL_CORE
 	help
 	  This driver is for the FPGA-based LiteUART serial controller from LiteX
diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c
index d361cd84ff8c..52518a606c06 100644
--- a/drivers/tty/serial/amba-pl011.c
+++ b/drivers/tty/serial/amba-pl011.c
@@ -2947,6 +2947,7 @@ MODULE_DEVICE_TABLE(of, sbsa_uart_of_match);
 
 static const struct acpi_device_id __maybe_unused sbsa_uart_acpi_match[] = {
 	{ "ARMH0011", 0 },
+	{ "ARMHB000", 0 },
 	{},
 };
 MODULE_DEVICE_TABLE(acpi, sbsa_uart_acpi_match);
diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c
index b1e7190ae483..ac5112def40d 100644
--- a/drivers/tty/serial/fsl_lpuart.c
+++ b/drivers/tty/serial/fsl_lpuart.c
@@ -2625,6 +2625,7 @@ OF_EARLYCON_DECLARE(lpuart, "fsl,vf610-lpuart", lpuart_early_console_setup);
 OF_EARLYCON_DECLARE(lpuart32, "fsl,ls1021a-lpuart", lpuart32_early_console_setup);
 OF_EARLYCON_DECLARE(lpuart32, "fsl,ls1028a-lpuart", ls1028a_early_console_setup);
 OF_EARLYCON_DECLARE(lpuart32, "fsl,imx7ulp-lpuart", lpuart32_imx_early_console_setup);
+OF_EARLYCON_DECLARE(lpuart32, "fsl,imx8qxp-lpuart", lpuart32_imx_early_console_setup);
 EARLYCON_DECLARE(lpuart, lpuart_early_console_setup);
 EARLYCON_DECLARE(lpuart32, lpuart32_early_console_setup);
 
diff --git a/drivers/tty/serial/liteuart.c b/drivers/tty/serial/liteuart.c
index dbc0559a9157..2941659e5274 100644
--- a/drivers/tty/serial/liteuart.c
+++ b/drivers/tty/serial/liteuart.c
@@ -270,8 +270,10 @@ static int liteuart_probe(struct platform_device *pdev)
 
 	/* get membase */
 	port->membase = devm_platform_get_and_ioremap_resource(pdev, 0, NULL);
-	if (IS_ERR(port->membase))
-		return PTR_ERR(port->membase);
+	if (IS_ERR(port->membase)) {
+		ret = PTR_ERR(port->membase);
+		goto err_erase_id;
+	}
 
 	/* values not from device tree */
 	port->dev = &pdev->dev;
@@ -285,7 +287,18 @@ static int liteuart_probe(struct platform_device *pdev)
 	port->line = dev_id;
 	spin_lock_init(&port->lock);
 
-	return uart_add_one_port(&liteuart_driver, &uart->port);
+	platform_set_drvdata(pdev, port);
+
+	ret = uart_add_one_port(&liteuart_driver, &uart->port);
+	if (ret)
+		goto err_erase_id;
+
+	return 0;
+
+err_erase_id:
+	xa_erase(&liteuart_array, uart->id);
+
+	return ret;
 }
 
 static int liteuart_remove(struct platform_device *pdev)
@@ -293,6 +306,7 @@ static int liteuart_remove(struct platform_device *pdev)
 	struct uart_port *port = platform_get_drvdata(pdev);
 	struct liteuart_port *uart = to_liteuart_port(port);
 
+	uart_remove_one_port(&liteuart_driver, port);
 	xa_erase(&liteuart_array, uart->id);
 
 	return 0;
diff --git a/drivers/tty/serial/msm_serial.c b/drivers/tty/serial/msm_serial.c
index fcef7a961430..489d19274f9a 100644
--- a/drivers/tty/serial/msm_serial.c
+++ b/drivers/tty/serial/msm_serial.c
@@ -598,6 +598,9 @@ static void msm_start_rx_dma(struct msm_port *msm_port)
 	u32 val;
 	int ret;
 
+	if (IS_ENABLED(CONFIG_CONSOLE_POLL))
+		return;
+
 	if (!dma->chan)
 		return;
 
diff --git a/drivers/tty/serial/serial-tegra.c b/drivers/tty/serial/serial-tegra.c
index 45e2e4109acd..b6223fab0687 100644
--- a/drivers/tty/serial/serial-tegra.c
+++ b/drivers/tty/serial/serial-tegra.c
@@ -1506,7 +1506,7 @@ static struct tegra_uart_chip_data tegra20_uart_chip_data = {
 	.fifo_mode_enable_status	= false,
 	.uart_max_port			= 5,
 	.max_dma_burst_bytes		= 4,
-	.error_tolerance_low_range	= 0,
+	.error_tolerance_low_range	= -4,
 	.error_tolerance_high_range	= 4,
 };
 
@@ -1517,7 +1517,7 @@ static struct tegra_uart_chip_data tegra30_uart_chip_data = {
 	.fifo_mode_enable_status	= false,
 	.uart_max_port			= 5,
 	.max_dma_burst_bytes		= 4,
-	.error_tolerance_low_range	= 0,
+	.error_tolerance_low_range	= -4,
 	.error_tolerance_high_range	= 4,
 };
 
diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index 1e738f265eea..61e3dd0222af 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -1075,6 +1075,11 @@ uart_tiocmset(struct tty_struct *tty, unsigned int set, unsigned int clear)
 		goto out;
 
 	if (!tty_io_error(tty)) {
+		if (uport->rs485.flags & SER_RS485_ENABLED) {
+			set &= ~TIOCM_RTS;
+			clear &= ~TIOCM_RTS;
+		}
+
 		uart_update_mctrl(uport, set, clear);
 		ret = 0;
 	}
@@ -1549,6 +1554,7 @@ static void uart_tty_port_shutdown(struct tty_port *port)
 {
 	struct uart_state *state = container_of(port, struct uart_state, port);
 	struct uart_port *uport = uart_port_check(state);
+	char *buf;
 
 	/*
 	 * At this point, we stop accepting input.  To do this, we
@@ -1570,8 +1576,18 @@ static void uart_tty_port_shutdown(struct tty_port *port)
 	 */
 	tty_port_set_suspended(port, 0);
 
-	uart_change_pm(state, UART_PM_STATE_OFF);
+	/*
+	 * Free the transmit buffer.
+	 */
+	spin_lock_irq(&uport->lock);
+	buf = state->xmit.buf;
+	state->xmit.buf = NULL;
+	spin_unlock_irq(&uport->lock);
 
+	if (buf)
+		free_page((unsigned long)buf);
+
+	uart_change_pm(state, UART_PM_STATE_OFF);
 }
 
 static void uart_wait_until_sent(struct tty_struct *tty, int timeout)
diff --git a/drivers/usb/cdns3/cdns3-gadget.c b/drivers/usb/cdns3/cdns3-gadget.c
index 1f3b4a142212..f9af7ebe003d 100644
--- a/drivers/usb/cdns3/cdns3-gadget.c
+++ b/drivers/usb/cdns3/cdns3-gadget.c
@@ -337,19 +337,6 @@ static void cdns3_ep_inc_deq(struct cdns3_endpoint *priv_ep)
 	cdns3_ep_inc_trb(&priv_ep->dequeue, &priv_ep->ccs, priv_ep->num_trbs);
 }
 
-static void cdns3_move_deq_to_next_trb(struct cdns3_request *priv_req)
-{
-	struct cdns3_endpoint *priv_ep = priv_req->priv_ep;
-	int current_trb = priv_req->start_trb;
-
-	while (current_trb != priv_req->end_trb) {
-		cdns3_ep_inc_deq(priv_ep);
-		current_trb = priv_ep->dequeue;
-	}
-
-	cdns3_ep_inc_deq(priv_ep);
-}
-
 /**
  * cdns3_allow_enable_l1 - enable/disable permits to transition to L1.
  * @priv_dev: Extended gadget object
@@ -1517,10 +1504,11 @@ static void cdns3_transfer_completed(struct cdns3_device *priv_dev,
 
 		trb = priv_ep->trb_pool + priv_ep->dequeue;
 
-		/* Request was dequeued and TRB was changed to TRB_LINK. */
-		if (TRB_FIELD_TO_TYPE(le32_to_cpu(trb->control)) == TRB_LINK) {
+		/* The TRB was changed as link TRB, and the request was handled at ep_dequeue */
+		while (TRB_FIELD_TO_TYPE(le32_to_cpu(trb->control)) == TRB_LINK) {
 			trace_cdns3_complete_trb(priv_ep, trb);
-			cdns3_move_deq_to_next_trb(priv_req);
+			cdns3_ep_inc_deq(priv_ep);
+			trb = priv_ep->trb_pool + priv_ep->dequeue;
 		}
 
 		if (!request->stream_id) {
diff --git a/drivers/usb/cdns3/cdnsp-gadget.c b/drivers/usb/cdns3/cdnsp-gadget.c
index 27df0c697897..e85bf768c66d 100644
--- a/drivers/usb/cdns3/cdnsp-gadget.c
+++ b/drivers/usb/cdns3/cdnsp-gadget.c
@@ -1541,15 +1541,27 @@ static int cdnsp_gadget_pullup(struct usb_gadget *gadget, int is_on)
 {
 	struct cdnsp_device *pdev = gadget_to_cdnsp(gadget);
 	struct cdns *cdns = dev_get_drvdata(pdev->dev);
+	unsigned long flags;
 
 	trace_cdnsp_pullup(is_on);
 
+	/*
+	 * Disable events handling while controller is being
+	 * enabled/disabled.
+	 */
+	disable_irq(cdns->dev_irq);
+	spin_lock_irqsave(&pdev->lock, flags);
+
 	if (!is_on) {
 		cdnsp_reset_device(pdev);
 		cdns_clear_vbus(cdns);
 	} else {
 		cdns_set_vbus(cdns);
 	}
+
+	spin_unlock_irqrestore(&pdev->lock, flags);
+	enable_irq(cdns->dev_irq);
+
 	return 0;
 }
 
diff --git a/drivers/usb/cdns3/cdnsp-mem.c b/drivers/usb/cdns3/cdnsp-mem.c
index ad9aee3f1e39..97866bfb2da9 100644
--- a/drivers/usb/cdns3/cdnsp-mem.c
+++ b/drivers/usb/cdns3/cdnsp-mem.c
@@ -987,6 +987,9 @@ int cdnsp_endpoint_init(struct cdnsp_device *pdev,
 
 	/* Set up the endpoint ring. */
 	pep->ring = cdnsp_ring_alloc(pdev, 2, ring_type, max_packet, mem_flags);
+	if (!pep->ring)
+		return -ENOMEM;
+
 	pep->skip = false;
 
 	/* Fill the endpoint context */
diff --git a/drivers/usb/cdns3/cdnsp-ring.c b/drivers/usb/cdns3/cdnsp-ring.c
index 1b1438457fb0..e45c3d6e1536 100644
--- a/drivers/usb/cdns3/cdnsp-ring.c
+++ b/drivers/usb/cdns3/cdnsp-ring.c
@@ -1029,6 +1029,8 @@ static void cdnsp_process_ctrl_td(struct cdnsp_device *pdev,
 		return;
 	}
 
+	*status = 0;
+
 	cdnsp_finish_td(pdev, td, event, pep, status);
 }
 
@@ -1523,7 +1525,14 @@ irqreturn_t cdnsp_thread_irq_handler(int irq, void *data)
 	spin_lock_irqsave(&pdev->lock, flags);
 
 	if (pdev->cdnsp_state & (CDNSP_STATE_HALTED | CDNSP_STATE_DYING)) {
-		cdnsp_died(pdev);
+		/*
+		 * While removing or stopping driver there may still be deferred
+		 * not handled interrupt which should not be treated as error.
+		 * Driver should simply ignore it.
+		 */
+		if (pdev->gadget_driver)
+			cdnsp_died(pdev);
+
 		spin_unlock_irqrestore(&pdev->lock, flags);
 		return IRQ_HANDLED;
 	}
diff --git a/drivers/usb/cdns3/cdnsp-trace.h b/drivers/usb/cdns3/cdnsp-trace.h
index 6a2571c6aa9e..5983dfb99653 100644
--- a/drivers/usb/cdns3/cdnsp-trace.h
+++ b/drivers/usb/cdns3/cdnsp-trace.h
@@ -57,9 +57,9 @@ DECLARE_EVENT_CLASS(cdnsp_log_ep,
 		__entry->first_prime_det = pep->stream_info.first_prime_det;
 		__entry->drbls_count = pep->stream_info.drbls_count;
 	),
-	TP_printk("%s: SID: %08x ep state: %x stream: enabled: %d num  %d "
+	TP_printk("%s: SID: %08x, ep state: %x, stream: enabled: %d num %d "
 		  "tds %d, first prime: %d drbls %d",
-		  __get_str(name), __entry->state, __entry->stream_id,
+		  __get_str(name), __entry->stream_id, __entry->state,
 		  __entry->enabled, __entry->num_streams, __entry->td_count,
 		  __entry->first_prime_det, __entry->drbls_count)
 );
diff --git a/drivers/usb/cdns3/host.c b/drivers/usb/cdns3/host.c
index 84dadfa726aa..9643b905e2d8 100644
--- a/drivers/usb/cdns3/host.c
+++ b/drivers/usb/cdns3/host.c
@@ -10,6 +10,7 @@
  */
 
 #include <linux/platform_device.h>
+#include <linux/slab.h>
 #include "core.h"
 #include "drd.h"
 #include "host-export.h"
diff --git a/drivers/usb/chipidea/ci_hdrc_imx.c b/drivers/usb/chipidea/ci_hdrc_imx.c
index f1d100671ee6..097142ffb184 100644
--- a/drivers/usb/chipidea/ci_hdrc_imx.c
+++ b/drivers/usb/chipidea/ci_hdrc_imx.c
@@ -420,15 +420,15 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev)
 	data->phy = devm_usb_get_phy_by_phandle(dev, "fsl,usbphy", 0);
 	if (IS_ERR(data->phy)) {
 		ret = PTR_ERR(data->phy);
-		if (ret == -ENODEV) {
-			data->phy = devm_usb_get_phy_by_phandle(dev, "phys", 0);
-			if (IS_ERR(data->phy)) {
-				ret = PTR_ERR(data->phy);
-				if (ret == -ENODEV)
-					data->phy = NULL;
-				else
-					goto err_clk;
-			}
+		if (ret != -ENODEV)
+			goto err_clk;
+		data->phy = devm_usb_get_phy_by_phandle(dev, "phys", 0);
+		if (IS_ERR(data->phy)) {
+			ret = PTR_ERR(data->phy);
+			if (ret == -ENODEV)
+				data->phy = NULL;
+			else
+				goto err_clk;
 		}
 	}
 
diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c
index 16b1fd9dc60c..48bc8a4814ac 100644
--- a/drivers/usb/core/config.c
+++ b/drivers/usb/core/config.c
@@ -406,7 +406,7 @@ static int usb_parse_endpoint(struct device *ddev, int cfgno,
 	 * the USB-2 spec requires such endpoints to have wMaxPacketSize = 0
 	 * (see the end of section 5.6.3), so don't warn about them.
 	 */
-	maxp = usb_endpoint_maxp(&endpoint->desc);
+	maxp = le16_to_cpu(endpoint->desc.wMaxPacketSize);
 	if (maxp == 0 && !(usb_endpoint_xfer_isoc(d) && asnum == 0)) {
 		dev_warn(ddev, "config %d interface %d altsetting %d endpoint 0x%X has invalid wMaxPacketSize 0\n",
 		    cfgno, inum, asnum, d->bEndpointAddress);
@@ -422,9 +422,9 @@ static int usb_parse_endpoint(struct device *ddev, int cfgno,
 		maxpacket_maxes = full_speed_maxpacket_maxes;
 		break;
 	case USB_SPEED_HIGH:
-		/* Bits 12..11 are allowed only for HS periodic endpoints */
+		/* Multiple-transactions bits are allowed only for HS periodic endpoints */
 		if (usb_endpoint_xfer_int(d) || usb_endpoint_xfer_isoc(d)) {
-			i = maxp & (BIT(12) | BIT(11));
+			i = maxp & USB_EP_MAXP_MULT_MASK;
 			maxp &= ~i;
 		}
 		fallthrough;
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 86658a81d284..00070a8a6507 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -4700,8 +4700,6 @@ hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1,
 	if (oldspeed == USB_SPEED_LOW)
 		delay = HUB_LONG_RESET_TIME;
 
-	mutex_lock(hcd->address0_mutex);
-
 	/* Reset the device; full speed may morph to high speed */
 	/* FIXME a USB 2.0 device may morph into SuperSpeed on reset. */
 	retval = hub_port_reset(hub, port1, udev, delay, false);
@@ -5016,7 +5014,6 @@ fail:
 		hub_port_disable(hub, port1, 0);
 		update_devnum(udev, devnum);	/* for disconnect processing */
 	}
-	mutex_unlock(hcd->address0_mutex);
 	return retval;
 }
 
@@ -5191,6 +5188,7 @@ static void hub_port_connect(struct usb_hub *hub, int port1, u16 portstatus,
 	struct usb_port *port_dev = hub->ports[port1 - 1];
 	struct usb_device *udev = port_dev->child;
 	static int unreliable_port = -1;
+	bool retry_locked;
 
 	/* Disconnect any existing devices under this port */
 	if (udev) {
@@ -5246,8 +5244,11 @@ static void hub_port_connect(struct usb_hub *hub, int port1, u16 portstatus,
 		unit_load = 100;
 
 	status = 0;
-	for (i = 0; i < PORT_INIT_TRIES; i++) {
 
+	for (i = 0; i < PORT_INIT_TRIES; i++) {
+		usb_lock_port(port_dev);
+		mutex_lock(hcd->address0_mutex);
+		retry_locked = true;
 		/* reallocate for each attempt, since references
 		 * to the previous one can escape in various ways
 		 */
@@ -5255,6 +5256,8 @@ static void hub_port_connect(struct usb_hub *hub, int port1, u16 portstatus,
 		if (!udev) {
 			dev_err(&port_dev->dev,
 					"couldn't allocate usb_device\n");
+			mutex_unlock(hcd->address0_mutex);
+			usb_unlock_port(port_dev);
 			goto done;
 		}
 
@@ -5276,12 +5279,14 @@ static void hub_port_connect(struct usb_hub *hub, int port1, u16 portstatus,
 		}
 
 		/* reset (non-USB 3.0 devices) and get descriptor */
-		usb_lock_port(port_dev);
 		status = hub_port_init(hub, udev, port1, i);
-		usb_unlock_port(port_dev);
 		if (status < 0)
 			goto loop;
 
+		mutex_unlock(hcd->address0_mutex);
+		usb_unlock_port(port_dev);
+		retry_locked = false;
+
 		if (udev->quirks & USB_QUIRK_DELAY_INIT)
 			msleep(2000);
 
@@ -5374,6 +5379,10 @@ loop:
 		usb_ep0_reinit(udev);
 		release_devnum(udev);
 		hub_free_dev(udev);
+		if (retry_locked) {
+			mutex_unlock(hcd->address0_mutex);
+			usb_unlock_port(port_dev);
+		}
 		usb_put_dev(udev);
 		if ((status == -ENOTCONN) || (status == -ENOTSUPP))
 			break;
@@ -5915,6 +5924,8 @@ static int usb_reset_and_verify_device(struct usb_device *udev)
 	bos = udev->bos;
 	udev->bos = NULL;
 
+	mutex_lock(hcd->address0_mutex);
+
 	for (i = 0; i < PORT_INIT_TRIES; ++i) {
 
 		/* ep0 maxpacket size may change; let the HCD know about it.
@@ -5924,6 +5935,7 @@ static int usb_reset_and_verify_device(struct usb_device *udev)
 		if (ret >= 0 || ret == -ENOTCONN || ret == -ENODEV)
 			break;
 	}
+	mutex_unlock(hcd->address0_mutex);
 
 	if (ret < 0)
 		goto re_enumerate;
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index 8239fe7129dd..d3c14b5ed4a1 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -434,6 +434,12 @@ static const struct usb_device_id usb_quirk_list[] = {
 	{ USB_DEVICE(0x1532, 0x0116), .driver_info =
 			USB_QUIRK_LINEAR_UFRAME_INTR_BINTERVAL },
 
+	/* Lenovo USB-C to Ethernet Adapter RTL8153-04 */
+	{ USB_DEVICE(0x17ef, 0x720c), .driver_info = USB_QUIRK_NO_LPM },
+
+	/* Lenovo Powered USB-C Travel Hub (4X90S92381, RTL8153 GigE) */
+	{ USB_DEVICE(0x17ef, 0x721e), .driver_info = USB_QUIRK_NO_LPM },
+
 	/* Lenovo ThinkCenter A630Z TI024Gen3 usb-audio */
 	{ USB_DEVICE(0x17ef, 0xa012), .driver_info =
 			USB_QUIRK_DISCONNECT_SUSPEND },
diff --git a/drivers/usb/dwc2/gadget.c b/drivers/usb/dwc2/gadget.c
index 4ab4a1d5062b..ab8d7dad9f56 100644
--- a/drivers/usb/dwc2/gadget.c
+++ b/drivers/usb/dwc2/gadget.c
@@ -1198,6 +1198,8 @@ static void dwc2_hsotg_start_req(struct dwc2_hsotg *hsotg,
 			}
 			ctrl |= DXEPCTL_CNAK;
 		} else {
+			hs_req->req.frame_number = hs_ep->target_frame;
+			hs_req->req.actual = 0;
 			dwc2_hsotg_complete_request(hsotg, hs_ep, hs_req, -ENODATA);
 			return;
 		}
@@ -2857,9 +2859,12 @@ static void dwc2_gadget_handle_ep_disabled(struct dwc2_hsotg_ep *hs_ep)
 
 	do {
 		hs_req = get_ep_head(hs_ep);
-		if (hs_req)
+		if (hs_req) {
+			hs_req->req.frame_number = hs_ep->target_frame;
+			hs_req->req.actual = 0;
 			dwc2_hsotg_complete_request(hsotg, hs_ep, hs_req,
 						    -ENODATA);
+		}
 		dwc2_gadget_incr_frame_num(hs_ep);
 		/* Update current frame number value. */
 		hsotg->frame_number = dwc2_hsotg_read_frameno(hsotg);
@@ -2912,8 +2917,11 @@ static void dwc2_gadget_handle_out_token_ep_disabled(struct dwc2_hsotg_ep *ep)
 
 	while (dwc2_gadget_target_frame_elapsed(ep)) {
 		hs_req = get_ep_head(ep);
-		if (hs_req)
+		if (hs_req) {
+			hs_req->req.frame_number = ep->target_frame;
+			hs_req->req.actual = 0;
 			dwc2_hsotg_complete_request(hsotg, ep, hs_req, -ENODATA);
+		}
 
 		dwc2_gadget_incr_frame_num(ep);
 		/* Update current frame number value. */
@@ -3002,8 +3010,11 @@ static void dwc2_gadget_handle_nak(struct dwc2_hsotg_ep *hs_ep)
 
 	while (dwc2_gadget_target_frame_elapsed(hs_ep)) {
 		hs_req = get_ep_head(hs_ep);
-		if (hs_req)
+		if (hs_req) {
+			hs_req->req.frame_number = hs_ep->target_frame;
+			hs_req->req.actual = 0;
 			dwc2_hsotg_complete_request(hsotg, hs_ep, hs_req, -ENODATA);
+		}
 
 		dwc2_gadget_incr_frame_num(hs_ep);
 		/* Update current frame number value. */
diff --git a/drivers/usb/dwc2/hcd_queue.c b/drivers/usb/dwc2/hcd_queue.c
index 89a788326c56..24beff610cf2 100644
--- a/drivers/usb/dwc2/hcd_queue.c
+++ b/drivers/usb/dwc2/hcd_queue.c
@@ -59,7 +59,7 @@
 #define DWC2_UNRESERVE_DELAY (msecs_to_jiffies(5))
 
 /* If we get a NAK, wait this long before retrying */
-#define DWC2_RETRY_WAIT_DELAY (1 * 1E6L)
+#define DWC2_RETRY_WAIT_DELAY (1 * NSEC_PER_MSEC)
 
 /**
  * dwc2_periodic_channel_available() - Checks that a channel is available for a
diff --git a/drivers/usb/dwc2/platform.c b/drivers/usb/dwc2/platform.c
index c8f18f3ba9e3..c331a5128c2c 100644
--- a/drivers/usb/dwc2/platform.c
+++ b/drivers/usb/dwc2/platform.c
@@ -575,6 +575,9 @@ static int dwc2_driver_probe(struct platform_device *dev)
 		ggpio |= GGPIO_STM32_OTG_GCCFG_IDEN;
 		ggpio |= GGPIO_STM32_OTG_GCCFG_VBDEN;
 		dwc2_writel(hsotg, ggpio, GGPIO);
+
+		/* ID/VBUS detection startup time */
+		usleep_range(5000, 7000);
 	}
 
 	retval = dwc2_drd_init(hsotg);
diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c
index 643239d7d370..f4c09951b517 100644
--- a/drivers/usb/dwc3/core.c
+++ b/drivers/usb/dwc3/core.c
@@ -1594,9 +1594,11 @@ static int dwc3_probe(struct platform_device *pdev)
 
 	dwc3_get_properties(dwc);
 
-	ret = dma_set_mask_and_coherent(dwc->sysdev, DMA_BIT_MASK(64));
-	if (ret)
-		return ret;
+	if (!dwc->sysdev_is_parent) {
+		ret = dma_set_mask_and_coherent(dwc->sysdev, DMA_BIT_MASK(64));
+		if (ret)
+			return ret;
+	}
 
 	dwc->reset = devm_reset_control_array_get_optional_shared(dev);
 	if (IS_ERR(dwc->reset))
diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h
index 620c8d3914d7..5c491d0a19d7 100644
--- a/drivers/usb/dwc3/core.h
+++ b/drivers/usb/dwc3/core.h
@@ -143,7 +143,7 @@
 #define DWC3_GHWPARAMS8		0xc600
 #define DWC3_GUCTL3		0xc60c
 #define DWC3_GFLADJ		0xc630
-#define DWC3_GHWPARAMS9		0xc680
+#define DWC3_GHWPARAMS9		0xc6e0
 
 /* Device Registers */
 #define DWC3_DCFG		0xc700
diff --git a/drivers/usb/dwc3/dwc3-qcom.c b/drivers/usb/dwc3/dwc3-qcom.c
index 9abbd01028c5..3cb01cdd02c2 100644
--- a/drivers/usb/dwc3/dwc3-qcom.c
+++ b/drivers/usb/dwc3/dwc3-qcom.c
@@ -649,7 +649,6 @@ static int dwc3_qcom_of_register_core(struct platform_device *pdev)
 	struct dwc3_qcom	*qcom = platform_get_drvdata(pdev);
 	struct device_node	*np = pdev->dev.of_node, *dwc3_np;
 	struct device		*dev = &pdev->dev;
-	struct property		*prop;
 	int			ret;
 
 	dwc3_np = of_get_compatible_child(np, "snps,dwc3");
@@ -658,20 +657,6 @@ static int dwc3_qcom_of_register_core(struct platform_device *pdev)
 		return -ENODEV;
 	}
 
-	prop = devm_kzalloc(dev, sizeof(*prop), GFP_KERNEL);
-	if (!prop) {
-		ret = -ENOMEM;
-		dev_err(dev, "unable to allocate memory for property\n");
-		goto node_put;
-	}
-
-	prop->name = "tx-fifo-resize";
-	ret = of_add_property(dwc3_np, prop);
-	if (ret) {
-		dev_err(dev, "unable to add property\n");
-		goto node_put;
-	}
-
 	ret = of_platform_populate(np, NULL, NULL, dev);
 	if (ret) {
 		dev_err(dev, "failed to register dwc3 core - %d\n", ret);
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 23de2a5a40d6..7e3db00e9759 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -310,13 +310,24 @@ int dwc3_send_gadget_ep_cmd(struct dwc3_ep *dep, unsigned int cmd,
 	if (DWC3_DEPCMD_CMD(cmd) == DWC3_DEPCMD_STARTTRANSFER) {
 		int link_state;
 
+		/*
+		 * Initiate remote wakeup if the link state is in U3 when
+		 * operating in SS/SSP or L1/L2 when operating in HS/FS. If the
+		 * link state is in U1/U2, no remote wakeup is needed. The Start
+		 * Transfer command will initiate the link recovery.
+		 */
 		link_state = dwc3_gadget_get_link_state(dwc);
-		if (link_state == DWC3_LINK_STATE_U1 ||
-		    link_state == DWC3_LINK_STATE_U2 ||
-		    link_state == DWC3_LINK_STATE_U3) {
+		switch (link_state) {
+		case DWC3_LINK_STATE_U2:
+			if (dwc->gadget->speed >= USB_SPEED_SUPER)
+				break;
+
+			fallthrough;
+		case DWC3_LINK_STATE_U3:
 			ret = __dwc3_gadget_wakeup(dwc);
 			dev_WARN_ONCE(dwc->dev, ret, "wakeup failed --> %d\n",
 					ret);
+			break;
 		}
 	}
 
@@ -3252,6 +3263,9 @@ static bool dwc3_gadget_endpoint_trbs_complete(struct dwc3_ep *dep,
 	struct dwc3		*dwc = dep->dwc;
 	bool			no_started_trb = true;
 
+	if (!dep->endpoint.desc)
+		return no_started_trb;
+
 	dwc3_gadget_ep_cleanup_completed_requests(dep, event, status);
 
 	if (dep->flags & DWC3_EP_END_TRANSFER_PENDING)
@@ -3299,6 +3313,9 @@ static void dwc3_gadget_endpoint_transfer_in_progress(struct dwc3_ep *dep,
 {
 	int status = 0;
 
+	if (!dep->endpoint.desc)
+		return;
+
 	if (usb_endpoint_xfer_isoc(dep->endpoint.desc))
 		dwc3_gadget_endpoint_frame_from_event(dep, event);
 
@@ -3352,6 +3369,14 @@ static void dwc3_gadget_endpoint_command_complete(struct dwc3_ep *dep,
 	if (cmd != DWC3_DEPCMD_ENDTRANSFER)
 		return;
 
+	/*
+	 * The END_TRANSFER command will cause the controller to generate a
+	 * NoStream Event, and it's not due to the host DP NoStream rejection.
+	 * Ignore the next NoStream event.
+	 */
+	if (dep->stream_capable)
+		dep->flags |= DWC3_EP_IGNORE_NEXT_NOSTREAM;
+
 	dep->flags &= ~DWC3_EP_END_TRANSFER_PENDING;
 	dep->flags &= ~DWC3_EP_TRANSFER_STARTED;
 	dwc3_gadget_ep_cleanup_cancelled_requests(dep);
@@ -3574,14 +3599,6 @@ static void dwc3_stop_active_transfer(struct dwc3_ep *dep, bool force,
 	WARN_ON_ONCE(ret);
 	dep->resource_index = 0;
 
-	/*
-	 * The END_TRANSFER command will cause the controller to generate a
-	 * NoStream Event, and it's not due to the host DP NoStream rejection.
-	 * Ignore the next NoStream event.
-	 */
-	if (dep->stream_capable)
-		dep->flags |= DWC3_EP_IGNORE_NEXT_NOSTREAM;
-
 	if (!interrupt)
 		dep->flags &= ~DWC3_EP_TRANSFER_STARTED;
 	else
diff --git a/drivers/usb/early/xhci-dbc.c b/drivers/usb/early/xhci-dbc.c
index 933d77ad0a64..4502108069cd 100644
--- a/drivers/usb/early/xhci-dbc.c
+++ b/drivers/usb/early/xhci-dbc.c
@@ -14,7 +14,6 @@
 #include <linux/pci_ids.h>
 #include <linux/memblock.h>
 #include <linux/io.h>
-#include <linux/iopoll.h>
 #include <asm/pci-direct.h>
 #include <asm/fixmap.h>
 #include <linux/bcd.h>
@@ -136,9 +135,17 @@ static int handshake(void __iomem *ptr, u32 mask, u32 done, int wait, int delay)
 {
 	u32 result;
 
-	return readl_poll_timeout_atomic(ptr, result,
-					 ((result & mask) == done),
-					 delay, wait);
+	/* Can not use readl_poll_timeout_atomic() for early boot things */
+	do {
+		result = readl(ptr);
+		result &= mask;
+		if (result == done)
+			return 0;
+		udelay(delay);
+		wait -= delay;
+	} while (wait > 0);
+
+	return -ETIMEDOUT;
 }
 
 static void __init xdbc_bios_handoff(void)
diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c
index 504c1cbc255d..3789c329183c 100644
--- a/drivers/usb/gadget/composite.c
+++ b/drivers/usb/gadget/composite.c
@@ -1679,6 +1679,18 @@ composite_setup(struct usb_gadget *gadget, const struct usb_ctrlrequest *ctrl)
 	struct usb_function		*f = NULL;
 	u8				endp;
 
+	if (w_length > USB_COMP_EP0_BUFSIZ) {
+		if (ctrl->bRequestType & USB_DIR_IN) {
+			/* Cast away the const, we are going to overwrite on purpose. */
+			__le16 *temp = (__le16 *)&ctrl->wLength;
+
+			*temp = cpu_to_le16(USB_COMP_EP0_BUFSIZ);
+			w_length = USB_COMP_EP0_BUFSIZ;
+		} else {
+			goto done;
+		}
+	}
+
 	/* partial re-init of the response message; the function or the
 	 * gadget might need to intercept e.g. a control-OUT completion
 	 * when we delegate to it.
@@ -2209,7 +2221,7 @@ int composite_dev_prepare(struct usb_composite_driver *composite,
 	if (!cdev->req)
 		return -ENOMEM;
 
-	cdev->req->buf = kmalloc(USB_COMP_EP0_BUFSIZ, GFP_KERNEL);
+	cdev->req->buf = kzalloc(USB_COMP_EP0_BUFSIZ, GFP_KERNEL);
 	if (!cdev->req->buf)
 		goto fail;
 
diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c
index e20c19a0f106..a7e069b18544 100644
--- a/drivers/usb/gadget/function/f_fs.c
+++ b/drivers/usb/gadget/function/f_fs.c
@@ -1773,11 +1773,15 @@ static void ffs_data_clear(struct ffs_data *ffs)
 
 	BUG_ON(ffs->gadget);
 
-	if (ffs->epfiles)
+	if (ffs->epfiles) {
 		ffs_epfiles_destroy(ffs->epfiles, ffs->eps_count);
+		ffs->epfiles = NULL;
+	}
 
-	if (ffs->ffs_eventfd)
+	if (ffs->ffs_eventfd) {
 		eventfd_ctx_put(ffs->ffs_eventfd);
+		ffs->ffs_eventfd = NULL;
+	}
 
 	kfree(ffs->raw_descs_data);
 	kfree(ffs->raw_strings);
@@ -1790,7 +1794,6 @@ static void ffs_data_reset(struct ffs_data *ffs)
 
 	ffs_data_clear(ffs);
 
-	ffs->epfiles = NULL;
 	ffs->raw_descs_data = NULL;
 	ffs->raw_descs = NULL;
 	ffs->raw_strings = NULL;
diff --git a/drivers/usb/gadget/function/u_ether.c b/drivers/usb/gadget/function/u_ether.c
index e0ad5aed6ac9..6f5d45ef2e39 100644
--- a/drivers/usb/gadget/function/u_ether.c
+++ b/drivers/usb/gadget/function/u_ether.c
@@ -17,6 +17,7 @@
 #include <linux/etherdevice.h>
 #include <linux/ethtool.h>
 #include <linux/if_vlan.h>
+#include <linux/etherdevice.h>
 
 #include "u_ether.h"
 
@@ -863,19 +864,23 @@ int gether_register_netdev(struct net_device *net)
 {
 	struct eth_dev *dev;
 	struct usb_gadget *g;
-	struct sockaddr sa;
 	int status;
 
 	if (!net->dev.parent)
 		return -EINVAL;
 	dev = netdev_priv(net);
 	g = dev->gadget;
+
+	net->addr_assign_type = NET_ADDR_RANDOM;
+	eth_hw_addr_set(net, dev->dev_mac);
+
 	status = register_netdev(net);
 	if (status < 0) {
 		dev_dbg(&g->dev, "register_netdev failed, %d\n", status);
 		return status;
 	} else {
 		INFO(dev, "HOST MAC %pM\n", dev->host_mac);
+		INFO(dev, "MAC %pM\n", dev->dev_mac);
 
 		/* two kinds of host-initiated state changes:
 		 *  - iff DATA transfer is active, carrier is "on"
@@ -883,15 +888,6 @@ int gether_register_netdev(struct net_device *net)
 		 */
 		netif_carrier_off(net);
 	}
-	sa.sa_family = net->type;
-	memcpy(sa.sa_data, dev->dev_mac, ETH_ALEN);
-	rtnl_lock();
-	status = dev_set_mac_address(net, &sa, NULL);
-	rtnl_unlock();
-	if (status)
-		pr_warn("cannot set self ethernet address: %d\n", status);
-	else
-		INFO(dev, "MAC %pM\n", dev->dev_mac);
 
 	return status;
 }
diff --git a/drivers/usb/gadget/legacy/dbgp.c b/drivers/usb/gadget/legacy/dbgp.c
index e1d566c9918a..6bcbad382580 100644
--- a/drivers/usb/gadget/legacy/dbgp.c
+++ b/drivers/usb/gadget/legacy/dbgp.c
@@ -137,7 +137,7 @@ static int dbgp_enable_ep_req(struct usb_ep *ep)
 		goto fail_1;
 	}
 
-	req->buf = kmalloc(DBGP_REQ_LEN, GFP_KERNEL);
+	req->buf = kzalloc(DBGP_REQ_LEN, GFP_KERNEL);
 	if (!req->buf) {
 		err = -ENOMEM;
 		stp = 2;
@@ -345,6 +345,19 @@ static int dbgp_setup(struct usb_gadget *gadget,
 	void *data = NULL;
 	u16 len = 0;
 
+	if (length > DBGP_REQ_LEN) {
+		if (ctrl->bRequestType & USB_DIR_IN) {
+			/* Cast away the const, we are going to overwrite on purpose. */
+			__le16 *temp = (__le16 *)&ctrl->wLength;
+
+			*temp = cpu_to_le16(DBGP_REQ_LEN);
+			length = DBGP_REQ_LEN;
+		} else {
+			return err;
+		}
+	}
+
+
 	if (request == USB_REQ_GET_DESCRIPTOR) {
 		switch (value>>8) {
 		case USB_DT_DEVICE:
diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c
index 78be94750232..3b58f4fc0a80 100644
--- a/drivers/usb/gadget/legacy/inode.c
+++ b/drivers/usb/gadget/legacy/inode.c
@@ -110,6 +110,8 @@ enum ep0_state {
 /* enough for the whole queue: most events invalidate others */
 #define	N_EVENT			5
 
+#define RBUF_SIZE		256
+
 struct dev_data {
 	spinlock_t			lock;
 	refcount_t			count;
@@ -144,7 +146,7 @@ struct dev_data {
 	struct dentry			*dentry;
 
 	/* except this scratch i/o buffer for ep0 */
-	u8				rbuf [256];
+	u8				rbuf[RBUF_SIZE];
 };
 
 static inline void get_dev (struct dev_data *data)
@@ -1331,6 +1333,18 @@ gadgetfs_setup (struct usb_gadget *gadget, const struct usb_ctrlrequest *ctrl)
 	u16				w_value = le16_to_cpu(ctrl->wValue);
 	u16				w_length = le16_to_cpu(ctrl->wLength);
 
+	if (w_length > RBUF_SIZE) {
+		if (ctrl->bRequestType & USB_DIR_IN) {
+			/* Cast away the const, we are going to overwrite on purpose. */
+			__le16 *temp = (__le16 *)&ctrl->wLength;
+
+			*temp = cpu_to_le16(RBUF_SIZE);
+			w_length = RBUF_SIZE;
+		} else {
+			return value;
+		}
+	}
+
 	spin_lock (&dev->lock);
 	dev->setup_abort = 0;
 	if (dev->state == STATE_DEV_UNCONNECTED) {
diff --git a/drivers/usb/gadget/udc/udc-xilinx.c b/drivers/usb/gadget/udc/udc-xilinx.c
index f5ca670776a3..857159dd5ae0 100644
--- a/drivers/usb/gadget/udc/udc-xilinx.c
+++ b/drivers/usb/gadget/udc/udc-xilinx.c
@@ -2136,7 +2136,7 @@ static int xudc_probe(struct platform_device *pdev)
 
 	ret = usb_add_gadget_udc(&pdev->dev, &udc->gadget);
 	if (ret)
-		goto fail;
+		goto err_disable_unprepare_clk;
 
 	udc->dev = &udc->gadget.dev;
 
@@ -2155,6 +2155,9 @@ static int xudc_probe(struct platform_device *pdev)
 		 udc->dma_enabled ? "with DMA" : "without DMA");
 
 	return 0;
+
+err_disable_unprepare_clk:
+	clk_disable_unprepare(udc->clk);
 fail:
 	dev_err(&pdev->dev, "probe failed, %d\n", ret);
 	return ret;
diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c
index af946c42b6f0..df3522dab31b 100644
--- a/drivers/usb/host/xhci-hub.c
+++ b/drivers/usb/host/xhci-hub.c
@@ -717,6 +717,7 @@ static int xhci_enter_test_mode(struct xhci_hcd *xhci,
 			continue;
 
 		retval = xhci_disable_slot(xhci, i);
+		xhci_free_virt_device(xhci, i);
 		if (retval)
 			xhci_err(xhci, "Failed to disable slot %d, %d. Enter test mode anyway\n",
 				 i, retval);
diff --git a/drivers/usb/host/xhci-mtk-sch.c b/drivers/usb/host/xhci-mtk-sch.c
index 1edef7527c11..edbfa82c6565 100644
--- a/drivers/usb/host/xhci-mtk-sch.c
+++ b/drivers/usb/host/xhci-mtk-sch.c
@@ -781,7 +781,7 @@ int xhci_mtk_check_bandwidth(struct usb_hcd *hcd, struct usb_device *udev)
 
 	ret = xhci_check_bandwidth(hcd, udev);
 	if (!ret)
-		INIT_LIST_HEAD(&mtk->bw_ep_chk_list);
+		list_del_init(&mtk->bw_ep_chk_list);
 
 	return ret;
 }
diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index 92adf6107864..5c351970cdf1 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -71,6 +71,8 @@
 #define PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_4		0x161e
 #define PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_5		0x15d6
 #define PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_6		0x15d7
+#define PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_7		0x161c
+#define PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_8		0x161f
 
 #define PCI_DEVICE_ID_ASMEDIA_1042_XHCI			0x1042
 #define PCI_DEVICE_ID_ASMEDIA_1042A_XHCI		0x1142
@@ -121,7 +123,6 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
 	/* Look for vendor-specific quirks */
 	if (pdev->vendor == PCI_VENDOR_ID_FRESCO_LOGIC &&
 			(pdev->device == PCI_DEVICE_ID_FRESCO_LOGIC_PDK ||
-			 pdev->device == PCI_DEVICE_ID_FRESCO_LOGIC_FL1100 ||
 			 pdev->device == PCI_DEVICE_ID_FRESCO_LOGIC_FL1400)) {
 		if (pdev->device == PCI_DEVICE_ID_FRESCO_LOGIC_PDK &&
 				pdev->revision == 0x0) {
@@ -156,6 +157,10 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
 			pdev->device == PCI_DEVICE_ID_FRESCO_LOGIC_FL1009)
 		xhci->quirks |= XHCI_BROKEN_STREAMS;
 
+	if (pdev->vendor == PCI_VENDOR_ID_FRESCO_LOGIC &&
+			pdev->device == PCI_DEVICE_ID_FRESCO_LOGIC_FL1100)
+		xhci->quirks |= XHCI_TRUST_TX_LENGTH;
+
 	if (pdev->vendor == PCI_VENDOR_ID_NEC)
 		xhci->quirks |= XHCI_NEC_HOST;
 
@@ -330,7 +335,9 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
 	    pdev->device == PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_3 ||
 	    pdev->device == PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_4 ||
 	    pdev->device == PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_5 ||
-	    pdev->device == PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_6))
+	    pdev->device == PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_6 ||
+	    pdev->device == PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_7 ||
+	    pdev->device == PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_8))
 		xhci->quirks |= XHCI_DEFAULT_PM_RUNTIME_ALLOW;
 
 	if (xhci->quirks & XHCI_RESET_ON_RESUME)
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index 311597bba80e..d0b6806275e0 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -366,7 +366,9 @@ static void xhci_handle_stopped_cmd_ring(struct xhci_hcd *xhci,
 /* Must be called with xhci->lock held, releases and aquires lock back */
 static int xhci_abort_cmd_ring(struct xhci_hcd *xhci, unsigned long flags)
 {
-	u32 temp_32;
+	struct xhci_segment *new_seg	= xhci->cmd_ring->deq_seg;
+	union xhci_trb *new_deq		= xhci->cmd_ring->dequeue;
+	u64 crcr;
 	int ret;
 
 	xhci_dbg(xhci, "Abort command ring\n");
@@ -375,13 +377,18 @@ static int xhci_abort_cmd_ring(struct xhci_hcd *xhci, unsigned long flags)
 
 	/*
 	 * The control bits like command stop, abort are located in lower
-	 * dword of the command ring control register. Limit the write
-	 * to the lower dword to avoid corrupting the command ring pointer
-	 * in case if the command ring is stopped by the time upper dword
-	 * is written.
+	 * dword of the command ring control register.
+	 * Some controllers require all 64 bits to be written to abort the ring.
+	 * Make sure the upper dword is valid, pointing to the next command,
+	 * avoiding corrupting the command ring pointer in case the command ring
+	 * is stopped by the time the upper dword is written.
 	 */
-	temp_32 = readl(&xhci->op_regs->cmd_ring);
-	writel(temp_32 | CMD_RING_ABORT, &xhci->op_regs->cmd_ring);
+	next_trb(xhci, NULL, &new_seg, &new_deq);
+	if (trb_is_link(new_deq))
+		next_trb(xhci, NULL, &new_seg, &new_deq);
+
+	crcr = xhci_trb_virt_to_dma(new_seg, new_deq);
+	xhci_write_64(xhci, crcr | CMD_RING_ABORT, &xhci->op_regs->cmd_ring);
 
 	/* Section 4.6.1.2 of xHCI 1.0 spec says software should also time the
 	 * completion of the Command Abort operation. If CRR is not negated in 5
@@ -1518,7 +1525,6 @@ static void xhci_handle_cmd_disable_slot(struct xhci_hcd *xhci, int slot_id)
 	if (xhci->quirks & XHCI_EP_LIMIT_QUIRK)
 		/* Delete default control endpoint resources */
 		xhci_free_device_endpoint_resources(xhci, virt_dev, true);
-	xhci_free_virt_device(xhci, slot_id);
 }
 
 static void xhci_handle_cmd_config_ep(struct xhci_hcd *xhci, int slot_id,
diff --git a/drivers/usb/host/xhci-tegra.c b/drivers/usb/host/xhci-tegra.c
index 1bf494b649bd..c8af2cd2216d 100644
--- a/drivers/usb/host/xhci-tegra.c
+++ b/drivers/usb/host/xhci-tegra.c
@@ -1400,6 +1400,7 @@ static void tegra_xusb_deinit_usb_phy(struct tegra_xusb *tegra)
 
 static int tegra_xusb_probe(struct platform_device *pdev)
 {
+	struct of_phandle_args args;
 	struct tegra_xusb *tegra;
 	struct device_node *np;
 	struct resource *regs;
@@ -1454,10 +1455,17 @@ static int tegra_xusb_probe(struct platform_device *pdev)
 		goto put_padctl;
 	}
 
-	tegra->padctl_irq = of_irq_get(np, 0);
-	if (tegra->padctl_irq <= 0) {
-		err = (tegra->padctl_irq == 0) ? -ENODEV : tegra->padctl_irq;
-		goto put_padctl;
+	/* Older device-trees don't have padctrl interrupt */
+	err = of_irq_parse_one(np, 0, &args);
+	if (!err) {
+		tegra->padctl_irq = of_irq_get(np, 0);
+		if (tegra->padctl_irq <= 0) {
+			err = (tegra->padctl_irq == 0) ? -ENODEV : tegra->padctl_irq;
+			goto put_padctl;
+		}
+	} else {
+		dev_dbg(&pdev->dev,
+			"%pOF is missing an interrupt, disabling PM support\n", np);
 	}
 
 	tegra->host_clk = devm_clk_get(&pdev->dev, "xusb_host");
@@ -1696,11 +1704,15 @@ static int tegra_xusb_probe(struct platform_device *pdev)
 		goto remove_usb3;
 	}
 
-	err = devm_request_threaded_irq(&pdev->dev, tegra->padctl_irq, NULL, tegra_xusb_padctl_irq,
-					IRQF_ONESHOT, dev_name(&pdev->dev), tegra);
-	if (err < 0) {
-		dev_err(&pdev->dev, "failed to request padctl IRQ: %d\n", err);
-		goto remove_usb3;
+	if (tegra->padctl_irq) {
+		err = devm_request_threaded_irq(&pdev->dev, tegra->padctl_irq,
+						NULL, tegra_xusb_padctl_irq,
+						IRQF_ONESHOT, dev_name(&pdev->dev),
+						tegra);
+		if (err < 0) {
+			dev_err(&pdev->dev, "failed to request padctl IRQ: %d\n", err);
+			goto remove_usb3;
+		}
 	}
 
 	err = tegra_xusb_enable_firmware_messages(tegra);
@@ -1718,13 +1730,16 @@ static int tegra_xusb_probe(struct platform_device *pdev)
 	/* Enable wake for both USB 2.0 and USB 3.0 roothubs */
 	device_init_wakeup(&tegra->hcd->self.root_hub->dev, true);
 	device_init_wakeup(&xhci->shared_hcd->self.root_hub->dev, true);
-	device_init_wakeup(tegra->dev, true);
 
 	pm_runtime_use_autosuspend(tegra->dev);
 	pm_runtime_set_autosuspend_delay(tegra->dev, 2000);
 	pm_runtime_mark_last_busy(tegra->dev);
 	pm_runtime_set_active(tegra->dev);
-	pm_runtime_enable(tegra->dev);
+
+	if (tegra->padctl_irq) {
+		device_init_wakeup(tegra->dev, true);
+		pm_runtime_enable(tegra->dev);
+	}
 
 	return 0;
 
@@ -1772,7 +1787,9 @@ static int tegra_xusb_remove(struct platform_device *pdev)
 	dma_free_coherent(&pdev->dev, tegra->fw.size, tegra->fw.virt,
 			  tegra->fw.phys);
 
-	pm_runtime_disable(&pdev->dev);
+	if (tegra->padctl_irq)
+		pm_runtime_disable(&pdev->dev);
+
 	pm_runtime_put(&pdev->dev);
 
 	tegra_xusb_powergate_partitions(tegra);
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 902f410874e8..f5b1bcc875de 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -3934,7 +3934,6 @@ static void xhci_free_dev(struct usb_hcd *hcd, struct usb_device *udev)
 	struct xhci_slot_ctx *slot_ctx;
 	int i, ret;
 
-#ifndef CONFIG_USB_DEFAULT_PERSIST
 	/*
 	 * We called pm_runtime_get_noresume when the device was attached.
 	 * Decrement the counter here to allow controller to runtime suspend
@@ -3942,7 +3941,6 @@ static void xhci_free_dev(struct usb_hcd *hcd, struct usb_device *udev)
 	 */
 	if (xhci->quirks & XHCI_RESET_ON_RESUME)
 		pm_runtime_put_noidle(hcd->self.controller);
-#endif
 
 	ret = xhci_check_args(hcd, udev, NULL, 0, true, __func__);
 	/* If the host is halted due to driver unload, we still need to free the
@@ -3961,9 +3959,8 @@ static void xhci_free_dev(struct usb_hcd *hcd, struct usb_device *udev)
 		del_timer_sync(&virt_dev->eps[i].stop_cmd_timer);
 	}
 	virt_dev->udev = NULL;
-	ret = xhci_disable_slot(xhci, udev->slot_id);
-	if (ret)
-		xhci_free_virt_device(xhci, udev->slot_id);
+	xhci_disable_slot(xhci, udev->slot_id);
+	xhci_free_virt_device(xhci, udev->slot_id);
 }
 
 int xhci_disable_slot(struct xhci_hcd *xhci, u32 slot_id)
@@ -3973,7 +3970,7 @@ int xhci_disable_slot(struct xhci_hcd *xhci, u32 slot_id)
 	u32 state;
 	int ret = 0;
 
-	command = xhci_alloc_command(xhci, false, GFP_KERNEL);
+	command = xhci_alloc_command(xhci, true, GFP_KERNEL);
 	if (!command)
 		return -ENOMEM;
 
@@ -3998,6 +3995,15 @@ int xhci_disable_slot(struct xhci_hcd *xhci, u32 slot_id)
 	}
 	xhci_ring_cmd_db(xhci);
 	spin_unlock_irqrestore(&xhci->lock, flags);
+
+	wait_for_completion(command->completion);
+
+	if (command->status != COMP_SUCCESS)
+		xhci_warn(xhci, "Unsuccessful disable slot %u command, status %d\n",
+			  slot_id, command->status);
+
+	xhci_free_command(xhci, command);
+
 	return ret;
 }
 
@@ -4094,23 +4100,20 @@ int xhci_alloc_dev(struct usb_hcd *hcd, struct usb_device *udev)
 
 	xhci_debugfs_create_slot(xhci, slot_id);
 
-#ifndef CONFIG_USB_DEFAULT_PERSIST
 	/*
 	 * If resetting upon resume, we can't put the controller into runtime
 	 * suspend if there is a device attached.
 	 */
 	if (xhci->quirks & XHCI_RESET_ON_RESUME)
 		pm_runtime_get_noresume(hcd->self.controller);
-#endif
 
 	/* Is this a LS or FS device under a HS hub? */
 	/* Hub or peripherial? */
 	return 1;
 
 disable_slot:
-	ret = xhci_disable_slot(xhci, udev->slot_id);
-	if (ret)
-		xhci_free_virt_device(xhci, udev->slot_id);
+	xhci_disable_slot(xhci, udev->slot_id);
+	xhci_free_virt_device(xhci, udev->slot_id);
 
 	return 0;
 }
@@ -4240,6 +4243,7 @@ static int xhci_setup_device(struct usb_hcd *hcd, struct usb_device *udev,
 
 		mutex_unlock(&xhci->mutex);
 		ret = xhci_disable_slot(xhci, udev->slot_id);
+		xhci_free_virt_device(xhci, udev->slot_id);
 		if (!ret)
 			xhci_alloc_dev(hcd, udev);
 		kfree(command->completion);
diff --git a/drivers/usb/mtu3/mtu3_gadget.c b/drivers/usb/mtu3/mtu3_gadget.c
index a9a65b4bbfed..9977600616d7 100644
--- a/drivers/usb/mtu3/mtu3_gadget.c
+++ b/drivers/usb/mtu3/mtu3_gadget.c
@@ -77,7 +77,7 @@ static int mtu3_ep_enable(struct mtu3_ep *mep)
 		if (usb_endpoint_xfer_int(desc) ||
 				usb_endpoint_xfer_isoc(desc)) {
 			interval = desc->bInterval;
-			interval = clamp_val(interval, 1, 16) - 1;
+			interval = clamp_val(interval, 1, 16);
 			if (usb_endpoint_xfer_isoc(desc) && comp_desc)
 				mult = comp_desc->bmAttributes;
 		}
@@ -89,10 +89,17 @@ static int mtu3_ep_enable(struct mtu3_ep *mep)
 		if (usb_endpoint_xfer_isoc(desc) ||
 				usb_endpoint_xfer_int(desc)) {
 			interval = desc->bInterval;
-			interval = clamp_val(interval, 1, 16) - 1;
+			interval = clamp_val(interval, 1, 16);
 			mult = usb_endpoint_maxp_mult(desc) - 1;
 		}
 		break;
+	case USB_SPEED_FULL:
+		if (usb_endpoint_xfer_isoc(desc))
+			interval = clamp_val(desc->bInterval, 1, 16);
+		else if (usb_endpoint_xfer_int(desc))
+			interval = clamp_val(desc->bInterval, 1, 255);
+
+		break;
 	default:
 		break; /*others are ignored */
 	}
@@ -235,6 +242,7 @@ struct usb_request *mtu3_alloc_request(struct usb_ep *ep, gfp_t gfp_flags)
 	mreq->request.dma = DMA_ADDR_INVALID;
 	mreq->epnum = mep->epnum;
 	mreq->mep = mep;
+	INIT_LIST_HEAD(&mreq->list);
 	trace_mtu3_alloc_request(mreq);
 
 	return &mreq->request;
diff --git a/drivers/usb/mtu3/mtu3_qmu.c b/drivers/usb/mtu3/mtu3_qmu.c
index 3f414f91b589..2ea3157ddb6e 100644
--- a/drivers/usb/mtu3/mtu3_qmu.c
+++ b/drivers/usb/mtu3/mtu3_qmu.c
@@ -273,6 +273,8 @@ static int mtu3_prepare_tx_gpd(struct mtu3_ep *mep, struct mtu3_request *mreq)
 			gpd->dw3_info |= cpu_to_le32(GPD_EXT_FLAG_ZLP);
 	}
 
+	/* prevent reorder, make sure GPD's HWO is set last */
+	mb();
 	gpd->dw0_info |= cpu_to_le32(GPD_FLAGS_IOC | GPD_FLAGS_HWO);
 
 	mreq->gpd = gpd;
@@ -306,6 +308,8 @@ static int mtu3_prepare_rx_gpd(struct mtu3_ep *mep, struct mtu3_request *mreq)
 	gpd->next_gpd = cpu_to_le32(lower_32_bits(enq_dma));
 	ext_addr |= GPD_EXT_NGP(mtu, upper_32_bits(enq_dma));
 	gpd->dw3_info = cpu_to_le32(ext_addr);
+	/* prevent reorder, make sure GPD's HWO is set last */
+	mb();
 	gpd->dw0_info |= cpu_to_le32(GPD_FLAGS_IOC | GPD_FLAGS_HWO);
 
 	mreq->gpd = gpd;
@@ -445,7 +449,8 @@ static void qmu_tx_zlp_error_handler(struct mtu3 *mtu, u8 epnum)
 		return;
 	}
 	mtu3_setbits(mbase, MU3D_EP_TXCR0(mep->epnum), TX_TXPKTRDY);
-
+	/* prevent reorder, make sure GPD's HWO is set last */
+	mb();
 	/* by pass the current GDP */
 	gpd_current->dw0_info |= cpu_to_le32(GPD_FLAGS_BPS | GPD_FLAGS_HWO);
 
diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c
index 7705328034ca..8a60c0d56863 100644
--- a/drivers/usb/serial/cp210x.c
+++ b/drivers/usb/serial/cp210x.c
@@ -1635,6 +1635,8 @@ static int cp2105_gpioconf_init(struct usb_serial *serial)
 
 	/*  2 banks of GPIO - One for the pins taken from each serial port */
 	if (intf_num == 0) {
+		priv->gc.ngpio = 2;
+
 		if (mode.eci == CP210X_PIN_MODE_MODEM) {
 			/* mark all GPIOs of this interface as reserved */
 			priv->gpio_altfunc = 0xff;
@@ -1645,8 +1647,9 @@ static int cp2105_gpioconf_init(struct usb_serial *serial)
 		priv->gpio_pushpull = (u8)((le16_to_cpu(config.gpio_mode) &
 						CP210X_ECI_GPIO_MODE_MASK) >>
 						CP210X_ECI_GPIO_MODE_OFFSET);
-		priv->gc.ngpio = 2;
 	} else if (intf_num == 1) {
+		priv->gc.ngpio = 3;
+
 		if (mode.sci == CP210X_PIN_MODE_MODEM) {
 			/* mark all GPIOs of this interface as reserved */
 			priv->gpio_altfunc = 0xff;
@@ -1657,7 +1660,6 @@ static int cp2105_gpioconf_init(struct usb_serial *serial)
 		priv->gpio_pushpull = (u8)((le16_to_cpu(config.gpio_mode) &
 						CP210X_SCI_GPIO_MODE_MASK) >>
 						CP210X_SCI_GPIO_MODE_OFFSET);
-		priv->gc.ngpio = 3;
 	} else {
 		return -ENODEV;
 	}
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index a484ff5e4ebf..42420bfc983c 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -1219,6 +1219,14 @@ static const struct usb_device_id option_ids[] = {
 	  .driver_info = NCTRL(2) | RSVD(3) },
 	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1063, 0xff),	/* Telit LN920 (ECM) */
 	  .driver_info = NCTRL(0) | RSVD(1) },
+	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1070, 0xff),	/* Telit FN990 (rmnet) */
+	  .driver_info = NCTRL(0) | RSVD(1) | RSVD(2) },
+	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1071, 0xff),	/* Telit FN990 (MBIM) */
+	  .driver_info = NCTRL(0) | RSVD(1) },
+	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1072, 0xff),	/* Telit FN990 (RNDIS) */
+	  .driver_info = NCTRL(2) | RSVD(3) },
+	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1073, 0xff),	/* Telit FN990 (ECM) */
+	  .driver_info = NCTRL(0) | RSVD(1) },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910),
 	  .driver_info = NCTRL(0) | RSVD(1) | RSVD(3) },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910_DUAL_MODEM),
@@ -1267,6 +1275,8 @@ static const struct usb_device_id option_ids[] = {
 	  .driver_info = NCTRL(2) },
 	{ USB_DEVICE(TELIT_VENDOR_ID, 0x9010),				/* Telit SBL FN980 flashing device */
 	  .driver_info = NCTRL(0) | ZLP },
+	{ USB_DEVICE(TELIT_VENDOR_ID, 0x9200),				/* Telit LE910S1 flashing device */
+	  .driver_info = NCTRL(0) | ZLP },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_MF622, 0xff, 0xff, 0xff) }, /* ZTE WCDMA products */
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0002, 0xff, 0xff, 0xff),
 	  .driver_info = RSVD(1) },
@@ -2094,6 +2104,9 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE_AND_INTERFACE_INFO(0x2cb7, 0x010b, 0xff, 0xff, 0x30) },	/* Fibocom FG150 Diag */
 	{ USB_DEVICE_AND_INTERFACE_INFO(0x2cb7, 0x010b, 0xff, 0, 0) },		/* Fibocom FG150 AT */
 	{ USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a0, 0xff) },			/* Fibocom NL668-AM/NL652-EU (laptop MBIM) */
+	{ USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a2, 0xff) },			/* Fibocom FM101-GL (laptop MBIM) */
+	{ USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x01a4, 0xff),			/* Fibocom FM101-GL (laptop MBIM) */
+	  .driver_info = RSVD(4) },
 	{ USB_DEVICE_INTERFACE_CLASS(0x2df3, 0x9d03, 0xff) },			/* LongSung M5710 */
 	{ USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1404, 0xff) },			/* GosunCn GM500 RNDIS */
 	{ USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1405, 0xff) },			/* GosunCn GM500 MBIM */
diff --git a/drivers/usb/serial/pl2303.c b/drivers/usb/serial/pl2303.c
index f45ca7ddf78e..a70fd86f735c 100644
--- a/drivers/usb/serial/pl2303.c
+++ b/drivers/usb/serial/pl2303.c
@@ -432,6 +432,7 @@ static int pl2303_detect_type(struct usb_serial *serial)
 	case 0x200:
 		switch (bcdDevice) {
 		case 0x100:
+		case 0x105:
 		case 0x305:
 		case 0x405:
 			/*
diff --git a/drivers/usb/typec/tcpm/fusb302.c b/drivers/usb/typec/tcpm/fusb302.c
index 7a2a17866a82..72f9001b0792 100644
--- a/drivers/usb/typec/tcpm/fusb302.c
+++ b/drivers/usb/typec/tcpm/fusb302.c
@@ -669,25 +669,27 @@ static int tcpm_set_cc(struct tcpc_dev *dev, enum typec_cc_status cc)
 		ret = fusb302_i2c_mask_write(chip, FUSB_REG_MASK,
 					     FUSB_REG_MASK_BC_LVL |
 					     FUSB_REG_MASK_COMP_CHNG,
-					     FUSB_REG_MASK_COMP_CHNG);
+					     FUSB_REG_MASK_BC_LVL);
 		if (ret < 0) {
 			fusb302_log(chip, "cannot set SRC interrupt, ret=%d",
 				    ret);
 			goto done;
 		}
 		chip->intr_comp_chng = true;
+		chip->intr_bc_lvl = false;
 		break;
 	case TYPEC_CC_RD:
 		ret = fusb302_i2c_mask_write(chip, FUSB_REG_MASK,
 					     FUSB_REG_MASK_BC_LVL |
 					     FUSB_REG_MASK_COMP_CHNG,
-					     FUSB_REG_MASK_BC_LVL);
+					     FUSB_REG_MASK_COMP_CHNG);
 		if (ret < 0) {
 			fusb302_log(chip, "cannot set SRC interrupt, ret=%d",
 				    ret);
 			goto done;
 		}
 		chip->intr_bc_lvl = true;
+		chip->intr_comp_chng = false;
 		break;
 	default:
 		break;
diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
index 7f2f3ff1b391..59d4fa2443f2 100644
--- a/drivers/usb/typec/tcpm/tcpm.c
+++ b/drivers/usb/typec/tcpm/tcpm.c
@@ -324,6 +324,7 @@ struct tcpm_port {
 
 	bool attached;
 	bool connected;
+	bool registered;
 	bool pd_supported;
 	enum typec_port_type port_type;
 
@@ -4110,11 +4111,7 @@ static void run_state_machine(struct tcpm_port *port)
 				       tcpm_try_src(port) ? SRC_TRY
 							  : SNK_ATTACHED,
 				       0);
-		else
-			/* Wait for VBUS, but not forever */
-			tcpm_set_state(port, PORT_RESET, PD_T_PS_SOURCE_ON);
 		break;
-
 	case SRC_TRY:
 		port->try_src_count++;
 		tcpm_set_cc(port, tcpm_rp_cc(port));
@@ -6295,7 +6292,8 @@ static enum hrtimer_restart state_machine_timer_handler(struct hrtimer *timer)
 {
 	struct tcpm_port *port = container_of(timer, struct tcpm_port, state_machine_timer);
 
-	kthread_queue_work(port->wq, &port->state_machine);
+	if (port->registered)
+		kthread_queue_work(port->wq, &port->state_machine);
 	return HRTIMER_NORESTART;
 }
 
@@ -6303,7 +6301,8 @@ static enum hrtimer_restart vdm_state_machine_timer_handler(struct hrtimer *time
 {
 	struct tcpm_port *port = container_of(timer, struct tcpm_port, vdm_state_machine_timer);
 
-	kthread_queue_work(port->wq, &port->vdm_state_machine);
+	if (port->registered)
+		kthread_queue_work(port->wq, &port->vdm_state_machine);
 	return HRTIMER_NORESTART;
 }
 
@@ -6311,7 +6310,8 @@ static enum hrtimer_restart enable_frs_timer_handler(struct hrtimer *timer)
 {
 	struct tcpm_port *port = container_of(timer, struct tcpm_port, enable_frs_timer);
 
-	kthread_queue_work(port->wq, &port->enable_frs);
+	if (port->registered)
+		kthread_queue_work(port->wq, &port->enable_frs);
 	return HRTIMER_NORESTART;
 }
 
@@ -6319,7 +6319,8 @@ static enum hrtimer_restart send_discover_timer_handler(struct hrtimer *timer)
 {
 	struct tcpm_port *port = container_of(timer, struct tcpm_port, send_discover_timer);
 
-	kthread_queue_work(port->wq, &port->send_discover_work);
+	if (port->registered)
+		kthread_queue_work(port->wq, &port->send_discover_work);
 	return HRTIMER_NORESTART;
 }
 
@@ -6407,6 +6408,7 @@ struct tcpm_port *tcpm_register_port(struct device *dev, struct tcpc_dev *tcpc)
 	typec_port_register_altmodes(port->typec_port,
 				     &tcpm_altmode_ops, port,
 				     port->port_altmode, ALTMODE_DISCOVERY_MAX);
+	port->registered = true;
 
 	mutex_lock(&port->lock);
 	tcpm_init(port);
@@ -6428,6 +6430,9 @@ void tcpm_unregister_port(struct tcpm_port *port)
 {
 	int i;
 
+	port->registered = false;
+	kthread_destroy_worker(port->wq);
+
 	hrtimer_cancel(&port->send_discover_timer);
 	hrtimer_cancel(&port->enable_frs_timer);
 	hrtimer_cancel(&port->vdm_state_machine_timer);
@@ -6439,7 +6444,6 @@ void tcpm_unregister_port(struct tcpm_port *port)
 	typec_unregister_port(port->typec_port);
 	usb_role_switch_put(port->role_sw);
 	tcpm_debugfs_exit(port);
-	kthread_destroy_worker(port->wq);
 }
 EXPORT_SYMBOL_GPL(tcpm_unregister_port);
 
diff --git a/drivers/usb/typec/tipd/core.c b/drivers/usb/typec/tipd/core.c
index fb8ef12bbe9c..6d27a5b5e3ca 100644
--- a/drivers/usb/typec/tipd/core.c
+++ b/drivers/usb/typec/tipd/core.c
@@ -653,7 +653,7 @@ static int cd321x_switch_power_state(struct tps6598x *tps, u8 target_state)
 	if (state == target_state)
 		return 0;
 
-	ret = tps6598x_exec_cmd(tps, "SPSS", sizeof(u8), &target_state, 0, NULL);
+	ret = tps6598x_exec_cmd(tps, "SSPS", sizeof(u8), &target_state, 0, NULL);
 	if (ret)
 		return ret;
 
@@ -707,6 +707,7 @@ static int tps6598x_probe(struct i2c_client *client)
 	u32 conf;
 	u32 vid;
 	int ret;
+	u64 mask1;
 
 	tps = devm_kzalloc(&client->dev, sizeof(*tps), GFP_KERNEL);
 	if (!tps)
@@ -730,11 +731,6 @@ static int tps6598x_probe(struct i2c_client *client)
 	if (i2c_check_functionality(client->adapter, I2C_FUNC_I2C))
 		tps->i2c_protocol = true;
 
-	/* Make sure the controller has application firmware running */
-	ret = tps6598x_check_mode(tps);
-	if (ret)
-		return ret;
-
 	if (np && of_device_is_compatible(np, "apple,cd321x")) {
 		/* Switch CD321X chips to the correct system power state */
 		ret = cd321x_switch_power_state(tps, TPS_SYSTEM_POWER_STATE_S0);
@@ -742,24 +738,27 @@ static int tps6598x_probe(struct i2c_client *client)
 			return ret;
 
 		/* CD321X chips have all interrupts masked initially */
-		ret = tps6598x_write64(tps, TPS_REG_INT_MASK1,
-					APPLE_CD_REG_INT_POWER_STATUS_UPDATE |
-					APPLE_CD_REG_INT_DATA_STATUS_UPDATE |
-					APPLE_CD_REG_INT_PLUG_EVENT);
-		if (ret)
-			return ret;
+		mask1 = APPLE_CD_REG_INT_POWER_STATUS_UPDATE |
+			APPLE_CD_REG_INT_DATA_STATUS_UPDATE |
+			APPLE_CD_REG_INT_PLUG_EVENT;
 
 		irq_handler = cd321x_interrupt;
 	} else {
 		/* Enable power status, data status and plug event interrupts */
-		ret = tps6598x_write64(tps, TPS_REG_INT_MASK1,
-				       TPS_REG_INT_POWER_STATUS_UPDATE |
-				       TPS_REG_INT_DATA_STATUS_UPDATE |
-				       TPS_REG_INT_PLUG_EVENT);
-		if (ret)
-			return ret;
+		mask1 = TPS_REG_INT_POWER_STATUS_UPDATE |
+			TPS_REG_INT_DATA_STATUS_UPDATE |
+			TPS_REG_INT_PLUG_EVENT;
 	}
 
+	/* Make sure the controller has application firmware running */
+	ret = tps6598x_check_mode(tps);
+	if (ret)
+		return ret;
+
+	ret = tps6598x_write64(tps, TPS_REG_INT_MASK1, mask1);
+	if (ret)
+		return ret;
+
 	ret = tps6598x_read32(tps, TPS_REG_STATUS, &status);
 	if (ret < 0)
 		return ret;
diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c
index 6aa28384f77f..08561bf7c40c 100644
--- a/drivers/usb/typec/ucsi/ucsi.c
+++ b/drivers/usb/typec/ucsi/ucsi.c
@@ -1150,7 +1150,9 @@ static int ucsi_register_port(struct ucsi *ucsi, int index)
 		ret = 0;
 	}
 
-	if (UCSI_CONSTAT_PWR_OPMODE(con->status.flags) == UCSI_CONSTAT_PWR_OPMODE_PD) {
+	if (con->partner &&
+	    UCSI_CONSTAT_PWR_OPMODE(con->status.flags) ==
+	    UCSI_CONSTAT_PWR_OPMODE_PD) {
 		ucsi_get_src_pdos(con);
 		ucsi_check_altmodes(con);
 	}
diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c
index 7332a74a4b00..09bbe53c3ac4 100644
--- a/drivers/vdpa/vdpa.c
+++ b/drivers/vdpa/vdpa.c
@@ -404,7 +404,8 @@ static int vdpa_mgmtdev_fill(const struct vdpa_mgmt_dev *mdev, struct sk_buff *m
 		goto msg_err;
 
 	while (mdev->id_table[i].device) {
-		supported_classes |= BIT(mdev->id_table[i].device);
+		if (mdev->id_table[i].device <= 63)
+			supported_classes |= BIT_ULL(mdev->id_table[i].device);
 		i++;
 	}
 
diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c
index 5f484fff8dbe..41b0cd17fcba 100644
--- a/drivers/vdpa/vdpa_sim/vdpa_sim.c
+++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c
@@ -591,8 +591,11 @@ static void vdpasim_free(struct vdpa_device *vdpa)
 		vringh_kiov_cleanup(&vdpasim->vqs[i].in_iov);
 	}
 
-	put_iova_domain(&vdpasim->iova);
-	iova_cache_put();
+	if (vdpa_get_dma_dev(vdpa)) {
+		put_iova_domain(&vdpasim->iova);
+		iova_cache_put();
+	}
+
 	kvfree(vdpasim->buffer);
 	if (vdpasim->iommu)
 		vhost_iotlb_free(vdpasim->iommu);
diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c
index c9204c62f339..eddcb64a910a 100644
--- a/drivers/vdpa/vdpa_user/vduse_dev.c
+++ b/drivers/vdpa/vdpa_user/vduse_dev.c
@@ -655,7 +655,8 @@ static void vduse_vdpa_get_config(struct vdpa_device *vdpa, unsigned int offset,
 {
 	struct vduse_dev *dev = vdpa_to_vduse(vdpa);
 
-	if (len > dev->config_size - offset)
+	if (offset > dev->config_size ||
+	    len > dev->config_size - offset)
 		return;
 
 	memcpy(buf, dev->config + offset, len);
@@ -975,7 +976,8 @@ static long vduse_dev_ioctl(struct file *file, unsigned int cmd,
 			break;
 
 		ret = -EINVAL;
-		if (config.length == 0 ||
+		if (config.offset > dev->config_size ||
+		    config.length == 0 ||
 		    config.length > dev->config_size - config.offset)
 			break;
 
diff --git a/drivers/vfio/pci/vfio_pci_igd.c b/drivers/vfio/pci/vfio_pci_igd.c
index 56cd551e0e04..362f91ec8845 100644
--- a/drivers/vfio/pci/vfio_pci_igd.c
+++ b/drivers/vfio/pci/vfio_pci_igd.c
@@ -98,7 +98,8 @@ static ssize_t vfio_pci_igd_rw(struct vfio_pci_core_device *vdev,
 			version = cpu_to_le16(0x0201);
 
 		if (igd_opregion_shift_copy(buf, &off,
-					    &version + (pos - OPREGION_VERSION),
+					    (u8 *)&version +
+					    (pos - OPREGION_VERSION),
 					    &pos, &remaining, bytes))
 			return -EFAULT;
 	}
@@ -121,7 +122,7 @@ static ssize_t vfio_pci_igd_rw(struct vfio_pci_core_device *vdev,
 					  OPREGION_SIZE : 0);
 
 		if (igd_opregion_shift_copy(buf, &off,
-					    &rvda + (pos - OPREGION_RVDA),
+					    (u8 *)&rvda + (pos - OPREGION_RVDA),
 					    &pos, &remaining, bytes))
 			return -EFAULT;
 	}
diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
index 82fb75464f92..735d1d344af9 100644
--- a/drivers/vfio/vfio.c
+++ b/drivers/vfio/vfio.c
@@ -232,7 +232,7 @@ static inline bool vfio_iommu_driver_allowed(struct vfio_container *container,
 }
 #endif /* CONFIG_VFIO_NOIOMMU */
 
-/**
+/*
  * IOMMU driver registration
  */
 int vfio_register_iommu_driver(const struct vfio_iommu_driver_ops *ops)
@@ -285,7 +285,7 @@ static int vfio_iommu_group_notifier(struct notifier_block *nb,
 				     unsigned long action, void *data);
 static void vfio_group_get(struct vfio_group *group);
 
-/**
+/*
  * Container objects - containers are created when /dev/vfio/vfio is
  * opened, but their lifecycle extends until the last user is done, so
  * it's freed via kref.  Must support container/group/device being
@@ -309,7 +309,7 @@ static void vfio_container_put(struct vfio_container *container)
 	kref_put(&container->kref, vfio_container_release);
 }
 
-/**
+/*
  * Group objects - create, release, get, put, search
  */
 static struct vfio_group *
@@ -488,7 +488,7 @@ static struct vfio_group *vfio_group_get_from_dev(struct device *dev)
 	return group;
 }
 
-/**
+/*
  * Device objects - create, release, get, put, search
  */
 /* Device reference always implies a group reference */
@@ -595,7 +595,7 @@ static int vfio_dev_viable(struct device *dev, void *data)
 	return ret;
 }
 
-/**
+/*
  * Async device support
  */
 static int vfio_group_nb_add_dev(struct vfio_group *group, struct device *dev)
@@ -689,7 +689,7 @@ static int vfio_iommu_group_notifier(struct notifier_block *nb,
 	return NOTIFY_OK;
 }
 
-/**
+/*
  * VFIO driver API
  */
 void vfio_init_group_dev(struct vfio_device *device, struct device *dev,
@@ -831,7 +831,7 @@ int vfio_register_emulated_iommu_dev(struct vfio_device *device)
 }
 EXPORT_SYMBOL_GPL(vfio_register_emulated_iommu_dev);
 
-/**
+/*
  * Get a reference to the vfio_device for a device.  Even if the
  * caller thinks they own the device, they could be racing with a
  * release call path, so we can't trust drvdata for the shortcut.
@@ -965,7 +965,7 @@ void vfio_unregister_group_dev(struct vfio_device *device)
 }
 EXPORT_SYMBOL_GPL(vfio_unregister_group_dev);
 
-/**
+/*
  * VFIO base fd, /dev/vfio/vfio
  */
 static long vfio_ioctl_check_extension(struct vfio_container *container,
@@ -1183,7 +1183,7 @@ static const struct file_operations vfio_fops = {
 	.compat_ioctl	= compat_ptr_ioctl,
 };
 
-/**
+/*
  * VFIO Group fd, /dev/vfio/$GROUP
  */
 static void __vfio_group_unset_container(struct vfio_group *group)
@@ -1536,7 +1536,7 @@ static const struct file_operations vfio_group_fops = {
 	.release	= vfio_group_fops_release,
 };
 
-/**
+/*
  * VFIO Device fd
  */
 static int vfio_device_fops_release(struct inode *inode, struct file *filep)
@@ -1611,7 +1611,7 @@ static const struct file_operations vfio_device_fops = {
 	.mmap		= vfio_device_fops_mmap,
 };
 
-/**
+/*
  * External user API, exported by symbols to be linked dynamically.
  *
  * The protocol includes:
@@ -1659,7 +1659,7 @@ struct vfio_group *vfio_group_get_external_user(struct file *filep)
 }
 EXPORT_SYMBOL_GPL(vfio_group_get_external_user);
 
-/**
+/*
  * External user API, exported by symbols to be linked dynamically.
  * The external user passes in a device pointer
  * to verify that:
@@ -1725,7 +1725,7 @@ long vfio_external_check_extension(struct vfio_group *group, unsigned long arg)
 }
 EXPORT_SYMBOL_GPL(vfio_external_check_extension);
 
-/**
+/*
  * Sub-module support
  */
 /*
@@ -2272,7 +2272,7 @@ struct iommu_domain *vfio_group_iommu_domain(struct vfio_group *group)
 }
 EXPORT_SYMBOL_GPL(vfio_group_iommu_domain);
 
-/**
+/*
  * Module/class support
  */
 static char *vfio_devnode(struct device *dev, umode_t *mode)
diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
index 01c59ce7e250..e3c4f059b21a 100644
--- a/drivers/vhost/vdpa.c
+++ b/drivers/vhost/vdpa.c
@@ -197,7 +197,7 @@ static int vhost_vdpa_config_validate(struct vhost_vdpa *v,
 	struct vdpa_device *vdpa = v->vdpa;
 	long size = vdpa->config->get_config_size(vdpa);
 
-	if (c->len == 0)
+	if (c->len == 0 || c->off > size)
 		return -EINVAL;
 
 	if (c->len > size - c->off)
@@ -1014,12 +1014,12 @@ static int vhost_vdpa_release(struct inode *inode, struct file *filep)
 
 	mutex_lock(&d->mutex);
 	filep->private_data = NULL;
+	vhost_vdpa_clean_irq(v);
 	vhost_vdpa_reset(v);
 	vhost_dev_stop(&v->vdev);
 	vhost_vdpa_iotlb_free(v);
 	vhost_vdpa_free_domain(v);
 	vhost_vdpa_config_put(v);
-	vhost_vdpa_clean_irq(v);
 	vhost_dev_cleanup(&v->vdev);
 	kfree(v->vdev.vqs);
 	mutex_unlock(&d->mutex);
diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index 938aefbc75ec..d6ca1c7ad513 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -511,8 +511,6 @@ static void vhost_vsock_handle_tx_kick(struct vhost_work *work)
 
 	vhost_disable_notify(&vsock->dev, vq);
 	do {
-		u32 len;
-
 		if (!vhost_vsock_more_replies(vsock)) {
 			/* Stop tx until the device processes already
 			 * pending replies.  Leave tx virtqueue
@@ -540,7 +538,7 @@ static void vhost_vsock_handle_tx_kick(struct vhost_work *work)
 			continue;
 		}
 
-		len = pkt->len;
+		total_len += sizeof(pkt->hdr) + pkt->len;
 
 		/* Deliver to monitoring devices all received packets */
 		virtio_transport_deliver_tap_pkt(pkt);
@@ -553,9 +551,7 @@ static void vhost_vsock_handle_tx_kick(struct vhost_work *work)
 		else
 			virtio_transport_free_pkt(pkt);
 
-		len += sizeof(pkt->hdr);
-		vhost_add_used(vq, head, len);
-		total_len += len;
+		vhost_add_used(vq, head, 0);
 		added = true;
 	} while(likely(!vhost_exceeds_weight(vq, ++pkts, total_len)));
 
diff --git a/drivers/video/console/sticon.c b/drivers/video/console/sticon.c
index 1b451165311c..40496e9e9b43 100644
--- a/drivers/video/console/sticon.c
+++ b/drivers/video/console/sticon.c
@@ -332,13 +332,13 @@ static u8 sticon_build_attr(struct vc_data *conp, u8 color,
 			    bool blink, bool underline, bool reverse,
 			    bool italic)
 {
-    u8 attr = ((color & 0x70) >> 1) | ((color & 7));
+	u8 fg = color & 7;
+	u8 bg = (color & 0x70) >> 4;
 
-    if (reverse) {
-	color = ((color >> 3) & 0x7) | ((color & 0x7) << 3);
-    }
-
-    return attr;
+	if (reverse)
+		return (fg << 3) | bg;
+	else
+		return (bg << 3) | fg;
 }
 
 static void sticon_invert_region(struct vc_data *conp, u16 *p, int count)
diff --git a/drivers/video/console/vgacon.c b/drivers/video/console/vgacon.c
index ef9c57ce0906..9a49ea6b5112 100644
--- a/drivers/video/console/vgacon.c
+++ b/drivers/video/console/vgacon.c
@@ -366,11 +366,17 @@ static void vgacon_init(struct vc_data *c, int init)
 	struct uni_pagedir *p;
 
 	/*
-	 * We cannot be loaded as a module, therefore init is always 1,
-	 * but vgacon_init can be called more than once, and init will
-	 * not be 1.
+	 * We cannot be loaded as a module, therefore init will be 1
+	 * if we are the default console, however if we are a fallback
+	 * console, for example if fbcon has failed registration, then
+	 * init will be 0, so we need to make sure our boot parameters
+	 * have been copied to the console structure for vgacon_resize
+	 * ultimately called by vc_resize.  Any subsequent calls to
+	 * vgacon_init init will have init set to 0 too.
 	 */
 	c->vc_can_do_color = vga_can_do_color;
+	c->vc_scan_lines = vga_scan_lines;
+	c->vc_font.height = c->vc_cell_height = vga_video_font_height;
 
 	/* set dimensions manually if init != 0 since vc_resize() will fail */
 	if (init) {
@@ -379,8 +385,6 @@ static void vgacon_init(struct vc_data *c, int init)
 	} else
 		vc_resize(c, vga_video_num_columns, vga_video_num_lines);
 
-	c->vc_scan_lines = vga_scan_lines;
-	c->vc_font.height = c->vc_cell_height = vga_video_font_height;
 	c->vc_complement_mask = 0x7700;
 	if (vga_512_chars)
 		c->vc_hi_font_mask = 0x0800;
diff --git a/drivers/video/fbdev/efifb.c b/drivers/video/fbdev/efifb.c
index edca3703b964..ea42ba6445b2 100644
--- a/drivers/video/fbdev/efifb.c
+++ b/drivers/video/fbdev/efifb.c
@@ -351,6 +351,17 @@ static int efifb_probe(struct platform_device *dev)
 	char *option = NULL;
 	efi_memory_desc_t md;
 
+	/*
+	 * Generic drivers must not be registered if a framebuffer exists.
+	 * If a native driver was probed, the display hardware was already
+	 * taken and attempting to use the system framebuffer is dangerous.
+	 */
+	if (num_registered_fb > 0) {
+		dev_err(&dev->dev,
+			"efifb: a framebuffer is already registered\n");
+		return -EINVAL;
+	}
+
 	if (screen_info.orig_video_isVGA != VIDEO_TYPE_EFI || pci_dev_disabled)
 		return -ENODEV;
 
diff --git a/drivers/video/fbdev/simplefb.c b/drivers/video/fbdev/simplefb.c
index 62f0ded70681..b63074fd892e 100644
--- a/drivers/video/fbdev/simplefb.c
+++ b/drivers/video/fbdev/simplefb.c
@@ -407,6 +407,17 @@ static int simplefb_probe(struct platform_device *pdev)
 	struct simplefb_par *par;
 	struct resource *mem;
 
+	/*
+	 * Generic drivers must not be registered if a framebuffer exists.
+	 * If a native driver was probed, the display hardware was already
+	 * taken and attempting to use the system framebuffer is dangerous.
+	 */
+	if (num_registered_fb > 0) {
+		dev_err(&pdev->dev,
+			"simplefb: a framebuffer is already registered\n");
+		return -EINVAL;
+	}
+
 	if (fb_get_options("simplefb", NULL))
 		return -ENODEV;
 
diff --git a/drivers/video/fbdev/xen-fbfront.c b/drivers/video/fbdev/xen-fbfront.c
index 5ec51445bee8..6826f986da43 100644
--- a/drivers/video/fbdev/xen-fbfront.c
+++ b/drivers/video/fbdev/xen-fbfront.c
@@ -695,6 +695,7 @@ static struct xenbus_driver xenfb_driver = {
 	.remove = xenfb_remove,
 	.resume = xenfb_resume,
 	.otherend_changed = xenfb_backend_changed,
+	.not_essential = true,
 };
 
 static int __init xenfb_init(void)
diff --git a/drivers/virt/nitro_enclaves/ne_misc_dev.c b/drivers/virt/nitro_enclaves/ne_misc_dev.c
index 8939612ee0e0..6894ccb868a6 100644
--- a/drivers/virt/nitro_enclaves/ne_misc_dev.c
+++ b/drivers/virt/nitro_enclaves/ne_misc_dev.c
@@ -886,8 +886,9 @@ static int ne_set_user_memory_region_ioctl(struct ne_enclave *ne_enclave,
 			goto put_pages;
 		}
 
-		gup_rc = get_user_pages(mem_region.userspace_addr + memory_size, 1, FOLL_GET,
-					ne_mem_region->pages + i, NULL);
+		gup_rc = get_user_pages_unlocked(mem_region.userspace_addr + memory_size, 1,
+						 ne_mem_region->pages + i, FOLL_GET);
+
 		if (gup_rc < 0) {
 			rc = gup_rc;
 
diff --git a/drivers/virtio/virtio_mem.c b/drivers/virtio/virtio_mem.c
index 0da0af251c73..96e5a8782769 100644
--- a/drivers/virtio/virtio_mem.c
+++ b/drivers/virtio/virtio_mem.c
@@ -2889,6 +2889,7 @@ static unsigned int virtio_mem_features[] = {
 #if defined(CONFIG_NUMA) && defined(CONFIG_ACPI_NUMA)
 	VIRTIO_MEM_F_ACPI_PXM,
 #endif
+	VIRTIO_MEM_F_UNPLUGGED_INACCESSIBLE,
 };
 
 static const struct virtio_device_id virtio_mem_id_table[] = {
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index 00f64f2f8b72..028b05d44546 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -14,9 +14,6 @@
 #include <linux/spinlock.h>
 #include <xen/xen.h>
 
-static bool force_used_validation = false;
-module_param(force_used_validation, bool, 0444);
-
 #ifdef DEBUG
 /* For development, we want to crash whenever the ring is screwed. */
 #define BAD_RING(_vq, fmt, args...)				\
@@ -185,9 +182,6 @@ struct vring_virtqueue {
 		} packed;
 	};
 
-	/* Per-descriptor in buffer length */
-	u32 *buflen;
-
 	/* How to notify other side. FIXME: commonalize hcalls! */
 	bool (*notify)(struct virtqueue *vq);
 
@@ -274,7 +268,7 @@ size_t virtio_max_dma_size(struct virtio_device *vdev)
 	size_t max_segment_size = SIZE_MAX;
 
 	if (vring_use_dma_api(vdev))
-		max_segment_size = dma_max_mapping_size(&vdev->dev);
+		max_segment_size = dma_max_mapping_size(vdev->dev.parent);
 
 	return max_segment_size;
 }
@@ -496,7 +490,6 @@ static inline int virtqueue_add_split(struct virtqueue *_vq,
 	unsigned int i, n, avail, descs_used, prev, err_idx;
 	int head;
 	bool indirect;
-	u32 buflen = 0;
 
 	START_USE(vq);
 
@@ -578,7 +571,6 @@ static inline int virtqueue_add_split(struct virtqueue *_vq,
 						     VRING_DESC_F_NEXT |
 						     VRING_DESC_F_WRITE,
 						     indirect);
-			buflen += sg->length;
 		}
 	}
 	/* Last one doesn't continue. */
@@ -618,10 +610,6 @@ static inline int virtqueue_add_split(struct virtqueue *_vq,
 	else
 		vq->split.desc_state[head].indir_desc = ctx;
 
-	/* Store in buffer length if necessary */
-	if (vq->buflen)
-		vq->buflen[head] = buflen;
-
 	/* Put entry in available array (but don't update avail->idx until they
 	 * do sync). */
 	avail = vq->split.avail_idx_shadow & (vq->split.vring.num - 1);
@@ -796,11 +784,6 @@ static void *virtqueue_get_buf_ctx_split(struct virtqueue *_vq,
 		BAD_RING(vq, "id %u is not a head!\n", i);
 		return NULL;
 	}
-	if (vq->buflen && unlikely(*len > vq->buflen[i])) {
-		BAD_RING(vq, "used len %d is larger than in buflen %u\n",
-			*len, vq->buflen[i]);
-		return NULL;
-	}
 
 	/* detach_buf_split clears data, so grab it now. */
 	ret = vq->split.desc_state[i].data;
@@ -1079,7 +1062,6 @@ static int virtqueue_add_indirect_packed(struct vring_virtqueue *vq,
 	unsigned int i, n, err_idx;
 	u16 head, id;
 	dma_addr_t addr;
-	u32 buflen = 0;
 
 	head = vq->packed.next_avail_idx;
 	desc = alloc_indirect_packed(total_sg, gfp);
@@ -1109,8 +1091,6 @@ static int virtqueue_add_indirect_packed(struct vring_virtqueue *vq,
 			desc[i].addr = cpu_to_le64(addr);
 			desc[i].len = cpu_to_le32(sg->length);
 			i++;
-			if (n >= out_sgs)
-				buflen += sg->length;
 		}
 	}
 
@@ -1164,10 +1144,6 @@ static int virtqueue_add_indirect_packed(struct vring_virtqueue *vq,
 	vq->packed.desc_state[id].indir_desc = desc;
 	vq->packed.desc_state[id].last = id;
 
-	/* Store in buffer length if necessary */
-	if (vq->buflen)
-		vq->buflen[id] = buflen;
-
 	vq->num_added += 1;
 
 	pr_debug("Added buffer head %i to %p\n", head, vq);
@@ -1203,7 +1179,6 @@ static inline int virtqueue_add_packed(struct virtqueue *_vq,
 	__le16 head_flags, flags;
 	u16 head, id, prev, curr, avail_used_flags;
 	int err;
-	u32 buflen = 0;
 
 	START_USE(vq);
 
@@ -1283,8 +1258,6 @@ static inline int virtqueue_add_packed(struct virtqueue *_vq,
 					1 << VRING_PACKED_DESC_F_AVAIL |
 					1 << VRING_PACKED_DESC_F_USED;
 			}
-			if (n >= out_sgs)
-				buflen += sg->length;
 		}
 	}
 
@@ -1304,10 +1277,6 @@ static inline int virtqueue_add_packed(struct virtqueue *_vq,
 	vq->packed.desc_state[id].indir_desc = ctx;
 	vq->packed.desc_state[id].last = prev;
 
-	/* Store in buffer length if necessary */
-	if (vq->buflen)
-		vq->buflen[id] = buflen;
-
 	/*
 	 * A driver MUST NOT make the first descriptor in the list
 	 * available before all subsequent descriptors comprising
@@ -1494,11 +1463,6 @@ static void *virtqueue_get_buf_ctx_packed(struct virtqueue *_vq,
 		BAD_RING(vq, "id %u is not a head!\n", id);
 		return NULL;
 	}
-	if (vq->buflen && unlikely(*len > vq->buflen[id])) {
-		BAD_RING(vq, "used len %d is larger than in buflen %u\n",
-			*len, vq->buflen[id]);
-		return NULL;
-	}
 
 	/* detach_buf_packed clears data, so grab it now. */
 	ret = vq->packed.desc_state[id].data;
@@ -1704,7 +1668,6 @@ static struct virtqueue *vring_create_virtqueue_packed(
 	struct vring_virtqueue *vq;
 	struct vring_packed_desc *ring;
 	struct vring_packed_desc_event *driver, *device;
-	struct virtio_driver *drv = drv_to_virtio(vdev->dev.driver);
 	dma_addr_t ring_dma_addr, driver_event_dma_addr, device_event_dma_addr;
 	size_t ring_size_in_bytes, event_size_in_bytes;
 
@@ -1794,15 +1757,6 @@ static struct virtqueue *vring_create_virtqueue_packed(
 	if (!vq->packed.desc_extra)
 		goto err_desc_extra;
 
-	if (!drv->suppress_used_validation || force_used_validation) {
-		vq->buflen = kmalloc_array(num, sizeof(*vq->buflen),
-					   GFP_KERNEL);
-		if (!vq->buflen)
-			goto err_buflen;
-	} else {
-		vq->buflen = NULL;
-	}
-
 	/* No callback?  Tell other side not to bother us. */
 	if (!callback) {
 		vq->packed.event_flags_shadow = VRING_PACKED_EVENT_FLAG_DISABLE;
@@ -1815,8 +1769,6 @@ static struct virtqueue *vring_create_virtqueue_packed(
 	spin_unlock(&vdev->vqs_list_lock);
 	return &vq->vq;
 
-err_buflen:
-	kfree(vq->packed.desc_extra);
 err_desc_extra:
 	kfree(vq->packed.desc_state);
 err_desc_state:
@@ -2224,7 +2176,6 @@ struct virtqueue *__vring_new_virtqueue(unsigned int index,
 					void (*callback)(struct virtqueue *),
 					const char *name)
 {
-	struct virtio_driver *drv = drv_to_virtio(vdev->dev.driver);
 	struct vring_virtqueue *vq;
 
 	if (virtio_has_feature(vdev, VIRTIO_F_RING_PACKED))
@@ -2284,15 +2235,6 @@ struct virtqueue *__vring_new_virtqueue(unsigned int index,
 	if (!vq->split.desc_extra)
 		goto err_extra;
 
-	if (!drv->suppress_used_validation || force_used_validation) {
-		vq->buflen = kmalloc_array(vring.num, sizeof(*vq->buflen),
-					   GFP_KERNEL);
-		if (!vq->buflen)
-			goto err_buflen;
-	} else {
-		vq->buflen = NULL;
-	}
-
 	/* Put everything in free lists. */
 	vq->free_head = 0;
 	memset(vq->split.desc_state, 0, vring.num *
@@ -2303,8 +2245,6 @@ struct virtqueue *__vring_new_virtqueue(unsigned int index,
 	spin_unlock(&vdev->vqs_list_lock);
 	return &vq->vq;
 
-err_buflen:
-	kfree(vq->split.desc_extra);
 err_extra:
 	kfree(vq->split.desc_state);
 err_state:
diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig
index a1b11c62da9e..33e941e40082 100644
--- a/drivers/xen/Kconfig
+++ b/drivers/xen/Kconfig
@@ -259,9 +259,15 @@ config XEN_SCSI_BACKEND
 	  if guests need generic access to SCSI devices.
 
 config XEN_PRIVCMD
-	tristate
+	tristate "Xen hypercall passthrough driver"
 	depends on XEN
 	default m
+	help
+	  The hypercall passthrough driver allows privileged user programs to
+	  perform Xen hypercalls. This driver is normally required for systems
+	  running as Dom0 to perform privileged operations, but in some
+	  disaggregated Xen setups this driver might be needed for other
+	  domains, too.
 
 config XEN_ACPI_PROCESSOR
 	tristate "Xen ACPI processor"
diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c
index a78704ae3618..46d9295d9a6e 100644
--- a/drivers/xen/events/events_base.c
+++ b/drivers/xen/events/events_base.c
@@ -1251,6 +1251,12 @@ int bind_evtchn_to_irq(evtchn_port_t evtchn)
 }
 EXPORT_SYMBOL_GPL(bind_evtchn_to_irq);
 
+int bind_evtchn_to_irq_lateeoi(evtchn_port_t evtchn)
+{
+	return bind_evtchn_to_irq_chip(evtchn, &xen_lateeoi_chip, NULL);
+}
+EXPORT_SYMBOL_GPL(bind_evtchn_to_irq_lateeoi);
+
 static int bind_ipi_to_irq(unsigned int ipi, unsigned int cpu)
 {
 	struct evtchn_bind_ipi bind_ipi;
diff --git a/drivers/xen/pvcalls-front.c b/drivers/xen/pvcalls-front.c
index 7984645b5956..3c9ae156b597 100644
--- a/drivers/xen/pvcalls-front.c
+++ b/drivers/xen/pvcalls-front.c
@@ -1275,6 +1275,7 @@ static struct xenbus_driver pvcalls_front_driver = {
 	.probe = pvcalls_front_probe,
 	.remove = pvcalls_front_remove,
 	.otherend_changed = pvcalls_front_changed,
+	.not_essential = true,
 };
 
 static int __init pvcalls_frontend_init(void)
diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c
index bd003ca8acbe..fe360c33ce71 100644
--- a/drivers/xen/xenbus/xenbus_probe.c
+++ b/drivers/xen/xenbus/xenbus_probe.c
@@ -909,7 +909,7 @@ static struct notifier_block xenbus_resume_nb = {
 
 static int __init xenbus_init(void)
 {
-	int err = 0;
+	int err;
 	uint64_t v = 0;
 	xen_store_domain_type = XS_UNKNOWN;
 
@@ -949,6 +949,29 @@ static int __init xenbus_init(void)
 		err = hvm_get_parameter(HVM_PARAM_STORE_PFN, &v);
 		if (err)
 			goto out_error;
+		/*
+		 * Uninitialized hvm_params are zero and return no error.
+		 * Although it is theoretically possible to have
+		 * HVM_PARAM_STORE_PFN set to zero on purpose, in reality it is
+		 * not zero when valid. If zero, it means that Xenstore hasn't
+		 * been properly initialized. Instead of attempting to map a
+		 * wrong guest physical address return error.
+		 *
+		 * Also recognize all bits set as an invalid value.
+		 */
+		if (!v || !~v) {
+			err = -ENOENT;
+			goto out_error;
+		}
+		/* Avoid truncation on 32-bit. */
+#if BITS_PER_LONG == 32
+		if (v > ULONG_MAX) {
+			pr_err("%s: cannot handle HVM_PARAM_STORE_PFN=%llx > ULONG_MAX\n",
+			       __func__, v);
+			err = -EINVAL;
+			goto out_error;
+		}
+#endif
 		xen_store_gfn = (unsigned long)v;
 		xen_store_interface =
 			xen_remap(xen_store_gfn << XEN_PAGE_SHIFT,
@@ -983,8 +1006,10 @@ static int __init xenbus_init(void)
 	 */
 	proc_create_mount_point("xen");
 #endif
+	return 0;
 
 out_error:
+	xen_store_domain_type = XS_UNKNOWN;
 	return err;
 }
 
diff --git a/drivers/xen/xenbus/xenbus_probe_frontend.c b/drivers/xen/xenbus/xenbus_probe_frontend.c
index 480944606a3c..07b010a68fcf 100644
--- a/drivers/xen/xenbus/xenbus_probe_frontend.c
+++ b/drivers/xen/xenbus/xenbus_probe_frontend.c
@@ -211,19 +211,11 @@ static int is_device_connecting(struct device *dev, void *data, bool ignore_none
 	if (drv && (dev->driver != drv))
 		return 0;
 
-	if (ignore_nonessential) {
-		/* With older QEMU, for PVonHVM guests the guest config files
-		 * could contain: vfb = [ 'vnc=1, vnclisten=0.0.0.0']
-		 * which is nonsensical as there is no PV FB (there can be
-		 * a PVKB) running as HVM guest. */
+	xendrv = to_xenbus_driver(dev->driver);
 
-		if ((strncmp(xendev->nodename, "device/vkbd", 11) == 0))
-			return 0;
+	if (ignore_nonessential && xendrv->not_essential)
+		return 0;
 
-		if ((strncmp(xendev->nodename, "device/vfb", 10) == 0))
-			return 0;
-	}
-	xendrv = to_xenbus_driver(dev->driver);
 	return (xendev->state < XenbusStateConnected ||
 		(xendev->state == XenbusStateConnected &&
 		 xendrv->is_ready && !xendrv->is_ready(xendev)));
diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c
index adafdf86f42f..fac918ccb305 100644
--- a/fs/9p/vfs_addr.c
+++ b/fs/9p/vfs_addr.c
@@ -108,7 +108,9 @@ static const struct netfs_read_request_ops v9fs_req_ops = {
  */
 static int v9fs_vfs_readpage(struct file *file, struct page *page)
 {
-	return netfs_readpage(file, page, &v9fs_req_ops, NULL);
+	struct folio *folio = page_folio(page);
+
+	return netfs_readpage(file, folio, &v9fs_req_ops, NULL);
 }
 
 /**
@@ -130,13 +132,15 @@ static void v9fs_vfs_readahead(struct readahead_control *ractl)
 
 static int v9fs_release_page(struct page *page, gfp_t gfp)
 {
-	if (PagePrivate(page))
+	struct folio *folio = page_folio(page);
+
+	if (folio_test_private(folio))
 		return 0;
 #ifdef CONFIG_9P_FSCACHE
-	if (PageFsCache(page)) {
+	if (folio_test_fscache(folio)) {
 		if (!(gfp & __GFP_DIRECT_RECLAIM) || !(gfp & __GFP_FS))
 			return 0;
-		wait_on_page_fscache(page);
+		folio_wait_fscache(folio);
 	}
 #endif
 	return 1;
@@ -152,55 +156,58 @@ static int v9fs_release_page(struct page *page, gfp_t gfp)
 static void v9fs_invalidate_page(struct page *page, unsigned int offset,
 				 unsigned int length)
 {
-	wait_on_page_fscache(page);
+	struct folio *folio = page_folio(page);
+
+	folio_wait_fscache(folio);
 }
 
-static int v9fs_vfs_writepage_locked(struct page *page)
+static int v9fs_vfs_write_folio_locked(struct folio *folio)
 {
-	struct inode *inode = page->mapping->host;
+	struct inode *inode = folio_inode(folio);
 	struct v9fs_inode *v9inode = V9FS_I(inode);
-	loff_t start = page_offset(page);
-	loff_t size = i_size_read(inode);
+	loff_t start = folio_pos(folio);
+	loff_t i_size = i_size_read(inode);
 	struct iov_iter from;
-	int err, len;
+	size_t len = folio_size(folio);
+	int err;
+
+	if (start >= i_size)
+		return 0; /* Simultaneous truncation occurred */
 
-	if (page->index == size >> PAGE_SHIFT)
-		len = size & ~PAGE_MASK;
-	else
-		len = PAGE_SIZE;
+	len = min_t(loff_t, i_size - start, len);
 
-	iov_iter_xarray(&from, WRITE, &page->mapping->i_pages, start, len);
+	iov_iter_xarray(&from, WRITE, &folio_mapping(folio)->i_pages, start, len);
 
 	/* We should have writeback_fid always set */
 	BUG_ON(!v9inode->writeback_fid);
 
-	set_page_writeback(page);
+	folio_start_writeback(folio);
 
 	p9_client_write(v9inode->writeback_fid, start, &from, &err);
 
-	end_page_writeback(page);
+	folio_end_writeback(folio);
 	return err;
 }
 
 static int v9fs_vfs_writepage(struct page *page, struct writeback_control *wbc)
 {
+	struct folio *folio = page_folio(page);
 	int retval;
 
-	p9_debug(P9_DEBUG_VFS, "page %p\n", page);
+	p9_debug(P9_DEBUG_VFS, "folio %p\n", folio);
 
-	retval = v9fs_vfs_writepage_locked(page);
+	retval = v9fs_vfs_write_folio_locked(folio);
 	if (retval < 0) {
 		if (retval == -EAGAIN) {
-			redirty_page_for_writepage(wbc, page);
+			folio_redirty_for_writepage(wbc, folio);
 			retval = 0;
 		} else {
-			SetPageError(page);
-			mapping_set_error(page->mapping, retval);
+			mapping_set_error(folio_mapping(folio), retval);
 		}
 	} else
 		retval = 0;
 
-	unlock_page(page);
+	folio_unlock(folio);
 	return retval;
 }
 
@@ -213,14 +220,15 @@ static int v9fs_vfs_writepage(struct page *page, struct writeback_control *wbc)
 
 static int v9fs_launder_page(struct page *page)
 {
+	struct folio *folio = page_folio(page);
 	int retval;
 
-	if (clear_page_dirty_for_io(page)) {
-		retval = v9fs_vfs_writepage_locked(page);
+	if (folio_clear_dirty_for_io(folio)) {
+		retval = v9fs_vfs_write_folio_locked(folio);
 		if (retval)
 			return retval;
 	}
-	wait_on_page_fscache(page);
+	folio_wait_fscache(folio);
 	return 0;
 }
 
@@ -265,10 +273,10 @@ v9fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 
 static int v9fs_write_begin(struct file *filp, struct address_space *mapping,
 			    loff_t pos, unsigned int len, unsigned int flags,
-			    struct page **pagep, void **fsdata)
+			    struct page **subpagep, void **fsdata)
 {
 	int retval;
-	struct page *page;
+	struct folio *folio;
 	struct v9fs_inode *v9inode = V9FS_I(mapping->host);
 
 	p9_debug(P9_DEBUG_VFS, "filp %p, mapping %p\n", filp, mapping);
@@ -279,31 +287,32 @@ static int v9fs_write_begin(struct file *filp, struct address_space *mapping,
 	 * file.  We need to do this before we get a lock on the page in case
 	 * there's more than one writer competing for the same cache block.
 	 */
-	retval = netfs_write_begin(filp, mapping, pos, len, flags, &page, fsdata,
+	retval = netfs_write_begin(filp, mapping, pos, len, flags, &folio, fsdata,
 				   &v9fs_req_ops, NULL);
 	if (retval < 0)
 		return retval;
 
-	*pagep = find_subpage(page, pos / PAGE_SIZE);
+	*subpagep = &folio->page;
 	return retval;
 }
 
 static int v9fs_write_end(struct file *filp, struct address_space *mapping,
 			  loff_t pos, unsigned int len, unsigned int copied,
-			  struct page *page, void *fsdata)
+			  struct page *subpage, void *fsdata)
 {
 	loff_t last_pos = pos + copied;
-	struct inode *inode = page->mapping->host;
+	struct folio *folio = page_folio(subpage);
+	struct inode *inode = mapping->host;
 
 	p9_debug(P9_DEBUG_VFS, "filp %p, mapping %p\n", filp, mapping);
 
-	if (!PageUptodate(page)) {
+	if (!folio_test_uptodate(folio)) {
 		if (unlikely(copied < len)) {
 			copied = 0;
 			goto out;
 		}
 
-		SetPageUptodate(page);
+		folio_mark_uptodate(folio);
 	}
 
 	/*
@@ -314,10 +323,10 @@ static int v9fs_write_end(struct file *filp, struct address_space *mapping,
 		inode_add_bytes(inode, last_pos - inode->i_size);
 		i_size_write(inode, last_pos);
 	}
-	set_page_dirty(page);
+	folio_mark_dirty(folio);
 out:
-	unlock_page(page);
-	put_page(page);
+	folio_unlock(folio);
+	folio_put(folio);
 
 	return copied;
 }
diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c
index 4244d48398ef..612e297f3763 100644
--- a/fs/9p/vfs_file.c
+++ b/fs/9p/vfs_file.c
@@ -528,13 +528,13 @@ static vm_fault_t
 v9fs_vm_page_mkwrite(struct vm_fault *vmf)
 {
 	struct v9fs_inode *v9inode;
-	struct page *page = vmf->page;
+	struct folio *folio = page_folio(vmf->page);
 	struct file *filp = vmf->vma->vm_file;
 	struct inode *inode = file_inode(filp);
 
 
-	p9_debug(P9_DEBUG_VFS, "page %p fid %lx\n",
-		 page, (unsigned long)filp->private_data);
+	p9_debug(P9_DEBUG_VFS, "folio %p fid %lx\n",
+		 folio, (unsigned long)filp->private_data);
 
 	v9inode = V9FS_I(inode);
 
@@ -542,24 +542,24 @@ v9fs_vm_page_mkwrite(struct vm_fault *vmf)
 	 * be modified.  We then assume the entire page will need writing back.
 	 */
 #ifdef CONFIG_9P_FSCACHE
-	if (PageFsCache(page) &&
-	    wait_on_page_fscache_killable(page) < 0)
-		return VM_FAULT_RETRY;
+	if (folio_test_fscache(folio) &&
+	    folio_wait_fscache_killable(folio) < 0)
+		return VM_FAULT_NOPAGE;
 #endif
 
 	/* Update file times before taking page lock */
 	file_update_time(filp);
 
 	BUG_ON(!v9inode->writeback_fid);
-	if (lock_page_killable(page) < 0)
+	if (folio_lock_killable(folio) < 0)
 		return VM_FAULT_RETRY;
-	if (page->mapping != inode->i_mapping)
+	if (folio_mapping(folio) != inode->i_mapping)
 		goto out_unlock;
-	wait_for_stable_page(page);
+	folio_wait_stable(folio);
 
 	return VM_FAULT_LOCKED;
 out_unlock:
-	unlock_page(page);
+	folio_unlock(folio);
 	return VM_FAULT_NOPAGE;
 }
 
diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index 4579bbda4634..da9b4f8577a1 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -103,13 +103,13 @@ struct afs_lookup_cookie {
 };
 
 /*
- * Drop the refs that we're holding on the pages we were reading into.  We've
+ * Drop the refs that we're holding on the folios we were reading into.  We've
  * got refs on the first nr_pages pages.
  */
 static void afs_dir_read_cleanup(struct afs_read *req)
 {
 	struct address_space *mapping = req->vnode->vfs_inode.i_mapping;
-	struct page *page;
+	struct folio *folio;
 	pgoff_t last = req->nr_pages - 1;
 
 	XA_STATE(xas, &mapping->i_pages, 0);
@@ -118,65 +118,56 @@ static void afs_dir_read_cleanup(struct afs_read *req)
 		return;
 
 	rcu_read_lock();
-	xas_for_each(&xas, page, last) {
-		if (xas_retry(&xas, page))
+	xas_for_each(&xas, folio, last) {
+		if (xas_retry(&xas, folio))
 			continue;
-		BUG_ON(xa_is_value(page));
-		BUG_ON(PageCompound(page));
-		ASSERTCMP(page->mapping, ==, mapping);
+		BUG_ON(xa_is_value(folio));
+		ASSERTCMP(folio_file_mapping(folio), ==, mapping);
 
-		put_page(page);
+		folio_put(folio);
 	}
 
 	rcu_read_unlock();
 }
 
 /*
- * check that a directory page is valid
+ * check that a directory folio is valid
  */
-static bool afs_dir_check_page(struct afs_vnode *dvnode, struct page *page,
-			       loff_t i_size)
+static bool afs_dir_check_folio(struct afs_vnode *dvnode, struct folio *folio,
+				loff_t i_size)
 {
-	struct afs_xdr_dir_page *dbuf;
-	loff_t latter, off;
-	int tmp, qty;
+	union afs_xdr_dir_block *block;
+	size_t offset, size;
+	loff_t pos;
 
-	/* Determine how many magic numbers there should be in this page, but
+	/* Determine how many magic numbers there should be in this folio, but
 	 * we must take care because the directory may change size under us.
 	 */
-	off = page_offset(page);
-	if (i_size <= off)
+	pos = folio_pos(folio);
+	if (i_size <= pos)
 		goto checked;
 
-	latter = i_size - off;
-	if (latter >= PAGE_SIZE)
-		qty = PAGE_SIZE;
-	else
-		qty = latter;
-	qty /= sizeof(union afs_xdr_dir_block);
-
-	/* check them */
-	dbuf = kmap_atomic(page);
-	for (tmp = 0; tmp < qty; tmp++) {
-		if (dbuf->blocks[tmp].hdr.magic != AFS_DIR_MAGIC) {
-			printk("kAFS: %s(%lx): bad magic %d/%d is %04hx\n",
-			       __func__, dvnode->vfs_inode.i_ino, tmp, qty,
-			       ntohs(dbuf->blocks[tmp].hdr.magic));
-			trace_afs_dir_check_failed(dvnode, off, i_size);
-			kunmap(page);
+	size = min_t(loff_t, folio_size(folio), i_size - pos);
+	for (offset = 0; offset < size; offset += sizeof(*block)) {
+		block = kmap_local_folio(folio, offset);
+		if (block->hdr.magic != AFS_DIR_MAGIC) {
+			printk("kAFS: %s(%lx): [%llx] bad magic %zx/%zx is %04hx\n",
+			       __func__, dvnode->vfs_inode.i_ino,
+			       pos, offset, size, ntohs(block->hdr.magic));
+			trace_afs_dir_check_failed(dvnode, pos + offset, i_size);
+			kunmap_local(block);
 			trace_afs_file_error(dvnode, -EIO, afs_file_error_dir_bad_magic);
 			goto error;
 		}
 
 		/* Make sure each block is NUL terminated so we can reasonably
-		 * use string functions on it.  The filenames in the page
+		 * use string functions on it.  The filenames in the folio
 		 * *should* be NUL-terminated anyway.
 		 */
-		((u8 *)&dbuf->blocks[tmp])[AFS_DIR_BLOCK_SIZE - 1] = 0;
-	}
-
-	kunmap_atomic(dbuf);
+		((u8 *)block)[AFS_DIR_BLOCK_SIZE - 1] = 0;
 
+		kunmap_local(block);
+	}
 checked:
 	afs_stat_v(dvnode, n_read_dir);
 	return true;
@@ -190,11 +181,11 @@ error:
  */
 static void afs_dir_dump(struct afs_vnode *dvnode, struct afs_read *req)
 {
-	struct afs_xdr_dir_page *dbuf;
+	union afs_xdr_dir_block *block;
 	struct address_space *mapping = dvnode->vfs_inode.i_mapping;
-	struct page *page;
-	unsigned int i, qty = PAGE_SIZE / sizeof(union afs_xdr_dir_block);
+	struct folio *folio;
 	pgoff_t last = req->nr_pages - 1;
+	size_t offset, size;
 
 	XA_STATE(xas, &mapping->i_pages, 0);
 
@@ -205,30 +196,28 @@ static void afs_dir_dump(struct afs_vnode *dvnode, struct afs_read *req)
 		req->pos, req->nr_pages,
 		req->iter->iov_offset,  iov_iter_count(req->iter));
 
-	xas_for_each(&xas, page, last) {
-		if (xas_retry(&xas, page))
+	xas_for_each(&xas, folio, last) {
+		if (xas_retry(&xas, folio))
 			continue;
 
-		BUG_ON(PageCompound(page));
-		BUG_ON(page->mapping != mapping);
-
-		dbuf = kmap_atomic(page);
-		for (i = 0; i < qty; i++) {
-			union afs_xdr_dir_block *block = &dbuf->blocks[i];
+		BUG_ON(folio_file_mapping(folio) != mapping);
 
-			pr_warn("[%02lx] %32phN\n", page->index * qty + i, block);
+		size = min_t(loff_t, folio_size(folio), req->actual_len - folio_pos(folio));
+		for (offset = 0; offset < size; offset += sizeof(*block)) {
+			block = kmap_local_folio(folio, offset);
+			pr_warn("[%02lx] %32phN\n", folio_index(folio) + offset, block);
+			kunmap_local(block);
 		}
-		kunmap_atomic(dbuf);
 	}
 }
 
 /*
- * Check all the pages in a directory.  All the pages are held pinned.
+ * Check all the blocks in a directory.  All the folios are held pinned.
  */
 static int afs_dir_check(struct afs_vnode *dvnode, struct afs_read *req)
 {
 	struct address_space *mapping = dvnode->vfs_inode.i_mapping;
-	struct page *page;
+	struct folio *folio;
 	pgoff_t last = req->nr_pages - 1;
 	int ret = 0;
 
@@ -238,14 +227,13 @@ static int afs_dir_check(struct afs_vnode *dvnode, struct afs_read *req)
 		return 0;
 
 	rcu_read_lock();
-	xas_for_each(&xas, page, last) {
-		if (xas_retry(&xas, page))
+	xas_for_each(&xas, folio, last) {
+		if (xas_retry(&xas, folio))
 			continue;
 
-		BUG_ON(PageCompound(page));
-		BUG_ON(page->mapping != mapping);
+		BUG_ON(folio_file_mapping(folio) != mapping);
 
-		if (!afs_dir_check_page(dvnode, page, req->file_size)) {
+		if (!afs_dir_check_folio(dvnode, folio, req->actual_len)) {
 			afs_dir_dump(dvnode, req);
 			ret = -EIO;
 			break;
@@ -274,15 +262,16 @@ static int afs_dir_open(struct inode *inode, struct file *file)
 
 /*
  * Read the directory into the pagecache in one go, scrubbing the previous
- * contents.  The list of pages is returned, pinning them so that they don't
+ * contents.  The list of folios is returned, pinning them so that they don't
  * get reclaimed during the iteration.
  */
 static struct afs_read *afs_read_dir(struct afs_vnode *dvnode, struct key *key)
 	__acquires(&dvnode->validate_lock)
 {
+	struct address_space *mapping = dvnode->vfs_inode.i_mapping;
 	struct afs_read *req;
 	loff_t i_size;
-	int nr_pages, i, n;
+	int nr_pages, i;
 	int ret;
 
 	_enter("");
@@ -320,43 +309,30 @@ expand:
 	req->iter = &req->def_iter;
 
 	/* Fill in any gaps that we might find where the memory reclaimer has
-	 * been at work and pin all the pages.  If there are any gaps, we will
+	 * been at work and pin all the folios.  If there are any gaps, we will
 	 * need to reread the entire directory contents.
 	 */
 	i = req->nr_pages;
 	while (i < nr_pages) {
-		struct page *pages[8], *page;
-
-		n = find_get_pages_contig(dvnode->vfs_inode.i_mapping, i,
-					  min_t(unsigned int, nr_pages - i,
-						ARRAY_SIZE(pages)),
-					  pages);
-		_debug("find %u at %u/%u", n, i, nr_pages);
-
-		if (n == 0) {
-			gfp_t gfp = dvnode->vfs_inode.i_mapping->gfp_mask;
+		struct folio *folio;
 
+		folio = filemap_get_folio(mapping, i);
+		if (!folio) {
 			if (test_and_clear_bit(AFS_VNODE_DIR_VALID, &dvnode->flags))
 				afs_stat_v(dvnode, n_inval);
 
 			ret = -ENOMEM;
-			page = __page_cache_alloc(gfp);
-			if (!page)
+			folio = __filemap_get_folio(mapping,
+						    i, FGP_LOCK | FGP_CREAT,
+						    mapping->gfp_mask);
+			if (!folio)
 				goto error;
-			ret = add_to_page_cache_lru(page,
-						    dvnode->vfs_inode.i_mapping,
-						    i, gfp);
-			if (ret < 0)
-				goto error;
-
-			attach_page_private(page, (void *)1);
-			unlock_page(page);
-			req->nr_pages++;
-			i++;
-		} else {
-			req->nr_pages += n;
-			i += n;
+			folio_attach_private(folio, (void *)1);
+			folio_unlock(folio);
 		}
+
+		req->nr_pages += folio_nr_pages(folio);
+		i += folio_nr_pages(folio);
 	}
 
 	/* If we're going to reload, we need to lock all the pages to prevent
@@ -424,7 +400,7 @@ static int afs_dir_iterate_block(struct afs_vnode *dvnode,
 	size_t nlen;
 	int tmp;
 
-	_enter("%u,%x,%p,,",(unsigned)ctx->pos,blkoff,block);
+	_enter("%llx,%x", ctx->pos, blkoff);
 
 	curr = (ctx->pos - blkoff) / sizeof(union afs_xdr_dirent);
 
@@ -513,12 +489,10 @@ static int afs_dir_iterate(struct inode *dir, struct dir_context *ctx,
 			   struct key *key, afs_dataversion_t *_dir_version)
 {
 	struct afs_vnode *dvnode = AFS_FS_I(dir);
-	struct afs_xdr_dir_page *dbuf;
 	union afs_xdr_dir_block *dblock;
 	struct afs_read *req;
-	struct page *page;
-	unsigned blkoff, limit;
-	void __rcu **slot;
+	struct folio *folio;
+	unsigned offset, size;
 	int ret;
 
 	_enter("{%lu},%u,,", dir->i_ino, (unsigned)ctx->pos);
@@ -540,43 +514,30 @@ static int afs_dir_iterate(struct inode *dir, struct dir_context *ctx,
 	/* walk through the blocks in sequence */
 	ret = 0;
 	while (ctx->pos < req->actual_len) {
-		blkoff = ctx->pos & ~(sizeof(union afs_xdr_dir_block) - 1);
-
-		/* Fetch the appropriate page from the directory and re-add it
+		/* Fetch the appropriate folio from the directory and re-add it
 		 * to the LRU.  We have all the pages pinned with an extra ref.
 		 */
-		rcu_read_lock();
-		page = NULL;
-		slot = radix_tree_lookup_slot(&dvnode->vfs_inode.i_mapping->i_pages,
-					      blkoff / PAGE_SIZE);
-		if (slot)
-			page = radix_tree_deref_slot(slot);
-		rcu_read_unlock();
-		if (!page) {
+		folio = __filemap_get_folio(dir->i_mapping, ctx->pos / PAGE_SIZE,
+					    FGP_ACCESSED, 0);
+		if (!folio) {
 			ret = afs_bad(dvnode, afs_file_error_dir_missing_page);
 			break;
 		}
-		mark_page_accessed(page);
 
-		limit = blkoff & ~(PAGE_SIZE - 1);
+		offset = round_down(ctx->pos, sizeof(*dblock)) - folio_file_pos(folio);
+		size = min_t(loff_t, folio_size(folio),
+			     req->actual_len - folio_file_pos(folio));
 
-		dbuf = kmap(page);
-
-		/* deal with the individual blocks stashed on this page */
 		do {
-			dblock = &dbuf->blocks[(blkoff % PAGE_SIZE) /
-					       sizeof(union afs_xdr_dir_block)];
-			ret = afs_dir_iterate_block(dvnode, ctx, dblock, blkoff);
-			if (ret != 1) {
-				kunmap(page);
+			dblock = kmap_local_folio(folio, offset);
+			ret = afs_dir_iterate_block(dvnode, ctx, dblock,
+						    folio_file_pos(folio) + offset);
+			kunmap_local(dblock);
+			if (ret != 1)
 				goto out;
-			}
 
-			blkoff += sizeof(union afs_xdr_dir_block);
+		} while (offset += sizeof(*dblock), offset < size);
 
-		} while (ctx->pos < dir->i_size && blkoff < limit);
-
-		kunmap(page);
 		ret = 0;
 	}
 
@@ -2037,42 +1998,42 @@ error:
 }
 
 /*
- * Release a directory page and clean up its private state if it's not busy
- * - return true if the page can now be released, false if not
+ * Release a directory folio and clean up its private state if it's not busy
+ * - return true if the folio can now be released, false if not
  */
-static int afs_dir_releasepage(struct page *page, gfp_t gfp_flags)
+static int afs_dir_releasepage(struct page *subpage, gfp_t gfp_flags)
 {
-	struct afs_vnode *dvnode = AFS_FS_I(page->mapping->host);
+	struct folio *folio = page_folio(subpage);
+	struct afs_vnode *dvnode = AFS_FS_I(folio_inode(folio));
 
-	_enter("{{%llx:%llu}[%lu]}", dvnode->fid.vid, dvnode->fid.vnode, page->index);
+	_enter("{{%llx:%llu}[%lu]}", dvnode->fid.vid, dvnode->fid.vnode, folio_index(folio));
 
-	detach_page_private(page);
+	folio_detach_private(folio);
 
 	/* The directory will need reloading. */
 	if (test_and_clear_bit(AFS_VNODE_DIR_VALID, &dvnode->flags))
 		afs_stat_v(dvnode, n_relpg);
-	return 1;
+	return true;
 }
 
 /*
- * invalidate part or all of a page
- * - release a page and clean up its private data if offset is 0 (indicating
- *   the entire page)
+ * Invalidate part or all of a folio.
  */
-static void afs_dir_invalidatepage(struct page *page, unsigned int offset,
+static void afs_dir_invalidatepage(struct page *subpage, unsigned int offset,
 				   unsigned int length)
 {
-	struct afs_vnode *dvnode = AFS_FS_I(page->mapping->host);
+	struct folio *folio = page_folio(subpage);
+	struct afs_vnode *dvnode = AFS_FS_I(folio_inode(folio));
 
-	_enter("{%lu},%u,%u", page->index, offset, length);
+	_enter("{%lu},%u,%u", folio_index(folio), offset, length);
 
-	BUG_ON(!PageLocked(page));
+	BUG_ON(!folio_test_locked(folio));
 
 	/* The directory will need reloading. */
 	if (test_and_clear_bit(AFS_VNODE_DIR_VALID, &dvnode->flags))
 		afs_stat_v(dvnode, n_inval);
 
-	/* we clean up only if the entire page is being invalidated */
-	if (offset == 0 && length == thp_size(page))
-		detach_page_private(page);
+	/* we clean up only if the entire folio is being invalidated */
+	if (offset == 0 && length == folio_size(folio))
+		folio_detach_private(folio);
 }
diff --git a/fs/afs/dir_edit.c b/fs/afs/dir_edit.c
index 540b9fc96824..d98e109ecee9 100644
--- a/fs/afs/dir_edit.c
+++ b/fs/afs/dir_edit.c
@@ -105,6 +105,25 @@ static void afs_clear_contig_bits(union afs_xdr_dir_block *block,
 }
 
 /*
+ * Get a new directory folio.
+ */
+static struct folio *afs_dir_get_folio(struct afs_vnode *vnode, pgoff_t index)
+{
+	struct address_space *mapping = vnode->vfs_inode.i_mapping;
+	struct folio *folio;
+
+	folio = __filemap_get_folio(mapping, index,
+				    FGP_LOCK | FGP_ACCESSED | FGP_CREAT,
+				    mapping->gfp_mask);
+	if (!folio)
+		clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags);
+	else if (folio && !folio_test_private(folio))
+		folio_attach_private(folio, (void *)1);
+
+	return folio;
+}
+
+/*
  * Scan a directory block looking for a dirent of the right name.
  */
 static int afs_dir_scan_block(union afs_xdr_dir_block *block, struct qstr *name,
@@ -188,13 +207,11 @@ void afs_edit_dir_add(struct afs_vnode *vnode,
 		      enum afs_edit_dir_reason why)
 {
 	union afs_xdr_dir_block *meta, *block;
-	struct afs_xdr_dir_page *meta_page, *dir_page;
 	union afs_xdr_dirent *de;
-	struct page *page0, *page;
+	struct folio *folio0, *folio;
 	unsigned int need_slots, nr_blocks, b;
 	pgoff_t index;
 	loff_t i_size;
-	gfp_t gfp;
 	int slot;
 
 	_enter(",,{%d,%s},", name->len, name->name);
@@ -206,10 +223,8 @@ void afs_edit_dir_add(struct afs_vnode *vnode,
 		return;
 	}
 
-	gfp = vnode->vfs_inode.i_mapping->gfp_mask;
-	page0 = find_or_create_page(vnode->vfs_inode.i_mapping, 0, gfp);
-	if (!page0) {
-		clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags);
+	folio0 = afs_dir_get_folio(vnode, 0);
+	if (!folio0) {
 		_leave(" [fgp]");
 		return;
 	}
@@ -217,42 +232,35 @@ void afs_edit_dir_add(struct afs_vnode *vnode,
 	/* Work out how many slots we're going to need. */
 	need_slots = afs_dir_calc_slots(name->len);
 
-	meta_page = kmap(page0);
-	meta = &meta_page->blocks[0];
+	meta = kmap_local_folio(folio0, 0);
 	if (i_size == 0)
 		goto new_directory;
 	nr_blocks = i_size / AFS_DIR_BLOCK_SIZE;
 
-	/* Find a block that has sufficient slots available.  Each VM page
+	/* Find a block that has sufficient slots available.  Each folio
 	 * contains two or more directory blocks.
 	 */
 	for (b = 0; b < nr_blocks + 1; b++) {
-		/* If the directory extended into a new page, then we need to
-		 * tack a new page on the end.
+		/* If the directory extended into a new folio, then we need to
+		 * tack a new folio on the end.
 		 */
 		index = b / AFS_DIR_BLOCKS_PER_PAGE;
-		if (index == 0) {
-			page = page0;
-			dir_page = meta_page;
-		} else {
-			if (nr_blocks >= AFS_DIR_MAX_BLOCKS)
-				goto error;
-			gfp = vnode->vfs_inode.i_mapping->gfp_mask;
-			page = find_or_create_page(vnode->vfs_inode.i_mapping,
-						   index, gfp);
-			if (!page)
+		if (nr_blocks >= AFS_DIR_MAX_BLOCKS)
+			goto error;
+		if (index >= folio_nr_pages(folio0)) {
+			folio = afs_dir_get_folio(vnode, index);
+			if (!folio)
 				goto error;
-			if (!PagePrivate(page))
-				attach_page_private(page, (void *)1);
-			dir_page = kmap(page);
+		} else {
+			folio = folio0;
 		}
 
+		block = kmap_local_folio(folio, b * AFS_DIR_BLOCK_SIZE - folio_file_pos(folio));
+
 		/* Abandon the edit if we got a callback break. */
 		if (!test_bit(AFS_VNODE_DIR_VALID, &vnode->flags))
 			goto invalidated;
 
-		block = &dir_page->blocks[b % AFS_DIR_BLOCKS_PER_PAGE];
-
 		_debug("block %u: %2u %3u %u",
 		       b,
 		       (b < AFS_DIR_BLOCKS_WITH_CTR) ? meta->meta.alloc_ctrs[b] : 99,
@@ -266,7 +274,7 @@ void afs_edit_dir_add(struct afs_vnode *vnode,
 			afs_set_i_size(vnode, (b + 1) * AFS_DIR_BLOCK_SIZE);
 		}
 
-		/* Only lower dir pages have a counter in the header. */
+		/* Only lower dir blocks have a counter in the header. */
 		if (b >= AFS_DIR_BLOCKS_WITH_CTR ||
 		    meta->meta.alloc_ctrs[b] >= need_slots) {
 			/* We need to try and find one or more consecutive
@@ -279,10 +287,10 @@ void afs_edit_dir_add(struct afs_vnode *vnode,
 			}
 		}
 
-		if (page != page0) {
-			unlock_page(page);
-			kunmap(page);
-			put_page(page);
+		kunmap_local(block);
+		if (folio != folio0) {
+			folio_unlock(folio);
+			folio_put(folio);
 		}
 	}
 
@@ -298,8 +306,8 @@ new_directory:
 	i_size = AFS_DIR_BLOCK_SIZE;
 	afs_set_i_size(vnode, i_size);
 	slot = AFS_DIR_RESV_BLOCKS0;
-	page = page0;
-	block = meta;
+	folio = folio0;
+	block = kmap_local_folio(folio, 0);
 	nr_blocks = 1;
 	b = 0;
 
@@ -318,10 +326,10 @@ found_space:
 
 	/* Adjust the bitmap. */
 	afs_set_contig_bits(block, slot, need_slots);
-	if (page != page0) {
-		unlock_page(page);
-		kunmap(page);
-		put_page(page);
+	kunmap_local(block);
+	if (folio != folio0) {
+		folio_unlock(folio);
+		folio_put(folio);
 	}
 
 	/* Adjust the allocation counter. */
@@ -333,18 +341,19 @@ found_space:
 	_debug("Insert %s in %u[%u]", name->name, b, slot);
 
 out_unmap:
-	unlock_page(page0);
-	kunmap(page0);
-	put_page(page0);
+	kunmap_local(meta);
+	folio_unlock(folio0);
+	folio_put(folio0);
 	_leave("");
 	return;
 
 invalidated:
 	trace_afs_edit_dir(vnode, why, afs_edit_dir_create_inval, 0, 0, 0, 0, name->name);
 	clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags);
-	if (page != page0) {
-		kunmap(page);
-		put_page(page);
+	kunmap_local(block);
+	if (folio != folio0) {
+		folio_unlock(folio);
+		folio_put(folio);
 	}
 	goto out_unmap;
 
@@ -364,10 +373,9 @@ error:
 void afs_edit_dir_remove(struct afs_vnode *vnode,
 			 struct qstr *name, enum afs_edit_dir_reason why)
 {
-	struct afs_xdr_dir_page *meta_page, *dir_page;
 	union afs_xdr_dir_block *meta, *block;
 	union afs_xdr_dirent *de;
-	struct page *page0, *page;
+	struct folio *folio0, *folio;
 	unsigned int need_slots, nr_blocks, b;
 	pgoff_t index;
 	loff_t i_size;
@@ -384,9 +392,8 @@ void afs_edit_dir_remove(struct afs_vnode *vnode,
 	}
 	nr_blocks = i_size / AFS_DIR_BLOCK_SIZE;
 
-	page0 = find_lock_page(vnode->vfs_inode.i_mapping, 0);
-	if (!page0) {
-		clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags);
+	folio0 = afs_dir_get_folio(vnode, 0);
+	if (!folio0) {
 		_leave(" [fgp]");
 		return;
 	}
@@ -394,30 +401,27 @@ void afs_edit_dir_remove(struct afs_vnode *vnode,
 	/* Work out how many slots we're going to discard. */
 	need_slots = afs_dir_calc_slots(name->len);
 
-	meta_page = kmap(page0);
-	meta = &meta_page->blocks[0];
+	meta = kmap_local_folio(folio0, 0);
 
-	/* Find a page that has sufficient slots available.  Each VM page
+	/* Find a block that has sufficient slots available.  Each folio
 	 * contains two or more directory blocks.
 	 */
 	for (b = 0; b < nr_blocks; b++) {
 		index = b / AFS_DIR_BLOCKS_PER_PAGE;
-		if (index != 0) {
-			page = find_lock_page(vnode->vfs_inode.i_mapping, index);
-			if (!page)
+		if (index >= folio_nr_pages(folio0)) {
+			folio = afs_dir_get_folio(vnode, index);
+			if (!folio)
 				goto error;
-			dir_page = kmap(page);
 		} else {
-			page = page0;
-			dir_page = meta_page;
+			folio = folio0;
 		}
 
+		block = kmap_local_folio(folio, b * AFS_DIR_BLOCK_SIZE - folio_file_pos(folio));
+
 		/* Abandon the edit if we got a callback break. */
 		if (!test_bit(AFS_VNODE_DIR_VALID, &vnode->flags))
 			goto invalidated;
 
-		block = &dir_page->blocks[b % AFS_DIR_BLOCKS_PER_PAGE];
-
 		if (b > AFS_DIR_BLOCKS_WITH_CTR ||
 		    meta->meta.alloc_ctrs[b] <= AFS_DIR_SLOTS_PER_BLOCK - 1 - need_slots) {
 			slot = afs_dir_scan_block(block, name, b);
@@ -425,10 +429,10 @@ void afs_edit_dir_remove(struct afs_vnode *vnode,
 				goto found_dirent;
 		}
 
-		if (page != page0) {
-			unlock_page(page);
-			kunmap(page);
-			put_page(page);
+		kunmap_local(block);
+		if (folio != folio0) {
+			folio_unlock(folio);
+			folio_put(folio);
 		}
 	}
 
@@ -449,10 +453,10 @@ found_dirent:
 
 	/* Adjust the bitmap. */
 	afs_clear_contig_bits(block, slot, need_slots);
-	if (page != page0) {
-		unlock_page(page);
-		kunmap(page);
-		put_page(page);
+	kunmap_local(block);
+	if (folio != folio0) {
+		folio_unlock(folio);
+		folio_put(folio);
 	}
 
 	/* Adjust the allocation counter. */
@@ -464,9 +468,9 @@ found_dirent:
 	_debug("Remove %s from %u[%u]", name->name, b, slot);
 
 out_unmap:
-	unlock_page(page0);
-	kunmap(page0);
-	put_page(page0);
+	kunmap_local(meta);
+	folio_unlock(folio0);
+	folio_put(folio0);
 	_leave("");
 	return;
 
@@ -474,10 +478,10 @@ invalidated:
 	trace_afs_edit_dir(vnode, why, afs_edit_dir_delete_inval,
 			   0, 0, 0, 0, name->name);
 	clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags);
-	if (page != page0) {
-		unlock_page(page);
-		kunmap(page);
-		put_page(page);
+	kunmap_local(block);
+	if (folio != folio0) {
+		folio_unlock(folio);
+		folio_put(folio);
 	}
 	goto out_unmap;
 
diff --git a/fs/afs/file.c b/fs/afs/file.c
index eb11d047c0ae..afe4b803f84b 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -324,21 +324,24 @@ static int afs_symlink_readpage(struct file *file, struct page *page)
 {
 	struct afs_vnode *vnode = AFS_FS_I(page->mapping->host);
 	struct afs_read *fsreq;
+	struct folio *folio = page_folio(page);
 	int ret;
 
 	fsreq = afs_alloc_read(GFP_NOFS);
 	if (!fsreq)
 		return -ENOMEM;
 
-	fsreq->pos	= page->index * PAGE_SIZE;
-	fsreq->len	= PAGE_SIZE;
+	fsreq->pos	= folio_pos(folio);
+	fsreq->len	= folio_size(folio);
 	fsreq->vnode	= vnode;
 	fsreq->iter	= &fsreq->def_iter;
 	iov_iter_xarray(&fsreq->def_iter, READ, &page->mapping->i_pages,
 			fsreq->pos, fsreq->len);
 
 	ret = afs_fetch_data(fsreq->vnode, fsreq);
-	page_endio(page, false, ret);
+	if (ret == 0)
+		SetPageUptodate(page);
+	unlock_page(page);
 	return ret;
 }
 
@@ -362,7 +365,7 @@ static int afs_begin_cache_operation(struct netfs_read_request *rreq)
 }
 
 static int afs_check_write_begin(struct file *file, loff_t pos, unsigned len,
-				 struct page *page, void **_fsdata)
+				 struct folio *folio, void **_fsdata)
 {
 	struct afs_vnode *vnode = AFS_FS_I(file_inode(file));
 
@@ -385,7 +388,9 @@ const struct netfs_read_request_ops afs_req_ops = {
 
 static int afs_readpage(struct file *file, struct page *page)
 {
-	return netfs_readpage(file, page, &afs_req_ops, NULL);
+	struct folio *folio = page_folio(page);
+
+	return netfs_readpage(file, folio, &afs_req_ops, NULL);
 }
 
 static void afs_readahead(struct readahead_control *ractl)
@@ -397,29 +402,29 @@ static void afs_readahead(struct readahead_control *ractl)
  * Adjust the dirty region of the page on truncation or full invalidation,
  * getting rid of the markers altogether if the region is entirely invalidated.
  */
-static void afs_invalidate_dirty(struct page *page, unsigned int offset,
+static void afs_invalidate_dirty(struct folio *folio, unsigned int offset,
 				 unsigned int length)
 {
-	struct afs_vnode *vnode = AFS_FS_I(page->mapping->host);
+	struct afs_vnode *vnode = AFS_FS_I(folio_inode(folio));
 	unsigned long priv;
 	unsigned int f, t, end = offset + length;
 
-	priv = page_private(page);
+	priv = (unsigned long)folio_get_private(folio);
 
 	/* we clean up only if the entire page is being invalidated */
-	if (offset == 0 && length == thp_size(page))
+	if (offset == 0 && length == folio_size(folio))
 		goto full_invalidate;
 
 	 /* If the page was dirtied by page_mkwrite(), the PTE stays writable
 	  * and we don't get another notification to tell us to expand it
 	  * again.
 	  */
-	if (afs_is_page_dirty_mmapped(priv))
+	if (afs_is_folio_dirty_mmapped(priv))
 		return;
 
 	/* We may need to shorten the dirty region */
-	f = afs_page_dirty_from(page, priv);
-	t = afs_page_dirty_to(page, priv);
+	f = afs_folio_dirty_from(folio, priv);
+	t = afs_folio_dirty_to(folio, priv);
 
 	if (t <= offset || f >= end)
 		return; /* Doesn't overlap */
@@ -437,17 +442,17 @@ static void afs_invalidate_dirty(struct page *page, unsigned int offset,
 	if (f == t)
 		goto undirty;
 
-	priv = afs_page_dirty(page, f, t);
-	set_page_private(page, priv);
-	trace_afs_page_dirty(vnode, tracepoint_string("trunc"), page);
+	priv = afs_folio_dirty(folio, f, t);
+	folio_change_private(folio, (void *)priv);
+	trace_afs_folio_dirty(vnode, tracepoint_string("trunc"), folio);
 	return;
 
 undirty:
-	trace_afs_page_dirty(vnode, tracepoint_string("undirty"), page);
-	clear_page_dirty_for_io(page);
+	trace_afs_folio_dirty(vnode, tracepoint_string("undirty"), folio);
+	folio_clear_dirty_for_io(folio);
 full_invalidate:
-	trace_afs_page_dirty(vnode, tracepoint_string("inval"), page);
-	detach_page_private(page);
+	trace_afs_folio_dirty(vnode, tracepoint_string("inval"), folio);
+	folio_detach_private(folio);
 }
 
 /*
@@ -458,14 +463,16 @@ full_invalidate:
 static void afs_invalidatepage(struct page *page, unsigned int offset,
 			       unsigned int length)
 {
-	_enter("{%lu},%u,%u", page->index, offset, length);
+	struct folio *folio = page_folio(page);
+
+	_enter("{%lu},%u,%u", folio_index(folio), offset, length);
 
 	BUG_ON(!PageLocked(page));
 
 	if (PagePrivate(page))
-		afs_invalidate_dirty(page, offset, length);
+		afs_invalidate_dirty(folio, offset, length);
 
-	wait_on_page_fscache(page);
+	folio_wait_fscache(folio);
 	_leave("");
 }
 
@@ -475,30 +482,31 @@ static void afs_invalidatepage(struct page *page, unsigned int offset,
  */
 static int afs_releasepage(struct page *page, gfp_t gfp_flags)
 {
-	struct afs_vnode *vnode = AFS_FS_I(page->mapping->host);
+	struct folio *folio = page_folio(page);
+	struct afs_vnode *vnode = AFS_FS_I(folio_inode(folio));
 
 	_enter("{{%llx:%llu}[%lu],%lx},%x",
-	       vnode->fid.vid, vnode->fid.vnode, page->index, page->flags,
+	       vnode->fid.vid, vnode->fid.vnode, folio_index(folio), folio->flags,
 	       gfp_flags);
 
 	/* deny if page is being written to the cache and the caller hasn't
 	 * elected to wait */
 #ifdef CONFIG_AFS_FSCACHE
-	if (PageFsCache(page)) {
+	if (folio_test_fscache(folio)) {
 		if (!(gfp_flags & __GFP_DIRECT_RECLAIM) || !(gfp_flags & __GFP_FS))
 			return false;
-		wait_on_page_fscache(page);
+		folio_wait_fscache(folio);
 	}
 #endif
 
-	if (PagePrivate(page)) {
-		trace_afs_page_dirty(vnode, tracepoint_string("rel"), page);
-		detach_page_private(page);
+	if (folio_test_private(folio)) {
+		trace_afs_folio_dirty(vnode, tracepoint_string("rel"), folio);
+		folio_detach_private(folio);
 	}
 
-	/* indicate that the page can be released */
+	/* Indicate that the folio can be released */
 	_leave(" = T");
-	return 1;
+	return true;
 }
 
 static void afs_add_open_mmap(struct afs_vnode *vnode)
@@ -506,8 +514,9 @@ static void afs_add_open_mmap(struct afs_vnode *vnode)
 	if (atomic_inc_return(&vnode->cb_nr_mmap) == 1) {
 		down_write(&vnode->volume->cell->fs_open_mmaps_lock);
 
-		list_add_tail(&vnode->cb_mmap_link,
-			      &vnode->volume->cell->fs_open_mmaps);
+		if (list_empty(&vnode->cb_mmap_link))
+			list_add_tail(&vnode->cb_mmap_link,
+				      &vnode->volume->cell->fs_open_mmaps);
 
 		up_write(&vnode->volume->cell->fs_open_mmaps_lock);
 	}
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index 9357c53faa69..aa4c0d6c9780 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -876,59 +876,59 @@ struct afs_vnode_cache_aux {
 } __packed;
 
 /*
- * We use page->private to hold the amount of the page that we've written to,
+ * We use folio->private to hold the amount of the folio that we've written to,
  * splitting the field into two parts.  However, we need to represent a range
- * 0...PAGE_SIZE, so we reduce the resolution if the size of the page
+ * 0...FOLIO_SIZE, so we reduce the resolution if the size of the folio
  * exceeds what we can encode.
  */
 #ifdef CONFIG_64BIT
-#define __AFS_PAGE_PRIV_MASK	0x7fffffffUL
-#define __AFS_PAGE_PRIV_SHIFT	32
-#define __AFS_PAGE_PRIV_MMAPPED	0x80000000UL
+#define __AFS_FOLIO_PRIV_MASK		0x7fffffffUL
+#define __AFS_FOLIO_PRIV_SHIFT		32
+#define __AFS_FOLIO_PRIV_MMAPPED	0x80000000UL
 #else
-#define __AFS_PAGE_PRIV_MASK	0x7fffUL
-#define __AFS_PAGE_PRIV_SHIFT	16
-#define __AFS_PAGE_PRIV_MMAPPED	0x8000UL
+#define __AFS_FOLIO_PRIV_MASK		0x7fffUL
+#define __AFS_FOLIO_PRIV_SHIFT		16
+#define __AFS_FOLIO_PRIV_MMAPPED	0x8000UL
 #endif
 
-static inline unsigned int afs_page_dirty_resolution(struct page *page)
+static inline unsigned int afs_folio_dirty_resolution(struct folio *folio)
 {
-	int shift = thp_order(page) + PAGE_SHIFT - (__AFS_PAGE_PRIV_SHIFT - 1);
+	int shift = folio_shift(folio) - (__AFS_FOLIO_PRIV_SHIFT - 1);
 	return (shift > 0) ? shift : 0;
 }
 
-static inline size_t afs_page_dirty_from(struct page *page, unsigned long priv)
+static inline size_t afs_folio_dirty_from(struct folio *folio, unsigned long priv)
 {
-	unsigned long x = priv & __AFS_PAGE_PRIV_MASK;
+	unsigned long x = priv & __AFS_FOLIO_PRIV_MASK;
 
 	/* The lower bound is inclusive */
-	return x << afs_page_dirty_resolution(page);
+	return x << afs_folio_dirty_resolution(folio);
 }
 
-static inline size_t afs_page_dirty_to(struct page *page, unsigned long priv)
+static inline size_t afs_folio_dirty_to(struct folio *folio, unsigned long priv)
 {
-	unsigned long x = (priv >> __AFS_PAGE_PRIV_SHIFT) & __AFS_PAGE_PRIV_MASK;
+	unsigned long x = (priv >> __AFS_FOLIO_PRIV_SHIFT) & __AFS_FOLIO_PRIV_MASK;
 
 	/* The upper bound is immediately beyond the region */
-	return (x + 1) << afs_page_dirty_resolution(page);
+	return (x + 1) << afs_folio_dirty_resolution(folio);
 }
 
-static inline unsigned long afs_page_dirty(struct page *page, size_t from, size_t to)
+static inline unsigned long afs_folio_dirty(struct folio *folio, size_t from, size_t to)
 {
-	unsigned int res = afs_page_dirty_resolution(page);
+	unsigned int res = afs_folio_dirty_resolution(folio);
 	from >>= res;
 	to = (to - 1) >> res;
-	return (to << __AFS_PAGE_PRIV_SHIFT) | from;
+	return (to << __AFS_FOLIO_PRIV_SHIFT) | from;
 }
 
-static inline unsigned long afs_page_dirty_mmapped(unsigned long priv)
+static inline unsigned long afs_folio_dirty_mmapped(unsigned long priv)
 {
-	return priv | __AFS_PAGE_PRIV_MMAPPED;
+	return priv | __AFS_FOLIO_PRIV_MMAPPED;
 }
 
-static inline bool afs_is_page_dirty_mmapped(unsigned long priv)
+static inline bool afs_is_folio_dirty_mmapped(unsigned long priv)
 {
-	return priv & __AFS_PAGE_PRIV_MMAPPED;
+	return priv & __AFS_FOLIO_PRIV_MMAPPED;
 }
 
 #include <trace/events/afs.h>
diff --git a/fs/afs/super.c b/fs/afs/super.c
index d110def8aa8e..34c68724c98b 100644
--- a/fs/afs/super.c
+++ b/fs/afs/super.c
@@ -667,6 +667,7 @@ static void afs_i_init_once(void *_vnode)
 	INIT_LIST_HEAD(&vnode->pending_locks);
 	INIT_LIST_HEAD(&vnode->granted_locks);
 	INIT_DELAYED_WORK(&vnode->lock_work, afs_lock_work);
+	INIT_LIST_HEAD(&vnode->cb_mmap_link);
 	seqlock_init(&vnode->cb_lock);
 }
 
diff --git a/fs/afs/write.c b/fs/afs/write.c
index 8b1d9c2f6bec..ca4909baf5e6 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -32,7 +32,7 @@ int afs_write_begin(struct file *file, struct address_space *mapping,
 		    struct page **_page, void **fsdata)
 {
 	struct afs_vnode *vnode = AFS_FS_I(file_inode(file));
-	struct page *page;
+	struct folio *folio;
 	unsigned long priv;
 	unsigned f, from;
 	unsigned t, to;
@@ -46,12 +46,12 @@ int afs_write_begin(struct file *file, struct address_space *mapping,
 	 * file.  We need to do this before we get a lock on the page in case
 	 * there's more than one writer competing for the same cache block.
 	 */
-	ret = netfs_write_begin(file, mapping, pos, len, flags, &page, fsdata,
+	ret = netfs_write_begin(file, mapping, pos, len, flags, &folio, fsdata,
 				&afs_req_ops, NULL);
 	if (ret < 0)
 		return ret;
 
-	index = page->index;
+	index = folio_index(folio);
 	from = pos - index * PAGE_SIZE;
 	to = from + len;
 
@@ -59,14 +59,14 @@ try_again:
 	/* See if this page is already partially written in a way that we can
 	 * merge the new write with.
 	 */
-	if (PagePrivate(page)) {
-		priv = page_private(page);
-		f = afs_page_dirty_from(page, priv);
-		t = afs_page_dirty_to(page, priv);
+	if (folio_test_private(folio)) {
+		priv = (unsigned long)folio_get_private(folio);
+		f = afs_folio_dirty_from(folio, priv);
+		t = afs_folio_dirty_to(folio, priv);
 		ASSERTCMP(f, <=, t);
 
-		if (PageWriteback(page)) {
-			trace_afs_page_dirty(vnode, tracepoint_string("alrdy"), page);
+		if (folio_test_writeback(folio)) {
+			trace_afs_folio_dirty(vnode, tracepoint_string("alrdy"), folio);
 			goto flush_conflicting_write;
 		}
 		/* If the file is being filled locally, allow inter-write
@@ -78,7 +78,7 @@ try_again:
 			goto flush_conflicting_write;
 	}
 
-	*_page = page;
+	*_page = &folio->page;
 	_leave(" = 0");
 	return 0;
 
@@ -87,17 +87,17 @@ try_again:
 	 */
 flush_conflicting_write:
 	_debug("flush conflict");
-	ret = write_one_page(page);
+	ret = folio_write_one(folio);
 	if (ret < 0)
 		goto error;
 
-	ret = lock_page_killable(page);
+	ret = folio_lock_killable(folio);
 	if (ret < 0)
 		goto error;
 	goto try_again;
 
 error:
-	put_page(page);
+	folio_put(folio);
 	_leave(" = %d", ret);
 	return ret;
 }
@@ -107,24 +107,25 @@ error:
  */
 int afs_write_end(struct file *file, struct address_space *mapping,
 		  loff_t pos, unsigned len, unsigned copied,
-		  struct page *page, void *fsdata)
+		  struct page *subpage, void *fsdata)
 {
+	struct folio *folio = page_folio(subpage);
 	struct afs_vnode *vnode = AFS_FS_I(file_inode(file));
 	unsigned long priv;
-	unsigned int f, from = pos & (thp_size(page) - 1);
+	unsigned int f, from = offset_in_folio(folio, pos);
 	unsigned int t, to = from + copied;
 	loff_t i_size, maybe_i_size;
 
 	_enter("{%llx:%llu},{%lx}",
-	       vnode->fid.vid, vnode->fid.vnode, page->index);
+	       vnode->fid.vid, vnode->fid.vnode, folio_index(folio));
 
-	if (!PageUptodate(page)) {
+	if (!folio_test_uptodate(folio)) {
 		if (copied < len) {
 			copied = 0;
 			goto out;
 		}
 
-		SetPageUptodate(page);
+		folio_mark_uptodate(folio);
 	}
 
 	if (copied == 0)
@@ -141,29 +142,29 @@ int afs_write_end(struct file *file, struct address_space *mapping,
 		write_sequnlock(&vnode->cb_lock);
 	}
 
-	if (PagePrivate(page)) {
-		priv = page_private(page);
-		f = afs_page_dirty_from(page, priv);
-		t = afs_page_dirty_to(page, priv);
+	if (folio_test_private(folio)) {
+		priv = (unsigned long)folio_get_private(folio);
+		f = afs_folio_dirty_from(folio, priv);
+		t = afs_folio_dirty_to(folio, priv);
 		if (from < f)
 			f = from;
 		if (to > t)
 			t = to;
-		priv = afs_page_dirty(page, f, t);
-		set_page_private(page, priv);
-		trace_afs_page_dirty(vnode, tracepoint_string("dirty+"), page);
+		priv = afs_folio_dirty(folio, f, t);
+		folio_change_private(folio, (void *)priv);
+		trace_afs_folio_dirty(vnode, tracepoint_string("dirty+"), folio);
 	} else {
-		priv = afs_page_dirty(page, from, to);
-		attach_page_private(page, (void *)priv);
-		trace_afs_page_dirty(vnode, tracepoint_string("dirty"), page);
+		priv = afs_folio_dirty(folio, from, to);
+		folio_attach_private(folio, (void *)priv);
+		trace_afs_folio_dirty(vnode, tracepoint_string("dirty"), folio);
 	}
 
-	if (set_page_dirty(page))
-		_debug("dirtied %lx", page->index);
+	if (folio_mark_dirty(folio))
+		_debug("dirtied %lx", folio_index(folio));
 
 out:
-	unlock_page(page);
-	put_page(page);
+	folio_unlock(folio);
+	folio_put(folio);
 	return copied;
 }
 
@@ -174,40 +175,32 @@ static void afs_kill_pages(struct address_space *mapping,
 			   loff_t start, loff_t len)
 {
 	struct afs_vnode *vnode = AFS_FS_I(mapping->host);
-	struct pagevec pv;
-	unsigned int loop, psize;
+	struct folio *folio;
+	pgoff_t index = start / PAGE_SIZE;
+	pgoff_t last = (start + len - 1) / PAGE_SIZE, next;
 
 	_enter("{%llx:%llu},%llx @%llx",
 	       vnode->fid.vid, vnode->fid.vnode, len, start);
 
-	pagevec_init(&pv);
-
 	do {
-		_debug("kill %llx @%llx", len, start);
-
-		pv.nr = find_get_pages_contig(mapping, start / PAGE_SIZE,
-					      PAGEVEC_SIZE, pv.pages);
-		if (pv.nr == 0)
-			break;
+		_debug("kill %lx (to %lx)", index, last);
 
-		for (loop = 0; loop < pv.nr; loop++) {
-			struct page *page = pv.pages[loop];
+		folio = filemap_get_folio(mapping, index);
+		if (!folio) {
+			next = index + 1;
+			continue;
+		}
 
-			if (page->index * PAGE_SIZE >= start + len)
-				break;
+		next = folio_next_index(folio);
 
-			psize = thp_size(page);
-			start += psize;
-			len -= psize;
-			ClearPageUptodate(page);
-			end_page_writeback(page);
-			lock_page(page);
-			generic_error_remove_page(mapping, page);
-			unlock_page(page);
-		}
+		folio_clear_uptodate(folio);
+		folio_end_writeback(folio);
+		folio_lock(folio);
+		generic_error_remove_page(mapping, &folio->page);
+		folio_unlock(folio);
+		folio_put(folio);
 
-		__pagevec_release(&pv);
-	} while (len > 0);
+	} while (index = next, index <= last);
 
 	_leave("");
 }
@@ -220,37 +213,27 @@ static void afs_redirty_pages(struct writeback_control *wbc,
 			      loff_t start, loff_t len)
 {
 	struct afs_vnode *vnode = AFS_FS_I(mapping->host);
-	struct pagevec pv;
-	unsigned int loop, psize;
+	struct folio *folio;
+	pgoff_t index = start / PAGE_SIZE;
+	pgoff_t last = (start + len - 1) / PAGE_SIZE, next;
 
 	_enter("{%llx:%llu},%llx @%llx",
 	       vnode->fid.vid, vnode->fid.vnode, len, start);
 
-	pagevec_init(&pv);
-
 	do {
 		_debug("redirty %llx @%llx", len, start);
 
-		pv.nr = find_get_pages_contig(mapping, start / PAGE_SIZE,
-					      PAGEVEC_SIZE, pv.pages);
-		if (pv.nr == 0)
-			break;
-
-		for (loop = 0; loop < pv.nr; loop++) {
-			struct page *page = pv.pages[loop];
-
-			if (page->index * PAGE_SIZE >= start + len)
-				break;
-
-			psize = thp_size(page);
-			start += psize;
-			len -= psize;
-			redirty_page_for_writepage(wbc, page);
-			end_page_writeback(page);
+		folio = filemap_get_folio(mapping, index);
+		if (!folio) {
+			next = index + 1;
+			continue;
 		}
 
-		__pagevec_release(&pv);
-	} while (len > 0);
+		next = index + folio_nr_pages(folio);
+		folio_redirty_for_writepage(wbc, folio);
+		folio_end_writeback(folio);
+		folio_put(folio);
+	} while (index = next, index <= last);
 
 	_leave("");
 }
@@ -261,7 +244,7 @@ static void afs_redirty_pages(struct writeback_control *wbc,
 static void afs_pages_written_back(struct afs_vnode *vnode, loff_t start, unsigned int len)
 {
 	struct address_space *mapping = vnode->vfs_inode.i_mapping;
-	struct page *page;
+	struct folio *folio;
 	pgoff_t end;
 
 	XA_STATE(xas, &mapping->i_pages, start / PAGE_SIZE);
@@ -272,15 +255,16 @@ static void afs_pages_written_back(struct afs_vnode *vnode, loff_t start, unsign
 	rcu_read_lock();
 
 	end = (start + len - 1) / PAGE_SIZE;
-	xas_for_each(&xas, page, end) {
-		if (!PageWriteback(page)) {
-			kdebug("bad %x @%llx page %lx %lx", len, start, page->index, end);
-			ASSERT(PageWriteback(page));
+	xas_for_each(&xas, folio, end) {
+		if (!folio_test_writeback(folio)) {
+			kdebug("bad %x @%llx page %lx %lx",
+			       len, start, folio_index(folio), end);
+			ASSERT(folio_test_writeback(folio));
 		}
 
-		trace_afs_page_dirty(vnode, tracepoint_string("clear"), page);
-		detach_page_private(page);
-		page_endio(page, true, 0);
+		trace_afs_folio_dirty(vnode, tracepoint_string("clear"), folio);
+		folio_detach_private(folio);
+		folio_end_writeback(folio);
 	}
 
 	rcu_read_unlock();
@@ -437,7 +421,7 @@ static void afs_extend_writeback(struct address_space *mapping,
 				 unsigned int *_len)
 {
 	struct pagevec pvec;
-	struct page *page;
+	struct folio *folio;
 	unsigned long priv;
 	unsigned int psize, filler = 0;
 	unsigned int f, t;
@@ -456,43 +440,43 @@ static void afs_extend_writeback(struct address_space *mapping,
 		 */
 		rcu_read_lock();
 
-		xas_for_each(&xas, page, ULONG_MAX) {
+		xas_for_each(&xas, folio, ULONG_MAX) {
 			stop = true;
-			if (xas_retry(&xas, page))
+			if (xas_retry(&xas, folio))
 				continue;
-			if (xa_is_value(page))
+			if (xa_is_value(folio))
 				break;
-			if (page->index != index)
+			if (folio_index(folio) != index)
 				break;
 
-			if (!page_cache_get_speculative(page)) {
+			if (!folio_try_get_rcu(folio)) {
 				xas_reset(&xas);
 				continue;
 			}
 
 			/* Has the page moved or been split? */
-			if (unlikely(page != xas_reload(&xas))) {
-				put_page(page);
+			if (unlikely(folio != xas_reload(&xas))) {
+				folio_put(folio);
 				break;
 			}
 
-			if (!trylock_page(page)) {
-				put_page(page);
+			if (!folio_trylock(folio)) {
+				folio_put(folio);
 				break;
 			}
-			if (!PageDirty(page) || PageWriteback(page)) {
-				unlock_page(page);
-				put_page(page);
+			if (!folio_test_dirty(folio) || folio_test_writeback(folio)) {
+				folio_unlock(folio);
+				folio_put(folio);
 				break;
 			}
 
-			psize = thp_size(page);
-			priv = page_private(page);
-			f = afs_page_dirty_from(page, priv);
-			t = afs_page_dirty_to(page, priv);
+			psize = folio_size(folio);
+			priv = (unsigned long)folio_get_private(folio);
+			f = afs_folio_dirty_from(folio, priv);
+			t = afs_folio_dirty_to(folio, priv);
 			if (f != 0 && !new_content) {
-				unlock_page(page);
-				put_page(page);
+				folio_unlock(folio);
+				folio_put(folio);
 				break;
 			}
 
@@ -503,8 +487,8 @@ static void afs_extend_writeback(struct address_space *mapping,
 			else if (t == psize || new_content)
 				stop = false;
 
-			index += thp_nr_pages(page);
-			if (!pagevec_add(&pvec, page))
+			index += folio_nr_pages(folio);
+			if (!pagevec_add(&pvec, &folio->page))
 				break;
 			if (stop)
 				break;
@@ -521,16 +505,16 @@ static void afs_extend_writeback(struct address_space *mapping,
 			break;
 
 		for (i = 0; i < pagevec_count(&pvec); i++) {
-			page = pvec.pages[i];
-			trace_afs_page_dirty(vnode, tracepoint_string("store+"), page);
+			folio = page_folio(pvec.pages[i]);
+			trace_afs_folio_dirty(vnode, tracepoint_string("store+"), folio);
 
-			if (!clear_page_dirty_for_io(page))
+			if (!folio_clear_dirty_for_io(folio))
 				BUG();
-			if (test_set_page_writeback(page))
+			if (folio_start_writeback(folio))
 				BUG();
 
-			*_count -= thp_nr_pages(page);
-			unlock_page(page);
+			*_count -= folio_nr_pages(folio);
+			folio_unlock(folio);
 		}
 
 		pagevec_release(&pvec);
@@ -544,10 +528,10 @@ static void afs_extend_writeback(struct address_space *mapping,
  * Synchronously write back the locked page and any subsequent non-locked dirty
  * pages.
  */
-static ssize_t afs_write_back_from_locked_page(struct address_space *mapping,
-					       struct writeback_control *wbc,
-					       struct page *page,
-					       loff_t start, loff_t end)
+static ssize_t afs_write_back_from_locked_folio(struct address_space *mapping,
+						struct writeback_control *wbc,
+						struct folio *folio,
+						loff_t start, loff_t end)
 {
 	struct afs_vnode *vnode = AFS_FS_I(mapping->host);
 	struct iov_iter iter;
@@ -558,22 +542,22 @@ static ssize_t afs_write_back_from_locked_page(struct address_space *mapping,
 	long count = wbc->nr_to_write;
 	int ret;
 
-	_enter(",%lx,%llx-%llx", page->index, start, end);
+	_enter(",%lx,%llx-%llx", folio_index(folio), start, end);
 
-	if (test_set_page_writeback(page))
+	if (folio_start_writeback(folio))
 		BUG();
 
-	count -= thp_nr_pages(page);
+	count -= folio_nr_pages(folio);
 
 	/* Find all consecutive lockable dirty pages that have contiguous
 	 * written regions, stopping when we find a page that is not
 	 * immediately lockable, is not dirty or is missing, or we reach the
 	 * end of the range.
 	 */
-	priv = page_private(page);
-	offset = afs_page_dirty_from(page, priv);
-	to = afs_page_dirty_to(page, priv);
-	trace_afs_page_dirty(vnode, tracepoint_string("store"), page);
+	priv = (unsigned long)folio_get_private(folio);
+	offset = afs_folio_dirty_from(folio, priv);
+	to = afs_folio_dirty_to(folio, priv);
+	trace_afs_folio_dirty(vnode, tracepoint_string("store"), folio);
 
 	len = to - offset;
 	start += offset;
@@ -586,7 +570,7 @@ static ssize_t afs_write_back_from_locked_page(struct address_space *mapping,
 		max_len = min_t(unsigned long long, max_len, i_size - start);
 
 		if (len < max_len &&
-		    (to == thp_size(page) || new_content))
+		    (to == folio_size(folio) || new_content))
 			afs_extend_writeback(mapping, vnode, &count,
 					     start, max_len, new_content, &len);
 		len = min_t(loff_t, len, max_len);
@@ -596,7 +580,7 @@ static ssize_t afs_write_back_from_locked_page(struct address_space *mapping,
 	 * set; the first page is still locked at this point, but all the rest
 	 * have been unlocked.
 	 */
-	unlock_page(page);
+	folio_unlock(folio);
 
 	if (start < i_size) {
 		_debug("write back %x @%llx [%llx]", len, start, i_size);
@@ -657,16 +641,17 @@ static ssize_t afs_write_back_from_locked_page(struct address_space *mapping,
  * write a page back to the server
  * - the caller locked the page for us
  */
-int afs_writepage(struct page *page, struct writeback_control *wbc)
+int afs_writepage(struct page *subpage, struct writeback_control *wbc)
 {
+	struct folio *folio = page_folio(subpage);
 	ssize_t ret;
 	loff_t start;
 
-	_enter("{%lx},", page->index);
+	_enter("{%lx},", folio_index(folio));
 
-	start = page->index * PAGE_SIZE;
-	ret = afs_write_back_from_locked_page(page->mapping, wbc, page,
-					      start, LLONG_MAX - start);
+	start = folio_index(folio) * PAGE_SIZE;
+	ret = afs_write_back_from_locked_folio(folio_mapping(folio), wbc,
+					       folio, start, LLONG_MAX - start);
 	if (ret < 0) {
 		_leave(" = %zd", ret);
 		return ret;
@@ -683,7 +668,8 @@ static int afs_writepages_region(struct address_space *mapping,
 				 struct writeback_control *wbc,
 				 loff_t start, loff_t end, loff_t *_next)
 {
-	struct page *page;
+	struct folio *folio;
+	struct page *head_page;
 	ssize_t ret;
 	int n;
 
@@ -693,13 +679,14 @@ static int afs_writepages_region(struct address_space *mapping,
 		pgoff_t index = start / PAGE_SIZE;
 
 		n = find_get_pages_range_tag(mapping, &index, end / PAGE_SIZE,
-					     PAGECACHE_TAG_DIRTY, 1, &page);
+					     PAGECACHE_TAG_DIRTY, 1, &head_page);
 		if (!n)
 			break;
 
-		start = (loff_t)page->index * PAGE_SIZE; /* May regress with THPs */
+		folio = page_folio(head_page);
+		start = folio_pos(folio); /* May regress with THPs */
 
-		_debug("wback %lx", page->index);
+		_debug("wback %lx", folio_index(folio));
 
 		/* At this point we hold neither the i_pages lock nor the
 		 * page lock: the page may be truncated or invalidated
@@ -707,37 +694,38 @@ static int afs_writepages_region(struct address_space *mapping,
 		 * back from swapper_space to tmpfs file mapping
 		 */
 		if (wbc->sync_mode != WB_SYNC_NONE) {
-			ret = lock_page_killable(page);
+			ret = folio_lock_killable(folio);
 			if (ret < 0) {
-				put_page(page);
+				folio_put(folio);
 				return ret;
 			}
 		} else {
-			if (!trylock_page(page)) {
-				put_page(page);
+			if (!folio_trylock(folio)) {
+				folio_put(folio);
 				return 0;
 			}
 		}
 
-		if (page->mapping != mapping || !PageDirty(page)) {
-			start += thp_size(page);
-			unlock_page(page);
-			put_page(page);
+		if (folio_mapping(folio) != mapping ||
+		    !folio_test_dirty(folio)) {
+			start += folio_size(folio);
+			folio_unlock(folio);
+			folio_put(folio);
 			continue;
 		}
 
-		if (PageWriteback(page)) {
-			unlock_page(page);
+		if (folio_test_writeback(folio)) {
+			folio_unlock(folio);
 			if (wbc->sync_mode != WB_SYNC_NONE)
-				wait_on_page_writeback(page);
-			put_page(page);
+				folio_wait_writeback(folio);
+			folio_put(folio);
 			continue;
 		}
 
-		if (!clear_page_dirty_for_io(page))
+		if (!folio_clear_dirty_for_io(folio))
 			BUG();
-		ret = afs_write_back_from_locked_page(mapping, wbc, page, start, end);
-		put_page(page);
+		ret = afs_write_back_from_locked_folio(mapping, wbc, folio, start, end);
+		folio_put(folio);
 		if (ret < 0) {
 			_leave(" = %zd", ret);
 			return ret;
@@ -862,7 +850,6 @@ int afs_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 vm_fault_t afs_page_mkwrite(struct vm_fault *vmf)
 {
 	struct folio *folio = page_folio(vmf->page);
-	struct page *page = &folio->page;
 	struct file *file = vmf->vma->vm_file;
 	struct inode *inode = file_inode(file);
 	struct afs_vnode *vnode = AFS_FS_I(inode);
@@ -870,7 +857,7 @@ vm_fault_t afs_page_mkwrite(struct vm_fault *vmf)
 	unsigned long priv;
 	vm_fault_t ret = VM_FAULT_RETRY;
 
-	_enter("{{%llx:%llu}},{%lx}", vnode->fid.vid, vnode->fid.vnode, page->index);
+	_enter("{{%llx:%llu}},{%lx}", vnode->fid.vid, vnode->fid.vnode, folio_index(folio));
 
 	afs_validate(vnode, af->key);
 
@@ -880,18 +867,18 @@ vm_fault_t afs_page_mkwrite(struct vm_fault *vmf)
 	 * be modified.  We then assume the entire page will need writing back.
 	 */
 #ifdef CONFIG_AFS_FSCACHE
-	if (PageFsCache(page) &&
-	    wait_on_page_fscache_killable(page) < 0)
+	if (folio_test_fscache(folio) &&
+	    folio_wait_fscache_killable(folio) < 0)
 		goto out;
 #endif
 
 	if (folio_wait_writeback_killable(folio))
 		goto out;
 
-	if (lock_page_killable(page) < 0)
+	if (folio_lock_killable(folio) < 0)
 		goto out;
 
-	/* We mustn't change page->private until writeback is complete as that
+	/* We mustn't change folio->private until writeback is complete as that
 	 * details the portion of the page we need to write back and we might
 	 * need to redirty the page if there's a problem.
 	 */
@@ -900,14 +887,14 @@ vm_fault_t afs_page_mkwrite(struct vm_fault *vmf)
 		goto out;
 	}
 
-	priv = afs_page_dirty(page, 0, thp_size(page));
-	priv = afs_page_dirty_mmapped(priv);
-	if (PagePrivate(page)) {
-		set_page_private(page, priv);
-		trace_afs_page_dirty(vnode, tracepoint_string("mkwrite+"), page);
+	priv = afs_folio_dirty(folio, 0, folio_size(folio));
+	priv = afs_folio_dirty_mmapped(priv);
+	if (folio_test_private(folio)) {
+		folio_change_private(folio, (void *)priv);
+		trace_afs_folio_dirty(vnode, tracepoint_string("mkwrite+"), folio);
 	} else {
-		attach_page_private(page, (void *)priv);
-		trace_afs_page_dirty(vnode, tracepoint_string("mkwrite"), page);
+		folio_attach_private(folio, (void *)priv);
+		trace_afs_folio_dirty(vnode, tracepoint_string("mkwrite"), folio);
 	}
 	file_update_time(file);
 
@@ -948,38 +935,38 @@ void afs_prune_wb_keys(struct afs_vnode *vnode)
 /*
  * Clean up a page during invalidation.
  */
-int afs_launder_page(struct page *page)
+int afs_launder_page(struct page *subpage)
 {
-	struct address_space *mapping = page->mapping;
-	struct afs_vnode *vnode = AFS_FS_I(mapping->host);
+	struct folio *folio = page_folio(subpage);
+	struct afs_vnode *vnode = AFS_FS_I(folio_inode(folio));
 	struct iov_iter iter;
 	struct bio_vec bv[1];
 	unsigned long priv;
 	unsigned int f, t;
 	int ret = 0;
 
-	_enter("{%lx}", page->index);
+	_enter("{%lx}", folio_index(folio));
 
-	priv = page_private(page);
-	if (clear_page_dirty_for_io(page)) {
+	priv = (unsigned long)folio_get_private(folio);
+	if (folio_clear_dirty_for_io(folio)) {
 		f = 0;
-		t = thp_size(page);
-		if (PagePrivate(page)) {
-			f = afs_page_dirty_from(page, priv);
-			t = afs_page_dirty_to(page, priv);
+		t = folio_size(folio);
+		if (folio_test_private(folio)) {
+			f = afs_folio_dirty_from(folio, priv);
+			t = afs_folio_dirty_to(folio, priv);
 		}
 
-		bv[0].bv_page = page;
+		bv[0].bv_page = &folio->page;
 		bv[0].bv_offset = f;
 		bv[0].bv_len = t - f;
 		iov_iter_bvec(&iter, WRITE, bv, 1, bv[0].bv_len);
 
-		trace_afs_page_dirty(vnode, tracepoint_string("launder"), page);
-		ret = afs_store_data(vnode, &iter, page_offset(page) + f, true);
+		trace_afs_folio_dirty(vnode, tracepoint_string("launder"), folio);
+		ret = afs_store_data(vnode, &iter, folio_pos(folio) + f, true);
 	}
 
-	trace_afs_page_dirty(vnode, tracepoint_string("laundered"), page);
-	detach_page_private(page);
-	wait_on_page_fscache(page);
+	trace_afs_folio_dirty(vnode, tracepoint_string("laundered"), folio);
+	folio_detach_private(folio);
+	folio_wait_fscache(folio);
 	return ret;
 }
diff --git a/fs/aio.c b/fs/aio.c
index 9c81cf611d65..f6f1cbffef9e 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -181,8 +181,9 @@ struct poll_iocb {
 	struct file		*file;
 	struct wait_queue_head	*head;
 	__poll_t		events;
-	bool			done;
 	bool			cancelled;
+	bool			work_scheduled;
+	bool			work_need_resched;
 	struct wait_queue_entry	wait;
 	struct work_struct	work;
 };
@@ -1619,6 +1620,51 @@ static void aio_poll_put_work(struct work_struct *work)
 	iocb_put(iocb);
 }
 
+/*
+ * Safely lock the waitqueue which the request is on, synchronizing with the
+ * case where the ->poll() provider decides to free its waitqueue early.
+ *
+ * Returns true on success, meaning that req->head->lock was locked, req->wait
+ * is on req->head, and an RCU read lock was taken.  Returns false if the
+ * request was already removed from its waitqueue (which might no longer exist).
+ */
+static bool poll_iocb_lock_wq(struct poll_iocb *req)
+{
+	wait_queue_head_t *head;
+
+	/*
+	 * While we hold the waitqueue lock and the waitqueue is nonempty,
+	 * wake_up_pollfree() will wait for us.  However, taking the waitqueue
+	 * lock in the first place can race with the waitqueue being freed.
+	 *
+	 * We solve this as eventpoll does: by taking advantage of the fact that
+	 * all users of wake_up_pollfree() will RCU-delay the actual free.  If
+	 * we enter rcu_read_lock() and see that the pointer to the queue is
+	 * non-NULL, we can then lock it without the memory being freed out from
+	 * under us, then check whether the request is still on the queue.
+	 *
+	 * Keep holding rcu_read_lock() as long as we hold the queue lock, in
+	 * case the caller deletes the entry from the queue, leaving it empty.
+	 * In that case, only RCU prevents the queue memory from being freed.
+	 */
+	rcu_read_lock();
+	head = smp_load_acquire(&req->head);
+	if (head) {
+		spin_lock(&head->lock);
+		if (!list_empty(&req->wait.entry))
+			return true;
+		spin_unlock(&head->lock);
+	}
+	rcu_read_unlock();
+	return false;
+}
+
+static void poll_iocb_unlock_wq(struct poll_iocb *req)
+{
+	spin_unlock(&req->head->lock);
+	rcu_read_unlock();
+}
+
 static void aio_poll_complete_work(struct work_struct *work)
 {
 	struct poll_iocb *req = container_of(work, struct poll_iocb, work);
@@ -1638,14 +1684,27 @@ static void aio_poll_complete_work(struct work_struct *work)
 	 * avoid further branches in the fast path.
 	 */
 	spin_lock_irq(&ctx->ctx_lock);
-	if (!mask && !READ_ONCE(req->cancelled)) {
-		add_wait_queue(req->head, &req->wait);
-		spin_unlock_irq(&ctx->ctx_lock);
-		return;
-	}
+	if (poll_iocb_lock_wq(req)) {
+		if (!mask && !READ_ONCE(req->cancelled)) {
+			/*
+			 * The request isn't actually ready to be completed yet.
+			 * Reschedule completion if another wakeup came in.
+			 */
+			if (req->work_need_resched) {
+				schedule_work(&req->work);
+				req->work_need_resched = false;
+			} else {
+				req->work_scheduled = false;
+			}
+			poll_iocb_unlock_wq(req);
+			spin_unlock_irq(&ctx->ctx_lock);
+			return;
+		}
+		list_del_init(&req->wait.entry);
+		poll_iocb_unlock_wq(req);
+	} /* else, POLLFREE has freed the waitqueue, so we must complete */
 	list_del_init(&iocb->ki_list);
 	iocb->ki_res.res = mangle_poll(mask);
-	req->done = true;
 	spin_unlock_irq(&ctx->ctx_lock);
 
 	iocb_put(iocb);
@@ -1657,13 +1716,14 @@ static int aio_poll_cancel(struct kiocb *iocb)
 	struct aio_kiocb *aiocb = container_of(iocb, struct aio_kiocb, rw);
 	struct poll_iocb *req = &aiocb->poll;
 
-	spin_lock(&req->head->lock);
-	WRITE_ONCE(req->cancelled, true);
-	if (!list_empty(&req->wait.entry)) {
-		list_del_init(&req->wait.entry);
-		schedule_work(&aiocb->poll.work);
-	}
-	spin_unlock(&req->head->lock);
+	if (poll_iocb_lock_wq(req)) {
+		WRITE_ONCE(req->cancelled, true);
+		if (!req->work_scheduled) {
+			schedule_work(&aiocb->poll.work);
+			req->work_scheduled = true;
+		}
+		poll_iocb_unlock_wq(req);
+	} /* else, the request was force-cancelled by POLLFREE already */
 
 	return 0;
 }
@@ -1680,21 +1740,27 @@ static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
 	if (mask && !(mask & req->events))
 		return 0;
 
-	list_del_init(&req->wait.entry);
-
-	if (mask && spin_trylock_irqsave(&iocb->ki_ctx->ctx_lock, flags)) {
+	/*
+	 * Complete the request inline if possible.  This requires that three
+	 * conditions be met:
+	 *   1. An event mask must have been passed.  If a plain wakeup was done
+	 *	instead, then mask == 0 and we have to call vfs_poll() to get
+	 *	the events, so inline completion isn't possible.
+	 *   2. The completion work must not have already been scheduled.
+	 *   3. ctx_lock must not be busy.  We have to use trylock because we
+	 *	already hold the waitqueue lock, so this inverts the normal
+	 *	locking order.  Use irqsave/irqrestore because not all
+	 *	filesystems (e.g. fuse) call this function with IRQs disabled,
+	 *	yet IRQs have to be disabled before ctx_lock is obtained.
+	 */
+	if (mask && !req->work_scheduled &&
+	    spin_trylock_irqsave(&iocb->ki_ctx->ctx_lock, flags)) {
 		struct kioctx *ctx = iocb->ki_ctx;
 
-		/*
-		 * Try to complete the iocb inline if we can. Use
-		 * irqsave/irqrestore because not all filesystems (e.g. fuse)
-		 * call this function with IRQs disabled and because IRQs
-		 * have to be disabled before ctx_lock is obtained.
-		 */
+		list_del_init(&req->wait.entry);
 		list_del(&iocb->ki_list);
 		iocb->ki_res.res = mangle_poll(mask);
-		req->done = true;
-		if (iocb->ki_eventfd && eventfd_signal_allowed()) {
+		if (iocb->ki_eventfd && !eventfd_signal_allowed()) {
 			iocb = NULL;
 			INIT_WORK(&req->work, aio_poll_put_work);
 			schedule_work(&req->work);
@@ -1703,7 +1769,43 @@ static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
 		if (iocb)
 			iocb_put(iocb);
 	} else {
-		schedule_work(&req->work);
+		/*
+		 * Schedule the completion work if needed.  If it was already
+		 * scheduled, record that another wakeup came in.
+		 *
+		 * Don't remove the request from the waitqueue here, as it might
+		 * not actually be complete yet (we won't know until vfs_poll()
+		 * is called), and we must not miss any wakeups.  POLLFREE is an
+		 * exception to this; see below.
+		 */
+		if (req->work_scheduled) {
+			req->work_need_resched = true;
+		} else {
+			schedule_work(&req->work);
+			req->work_scheduled = true;
+		}
+
+		/*
+		 * If the waitqueue is being freed early but we can't complete
+		 * the request inline, we have to tear down the request as best
+		 * we can.  That means immediately removing the request from its
+		 * waitqueue and preventing all further accesses to the
+		 * waitqueue via the request.  We also need to schedule the
+		 * completion work (done above).  Also mark the request as
+		 * cancelled, to potentially skip an unneeded call to ->poll().
+		 */
+		if (mask & POLLFREE) {
+			WRITE_ONCE(req->cancelled, true);
+			list_del_init(&req->wait.entry);
+
+			/*
+			 * Careful: this *must* be the last step, since as soon
+			 * as req->head is NULL'ed out, the request can be
+			 * completed and freed, since aio_poll_complete_work()
+			 * will no longer need to take the waitqueue lock.
+			 */
+			smp_store_release(&req->head, NULL);
+		}
 	}
 	return 1;
 }
@@ -1711,6 +1813,7 @@ static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
 struct aio_poll_table {
 	struct poll_table_struct	pt;
 	struct aio_kiocb		*iocb;
+	bool				queued;
 	int				error;
 };
 
@@ -1721,11 +1824,12 @@ aio_poll_queue_proc(struct file *file, struct wait_queue_head *head,
 	struct aio_poll_table *pt = container_of(p, struct aio_poll_table, pt);
 
 	/* multiple wait queues per file are not supported */
-	if (unlikely(pt->iocb->poll.head)) {
+	if (unlikely(pt->queued)) {
 		pt->error = -EINVAL;
 		return;
 	}
 
+	pt->queued = true;
 	pt->error = 0;
 	pt->iocb->poll.head = head;
 	add_wait_queue(head, &pt->iocb->poll.wait);
@@ -1750,12 +1854,14 @@ static int aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb)
 	req->events = demangle_poll(iocb->aio_buf) | EPOLLERR | EPOLLHUP;
 
 	req->head = NULL;
-	req->done = false;
 	req->cancelled = false;
+	req->work_scheduled = false;
+	req->work_need_resched = false;
 
 	apt.pt._qproc = aio_poll_queue_proc;
 	apt.pt._key = req->events;
 	apt.iocb = aiocb;
+	apt.queued = false;
 	apt.error = -EINVAL; /* same as no support for IOCB_CMD_POLL */
 
 	/* initialized the list so that we can do list_empty checks */
@@ -1764,23 +1870,35 @@ static int aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb)
 
 	mask = vfs_poll(req->file, &apt.pt) & req->events;
 	spin_lock_irq(&ctx->ctx_lock);
-	if (likely(req->head)) {
-		spin_lock(&req->head->lock);
-		if (unlikely(list_empty(&req->wait.entry))) {
-			if (apt.error)
+	if (likely(apt.queued)) {
+		bool on_queue = poll_iocb_lock_wq(req);
+
+		if (!on_queue || req->work_scheduled) {
+			/*
+			 * aio_poll_wake() already either scheduled the async
+			 * completion work, or completed the request inline.
+			 */
+			if (apt.error) /* unsupported case: multiple queues */
 				cancel = true;
 			apt.error = 0;
 			mask = 0;
 		}
 		if (mask || apt.error) {
+			/* Steal to complete synchronously. */
 			list_del_init(&req->wait.entry);
 		} else if (cancel) {
+			/* Cancel if possible (may be too late though). */
 			WRITE_ONCE(req->cancelled, true);
-		} else if (!req->done) { /* actually waiting for an event */
+		} else if (on_queue) {
+			/*
+			 * Actually waiting for an event, so add the request to
+			 * active_reqs so that it can be cancelled if needed.
+			 */
 			list_add_tail(&aiocb->ki_list, &ctx->active_reqs);
 			aiocb->ki_cancel = aio_poll_cancel;
 		}
-		spin_unlock(&req->head->lock);
+		if (on_queue)
+			poll_iocb_unlock_wq(req);
 	}
 	if (mask) { /* no async, we'd stolen it */
 		aiocb->ki_res.res = mangle_poll(mask);
diff --git a/fs/attr.c b/fs/attr.c
index 473d21b3a86d..66899b6e9bd8 100644
--- a/fs/attr.c
+++ b/fs/attr.c
@@ -35,7 +35,7 @@ static bool chown_ok(struct user_namespace *mnt_userns,
 		     kuid_t uid)
 {
 	kuid_t kuid = i_uid_into_mnt(mnt_userns, inode);
-	if (uid_eq(current_fsuid(), kuid) && uid_eq(uid, kuid))
+	if (uid_eq(current_fsuid(), kuid) && uid_eq(uid, inode->i_uid))
 		return true;
 	if (capable_wrt_inode_uidgid(mnt_userns, inode, CAP_CHOWN))
 		return true;
@@ -62,7 +62,7 @@ static bool chgrp_ok(struct user_namespace *mnt_userns,
 {
 	kgid_t kgid = i_gid_into_mnt(mnt_userns, inode);
 	if (uid_eq(current_fsuid(), i_uid_into_mnt(mnt_userns, inode)) &&
-	    (in_group_p(gid) || gid_eq(gid, kgid)))
+	    (in_group_p(gid) || gid_eq(gid, inode->i_gid)))
 		return true;
 	if (capable_wrt_inode_uidgid(mnt_userns, inode, CAP_CHOWN))
 		return true;
diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c
index 309516e6a968..43c89952b7d2 100644
--- a/fs/btrfs/async-thread.c
+++ b/fs/btrfs/async-thread.c
@@ -234,6 +234,13 @@ static void run_ordered_work(struct __btrfs_workqueue *wq,
 				  ordered_list);
 		if (!test_bit(WORK_DONE_BIT, &work->flags))
 			break;
+		/*
+		 * Orders all subsequent loads after reading WORK_DONE_BIT,
+		 * paired with the smp_mb__before_atomic in btrfs_work_helper
+		 * this guarantees that the ordered function will see all
+		 * updates from ordinary work function.
+		 */
+		smp_rmb();
 
 		/*
 		 * we are going to call the ordered done function, but
@@ -317,6 +324,13 @@ static void btrfs_work_helper(struct work_struct *normal_work)
 	thresh_exec_hook(wq);
 	work->func(work);
 	if (need_order) {
+		/*
+		 * Ensures all memory accesses done in the work function are
+		 * ordered before setting the WORK_DONE_BIT. Ensuring the thread
+		 * which is going to executed the ordered work sees them.
+		 * Pairs with the smp_rmb in run_ordered_work.
+		 */
+		smp_mb__before_atomic();
 		set_bit(WORK_DONE_BIT, &work->flags);
 		run_ordered_work(wq, work);
 	} else {
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index c3983bdaf4b8..f704339c6b86 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -463,8 +463,8 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans,
 		BUG_ON(ret < 0);
 		rcu_assign_pointer(root->node, cow);
 
-		btrfs_free_tree_block(trans, root, buf, parent_start,
-				      last_ref);
+		btrfs_free_tree_block(trans, btrfs_root_id(root), buf,
+				      parent_start, last_ref);
 		free_extent_buffer(buf);
 		add_root_to_dirty_list(root);
 	} else {
@@ -485,8 +485,8 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans,
 				return ret;
 			}
 		}
-		btrfs_free_tree_block(trans, root, buf, parent_start,
-				      last_ref);
+		btrfs_free_tree_block(trans, btrfs_root_id(root), buf,
+				      parent_start, last_ref);
 	}
 	if (unlock_orig)
 		btrfs_tree_unlock(buf);
@@ -927,7 +927,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
 		free_extent_buffer(mid);
 
 		root_sub_used(root, mid->len);
-		btrfs_free_tree_block(trans, root, mid, 0, 1);
+		btrfs_free_tree_block(trans, btrfs_root_id(root), mid, 0, 1);
 		/* once for the root ptr */
 		free_extent_buffer_stale(mid);
 		return 0;
@@ -986,7 +986,8 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
 			btrfs_tree_unlock(right);
 			del_ptr(root, path, level + 1, pslot + 1);
 			root_sub_used(root, right->len);
-			btrfs_free_tree_block(trans, root, right, 0, 1);
+			btrfs_free_tree_block(trans, btrfs_root_id(root), right,
+					      0, 1);
 			free_extent_buffer_stale(right);
 			right = NULL;
 		} else {
@@ -1031,7 +1032,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
 		btrfs_tree_unlock(mid);
 		del_ptr(root, path, level + 1, pslot);
 		root_sub_used(root, mid->len);
-		btrfs_free_tree_block(trans, root, mid, 0, 1);
+		btrfs_free_tree_block(trans, btrfs_root_id(root), mid, 0, 1);
 		free_extent_buffer_stale(mid);
 		mid = NULL;
 	} else {
@@ -4032,7 +4033,7 @@ static noinline void btrfs_del_leaf(struct btrfs_trans_handle *trans,
 	root_sub_used(root, leaf->len);
 
 	atomic_inc(&leaf->refs);
-	btrfs_free_tree_block(trans, root, leaf, 0, 1);
+	btrfs_free_tree_block(trans, btrfs_root_id(root), leaf, 0, 1);
 	free_extent_buffer_stale(leaf);
 }
 /*
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 7553e9dc5f93..5fe5eccb3c87 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -2257,6 +2257,11 @@ static inline bool btrfs_root_dead(const struct btrfs_root *root)
 	return (root->root_item.flags & cpu_to_le64(BTRFS_ROOT_SUBVOL_DEAD)) != 0;
 }
 
+static inline u64 btrfs_root_id(const struct btrfs_root *root)
+{
+	return root->root_key.objectid;
+}
+
 /* struct btrfs_root_backup */
 BTRFS_SETGET_STACK_FUNCS(backup_tree_root, struct btrfs_root_backup,
 		   tree_root, 64);
@@ -2719,7 +2724,7 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans,
 					     u64 empty_size,
 					     enum btrfs_lock_nesting nest);
 void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
-			   struct btrfs_root *root,
+			   u64 root_id,
 			   struct extent_buffer *buf,
 			   u64 parent, int last_ref);
 int btrfs_alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/delalloc-space.c b/fs/btrfs/delalloc-space.c
index 2059d1504149..40c4d6ba3fb9 100644
--- a/fs/btrfs/delalloc-space.c
+++ b/fs/btrfs/delalloc-space.c
@@ -143,10 +143,13 @@ int btrfs_check_data_free_space(struct btrfs_inode *inode,
 
 	/* Use new btrfs_qgroup_reserve_data to reserve precious data space. */
 	ret = btrfs_qgroup_reserve_data(inode, reserved, start, len);
-	if (ret < 0)
+	if (ret < 0) {
 		btrfs_free_reserved_data_space_noquota(fs_info, len);
-	else
+		extent_changeset_free(*reserved);
+		*reserved = NULL;
+	} else {
 		ret = 0;
+	}
 	return ret;
 }
 
@@ -452,8 +455,11 @@ int btrfs_delalloc_reserve_space(struct btrfs_inode *inode,
 	if (ret < 0)
 		return ret;
 	ret = btrfs_delalloc_reserve_metadata(inode, len);
-	if (ret < 0)
+	if (ret < 0) {
 		btrfs_free_reserved_data_space(inode, *reserved, start, len);
+		extent_changeset_free(*reserved);
+		*reserved = NULL;
+	}
 	return ret;
 }
 
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 59c3be8c1f4c..b3f2e2232326 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1732,6 +1732,14 @@ again:
 	}
 	return root;
 fail:
+	/*
+	 * If our caller provided us an anonymous device, then it's his
+	 * responsability to free it in case we fail. So we have to set our
+	 * root's anon_dev to 0 to avoid a double free, once by btrfs_put_root()
+	 * and once again by our caller.
+	 */
+	if (anon_dev)
+		root->anon_dev = 0;
 	btrfs_put_root(root);
 	return ERR_PTR(ret);
 }
@@ -3978,11 +3986,23 @@ static void btrfs_end_empty_barrier(struct bio *bio)
  */
 static void write_dev_flush(struct btrfs_device *device)
 {
-	struct request_queue *q = bdev_get_queue(device->bdev);
 	struct bio *bio = device->flush_bio;
 
+#ifndef CONFIG_BTRFS_FS_CHECK_INTEGRITY
+	/*
+	 * When a disk has write caching disabled, we skip submission of a bio
+	 * with flush and sync requests before writing the superblock, since
+	 * it's not needed. However when the integrity checker is enabled, this
+	 * results in reports that there are metadata blocks referred by a
+	 * superblock that were not properly flushed. So don't skip the bio
+	 * submission only when the integrity checker is enabled for the sake
+	 * of simplicity, since this is a debug tool and not meant for use in
+	 * non-debug builds.
+	 */
+	struct request_queue *q = bdev_get_queue(device->bdev);
 	if (!test_bit(QUEUE_FLAG_WC, &q->queue_flags))
 		return;
+#endif
 
 	bio_reset(bio);
 	bio->bi_end_io = btrfs_end_empty_barrier;
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 3fd736a02c1e..25ef6e3fd306 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3275,20 +3275,20 @@ out_delayed_unlock:
 }
 
 void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
-			   struct btrfs_root *root,
+			   u64 root_id,
 			   struct extent_buffer *buf,
 			   u64 parent, int last_ref)
 {
-	struct btrfs_fs_info *fs_info = root->fs_info;
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_ref generic_ref = { 0 };
 	int ret;
 
 	btrfs_init_generic_ref(&generic_ref, BTRFS_DROP_DELAYED_REF,
 			       buf->start, buf->len, parent);
 	btrfs_init_tree_ref(&generic_ref, btrfs_header_level(buf),
-			    root->root_key.objectid, 0, false);
+			    root_id, 0, false);
 
-	if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) {
+	if (root_id != BTRFS_TREE_LOG_OBJECTID) {
 		btrfs_ref_tree_mod(fs_info, &generic_ref);
 		ret = btrfs_add_delayed_tree_ref(trans, &generic_ref, NULL);
 		BUG_ON(ret); /* -ENOMEM */
@@ -3298,7 +3298,7 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
 		struct btrfs_block_group *cache;
 		bool must_pin = false;
 
-		if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) {
+		if (root_id != BTRFS_TREE_LOG_OBJECTID) {
 			ret = check_ref_cleanup(trans, buf->start);
 			if (!ret) {
 				btrfs_redirty_list_add(trans->transaction, buf);
@@ -5472,7 +5472,8 @@ static noinline int walk_up_proc(struct btrfs_trans_handle *trans,
 			goto owner_mismatch;
 	}
 
-	btrfs_free_tree_block(trans, root, eb, parent, wc->refs[level] == 1);
+	btrfs_free_tree_block(trans, btrfs_root_id(root), eb, parent,
+			      wc->refs[level] == 1);
 out:
 	wc->refs[level] = 0;
 	wc->flags[level] = 0;
@@ -6051,6 +6052,9 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range)
 	int dev_ret = 0;
 	int ret = 0;
 
+	if (range->start == U64_MAX)
+		return -EINVAL;
+
 	/*
 	 * Check range overflow if range->len is set.
 	 * The default range->len is U64_MAX.
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 4e03a6d3aa32..9234d96a7fd5 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -4314,6 +4314,20 @@ static void set_btree_ioerr(struct page *page, struct extent_buffer *eb)
 		return;
 
 	/*
+	 * A read may stumble upon this buffer later, make sure that it gets an
+	 * error and knows there was an error.
+	 */
+	clear_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
+
+	/*
+	 * We need to set the mapping with the io error as well because a write
+	 * error will flip the file system readonly, and then syncfs() will
+	 * return a 0 because we are readonly if we don't modify the err seq for
+	 * the superblock.
+	 */
+	mapping_set_error(page->mapping, -EIO);
+
+	/*
 	 * If we error out, we should add back the dirty_metadata_bytes
 	 * to make it consistent.
 	 */
@@ -6597,6 +6611,14 @@ int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num)
 	if (test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags))
 		return 0;
 
+	/*
+	 * We could have had EXTENT_BUFFER_UPTODATE cleared by the write
+	 * operation, which could potentially still be in flight.  In this case
+	 * we simply want to return an error.
+	 */
+	if (unlikely(test_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags)))
+		return -EIO;
+
 	if (eb->fs_info->sectorsize < PAGE_SIZE)
 		return read_extent_buffer_subpage(eb, wait, mirror_num);
 
diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c
index a33bca94d133..3abec44c6255 100644
--- a/fs/btrfs/free-space-tree.c
+++ b/fs/btrfs/free-space-tree.c
@@ -1256,8 +1256,8 @@ int btrfs_clear_free_space_tree(struct btrfs_fs_info *fs_info)
 	btrfs_tree_lock(free_space_root->node);
 	btrfs_clean_tree_block(free_space_root->node);
 	btrfs_tree_unlock(free_space_root->node);
-	btrfs_free_tree_block(trans, free_space_root, free_space_root->node,
-			      0, 1);
+	btrfs_free_tree_block(trans, btrfs_root_id(free_space_root),
+			      free_space_root->node, 0, 1);
 
 	btrfs_put_root(free_space_root);
 
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index fb8cc9642ac4..edfecfe62b4b 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -617,11 +617,13 @@ static noinline int create_subvol(struct user_namespace *mnt_userns,
 		 * Since we don't abort the transaction in this case, free the
 		 * tree block so that we don't leak space and leave the
 		 * filesystem in an inconsistent state (an extent item in the
-		 * extent tree without backreferences). Also no need to have
-		 * the tree block locked since it is not in any tree at this
-		 * point, so no other task can find it and use it.
+		 * extent tree with a backreference for a root that does not
+		 * exists).
 		 */
-		btrfs_free_tree_block(trans, root, leaf, 0, 1);
+		btrfs_tree_lock(leaf);
+		btrfs_clean_tree_block(leaf);
+		btrfs_tree_unlock(leaf);
+		btrfs_free_tree_block(trans, objectid, leaf, 0, 1);
 		free_extent_buffer(leaf);
 		goto fail;
 	}
@@ -3187,10 +3189,8 @@ static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg)
 		return -EPERM;
 
 	vol_args = memdup_user(arg, sizeof(*vol_args));
-	if (IS_ERR(vol_args)) {
-		ret = PTR_ERR(vol_args);
-		goto out;
-	}
+	if (IS_ERR(vol_args))
+		return PTR_ERR(vol_args);
 
 	if (vol_args->flags & ~BTRFS_DEVICE_REMOVE_ARGS_MASK) {
 		ret = -EOPNOTSUPP;
@@ -3985,6 +3985,10 @@ static long btrfs_ioctl_balance(struct file *file, void __user *arg)
 	bool need_unlock; /* for mut. excl. ops lock */
 	int ret;
 
+	if (!arg)
+		btrfs_warn(fs_info,
+	"IOC_BALANCE ioctl (v1) is deprecated and will be removed in kernel 5.18");
+
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
diff --git a/fs/btrfs/lzo.c b/fs/btrfs/lzo.c
index 65cb0766e62d..0fb90cbe7669 100644
--- a/fs/btrfs/lzo.c
+++ b/fs/btrfs/lzo.c
@@ -125,6 +125,7 @@ static inline size_t read_compress_length(const char *buf)
 static int copy_compressed_data_to_page(char *compressed_data,
 					size_t compressed_size,
 					struct page **out_pages,
+					unsigned long max_nr_page,
 					u32 *cur_out,
 					const u32 sectorsize)
 {
@@ -133,6 +134,9 @@ static int copy_compressed_data_to_page(char *compressed_data,
 	struct page *cur_page;
 	char *kaddr;
 
+	if ((*cur_out / PAGE_SIZE) >= max_nr_page)
+		return -E2BIG;
+
 	/*
 	 * We never allow a segment header crossing sector boundary, previous
 	 * run should ensure we have enough space left inside the sector.
@@ -161,6 +165,10 @@ static int copy_compressed_data_to_page(char *compressed_data,
 				     orig_out + compressed_size - *cur_out);
 
 		kunmap(cur_page);
+
+		if ((*cur_out / PAGE_SIZE) >= max_nr_page)
+			return -E2BIG;
+
 		cur_page = out_pages[*cur_out / PAGE_SIZE];
 		/* Allocate a new page */
 		if (!cur_page) {
@@ -203,6 +211,7 @@ int lzo_compress_pages(struct list_head *ws, struct address_space *mapping,
 	const u32 sectorsize = btrfs_sb(mapping->host->i_sb)->sectorsize;
 	struct page *page_in = NULL;
 	char *sizes_ptr;
+	const unsigned long max_nr_page = *out_pages;
 	int ret = 0;
 	/* Points to the file offset of input data */
 	u64 cur_in = start;
@@ -210,6 +219,7 @@ int lzo_compress_pages(struct list_head *ws, struct address_space *mapping,
 	u32 cur_out = 0;
 	u32 len = *total_out;
 
+	ASSERT(max_nr_page > 0);
 	*out_pages = 0;
 	*total_out = 0;
 	*total_in = 0;
@@ -248,7 +258,8 @@ int lzo_compress_pages(struct list_head *ws, struct address_space *mapping,
 		}
 
 		ret = copy_compressed_data_to_page(workspace->cbuf, out_len,
-						   pages, &cur_out, sectorsize);
+						   pages, max_nr_page,
+						   &cur_out, sectorsize);
 		if (ret < 0)
 			goto out;
 
@@ -279,6 +290,8 @@ int lzo_compress_pages(struct list_head *ws, struct address_space *mapping,
 	*total_out = cur_out;
 	*total_in = cur_in - start;
 out:
+	if (page_in)
+		put_page(page_in);
 	*out_pages = DIV_ROUND_UP(cur_out, PAGE_SIZE);
 	return ret;
 }
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index db680f5be745..6c037f1252b7 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1219,7 +1219,8 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info)
 	btrfs_tree_lock(quota_root->node);
 	btrfs_clean_tree_block(quota_root->node);
 	btrfs_tree_unlock(quota_root->node);
-	btrfs_free_tree_block(trans, quota_root, quota_root->node, 0, 1);
+	btrfs_free_tree_block(trans, btrfs_root_id(quota_root),
+			      quota_root->node, 0, 1);
 
 	btrfs_put_root(quota_root);
 
diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c
index 12ceb14a1141..d20166336557 100644
--- a/fs/btrfs/root-tree.c
+++ b/fs/btrfs/root-tree.c
@@ -334,7 +334,8 @@ int btrfs_del_root_ref(struct btrfs_trans_handle *trans, u64 root_id,
 	key.offset = ref_id;
 again:
 	ret = btrfs_search_slot(trans, tree_root, &key, path, -1, 1);
-	BUG_ON(ret < 0);
+	if (ret < 0)
+		goto out;
 	if (ret == 0) {
 		leaf = path->nodes[0];
 		ref = btrfs_item_ptr(leaf, path->slots[0],
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index cf82ea6f54fb..8f6ceea33969 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -73,8 +73,8 @@ struct scrub_page {
 	u64			physical_for_dev_replace;
 	atomic_t		refs;
 	u8			mirror_num;
-	int			have_csum:1;
-	int			io_error:1;
+	unsigned int		have_csum:1;
+	unsigned int		io_error:1;
 	u8			csum[BTRFS_CSUM_SIZE];
 
 	struct scrub_recover	*recover;
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 8ab33caf016f..6993dcdba6f1 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -1181,6 +1181,7 @@ again:
 					     parent_objectid, victim_name,
 					     victim_name_len);
 			if (ret < 0) {
+				kfree(victim_name);
 				return ret;
 			} else if (!ret) {
 				ret = -ENOENT;
@@ -2908,6 +2909,8 @@ static noinline int walk_up_log_tree(struct btrfs_trans_handle *trans,
 						     path->nodes[*level]->len);
 					if (ret)
 						return ret;
+					btrfs_redirty_list_add(trans->transaction,
+							       next);
 				} else {
 					if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &next->bflags))
 						clear_extent_buffer_dirty(next);
@@ -2988,6 +2991,7 @@ static int walk_log_tree(struct btrfs_trans_handle *trans,
 						next->start, next->len);
 				if (ret)
 					goto out;
+				btrfs_redirty_list_add(trans->transaction, next);
 			} else {
 				if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &next->bflags))
 					clear_extent_buffer_dirty(next);
@@ -3438,8 +3442,6 @@ static void free_log_tree(struct btrfs_trans_handle *trans,
 			  EXTENT_DIRTY | EXTENT_NEW | EXTENT_NEED_WAIT);
 	extent_io_tree_release(&log->log_csum_range);
 
-	if (trans && log->node)
-		btrfs_redirty_list_add(trans->transaction, log->node);
 	btrfs_put_root(log);
 }
 
@@ -3976,6 +3978,7 @@ search:
 			goto done;
 		}
 		if (btrfs_header_generation(path->nodes[0]) != trans->transid) {
+			ctx->last_dir_item_offset = min_key.offset;
 			ret = overwrite_item(trans, log, dst_path,
 					     path->nodes[0], path->slots[0],
 					     &min_key);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 61ac57bcbf1a..fd0ced829edb 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1370,8 +1370,10 @@ struct btrfs_device *btrfs_scan_one_device(const char *path, fmode_t flags,
 
 	bytenr_orig = btrfs_sb_offset(0);
 	ret = btrfs_sb_log_location_bdev(bdev, 0, READ, &bytenr);
-	if (ret)
-		return ERR_PTR(ret);
+	if (ret) {
+		device = ERR_PTR(ret);
+		goto error_bdev_put;
+	}
 
 	disk_super = btrfs_read_disk_super(bdev, bytenr, bytenr_orig);
 	if (IS_ERR(disk_super)) {
@@ -7559,6 +7561,19 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info)
 	fs_info->fs_devices->total_rw_bytes = 0;
 
 	/*
+	 * Lockdep complains about possible circular locking dependency between
+	 * a disk's open_mutex (struct gendisk.open_mutex), the rw semaphores
+	 * used for freeze procection of a fs (struct super_block.s_writers),
+	 * which we take when starting a transaction, and extent buffers of the
+	 * chunk tree if we call read_one_dev() while holding a lock on an
+	 * extent buffer of the chunk tree. Since we are mounting the filesystem
+	 * and at this point there can't be any concurrent task modifying the
+	 * chunk tree, to keep it simple, just skip locking on the chunk tree.
+	 */
+	ASSERT(!test_bit(BTRFS_FS_OPEN, &fs_info->flags));
+	path->skip_locking = 1;
+
+	/*
 	 * Read all device items, and then all the chunk items. All
 	 * device items are found before any chunk item (their object id
 	 * is smaller than the lowest possible object id for a chunk
@@ -7583,10 +7598,6 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info)
 				goto error;
 			break;
 		}
-		/*
-		 * The nodes on level 1 are not locked but we don't need to do
-		 * that during mount time as nothing else can access the tree
-		 */
 		node = path->nodes[1];
 		if (node) {
 			if (last_ra_node != node->start) {
@@ -7614,7 +7625,6 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info)
 			 * requirement for chunk allocation, see the comment on
 			 * top of btrfs_chunk_alloc() for details.
 			 */
-			ASSERT(!test_bit(BTRFS_FS_OPEN, &fs_info->flags));
 			chunk = btrfs_item_ptr(leaf, slot, struct btrfs_chunk);
 			ret = read_one_chunk(&found_key, leaf, chunk);
 			if (ret)
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index 67d932d70798..678a29469511 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -1860,6 +1860,7 @@ int btrfs_zone_finish(struct btrfs_block_group *block_group)
 	block_group->alloc_offset = block_group->zone_capacity;
 	block_group->free_space_ctl->free_space = 0;
 	btrfs_clear_treelog_bg(block_group);
+	btrfs_clear_data_reloc_bg(block_group);
 	spin_unlock(&block_group->lock);
 
 	ret = blkdev_zone_mgmt(device->bdev, REQ_OP_ZONE_FINISH,
@@ -1942,6 +1943,7 @@ void btrfs_zone_finish_endio(struct btrfs_fs_info *fs_info, u64 logical, u64 len
 	ASSERT(block_group->alloc_offset == block_group->zone_capacity);
 	ASSERT(block_group->free_space_ctl->free_space == 0);
 	btrfs_clear_treelog_bg(block_group);
+	btrfs_clear_data_reloc_bg(block_group);
 	spin_unlock(&block_group->lock);
 
 	map = block_group->physical_map;
diff --git a/fs/btrfs/zstd.c b/fs/btrfs/zstd.c
index f06b68040352..fc42dd0badd7 100644
--- a/fs/btrfs/zstd.c
+++ b/fs/btrfs/zstd.c
@@ -28,10 +28,10 @@
 /* 307s to avoid pathologically clashing with transaction commit */
 #define ZSTD_BTRFS_RECLAIM_JIFFIES (307 * HZ)
 
-static ZSTD_parameters zstd_get_btrfs_parameters(unsigned int level,
+static zstd_parameters zstd_get_btrfs_parameters(unsigned int level,
 						 size_t src_len)
 {
-	ZSTD_parameters params = ZSTD_getParams(level, src_len, 0);
+	zstd_parameters params = zstd_get_params(level, src_len);
 
 	if (params.cParams.windowLog > ZSTD_BTRFS_MAX_WINDOWLOG)
 		params.cParams.windowLog = ZSTD_BTRFS_MAX_WINDOWLOG;
@@ -48,8 +48,8 @@ struct workspace {
 	unsigned long last_used; /* jiffies */
 	struct list_head list;
 	struct list_head lru_list;
-	ZSTD_inBuffer in_buf;
-	ZSTD_outBuffer out_buf;
+	zstd_in_buffer in_buf;
+	zstd_out_buffer out_buf;
 };
 
 /*
@@ -155,12 +155,12 @@ static void zstd_calc_ws_mem_sizes(void)
 	unsigned int level;
 
 	for (level = 1; level <= ZSTD_BTRFS_MAX_LEVEL; level++) {
-		ZSTD_parameters params =
+		zstd_parameters params =
 			zstd_get_btrfs_parameters(level, ZSTD_BTRFS_MAX_INPUT);
 		size_t level_size =
 			max_t(size_t,
-			      ZSTD_CStreamWorkspaceBound(params.cParams),
-			      ZSTD_DStreamWorkspaceBound(ZSTD_BTRFS_MAX_INPUT));
+			      zstd_cstream_workspace_bound(&params.cParams),
+			      zstd_dstream_workspace_bound(ZSTD_BTRFS_MAX_INPUT));
 
 		max_size = max_t(size_t, max_size, level_size);
 		zstd_ws_mem_sizes[level - 1] = max_size;
@@ -371,7 +371,7 @@ int zstd_compress_pages(struct list_head *ws, struct address_space *mapping,
 		unsigned long *total_in, unsigned long *total_out)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
-	ZSTD_CStream *stream;
+	zstd_cstream *stream;
 	int ret = 0;
 	int nr_pages = 0;
 	struct page *in_page = NULL;  /* The current page to read */
@@ -381,7 +381,7 @@ int zstd_compress_pages(struct list_head *ws, struct address_space *mapping,
 	unsigned long len = *total_out;
 	const unsigned long nr_dest_pages = *out_pages;
 	unsigned long max_out = nr_dest_pages * PAGE_SIZE;
-	ZSTD_parameters params = zstd_get_btrfs_parameters(workspace->req_level,
+	zstd_parameters params = zstd_get_btrfs_parameters(workspace->req_level,
 							   len);
 
 	*out_pages = 0;
@@ -389,10 +389,10 @@ int zstd_compress_pages(struct list_head *ws, struct address_space *mapping,
 	*total_in = 0;
 
 	/* Initialize the stream */
-	stream = ZSTD_initCStream(params, len, workspace->mem,
+	stream = zstd_init_cstream(&params, len, workspace->mem,
 			workspace->size);
 	if (!stream) {
-		pr_warn("BTRFS: ZSTD_initCStream failed\n");
+		pr_warn("BTRFS: zstd_init_cstream failed\n");
 		ret = -EIO;
 		goto out;
 	}
@@ -418,11 +418,11 @@ int zstd_compress_pages(struct list_head *ws, struct address_space *mapping,
 	while (1) {
 		size_t ret2;
 
-		ret2 = ZSTD_compressStream(stream, &workspace->out_buf,
+		ret2 = zstd_compress_stream(stream, &workspace->out_buf,
 				&workspace->in_buf);
-		if (ZSTD_isError(ret2)) {
-			pr_debug("BTRFS: ZSTD_compressStream returned %d\n",
-					ZSTD_getErrorCode(ret2));
+		if (zstd_is_error(ret2)) {
+			pr_debug("BTRFS: zstd_compress_stream returned %d\n",
+					zstd_get_error_code(ret2));
 			ret = -EIO;
 			goto out;
 		}
@@ -487,10 +487,10 @@ int zstd_compress_pages(struct list_head *ws, struct address_space *mapping,
 	while (1) {
 		size_t ret2;
 
-		ret2 = ZSTD_endStream(stream, &workspace->out_buf);
-		if (ZSTD_isError(ret2)) {
-			pr_debug("BTRFS: ZSTD_endStream returned %d\n",
-					ZSTD_getErrorCode(ret2));
+		ret2 = zstd_end_stream(stream, &workspace->out_buf);
+		if (zstd_is_error(ret2)) {
+			pr_debug("BTRFS: zstd_end_stream returned %d\n",
+					zstd_get_error_code(ret2));
 			ret = -EIO;
 			goto out;
 		}
@@ -548,17 +548,17 @@ 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;
 	size_t srclen = cb->compressed_len;
-	ZSTD_DStream *stream;
+	zstd_dstream *stream;
 	int ret = 0;
 	unsigned long page_in_index = 0;
 	unsigned long total_pages_in = DIV_ROUND_UP(srclen, PAGE_SIZE);
 	unsigned long buf_start;
 	unsigned long total_out = 0;
 
-	stream = ZSTD_initDStream(
+	stream = zstd_init_dstream(
 			ZSTD_BTRFS_MAX_INPUT, workspace->mem, workspace->size);
 	if (!stream) {
-		pr_debug("BTRFS: ZSTD_initDStream failed\n");
+		pr_debug("BTRFS: zstd_init_dstream failed\n");
 		ret = -EIO;
 		goto done;
 	}
@@ -574,11 +574,11 @@ int zstd_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
 	while (1) {
 		size_t ret2;
 
-		ret2 = ZSTD_decompressStream(stream, &workspace->out_buf,
+		ret2 = zstd_decompress_stream(stream, &workspace->out_buf,
 				&workspace->in_buf);
-		if (ZSTD_isError(ret2)) {
-			pr_debug("BTRFS: ZSTD_decompressStream returned %d\n",
-					ZSTD_getErrorCode(ret2));
+		if (zstd_is_error(ret2)) {
+			pr_debug("BTRFS: zstd_decompress_stream returned %d\n",
+					zstd_get_error_code(ret2));
 			ret = -EIO;
 			goto done;
 		}
@@ -624,16 +624,16 @@ int zstd_decompress(struct list_head *ws, unsigned char *data_in,
 		size_t destlen)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
-	ZSTD_DStream *stream;
+	zstd_dstream *stream;
 	int ret = 0;
 	size_t ret2;
 	unsigned long total_out = 0;
 	unsigned long pg_offset = 0;
 
-	stream = ZSTD_initDStream(
+	stream = zstd_init_dstream(
 			ZSTD_BTRFS_MAX_INPUT, workspace->mem, workspace->size);
 	if (!stream) {
-		pr_warn("BTRFS: ZSTD_initDStream failed\n");
+		pr_warn("BTRFS: zstd_init_dstream failed\n");
 		ret = -EIO;
 		goto finish;
 	}
@@ -657,15 +657,15 @@ int zstd_decompress(struct list_head *ws, unsigned char *data_in,
 
 		/* Check if the frame is over and we still need more input */
 		if (ret2 == 0) {
-			pr_debug("BTRFS: ZSTD_decompressStream ended early\n");
+			pr_debug("BTRFS: zstd_decompress_stream ended early\n");
 			ret = -EIO;
 			goto finish;
 		}
-		ret2 = ZSTD_decompressStream(stream, &workspace->out_buf,
+		ret2 = zstd_decompress_stream(stream, &workspace->out_buf,
 				&workspace->in_buf);
-		if (ZSTD_isError(ret2)) {
-			pr_debug("BTRFS: ZSTD_decompressStream returned %d\n",
-					ZSTD_getErrorCode(ret2));
+		if (zstd_is_error(ret2)) {
+			pr_debug("BTRFS: zstd_decompress_stream returned %d\n",
+					zstd_get_error_code(ret2));
 			ret = -EIO;
 			goto finish;
 		}
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 99b80b5c7a93..e53c8541f5b2 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -63,7 +63,7 @@
 	 (CONGESTION_ON_THRESH(congestion_kb) >> 2))
 
 static int ceph_netfs_check_write_begin(struct file *file, loff_t pos, unsigned int len,
-					struct page *page, void **_fsdata);
+					struct folio *folio, void **_fsdata);
 
 static inline struct ceph_snap_context *page_snap_context(struct page *page)
 {
@@ -317,13 +317,14 @@ static const struct netfs_read_request_ops ceph_netfs_read_ops = {
 };
 
 /* read a single page, without unlocking it. */
-static int ceph_readpage(struct file *file, struct page *page)
+static int ceph_readpage(struct file *file, struct page *subpage)
 {
+	struct folio *folio = page_folio(subpage);
 	struct inode *inode = file_inode(file);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_vino vino = ceph_vino(inode);
-	u64 off = page_offset(page);
-	u64 len = thp_size(page);
+	size_t len = folio_size(folio);
+	u64 off = folio_file_pos(folio);
 
 	if (ci->i_inline_version != CEPH_INLINE_NONE) {
 		/*
@@ -331,19 +332,19 @@ static int ceph_readpage(struct file *file, struct page *page)
 		 * into page cache while getting Fcr caps.
 		 */
 		if (off == 0) {
-			unlock_page(page);
+			folio_unlock(folio);
 			return -EINVAL;
 		}
-		zero_user_segment(page, 0, thp_size(page));
-		SetPageUptodate(page);
-		unlock_page(page);
+		zero_user_segment(&folio->page, 0, folio_size(folio));
+		folio_mark_uptodate(folio);
+		folio_unlock(folio);
 		return 0;
 	}
 
-	dout("readpage ino %llx.%llx file %p off %llu len %llu page %p index %lu\n",
-	     vino.ino, vino.snap, file, off, len, page, page->index);
+	dout("readpage ino %llx.%llx file %p off %llu len %zu folio %p index %lu\n",
+	     vino.ino, vino.snap, file, off, len, folio, folio_index(folio));
 
-	return netfs_readpage(file, page, &ceph_netfs_read_ops, NULL);
+	return netfs_readpage(file, folio, &ceph_netfs_read_ops, NULL);
 }
 
 static void ceph_readahead(struct readahead_control *ractl)
@@ -724,7 +725,7 @@ static int ceph_writepages_start(struct address_space *mapping,
 	     wbc->sync_mode == WB_SYNC_NONE ? "NONE" :
 	     (wbc->sync_mode == WB_SYNC_ALL ? "ALL" : "HOLD"));
 
-	if (READ_ONCE(fsc->mount_state) >= CEPH_MOUNT_SHUTDOWN) {
+	if (ceph_inode_is_shutdown(inode)) {
 		if (ci->i_wrbuffer_ref > 0) {
 			pr_warn_ratelimited(
 				"writepage_start %p %lld forced umount\n",
@@ -1145,12 +1146,12 @@ static struct ceph_snap_context *
 ceph_find_incompatible(struct page *page)
 {
 	struct inode *inode = page->mapping->host;
-	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 
-	if (READ_ONCE(fsc->mount_state) >= CEPH_MOUNT_SHUTDOWN) {
-		dout(" page %p forced umount\n", page);
-		return ERR_PTR(-EIO);
+	if (ceph_inode_is_shutdown(inode)) {
+		dout(" page %p %llx:%llx is shutdown\n", page,
+		     ceph_vinop(inode));
+		return ERR_PTR(-ESTALE);
 	}
 
 	for (;;) {
@@ -1187,18 +1188,18 @@ ceph_find_incompatible(struct page *page)
 }
 
 static int ceph_netfs_check_write_begin(struct file *file, loff_t pos, unsigned int len,
-					struct page *page, void **_fsdata)
+					struct folio *folio, void **_fsdata)
 {
 	struct inode *inode = file_inode(file);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_snap_context *snapc;
 
-	snapc = ceph_find_incompatible(page);
+	snapc = ceph_find_incompatible(folio_page(folio, 0));
 	if (snapc) {
 		int r;
 
-		unlock_page(page);
-		put_page(page);
+		folio_unlock(folio);
+		folio_put(folio);
 		if (IS_ERR(snapc))
 			return PTR_ERR(snapc);
 
@@ -1216,12 +1217,12 @@ static int ceph_netfs_check_write_begin(struct file *file, loff_t pos, unsigned
  * clean, or already dirty within the same snap context.
  */
 static int ceph_write_begin(struct file *file, struct address_space *mapping,
-			    loff_t pos, unsigned len, unsigned flags,
+			    loff_t pos, unsigned len, unsigned aop_flags,
 			    struct page **pagep, void **fsdata)
 {
 	struct inode *inode = file_inode(file);
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct page *page = NULL;
+	struct folio *folio = NULL;
 	pgoff_t index = pos >> PAGE_SHIFT;
 	int r;
 
@@ -1230,39 +1231,43 @@ static int ceph_write_begin(struct file *file, struct address_space *mapping,
 	 * for inline_version sent to the MDS.
 	 */
 	if (ci->i_inline_version != CEPH_INLINE_NONE) {
-		page = grab_cache_page_write_begin(mapping, index, flags);
-		if (!page)
+		unsigned int fgp_flags = FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE;
+		if (aop_flags & AOP_FLAG_NOFS)
+			fgp_flags |= FGP_NOFS;
+		folio = __filemap_get_folio(mapping, index, fgp_flags,
+					    mapping_gfp_mask(mapping));
+		if (!folio)
 			return -ENOMEM;
 
 		/*
 		 * The inline_version on a new inode is set to 1. If that's the
-		 * case, then the page is brand new and isn't yet Uptodate.
+		 * case, then the folio is brand new and isn't yet Uptodate.
 		 */
 		r = 0;
 		if (index == 0 && ci->i_inline_version != 1) {
-			if (!PageUptodate(page)) {
+			if (!folio_test_uptodate(folio)) {
 				WARN_ONCE(1, "ceph: write_begin called on still-inlined inode (inline_version %llu)!\n",
 					  ci->i_inline_version);
 				r = -EINVAL;
 			}
 			goto out;
 		}
-		zero_user_segment(page, 0, thp_size(page));
-		SetPageUptodate(page);
+		zero_user_segment(&folio->page, 0, folio_size(folio));
+		folio_mark_uptodate(folio);
 		goto out;
 	}
 
-	r = netfs_write_begin(file, inode->i_mapping, pos, len, 0, &page, NULL,
+	r = netfs_write_begin(file, inode->i_mapping, pos, len, 0, &folio, NULL,
 			      &ceph_netfs_read_ops, NULL);
 out:
 	if (r == 0)
-		wait_on_page_fscache(page);
+		folio_wait_fscache(folio);
 	if (r < 0) {
-		if (page)
-			put_page(page);
+		if (folio)
+			folio_put(folio);
 	} else {
-		WARN_ON_ONCE(!PageLocked(page));
-		*pagep = page;
+		WARN_ON_ONCE(!folio_test_locked(folio));
+		*pagep = &folio->page;
 	}
 	return r;
 }
@@ -1273,32 +1278,33 @@ out:
  */
 static int ceph_write_end(struct file *file, struct address_space *mapping,
 			  loff_t pos, unsigned len, unsigned copied,
-			  struct page *page, void *fsdata)
+			  struct page *subpage, void *fsdata)
 {
+	struct folio *folio = page_folio(subpage);
 	struct inode *inode = file_inode(file);
 	bool check_cap = false;
 
-	dout("write_end file %p inode %p page %p %d~%d (%d)\n", file,
-	     inode, page, (int)pos, (int)copied, (int)len);
+	dout("write_end file %p inode %p folio %p %d~%d (%d)\n", file,
+	     inode, folio, (int)pos, (int)copied, (int)len);
 
-	if (!PageUptodate(page)) {
+	if (!folio_test_uptodate(folio)) {
 		/* just return that nothing was copied on a short copy */
 		if (copied < len) {
 			copied = 0;
 			goto out;
 		}
-		SetPageUptodate(page);
+		folio_mark_uptodate(folio);
 	}
 
 	/* did file size increase? */
 	if (pos+copied > i_size_read(inode))
 		check_cap = ceph_inode_set_size(inode, pos+copied);
 
-	set_page_dirty(page);
+	folio_mark_dirty(folio);
 
 out:
-	unlock_page(page);
-	put_page(page);
+	folio_unlock(folio);
+	folio_put(folio);
 
 	if (check_cap)
 		ceph_check_caps(ceph_inode(inode), CHECK_CAPS_AUTHONLY, NULL);
@@ -1306,17 +1312,6 @@ out:
 	return copied;
 }
 
-/*
- * we set .direct_IO to indicate direct io is supported, but since we
- * intercept O_DIRECT reads and writes early, this function should
- * never get called.
- */
-static ssize_t ceph_direct_io(struct kiocb *iocb, struct iov_iter *iter)
-{
-	WARN_ON(1);
-	return -EINVAL;
-}
-
 const struct address_space_operations ceph_aops = {
 	.readpage = ceph_readpage,
 	.readahead = ceph_readahead,
@@ -1327,7 +1322,7 @@ const struct address_space_operations ceph_aops = {
 	.set_page_dirty = ceph_set_page_dirty,
 	.invalidatepage = ceph_invalidatepage,
 	.releasepage = ceph_releasepage,
-	.direct_IO = ceph_direct_io,
+	.direct_IO = noop_direct_IO,
 };
 
 static void ceph_block_sigs(sigset_t *oldset)
@@ -1356,6 +1351,9 @@ static vm_fault_t ceph_filemap_fault(struct vm_fault *vmf)
 	sigset_t oldset;
 	vm_fault_t ret = VM_FAULT_SIGBUS;
 
+	if (ceph_inode_is_shutdown(inode))
+		return ret;
+
 	ceph_block_sigs(&oldset);
 
 	dout("filemap_fault %p %llx.%llx %llu trying to get caps\n",
@@ -1447,6 +1445,9 @@ static vm_fault_t ceph_page_mkwrite(struct vm_fault *vmf)
 	sigset_t oldset;
 	vm_fault_t ret = VM_FAULT_SIGBUS;
 
+	if (ceph_inode_is_shutdown(inode))
+		return ret;
+
 	prealloc_cf = ceph_alloc_cap_flush();
 	if (!prealloc_cf)
 		return VM_FAULT_OOM;
diff --git a/fs/ceph/cache.c b/fs/ceph/cache.c
index 9cfadbb86568..457afda5498a 100644
--- a/fs/ceph/cache.c
+++ b/fs/ceph/cache.c
@@ -12,12 +12,6 @@
 #include "super.h"
 #include "cache.h"
 
-struct ceph_aux_inode {
-	u64 	version;
-	u64	mtime_sec;
-	u64	mtime_nsec;
-};
-
 struct fscache_netfs ceph_cache_netfs = {
 	.name		= "ceph",
 	.version	= 0,
@@ -109,20 +103,14 @@ static enum fscache_checkaux ceph_fscache_inode_check_aux(
 	void *cookie_netfs_data, const void *data, uint16_t dlen,
 	loff_t object_size)
 {
-	struct ceph_aux_inode aux;
 	struct ceph_inode_info* ci = cookie_netfs_data;
 	struct inode* inode = &ci->vfs_inode;
 
-	if (dlen != sizeof(aux) ||
+	if (dlen != sizeof(ci->i_version) ||
 	    i_size_read(inode) != object_size)
 		return FSCACHE_CHECKAUX_OBSOLETE;
 
-	memset(&aux, 0, sizeof(aux));
-	aux.version = ci->i_version;
-	aux.mtime_sec = inode->i_mtime.tv_sec;
-	aux.mtime_nsec = inode->i_mtime.tv_nsec;
-
-	if (memcmp(data, &aux, sizeof(aux)) != 0)
+	if (*(u64 *)data != ci->i_version)
 		return FSCACHE_CHECKAUX_OBSOLETE;
 
 	dout("ceph inode 0x%p cached okay\n", ci);
@@ -139,7 +127,6 @@ void ceph_fscache_register_inode_cookie(struct inode *inode)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
-	struct ceph_aux_inode aux;
 
 	/* No caching for filesystem */
 	if (!fsc->fscache)
@@ -151,14 +138,10 @@ void ceph_fscache_register_inode_cookie(struct inode *inode)
 
 	inode_lock_nested(inode, I_MUTEX_CHILD);
 	if (!ci->fscache) {
-		memset(&aux, 0, sizeof(aux));
-		aux.version = ci->i_version;
-		aux.mtime_sec = inode->i_mtime.tv_sec;
-		aux.mtime_nsec = inode->i_mtime.tv_nsec;
 		ci->fscache = fscache_acquire_cookie(fsc->fscache,
 						     &ceph_fscache_inode_object_def,
 						     &ci->i_vino, sizeof(ci->i_vino),
-						     &aux, sizeof(aux),
+						     &ci->i_version, sizeof(ci->i_version),
 						     ci, i_size_read(inode), false);
 	}
 	inode_unlock(inode);
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 8f537f1d9d1d..c447fa2e2d1f 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -1188,11 +1188,11 @@ void ceph_remove_cap(struct ceph_cap *cap, bool queue_release)
 
 	lockdep_assert_held(&ci->i_ceph_lock);
 
-	fsc = ceph_sb_to_client(ci->vfs_inode.i_sb);
+	fsc = ceph_inode_to_client(&ci->vfs_inode);
 	WARN_ON_ONCE(ci->i_auth_cap == cap &&
 		     !list_empty(&ci->i_dirty_item) &&
 		     !fsc->blocklisted &&
-		     READ_ONCE(fsc->mount_state) != CEPH_MOUNT_SHUTDOWN);
+		     !ceph_inode_is_shutdown(&ci->vfs_inode));
 
 	__ceph_remove_cap(cap, queue_release);
 }
@@ -1968,8 +1968,8 @@ retry:
 		}
 	}
 
-	dout("check_caps %p file_want %s used %s dirty %s flushing %s"
-	     " issued %s revoking %s retain %s %s%s\n", inode,
+	dout("check_caps %llx.%llx file_want %s used %s dirty %s flushing %s"
+	     " issued %s revoking %s retain %s %s%s\n", ceph_vinop(inode),
 	     ceph_cap_string(file_wanted),
 	     ceph_cap_string(used), ceph_cap_string(ci->i_dirty_caps),
 	     ceph_cap_string(ci->i_flushing_caps),
@@ -1990,7 +1990,8 @@ retry:
 	    (revoking & (CEPH_CAP_FILE_CACHE|
 			 CEPH_CAP_FILE_LAZYIO)) && /*  or revoking cache */
 	    !tried_invalidate) {
-		dout("check_caps trying to invalidate on %p\n", inode);
+		dout("check_caps trying to invalidate on %llx.%llx\n",
+		     ceph_vinop(inode));
 		if (try_nonblocking_invalidate(inode) < 0) {
 			dout("check_caps queuing invalidate\n");
 			queue_invalidate = true;
@@ -2629,9 +2630,9 @@ void ceph_take_cap_refs(struct ceph_inode_info *ci, int got,
  *
  * Returns 0 if caps were not able to be acquired (yet), 1 if succeed,
  * or a negative error code. There are 3 speical error codes:
- *  -EAGAIN: need to sleep but non-blocking is specified
- *  -EFBIG:  ask caller to call check_max_size() and try again.
- *  -ESTALE: ask caller to call ceph_renew_caps() and try again.
+ *  -EAGAIN:  need to sleep but non-blocking is specified
+ *  -EFBIG:   ask caller to call check_max_size() and try again.
+ *  -EUCLEAN: ask caller to call ceph_renew_caps() and try again.
  */
 enum {
 	/* first 8 bits are reserved for CEPH_FILE_MODE_FOO */
@@ -2679,7 +2680,7 @@ again:
 			dout("get_cap_refs %p endoff %llu > maxsize %llu\n",
 			     inode, endoff, ci->i_max_size);
 			if (endoff > ci->i_requested_max_size)
-				ret = ci->i_auth_cap ? -EFBIG : -ESTALE;
+				ret = ci->i_auth_cap ? -EFBIG : -EUCLEAN;
 			goto out_unlock;
 		}
 		/*
@@ -2749,9 +2750,9 @@ again:
 			goto out_unlock;
 		}
 
-		if (READ_ONCE(mdsc->fsc->mount_state) >= CEPH_MOUNT_SHUTDOWN) {
-			dout("get_cap_refs %p forced umount\n", inode);
-			ret = -EIO;
+		if (ceph_inode_is_shutdown(inode)) {
+			dout("get_cap_refs %p inode is shutdown\n", inode);
+			ret = -ESTALE;
 			goto out_unlock;
 		}
 		mds_wanted = __ceph_caps_mds_wanted(ci, false);
@@ -2759,7 +2760,7 @@ again:
 			dout("get_cap_refs %p need %s > mds_wanted %s\n",
 			     inode, ceph_cap_string(need),
 			     ceph_cap_string(mds_wanted));
-			ret = -ESTALE;
+			ret = -EUCLEAN;
 			goto out_unlock;
 		}
 
@@ -2843,7 +2844,7 @@ int ceph_try_get_caps(struct inode *inode, int need, int want,
 
 	ret = try_get_cap_refs(inode, need, want, 0, flags, got);
 	/* three special error codes */
-	if (ret == -EAGAIN || ret == -EFBIG || ret == -ESTALE)
+	if (ret == -EAGAIN || ret == -EFBIG || ret == -EUCLEAN)
 		ret = 0;
 	return ret;
 }
@@ -2926,7 +2927,7 @@ int ceph_get_caps(struct file *filp, int need, int want, loff_t endoff, int *got
 		}
 
 		if (ret < 0) {
-			if (ret == -EFBIG || ret == -ESTALE) {
+			if (ret == -EFBIG || ret == -EUCLEAN) {
 				int ret2 = ceph_wait_on_async_create(inode);
 				if (ret2 < 0)
 					return ret2;
@@ -2935,7 +2936,7 @@ int ceph_get_caps(struct file *filp, int need, int want, loff_t endoff, int *got
 				check_max_size(inode, endoff);
 				continue;
 			}
-			if (ret == -ESTALE) {
+			if (ret == -EUCLEAN) {
 				/* session was killed, try renew caps */
 				ret = ceph_renew_caps(inode, flags);
 				if (ret == 0)
@@ -4315,7 +4316,7 @@ static void flush_dirty_session_caps(struct ceph_mds_session *s)
 				      i_dirty_item);
 		inode = &ci->vfs_inode;
 		ihold(inode);
-		dout("flush_dirty_caps %p\n", inode);
+		dout("flush_dirty_caps %llx.%llx\n", ceph_vinop(inode));
 		spin_unlock(&mdsc->cap_dirty_lock);
 		ceph_check_caps(ci, CHECK_CAPS_FLUSH, NULL);
 		iput(inode);
@@ -4349,7 +4350,7 @@ void ceph_get_fmode(struct ceph_inode_info *ci, int fmode, int count)
 {
 	struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(ci->vfs_inode.i_sb);
 	int bits = (fmode << 1) | 1;
-	bool is_opened = false;
+	bool already_opened = false;
 	int i;
 
 	if (count == 1)
@@ -4357,19 +4358,19 @@ void ceph_get_fmode(struct ceph_inode_info *ci, int fmode, int count)
 
 	spin_lock(&ci->i_ceph_lock);
 	for (i = 0; i < CEPH_FILE_MODE_BITS; i++) {
-		if (bits & (1 << i))
-			ci->i_nr_by_mode[i] += count;
-
 		/*
-		 * If any of the mode ref is larger than 1,
+		 * If any of the mode ref is larger than 0,
 		 * that means it has been already opened by
 		 * others. Just skip checking the PIN ref.
 		 */
-		if (i && ci->i_nr_by_mode[i] > 1)
-			is_opened = true;
+		if (i && ci->i_nr_by_mode[i])
+			already_opened = true;
+
+		if (bits & (1 << i))
+			ci->i_nr_by_mode[i] += count;
 	}
 
-	if (!is_opened)
+	if (!already_opened)
 		percpu_counter_inc(&mdsc->metric.opened_inodes);
 	spin_unlock(&ci->i_ceph_lock);
 }
@@ -4560,3 +4561,119 @@ int ceph_encode_dentry_release(void **p, struct dentry *dentry,
 	spin_unlock(&dentry->d_lock);
 	return ret;
 }
+
+static int remove_capsnaps(struct ceph_mds_client *mdsc, struct inode *inode)
+{
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_cap_snap *capsnap;
+	int capsnap_release = 0;
+
+	lockdep_assert_held(&ci->i_ceph_lock);
+
+	dout("removing capsnaps, ci is %p, inode is %p\n", ci, inode);
+
+	while (!list_empty(&ci->i_cap_snaps)) {
+		capsnap = list_first_entry(&ci->i_cap_snaps,
+					   struct ceph_cap_snap, ci_item);
+		__ceph_remove_capsnap(inode, capsnap, NULL, NULL);
+		ceph_put_snap_context(capsnap->context);
+		ceph_put_cap_snap(capsnap);
+		capsnap_release++;
+	}
+	wake_up_all(&ci->i_cap_wq);
+	wake_up_all(&mdsc->cap_flushing_wq);
+	return capsnap_release;
+}
+
+int ceph_purge_inode_cap(struct inode *inode, struct ceph_cap *cap, bool *invalidate)
+{
+	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
+	struct ceph_mds_client *mdsc = fsc->mdsc;
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	bool is_auth;
+	bool dirty_dropped = false;
+	int iputs = 0;
+
+	lockdep_assert_held(&ci->i_ceph_lock);
+
+	dout("removing cap %p, ci is %p, inode is %p\n",
+	     cap, ci, &ci->vfs_inode);
+
+	is_auth = (cap == ci->i_auth_cap);
+	__ceph_remove_cap(cap, false);
+	if (is_auth) {
+		struct ceph_cap_flush *cf;
+
+		if (ceph_inode_is_shutdown(inode)) {
+			if (inode->i_data.nrpages > 0)
+				*invalidate = true;
+			if (ci->i_wrbuffer_ref > 0)
+				mapping_set_error(&inode->i_data, -EIO);
+		}
+
+		spin_lock(&mdsc->cap_dirty_lock);
+
+		/* trash all of the cap flushes for this inode */
+		while (!list_empty(&ci->i_cap_flush_list)) {
+			cf = list_first_entry(&ci->i_cap_flush_list,
+					      struct ceph_cap_flush, i_list);
+			list_del_init(&cf->g_list);
+			list_del_init(&cf->i_list);
+			if (!cf->is_capsnap)
+				ceph_free_cap_flush(cf);
+		}
+
+		if (!list_empty(&ci->i_dirty_item)) {
+			pr_warn_ratelimited(
+				" dropping dirty %s state for %p %lld\n",
+				ceph_cap_string(ci->i_dirty_caps),
+				inode, ceph_ino(inode));
+			ci->i_dirty_caps = 0;
+			list_del_init(&ci->i_dirty_item);
+			dirty_dropped = true;
+		}
+		if (!list_empty(&ci->i_flushing_item)) {
+			pr_warn_ratelimited(
+				" dropping dirty+flushing %s state for %p %lld\n",
+				ceph_cap_string(ci->i_flushing_caps),
+				inode, ceph_ino(inode));
+			ci->i_flushing_caps = 0;
+			list_del_init(&ci->i_flushing_item);
+			mdsc->num_cap_flushing--;
+			dirty_dropped = true;
+		}
+		spin_unlock(&mdsc->cap_dirty_lock);
+
+		if (dirty_dropped) {
+			mapping_set_error(inode->i_mapping, -EIO);
+
+			if (ci->i_wrbuffer_ref_head == 0 &&
+			    ci->i_wr_ref == 0 &&
+			    ci->i_dirty_caps == 0 &&
+			    ci->i_flushing_caps == 0) {
+				ceph_put_snap_context(ci->i_head_snapc);
+				ci->i_head_snapc = NULL;
+			}
+		}
+
+		if (atomic_read(&ci->i_filelock_ref) > 0) {
+			/* make further file lock syscall return -EIO */
+			ci->i_ceph_flags |= CEPH_I_ERROR_FILELOCK;
+			pr_warn_ratelimited(" dropping file locks for %p %lld\n",
+					    inode, ceph_ino(inode));
+		}
+
+		if (!ci->i_dirty_caps && ci->i_prealloc_cap_flush) {
+			cf = ci->i_prealloc_cap_flush;
+			ci->i_prealloc_cap_flush = NULL;
+			if (!cf->is_capsnap)
+				ceph_free_cap_flush(cf);
+		}
+
+		if (!list_empty(&ci->i_cap_snaps))
+			iputs = remove_capsnaps(mdsc, inode);
+	}
+	if (dirty_dropped)
+		++iputs;
+	return iputs;
+}
diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c
index 38b78b45811f..3cf7c9c1085b 100644
--- a/fs/ceph/debugfs.c
+++ b/fs/ceph/debugfs.c
@@ -146,82 +146,93 @@ static int mdsc_show(struct seq_file *s, void *p)
 		   name, total, avg, _min, max, sum);			\
 }
 
-static int metric_show(struct seq_file *s, void *p)
+static int metrics_file_show(struct seq_file *s, void *p)
 {
 	struct ceph_fs_client *fsc = s->private;
-	struct ceph_mds_client *mdsc = fsc->mdsc;
-	struct ceph_client_metric *m = &mdsc->metric;
-	int nr_caps = 0;
-	s64 total, sum, avg, min, max, sq;
-	u64 sum_sz, avg_sz, min_sz, max_sz;
+	struct ceph_client_metric *m = &fsc->mdsc->metric;
 
-	sum = percpu_counter_sum(&m->total_inodes);
 	seq_printf(s, "item                               total\n");
 	seq_printf(s, "------------------------------------------\n");
-	seq_printf(s, "%-35s%lld / %lld\n", "opened files  / total inodes",
-		   atomic64_read(&m->opened_files), sum);
-	seq_printf(s, "%-35s%lld / %lld\n", "pinned i_caps / total inodes",
-		   atomic64_read(&m->total_caps), sum);
-	seq_printf(s, "%-35s%lld / %lld\n", "opened inodes / total inodes",
-		   percpu_counter_sum(&m->opened_inodes), sum);
-
-	seq_printf(s, "\n");
+	seq_printf(s, "%-35s%lld\n", "total inodes",
+		   percpu_counter_sum(&m->total_inodes));
+	seq_printf(s, "%-35s%lld\n", "opened files",
+		   atomic64_read(&m->opened_files));
+	seq_printf(s, "%-35s%lld\n", "pinned i_caps",
+		   atomic64_read(&m->total_caps));
+	seq_printf(s, "%-35s%lld\n", "opened inodes",
+		   percpu_counter_sum(&m->opened_inodes));
+	return 0;
+}
+
+static const char * const metric_str[] = {
+	"read",
+	"write",
+	"metadata",
+	"copyfrom"
+};
+static int metrics_latency_show(struct seq_file *s, void *p)
+{
+	struct ceph_fs_client *fsc = s->private;
+	struct ceph_client_metric *cm = &fsc->mdsc->metric;
+	struct ceph_metric *m;
+	s64 total, sum, avg, min, max, sq;
+	int i;
+
 	seq_printf(s, "item          total       avg_lat(us)     min_lat(us)     max_lat(us)     stdev(us)\n");
 	seq_printf(s, "-----------------------------------------------------------------------------------\n");
 
-	spin_lock(&m->read_metric_lock);
-	total = m->total_reads;
-	sum = m->read_latency_sum;
-	avg = total > 0 ? DIV64_U64_ROUND_CLOSEST(sum, total) : 0;
-	min = m->read_latency_min;
-	max = m->read_latency_max;
-	sq = m->read_latency_sq_sum;
-	spin_unlock(&m->read_metric_lock);
-	CEPH_LAT_METRIC_SHOW("read", total, avg, min, max, sq);
-
-	spin_lock(&m->write_metric_lock);
-	total = m->total_writes;
-	sum = m->write_latency_sum;
-	avg = total > 0 ? DIV64_U64_ROUND_CLOSEST(sum, total) : 0;
-	min = m->write_latency_min;
-	max = m->write_latency_max;
-	sq = m->write_latency_sq_sum;
-	spin_unlock(&m->write_metric_lock);
-	CEPH_LAT_METRIC_SHOW("write", total, avg, min, max, sq);
-
-	spin_lock(&m->metadata_metric_lock);
-	total = m->total_metadatas;
-	sum = m->metadata_latency_sum;
-	avg = total > 0 ? DIV64_U64_ROUND_CLOSEST(sum, total) : 0;
-	min = m->metadata_latency_min;
-	max = m->metadata_latency_max;
-	sq = m->metadata_latency_sq_sum;
-	spin_unlock(&m->metadata_metric_lock);
-	CEPH_LAT_METRIC_SHOW("metadata", total, avg, min, max, sq);
-
-	seq_printf(s, "\n");
+	for (i = 0; i < METRIC_MAX; i++) {
+		m = &cm->metric[i];
+		spin_lock(&m->lock);
+		total = m->total;
+		sum = m->latency_sum;
+		avg = total > 0 ? DIV64_U64_ROUND_CLOSEST(sum, total) : 0;
+		min = m->latency_min;
+		max = m->latency_max;
+		sq = m->latency_sq_sum;
+		spin_unlock(&m->lock);
+		CEPH_LAT_METRIC_SHOW(metric_str[i], total, avg, min, max, sq);
+	}
+
+	return 0;
+}
+
+static int metrics_size_show(struct seq_file *s, void *p)
+{
+	struct ceph_fs_client *fsc = s->private;
+	struct ceph_client_metric *cm = &fsc->mdsc->metric;
+	struct ceph_metric *m;
+	s64 total;
+	u64 sum, avg, min, max;
+	int i;
+
 	seq_printf(s, "item          total       avg_sz(bytes)   min_sz(bytes)   max_sz(bytes)  total_sz(bytes)\n");
 	seq_printf(s, "----------------------------------------------------------------------------------------\n");
 
-	spin_lock(&m->read_metric_lock);
-	total = m->total_reads;
-	sum_sz = m->read_size_sum;
-	avg_sz = total > 0 ? DIV64_U64_ROUND_CLOSEST(sum_sz, total) : 0;
-	min_sz = m->read_size_min;
-	max_sz = m->read_size_max;
-	spin_unlock(&m->read_metric_lock);
-	CEPH_SZ_METRIC_SHOW("read", total, avg_sz, min_sz, max_sz, sum_sz);
-
-	spin_lock(&m->write_metric_lock);
-	total = m->total_writes;
-	sum_sz = m->write_size_sum;
-	avg_sz = total > 0 ? DIV64_U64_ROUND_CLOSEST(sum_sz, total) : 0;
-	min_sz = m->write_size_min;
-	max_sz = m->write_size_max;
-	spin_unlock(&m->write_metric_lock);
-	CEPH_SZ_METRIC_SHOW("write", total, avg_sz, min_sz, max_sz, sum_sz);
-
-	seq_printf(s, "\n");
+	for (i = 0; i < METRIC_MAX; i++) {
+		/* skip 'metadata' as it doesn't use the size metric */
+		if (i == METRIC_METADATA)
+			continue;
+		m = &cm->metric[i];
+		spin_lock(&m->lock);
+		total = m->total;
+		sum = m->size_sum;
+		avg = total > 0 ? DIV64_U64_ROUND_CLOSEST(sum, total) : 0;
+		min = m->size_min;
+		max = m->size_max;
+		spin_unlock(&m->lock);
+		CEPH_SZ_METRIC_SHOW(metric_str[i], total, avg, min, max, sum);
+	}
+
+	return 0;
+}
+
+static int metrics_caps_show(struct seq_file *s, void *p)
+{
+	struct ceph_fs_client *fsc = s->private;
+	struct ceph_client_metric *m = &fsc->mdsc->metric;
+	int nr_caps = 0;
+
 	seq_printf(s, "item          total           miss            hit\n");
 	seq_printf(s, "-------------------------------------------------\n");
 
@@ -350,8 +361,11 @@ DEFINE_SHOW_ATTRIBUTE(mdsmap);
 DEFINE_SHOW_ATTRIBUTE(mdsc);
 DEFINE_SHOW_ATTRIBUTE(caps);
 DEFINE_SHOW_ATTRIBUTE(mds_sessions);
-DEFINE_SHOW_ATTRIBUTE(metric);
 DEFINE_SHOW_ATTRIBUTE(status);
+DEFINE_SHOW_ATTRIBUTE(metrics_file);
+DEFINE_SHOW_ATTRIBUTE(metrics_latency);
+DEFINE_SHOW_ATTRIBUTE(metrics_size);
+DEFINE_SHOW_ATTRIBUTE(metrics_caps);
 
 
 /*
@@ -385,8 +399,9 @@ void ceph_fs_debugfs_cleanup(struct ceph_fs_client *fsc)
 	debugfs_remove(fsc->debugfs_mdsmap);
 	debugfs_remove(fsc->debugfs_mds_sessions);
 	debugfs_remove(fsc->debugfs_caps);
-	debugfs_remove(fsc->debugfs_metric);
+	debugfs_remove(fsc->debugfs_status);
 	debugfs_remove(fsc->debugfs_mdsc);
+	debugfs_remove_recursive(fsc->debugfs_metrics_dir);
 }
 
 void ceph_fs_debugfs_init(struct ceph_fs_client *fsc)
@@ -426,12 +441,6 @@ void ceph_fs_debugfs_init(struct ceph_fs_client *fsc)
 						fsc,
 						&mdsc_fops);
 
-	fsc->debugfs_metric = debugfs_create_file("metrics",
-						  0400,
-						  fsc->client->debugfs_dir,
-						  fsc,
-						  &metric_fops);
-
 	fsc->debugfs_caps = debugfs_create_file("caps",
 						0400,
 						fsc->client->debugfs_dir,
@@ -443,6 +452,18 @@ void ceph_fs_debugfs_init(struct ceph_fs_client *fsc)
 						  fsc->client->debugfs_dir,
 						  fsc,
 						  &status_fops);
+
+	fsc->debugfs_metrics_dir = debugfs_create_dir("metrics",
+						      fsc->client->debugfs_dir);
+
+	debugfs_create_file("file", 0400, fsc->debugfs_metrics_dir, fsc,
+			    &metrics_file_fops);
+	debugfs_create_file("latency", 0400, fsc->debugfs_metrics_dir, fsc,
+			    &metrics_latency_fops);
+	debugfs_create_file("size", 0400, fsc->debugfs_metrics_dir, fsc,
+			    &metrics_size_fops);
+	debugfs_create_file("caps", 0400, fsc->debugfs_metrics_dir, fsc,
+			    &metrics_caps_fops);
 }
 
 
diff --git a/fs/ceph/export.c b/fs/ceph/export.c
index 1d65934c1262..e0fa66ac8b9f 100644
--- a/fs/ceph/export.c
+++ b/fs/ceph/export.c
@@ -157,6 +157,11 @@ static struct inode *__lookup_inode(struct super_block *sb, u64 ino)
 		ceph_mdsc_put_request(req);
 		if (!inode)
 			return err < 0 ? ERR_PTR(err) : ERR_PTR(-ESTALE);
+	} else {
+		if (ceph_inode_is_shutdown(inode)) {
+			iput(inode);
+			return ERR_PTR(-ESTALE);
+		}
 	}
 	return inode;
 }
@@ -223,8 +228,13 @@ static struct dentry *__snapfh_to_dentry(struct super_block *sb,
 		return ERR_PTR(-ESTALE);
 
 	inode = ceph_find_inode(sb, vino);
-	if (inode)
+	if (inode) {
+		if (ceph_inode_is_shutdown(inode)) {
+			iput(inode);
+			return ERR_PTR(-ESTALE);
+		}
 		return d_obtain_alias(inode);
+	}
 
 	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_LOOKUPINO,
 				       USE_ANY_MDS);
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index b129ea551378..c138e8126286 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -525,6 +525,7 @@ static void ceph_async_create_cb(struct ceph_mds_client *mdsc,
 
 	if (result) {
 		struct dentry *dentry = req->r_dentry;
+		struct inode *inode = d_inode(dentry);
 		int pathlen = 0;
 		u64 base = 0;
 		char *path = ceph_mdsc_build_path(req->r_dentry, &pathlen,
@@ -534,7 +535,8 @@ static void ceph_async_create_cb(struct ceph_mds_client *mdsc,
 		if (!d_unhashed(dentry))
 			d_drop(dentry);
 
-		/* FIXME: start returning I/O errors on all accesses? */
+		ceph_inode_shutdown(inode);
+
 		pr_warn("ceph: async create failure path=(%llx)%s result=%d!\n",
 			base, IS_ERR(path) ? "<<bad>>" : path, result);
 		ceph_mdsc_free_path(path, pathlen);
@@ -556,7 +558,7 @@ static void ceph_async_create_cb(struct ceph_mds_client *mdsc,
 		}
 		ceph_kick_flushing_inode_caps(req->r_session, ci);
 		spin_unlock(&ci->i_ceph_lock);
-	} else {
+	} else if (!result) {
 		pr_warn("%s: no req->r_target_inode for 0x%llx\n", __func__,
 			req->r_deleg_ino);
 	}
@@ -603,13 +605,25 @@ static int ceph_finish_async_create(struct inode *dir, struct dentry *dentry,
 	in.cap.realm = cpu_to_le64(ci->i_snap_realm->ino);
 	in.cap.flags = CEPH_CAP_FLAG_AUTH;
 	in.ctime = in.mtime = in.atime = iinfo.btime;
-	in.mode = cpu_to_le32((u32)mode);
 	in.truncate_seq = cpu_to_le32(1);
 	in.truncate_size = cpu_to_le64(-1ULL);
 	in.xattr_version = cpu_to_le64(1);
 	in.uid = cpu_to_le32(from_kuid(&init_user_ns, current_fsuid()));
-	in.gid = cpu_to_le32(from_kgid(&init_user_ns, dir->i_mode & S_ISGID ?
-				dir->i_gid : current_fsgid()));
+	if (dir->i_mode & S_ISGID) {
+		in.gid = cpu_to_le32(from_kgid(&init_user_ns, dir->i_gid));
+
+		/* Directories always inherit the setgid bit. */
+		if (S_ISDIR(mode))
+			mode |= S_ISGID;
+		else if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP) &&
+			 !in_group_p(dir->i_gid) &&
+			 !capable_wrt_inode_uidgid(&init_user_ns, dir, CAP_FSETID))
+			mode &= ~S_ISGID;
+	} else {
+		in.gid = cpu_to_le32(from_kgid(&init_user_ns, current_fsgid()));
+	}
+	in.mode = cpu_to_le32((u32)mode);
+
 	in.nlink = cpu_to_le32(1);
 	in.max_size = cpu_to_le64(lo->stripe_unit);
 
@@ -845,6 +859,7 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *to,
 	ssize_t ret;
 	u64 off = iocb->ki_pos;
 	u64 len = iov_iter_count(to);
+	u64 i_size = i_size_read(inode);
 
 	dout("sync_read on file %p %llu~%u %s\n", file, off, (unsigned)len,
 	     (file->f_flags & O_DIRECT) ? "O_DIRECT" : "");
@@ -868,7 +883,6 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *to,
 		struct page **pages;
 		int num_pages;
 		size_t page_off;
-		u64 i_size;
 		bool more;
 		int idx;
 		size_t left;
@@ -951,11 +965,14 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *to,
 	}
 
 	if (off > iocb->ki_pos) {
-		if (ret >= 0 &&
-		    iov_iter_count(to) > 0 && off >= i_size_read(inode))
+		if (off >= i_size) {
 			*retry_op = CHECK_EOF;
-		ret = off - iocb->ki_pos;
-		iocb->ki_pos = off;
+			ret = i_size - iocb->ki_pos;
+			iocb->ki_pos = i_size;
+		} else {
+			ret = off - iocb->ki_pos;
+			iocb->ki_pos = off;
+		}
 	}
 
 	dout("sync_read result %zd retry_op %d\n", ret, *retry_op);
@@ -1526,6 +1543,9 @@ again:
 	dout("aio_read %p %llx.%llx %llu~%u trying to get caps on %p\n",
 	     inode, ceph_vinop(inode), iocb->ki_pos, (unsigned)len, inode);
 
+	if (ceph_inode_is_shutdown(inode))
+		return -ESTALE;
+
 	if (direct_lock)
 		ceph_start_io_direct(inode);
 	else
@@ -1678,6 +1698,9 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	loff_t pos;
 	loff_t limit = max(i_size_read(inode), fsc->max_file_size);
 
+	if (ceph_inode_is_shutdown(inode))
+		return -ESTALE;
+
 	if (ceph_snap(inode) != CEPH_NOSNAP)
 		return -EROFS;
 
@@ -2200,6 +2223,54 @@ static int is_file_size_ok(struct inode *src_inode, struct inode *dst_inode,
 	return 0;
 }
 
+static struct ceph_osd_request *
+ceph_alloc_copyfrom_request(struct ceph_osd_client *osdc,
+			    u64 src_snapid,
+			    struct ceph_object_id *src_oid,
+			    struct ceph_object_locator *src_oloc,
+			    struct ceph_object_id *dst_oid,
+			    struct ceph_object_locator *dst_oloc,
+			    u32 truncate_seq, u64 truncate_size)
+{
+	struct ceph_osd_request *req;
+	int ret;
+	u32 src_fadvise_flags =
+		CEPH_OSD_OP_FLAG_FADVISE_SEQUENTIAL |
+		CEPH_OSD_OP_FLAG_FADVISE_NOCACHE;
+	u32 dst_fadvise_flags =
+		CEPH_OSD_OP_FLAG_FADVISE_SEQUENTIAL |
+		CEPH_OSD_OP_FLAG_FADVISE_DONTNEED;
+
+	req = ceph_osdc_alloc_request(osdc, NULL, 1, false, GFP_KERNEL);
+	if (!req)
+		return ERR_PTR(-ENOMEM);
+
+	req->r_flags = CEPH_OSD_FLAG_WRITE;
+
+	ceph_oloc_copy(&req->r_t.base_oloc, dst_oloc);
+	ceph_oid_copy(&req->r_t.base_oid, dst_oid);
+
+	ret = osd_req_op_copy_from_init(req, src_snapid, 0,
+					src_oid, src_oloc,
+					src_fadvise_flags,
+					dst_fadvise_flags,
+					truncate_seq,
+					truncate_size,
+					CEPH_OSD_COPY_FROM_FLAG_TRUNCATE_SEQ);
+	if (ret)
+		goto out;
+
+	ret = ceph_osdc_alloc_messages(req, GFP_KERNEL);
+	if (ret)
+		goto out;
+
+	return req;
+
+out:
+	ceph_osdc_put_request(req);
+	return ERR_PTR(ret);
+}
+
 static ssize_t ceph_do_objects_copy(struct ceph_inode_info *src_ci, u64 *src_off,
 				    struct ceph_inode_info *dst_ci, u64 *dst_off,
 				    struct ceph_fs_client *fsc,
@@ -2207,6 +2278,8 @@ static ssize_t ceph_do_objects_copy(struct ceph_inode_info *src_ci, u64 *src_off
 {
 	struct ceph_object_locator src_oloc, dst_oloc;
 	struct ceph_object_id src_oid, dst_oid;
+	struct ceph_osd_client *osdc;
+	struct ceph_osd_request *req;
 	size_t bytes = 0;
 	u64 src_objnum, src_objoff, dst_objnum, dst_objoff;
 	u32 src_objlen, dst_objlen;
@@ -2217,6 +2290,7 @@ static ssize_t ceph_do_objects_copy(struct ceph_inode_info *src_ci, u64 *src_off
 	src_oloc.pool_ns = ceph_try_get_string(src_ci->i_layout.pool_ns);
 	dst_oloc.pool = dst_ci->i_layout.pool_id;
 	dst_oloc.pool_ns = ceph_try_get_string(dst_ci->i_layout.pool_ns);
+	osdc = &fsc->client->osdc;
 
 	while (len >= object_size) {
 		ceph_calc_file_object_mapping(&src_ci->i_layout, *src_off,
@@ -2232,17 +2306,22 @@ static ssize_t ceph_do_objects_copy(struct ceph_inode_info *src_ci, u64 *src_off
 		ceph_oid_printf(&dst_oid, "%llx.%08llx",
 				dst_ci->i_vino.ino, dst_objnum);
 		/* Do an object remote copy */
-		ret = ceph_osdc_copy_from(&fsc->client->osdc,
-					  src_ci->i_vino.snap, 0,
-					  &src_oid, &src_oloc,
-					  CEPH_OSD_OP_FLAG_FADVISE_SEQUENTIAL |
-					  CEPH_OSD_OP_FLAG_FADVISE_NOCACHE,
-					  &dst_oid, &dst_oloc,
-					  CEPH_OSD_OP_FLAG_FADVISE_SEQUENTIAL |
-					  CEPH_OSD_OP_FLAG_FADVISE_DONTNEED,
-					  dst_ci->i_truncate_seq,
-					  dst_ci->i_truncate_size,
-					  CEPH_OSD_COPY_FROM_FLAG_TRUNCATE_SEQ);
+		req = ceph_alloc_copyfrom_request(osdc, src_ci->i_vino.snap,
+						  &src_oid, &src_oloc,
+						  &dst_oid, &dst_oloc,
+						  dst_ci->i_truncate_seq,
+						  dst_ci->i_truncate_size);
+		if (IS_ERR(req))
+			ret = PTR_ERR(req);
+		else {
+			ceph_osdc_start_request(osdc, req, false);
+			ret = ceph_osdc_wait_request(osdc, req);
+			ceph_update_copyfrom_metrics(&fsc->mdsc->metric,
+						     req->r_start_latency,
+						     req->r_end_latency,
+						     object_size, ret);
+			ceph_osdc_put_request(req);
+		}
 		if (ret) {
 			if (ret == -EOPNOTSUPP) {
 				fsc->have_copy_from2 = false;
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 1c7574105478..e3322fcb2e8d 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -1841,15 +1841,14 @@ void ceph_queue_inode_work(struct inode *inode, int work_bit)
 static void ceph_do_invalidate_pages(struct inode *inode)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
 	u32 orig_gen;
 	int check = 0;
 
 	mutex_lock(&ci->i_truncate_mutex);
 
-	if (READ_ONCE(fsc->mount_state) >= CEPH_MOUNT_SHUTDOWN) {
-		pr_warn_ratelimited("invalidate_pages %p %lld forced umount\n",
-				    inode, ceph_ino(inode));
+	if (ceph_inode_is_shutdown(inode)) {
+		pr_warn_ratelimited("%s: inode %llx.%llx is shut down\n",
+				    __func__, ceph_vinop(inode));
 		mapping_set_error(inode->i_mapping, -EIO);
 		truncate_pagecache(inode, 0);
 		mutex_unlock(&ci->i_truncate_mutex);
@@ -1871,7 +1870,8 @@ static void ceph_do_invalidate_pages(struct inode *inode)
 
 	ceph_fscache_invalidate(inode);
 	if (invalidate_inode_pages2(inode->i_mapping) < 0) {
-		pr_err("invalidate_pages %p fails\n", inode);
+		pr_err("invalidate_inode_pages2 %llx.%llx failed\n",
+		       ceph_vinop(inode));
 	}
 
 	spin_lock(&ci->i_ceph_lock);
@@ -2103,12 +2103,14 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr)
 		loff_t isize = i_size_read(inode);
 
 		dout("setattr %p size %lld -> %lld\n", inode, isize, attr->ia_size);
-		if ((issued & CEPH_CAP_FILE_EXCL) && attr->ia_size > isize) {
-			i_size_write(inode, attr->ia_size);
-			inode->i_blocks = calc_inode_blocks(attr->ia_size);
-			ci->i_reported_size = attr->ia_size;
-			dirtied |= CEPH_CAP_FILE_EXCL;
-			ia_valid |= ATTR_MTIME;
+		if ((issued & CEPH_CAP_FILE_EXCL) && attr->ia_size >= isize) {
+			if (attr->ia_size > isize) {
+				i_size_write(inode, attr->ia_size);
+				inode->i_blocks = calc_inode_blocks(attr->ia_size);
+				ci->i_reported_size = attr->ia_size;
+				dirtied |= CEPH_CAP_FILE_EXCL;
+				ia_valid |= ATTR_MTIME;
+			}
 		} else if ((issued & CEPH_CAP_FILE_SHARED) == 0 ||
 			   attr->ia_size != isize) {
 			req->r_args.setattr.size = cpu_to_le64(attr->ia_size);
@@ -2217,6 +2219,9 @@ int ceph_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
 	if (ceph_snap(inode) != CEPH_NOSNAP)
 		return -EROFS;
 
+	if (ceph_inode_is_shutdown(inode))
+		return -ESTALE;
+
 	err = setattr_prepare(&init_user_ns, dentry, attr);
 	if (err != 0)
 		return err;
@@ -2347,6 +2352,9 @@ int ceph_getattr(struct user_namespace *mnt_userns, const struct path *path,
 	u32 valid_mask = STATX_BASIC_STATS;
 	int err = 0;
 
+	if (ceph_inode_is_shutdown(inode))
+		return -ESTALE;
+
 	/* Skip the getattr altogether if we're asked not to sync */
 	if (!(flags & AT_STATX_DONT_SYNC)) {
 		err = ceph_do_getattr(inode,
@@ -2394,3 +2402,27 @@ int ceph_getattr(struct user_namespace *mnt_userns, const struct path *path,
 	stat->result_mask = request_mask & valid_mask;
 	return err;
 }
+
+void ceph_inode_shutdown(struct inode *inode)
+{
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct rb_node *p;
+	int iputs = 0;
+	bool invalidate = false;
+
+	spin_lock(&ci->i_ceph_lock);
+	ci->i_ceph_flags |= CEPH_I_SHUTDOWN;
+	p = rb_first(&ci->i_caps);
+	while (p) {
+		struct ceph_cap *cap = rb_entry(p, struct ceph_cap, ci_node);
+
+		p = rb_next(p);
+		iputs += ceph_purge_inode_cap(inode, cap, &invalidate);
+	}
+	spin_unlock(&ci->i_ceph_lock);
+
+	if (invalidate)
+		ceph_queue_invalidate(inode);
+	while (iputs--)
+		iput(inode);
+}
diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c
index d8c31069fbf2..d1f154aec249 100644
--- a/fs/ceph/locks.c
+++ b/fs/ceph/locks.c
@@ -241,6 +241,9 @@ int ceph_lock(struct file *file, int cmd, struct file_lock *fl)
 	if (!(fl->fl_flags & FL_POSIX))
 		return -ENOLCK;
 
+	if (ceph_inode_is_shutdown(inode))
+		return -ESTALE;
+
 	dout("ceph_lock, fl_owner: %p\n", fl->fl_owner);
 
 	/* set wait bit as appropriate, then make command as Ceph expects it*/
@@ -303,6 +306,9 @@ int ceph_flock(struct file *file, int cmd, struct file_lock *fl)
 	if (!(fl->fl_flags & FL_FLOCK))
 		return -ENOLCK;
 
+	if (ceph_inode_is_shutdown(inode))
+		return -ESTALE;
+
 	dout("ceph_flock, fl_file: %p\n", fl->fl_file);
 
 	spin_lock(&ci->i_ceph_lock);
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index d64413adc0fd..c30eefc0ac19 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -1590,129 +1590,23 @@ out:
 	return ret;
 }
 
-static int remove_capsnaps(struct ceph_mds_client *mdsc, struct inode *inode)
-{
-	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_cap_snap *capsnap;
-	int capsnap_release = 0;
-
-	lockdep_assert_held(&ci->i_ceph_lock);
-
-	dout("removing capsnaps, ci is %p, inode is %p\n", ci, inode);
-
-	while (!list_empty(&ci->i_cap_snaps)) {
-		capsnap = list_first_entry(&ci->i_cap_snaps,
-					   struct ceph_cap_snap, ci_item);
-		__ceph_remove_capsnap(inode, capsnap, NULL, NULL);
-		ceph_put_snap_context(capsnap->context);
-		ceph_put_cap_snap(capsnap);
-		capsnap_release++;
-	}
-	wake_up_all(&ci->i_cap_wq);
-	wake_up_all(&mdsc->cap_flushing_wq);
-	return capsnap_release;
-}
-
 static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap,
 				  void *arg)
 {
-	struct ceph_fs_client *fsc = (struct ceph_fs_client *)arg;
-	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	LIST_HEAD(to_remove);
-	bool dirty_dropped = false;
 	bool invalidate = false;
-	int capsnap_release = 0;
+	int iputs;
 
 	dout("removing cap %p, ci is %p, inode is %p\n",
 	     cap, ci, &ci->vfs_inode);
 	spin_lock(&ci->i_ceph_lock);
-	__ceph_remove_cap(cap, false);
-	if (!ci->i_auth_cap) {
-		struct ceph_cap_flush *cf;
-
-		if (READ_ONCE(fsc->mount_state) >= CEPH_MOUNT_SHUTDOWN) {
-			if (inode->i_data.nrpages > 0)
-				invalidate = true;
-			if (ci->i_wrbuffer_ref > 0)
-				mapping_set_error(&inode->i_data, -EIO);
-		}
-
-		while (!list_empty(&ci->i_cap_flush_list)) {
-			cf = list_first_entry(&ci->i_cap_flush_list,
-					      struct ceph_cap_flush, i_list);
-			list_move(&cf->i_list, &to_remove);
-		}
-
-		spin_lock(&mdsc->cap_dirty_lock);
-
-		list_for_each_entry(cf, &to_remove, i_list)
-			list_del_init(&cf->g_list);
-
-		if (!list_empty(&ci->i_dirty_item)) {
-			pr_warn_ratelimited(
-				" dropping dirty %s state for %p %lld\n",
-				ceph_cap_string(ci->i_dirty_caps),
-				inode, ceph_ino(inode));
-			ci->i_dirty_caps = 0;
-			list_del_init(&ci->i_dirty_item);
-			dirty_dropped = true;
-		}
-		if (!list_empty(&ci->i_flushing_item)) {
-			pr_warn_ratelimited(
-				" dropping dirty+flushing %s state for %p %lld\n",
-				ceph_cap_string(ci->i_flushing_caps),
-				inode, ceph_ino(inode));
-			ci->i_flushing_caps = 0;
-			list_del_init(&ci->i_flushing_item);
-			mdsc->num_cap_flushing--;
-			dirty_dropped = true;
-		}
-		spin_unlock(&mdsc->cap_dirty_lock);
-
-		if (dirty_dropped) {
-			mapping_set_error(inode->i_mapping, -EIO);
-
-			if (ci->i_wrbuffer_ref_head == 0 &&
-			    ci->i_wr_ref == 0 &&
-			    ci->i_dirty_caps == 0 &&
-			    ci->i_flushing_caps == 0) {
-				ceph_put_snap_context(ci->i_head_snapc);
-				ci->i_head_snapc = NULL;
-			}
-		}
-
-		if (atomic_read(&ci->i_filelock_ref) > 0) {
-			/* make further file lock syscall return -EIO */
-			ci->i_ceph_flags |= CEPH_I_ERROR_FILELOCK;
-			pr_warn_ratelimited(" dropping file locks for %p %lld\n",
-					    inode, ceph_ino(inode));
-		}
-
-		if (!ci->i_dirty_caps && ci->i_prealloc_cap_flush) {
-			list_add(&ci->i_prealloc_cap_flush->i_list, &to_remove);
-			ci->i_prealloc_cap_flush = NULL;
-		}
-
-		if (!list_empty(&ci->i_cap_snaps))
-			capsnap_release = remove_capsnaps(mdsc, inode);
-	}
+	iputs = ceph_purge_inode_cap(inode, cap, &invalidate);
 	spin_unlock(&ci->i_ceph_lock);
-	while (!list_empty(&to_remove)) {
-		struct ceph_cap_flush *cf;
-		cf = list_first_entry(&to_remove,
-				      struct ceph_cap_flush, i_list);
-		list_del_init(&cf->i_list);
-		if (!cf->is_capsnap)
-			ceph_free_cap_flush(cf);
-	}
 
 	wake_up_all(&ci->i_cap_wq);
 	if (invalidate)
 		ceph_queue_invalidate(inode);
-	if (dirty_dropped)
-		iput(inode);
-	while (capsnap_release--)
+	while (iputs--)
 		iput(inode);
 	return 0;
 }
@@ -3467,9 +3361,14 @@ static void handle_session(struct ceph_mds_session *session,
 
 	if (msg_version >= 3) {
 		u32 len;
-		/* version >= 2, metadata */
-		if (__decode_session_metadata(&p, end, &blocklisted) < 0)
+		/* version >= 2 and < 5, decode metadata, skip otherwise
+		 * as it's handled via flags.
+		 */
+		if (msg_version >= 5)
+			ceph_decode_skip_map(&p, end, string, string, bad);
+		else if (__decode_session_metadata(&p, end, &blocklisted) < 0)
 			goto bad;
+
 		/* version >= 3, feature bits */
 		ceph_decode_32_safe(&p, end, len, bad);
 		if (len) {
@@ -3478,6 +3377,18 @@ static void handle_session(struct ceph_mds_session *session,
 		}
 	}
 
+	if (msg_version >= 5) {
+		u32 flags;
+		/* version >= 4, struct_v, struct_cv, len, metric_spec */
+	        ceph_decode_skip_n(&p, end, 2 + sizeof(u32) * 2, bad);
+		/* version >= 5, flags   */
+                ceph_decode_32_safe(&p, end, flags, bad);
+		if (flags & CEPH_SESSION_BLOCKLISTED) {
+		        pr_warn("mds%d session blocklisted\n", session->s_mds);
+			blocklisted = true;
+		}
+	}
+
 	mutex_lock(&mdsc->mutex);
 	if (op == CEPH_SESSION_CLOSE) {
 		ceph_get_mds_session(session);
@@ -3772,7 +3683,7 @@ static int reconnect_caps_cb(struct inode *inode, struct ceph_cap *cap,
 	struct ceph_pagelist *pagelist = recon_state->pagelist;
 	struct dentry *dentry;
 	char *path;
-	int pathlen, err;
+	int pathlen = 0, err;
 	u64 pathbase;
 	u64 snap_follows;
 
@@ -3792,7 +3703,6 @@ static int reconnect_caps_cb(struct inode *inode, struct ceph_cap *cap,
 		}
 	} else {
 		path = NULL;
-		pathlen = 0;
 		pathbase = 0;
 	}
 
@@ -5072,7 +4982,8 @@ void ceph_mdsc_handle_fsmap(struct ceph_mds_client *mdsc, struct ceph_msg *msg)
 	return;
 
 bad:
-	pr_err("error decoding fsmap\n");
+	pr_err("error decoding fsmap %d. Shutting down mount.\n", err);
+	ceph_umount_begin(mdsc->fsc->sb);
 err_out:
 	mutex_lock(&mdsc->mutex);
 	mdsc->mdsmap_err = err;
@@ -5139,7 +5050,8 @@ void ceph_mdsc_handle_mdsmap(struct ceph_mds_client *mdsc, struct ceph_msg *msg)
 bad_unlock:
 	mutex_unlock(&mdsc->mutex);
 bad:
-	pr_err("error decoding mdsmap %d\n", err);
+	pr_err("error decoding mdsmap %d. Shutting down mount.\n", err);
+	ceph_umount_begin(mdsc->fsc->sb);
 	return;
 }
 
diff --git a/fs/ceph/mdsmap.c b/fs/ceph/mdsmap.c
index 61d67cbcb367..30387733765d 100644
--- a/fs/ceph/mdsmap.c
+++ b/fs/ceph/mdsmap.c
@@ -263,10 +263,6 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end, bool msgr2)
 				goto nomem;
 			for (j = 0; j < num_export_targets; j++) {
 				target = ceph_decode_32(&pexport_targets);
-				if (target >= m->possible_max_rank) {
-					err = -EIO;
-					goto corrupt;
-				}
 				info->export_targets[j] = target;
 			}
 		} else {
diff --git a/fs/ceph/metric.c b/fs/ceph/metric.c
index 04d5df29bbbf..c57699d8408d 100644
--- a/fs/ceph/metric.c
+++ b/fs/ceph/metric.c
@@ -62,7 +62,7 @@ static bool ceph_mdsc_send_metrics(struct ceph_mds_client *mdsc,
 	read->header.ver = 1;
 	read->header.compat = 1;
 	read->header.data_len = cpu_to_le32(sizeof(*read) - header_len);
-	sum = m->read_latency_sum;
+	sum = m->metric[METRIC_READ].latency_sum;
 	jiffies_to_timespec64(sum, &ts);
 	read->sec = cpu_to_le32(ts.tv_sec);
 	read->nsec = cpu_to_le32(ts.tv_nsec);
@@ -74,7 +74,7 @@ static bool ceph_mdsc_send_metrics(struct ceph_mds_client *mdsc,
 	write->header.ver = 1;
 	write->header.compat = 1;
 	write->header.data_len = cpu_to_le32(sizeof(*write) - header_len);
-	sum = m->write_latency_sum;
+	sum = m->metric[METRIC_WRITE].latency_sum;
 	jiffies_to_timespec64(sum, &ts);
 	write->sec = cpu_to_le32(ts.tv_sec);
 	write->nsec = cpu_to_le32(ts.tv_nsec);
@@ -86,7 +86,7 @@ static bool ceph_mdsc_send_metrics(struct ceph_mds_client *mdsc,
 	meta->header.ver = 1;
 	meta->header.compat = 1;
 	meta->header.data_len = cpu_to_le32(sizeof(*meta) - header_len);
-	sum = m->metadata_latency_sum;
+	sum = m->metric[METRIC_METADATA].latency_sum;
 	jiffies_to_timespec64(sum, &ts);
 	meta->sec = cpu_to_le32(ts.tv_sec);
 	meta->nsec = cpu_to_le32(ts.tv_nsec);
@@ -141,8 +141,8 @@ static bool ceph_mdsc_send_metrics(struct ceph_mds_client *mdsc,
 	rsize->header.ver = 1;
 	rsize->header.compat = 1;
 	rsize->header.data_len = cpu_to_le32(sizeof(*rsize) - header_len);
-	rsize->total_ops = cpu_to_le64(m->total_reads);
-	rsize->total_size = cpu_to_le64(m->read_size_sum);
+	rsize->total_ops = cpu_to_le64(m->metric[METRIC_READ].total);
+	rsize->total_size = cpu_to_le64(m->metric[METRIC_READ].size_sum);
 	items++;
 
 	/* encode the write io size metric */
@@ -151,8 +151,8 @@ static bool ceph_mdsc_send_metrics(struct ceph_mds_client *mdsc,
 	wsize->header.ver = 1;
 	wsize->header.compat = 1;
 	wsize->header.data_len = cpu_to_le32(sizeof(*wsize) - header_len);
-	wsize->total_ops = cpu_to_le64(m->total_writes);
-	wsize->total_size = cpu_to_le64(m->write_size_sum);
+	wsize->total_ops = cpu_to_le64(m->metric[METRIC_WRITE].total);
+	wsize->total_size = cpu_to_le64(m->metric[METRIC_WRITE].size_sum);
 	items++;
 
 	put_unaligned_le32(items, &head->num);
@@ -220,7 +220,8 @@ static void metric_delayed_work(struct work_struct *work)
 
 int ceph_metric_init(struct ceph_client_metric *m)
 {
-	int ret;
+	struct ceph_metric *metric;
+	int ret, i;
 
 	if (!m)
 		return -EINVAL;
@@ -243,32 +244,18 @@ int ceph_metric_init(struct ceph_client_metric *m)
 	if (ret)
 		goto err_i_caps_mis;
 
-	spin_lock_init(&m->read_metric_lock);
-	m->read_latency_sq_sum = 0;
-	m->read_latency_min = KTIME_MAX;
-	m->read_latency_max = 0;
-	m->total_reads = 0;
-	m->read_latency_sum = 0;
-	m->read_size_min = U64_MAX;
-	m->read_size_max = 0;
-	m->read_size_sum = 0;
-
-	spin_lock_init(&m->write_metric_lock);
-	m->write_latency_sq_sum = 0;
-	m->write_latency_min = KTIME_MAX;
-	m->write_latency_max = 0;
-	m->total_writes = 0;
-	m->write_latency_sum = 0;
-	m->write_size_min = U64_MAX;
-	m->write_size_max = 0;
-	m->write_size_sum = 0;
-
-	spin_lock_init(&m->metadata_metric_lock);
-	m->metadata_latency_sq_sum = 0;
-	m->metadata_latency_min = KTIME_MAX;
-	m->metadata_latency_max = 0;
-	m->total_metadatas = 0;
-	m->metadata_latency_sum = 0;
+	for (i = 0; i < METRIC_MAX; i++) {
+		metric = &m->metric[i];
+		spin_lock_init(&metric->lock);
+		metric->size_sum = 0;
+		metric->size_min = U64_MAX;
+		metric->size_max = 0;
+		metric->total = 0;
+		metric->latency_sum = 0;
+		metric->latency_sq_sum = 0;
+		metric->latency_min = KTIME_MAX;
+		metric->latency_max = 0;
+	}
 
 	atomic64_set(&m->opened_files, 0);
 	ret = percpu_counter_init(&m->opened_inodes, 0, GFP_KERNEL);
@@ -338,9 +325,9 @@ static inline void __update_stdev(ktime_t total, ktime_t lsum,
 	*sq_sump += sq;
 }
 
-void ceph_update_read_metrics(struct ceph_client_metric *m,
-			      ktime_t r_start, ktime_t r_end,
-			      unsigned int size, int rc)
+void ceph_update_metrics(struct ceph_metric *m,
+			 ktime_t r_start, ktime_t r_end,
+			 unsigned int size, int rc)
 {
 	ktime_t lat = ktime_sub(r_end, r_start);
 	ktime_t total;
@@ -348,63 +335,12 @@ void ceph_update_read_metrics(struct ceph_client_metric *m,
 	if (unlikely(rc < 0 && rc != -ENOENT && rc != -ETIMEDOUT))
 		return;
 
-	spin_lock(&m->read_metric_lock);
-	total = ++m->total_reads;
-	m->read_size_sum += size;
-	m->read_latency_sum += lat;
-	METRIC_UPDATE_MIN_MAX(m->read_size_min,
-			      m->read_size_max,
-			      size);
-	METRIC_UPDATE_MIN_MAX(m->read_latency_min,
-			      m->read_latency_max,
-			      lat);
-	__update_stdev(total, m->read_latency_sum,
-		       &m->read_latency_sq_sum, lat);
-	spin_unlock(&m->read_metric_lock);
-}
-
-void ceph_update_write_metrics(struct ceph_client_metric *m,
-			       ktime_t r_start, ktime_t r_end,
-			       unsigned int size, int rc)
-{
-	ktime_t lat = ktime_sub(r_end, r_start);
-	ktime_t total;
-
-	if (unlikely(rc && rc != -ETIMEDOUT))
-		return;
-
-	spin_lock(&m->write_metric_lock);
-	total = ++m->total_writes;
-	m->write_size_sum += size;
-	m->write_latency_sum += lat;
-	METRIC_UPDATE_MIN_MAX(m->write_size_min,
-			      m->write_size_max,
-			      size);
-	METRIC_UPDATE_MIN_MAX(m->write_latency_min,
-			      m->write_latency_max,
-			      lat);
-	__update_stdev(total, m->write_latency_sum,
-		       &m->write_latency_sq_sum, lat);
-	spin_unlock(&m->write_metric_lock);
-}
-
-void ceph_update_metadata_metrics(struct ceph_client_metric *m,
-				  ktime_t r_start, ktime_t r_end,
-				  int rc)
-{
-	ktime_t lat = ktime_sub(r_end, r_start);
-	ktime_t total;
-
-	if (unlikely(rc && rc != -ENOENT))
-		return;
-
-	spin_lock(&m->metadata_metric_lock);
-	total = ++m->total_metadatas;
-	m->metadata_latency_sum += lat;
-	METRIC_UPDATE_MIN_MAX(m->metadata_latency_min,
-			      m->metadata_latency_max,
-			      lat);
-	__update_stdev(total, m->metadata_latency_sum,
-		       &m->metadata_latency_sq_sum, lat);
-	spin_unlock(&m->metadata_metric_lock);
+	spin_lock(&m->lock);
+	total = ++m->total;
+	m->size_sum += size;
+	METRIC_UPDATE_MIN_MAX(m->size_min, m->size_max, size);
+	m->latency_sum += lat;
+	METRIC_UPDATE_MIN_MAX(m->latency_min, m->latency_max, lat);
+	__update_stdev(total, m->latency_sum, &m->latency_sq_sum, lat);
+	spin_unlock(&m->lock);
 }
diff --git a/fs/ceph/metric.h b/fs/ceph/metric.h
index 0133955a3c6a..bb45608181e7 100644
--- a/fs/ceph/metric.h
+++ b/fs/ceph/metric.h
@@ -125,6 +125,26 @@ struct ceph_metric_head {
 	__le32 num;	/* the number of metrics that will be sent */
 } __packed;
 
+enum metric_type {
+	METRIC_READ,
+	METRIC_WRITE,
+	METRIC_METADATA,
+	METRIC_COPYFROM,
+	METRIC_MAX
+};
+
+struct ceph_metric {
+	spinlock_t lock;
+	u64 total;
+	u64 size_sum;
+	u64 size_min;
+	u64 size_max;
+	ktime_t latency_sum;
+	ktime_t latency_sq_sum;
+	ktime_t latency_min;
+	ktime_t latency_max;
+};
+
 /* This is the global metrics */
 struct ceph_client_metric {
 	atomic64_t            total_dentries;
@@ -135,32 +155,7 @@ struct ceph_client_metric {
 	struct percpu_counter i_caps_hit;
 	struct percpu_counter i_caps_mis;
 
-	spinlock_t read_metric_lock;
-	u64 total_reads;
-	u64 read_size_sum;
-	u64 read_size_min;
-	u64 read_size_max;
-	ktime_t read_latency_sum;
-	ktime_t read_latency_sq_sum;
-	ktime_t read_latency_min;
-	ktime_t read_latency_max;
-
-	spinlock_t write_metric_lock;
-	u64 total_writes;
-	u64 write_size_sum;
-	u64 write_size_min;
-	u64 write_size_max;
-	ktime_t write_latency_sum;
-	ktime_t write_latency_sq_sum;
-	ktime_t write_latency_min;
-	ktime_t write_latency_max;
-
-	spinlock_t metadata_metric_lock;
-	u64 total_metadatas;
-	ktime_t metadata_latency_sum;
-	ktime_t metadata_latency_sq_sum;
-	ktime_t metadata_latency_min;
-	ktime_t metadata_latency_max;
+	struct ceph_metric metric[METRIC_MAX];
 
 	/* The total number of directories and files that are opened */
 	atomic64_t opened_files;
@@ -195,13 +190,36 @@ static inline void ceph_update_cap_mis(struct ceph_client_metric *m)
 	percpu_counter_inc(&m->i_caps_mis);
 }
 
-extern void ceph_update_read_metrics(struct ceph_client_metric *m,
-				     ktime_t r_start, ktime_t r_end,
-				     unsigned int size, int rc);
-extern void ceph_update_write_metrics(struct ceph_client_metric *m,
-				      ktime_t r_start, ktime_t r_end,
-				      unsigned int size, int rc);
-extern void ceph_update_metadata_metrics(struct ceph_client_metric *m,
-				         ktime_t r_start, ktime_t r_end,
-					 int rc);
+extern void ceph_update_metrics(struct ceph_metric *m,
+				ktime_t r_start, ktime_t r_end,
+				unsigned int size, int rc);
+
+static inline void ceph_update_read_metrics(struct ceph_client_metric *m,
+					    ktime_t r_start, ktime_t r_end,
+					    unsigned int size, int rc)
+{
+	ceph_update_metrics(&m->metric[METRIC_READ],
+			    r_start, r_end, size, rc);
+}
+static inline void ceph_update_write_metrics(struct ceph_client_metric *m,
+					     ktime_t r_start, ktime_t r_end,
+					     unsigned int size, int rc)
+{
+	ceph_update_metrics(&m->metric[METRIC_WRITE],
+			    r_start, r_end, size, rc);
+}
+static inline void ceph_update_metadata_metrics(struct ceph_client_metric *m,
+						ktime_t r_start, ktime_t r_end,
+						int rc)
+{
+	ceph_update_metrics(&m->metric[METRIC_METADATA],
+			    r_start, r_end, 0, rc);
+}
+static inline void ceph_update_copyfrom_metrics(struct ceph_client_metric *m,
+						ktime_t r_start, ktime_t r_end,
+						unsigned int size, int rc)
+{
+	ceph_update_metrics(&m->metric[METRIC_COPYFROM],
+			    r_start, r_end, size, rc);
+}
 #endif /* _FS_CEPH_MDS_METRIC_H */
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index fd8742bae847..bab61232dc5a 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -52,8 +52,7 @@ static int ceph_statfs(struct dentry *dentry, struct kstatfs *buf)
 	struct ceph_fs_client *fsc = ceph_inode_to_client(d_inode(dentry));
 	struct ceph_mon_client *monc = &fsc->client->monc;
 	struct ceph_statfs st;
-	u64 fsid;
-	int err;
+	int i, err;
 	u64 data_pool;
 
 	if (fsc->mdsc->mdsmap->m_num_data_pg_pools == 1) {
@@ -99,12 +98,14 @@ static int ceph_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_namelen = NAME_MAX;
 
 	/* Must convert the fsid, for consistent values across arches */
+	buf->f_fsid.val[0] = 0;
 	mutex_lock(&monc->mutex);
-	fsid = le64_to_cpu(*(__le64 *)(&monc->monmap->fsid)) ^
-	       le64_to_cpu(*((__le64 *)&monc->monmap->fsid + 1));
+	for (i = 0 ; i < sizeof(monc->monmap->fsid) / sizeof(__le32) ; ++i)
+		buf->f_fsid.val[0] ^= le32_to_cpu(((__le32 *)&monc->monmap->fsid)[i]);
 	mutex_unlock(&monc->mutex);
 
-	buf->f_fsid = u64_to_fsid(fsid);
+	/* fold the fs_cluster_id into the upper bits */
+	buf->f_fsid.val[1] = monc->fs_cluster_id;
 
 	return 0;
 }
@@ -577,8 +578,8 @@ static int ceph_show_options(struct seq_file *m, struct dentry *root)
 	if (fsopt->flags & CEPH_MOUNT_OPT_CLEANRECOVER)
 		seq_show_option(m, "recover_session", "clean");
 
-	if (fsopt->flags & CEPH_MOUNT_OPT_ASYNC_DIROPS)
-		seq_puts(m, ",nowsync");
+	if (!(fsopt->flags & CEPH_MOUNT_OPT_ASYNC_DIROPS))
+		seq_puts(m, ",wsync");
 
 	if (fsopt->wsize != CEPH_MAX_WRITE_SIZE)
 		seq_printf(m, ",wsize=%u", fsopt->wsize);
@@ -842,7 +843,7 @@ static void __ceph_umount_begin(struct ceph_fs_client *fsc)
  * ceph_umount_begin - initiate forced umount.  Tear down the
  * mount, skipping steps that may hang while waiting for server(s).
  */
-static void ceph_umount_begin(struct super_block *sb)
+void ceph_umount_begin(struct super_block *sb)
 {
 	struct ceph_fs_client *fsc = ceph_sb_to_client(sb);
 
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 14f951cd5b61..ac331aa07cfa 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -48,7 +48,8 @@
 
 #define CEPH_MOUNT_OPT_DEFAULT			\
 	(CEPH_MOUNT_OPT_DCACHE |		\
-	 CEPH_MOUNT_OPT_NOCOPYFROM)
+	 CEPH_MOUNT_OPT_NOCOPYFROM |		\
+	 CEPH_MOUNT_OPT_ASYNC_DIROPS)
 
 #define ceph_set_mount_opt(fsc, opt) \
 	(fsc)->mount_options->flags |= CEPH_MOUNT_OPT_##opt
@@ -128,9 +129,9 @@ struct ceph_fs_client {
 	struct dentry *debugfs_congestion_kb;
 	struct dentry *debugfs_bdi;
 	struct dentry *debugfs_mdsc, *debugfs_mdsmap;
-	struct dentry *debugfs_metric;
 	struct dentry *debugfs_status;
 	struct dentry *debugfs_mds_sessions;
+	struct dentry *debugfs_metrics_dir;
 #endif
 
 #ifdef CONFIG_CEPH_FSCACHE
@@ -580,6 +581,7 @@ static inline struct inode *ceph_find_inode(struct super_block *sb,
 #define CEPH_I_ODIRECT		(1 << 11) /* inode in direct I/O mode */
 #define CEPH_ASYNC_CREATE_BIT	(12)	  /* async create in flight for this */
 #define CEPH_I_ASYNC_CREATE	(1 << CEPH_ASYNC_CREATE_BIT)
+#define CEPH_I_SHUTDOWN		(1 << 13) /* inode is no longer usable */
 
 /*
  * Masks of ceph inode work.
@@ -939,6 +941,7 @@ extern void ceph_put_snapid_map(struct ceph_mds_client* mdsc,
 				struct ceph_snapid_map *sm);
 extern void ceph_trim_snapid_map(struct ceph_mds_client *mdsc);
 extern void ceph_cleanup_snapid_map(struct ceph_mds_client *mdsc);
+void ceph_umount_begin(struct super_block *sb);
 
 
 /*
@@ -1027,6 +1030,16 @@ extern int ceph_setattr(struct user_namespace *mnt_userns,
 extern int ceph_getattr(struct user_namespace *mnt_userns,
 			const struct path *path, struct kstat *stat,
 			u32 request_mask, unsigned int flags);
+void ceph_inode_shutdown(struct inode *inode);
+
+static inline bool ceph_inode_is_shutdown(struct inode *inode)
+{
+	unsigned long flags = READ_ONCE(ceph_inode(inode)->i_ceph_flags);
+	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
+	int state = READ_ONCE(fsc->mount_state);
+
+	return (flags & CEPH_I_SHUTDOWN) || state >= CEPH_MOUNT_SHUTDOWN;
+}
 
 /* xattr.c */
 int __ceph_setxattr(struct inode *, const char *, const void *, size_t, int);
@@ -1198,6 +1211,7 @@ extern int ceph_mmap(struct file *file, struct vm_area_struct *vma);
 extern int ceph_uninline_data(struct file *filp, struct page *locked_page);
 extern int ceph_pool_perm_check(struct inode *inode, int need);
 extern void ceph_pool_perm_destroy(struct ceph_mds_client* mdsc);
+int ceph_purge_inode_cap(struct inode *inode, struct ceph_cap *cap, bool *invalidate);
 
 /* file.c */
 extern const struct file_operations ceph_file_fops;
diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c
index de2c12bcfa4b..d282caf9f037 100644
--- a/fs/cifs/cifs_debug.c
+++ b/fs/cifs/cifs_debug.c
@@ -271,7 +271,8 @@ static int cifs_debug_data_proc_show(struct seq_file *m, void *v)
 	c = 0;
 	spin_lock(&cifs_tcp_ses_lock);
 	list_for_each_entry(server, &cifs_tcp_ses_list, tcp_ses_list) {
-		if (server->is_channel)
+		/* channel info will be printed as a part of sessions below */
+		if (CIFS_SERVER_IS_CHAN(server))
 			continue;
 
 		c++;
@@ -358,6 +359,8 @@ skip_rdma:
 			seq_printf(m, " signed");
 		if (server->posix_ext_supported)
 			seq_printf(m, " posix");
+		if (server->nosharesock)
+			seq_printf(m, " nosharesock");
 
 		if (server->rdma)
 			seq_printf(m, "\nRDMA ");
@@ -412,12 +415,14 @@ skip_rdma:
 				   from_kuid(&init_user_ns, ses->linux_uid),
 				   from_kuid(&init_user_ns, ses->cred_uid));
 
+			spin_lock(&ses->chan_lock);
 			if (ses->chan_count > 1) {
 				seq_printf(m, "\n\n\tExtra Channels: %zu ",
 					   ses->chan_count-1);
 				for (j = 1; j < ses->chan_count; j++)
 					cifs_dump_channel(m, j, &ses->chans[j]);
 			}
+			spin_unlock(&ses->chan_lock);
 
 			seq_puts(m, "\n\n\tShares: ");
 			j = 0;
diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c
index 007427ba75e5..b0864da9ef43 100644
--- a/fs/cifs/cifs_dfs_ref.c
+++ b/fs/cifs/cifs_dfs_ref.c
@@ -307,12 +307,8 @@ static struct vfsmount *cifs_dfs_do_mount(struct dentry *mntpt,
 static struct vfsmount *cifs_dfs_do_automount(struct dentry *mntpt)
 {
 	struct cifs_sb_info *cifs_sb;
-	struct cifs_ses *ses;
-	struct cifs_tcon *tcon;
 	void *page;
-	char *full_path, *root_path;
-	unsigned int xid;
-	int rc;
+	char *full_path;
 	struct vfsmount *mnt;
 
 	cifs_dbg(FYI, "in %s\n", __func__);
@@ -324,8 +320,6 @@ static struct vfsmount *cifs_dfs_do_automount(struct dentry *mntpt)
 	 * the double backslashes usually used in the UNC. This function
 	 * gives us the latter, so we must adjust the result.
 	 */
-	mnt = ERR_PTR(-ENOMEM);
-
 	cifs_sb = CIFS_SB(mntpt->d_sb);
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_DFS) {
 		mnt = ERR_PTR(-EREMOTE);
@@ -341,60 +335,11 @@ static struct vfsmount *cifs_dfs_do_automount(struct dentry *mntpt)
 	}
 
 	convert_delimiter(full_path, '\\');
-
 	cifs_dbg(FYI, "%s: full_path: %s\n", __func__, full_path);
 
-	if (!cifs_sb_master_tlink(cifs_sb)) {
-		cifs_dbg(FYI, "%s: master tlink is NULL\n", __func__);
-		goto free_full_path;
-	}
-
-	tcon = cifs_sb_master_tcon(cifs_sb);
-	if (!tcon) {
-		cifs_dbg(FYI, "%s: master tcon is NULL\n", __func__);
-		goto free_full_path;
-	}
-
-	root_path = kstrdup(tcon->treeName, GFP_KERNEL);
-	if (!root_path) {
-		mnt = ERR_PTR(-ENOMEM);
-		goto free_full_path;
-	}
-	cifs_dbg(FYI, "%s: root path: %s\n", __func__, root_path);
-
-	ses = tcon->ses;
-	xid = get_xid();
-
-	/*
-	 * If DFS root has been expired, then unconditionally fetch it again to
-	 * refresh DFS referral cache.
-	 */
-	rc = dfs_cache_find(xid, ses, cifs_sb->local_nls, cifs_remap(cifs_sb),
-			    root_path + 1, NULL, NULL);
-	if (!rc) {
-		rc = dfs_cache_find(xid, ses, cifs_sb->local_nls,
-				    cifs_remap(cifs_sb), full_path + 1,
-				    NULL, NULL);
-	}
-
-	free_xid(xid);
-
-	if (rc) {
-		mnt = ERR_PTR(rc);
-		goto free_root_path;
-	}
-	/*
-	 * OK - we were able to get and cache a referral for @full_path.
-	 *
-	 * Now, pass it down to cifs_mount() and it will retry every available
-	 * node server in case of failures - no need to do it here.
-	 */
 	mnt = cifs_dfs_do_mount(mntpt, cifs_sb, full_path);
-	cifs_dbg(FYI, "%s: cifs_dfs_do_mount:%s , mnt:%p\n", __func__,
-		 full_path + 1, mnt);
+	cifs_dbg(FYI, "%s: cifs_dfs_do_mount:%s , mnt:%p\n", __func__, full_path + 1, mnt);
 
-free_root_path:
-	kfree(root_path);
 free_full_path:
 	free_dentry_path(page);
 cdda_exit:
diff --git a/fs/cifs/cifs_fs_sb.h b/fs/cifs/cifs_fs_sb.h
index f97407520ea1..013a4bd65280 100644
--- a/fs/cifs/cifs_fs_sb.h
+++ b/fs/cifs/cifs_fs_sb.h
@@ -61,11 +61,6 @@ struct cifs_sb_info {
 	/* only used when CIFS_MOUNT_USE_PREFIX_PATH is set */
 	char *prepath;
 
-	/*
-	 * Canonical DFS path initially provided by the mount call. We might connect to something
-	 * different via DFS but we want to keep it to do failover properly.
-	 */
-	char *origin_fullpath; /* \\HOST\SHARE\[OPTIONAL PATH] */
 	/* randomly generated 128-bit number for indexing dfs mount groups in referral cache */
 	uuid_t dfs_mount_id;
 	/*
diff --git a/fs/cifs/cifs_swn.c b/fs/cifs/cifs_swn.c
index 12bde7bfda86..23a1ed2fb769 100644
--- a/fs/cifs/cifs_swn.c
+++ b/fs/cifs/cifs_swn.c
@@ -393,26 +393,14 @@ static void cifs_put_swn_reg(struct cifs_swn_reg *swnreg)
 
 static int cifs_swn_resource_state_changed(struct cifs_swn_reg *swnreg, const char *name, int state)
 {
-	int i;
-
 	switch (state) {
 	case CIFS_SWN_RESOURCE_STATE_UNAVAILABLE:
 		cifs_dbg(FYI, "%s: resource name '%s' become unavailable\n", __func__, name);
-		for (i = 0; i < swnreg->tcon->ses->chan_count; i++) {
-			spin_lock(&GlobalMid_Lock);
-			if (swnreg->tcon->ses->chans[i].server->tcpStatus != CifsExiting)
-				swnreg->tcon->ses->chans[i].server->tcpStatus = CifsNeedReconnect;
-			spin_unlock(&GlobalMid_Lock);
-		}
+		cifs_ses_mark_for_reconnect(swnreg->tcon->ses);
 		break;
 	case CIFS_SWN_RESOURCE_STATE_AVAILABLE:
 		cifs_dbg(FYI, "%s: resource name '%s' become available\n", __func__, name);
-		for (i = 0; i < swnreg->tcon->ses->chan_count; i++) {
-			spin_lock(&GlobalMid_Lock);
-			if (swnreg->tcon->ses->chans[i].server->tcpStatus != CifsExiting)
-				swnreg->tcon->ses->chans[i].server->tcpStatus = CifsNeedReconnect;
-			spin_unlock(&GlobalMid_Lock);
-		}
+		cifs_ses_mark_for_reconnect(swnreg->tcon->ses);
 		break;
 	case CIFS_SWN_RESOURCE_STATE_UNKNOWN:
 		cifs_dbg(FYI, "%s: resource name '%s' changed to unknown state\n", __func__, name);
diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h
index b50da1901ebd..9e5d9e192ef0 100644
--- a/fs/cifs/cifsfs.h
+++ b/fs/cifs/cifsfs.h
@@ -152,5 +152,5 @@ extern struct dentry *cifs_smb3_do_mount(struct file_system_type *fs_type,
 extern const struct export_operations cifs_export_ops;
 #endif /* CONFIG_CIFS_NFSD_EXPORT */
 
-#define CIFS_VERSION   "2.33"
+#define CIFS_VERSION   "2.34"
 #endif				/* _CIFSFS_H */
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index abff31dcd005..be74606724c7 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -15,6 +15,7 @@
 #include <linux/slab.h>
 #include <linux/mempool.h>
 #include <linux/workqueue.h>
+#include <linux/utsname.h>
 #include "cifs_fs_sb.h"
 #include "cifsacl.h"
 #include <crypto/internal/hash.h>
@@ -75,7 +76,8 @@
 #define SMB_ECHO_INTERVAL_MAX 600
 #define SMB_ECHO_INTERVAL_DEFAULT 60
 
-/* dns resolution interval in seconds */
+/* dns resolution intervals in seconds */
+#define SMB_DNS_RESOLVE_INTERVAL_MIN     120
 #define SMB_DNS_RESOLVE_INTERVAL_DEFAULT 600
 
 /* maximum number of PDUs in one compound */
@@ -99,6 +101,8 @@
 #define XATTR_DOS_ATTRIB "user.DOSATTRIB"
 #endif
 
+#define CIFS_MAX_WORKSTATION_LEN  (__NEW_UTS_LEN + 1)  /* reasonable max for client */
+
 /*
  * CIFS vfs client Status information (based on what we know.)
  */
@@ -592,6 +596,7 @@ struct TCP_Server_Info {
 	struct list_head pending_mid_q;
 	bool noblocksnd;		/* use blocking sendmsg */
 	bool noautotune;		/* do not autotune send buf sizes */
+	bool nosharesock;
 	bool tcp_nodelay;
 	unsigned int credits;  /* send no more requests at once */
 	unsigned int max_credits; /* can override large 32000 default at mnt */
@@ -685,13 +690,34 @@ struct TCP_Server_Info {
 	 */
 	int nr_targets;
 	bool noblockcnt; /* use non-blocking connect() */
-	bool is_channel; /* if a session channel */
+
+	/*
+	 * If this is a session channel,
+	 * primary_server holds the ref-counted
+	 * pointer to primary channel connection for the session.
+	 */
+#define CIFS_SERVER_IS_CHAN(server)	(!!(server)->primary_server)
+	struct TCP_Server_Info *primary_server;
+
 #ifdef CONFIG_CIFS_SWN_UPCALL
 	bool use_swn_dstaddr;
 	struct sockaddr_storage swn_dstaddr;
 #endif
 #ifdef CONFIG_CIFS_DFS_UPCALL
 	bool is_dfs_conn; /* if a dfs connection */
+	struct mutex refpath_lock; /* protects leaf_fullpath */
+	/*
+	 * Canonical DFS full paths that were used to chase referrals in mount and reconnect.
+	 *
+	 * origin_fullpath: first or original referral path
+	 * leaf_fullpath: last referral path (might be changed due to nested links in reconnect)
+	 *
+	 * current_fullpath: pointer to either origin_fullpath or leaf_fullpath
+	 * NOTE: cannot be accessed outside cifs_reconnect() and smb2_reconnect()
+	 *
+	 * format: \\HOST\SHARE\[OPTIONAL PATH]
+	 */
+	char *origin_fullpath, *leaf_fullpath, *current_fullpath;
 #endif
 };
 
@@ -908,6 +934,7 @@ struct cifs_ses {
 				   and after mount option parsing we fill it */
 	char *domainName;
 	char *password;
+	char *workstation_name;
 	struct session_key auth_key;
 	struct ntlmssp_auth *ntlmssp; /* ciphertext, flags, server challenge */
 	enum securityEnum sectype; /* what security flavor was specified? */
@@ -933,16 +960,21 @@ struct cifs_ses {
 	 * iface_lock should be taken when accessing any of these fields
 	 */
 	spinlock_t iface_lock;
+	/* ========= begin: protected by iface_lock ======== */
 	struct cifs_server_iface *iface_list;
 	size_t iface_count;
 	unsigned long iface_last_update; /* jiffies */
+	/* ========= end: protected by iface_lock ======== */
 
+	spinlock_t chan_lock;
+	/* ========= begin: protected by chan_lock ======== */
 #define CIFS_MAX_CHANNELS 16
 	struct cifs_chan chans[CIFS_MAX_CHANNELS];
 	struct cifs_chan *binding_chan;
 	size_t chan_count;
 	size_t chan_max;
 	atomic_t chan_seq; /* round robin state */
+	/* ========= end: protected by chan_lock ======== */
 };
 
 /*
@@ -1091,7 +1123,6 @@ struct cifs_tcon {
 	struct cached_fid crfid; /* Cached root fid */
 	/* BB add field for back pointer to sb struct(s)? */
 #ifdef CONFIG_CIFS_DFS_UPCALL
-	char *dfs_path; /* canonical DFS path */
 	struct list_head ulist; /* cache update list */
 #endif
 };
@@ -1942,4 +1973,14 @@ static inline bool is_tcon_dfs(struct cifs_tcon *tcon)
 		tcon->share_flags & (SHI1005_FLAGS_DFS | SHI1005_FLAGS_DFS_ROOT);
 }
 
+static inline bool cifs_is_referral_server(struct cifs_tcon *tcon,
+					   const struct dfs_info3_param *ref)
+{
+	/*
+	 * Check if all targets are capable of handling DFS referrals as per
+	 * MS-DFSC 2.2.4 RESP_GET_DFS_REFERRAL.
+	 */
+	return is_tcon_dfs(tcon) || (ref && (ref->flags & DFSREF_REFERRAL_SERVER));
+}
+
 #endif	/* _CIFS_GLOB_H */
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index d0f85b666662..4f5a3e857df4 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -269,8 +269,9 @@ extern void cifs_close_all_deferred_files(struct cifs_tcon *cifs_tcon);
 
 extern void cifs_close_deferred_file_under_dentry(struct cifs_tcon *cifs_tcon,
 				const char *path);
-
-extern struct TCP_Server_Info *cifs_get_tcp_session(struct smb3_fs_context *ctx);
+extern struct TCP_Server_Info *
+cifs_get_tcp_session(struct smb3_fs_context *ctx,
+		     struct TCP_Server_Info *primary_server);
 extern void cifs_put_tcp_session(struct TCP_Server_Info *server,
 				 int from_reconnect);
 extern void cifs_put_tcon(struct cifs_tcon *tcon);
@@ -598,6 +599,7 @@ int cifs_try_adding_channels(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses)
 bool is_server_using_iface(struct TCP_Server_Info *server,
 			   struct cifs_server_iface *iface);
 bool is_ses_using_iface(struct cifs_ses *ses, struct cifs_server_iface *iface);
+void cifs_ses_mark_for_reconnect(struct cifs_ses *ses);
 
 void extract_unc_hostname(const char *unc, const char **h, size_t *len);
 int copy_path_name(char *dst, const char *src);
@@ -607,7 +609,7 @@ int smb2_parse_query_directory(struct cifs_tcon *tcon, struct kvec *rsp_iov,
 
 struct super_block *cifs_get_tcp_super(struct TCP_Server_Info *server);
 void cifs_put_tcp_super(struct super_block *sb);
-int update_super_prepath(struct cifs_tcon *tcon, char *prefix);
+int cifs_update_super_prepath(struct cifs_sb_info *cifs_sb, char *prefix);
 char *extract_hostname(const char *unc);
 char *extract_sharename(const char *unc);
 
@@ -634,4 +636,7 @@ static inline int cifs_create_options(struct cifs_sb_info *cifs_sb, int options)
 		return options;
 }
 
+struct super_block *cifs_get_tcon_super(struct cifs_tcon *tcon);
+void cifs_put_tcon_super(struct super_block *sb);
+
 #endif			/* _CIFSPROTO_H */
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 0abbff4e4135..1060164b984a 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -61,6 +61,20 @@ extern bool disable_legacy_dialects;
 /* Drop the connection to not overload the server */
 #define NUM_STATUS_IO_TIMEOUT   5
 
+struct mount_ctx {
+	struct cifs_sb_info *cifs_sb;
+	struct smb3_fs_context *fs_ctx;
+	unsigned int xid;
+	struct TCP_Server_Info *server;
+	struct cifs_ses *ses;
+	struct cifs_tcon *tcon;
+#ifdef CONFIG_CIFS_DFS_UPCALL
+	struct cifs_ses *root_ses;
+	uuid_t mount_id;
+	char *origin_fullpath, *leaf_fullpath;
+#endif
+};
+
 static int ip_connect(struct TCP_Server_Info *server);
 static int generic_ip_connect(struct TCP_Server_Info *server);
 static void tlink_rb_insert(struct rb_root *root, struct tcon_link *new_tlink);
@@ -115,7 +129,7 @@ static int reconn_set_ipaddr_from_hostname(struct TCP_Server_Info *server)
 			 * To make sure we don't use the cached entry, retry 1s
 			 * after expiry.
 			 */
-			ttl = (expiry - now + 1);
+			ttl = max_t(unsigned long, expiry - now, SMB_DNS_RESOLVE_INTERVAL_MIN) + 1;
 	}
 	rc = !rc ? -1 : 0;
 
@@ -148,139 +162,38 @@ static void cifs_resolve_server(struct work_struct *work)
 	mutex_unlock(&server->srv_mutex);
 }
 
-#ifdef CONFIG_CIFS_DFS_UPCALL
-/* These functions must be called with server->srv_mutex held */
-static void reconn_set_next_dfs_target(struct TCP_Server_Info *server,
-				       struct cifs_sb_info *cifs_sb,
-				       struct dfs_cache_tgt_list *tgt_list,
-				       struct dfs_cache_tgt_iterator **tgt_it)
-{
-	const char *name;
-	int rc;
-
-	if (!cifs_sb || !cifs_sb->origin_fullpath)
-		return;
-
-	if (!*tgt_it) {
-		*tgt_it = dfs_cache_get_tgt_iterator(tgt_list);
-	} else {
-		*tgt_it = dfs_cache_get_next_tgt(tgt_list, *tgt_it);
-		if (!*tgt_it)
-			*tgt_it = dfs_cache_get_tgt_iterator(tgt_list);
-	}
-
-	cifs_dbg(FYI, "%s: UNC: %s\n", __func__, cifs_sb->origin_fullpath);
-
-	name = dfs_cache_get_tgt_name(*tgt_it);
-
-	kfree(server->hostname);
-
-	server->hostname = extract_hostname(name);
-	if (IS_ERR(server->hostname)) {
-		cifs_dbg(FYI,
-			 "%s: failed to extract hostname from target: %ld\n",
-			 __func__, PTR_ERR(server->hostname));
-		return;
-	}
-
-	rc = reconn_set_ipaddr_from_hostname(server);
-	if (rc) {
-		cifs_dbg(FYI, "%s: failed to resolve hostname: %d\n",
-			 __func__, rc);
-	}
-}
-
-static inline int reconn_setup_dfs_targets(struct cifs_sb_info *cifs_sb,
-					   struct dfs_cache_tgt_list *tl)
-{
-	if (!cifs_sb->origin_fullpath)
-		return -EOPNOTSUPP;
-	return dfs_cache_noreq_find(cifs_sb->origin_fullpath + 1, NULL, tl);
-}
-#endif
-
-/*
- * cifs tcp session reconnection
+/**
+ * Mark all sessions and tcons for reconnect.
  *
- * mark tcp session as reconnecting so temporarily locked
- * mark all smb sessions as reconnecting for tcp session
- * reconnect tcp session
- * wake up waiters on reconnection? - (not needed currently)
+ * @server needs to be previously set to CifsNeedReconnect.
  */
-int
-cifs_reconnect(struct TCP_Server_Info *server)
+static void cifs_mark_tcp_ses_conns_for_reconnect(struct TCP_Server_Info *server)
 {
-	int rc = 0;
-	struct list_head *tmp, *tmp2;
 	struct cifs_ses *ses;
 	struct cifs_tcon *tcon;
-	struct mid_q_entry *mid_entry;
+	struct mid_q_entry *mid, *nmid;
 	struct list_head retry_list;
-#ifdef CONFIG_CIFS_DFS_UPCALL
-	struct super_block *sb = NULL;
-	struct cifs_sb_info *cifs_sb = NULL;
-	struct dfs_cache_tgt_list tgt_list = DFS_CACHE_TGT_LIST_INIT(tgt_list);
-	struct dfs_cache_tgt_iterator *tgt_it = NULL;
-#endif
+	struct TCP_Server_Info *pserver;
 
-	spin_lock(&GlobalMid_Lock);
-	server->nr_targets = 1;
-#ifdef CONFIG_CIFS_DFS_UPCALL
-	spin_unlock(&GlobalMid_Lock);
-	sb = cifs_get_tcp_super(server);
-	if (IS_ERR(sb)) {
-		rc = PTR_ERR(sb);
-		cifs_dbg(FYI, "%s: will not do DFS failover: rc = %d\n",
-			 __func__, rc);
-		sb = NULL;
-	} else {
-		cifs_sb = CIFS_SB(sb);
-		rc = reconn_setup_dfs_targets(cifs_sb, &tgt_list);
-		if (rc) {
-			cifs_sb = NULL;
-			if (rc != -EOPNOTSUPP) {
-				cifs_server_dbg(VFS, "%s: no target servers for DFS failover\n",
-						__func__);
-			}
-		} else {
-			server->nr_targets = dfs_cache_get_nr_tgts(&tgt_list);
-		}
-	}
-	cifs_dbg(FYI, "%s: will retry %d target(s)\n", __func__,
-		 server->nr_targets);
-	spin_lock(&GlobalMid_Lock);
-#endif
-	if (server->tcpStatus == CifsExiting) {
-		/* the demux thread will exit normally
-		next time through the loop */
-		spin_unlock(&GlobalMid_Lock);
-#ifdef CONFIG_CIFS_DFS_UPCALL
-		dfs_cache_free_tgts(&tgt_list);
-		cifs_put_tcp_super(sb);
-#endif
-		wake_up(&server->response_q);
-		return rc;
-	} else
-		server->tcpStatus = CifsNeedReconnect;
-	spin_unlock(&GlobalMid_Lock);
 	server->maxBuf = 0;
 	server->max_read = 0;
 
 	cifs_dbg(FYI, "Mark tcp session as need reconnect\n");
 	trace_smb3_reconnect(server->CurrentMid, server->conn_id, server->hostname);
+	/*
+	 * before reconnecting the tcp session, mark the smb session (uid) and the tid bad so they
+	 * are not used until reconnected.
+	 */
+	cifs_dbg(FYI, "%s: marking sessions and tcons for reconnect\n", __func__);
+
+	/* If server is a channel, select the primary channel */
+	pserver = CIFS_SERVER_IS_CHAN(server) ? server->primary_server : server;
 
-	/* before reconnecting the tcp session, mark the smb session (uid)
-		and the tid bad so they are not used until reconnected */
-	cifs_dbg(FYI, "%s: marking sessions and tcons for reconnect\n",
-		 __func__);
 	spin_lock(&cifs_tcp_ses_lock);
-	list_for_each(tmp, &server->smb_ses_list) {
-		ses = list_entry(tmp, struct cifs_ses, smb_ses_list);
+	list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) {
 		ses->need_reconnect = true;
-		list_for_each(tmp2, &ses->tcon_list) {
-			tcon = list_entry(tmp2, struct cifs_tcon, tcon_list);
+		list_for_each_entry(tcon, &ses->tcon_list, tcon_list)
 			tcon->need_reconnect = true;
-		}
 		if (ses->tcon_ipc)
 			ses->tcon_ipc->need_reconnect = true;
 	}
@@ -290,11 +203,11 @@ cifs_reconnect(struct TCP_Server_Info *server)
 	cifs_dbg(FYI, "%s: tearing down socket\n", __func__);
 	mutex_lock(&server->srv_mutex);
 	if (server->ssocket) {
-		cifs_dbg(FYI, "State: 0x%x Flags: 0x%lx\n",
-			 server->ssocket->state, server->ssocket->flags);
+		cifs_dbg(FYI, "State: 0x%x Flags: 0x%lx\n", server->ssocket->state,
+			 server->ssocket->flags);
 		kernel_sock_shutdown(server->ssocket, SHUT_WR);
-		cifs_dbg(FYI, "Post shutdown state: 0x%x Flags: 0x%lx\n",
-			 server->ssocket->state, server->ssocket->flags);
+		cifs_dbg(FYI, "Post shutdown state: 0x%x Flags: 0x%lx\n", server->ssocket->state,
+			 server->ssocket->flags);
 		sock_release(server->ssocket);
 		server->ssocket = NULL;
 	}
@@ -309,23 +222,21 @@ cifs_reconnect(struct TCP_Server_Info *server)
 	INIT_LIST_HEAD(&retry_list);
 	cifs_dbg(FYI, "%s: moving mids to private list\n", __func__);
 	spin_lock(&GlobalMid_Lock);
-	list_for_each_safe(tmp, tmp2, &server->pending_mid_q) {
-		mid_entry = list_entry(tmp, struct mid_q_entry, qhead);
-		kref_get(&mid_entry->refcount);
-		if (mid_entry->mid_state == MID_REQUEST_SUBMITTED)
-			mid_entry->mid_state = MID_RETRY_NEEDED;
-		list_move(&mid_entry->qhead, &retry_list);
-		mid_entry->mid_flags |= MID_DELETED;
+	list_for_each_entry_safe(mid, nmid, &server->pending_mid_q, qhead) {
+		kref_get(&mid->refcount);
+		if (mid->mid_state == MID_REQUEST_SUBMITTED)
+			mid->mid_state = MID_RETRY_NEEDED;
+		list_move(&mid->qhead, &retry_list);
+		mid->mid_flags |= MID_DELETED;
 	}
 	spin_unlock(&GlobalMid_Lock);
 	mutex_unlock(&server->srv_mutex);
 
 	cifs_dbg(FYI, "%s: issuing mid callbacks\n", __func__);
-	list_for_each_safe(tmp, tmp2, &retry_list) {
-		mid_entry = list_entry(tmp, struct mid_q_entry, qhead);
-		list_del_init(&mid_entry->qhead);
-		mid_entry->callback(mid_entry);
-		cifs_mid_q_entry_release(mid_entry);
+	list_for_each_entry_safe(mid, nmid, &retry_list, qhead) {
+		list_del_init(&mid->qhead);
+		mid->callback(mid);
+		cifs_mid_q_entry_release(mid);
 	}
 
 	if (cifs_rdma_enabled(server)) {
@@ -333,38 +244,48 @@ cifs_reconnect(struct TCP_Server_Info *server)
 		smbd_destroy(server);
 		mutex_unlock(&server->srv_mutex);
 	}
+}
+
+static bool cifs_tcp_ses_needs_reconnect(struct TCP_Server_Info *server, int num_targets)
+{
+	spin_lock(&GlobalMid_Lock);
+	server->nr_targets = num_targets;
+	if (server->tcpStatus == CifsExiting) {
+		/* the demux thread will exit normally next time through the loop */
+		spin_unlock(&GlobalMid_Lock);
+		wake_up(&server->response_q);
+		return false;
+	}
+	server->tcpStatus = CifsNeedReconnect;
+	spin_unlock(&GlobalMid_Lock);
+	return true;
+}
+
+/*
+ * cifs tcp session reconnection
+ *
+ * mark tcp session as reconnecting so temporarily locked
+ * mark all smb sessions as reconnecting for tcp session
+ * reconnect tcp session
+ * wake up waiters on reconnection? - (not needed currently)
+ */
+static int __cifs_reconnect(struct TCP_Server_Info *server)
+{
+	int rc = 0;
+
+	if (!cifs_tcp_ses_needs_reconnect(server, 1))
+		return 0;
+
+	cifs_mark_tcp_ses_conns_for_reconnect(server);
 
 	do {
 		try_to_freeze();
-
 		mutex_lock(&server->srv_mutex);
 
-
 		if (!cifs_swn_set_server_dstaddr(server)) {
-#ifdef CONFIG_CIFS_DFS_UPCALL
-		if (cifs_sb && cifs_sb->origin_fullpath)
-			/*
-			 * Set up next DFS target server (if any) for reconnect. If DFS
-			 * feature is disabled, then we will retry last server we
-			 * connected to before.
-			 */
-			reconn_set_next_dfs_target(server, cifs_sb, &tgt_list, &tgt_it);
-		else {
-#endif
-			/*
-			 * Resolve the hostname again to make sure that IP address is up-to-date.
-			 */
+			/* resolve the hostname again to make sure that IP address is up-to-date */
 			rc = reconn_set_ipaddr_from_hostname(server);
-			if (rc) {
-				cifs_dbg(FYI, "%s: failed to resolve hostname: %d\n",
-						__func__, rc);
-			}
-
-#ifdef CONFIG_CIFS_DFS_UPCALL
-		}
-#endif
-
-
+			cifs_dbg(FYI, "%s: reconn_set_ipaddr_from_hostname: rc=%d\n", __func__, rc);
 		}
 
 		if (cifs_rdma_enabled(server))
@@ -372,8 +293,8 @@ cifs_reconnect(struct TCP_Server_Info *server)
 		else
 			rc = generic_ip_connect(server);
 		if (rc) {
-			cifs_dbg(FYI, "reconnect error %d\n", rc);
 			mutex_unlock(&server->srv_mutex);
+			cifs_dbg(FYI, "%s: reconnect error %d\n", __func__, rc);
 			msleep(3000);
 		} else {
 			atomic_inc(&tcpSesReconnectCount);
@@ -387,19 +308,128 @@ cifs_reconnect(struct TCP_Server_Info *server)
 		}
 	} while (server->tcpStatus == CifsNeedReconnect);
 
+	if (server->tcpStatus == CifsNeedNegotiate)
+		mod_delayed_work(cifsiod_wq, &server->echo, 0);
+
+	wake_up(&server->response_q);
+	return rc;
+}
+
 #ifdef CONFIG_CIFS_DFS_UPCALL
-	if (tgt_it) {
-		rc = dfs_cache_noreq_update_tgthint(cifs_sb->origin_fullpath + 1,
-						    tgt_it);
-		if (rc) {
-			cifs_server_dbg(VFS, "%s: failed to update DFS target hint: rc = %d\n",
-				 __func__, rc);
+static int __reconnect_target_unlocked(struct TCP_Server_Info *server, const char *target)
+{
+	int rc;
+	char *hostname;
+
+	if (!cifs_swn_set_server_dstaddr(server)) {
+		if (server->hostname != target) {
+			hostname = extract_hostname(target);
+			if (!IS_ERR(hostname)) {
+				kfree(server->hostname);
+				server->hostname = hostname;
+			} else {
+				cifs_dbg(FYI, "%s: couldn't extract hostname or address from dfs target: %ld\n",
+					 __func__, PTR_ERR(hostname));
+				cifs_dbg(FYI, "%s: default to last target server: %s\n", __func__,
+					 server->hostname);
+			}
 		}
-		dfs_cache_free_tgts(&tgt_list);
+		/* resolve the hostname again to make sure that IP address is up-to-date. */
+		rc = reconn_set_ipaddr_from_hostname(server);
+		cifs_dbg(FYI, "%s: reconn_set_ipaddr_from_hostname: rc=%d\n", __func__, rc);
 	}
+	/* Reconnect the socket */
+	if (cifs_rdma_enabled(server))
+		rc = smbd_reconnect(server);
+	else
+		rc = generic_ip_connect(server);
 
-	cifs_put_tcp_super(sb);
-#endif
+	return rc;
+}
+
+static int reconnect_target_unlocked(struct TCP_Server_Info *server, struct dfs_cache_tgt_list *tl,
+				     struct dfs_cache_tgt_iterator **target_hint)
+{
+	int rc;
+	struct dfs_cache_tgt_iterator *tit;
+
+	*target_hint = NULL;
+
+	/* If dfs target list is empty, then reconnect to last server */
+	tit = dfs_cache_get_tgt_iterator(tl);
+	if (!tit)
+		return __reconnect_target_unlocked(server, server->hostname);
+
+	/* Otherwise, try every dfs target in @tl */
+	for (; tit; tit = dfs_cache_get_next_tgt(tl, tit)) {
+		rc = __reconnect_target_unlocked(server, dfs_cache_get_tgt_name(tit));
+		if (!rc) {
+			*target_hint = tit;
+			break;
+		}
+	}
+	return rc;
+}
+
+static int reconnect_dfs_server(struct TCP_Server_Info *server)
+{
+	int rc = 0;
+	const char *refpath = server->current_fullpath + 1;
+	struct dfs_cache_tgt_list tl = DFS_CACHE_TGT_LIST_INIT(tl);
+	struct dfs_cache_tgt_iterator *target_hint = NULL;
+	int num_targets = 0;
+
+	/*
+	 * Determine the number of dfs targets the referral path in @cifs_sb resolves to.
+	 *
+	 * smb2_reconnect() needs to know how long it should wait based upon the number of dfs
+	 * targets (server->nr_targets).  It's also possible that the cached referral was cleared
+	 * through /proc/fs/cifs/dfscache or the target list is empty due to server settings after
+	 * refreshing the referral, so, in this case, default it to 1.
+	 */
+	if (!dfs_cache_noreq_find(refpath, NULL, &tl))
+		num_targets = dfs_cache_get_nr_tgts(&tl);
+	if (!num_targets)
+		num_targets = 1;
+
+	if (!cifs_tcp_ses_needs_reconnect(server, num_targets))
+		return 0;
+
+	cifs_mark_tcp_ses_conns_for_reconnect(server);
+
+	do {
+		try_to_freeze();
+		mutex_lock(&server->srv_mutex);
+
+		rc = reconnect_target_unlocked(server, &tl, &target_hint);
+		if (rc) {
+			/* Failed to reconnect socket */
+			mutex_unlock(&server->srv_mutex);
+			cifs_dbg(FYI, "%s: reconnect error %d\n", __func__, rc);
+			msleep(3000);
+			continue;
+		}
+		/*
+		 * Socket was created.  Update tcp session status to CifsNeedNegotiate so that a
+		 * process waiting for reconnect will know it needs to re-establish session and tcon
+		 * through the reconnected target server.
+		 */
+		atomic_inc(&tcpSesReconnectCount);
+		set_credits(server, 1);
+		spin_lock(&GlobalMid_Lock);
+		if (server->tcpStatus != CifsExiting)
+			server->tcpStatus = CifsNeedNegotiate;
+		spin_unlock(&GlobalMid_Lock);
+		cifs_swn_reset_server_dstaddr(server);
+		mutex_unlock(&server->srv_mutex);
+	} while (server->tcpStatus == CifsNeedReconnect);
+
+	if (target_hint)
+		dfs_cache_noreq_update_tgthint(refpath, target_hint);
+
+	dfs_cache_free_tgts(&tl);
+
+	/* Need to set up echo worker again once connection has been established */
 	if (server->tcpStatus == CifsNeedNegotiate)
 		mod_delayed_work(cifsiod_wq, &server->echo, 0);
 
@@ -407,6 +437,25 @@ cifs_reconnect(struct TCP_Server_Info *server)
 	return rc;
 }
 
+int cifs_reconnect(struct TCP_Server_Info *server)
+{
+	/* If tcp session is not an dfs connection, then reconnect to last target server */
+	spin_lock(&cifs_tcp_ses_lock);
+	if (!server->is_dfs_conn || !server->origin_fullpath || !server->leaf_fullpath) {
+		spin_unlock(&cifs_tcp_ses_lock);
+		return __cifs_reconnect(server);
+	}
+	spin_unlock(&cifs_tcp_ses_lock);
+
+	return reconnect_dfs_server(server);
+}
+#else
+int cifs_reconnect(struct TCP_Server_Info *server)
+{
+	return __cifs_reconnect(server);
+}
+#endif
+
 static void
 cifs_echo_request(struct work_struct *work)
 {
@@ -665,13 +714,14 @@ dequeue_mid(struct mid_q_entry *mid, bool malformed)
 	 * Trying to handle/dequeue a mid after the send_recv()
 	 * function has finished processing it is a bug.
 	 */
-	if (mid->mid_flags & MID_DELETED)
+	if (mid->mid_flags & MID_DELETED) {
+		spin_unlock(&GlobalMid_Lock);
 		pr_warn_once("trying to dequeue a deleted mid\n");
-	else {
+	} else {
 		list_del_init(&mid->qhead);
 		mid->mid_flags |= MID_DELETED;
+		spin_unlock(&GlobalMid_Lock);
 	}
-	spin_unlock(&GlobalMid_Lock);
 }
 
 static unsigned int
@@ -794,6 +844,10 @@ static void clean_demultiplex_info(struct TCP_Server_Info *server)
 		 */
 	}
 
+#ifdef CONFIG_CIFS_DFS_UPCALL
+	kfree(server->origin_fullpath);
+	kfree(server->leaf_fullpath);
+#endif
 	kfree(server);
 
 	length = atomic_dec_return(&tcpSesAllocCount);
@@ -1220,6 +1274,10 @@ static int match_server(struct TCP_Server_Info *server, struct smb3_fs_context *
 	if (ctx->nosharesock)
 		return 0;
 
+	/* this server does not share socket */
+	if (server->nosharesock)
+		return 0;
+
 	/* If multidialect negotiation see if existing sessions match one */
 	if (strcmp(ctx->vals->version_string, SMB3ANY_VERSION_STRING) == 0) {
 		if (server->vals->protocol_id < SMB30_PROT_ID)
@@ -1283,7 +1341,7 @@ cifs_find_tcp_session(struct smb3_fs_context *ctx)
 		 * Skip ses channels since they're only handled in lower layers
 		 * (e.g. cifs_send_recv).
 		 */
-		if (server->is_channel || !match_server(server, ctx))
+		if (CIFS_SERVER_IS_CHAN(server) || !match_server(server, ctx))
 			continue;
 
 		++server->srv_count;
@@ -1314,6 +1372,10 @@ cifs_put_tcp_session(struct TCP_Server_Info *server, int from_reconnect)
 	list_del_init(&server->tcp_ses_list);
 	spin_unlock(&cifs_tcp_ses_lock);
 
+	/* For secondary channels, we pick up ref-count on the primary server */
+	if (CIFS_SERVER_IS_CHAN(server))
+		cifs_put_tcp_session(server->primary_server, from_reconnect);
+
 	cancel_delayed_work_sync(&server->echo);
 	cancel_delayed_work_sync(&server->resolve);
 
@@ -1333,7 +1395,10 @@ cifs_put_tcp_session(struct TCP_Server_Info *server, int from_reconnect)
 	spin_unlock(&GlobalMid_Lock);
 
 	cifs_crypto_secmech_release(server);
-	cifs_fscache_release_client_cookie(server);
+
+	/* fscache server cookies are based on primary channel only */
+	if (!CIFS_SERVER_IS_CHAN(server))
+		cifs_fscache_release_client_cookie(server);
 
 	kfree(server->session_key.response);
 	server->session_key.response = NULL;
@@ -1346,7 +1411,8 @@ cifs_put_tcp_session(struct TCP_Server_Info *server, int from_reconnect)
 }
 
 struct TCP_Server_Info *
-cifs_get_tcp_session(struct smb3_fs_context *ctx)
+cifs_get_tcp_session(struct smb3_fs_context *ctx,
+		     struct TCP_Server_Info *primary_server)
 {
 	struct TCP_Server_Info *tcp_ses = NULL;
 	int rc;
@@ -1370,6 +1436,9 @@ cifs_get_tcp_session(struct smb3_fs_context *ctx)
 		goto out_err;
 	}
 
+	if (ctx->nosharesock)
+		tcp_ses->nosharesock = true;
+
 	tcp_ses->ops = ctx->ops;
 	tcp_ses->vals = ctx->vals;
 	cifs_set_net_ns(tcp_ses, get_net(current->nsproxy->net_ns));
@@ -1383,6 +1452,12 @@ cifs_get_tcp_session(struct smb3_fs_context *ctx)
 	tcp_ses->in_flight = 0;
 	tcp_ses->max_in_flight = 0;
 	tcp_ses->credits = 1;
+	if (primary_server) {
+		spin_lock(&cifs_tcp_ses_lock);
+		++primary_server->srv_count;
+		tcp_ses->primary_server = primary_server;
+		spin_unlock(&cifs_tcp_ses_lock);
+	}
 	init_waitqueue_head(&tcp_ses->response_q);
 	init_waitqueue_head(&tcp_ses->request_q);
 	INIT_LIST_HEAD(&tcp_ses->pending_mid_q);
@@ -1403,6 +1478,9 @@ cifs_get_tcp_session(struct smb3_fs_context *ctx)
 	INIT_DELAYED_WORK(&tcp_ses->resolve, cifs_resolve_server);
 	INIT_DELAYED_WORK(&tcp_ses->reconnect, smb2_reconnect_server);
 	mutex_init(&tcp_ses->reconnect_mutex);
+#ifdef CONFIG_CIFS_DFS_UPCALL
+	mutex_init(&tcp_ses->refpath_lock);
+#endif
 	memcpy(&tcp_ses->srcaddr, &ctx->srcaddr,
 	       sizeof(tcp_ses->srcaddr));
 	memcpy(&tcp_ses->dstaddr, &ctx->dstaddr,
@@ -1481,7 +1559,13 @@ smbd_connected:
 	list_add(&tcp_ses->tcp_ses_list, &cifs_tcp_ses_list);
 	spin_unlock(&cifs_tcp_ses_lock);
 
-	cifs_fscache_get_client_cookie(tcp_ses);
+	/* fscache server cookies are based on primary channel only */
+	if (!CIFS_SERVER_IS_CHAN(tcp_ses))
+		cifs_fscache_get_client_cookie(tcp_ses);
+#ifdef CONFIG_CIFS_FSCACHE
+	else
+		tcp_ses->fscache = tcp_ses->primary_server->fscache;
+#endif /* CONFIG_CIFS_FSCACHE */
 
 	/* queue echo request delayed work */
 	queue_delayed_work(cifsiod_wq, &tcp_ses->echo, tcp_ses->echo_interval);
@@ -1501,6 +1585,8 @@ out_err_crypto_release:
 
 out_err:
 	if (tcp_ses) {
+		if (CIFS_SERVER_IS_CHAN(tcp_ses))
+			cifs_put_tcp_session(tcp_ses->primary_server, false);
 		kfree(tcp_ses->hostname);
 		if (tcp_ses->ssocket)
 			sock_release(tcp_ses->ssocket);
@@ -1519,8 +1605,12 @@ static int match_session(struct cifs_ses *ses, struct smb3_fs_context *ctx)
 	 * If an existing session is limited to less channels than
 	 * requested, it should not be reused
 	 */
-	if (ses->chan_max < ctx->max_channels)
+	spin_lock(&ses->chan_lock);
+	if (ses->chan_max < ctx->max_channels) {
+		spin_unlock(&ses->chan_lock);
 		return 0;
+	}
+	spin_unlock(&ses->chan_lock);
 
 	switch (ses->sectype) {
 	case Kerberos:
@@ -1655,6 +1745,7 @@ cifs_find_smb_ses(struct TCP_Server_Info *server, struct smb3_fs_context *ctx)
 void cifs_put_smb_ses(struct cifs_ses *ses)
 {
 	unsigned int rc, xid;
+	unsigned int chan_count;
 	struct TCP_Server_Info *server = ses->server;
 	cifs_dbg(FYI, "%s: ses_count=%d\n", __func__, ses->ses_count);
 
@@ -1696,12 +1787,24 @@ void cifs_put_smb_ses(struct cifs_ses *ses)
 	list_del_init(&ses->smb_ses_list);
 	spin_unlock(&cifs_tcp_ses_lock);
 
+	spin_lock(&ses->chan_lock);
+	chan_count = ses->chan_count;
+	spin_unlock(&ses->chan_lock);
+
 	/* close any extra channels */
-	if (ses->chan_count > 1) {
+	if (chan_count > 1) {
 		int i;
 
-		for (i = 1; i < ses->chan_count; i++)
+		for (i = 1; i < chan_count; i++) {
+			/*
+			 * note: for now, we're okay accessing ses->chans
+			 * without chan_lock. But when chans can go away, we'll
+			 * need to introduce ref counting to make sure that chan
+			 * is not freed from under us.
+			 */
 			cifs_put_tcp_session(ses->chans[i].server, 0);
+			ses->chans[i].server = NULL;
+		}
 	}
 
 	sesInfoFree(ses);
@@ -1885,16 +1988,18 @@ cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb3_fs_context *ctx)
 			 ses->status);
 
 		mutex_lock(&ses->session_mutex);
-		rc = cifs_negotiate_protocol(xid, ses);
-		if (rc) {
-			mutex_unlock(&ses->session_mutex);
-			/* problem -- put our ses reference */
-			cifs_put_smb_ses(ses);
-			free_xid(xid);
-			return ERR_PTR(rc);
-		}
 		if (ses->need_reconnect) {
 			cifs_dbg(FYI, "Session needs reconnect\n");
+
+			rc = cifs_negotiate_protocol(xid, ses);
+			if (rc) {
+				mutex_unlock(&ses->session_mutex);
+				/* problem -- put our ses reference */
+				cifs_put_smb_ses(ses);
+				free_xid(xid);
+				return ERR_PTR(rc);
+			}
+
 			rc = cifs_setup_session(xid, ses,
 						ctx->local_nls);
 			if (rc) {
@@ -1942,6 +2047,12 @@ cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb3_fs_context *ctx)
 		if (!ses->domainName)
 			goto get_ses_fail;
 	}
+	if (ctx->workstation_name) {
+		ses->workstation_name = kstrdup(ctx->workstation_name,
+						GFP_KERNEL);
+		if (!ses->workstation_name)
+			goto get_ses_fail;
+	}
 	if (ctx->domainauto)
 		ses->domainAuto = ctx->domainauto;
 	ses->cred_uid = ctx->cred_uid;
@@ -1952,9 +2063,11 @@ cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb3_fs_context *ctx)
 	mutex_lock(&ses->session_mutex);
 
 	/* add server as first channel */
+	spin_lock(&ses->chan_lock);
 	ses->chans[0].server = server;
 	ses->chan_count = 1;
 	ses->chan_max = ctx->multichannel ? ctx->max_channels:1;
+	spin_unlock(&ses->chan_lock);
 
 	rc = cifs_negotiate_protocol(xid, ses);
 	if (!rc)
@@ -2286,8 +2399,6 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb3_fs_context *ctx)
 	list_add(&tcon->tcon_list, &ses->tcon_list);
 	spin_unlock(&cifs_tcp_ses_lock);
 
-	cifs_fscache_get_super_cookie(tcon);
-
 	return tcon;
 
 out_fail:
@@ -2849,73 +2960,64 @@ int cifs_setup_cifs_sb(struct cifs_sb_info *cifs_sb)
 }
 
 /* Release all succeed connections */
-static inline void mount_put_conns(struct cifs_sb_info *cifs_sb,
-				   unsigned int xid,
-				   struct TCP_Server_Info *server,
-				   struct cifs_ses *ses, struct cifs_tcon *tcon)
+static inline void mount_put_conns(struct mount_ctx *mnt_ctx)
 {
 	int rc = 0;
 
-	if (tcon)
-		cifs_put_tcon(tcon);
-	else if (ses)
-		cifs_put_smb_ses(ses);
-	else if (server)
-		cifs_put_tcp_session(server, 0);
-	cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_POSIX_PATHS;
-	free_xid(xid);
+	if (mnt_ctx->tcon)
+		cifs_put_tcon(mnt_ctx->tcon);
+	else if (mnt_ctx->ses)
+		cifs_put_smb_ses(mnt_ctx->ses);
+	else if (mnt_ctx->server)
+		cifs_put_tcp_session(mnt_ctx->server, 0);
+	mnt_ctx->cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_POSIX_PATHS;
+	free_xid(mnt_ctx->xid);
 }
 
 /* Get connections for tcp, ses and tcon */
-static int mount_get_conns(struct smb3_fs_context *ctx, struct cifs_sb_info *cifs_sb,
-			   unsigned int *xid,
-			   struct TCP_Server_Info **nserver,
-			   struct cifs_ses **nses, struct cifs_tcon **ntcon)
+static int mount_get_conns(struct mount_ctx *mnt_ctx)
 {
 	int rc = 0;
-	struct TCP_Server_Info *server;
-	struct cifs_ses *ses;
-	struct cifs_tcon *tcon;
-
-	*nserver = NULL;
-	*nses = NULL;
-	*ntcon = NULL;
+	struct TCP_Server_Info *server = NULL;
+	struct cifs_ses *ses = NULL;
+	struct cifs_tcon *tcon = NULL;
+	struct smb3_fs_context *ctx = mnt_ctx->fs_ctx;
+	struct cifs_sb_info *cifs_sb = mnt_ctx->cifs_sb;
+	unsigned int xid;
 
-	*xid = get_xid();
+	xid = get_xid();
 
 	/* get a reference to a tcp session */
-	server = cifs_get_tcp_session(ctx);
+	server = cifs_get_tcp_session(ctx, NULL);
 	if (IS_ERR(server)) {
 		rc = PTR_ERR(server);
-		return rc;
+		server = NULL;
+		goto out;
 	}
 
-	*nserver = server;
-
 	/* get a reference to a SMB session */
 	ses = cifs_get_smb_ses(server, ctx);
 	if (IS_ERR(ses)) {
 		rc = PTR_ERR(ses);
-		return rc;
+		ses = NULL;
+		goto out;
 	}
 
-	*nses = ses;
-
 	if ((ctx->persistent == true) && (!(ses->server->capabilities &
 					    SMB2_GLOBAL_CAP_PERSISTENT_HANDLES))) {
 		cifs_server_dbg(VFS, "persistent handles not supported by server\n");
-		return -EOPNOTSUPP;
+		rc = -EOPNOTSUPP;
+		goto out;
 	}
 
 	/* search for existing tcon to this server share */
 	tcon = cifs_get_tcon(ses, ctx);
 	if (IS_ERR(tcon)) {
 		rc = PTR_ERR(tcon);
-		return rc;
+		tcon = NULL;
+		goto out;
 	}
 
-	*ntcon = tcon;
-
 	/* if new SMB3.11 POSIX extensions are supported do not remap / and \ */
 	if (tcon->posix_extensions)
 		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_POSIX_PATHS;
@@ -2926,17 +3028,19 @@ static int mount_get_conns(struct smb3_fs_context *ctx, struct cifs_sb_info *cif
 		 * reset of caps checks mount to see if unix extensions disabled
 		 * for just this mount.
 		 */
-		reset_cifs_unix_caps(*xid, tcon, cifs_sb, ctx);
+		reset_cifs_unix_caps(xid, tcon, cifs_sb, ctx);
 		if ((tcon->ses->server->tcpStatus == CifsNeedReconnect) &&
 		    (le64_to_cpu(tcon->fsUnixInfo.Capability) &
-		     CIFS_UNIX_TRANSPORT_ENCRYPTION_MANDATORY_CAP))
-			return -EACCES;
+		     CIFS_UNIX_TRANSPORT_ENCRYPTION_MANDATORY_CAP)) {
+			rc = -EACCES;
+			goto out;
+		}
 	} else
 		tcon->unix_ext = 0; /* server does not support them */
 
 	/* do not care if a following call succeed - informational */
 	if (!tcon->pipe && server->ops->qfs_tcon) {
-		server->ops->qfs_tcon(*xid, tcon, cifs_sb);
+		server->ops->qfs_tcon(xid, tcon, cifs_sb);
 		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RO_CACHE) {
 			if (tcon->fsDevInfo.DeviceCharacteristics &
 			    cpu_to_le32(FILE_READ_ONLY_DEVICE))
@@ -2960,7 +3064,20 @@ static int mount_get_conns(struct smb3_fs_context *ctx, struct cifs_sb_info *cif
 	    (cifs_sb->ctx->rsize > server->ops->negotiate_rsize(tcon, ctx)))
 		cifs_sb->ctx->rsize = server->ops->negotiate_rsize(tcon, ctx);
 
-	return 0;
+	/*
+	 * The cookie is initialized from volume info returned above.
+	 * Inside cifs_fscache_get_super_cookie it checks
+	 * that we do not get super cookie twice.
+	 */
+	cifs_fscache_get_super_cookie(tcon);
+
+out:
+	mnt_ctx->server = server;
+	mnt_ctx->ses = ses;
+	mnt_ctx->tcon = tcon;
+	mnt_ctx->xid = xid;
+
+	return rc;
 }
 
 static int mount_setup_tlink(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses,
@@ -2990,18 +3107,17 @@ static int mount_setup_tlink(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses,
 }
 
 #ifdef CONFIG_CIFS_DFS_UPCALL
-static int mount_get_dfs_conns(struct smb3_fs_context *ctx, struct cifs_sb_info *cifs_sb,
-			       unsigned int *xid, struct TCP_Server_Info **nserver,
-			       struct cifs_ses **nses, struct cifs_tcon **ntcon)
+/* Get unique dfs connections */
+static int mount_get_dfs_conns(struct mount_ctx *mnt_ctx)
 {
 	int rc;
 
-	ctx->nosharesock = true;
-	rc = mount_get_conns(ctx, cifs_sb, xid, nserver, nses, ntcon);
-	if (*nserver) {
+	mnt_ctx->fs_ctx->nosharesock = true;
+	rc = mount_get_conns(mnt_ctx);
+	if (mnt_ctx->server) {
 		cifs_dbg(FYI, "%s: marking tcp session as a dfs connection\n", __func__);
 		spin_lock(&cifs_tcp_ses_lock);
-		(*nserver)->is_dfs_conn = true;
+		mnt_ctx->server->is_dfs_conn = true;
 		spin_unlock(&cifs_tcp_ses_lock);
 	}
 	return rc;
@@ -3043,190 +3159,38 @@ build_unc_path_to_root(const struct smb3_fs_context *ctx,
 }
 
 /*
- * expand_dfs_referral - Perform a dfs referral query and update the cifs_sb
- *
- * If a referral is found, cifs_sb->ctx->mount_options will be (re-)allocated
- * to a string containing updated options for the submount.  Otherwise it
- * will be left untouched.
+ * expand_dfs_referral - Update cifs_sb from dfs referral path
  *
- * Returns the rc from get_dfs_path to the caller, which can be used to
- * determine whether there were referrals.
+ * cifs_sb->ctx->mount_options will be (re-)allocated to a string containing updated options for the
+ * submount.  Otherwise it will be left untouched.
  */
-static int
-expand_dfs_referral(const unsigned int xid, struct cifs_ses *ses,
-		    struct smb3_fs_context *ctx, struct cifs_sb_info *cifs_sb,
-		    char *ref_path)
-{
-	int rc;
-	struct dfs_info3_param referral = {0};
-	char *full_path = NULL, *mdata = NULL;
-
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_DFS)
-		return -EREMOTE;
-
-	full_path = build_unc_path_to_root(ctx, cifs_sb, true);
-	if (IS_ERR(full_path))
-		return PTR_ERR(full_path);
-
-	rc = dfs_cache_find(xid, ses, cifs_sb->local_nls, cifs_remap(cifs_sb),
-			    ref_path, &referral, NULL);
-	if (!rc) {
-		char *fake_devname = NULL;
-
-		mdata = cifs_compose_mount_options(cifs_sb->ctx->mount_options,
-						   full_path + 1, &referral,
-						   &fake_devname);
-		free_dfs_info_param(&referral);
-
-		if (IS_ERR(mdata)) {
-			rc = PTR_ERR(mdata);
-			mdata = NULL;
-		} else {
-			/*
-			 * We can not clear out the whole structure since we
-			 * no longer have an explicit function to parse
-			 * a mount-string. Instead we need to clear out the
-			 * individual fields that are no longer valid.
-			 */
-			kfree(ctx->prepath);
-			ctx->prepath = NULL;
-			rc = cifs_setup_volume_info(ctx, mdata, fake_devname);
-		}
-		kfree(fake_devname);
-		kfree(cifs_sb->ctx->mount_options);
-		cifs_sb->ctx->mount_options = mdata;
-	}
-	kfree(full_path);
-	return rc;
-}
-
-static int get_next_dfs_tgt(struct dfs_cache_tgt_list *tgt_list,
-			    struct dfs_cache_tgt_iterator **tgt_it)
-{
-	if (!*tgt_it)
-		*tgt_it = dfs_cache_get_tgt_iterator(tgt_list);
-	else
-		*tgt_it = dfs_cache_get_next_tgt(tgt_list, *tgt_it);
-	return !*tgt_it ? -EHOSTDOWN : 0;
-}
-
-static int update_vol_info(const struct dfs_cache_tgt_iterator *tgt_it,
-			   struct smb3_fs_context *fake_ctx, struct smb3_fs_context *ctx)
-{
-	const char *tgt = dfs_cache_get_tgt_name(tgt_it);
-	int len = strlen(tgt) + 2;
-	char *new_unc;
-
-	new_unc = kmalloc(len, GFP_KERNEL);
-	if (!new_unc)
-		return -ENOMEM;
-	scnprintf(new_unc, len, "\\%s", tgt);
-
-	kfree(ctx->UNC);
-	ctx->UNC = new_unc;
-
-	if (fake_ctx->prepath) {
-		kfree(ctx->prepath);
-		ctx->prepath = fake_ctx->prepath;
-		fake_ctx->prepath = NULL;
-	}
-	memcpy(&ctx->dstaddr, &fake_ctx->dstaddr, sizeof(ctx->dstaddr));
-
-	return 0;
-}
-
-static int do_dfs_failover(const char *path, const char *full_path, struct cifs_sb_info *cifs_sb,
-			   struct smb3_fs_context *ctx, struct cifs_ses *root_ses,
-			   unsigned int *xid, struct TCP_Server_Info **server,
-			   struct cifs_ses **ses, struct cifs_tcon **tcon)
+static int expand_dfs_referral(struct mount_ctx *mnt_ctx, const char *full_path,
+			       struct dfs_info3_param *referral)
 {
 	int rc;
-	char *npath = NULL;
-	struct dfs_cache_tgt_list tgt_list = DFS_CACHE_TGT_LIST_INIT(tgt_list);
-	struct dfs_cache_tgt_iterator *tgt_it = NULL;
-	struct smb3_fs_context tmp_ctx = {NULL};
-
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_DFS)
-		return -EOPNOTSUPP;
-
-	npath = dfs_cache_canonical_path(path, cifs_sb->local_nls, cifs_remap(cifs_sb));
-	if (IS_ERR(npath))
-		return PTR_ERR(npath);
-
-	cifs_dbg(FYI, "%s: path=%s full_path=%s\n", __func__, npath, full_path);
-
-	rc = dfs_cache_noreq_find(npath, NULL, &tgt_list);
-	if (rc)
-		goto out;
-	/*
-	 * We use a 'tmp_ctx' here because we need pass it down to the mount_{get,put} functions to
-	 * test connection against new DFS targets.
-	 */
-	rc = smb3_fs_context_dup(&tmp_ctx, ctx);
-	if (rc)
-		goto out;
-
-	for (;;) {
-		struct dfs_info3_param ref = {0};
-		char *fake_devname = NULL, *mdata = NULL;
-
-		/* Get next DFS target server - if any */
-		rc = get_next_dfs_tgt(&tgt_list, &tgt_it);
-		if (rc)
-			break;
-
-		rc = dfs_cache_get_tgt_referral(npath, tgt_it, &ref);
-		if (rc)
-			break;
-
-		cifs_dbg(FYI, "%s: old ctx: UNC=%s prepath=%s\n", __func__, tmp_ctx.UNC,
-			 tmp_ctx.prepath);
-
-		mdata = cifs_compose_mount_options(cifs_sb->ctx->mount_options, full_path + 1, &ref,
-						   &fake_devname);
-		free_dfs_info_param(&ref);
-
-		if (IS_ERR(mdata)) {
-			rc = PTR_ERR(mdata);
-			mdata = NULL;
-		} else
-			rc = cifs_setup_volume_info(&tmp_ctx, mdata, fake_devname);
-
-		kfree(mdata);
-		kfree(fake_devname);
-
-		if (rc)
-			break;
-
-		cifs_dbg(FYI, "%s: new ctx: UNC=%s prepath=%s\n", __func__, tmp_ctx.UNC,
-			 tmp_ctx.prepath);
-
-		mount_put_conns(cifs_sb, *xid, *server, *ses, *tcon);
-		rc = mount_get_dfs_conns(&tmp_ctx, cifs_sb, xid, server, ses, tcon);
-		if (!rc || (*server && *ses)) {
-			/*
-			 * We were able to connect to new target server. Update current context with
-			 * new target server.
-			 */
-			rc = update_vol_info(tgt_it, &tmp_ctx, ctx);
-			break;
-		}
-	}
-	if (!rc) {
-		cifs_dbg(FYI, "%s: final ctx: UNC=%s prepath=%s\n", __func__, tmp_ctx.UNC,
-			 tmp_ctx.prepath);
+	struct cifs_sb_info *cifs_sb = mnt_ctx->cifs_sb;
+	struct smb3_fs_context *ctx = mnt_ctx->fs_ctx;
+	char *fake_devname = NULL, *mdata = NULL;
+
+	mdata = cifs_compose_mount_options(cifs_sb->ctx->mount_options, full_path + 1, referral,
+					   &fake_devname);
+	if (IS_ERR(mdata)) {
+		rc = PTR_ERR(mdata);
+		mdata = NULL;
+	} else {
 		/*
-		 * Update DFS target hint in DFS referral cache with the target server we
-		 * successfully reconnected to.
+		 * We can not clear out the whole structure since we no longer have an explicit
+		 * function to parse a mount-string. Instead we need to clear out the individual
+		 * fields that are no longer valid.
 		 */
-		rc = dfs_cache_update_tgthint(*xid, root_ses ? root_ses : *ses, cifs_sb->local_nls,
-					      cifs_remap(cifs_sb), path, tgt_it);
+		kfree(ctx->prepath);
+		ctx->prepath = NULL;
+		rc = cifs_setup_volume_info(ctx, mdata, fake_devname);
 	}
+	kfree(fake_devname);
+	kfree(cifs_sb->ctx->mount_options);
+	cifs_sb->ctx->mount_options = mdata;
 
-out:
-	kfree(npath);
-	smb3_cleanup_fs_context_contents(&tmp_ctx);
-	dfs_cache_free_tgts(&tgt_list);
 	return rc;
 }
 #endif
@@ -3333,12 +3297,14 @@ cifs_are_all_path_components_accessible(struct TCP_Server_Info *server,
  * Check if path is remote (e.g. a DFS share). Return -EREMOTE if it is,
  * otherwise 0.
  */
-static int is_path_remote(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx,
-			  const unsigned int xid,
-			  struct TCP_Server_Info *server,
-			  struct cifs_tcon *tcon)
+static int is_path_remote(struct mount_ctx *mnt_ctx)
 {
 	int rc;
+	struct cifs_sb_info *cifs_sb = mnt_ctx->cifs_sb;
+	struct TCP_Server_Info *server = mnt_ctx->server;
+	unsigned int xid = mnt_ctx->xid;
+	struct cifs_tcon *tcon = mnt_ctx->tcon;
+	struct smb3_fs_context *ctx = mnt_ctx->fs_ctx;
 	char *full_path;
 
 	if (!server->ops->is_path_accessible)
@@ -3376,280 +3342,290 @@ static int is_path_remote(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *
 }
 
 #ifdef CONFIG_CIFS_DFS_UPCALL
-static void set_root_ses(struct cifs_sb_info *cifs_sb, const uuid_t *mount_id, struct cifs_ses *ses,
-			 struct cifs_ses **root_ses)
+static void set_root_ses(struct mount_ctx *mnt_ctx)
 {
-	if (ses) {
+	if (mnt_ctx->ses) {
 		spin_lock(&cifs_tcp_ses_lock);
-		ses->ses_count++;
+		mnt_ctx->ses->ses_count++;
 		spin_unlock(&cifs_tcp_ses_lock);
-		dfs_cache_add_refsrv_session(mount_id, ses);
+		dfs_cache_add_refsrv_session(&mnt_ctx->mount_id, mnt_ctx->ses);
 	}
-	*root_ses = ses;
+	mnt_ctx->root_ses = mnt_ctx->ses;
 }
 
-/* Set up next dfs prefix path in @dfs_path */
-static int next_dfs_prepath(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx,
-			    const unsigned int xid, struct TCP_Server_Info *server,
-			    struct cifs_tcon *tcon, char **dfs_path)
+static int is_dfs_mount(struct mount_ctx *mnt_ctx, bool *isdfs, struct dfs_cache_tgt_list *root_tl)
 {
-	char *path, *npath;
-	int added_treename = is_tcon_dfs(tcon);
 	int rc;
+	struct cifs_sb_info *cifs_sb = mnt_ctx->cifs_sb;
+	struct smb3_fs_context *ctx = mnt_ctx->fs_ctx;
 
-	path = cifs_build_path_to_root(ctx, cifs_sb, tcon, added_treename);
-	if (!path)
-		return -ENOMEM;
+	*isdfs = true;
 
-	rc = is_path_remote(cifs_sb, ctx, xid, server, tcon);
-	if (rc == -EREMOTE) {
-		struct smb3_fs_context v = {NULL};
-		/* if @path contains a tree name, skip it in the prefix path */
-		if (added_treename) {
-			rc = smb3_parse_devname(path, &v);
-			if (rc)
-				goto out;
-			npath = build_unc_path_to_root(&v, cifs_sb, true);
-			smb3_cleanup_fs_context_contents(&v);
-		} else {
-			v.UNC = ctx->UNC;
-			v.prepath = path + 1;
-			npath = build_unc_path_to_root(&v, cifs_sb, true);
-		}
+	rc = mount_get_conns(mnt_ctx);
+	/*
+	 * If called with 'nodfs' mount option, then skip DFS resolving.  Otherwise unconditionally
+	 * try to get an DFS referral (even cached) to determine whether it is an DFS mount.
+	 *
+	 * Skip prefix path to provide support for DFS referrals from w2k8 servers which don't seem
+	 * to respond with PATH_NOT_COVERED to requests that include the prefix.
+	 */
+	if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_DFS) ||
+	    dfs_cache_find(mnt_ctx->xid, mnt_ctx->ses, cifs_sb->local_nls, cifs_remap(cifs_sb),
+			   ctx->UNC + 1, NULL, root_tl)) {
+		if (rc)
+			return rc;
+		/* Check if it is fully accessible and then mount it */
+		rc = is_path_remote(mnt_ctx);
+		if (!rc)
+			*isdfs = false;
+		else if (rc != -EREMOTE)
+			return rc;
+	}
+	return 0;
+}
 
-		if (IS_ERR(npath)) {
-			rc = PTR_ERR(npath);
-			goto out;
-		}
+static int connect_dfs_target(struct mount_ctx *mnt_ctx, const char *full_path,
+			      const char *ref_path, struct dfs_cache_tgt_iterator *tit)
+{
+	int rc;
+	struct dfs_info3_param ref = {};
+	struct cifs_sb_info *cifs_sb = mnt_ctx->cifs_sb;
+	char *oldmnt = cifs_sb->ctx->mount_options;
+
+	rc = dfs_cache_get_tgt_referral(ref_path, tit, &ref);
+	if (rc)
+		goto out;
+
+	rc = expand_dfs_referral(mnt_ctx, full_path, &ref);
+	if (rc)
+		goto out;
 
-		kfree(*dfs_path);
-		*dfs_path = npath;
-		rc = -EREMOTE;
+	/* Connect to new target only if we were redirected (e.g. mount options changed) */
+	if (oldmnt != cifs_sb->ctx->mount_options) {
+		mount_put_conns(mnt_ctx);
+		rc = mount_get_dfs_conns(mnt_ctx);
+	}
+	if (!rc) {
+		if (cifs_is_referral_server(mnt_ctx->tcon, &ref))
+			set_root_ses(mnt_ctx);
+		rc = dfs_cache_update_tgthint(mnt_ctx->xid, mnt_ctx->root_ses, cifs_sb->local_nls,
+					      cifs_remap(cifs_sb), ref_path, tit);
 	}
 
 out:
-	kfree(path);
+	free_dfs_info_param(&ref);
 	return rc;
 }
 
-/* Check if resolved targets can handle any DFS referrals */
-static int is_referral_server(const char *ref_path, struct cifs_sb_info *cifs_sb,
-			      struct cifs_tcon *tcon, bool *ref_server)
+static int connect_dfs_root(struct mount_ctx *mnt_ctx, struct dfs_cache_tgt_list *root_tl)
 {
 	int rc;
-	struct dfs_info3_param ref = {0};
+	char *full_path;
+	struct cifs_sb_info *cifs_sb = mnt_ctx->cifs_sb;
+	struct smb3_fs_context *ctx = mnt_ctx->fs_ctx;
+	struct dfs_cache_tgt_iterator *tit;
 
-	cifs_dbg(FYI, "%s: ref_path=%s\n", __func__, ref_path);
+	/* Put initial connections as they might be shared with other mounts.  We need unique dfs
+	 * connections per mount to properly failover, so mount_get_dfs_conns() must be used from
+	 * now on.
+	 */
+	mount_put_conns(mnt_ctx);
+	mount_get_dfs_conns(mnt_ctx);
+	set_root_ses(mnt_ctx);
 
-	if (is_tcon_dfs(tcon)) {
-		*ref_server = true;
-	} else {
-		char *npath;
+	full_path = build_unc_path_to_root(ctx, cifs_sb, true);
+	if (IS_ERR(full_path))
+		return PTR_ERR(full_path);
 
-		npath = dfs_cache_canonical_path(ref_path, cifs_sb->local_nls, cifs_remap(cifs_sb));
-		if (IS_ERR(npath))
-			return PTR_ERR(npath);
+	mnt_ctx->origin_fullpath = dfs_cache_canonical_path(ctx->UNC, cifs_sb->local_nls,
+							    cifs_remap(cifs_sb));
+	if (IS_ERR(mnt_ctx->origin_fullpath)) {
+		rc = PTR_ERR(mnt_ctx->origin_fullpath);
+		mnt_ctx->origin_fullpath = NULL;
+		goto out;
+	}
 
-		rc = dfs_cache_noreq_find(npath, &ref, NULL);
-		kfree(npath);
-		if (rc) {
-			cifs_dbg(VFS, "%s: dfs_cache_noreq_find: failed (rc=%d)\n", __func__, rc);
-			return rc;
+	/* Try all dfs root targets */
+	for (rc = -ENOENT, tit = dfs_cache_get_tgt_iterator(root_tl);
+	     tit; tit = dfs_cache_get_next_tgt(root_tl, tit)) {
+		rc = connect_dfs_target(mnt_ctx, full_path, mnt_ctx->origin_fullpath + 1, tit);
+		if (!rc) {
+			mnt_ctx->leaf_fullpath = kstrdup(mnt_ctx->origin_fullpath, GFP_KERNEL);
+			if (!mnt_ctx->leaf_fullpath)
+				rc = -ENOMEM;
+			break;
 		}
-		cifs_dbg(FYI, "%s: ref.flags=0x%x\n", __func__, ref.flags);
-		/*
-		 * Check if all targets are capable of handling DFS referrals as per
-		 * MS-DFSC 2.2.4 RESP_GET_DFS_REFERRAL.
-		 */
-		*ref_server = !!(ref.flags & DFSREF_REFERRAL_SERVER);
-		free_dfs_info_param(&ref);
 	}
-	return 0;
+
+out:
+	kfree(full_path);
+	return rc;
 }
 
-int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx)
+static int __follow_dfs_link(struct mount_ctx *mnt_ctx)
 {
-	int rc = 0;
-	unsigned int xid;
-	struct TCP_Server_Info *server = NULL;
-	struct cifs_ses *ses = NULL, *root_ses = NULL;
-	struct cifs_tcon *tcon = NULL;
-	int count = 0;
-	uuid_t mount_id = {0};
-	char *ref_path = NULL, *full_path = NULL;
-	char *oldmnt = NULL;
-	bool ref_server = false;
+	int rc;
+	struct cifs_sb_info *cifs_sb = mnt_ctx->cifs_sb;
+	struct smb3_fs_context *ctx = mnt_ctx->fs_ctx;
+	char *full_path;
+	struct dfs_cache_tgt_list tl = DFS_CACHE_TGT_LIST_INIT(tl);
+	struct dfs_cache_tgt_iterator *tit;
 
-	rc = mount_get_conns(ctx, cifs_sb, &xid, &server, &ses, &tcon);
-	/*
-	 * If called with 'nodfs' mount option, then skip DFS resolving.  Otherwise unconditionally
-	 * try to get an DFS referral (even cached) to determine whether it is an DFS mount.
-	 *
-	 * Skip prefix path to provide support for DFS referrals from w2k8 servers which don't seem
-	 * to respond with PATH_NOT_COVERED to requests that include the prefix.
-	 */
-	if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_DFS) ||
-	    dfs_cache_find(xid, ses, cifs_sb->local_nls, cifs_remap(cifs_sb), ctx->UNC + 1, NULL,
-			   NULL)) {
-		if (rc)
-			goto error;
-		/* Check if it is fully accessible and then mount it */
-		rc = is_path_remote(cifs_sb, ctx, xid, server, tcon);
-		if (!rc)
-			goto out;
-		if (rc != -EREMOTE)
-			goto error;
+	full_path = build_unc_path_to_root(ctx, cifs_sb, true);
+	if (IS_ERR(full_path))
+		return PTR_ERR(full_path);
+
+	kfree(mnt_ctx->leaf_fullpath);
+	mnt_ctx->leaf_fullpath = dfs_cache_canonical_path(full_path, cifs_sb->local_nls,
+							  cifs_remap(cifs_sb));
+	if (IS_ERR(mnt_ctx->leaf_fullpath)) {
+		rc = PTR_ERR(mnt_ctx->leaf_fullpath);
+		mnt_ctx->leaf_fullpath = NULL;
+		goto out;
 	}
 
-	mount_put_conns(cifs_sb, xid, server, ses, tcon);
-	/*
-	 * Ignore error check here because we may failover to other targets from cached a
-	 * referral.
-	 */
-	(void)mount_get_dfs_conns(ctx, cifs_sb, &xid, &server, &ses, &tcon);
+	/* Get referral from dfs link */
+	rc = dfs_cache_find(mnt_ctx->xid, mnt_ctx->root_ses, cifs_sb->local_nls,
+			    cifs_remap(cifs_sb), mnt_ctx->leaf_fullpath + 1, NULL, &tl);
+	if (rc)
+		goto out;
 
-	/* Get path of DFS root */
-	ref_path = build_unc_path_to_root(ctx, cifs_sb, false);
-	if (IS_ERR(ref_path)) {
-		rc = PTR_ERR(ref_path);
-		ref_path = NULL;
-		goto error;
+	/* Try all dfs link targets */
+	for (rc = -ENOENT, tit = dfs_cache_get_tgt_iterator(&tl);
+	     tit; tit = dfs_cache_get_next_tgt(&tl, tit)) {
+		rc = connect_dfs_target(mnt_ctx, full_path, mnt_ctx->leaf_fullpath + 1, tit);
+		if (!rc) {
+			rc = is_path_remote(mnt_ctx);
+			break;
+		}
+	}
+
+out:
+	kfree(full_path);
+	dfs_cache_free_tgts(&tl);
+	return rc;
+}
+
+static int follow_dfs_link(struct mount_ctx *mnt_ctx)
+{
+	int rc;
+	struct cifs_sb_info *cifs_sb = mnt_ctx->cifs_sb;
+	struct smb3_fs_context *ctx = mnt_ctx->fs_ctx;
+	char *full_path;
+	int num_links = 0;
+
+	full_path = build_unc_path_to_root(ctx, cifs_sb, true);
+	if (IS_ERR(full_path))
+		return PTR_ERR(full_path);
+
+	kfree(mnt_ctx->origin_fullpath);
+	mnt_ctx->origin_fullpath = dfs_cache_canonical_path(full_path, cifs_sb->local_nls,
+							    cifs_remap(cifs_sb));
+	kfree(full_path);
+
+	if (IS_ERR(mnt_ctx->origin_fullpath)) {
+		rc = PTR_ERR(mnt_ctx->origin_fullpath);
+		mnt_ctx->origin_fullpath = NULL;
+		return rc;
 	}
 
-	uuid_gen(&mount_id);
-	set_root_ses(cifs_sb, &mount_id, ses, &root_ses);
 	do {
-		/* Save full path of last DFS path we used to resolve final target server */
-		kfree(full_path);
-		full_path = build_unc_path_to_root(ctx, cifs_sb, !!count);
-		if (IS_ERR(full_path)) {
-			rc = PTR_ERR(full_path);
-			full_path = NULL;
-			break;
-		}
-		/* Chase referral */
-		oldmnt = cifs_sb->ctx->mount_options;
-		rc = expand_dfs_referral(xid, root_ses, ctx, cifs_sb, ref_path + 1);
-		if (rc)
+		rc = __follow_dfs_link(mnt_ctx);
+		if (!rc || rc != -EREMOTE)
 			break;
-		/* Connect to new DFS target only if we were redirected */
-		if (oldmnt != cifs_sb->ctx->mount_options) {
-			mount_put_conns(cifs_sb, xid, server, ses, tcon);
-			rc = mount_get_dfs_conns(ctx, cifs_sb, &xid, &server, &ses, &tcon);
-		}
-		if (rc && !server && !ses) {
-			/* Failed to connect. Try to connect to other targets in the referral. */
-			rc = do_dfs_failover(ref_path + 1, full_path, cifs_sb, ctx, root_ses, &xid,
-					     &server, &ses, &tcon);
-		}
-		if (rc == -EACCES || rc == -EOPNOTSUPP || !server || !ses)
-			break;
-		if (!tcon)
-			continue;
+	} while (rc = -ELOOP, ++num_links < MAX_NESTED_LINKS);
 
-		/* Make sure that requests go through new root servers */
-		rc = is_referral_server(ref_path + 1, cifs_sb, tcon, &ref_server);
-		if (rc)
-			break;
-		if (ref_server)
-			set_root_ses(cifs_sb, &mount_id, ses, &root_ses);
+	return rc;
+}
 
-		/* Get next dfs path and then continue chasing them if -EREMOTE */
-		rc = next_dfs_prepath(cifs_sb, ctx, xid, server, tcon, &ref_path);
-		/* Prevent recursion on broken link referrals */
-		if (rc == -EREMOTE && ++count > MAX_NESTED_LINKS)
-			rc = -ELOOP;
-	} while (rc == -EREMOTE);
+/* Set up DFS referral paths for failover */
+static void setup_server_referral_paths(struct mount_ctx *mnt_ctx)
+{
+	struct TCP_Server_Info *server = mnt_ctx->server;
 
-	if (rc || !tcon || !ses)
+	server->origin_fullpath = mnt_ctx->origin_fullpath;
+	server->leaf_fullpath = mnt_ctx->leaf_fullpath;
+	server->current_fullpath = mnt_ctx->leaf_fullpath;
+	mnt_ctx->origin_fullpath = mnt_ctx->leaf_fullpath = NULL;
+}
+
+int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx)
+{
+	int rc;
+	struct mount_ctx mnt_ctx = { .cifs_sb = cifs_sb, .fs_ctx = ctx, };
+	struct dfs_cache_tgt_list tl = DFS_CACHE_TGT_LIST_INIT(tl);
+	bool isdfs;
+
+	rc = is_dfs_mount(&mnt_ctx, &isdfs, &tl);
+	if (rc)
 		goto error;
+	if (!isdfs)
+		goto out;
 
-	kfree(ref_path);
-	/*
-	 * Store DFS full path in both superblock and tree connect structures.
-	 *
-	 * For DFS root mounts, the prefix path (cifs_sb->prepath) is preserved during reconnect so
-	 * only the root path is set in cifs_sb->origin_fullpath and tcon->dfs_path. And for DFS
-	 * links, the prefix path is included in both and may be changed during reconnect.  See
-	 * cifs_tree_connect().
-	 */
-	ref_path = dfs_cache_canonical_path(full_path, cifs_sb->local_nls, cifs_remap(cifs_sb));
-	kfree(full_path);
-	full_path = NULL;
+	uuid_gen(&mnt_ctx.mount_id);
+	rc = connect_dfs_root(&mnt_ctx, &tl);
+	dfs_cache_free_tgts(&tl);
 
-	if (IS_ERR(ref_path)) {
-		rc = PTR_ERR(ref_path);
-		ref_path = NULL;
+	if (rc)
 		goto error;
-	}
-	cifs_sb->origin_fullpath = ref_path;
 
-	ref_path = kstrdup(cifs_sb->origin_fullpath, GFP_KERNEL);
-	if (!ref_path) {
-		rc = -ENOMEM;
+	rc = is_path_remote(&mnt_ctx);
+	if (rc == -EREMOTE)
+		rc = follow_dfs_link(&mnt_ctx);
+	if (rc)
 		goto error;
-	}
-	spin_lock(&cifs_tcp_ses_lock);
-	tcon->dfs_path = ref_path;
-	ref_path = NULL;
-	spin_unlock(&cifs_tcp_ses_lock);
 
+	setup_server_referral_paths(&mnt_ctx);
 	/*
-	 * After reconnecting to a different server, unique ids won't
-	 * match anymore, so we disable serverino. This prevents
-	 * dentry revalidation to think the dentry are stale (ESTALE).
+	 * After reconnecting to a different server, unique ids won't match anymore, so we disable
+	 * serverino. This prevents dentry revalidation to think the dentry are stale (ESTALE).
 	 */
 	cifs_autodisable_serverino(cifs_sb);
 	/*
-	 * Force the use of prefix path to support failover on DFS paths that
-	 * resolve to targets that have different prefix paths.
+	 * Force the use of prefix path to support failover on DFS paths that resolve to targets
+	 * that have different prefix paths.
 	 */
 	cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_USE_PREFIX_PATH;
 	kfree(cifs_sb->prepath);
 	cifs_sb->prepath = ctx->prepath;
 	ctx->prepath = NULL;
-	uuid_copy(&cifs_sb->dfs_mount_id, &mount_id);
+	uuid_copy(&cifs_sb->dfs_mount_id, &mnt_ctx.mount_id);
 
 out:
-	free_xid(xid);
-	cifs_try_adding_channels(cifs_sb, ses);
-	return mount_setup_tlink(cifs_sb, ses, tcon);
+	free_xid(mnt_ctx.xid);
+	cifs_try_adding_channels(cifs_sb, mnt_ctx.ses);
+	return mount_setup_tlink(cifs_sb, mnt_ctx.ses, mnt_ctx.tcon);
 
 error:
-	kfree(ref_path);
-	kfree(full_path);
-	kfree(cifs_sb->origin_fullpath);
-	dfs_cache_put_refsrv_sessions(&mount_id);
-	mount_put_conns(cifs_sb, xid, server, ses, tcon);
+	dfs_cache_put_refsrv_sessions(&mnt_ctx.mount_id);
+	kfree(mnt_ctx.origin_fullpath);
+	kfree(mnt_ctx.leaf_fullpath);
+	mount_put_conns(&mnt_ctx);
 	return rc;
 }
 #else
 int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx)
 {
 	int rc = 0;
-	unsigned int xid;
-	struct cifs_ses *ses;
-	struct cifs_tcon *tcon;
-	struct TCP_Server_Info *server;
+	struct mount_ctx mnt_ctx = { .cifs_sb = cifs_sb, .fs_ctx = ctx, };
 
-	rc = mount_get_conns(ctx, cifs_sb, &xid, &server, &ses, &tcon);
+	rc = mount_get_conns(&mnt_ctx);
 	if (rc)
 		goto error;
 
-	if (tcon) {
-		rc = is_path_remote(cifs_sb, ctx, xid, server, tcon);
+	if (mnt_ctx.tcon) {
+		rc = is_path_remote(&mnt_ctx);
 		if (rc == -EREMOTE)
 			rc = -EOPNOTSUPP;
 		if (rc)
 			goto error;
 	}
 
-	free_xid(xid);
-
-	return mount_setup_tlink(cifs_sb, ses, tcon);
+	free_xid(mnt_ctx.xid);
+	return mount_setup_tlink(cifs_sb, mnt_ctx.ses, mnt_ctx.tcon);
 
 error:
-	mount_put_conns(cifs_sb, xid, server, ses, tcon);
+	mount_put_conns(&mnt_ctx);
 	return rc;
 }
 #endif
@@ -3818,7 +3794,6 @@ cifs_umount(struct cifs_sb_info *cifs_sb)
 	kfree(cifs_sb->prepath);
 #ifdef CONFIG_CIFS_DFS_UPCALL
 	dfs_cache_put_refsrv_sessions(&cifs_sb->dfs_mount_id);
-	kfree(cifs_sb->origin_fullpath);
 #endif
 	call_rcu(&cifs_sb->rcu, delayed_free);
 }
@@ -4145,104 +4120,234 @@ cifs_prune_tlinks(struct work_struct *work)
 }
 
 #ifdef CONFIG_CIFS_DFS_UPCALL
-int cifs_tree_connect(const unsigned int xid, struct cifs_tcon *tcon, const struct nls_table *nlsc)
+/* Update dfs referral path of superblock */
+static int update_server_fullpath(struct TCP_Server_Info *server, struct cifs_sb_info *cifs_sb,
+				  const char *target)
+{
+	int rc = 0;
+	size_t len = strlen(target);
+	char *refpath, *npath;
+
+	if (unlikely(len < 2 || *target != '\\'))
+		return -EINVAL;
+
+	if (target[1] == '\\') {
+		len += 1;
+		refpath = kmalloc(len, GFP_KERNEL);
+		if (!refpath)
+			return -ENOMEM;
+
+		scnprintf(refpath, len, "%s", target);
+	} else {
+		len += sizeof("\\");
+		refpath = kmalloc(len, GFP_KERNEL);
+		if (!refpath)
+			return -ENOMEM;
+
+		scnprintf(refpath, len, "\\%s", target);
+	}
+
+	npath = dfs_cache_canonical_path(refpath, cifs_sb->local_nls, cifs_remap(cifs_sb));
+	kfree(refpath);
+
+	if (IS_ERR(npath)) {
+		rc = PTR_ERR(npath);
+	} else {
+		mutex_lock(&server->refpath_lock);
+		kfree(server->leaf_fullpath);
+		server->leaf_fullpath = npath;
+		mutex_unlock(&server->refpath_lock);
+		server->current_fullpath = server->leaf_fullpath;
+	}
+	return rc;
+}
+
+static int target_share_matches_server(struct TCP_Server_Info *server, const char *tcp_host,
+				       size_t tcp_host_len, char *share, bool *target_match)
+{
+	int rc = 0;
+	const char *dfs_host;
+	size_t dfs_host_len;
+
+	*target_match = true;
+	extract_unc_hostname(share, &dfs_host, &dfs_host_len);
+
+	/* Check if hostnames or addresses match */
+	if (dfs_host_len != tcp_host_len || strncasecmp(dfs_host, tcp_host, dfs_host_len) != 0) {
+		cifs_dbg(FYI, "%s: %.*s doesn't match %.*s\n", __func__, (int)dfs_host_len,
+			 dfs_host, (int)tcp_host_len, tcp_host);
+		rc = match_target_ip(server, dfs_host, dfs_host_len, target_match);
+		if (rc)
+			cifs_dbg(VFS, "%s: failed to match target ip: %d\n", __func__, rc);
+	}
+	return rc;
+}
+
+static int __tree_connect_dfs_target(const unsigned int xid, struct cifs_tcon *tcon,
+				     struct cifs_sb_info *cifs_sb, char *tree, bool islink,
+				     struct dfs_cache_tgt_list *tl)
 {
 	int rc;
 	struct TCP_Server_Info *server = tcon->ses->server;
 	const struct smb_version_operations *ops = server->ops;
-	struct dfs_cache_tgt_list tl;
-	struct dfs_cache_tgt_iterator *it = NULL;
-	char *tree;
+	struct cifs_tcon *ipc = tcon->ses->tcon_ipc;
+	char *share = NULL, *prefix = NULL;
 	const char *tcp_host;
 	size_t tcp_host_len;
-	const char *dfs_host;
-	size_t dfs_host_len;
-	char *share = NULL, *prefix = NULL;
-	struct dfs_info3_param ref = {0};
-	bool isroot;
+	struct dfs_cache_tgt_iterator *tit;
+	bool target_match;
 
-	tree = kzalloc(MAX_TREE_SIZE, GFP_KERNEL);
-	if (!tree)
-		return -ENOMEM;
+	extract_unc_hostname(server->hostname, &tcp_host, &tcp_host_len);
 
-	/* If it is not dfs or there was no cached dfs referral, then reconnect to same share */
-	if (!tcon->dfs_path || dfs_cache_noreq_find(tcon->dfs_path + 1, &ref, &tl)) {
-		if (tcon->ipc) {
-			scnprintf(tree, MAX_TREE_SIZE, "\\\\%s\\IPC$", server->hostname);
-			rc = ops->tree_connect(xid, tcon->ses, tree, tcon, nlsc);
-		} else {
-			rc = ops->tree_connect(xid, tcon->ses, tcon->treeName, tcon, nlsc);
-		}
+	tit = dfs_cache_get_tgt_iterator(tl);
+	if (!tit) {
+		rc = -ENOENT;
 		goto out;
 	}
 
-	isroot = ref.server_type == DFS_TYPE_ROOT;
-	free_dfs_info_param(&ref);
-
-	extract_unc_hostname(server->hostname, &tcp_host, &tcp_host_len);
-
-	for (it = dfs_cache_get_tgt_iterator(&tl); it; it = dfs_cache_get_next_tgt(&tl, it)) {
-		bool target_match;
+	/* Try to tree connect to all dfs targets */
+	for (; tit; tit = dfs_cache_get_next_tgt(tl, tit)) {
+		const char *target = dfs_cache_get_tgt_name(tit);
+		struct dfs_cache_tgt_list ntl = DFS_CACHE_TGT_LIST_INIT(ntl);
 
 		kfree(share);
 		kfree(prefix);
-		share = NULL;
-		prefix = NULL;
+		share = prefix = NULL;
 
-		rc = dfs_cache_get_tgt_share(tcon->dfs_path + 1, it, &share, &prefix);
+		/* Check if share matches with tcp ses */
+		rc = dfs_cache_get_tgt_share(server->current_fullpath + 1, tit, &share, &prefix);
 		if (rc) {
-			cifs_dbg(VFS, "%s: failed to parse target share %d\n",
-				 __func__, rc);
-			continue;
+			cifs_dbg(VFS, "%s: failed to parse target share: %d\n", __func__, rc);
+			break;
 		}
 
-		extract_unc_hostname(share, &dfs_host, &dfs_host_len);
-
-		if (dfs_host_len != tcp_host_len
-		    || strncasecmp(dfs_host, tcp_host, dfs_host_len) != 0) {
-			cifs_dbg(FYI, "%s: %.*s doesn't match %.*s\n", __func__, (int)dfs_host_len,
-				 dfs_host, (int)tcp_host_len, tcp_host);
+		rc = target_share_matches_server(server, tcp_host, tcp_host_len, share,
+						 &target_match);
+		if (rc)
+			break;
+		if (!target_match) {
+			rc = -EHOSTUNREACH;
+			continue;
+		}
 
-			rc = match_target_ip(server, dfs_host, dfs_host_len, &target_match);
-			if (rc) {
-				cifs_dbg(VFS, "%s: failed to match target ip: %d\n", __func__, rc);
+		if (ipc->need_reconnect) {
+			scnprintf(tree, MAX_TREE_SIZE, "\\\\%s\\IPC$", server->hostname);
+			rc = ops->tree_connect(xid, ipc->ses, tree, ipc, cifs_sb->local_nls);
+			if (rc)
 				break;
-			}
-
-			if (!target_match) {
-				cifs_dbg(FYI, "%s: skipping target\n", __func__);
-				continue;
-			}
 		}
 
-		if (tcon->ipc) {
-			scnprintf(tree, MAX_TREE_SIZE, "\\\\%s\\IPC$", share);
-			rc = ops->tree_connect(xid, tcon->ses, tree, tcon, nlsc);
+		scnprintf(tree, MAX_TREE_SIZE, "\\%s", share);
+		if (!islink) {
+			rc = ops->tree_connect(xid, tcon->ses, tree, tcon, cifs_sb->local_nls);
+			break;
+		}
+		/*
+		 * If no dfs referrals were returned from link target, then just do a TREE_CONNECT
+		 * to it.  Otherwise, cache the dfs referral and then mark current tcp ses for
+		 * reconnect so either the demultiplex thread or the echo worker will reconnect to
+		 * newly resolved target.
+		 */
+		if (dfs_cache_find(xid, tcon->ses, cifs_sb->local_nls, cifs_remap(cifs_sb), target,
+				   NULL, &ntl)) {
+			rc = ops->tree_connect(xid, tcon->ses, tree, tcon, cifs_sb->local_nls);
+			if (rc)
+				continue;
+			rc = dfs_cache_noreq_update_tgthint(server->current_fullpath + 1, tit);
+			if (!rc)
+				rc = cifs_update_super_prepath(cifs_sb, prefix);
 		} else {
-			scnprintf(tree, MAX_TREE_SIZE, "\\%s", share);
-			rc = ops->tree_connect(xid, tcon->ses, tree, tcon, nlsc);
-			/* Only handle prefix paths of DFS link targets */
-			if (!rc && !isroot) {
-				rc = update_super_prepath(tcon, prefix);
-				break;
-			}
+			/* Target is another dfs share */
+			rc = update_server_fullpath(server, cifs_sb, target);
+			dfs_cache_free_tgts(tl);
+
+			if (!rc) {
+				rc = -EREMOTE;
+				list_replace_init(&ntl.tl_list, &tl->tl_list);
+			} else
+				dfs_cache_free_tgts(&ntl);
 		}
-		if (rc == -EREMOTE)
-			break;
+		break;
 	}
 
+out:
 	kfree(share);
 	kfree(prefix);
 
-	if (!rc) {
-		if (it)
-			rc = dfs_cache_noreq_update_tgthint(tcon->dfs_path + 1, it);
-		else
-			rc = -ENOENT;
+	return rc;
+}
+
+static int tree_connect_dfs_target(const unsigned int xid, struct cifs_tcon *tcon,
+				   struct cifs_sb_info *cifs_sb, char *tree, bool islink,
+				   struct dfs_cache_tgt_list *tl)
+{
+	int rc;
+	int num_links = 0;
+	struct TCP_Server_Info *server = tcon->ses->server;
+
+	do {
+		rc = __tree_connect_dfs_target(xid, tcon, cifs_sb, tree, islink, tl);
+		if (!rc || rc != -EREMOTE)
+			break;
+	} while (rc = -ELOOP, ++num_links < MAX_NESTED_LINKS);
+	/*
+	 * If we couldn't tree connect to any targets from last referral path, then retry from
+	 * original referral path.
+	 */
+	if (rc && server->current_fullpath != server->origin_fullpath) {
+		server->current_fullpath = server->origin_fullpath;
+		cifs_ses_mark_for_reconnect(tcon->ses);
 	}
-	dfs_cache_free_tgts(&tl);
+
+	dfs_cache_free_tgts(tl);
+	return rc;
+}
+
+int cifs_tree_connect(const unsigned int xid, struct cifs_tcon *tcon, const struct nls_table *nlsc)
+{
+	int rc;
+	struct TCP_Server_Info *server = tcon->ses->server;
+	const struct smb_version_operations *ops = server->ops;
+	struct super_block *sb = NULL;
+	struct cifs_sb_info *cifs_sb;
+	struct dfs_cache_tgt_list tl = DFS_CACHE_TGT_LIST_INIT(tl);
+	char *tree;
+	struct dfs_info3_param ref = {0};
+
+	tree = kzalloc(MAX_TREE_SIZE, GFP_KERNEL);
+	if (!tree)
+		return -ENOMEM;
+
+	if (tcon->ipc) {
+		scnprintf(tree, MAX_TREE_SIZE, "\\\\%s\\IPC$", server->hostname);
+		rc = ops->tree_connect(xid, tcon->ses, tree, tcon, nlsc);
+		goto out;
+	}
+
+	sb = cifs_get_tcp_super(server);
+	if (IS_ERR(sb)) {
+		rc = PTR_ERR(sb);
+		cifs_dbg(VFS, "%s: could not find superblock: %d\n", __func__, rc);
+		goto out;
+	}
+
+	cifs_sb = CIFS_SB(sb);
+
+	/* If it is not dfs or there was no cached dfs referral, then reconnect to same share */
+	if (!server->current_fullpath ||
+	    dfs_cache_noreq_find(server->current_fullpath + 1, &ref, &tl)) {
+		rc = ops->tree_connect(xid, tcon->ses, tcon->treeName, tcon, cifs_sb->local_nls);
+		goto out;
+	}
+
+	rc = tree_connect_dfs_target(xid, tcon, cifs_sb, tree, ref.server_type == DFS_TYPE_LINK,
+				     &tl);
+	free_dfs_info_param(&ref);
+
 out:
 	kfree(tree);
+	cifs_put_tcp_super(sb);
+
 	return rc;
 }
 #else
diff --git a/fs/cifs/dfs_cache.c b/fs/cifs/dfs_cache.c
index 283745592844..e9b0fa2a9614 100644
--- a/fs/cifs/dfs_cache.c
+++ b/fs/cifs/dfs_cache.c
@@ -283,7 +283,7 @@ static int dfscache_proc_show(struct seq_file *m, void *v)
 			seq_printf(m,
 				   "cache entry: path=%s,type=%s,ttl=%d,etime=%ld,hdr_flags=0x%x,ref_flags=0x%x,interlink=%s,path_consumed=%d,expired=%s\n",
 				   ce->path, ce->srvtype == DFS_TYPE_ROOT ? "root" : "link",
-				   ce->ttl, ce->etime.tv_nsec, ce->ref_flags, ce->hdr_flags,
+				   ce->ttl, ce->etime.tv_nsec, ce->hdr_flags, ce->ref_flags,
 				   IS_DFS_INTERLINK(ce->hdr_flags) ? "yes" : "no",
 				   ce->path_consumed, cache_entry_expired(ce) ? "yes" : "no");
 
@@ -1355,18 +1355,13 @@ static void mark_for_reconnect_if_needed(struct cifs_tcon *tcon, struct dfs_cach
 	}
 
 	cifs_dbg(FYI, "%s: no cached or matched targets. mark dfs share for reconnect.\n", __func__);
-	for (i = 0; i < tcon->ses->chan_count; i++) {
-		spin_lock(&GlobalMid_Lock);
-		if (tcon->ses->chans[i].server->tcpStatus != CifsExiting)
-			tcon->ses->chans[i].server->tcpStatus = CifsNeedReconnect;
-		spin_unlock(&GlobalMid_Lock);
-	}
+	cifs_ses_mark_for_reconnect(tcon->ses);
 }
 
 /* Refresh dfs referral of tcon and mark it for reconnect if needed */
-static int refresh_tcon(struct cifs_ses **sessions, struct cifs_tcon *tcon, bool force_refresh)
+static int __refresh_tcon(const char *path, struct cifs_ses **sessions, struct cifs_tcon *tcon,
+			  bool force_refresh)
 {
-	const char *path = tcon->dfs_path + 1;
 	struct cifs_ses *ses;
 	struct cache_entry *ce;
 	struct dfs_info3_param *refs = NULL;
@@ -1422,6 +1417,20 @@ out:
 	return rc;
 }
 
+static int refresh_tcon(struct cifs_ses **sessions, struct cifs_tcon *tcon, bool force_refresh)
+{
+	struct TCP_Server_Info *server = tcon->ses->server;
+
+	mutex_lock(&server->refpath_lock);
+	if (strcasecmp(server->leaf_fullpath, server->origin_fullpath))
+		__refresh_tcon(server->leaf_fullpath + 1, sessions, tcon, force_refresh);
+	mutex_unlock(&server->refpath_lock);
+
+	__refresh_tcon(server->origin_fullpath + 1, sessions, tcon, force_refresh);
+
+	return 0;
+}
+
 /**
  * dfs_cache_remount_fs - remount a DFS share
  *
@@ -1435,6 +1444,7 @@ out:
 int dfs_cache_remount_fs(struct cifs_sb_info *cifs_sb)
 {
 	struct cifs_tcon *tcon;
+	struct TCP_Server_Info *server;
 	struct mount_group *mg;
 	struct cifs_ses *sessions[CACHE_MAX_ENTRIES + 1] = {NULL};
 	int rc;
@@ -1443,13 +1453,15 @@ int dfs_cache_remount_fs(struct cifs_sb_info *cifs_sb)
 		return -EINVAL;
 
 	tcon = cifs_sb_master_tcon(cifs_sb);
-	if (!tcon->dfs_path) {
-		cifs_dbg(FYI, "%s: not a dfs tcon\n", __func__);
+	server = tcon->ses->server;
+
+	if (!server->origin_fullpath) {
+		cifs_dbg(FYI, "%s: not a dfs mount\n", __func__);
 		return 0;
 	}
 
 	if (uuid_is_null(&cifs_sb->dfs_mount_id)) {
-		cifs_dbg(FYI, "%s: tcon has no dfs mount group id\n", __func__);
+		cifs_dbg(FYI, "%s: no dfs mount group id\n", __func__);
 		return -EINVAL;
 	}
 
@@ -1457,7 +1469,7 @@ int dfs_cache_remount_fs(struct cifs_sb_info *cifs_sb)
 	mg = find_mount_group_locked(&cifs_sb->dfs_mount_id);
 	if (IS_ERR(mg)) {
 		mutex_unlock(&mount_group_list_lock);
-		cifs_dbg(FYI, "%s: tcon has ipc session to refresh referral\n", __func__);
+		cifs_dbg(FYI, "%s: no ipc session for refreshing referral\n", __func__);
 		return PTR_ERR(mg);
 	}
 	kref_get(&mg->refcount);
@@ -1498,9 +1510,12 @@ static void refresh_mounts(struct cifs_ses **sessions)
 
 	spin_lock(&cifs_tcp_ses_lock);
 	list_for_each_entry(server, &cifs_tcp_ses_list, tcp_ses_list) {
+		if (!server->is_dfs_conn)
+			continue;
+
 		list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) {
 			list_for_each_entry(tcon, &ses->tcon_list, tcon_list) {
-				if (tcon->dfs_path) {
+				if (!tcon->ipc && !tcon->need_reconnect) {
 					tcon->tc_count++;
 					list_add_tail(&tcon->ulist, &tcons);
 				}
@@ -1510,8 +1525,16 @@ static void refresh_mounts(struct cifs_ses **sessions)
 	spin_unlock(&cifs_tcp_ses_lock);
 
 	list_for_each_entry_safe(tcon, ntcon, &tcons, ulist) {
+		struct TCP_Server_Info *server = tcon->ses->server;
+
 		list_del_init(&tcon->ulist);
-		refresh_tcon(sessions, tcon, false);
+
+		mutex_lock(&server->refpath_lock);
+		if (strcasecmp(server->leaf_fullpath, server->origin_fullpath))
+			__refresh_tcon(server->leaf_fullpath + 1, sessions, tcon, false);
+		mutex_unlock(&server->refpath_lock);
+
+		__refresh_tcon(server->origin_fullpath + 1, sessions, tcon, false);
 		cifs_put_tcon(tcon);
 	}
 }
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 1b855fcb179e..9fee3af83a73 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -2692,12 +2692,23 @@ int cifs_strict_fsync(struct file *file, loff_t start, loff_t end,
 	tcon = tlink_tcon(smbfile->tlink);
 	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOSSYNC)) {
 		server = tcon->ses->server;
-		if (server->ops->flush)
-			rc = server->ops->flush(xid, tcon, &smbfile->fid);
-		else
+		if (server->ops->flush == NULL) {
 			rc = -ENOSYS;
+			goto strict_fsync_exit;
+		}
+
+		if ((OPEN_FMODE(smbfile->f_flags) & FMODE_WRITE) == 0) {
+			smbfile = find_writable_file(CIFS_I(inode), FIND_WR_ANY);
+			if (smbfile) {
+				rc = server->ops->flush(xid, tcon, &smbfile->fid);
+				cifsFileInfo_put(smbfile);
+			} else
+				cifs_dbg(FYI, "ignore fsync for file not open for write\n");
+		} else
+			rc = server->ops->flush(xid, tcon, &smbfile->fid);
 	}
 
+strict_fsync_exit:
 	free_xid(xid);
 	return rc;
 }
@@ -2709,6 +2720,7 @@ int cifs_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 	struct cifs_tcon *tcon;
 	struct TCP_Server_Info *server;
 	struct cifsFileInfo *smbfile = file->private_data;
+	struct inode *inode = file_inode(file);
 	struct cifs_sb_info *cifs_sb = CIFS_FILE_SB(file);
 
 	rc = file_write_and_wait_range(file, start, end);
@@ -2725,12 +2737,23 @@ int cifs_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 	tcon = tlink_tcon(smbfile->tlink);
 	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOSSYNC)) {
 		server = tcon->ses->server;
-		if (server->ops->flush)
-			rc = server->ops->flush(xid, tcon, &smbfile->fid);
-		else
+		if (server->ops->flush == NULL) {
 			rc = -ENOSYS;
+			goto fsync_exit;
+		}
+
+		if ((OPEN_FMODE(smbfile->f_flags) & FMODE_WRITE) == 0) {
+			smbfile = find_writable_file(CIFS_I(inode), FIND_WR_ANY);
+			if (smbfile) {
+				rc = server->ops->flush(xid, tcon, &smbfile->fid);
+				cifsFileInfo_put(smbfile);
+			} else
+				cifs_dbg(FYI, "ignore fsync for file not open for write\n");
+		} else
+			rc = server->ops->flush(xid, tcon, &smbfile->fid);
 	}
 
+fsync_exit:
 	free_xid(xid);
 	return rc;
 }
diff --git a/fs/cifs/fs_context.c b/fs/cifs/fs_context.c
index 38d96a480745..e3ed25dc6f3f 100644
--- a/fs/cifs/fs_context.c
+++ b/fs/cifs/fs_context.c
@@ -308,7 +308,9 @@ smb3_fs_context_dup(struct smb3_fs_context *new_ctx, struct smb3_fs_context *ctx
 	new_ctx->nodename = NULL;
 	new_ctx->username = NULL;
 	new_ctx->password = NULL;
+	new_ctx->server_hostname = NULL;
 	new_ctx->domainname = NULL;
+	new_ctx->workstation_name = NULL;
 	new_ctx->UNC = NULL;
 	new_ctx->source = NULL;
 	new_ctx->iocharset = NULL;
@@ -323,6 +325,7 @@ smb3_fs_context_dup(struct smb3_fs_context *new_ctx, struct smb3_fs_context *ctx
 	DUP_CTX_STR(UNC);
 	DUP_CTX_STR(source);
 	DUP_CTX_STR(domainname);
+	DUP_CTX_STR(workstation_name);
 	DUP_CTX_STR(nodename);
 	DUP_CTX_STR(iocharset);
 
@@ -432,6 +435,42 @@ out:
 }
 
 /*
+ * Remove duplicate path delimiters. Windows is supposed to do that
+ * but there are some bugs that prevent rename from working if there are
+ * multiple delimiters.
+ *
+ * Returns a sanitized duplicate of @path. The caller is responsible for
+ * cleaning up the original.
+ */
+#define IS_DELIM(c) ((c) == '/' || (c) == '\\')
+static char *sanitize_path(char *path)
+{
+	char *cursor1 = path, *cursor2 = path;
+
+	/* skip all prepended delimiters */
+	while (IS_DELIM(*cursor1))
+		cursor1++;
+
+	/* copy the first letter */
+	*cursor2 = *cursor1;
+
+	/* copy the remainder... */
+	while (*(cursor1++)) {
+		/* ... skipping all duplicated delimiters */
+		if (IS_DELIM(*cursor1) && IS_DELIM(*cursor2))
+			continue;
+		*(++cursor2) = *cursor1;
+	}
+
+	/* if the last character is a delimiter, skip it */
+	if (IS_DELIM(*(cursor2 - 1)))
+		cursor2--;
+
+	*(cursor2) = '\0';
+	return kstrdup(path, GFP_KERNEL);
+}
+
+/*
  * Parse a devname into substrings and populate the ctx->UNC and ctx->prepath
  * fields with the result. Returns 0 on success and an error otherwise
  * (e.g. ENOMEM or EINVAL)
@@ -459,6 +498,7 @@ smb3_parse_devname(const char *devname, struct smb3_fs_context *ctx)
 		return -EINVAL;
 
 	/* record the server hostname */
+	kfree(ctx->server_hostname);
 	ctx->server_hostname = kstrndup(devname + 2, pos - devname - 2, GFP_KERNEL);
 	if (!ctx->server_hostname)
 		return -ENOMEM;
@@ -489,7 +529,7 @@ smb3_parse_devname(const char *devname, struct smb3_fs_context *ctx)
 	if (!*pos)
 		return 0;
 
-	ctx->prepath = kstrdup(pos, GFP_KERNEL);
+	ctx->prepath = sanitize_path(pos);
 	if (!ctx->prepath)
 		return -ENOMEM;
 
@@ -720,6 +760,11 @@ static int smb3_verify_reconfigure_ctx(struct fs_context *fc,
 		cifs_errorf(fc, "can not change domainname during remount\n");
 		return -EINVAL;
 	}
+	if (new_ctx->workstation_name &&
+	    (!old_ctx->workstation_name || strcmp(new_ctx->workstation_name, old_ctx->workstation_name))) {
+		cifs_errorf(fc, "can not change workstation_name during remount\n");
+		return -EINVAL;
+	}
 	if (new_ctx->nodename &&
 	    (!old_ctx->nodename || strcmp(new_ctx->nodename, old_ctx->nodename))) {
 		cifs_errorf(fc, "can not change nodename during remount\n");
@@ -753,7 +798,8 @@ static int smb3_reconfigure(struct fs_context *fc)
 		return rc;
 
 	/*
-	 * We can not change UNC/username/password/domainname/nodename/iocharset
+	 * We can not change UNC/username/password/domainname/
+	 * workstation_name/nodename/iocharset
 	 * during reconnect so ignore what we have in the new context and
 	 * just use what we already have in cifs_sb->ctx.
 	 */
@@ -762,6 +808,7 @@ static int smb3_reconfigure(struct fs_context *fc)
 	STEAL_STRING(cifs_sb, ctx, username);
 	STEAL_STRING(cifs_sb, ctx, password);
 	STEAL_STRING(cifs_sb, ctx, domainname);
+	STEAL_STRING(cifs_sb, ctx, workstation_name);
 	STEAL_STRING(cifs_sb, ctx, nodename);
 	STEAL_STRING(cifs_sb, ctx, iocharset);
 
@@ -1414,13 +1461,22 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
 
 int smb3_init_fs_context(struct fs_context *fc)
 {
+	int rc;
 	struct smb3_fs_context *ctx;
 	char *nodename = utsname()->nodename;
 	int i;
 
 	ctx = kzalloc(sizeof(struct smb3_fs_context), GFP_KERNEL);
-	if (unlikely(!ctx))
-		return -ENOMEM;
+	if (unlikely(!ctx)) {
+		rc = -ENOMEM;
+		goto err_exit;
+	}
+
+	ctx->workstation_name = kstrdup(nodename, GFP_KERNEL);
+	if (unlikely(!ctx->workstation_name)) {
+		rc = -ENOMEM;
+		goto err_exit;
+	}
 
 	/*
 	 * does not have to be perfect mapping since field is
@@ -1493,6 +1549,14 @@ int smb3_init_fs_context(struct fs_context *fc)
 	fc->fs_private = ctx;
 	fc->ops = &smb3_fs_context_ops;
 	return 0;
+
+err_exit:
+	if (ctx) {
+		kfree(ctx->workstation_name);
+		kfree(ctx);
+	}
+
+	return rc;
 }
 
 void
@@ -1518,6 +1582,8 @@ smb3_cleanup_fs_context_contents(struct smb3_fs_context *ctx)
 	ctx->source = NULL;
 	kfree(ctx->domainname);
 	ctx->domainname = NULL;
+	kfree(ctx->workstation_name);
+	ctx->workstation_name = NULL;
 	kfree(ctx->nodename);
 	ctx->nodename = NULL;
 	kfree(ctx->iocharset);
diff --git a/fs/cifs/fs_context.h b/fs/cifs/fs_context.h
index b2d22cf9cb18..e54090d9ef36 100644
--- a/fs/cifs/fs_context.h
+++ b/fs/cifs/fs_context.h
@@ -170,6 +170,7 @@ struct smb3_fs_context {
 	char *server_hostname;
 	char *UNC;
 	char *nodename;
+	char *workstation_name;
 	char *iocharset;  /* local code page for mapping to and from Unicode */
 	char source_rfc1001_name[RFC1001_NAME_LEN_WITH_NULL]; /* clnt nb name */
 	char target_rfc1001_name[RFC1001_NAME_LEN_WITH_NULL]; /* srvr nb name */
diff --git a/fs/cifs/fscache.c b/fs/cifs/fscache.c
index 8eedd20c44ab..003c5f1f4dfb 100644
--- a/fs/cifs/fscache.c
+++ b/fs/cifs/fscache.c
@@ -16,14 +16,7 @@
  * Key layout of CIFS server cache index object
  */
 struct cifs_server_key {
-	struct {
-		uint16_t	family;		/* address family */
-		__be16		port;		/* IP port */
-	} hdr;
-	union {
-		struct in_addr	ipv4_addr;
-		struct in6_addr	ipv6_addr;
-	};
+	__u64 conn_id;
 } __packed;
 
 /*
@@ -31,42 +24,23 @@ struct cifs_server_key {
  */
 void cifs_fscache_get_client_cookie(struct TCP_Server_Info *server)
 {
-	const struct sockaddr *sa = (struct sockaddr *) &server->dstaddr;
-	const struct sockaddr_in *addr = (struct sockaddr_in *) sa;
-	const struct sockaddr_in6 *addr6 = (struct sockaddr_in6 *) sa;
 	struct cifs_server_key key;
-	uint16_t key_len = sizeof(key.hdr);
-
-	memset(&key, 0, sizeof(key));
 
 	/*
-	 * Should not be a problem as sin_family/sin6_family overlays
-	 * sa_family field
+	 * Check if cookie was already initialized so don't reinitialize it.
+	 * In the future, as we integrate with newer fscache features,
+	 * we may want to instead add a check if cookie has changed
 	 */
-	key.hdr.family = sa->sa_family;
-	switch (sa->sa_family) {
-	case AF_INET:
-		key.hdr.port = addr->sin_port;
-		key.ipv4_addr = addr->sin_addr;
-		key_len += sizeof(key.ipv4_addr);
-		break;
-
-	case AF_INET6:
-		key.hdr.port = addr6->sin6_port;
-		key.ipv6_addr = addr6->sin6_addr;
-		key_len += sizeof(key.ipv6_addr);
-		break;
-
-	default:
-		cifs_dbg(VFS, "Unknown network family '%d'\n", sa->sa_family);
-		server->fscache = NULL;
+	if (server->fscache)
 		return;
-	}
+
+	memset(&key, 0, sizeof(key));
+	key.conn_id = server->conn_id;
 
 	server->fscache =
 		fscache_acquire_cookie(cifs_fscache_netfs.primary_index,
 				       &cifs_fscache_server_index_def,
-				       &key, key_len,
+				       &key, sizeof(key),
 				       NULL, 0,
 				       server, 0, true);
 	cifs_dbg(FYI, "%s: (0x%p/0x%p)\n",
@@ -87,6 +61,14 @@ void cifs_fscache_get_super_cookie(struct cifs_tcon *tcon)
 	char *sharename;
 	struct cifs_fscache_super_auxdata auxdata;
 
+	/*
+	 * Check if cookie was already initialized so don't reinitialize it.
+	 * In the future, as we integrate with newer fscache features,
+	 * we may want to instead add a check if cookie has changed
+	 */
+	if (tcon->fscache)
+		return;
+
 	sharename = extract_sharename(tcon->treeName);
 	if (IS_ERR(sharename)) {
 		cifs_dbg(FYI, "%s: couldn't extract sharename\n", __func__);
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 82848412ad85..279622e4eb1c 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -1356,11 +1356,6 @@ iget_no_retry:
 		goto out;
 	}
 
-#ifdef CONFIG_CIFS_FSCACHE
-	/* populate tcon->resource_id */
-	tcon->resource_id = CIFS_I(inode)->uniqueid;
-#endif
-
 	if (rc && tcon->pipe) {
 		cifs_dbg(FYI, "ipc connection - fake read inode\n");
 		spin_lock(&inode->i_lock);
@@ -1375,7 +1370,6 @@ iget_no_retry:
 		iget_failed(inode);
 		inode = ERR_PTR(rc);
 	}
-
 out:
 	kfree(path);
 	free_xid(xid);
diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c
index ba2c3e897b29..5148d48d6a35 100644
--- a/fs/cifs/misc.c
+++ b/fs/cifs/misc.c
@@ -75,6 +75,7 @@ sesInfoAlloc(void)
 		INIT_LIST_HEAD(&ret_buf->tcon_list);
 		mutex_init(&ret_buf->session_mutex);
 		spin_lock_init(&ret_buf->iface_lock);
+		spin_lock_init(&ret_buf->chan_lock);
 	}
 	return ret_buf;
 }
@@ -94,6 +95,7 @@ sesInfoFree(struct cifs_ses *buf_to_free)
 	kfree_sensitive(buf_to_free->password);
 	kfree(buf_to_free->user_name);
 	kfree(buf_to_free->domainName);
+	kfree(buf_to_free->workstation_name);
 	kfree_sensitive(buf_to_free->auth_key.response);
 	kfree(buf_to_free->iface_list);
 	kfree_sensitive(buf_to_free);
@@ -138,9 +140,6 @@ tconInfoFree(struct cifs_tcon *buf_to_free)
 	kfree(buf_to_free->nativeFileSystem);
 	kfree_sensitive(buf_to_free->password);
 	kfree(buf_to_free->crfid.fid);
-#ifdef CONFIG_CIFS_DFS_UPCALL
-	kfree(buf_to_free->dfs_path);
-#endif
 	kfree(buf_to_free);
 }
 
@@ -1287,69 +1286,20 @@ out:
 	return rc;
 }
 
-static void tcon_super_cb(struct super_block *sb, void *arg)
+int cifs_update_super_prepath(struct cifs_sb_info *cifs_sb, char *prefix)
 {
-	struct super_cb_data *sd = arg;
-	struct cifs_tcon *tcon = sd->data;
-	struct cifs_sb_info *cifs_sb;
-
-	if (sd->sb)
-		return;
-
-	cifs_sb = CIFS_SB(sb);
-	if (tcon->dfs_path && cifs_sb->origin_fullpath &&
-	    !strcasecmp(tcon->dfs_path, cifs_sb->origin_fullpath))
-		sd->sb = sb;
-}
-
-static inline struct super_block *cifs_get_tcon_super(struct cifs_tcon *tcon)
-{
-	return __cifs_get_super(tcon_super_cb, tcon);
-}
-
-static inline void cifs_put_tcon_super(struct super_block *sb)
-{
-	__cifs_put_super(sb);
-}
-#else
-static inline struct super_block *cifs_get_tcon_super(struct cifs_tcon *tcon)
-{
-	return ERR_PTR(-EOPNOTSUPP);
-}
-
-static inline void cifs_put_tcon_super(struct super_block *sb)
-{
-}
-#endif
-
-int update_super_prepath(struct cifs_tcon *tcon, char *prefix)
-{
-	struct super_block *sb;
-	struct cifs_sb_info *cifs_sb;
-	int rc = 0;
-
-	sb = cifs_get_tcon_super(tcon);
-	if (IS_ERR(sb))
-		return PTR_ERR(sb);
-
-	cifs_sb = CIFS_SB(sb);
-
 	kfree(cifs_sb->prepath);
 
 	if (prefix && *prefix) {
 		cifs_sb->prepath = kstrdup(prefix, GFP_ATOMIC);
-		if (!cifs_sb->prepath) {
-			rc = -ENOMEM;
-			goto out;
-		}
+		if (!cifs_sb->prepath)
+			return -ENOMEM;
 
 		convert_delimiter(cifs_sb->prepath, CIFS_DIR_SEP(cifs_sb));
 	} else
 		cifs_sb->prepath = NULL;
 
 	cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_USE_PREFIX_PATH;
-
-out:
-	cifs_put_tcon_super(sb);
-	return rc;
+	return 0;
 }
+#endif
diff --git a/fs/cifs/ntlmssp.h b/fs/cifs/ntlmssp.h
index 25a2b8ef88b9..fe707f45da89 100644
--- a/fs/cifs/ntlmssp.h
+++ b/fs/cifs/ntlmssp.h
@@ -119,7 +119,9 @@ typedef struct _AUTHENTICATE_MESSAGE {
  */
 
 int decode_ntlmssp_challenge(char *bcc_ptr, int blob_len, struct cifs_ses *ses);
-void build_ntlmssp_negotiate_blob(unsigned char *pbuffer, struct cifs_ses *ses);
+int build_ntlmssp_negotiate_blob(unsigned char **pbuffer, u16 *buflen,
+				 struct cifs_ses *ses,
+				 const struct nls_table *nls_cp);
 int build_ntlmssp_auth_blob(unsigned char **pbuffer, u16 *buflen,
 			struct cifs_ses *ses,
 			const struct nls_table *nls_cp);
diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c
index 23e02db7923f..035dc3e245dc 100644
--- a/fs/cifs/sess.c
+++ b/fs/cifs/sess.c
@@ -54,41 +54,53 @@ bool is_ses_using_iface(struct cifs_ses *ses, struct cifs_server_iface *iface)
 {
 	int i;
 
+	spin_lock(&ses->chan_lock);
 	for (i = 0; i < ses->chan_count; i++) {
-		if (is_server_using_iface(ses->chans[i].server, iface))
+		if (is_server_using_iface(ses->chans[i].server, iface)) {
+			spin_unlock(&ses->chan_lock);
 			return true;
+		}
 	}
+	spin_unlock(&ses->chan_lock);
 	return false;
 }
 
 /* returns number of channels added */
 int cifs_try_adding_channels(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses)
 {
-	int old_chan_count = ses->chan_count;
-	int left = ses->chan_max - ses->chan_count;
+	int old_chan_count, new_chan_count;
+	int left;
 	int i = 0;
 	int rc = 0;
 	int tries = 0;
 	struct cifs_server_iface *ifaces = NULL;
 	size_t iface_count;
 
+	if (ses->server->dialect < SMB30_PROT_ID) {
+		cifs_dbg(VFS, "multichannel is not supported on this protocol version, use 3.0 or above\n");
+		return 0;
+	}
+
+	spin_lock(&ses->chan_lock);
+
+	new_chan_count = old_chan_count = ses->chan_count;
+	left = ses->chan_max - ses->chan_count;
+
 	if (left <= 0) {
 		cifs_dbg(FYI,
 			 "ses already at max_channels (%zu), nothing to open\n",
 			 ses->chan_max);
-		return 0;
-	}
-
-	if (ses->server->dialect < SMB30_PROT_ID) {
-		cifs_dbg(VFS, "multichannel is not supported on this protocol version, use 3.0 or above\n");
+		spin_unlock(&ses->chan_lock);
 		return 0;
 	}
 
 	if (!(ses->server->capabilities & SMB2_GLOBAL_CAP_MULTI_CHANNEL)) {
-		cifs_dbg(VFS, "server %s does not support multichannel\n", ses->server->hostname);
 		ses->chan_max = 1;
+		spin_unlock(&ses->chan_lock);
+		cifs_dbg(VFS, "server %s does not support multichannel\n", ses->server->hostname);
 		return 0;
 	}
+	spin_unlock(&ses->chan_lock);
 
 	/*
 	 * Make a copy of the iface list at the time and use that
@@ -142,10 +154,11 @@ int cifs_try_adding_channels(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses)
 		cifs_dbg(FYI, "successfully opened new channel on iface#%d\n",
 			 i);
 		left--;
+		new_chan_count++;
 	}
 
 	kfree(ifaces);
-	return ses->chan_count - old_chan_count;
+	return new_chan_count - old_chan_count;
 }
 
 /*
@@ -157,10 +170,14 @@ cifs_ses_find_chan(struct cifs_ses *ses, struct TCP_Server_Info *server)
 {
 	int i;
 
+	spin_lock(&ses->chan_lock);
 	for (i = 0; i < ses->chan_count; i++) {
-		if (ses->chans[i].server == server)
+		if (ses->chans[i].server == server) {
+			spin_unlock(&ses->chan_lock);
 			return &ses->chans[i];
+		}
 	}
+	spin_unlock(&ses->chan_lock);
 	return NULL;
 }
 
@@ -168,6 +185,7 @@ static int
 cifs_ses_add_channel(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses,
 		     struct cifs_server_iface *iface)
 {
+	struct TCP_Server_Info *chan_server;
 	struct cifs_chan *chan;
 	struct smb3_fs_context ctx = {NULL};
 	static const char unc_fmt[] = "\\%s\\foo";
@@ -204,6 +222,7 @@ cifs_ses_add_channel(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses,
 	/* Auth */
 	ctx.domainauto = ses->domainAuto;
 	ctx.domainname = ses->domainName;
+	ctx.server_hostname = ses->server->hostname;
 	ctx.username = ses->user_name;
 	ctx.password = ses->password;
 	ctx.sectype = ses->sectype;
@@ -240,18 +259,19 @@ cifs_ses_add_channel(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses,
 	       SMB2_CLIENT_GUID_SIZE);
 	ctx.use_client_guid = true;
 
-	mutex_lock(&ses->session_mutex);
+	chan_server = cifs_get_tcp_session(&ctx, ses->server);
 
+	mutex_lock(&ses->session_mutex);
+	spin_lock(&ses->chan_lock);
 	chan = ses->binding_chan = &ses->chans[ses->chan_count];
-	chan->server = cifs_get_tcp_session(&ctx);
+	chan->server = chan_server;
 	if (IS_ERR(chan->server)) {
 		rc = PTR_ERR(chan->server);
 		chan->server = NULL;
+		spin_unlock(&ses->chan_lock);
 		goto out;
 	}
-	spin_lock(&cifs_tcp_ses_lock);
-	chan->server->is_channel = true;
-	spin_unlock(&cifs_tcp_ses_lock);
+	spin_unlock(&ses->chan_lock);
 
 	/*
 	 * We need to allocate the server crypto now as we will need
@@ -283,8 +303,11 @@ cifs_ses_add_channel(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses,
 	 * ses to the new server.
 	 */
 
+	spin_lock(&ses->chan_lock);
 	ses->chan_count++;
 	atomic_set(&ses->chan_seq, 0);
+	spin_unlock(&ses->chan_lock);
+
 out:
 	ses->binding = false;
 	ses->binding_chan = NULL;
@@ -296,6 +319,19 @@ out:
 	return rc;
 }
 
+/* Mark all session channels for reconnect */
+void cifs_ses_mark_for_reconnect(struct cifs_ses *ses)
+{
+	int i;
+
+	for (i = 0; i < ses->chan_count; i++) {
+		spin_lock(&GlobalMid_Lock);
+		if (ses->chans[i].server->tcpStatus != CifsExiting)
+			ses->chans[i].server->tcpStatus = CifsNeedReconnect;
+		spin_unlock(&GlobalMid_Lock);
+	}
+}
+
 static __u32 cifs_ssetup_hdr(struct cifs_ses *ses, SESSION_SETUP_ANDX *pSMB)
 {
 	__u32 capabilities = 0;
@@ -554,8 +590,8 @@ int decode_ntlmssp_challenge(char *bcc_ptr, int blob_len,
 {
 	unsigned int tioffset; /* challenge message target info area */
 	unsigned int tilen; /* challenge message target info area length  */
-
 	CHALLENGE_MESSAGE *pblob = (CHALLENGE_MESSAGE *)bcc_ptr;
+	__u32 server_flags;
 
 	if (blob_len < sizeof(CHALLENGE_MESSAGE)) {
 		cifs_dbg(VFS, "challenge blob len %d too small\n", blob_len);
@@ -573,12 +609,37 @@ int decode_ntlmssp_challenge(char *bcc_ptr, int blob_len,
 		return -EINVAL;
 	}
 
+	server_flags = le32_to_cpu(pblob->NegotiateFlags);
+	cifs_dbg(FYI, "%s: negotiate=0x%08x challenge=0x%08x\n", __func__,
+		 ses->ntlmssp->client_flags, server_flags);
+
+	if ((ses->ntlmssp->client_flags & (NTLMSSP_NEGOTIATE_SEAL | NTLMSSP_NEGOTIATE_SIGN)) &&
+	    (!(server_flags & NTLMSSP_NEGOTIATE_56) && !(server_flags & NTLMSSP_NEGOTIATE_128))) {
+		cifs_dbg(VFS, "%s: requested signing/encryption but server did not return either 56-bit or 128-bit session key size\n",
+			 __func__);
+		return -EINVAL;
+	}
+	if (!(server_flags & NTLMSSP_NEGOTIATE_NTLM) && !(server_flags & NTLMSSP_NEGOTIATE_EXTENDED_SEC)) {
+		cifs_dbg(VFS, "%s: server does not seem to support either NTLMv1 or NTLMv2\n", __func__);
+		return -EINVAL;
+	}
+	if (ses->server->sign && !(server_flags & NTLMSSP_NEGOTIATE_SIGN)) {
+		cifs_dbg(VFS, "%s: forced packet signing but server does not seem to support it\n",
+			 __func__);
+		return -EOPNOTSUPP;
+	}
+	if ((ses->ntlmssp->client_flags & NTLMSSP_NEGOTIATE_KEY_XCH) &&
+	    !(server_flags & NTLMSSP_NEGOTIATE_KEY_XCH))
+		pr_warn_once("%s: authentication has been weakened as server does not support key exchange\n",
+			     __func__);
+
+	ses->ntlmssp->server_flags = server_flags;
+
 	memcpy(ses->ntlmssp->cryptkey, pblob->Challenge, CIFS_CRYPTO_KEY_SIZE);
-	/* BB we could decode pblob->NegotiateFlags; some may be useful */
 	/* In particular we can examine sign flags */
 	/* BB spec says that if AvId field of MsvAvTimestamp is populated then
 		we must set the MIC field of the AUTHENTICATE_MESSAGE */
-	ses->ntlmssp->server_flags = le32_to_cpu(pblob->NegotiateFlags);
+
 	tioffset = le32_to_cpu(pblob->TargetInfoArray.BufferOffset);
 	tilen = le16_to_cpu(pblob->TargetInfoArray.Length);
 	if (tioffset > blob_len || tioffset + tilen > blob_len) {
@@ -599,18 +660,85 @@ int decode_ntlmssp_challenge(char *bcc_ptr, int blob_len,
 	return 0;
 }
 
+static int size_of_ntlmssp_blob(struct cifs_ses *ses, int base_size)
+{
+	int sz = base_size + ses->auth_key.len
+		- CIFS_SESS_KEY_SIZE + CIFS_CPHTXT_SIZE + 2;
+
+	if (ses->domainName)
+		sz += sizeof(__le16) * strnlen(ses->domainName, CIFS_MAX_DOMAINNAME_LEN);
+	else
+		sz += sizeof(__le16);
+
+	if (ses->user_name)
+		sz += sizeof(__le16) * strnlen(ses->user_name, CIFS_MAX_USERNAME_LEN);
+	else
+		sz += sizeof(__le16);
+
+	sz += sizeof(__le16) * strnlen(ses->workstation_name, CIFS_MAX_WORKSTATION_LEN);
+
+	return sz;
+}
+
+static inline void cifs_security_buffer_from_str(SECURITY_BUFFER *pbuf,
+						 char *str_value,
+						 int str_length,
+						 unsigned char *pstart,
+						 unsigned char **pcur,
+						 const struct nls_table *nls_cp)
+{
+	unsigned char *tmp = pstart;
+	int len;
+
+	if (!pbuf)
+		return;
+
+	if (!pcur)
+		pcur = &tmp;
+
+	if (!str_value) {
+		pbuf->BufferOffset = cpu_to_le32(*pcur - pstart);
+		pbuf->Length = 0;
+		pbuf->MaximumLength = 0;
+		*pcur += sizeof(__le16);
+	} else {
+		len = cifs_strtoUTF16((__le16 *)*pcur,
+				      str_value,
+				      str_length,
+				      nls_cp);
+		len *= sizeof(__le16);
+		pbuf->BufferOffset = cpu_to_le32(*pcur - pstart);
+		pbuf->Length = cpu_to_le16(len);
+		pbuf->MaximumLength = cpu_to_le16(len);
+		*pcur += len;
+	}
+}
+
 /* BB Move to ntlmssp.c eventually */
 
-/* We do not malloc the blob, it is passed in pbuffer, because
-   it is fixed size, and small, making this approach cleaner */
-void build_ntlmssp_negotiate_blob(unsigned char *pbuffer,
-					 struct cifs_ses *ses)
+int build_ntlmssp_negotiate_blob(unsigned char **pbuffer,
+				 u16 *buflen,
+				 struct cifs_ses *ses,
+				 const struct nls_table *nls_cp)
 {
+	int rc = 0;
 	struct TCP_Server_Info *server = cifs_ses_server(ses);
-	NEGOTIATE_MESSAGE *sec_blob = (NEGOTIATE_MESSAGE *)pbuffer;
+	NEGOTIATE_MESSAGE *sec_blob;
 	__u32 flags;
+	unsigned char *tmp;
+	int len;
+
+	len = size_of_ntlmssp_blob(ses, sizeof(NEGOTIATE_MESSAGE));
+	*pbuffer = kmalloc(len, GFP_KERNEL);
+	if (!*pbuffer) {
+		rc = -ENOMEM;
+		cifs_dbg(VFS, "Error %d during NTLMSSP allocation\n", rc);
+		*buflen = 0;
+		goto setup_ntlm_neg_ret;
+	}
+	sec_blob = (NEGOTIATE_MESSAGE *)*pbuffer;
 
-	memset(pbuffer, 0, sizeof(NEGOTIATE_MESSAGE));
+	memset(*pbuffer, 0, sizeof(NEGOTIATE_MESSAGE));
 	memcpy(sec_blob->Signature, NTLMSSP_SIGNATURE, 8);
 	sec_blob->MessageType = NtLmNegotiate;
 
@@ -618,40 +746,31 @@ void build_ntlmssp_negotiate_blob(unsigned char *pbuffer,
 	flags = NTLMSSP_NEGOTIATE_56 |	NTLMSSP_REQUEST_TARGET |
 		NTLMSSP_NEGOTIATE_128 | NTLMSSP_NEGOTIATE_UNICODE |
 		NTLMSSP_NEGOTIATE_NTLM | NTLMSSP_NEGOTIATE_EXTENDED_SEC |
-		NTLMSSP_NEGOTIATE_SEAL;
-	if (server->sign)
-		flags |= NTLMSSP_NEGOTIATE_SIGN;
+		NTLMSSP_NEGOTIATE_ALWAYS_SIGN | NTLMSSP_NEGOTIATE_SEAL |
+		NTLMSSP_NEGOTIATE_SIGN;
 	if (!server->session_estab || ses->ntlmssp->sesskey_per_smbsess)
 		flags |= NTLMSSP_NEGOTIATE_KEY_XCH;
 
+	tmp = *pbuffer + sizeof(NEGOTIATE_MESSAGE);
+	ses->ntlmssp->client_flags = flags;
 	sec_blob->NegotiateFlags = cpu_to_le32(flags);
 
-	sec_blob->WorkstationName.BufferOffset = 0;
-	sec_blob->WorkstationName.Length = 0;
-	sec_blob->WorkstationName.MaximumLength = 0;
+	/* these fields should be null in negotiate phase MS-NLMP 3.1.5.1.1 */
+	cifs_security_buffer_from_str(&sec_blob->DomainName,
+				      NULL,
+				      CIFS_MAX_DOMAINNAME_LEN,
+				      *pbuffer, &tmp,
+				      nls_cp);
 
-	/* Domain name is sent on the Challenge not Negotiate NTLMSSP request */
-	sec_blob->DomainName.BufferOffset = 0;
-	sec_blob->DomainName.Length = 0;
-	sec_blob->DomainName.MaximumLength = 0;
-}
-
-static int size_of_ntlmssp_blob(struct cifs_ses *ses)
-{
-	int sz = sizeof(AUTHENTICATE_MESSAGE) + ses->auth_key.len
-		- CIFS_SESS_KEY_SIZE + CIFS_CPHTXT_SIZE + 2;
-
-	if (ses->domainName)
-		sz += 2 * strnlen(ses->domainName, CIFS_MAX_DOMAINNAME_LEN);
-	else
-		sz += 2;
-
-	if (ses->user_name)
-		sz += 2 * strnlen(ses->user_name, CIFS_MAX_USERNAME_LEN);
-	else
-		sz += 2;
+	cifs_security_buffer_from_str(&sec_blob->WorkstationName,
+				      NULL,
+				      CIFS_MAX_WORKSTATION_LEN,
+				      *pbuffer, &tmp,
+				      nls_cp);
 
-	return sz;
+	*buflen = tmp - *pbuffer;
+setup_ntlm_neg_ret:
+	return rc;
 }
 
 int build_ntlmssp_auth_blob(unsigned char **pbuffer,
@@ -663,6 +782,7 @@ int build_ntlmssp_auth_blob(unsigned char **pbuffer,
 	AUTHENTICATE_MESSAGE *sec_blob;
 	__u32 flags;
 	unsigned char *tmp;
+	int len;
 
 	rc = setup_ntlmv2_rsp(ses, nls_cp);
 	if (rc) {
@@ -670,7 +790,9 @@ int build_ntlmssp_auth_blob(unsigned char **pbuffer,
 		*buflen = 0;
 		goto setup_ntlmv2_ret;
 	}
-	*pbuffer = kmalloc(size_of_ntlmssp_blob(ses), GFP_KERNEL);
+
+	len = size_of_ntlmssp_blob(ses, sizeof(AUTHENTICATE_MESSAGE));
+	*pbuffer = kmalloc(len, GFP_KERNEL);
 	if (!*pbuffer) {
 		rc = -ENOMEM;
 		cifs_dbg(VFS, "Error %d during NTLMSSP allocation\n", rc);
@@ -682,15 +804,8 @@ int build_ntlmssp_auth_blob(unsigned char **pbuffer,
 	memcpy(sec_blob->Signature, NTLMSSP_SIGNATURE, 8);
 	sec_blob->MessageType = NtLmAuthenticate;
 
-	flags = NTLMSSP_NEGOTIATE_56 |
-		NTLMSSP_REQUEST_TARGET | NTLMSSP_NEGOTIATE_TARGET_INFO |
-		NTLMSSP_NEGOTIATE_128 | NTLMSSP_NEGOTIATE_UNICODE |
-		NTLMSSP_NEGOTIATE_NTLM | NTLMSSP_NEGOTIATE_EXTENDED_SEC |
-		NTLMSSP_NEGOTIATE_SEAL;
-	if (ses->server->sign)
-		flags |= NTLMSSP_NEGOTIATE_SIGN;
-	if (!ses->server->session_estab || ses->ntlmssp->sesskey_per_smbsess)
-		flags |= NTLMSSP_NEGOTIATE_KEY_XCH;
+	flags = ses->ntlmssp->server_flags | NTLMSSP_REQUEST_TARGET |
+		NTLMSSP_NEGOTIATE_TARGET_INFO | NTLMSSP_NEGOTIATE_WORKSTATION_SUPPLIED;
 
 	tmp = *pbuffer + sizeof(AUTHENTICATE_MESSAGE);
 	sec_blob->NegotiateFlags = cpu_to_le32(flags);
@@ -719,46 +834,27 @@ int build_ntlmssp_auth_blob(unsigned char **pbuffer,
 		sec_blob->NtChallengeResponse.MaximumLength = 0;
 	}
 
-	if (ses->domainName == NULL) {
-		sec_blob->DomainName.BufferOffset = cpu_to_le32(tmp - *pbuffer);
-		sec_blob->DomainName.Length = 0;
-		sec_blob->DomainName.MaximumLength = 0;
-		tmp += 2;
-	} else {
-		int len;
-		len = cifs_strtoUTF16((__le16 *)tmp, ses->domainName,
-				      CIFS_MAX_DOMAINNAME_LEN, nls_cp);
-		len *= 2; /* unicode is 2 bytes each */
-		sec_blob->DomainName.BufferOffset = cpu_to_le32(tmp - *pbuffer);
-		sec_blob->DomainName.Length = cpu_to_le16(len);
-		sec_blob->DomainName.MaximumLength = cpu_to_le16(len);
-		tmp += len;
-	}
-
-	if (ses->user_name == NULL) {
-		sec_blob->UserName.BufferOffset = cpu_to_le32(tmp - *pbuffer);
-		sec_blob->UserName.Length = 0;
-		sec_blob->UserName.MaximumLength = 0;
-		tmp += 2;
-	} else {
-		int len;
-		len = cifs_strtoUTF16((__le16 *)tmp, ses->user_name,
-				      CIFS_MAX_USERNAME_LEN, nls_cp);
-		len *= 2; /* unicode is 2 bytes each */
-		sec_blob->UserName.BufferOffset = cpu_to_le32(tmp - *pbuffer);
-		sec_blob->UserName.Length = cpu_to_le16(len);
-		sec_blob->UserName.MaximumLength = cpu_to_le16(len);
-		tmp += len;
-	}
-
-	sec_blob->WorkstationName.BufferOffset = cpu_to_le32(tmp - *pbuffer);
-	sec_blob->WorkstationName.Length = 0;
-	sec_blob->WorkstationName.MaximumLength = 0;
-	tmp += 2;
-
-	if (((ses->ntlmssp->server_flags & NTLMSSP_NEGOTIATE_KEY_XCH) ||
-		(ses->ntlmssp->server_flags & NTLMSSP_NEGOTIATE_EXTENDED_SEC))
-			&& !calc_seckey(ses)) {
+	cifs_security_buffer_from_str(&sec_blob->DomainName,
+				      ses->domainName,
+				      CIFS_MAX_DOMAINNAME_LEN,
+				      *pbuffer, &tmp,
+				      nls_cp);
+
+	cifs_security_buffer_from_str(&sec_blob->UserName,
+				      ses->user_name,
+				      CIFS_MAX_USERNAME_LEN,
+				      *pbuffer, &tmp,
+				      nls_cp);
+
+	cifs_security_buffer_from_str(&sec_blob->WorkstationName,
+				      ses->workstation_name,
+				      CIFS_MAX_WORKSTATION_LEN,
+				      *pbuffer, &tmp,
+				      nls_cp);
+
+	if ((ses->ntlmssp->server_flags & NTLMSSP_NEGOTIATE_KEY_XCH) &&
+	    (!ses->server->session_estab || ses->ntlmssp->sesskey_per_smbsess) &&
+	    !calc_seckey(ses)) {
 		memcpy(tmp, ses->ntlmssp->ciphertext, CIFS_CPHTXT_SIZE);
 		sec_blob->SessionKey.BufferOffset = cpu_to_le32(tmp - *pbuffer);
 		sec_blob->SessionKey.Length = cpu_to_le16(CIFS_CPHTXT_SIZE);
@@ -1230,6 +1326,7 @@ sess_auth_rawntlmssp_negotiate(struct sess_data *sess_data)
 	struct cifs_ses *ses = sess_data->ses;
 	__u16 bytes_remaining;
 	char *bcc_ptr;
+	unsigned char *ntlmsspblob = NULL;
 	u16 blob_len;
 
 	cifs_dbg(FYI, "rawntlmssp session setup negotiate phase\n");
@@ -1253,10 +1350,15 @@ sess_auth_rawntlmssp_negotiate(struct sess_data *sess_data)
 	pSMB = (SESSION_SETUP_ANDX *)sess_data->iov[0].iov_base;
 
 	/* Build security blob before we assemble the request */
-	build_ntlmssp_negotiate_blob(pSMB->req.SecurityBlob, ses);
-	sess_data->iov[1].iov_len = sizeof(NEGOTIATE_MESSAGE);
-	sess_data->iov[1].iov_base = pSMB->req.SecurityBlob;
-	pSMB->req.SecurityBlobLength = cpu_to_le16(sizeof(NEGOTIATE_MESSAGE));
+	rc = build_ntlmssp_negotiate_blob(&ntlmsspblob,
+				     &blob_len, ses,
+				     sess_data->nls_cp);
+	if (rc)
+		goto out;
+
+	sess_data->iov[1].iov_len = blob_len;
+	sess_data->iov[1].iov_base = ntlmsspblob;
+	pSMB->req.SecurityBlobLength = cpu_to_le16(blob_len);
 
 	rc = _sess_auth_rawntlmssp_assemble_req(sess_data);
 	if (rc)
diff --git a/fs/cifs/smb2inode.c b/fs/cifs/smb2inode.c
index 8297703492ee..fe5bfa245fa7 100644
--- a/fs/cifs/smb2inode.c
+++ b/fs/cifs/smb2inode.c
@@ -46,6 +46,10 @@ struct cop_vars {
 	struct smb2_file_link_info link_info;
 };
 
+/*
+ * note: If cfile is passed, the reference to it is dropped here.
+ * So make sure that you do not reuse cfile after return from this func.
+ */
 static int
 smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon,
 		 struct cifs_sb_info *cifs_sb, const char *full_path,
@@ -536,10 +540,11 @@ smb2_query_path_info(const unsigned int xid, struct cifs_tcon *tcon,
 		create_options |= OPEN_REPARSE_POINT;
 
 		/* Failed on a symbolic link - query a reparse point info */
+		cifs_get_readable_path(tcon, full_path, &cfile);
 		rc = smb2_compound_op(xid, tcon, cifs_sb, full_path,
 				      FILE_READ_ATTRIBUTES, FILE_OPEN,
 				      create_options, ACL_NO_MODE,
-				      smb2_data, SMB2_OP_QUERY_INFO, NULL);
+				      smb2_data, SMB2_OP_QUERY_INFO, cfile);
 	}
 	if (rc)
 		goto out;
@@ -587,10 +592,11 @@ smb311_posix_query_path_info(const unsigned int xid, struct cifs_tcon *tcon,
 		create_options |= OPEN_REPARSE_POINT;
 
 		/* Failed on a symbolic link - query a reparse point info */
+		cifs_get_readable_path(tcon, full_path, &cfile);
 		rc = smb2_compound_op(xid, tcon, cifs_sb, full_path,
 				      FILE_READ_ATTRIBUTES, FILE_OPEN,
 				      create_options, ACL_NO_MODE,
-				      smb2_data, SMB2_OP_POSIX_QUERY_INFO, NULL);
+				      smb2_data, SMB2_OP_POSIX_QUERY_INFO, cfile);
 	}
 	if (rc)
 		goto out;
@@ -707,10 +713,12 @@ smb2_set_path_size(const unsigned int xid, struct cifs_tcon *tcon,
 		   struct cifs_sb_info *cifs_sb, bool set_alloc)
 {
 	__le64 eof = cpu_to_le64(size);
+	struct cifsFileInfo *cfile;
 
+	cifs_get_writable_path(tcon, full_path, FIND_WR_ANY, &cfile);
 	return smb2_compound_op(xid, tcon, cifs_sb, full_path,
 				FILE_WRITE_DATA, FILE_OPEN, 0, ACL_NO_MODE,
-				&eof, SMB2_OP_SET_EOF, NULL);
+				&eof, SMB2_OP_SET_EOF, cfile);
 }
 
 int
@@ -719,6 +727,8 @@ smb2_set_file_info(struct inode *inode, const char *full_path,
 {
 	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
 	struct tcon_link *tlink;
+	struct cifs_tcon *tcon;
+	struct cifsFileInfo *cfile;
 	int rc;
 
 	if ((buf->CreationTime == 0) && (buf->LastAccessTime == 0) &&
@@ -729,10 +739,12 @@ smb2_set_file_info(struct inode *inode, const char *full_path,
 	tlink = cifs_sb_tlink(cifs_sb);
 	if (IS_ERR(tlink))
 		return PTR_ERR(tlink);
+	tcon = tlink_tcon(tlink);
 
-	rc = smb2_compound_op(xid, tlink_tcon(tlink), cifs_sb, full_path,
+	cifs_get_writable_path(tcon, full_path, FIND_WR_ANY, &cfile);
+	rc = smb2_compound_op(xid, tcon, cifs_sb, full_path,
 			      FILE_WRITE_ATTRIBUTES, FILE_OPEN,
-			      0, ACL_NO_MODE, buf, SMB2_OP_SET_INFO, NULL);
+			      0, ACL_NO_MODE, buf, SMB2_OP_SET_INFO, cfile);
 	cifs_put_tlink(tlink);
 	return rc;
 }
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index 7acf71defea7..c5b1dea54ebc 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -2844,6 +2844,7 @@ smb2_get_dfs_refer(const unsigned int xid, struct cifs_ses *ses,
 	struct fsctl_get_dfs_referral_req *dfs_req = NULL;
 	struct get_dfs_referral_rsp *dfs_rsp = NULL;
 	u32 dfs_req_size = 0, dfs_rsp_size = 0;
+	int retry_count = 0;
 
 	cifs_dbg(FYI, "%s: path: %s\n", __func__, search_name);
 
@@ -2895,11 +2896,14 @@ smb2_get_dfs_refer(const unsigned int xid, struct cifs_ses *ses,
 				true /* is_fsctl */,
 				(char *)dfs_req, dfs_req_size, CIFSMaxBufSize,
 				(char **)&dfs_rsp, &dfs_rsp_size);
-	} while (rc == -EAGAIN);
+		if (!is_retryable_error(rc))
+			break;
+		usleep_range(512, 2048);
+	} while (++retry_count < 5);
 
 	if (rc) {
-		if ((rc != -ENOENT) && (rc != -EOPNOTSUPP))
-			cifs_tcon_dbg(VFS, "ioctl error in %s rc=%d\n", __func__, rc);
+		if (!is_retryable_error(rc) && rc != -ENOENT && rc != -EOPNOTSUPP)
+			cifs_tcon_dbg(VFS, "%s: ioctl error: rc=%d\n", __func__, rc);
 		goto out;
 	}
 
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index d2ecb2ea37c0..8b3670388cda 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -142,7 +142,7 @@ static int
 smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon,
 	       struct TCP_Server_Info *server)
 {
-	int rc;
+	int rc = 0;
 	struct nls_table *nls_codepage;
 	struct cifs_ses *ses;
 	int retries;
@@ -155,7 +155,11 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon,
 	if (tcon == NULL)
 		return 0;
 
-	if (smb2_command == SMB2_TREE_CONNECT)
+	/*
+	 * Need to also skip SMB2_IOCTL because it is used for checking nested dfs links in
+	 * cifs_tree_connect().
+	 */
+	if (smb2_command == SMB2_TREE_CONNECT || smb2_command == SMB2_IOCTL)
 		return 0;
 
 	if (tcon->tidStatus == CifsExiting) {
@@ -253,7 +257,7 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon,
 	/*
 	 * If we are reconnecting an extra channel, bind
 	 */
-	if (server->is_channel) {
+	if (CIFS_SERVER_IS_CHAN(server)) {
 		ses->binding = true;
 		ses->binding_chan = cifs_ses_find_chan(ses, server);
 	}
@@ -1456,7 +1460,7 @@ SMB2_sess_auth_rawntlmssp_negotiate(struct SMB2_sess_data *sess_data)
 	int rc;
 	struct cifs_ses *ses = sess_data->ses;
 	struct smb2_sess_setup_rsp *rsp = NULL;
-	char *ntlmssp_blob = NULL;
+	unsigned char *ntlmssp_blob = NULL;
 	bool use_spnego = false; /* else use raw ntlmssp */
 	u16 blob_length = 0;
 
@@ -1475,22 +1479,17 @@ SMB2_sess_auth_rawntlmssp_negotiate(struct SMB2_sess_data *sess_data)
 	if (rc)
 		goto out_err;
 
-	ntlmssp_blob = kmalloc(sizeof(struct _NEGOTIATE_MESSAGE),
-			       GFP_KERNEL);
-	if (ntlmssp_blob == NULL) {
-		rc = -ENOMEM;
-		goto out;
-	}
+	rc = build_ntlmssp_negotiate_blob(&ntlmssp_blob,
+					  &blob_length, ses,
+					  sess_data->nls_cp);
+	if (rc)
+		goto out_err;
 
-	build_ntlmssp_negotiate_blob(ntlmssp_blob, ses);
 	if (use_spnego) {
 		/* BB eventually need to add this */
 		cifs_dbg(VFS, "spnego not supported for SMB2 yet\n");
 		rc = -EOPNOTSUPP;
 		goto out;
-	} else {
-		blob_length = sizeof(struct _NEGOTIATE_MESSAGE);
-		/* with raw NTLMSSP we don't encapsulate in SPNEGO */
 	}
 	sess_data->iov[1].iov_base = ntlmssp_blob;
 	sess_data->iov[1].iov_len = blob_length;
@@ -1841,7 +1840,7 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree,
 	cifs_small_buf_release(req);
 	rsp = (struct smb2_tree_connect_rsp *)rsp_iov.iov_base;
 	trace_smb3_tcon(xid, tcon->tid, ses->Suid, tree, rc);
-	if (rc != 0) {
+	if ((rc != 0) || (rsp == NULL)) {
 		cifs_stats_fail_inc(tcon, SMB2_TREE_CONNECT_HE);
 		tcon->need_reconnect = true;
 		goto tcon_error_exit;
@@ -2669,7 +2668,18 @@ int smb311_posix_mkdir(const unsigned int xid, struct inode *inode,
 		goto err_free_rsp_buf;
 	}
 
+	/*
+	 * Although unlikely to be possible for rsp to be null and rc not set,
+	 * adding check below is slightly safer long term (and quiets Coverity
+	 * warning)
+	 */
 	rsp = (struct smb2_create_rsp *)rsp_iov.iov_base;
+	if (rsp == NULL) {
+		rc = -EIO;
+		kfree(pc_buf);
+		goto err_free_req;
+	}
+
 	trace_smb3_posix_mkdir_done(xid, le64_to_cpu(rsp->PersistentFileId),
 				    tcon->tid,
 				    ses->Suid, CREATE_NOT_FILE,
@@ -2942,7 +2952,9 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 			tcon->need_reconnect = true;
 		}
 		goto creat_exit;
-	} else
+	} else if (rsp == NULL) /* unlikely to happen, but safer to check */
+		goto creat_exit;
+	else
 		trace_smb3_open_done(xid, le64_to_cpu(rsp->PersistentFileId),
 				     tcon->tid,
 				     ses->Suid, oparms->create_options,
@@ -3163,6 +3175,16 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
 	if ((plen == NULL) || (out_data == NULL))
 		goto ioctl_exit;
 
+	/*
+	 * Although unlikely to be possible for rsp to be null and rc not set,
+	 * adding check below is slightly safer long term (and quiets Coverity
+	 * warning)
+	 */
+	if (rsp == NULL) {
+		rc = -EIO;
+		goto ioctl_exit;
+	}
+
 	*plen = le32_to_cpu(rsp->OutputCount);
 
 	/* We check for obvious errors in the output buffer length and offset */
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index b7379329b741..61ea3d3f95b4 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -1044,14 +1044,17 @@ struct TCP_Server_Info *cifs_pick_channel(struct cifs_ses *ses)
 	if (!ses)
 		return NULL;
 
+	spin_lock(&ses->chan_lock);
 	if (!ses->binding) {
 		/* round robin */
 		if (ses->chan_count > 1) {
 			index = (uint)atomic_inc_return(&ses->chan_seq);
 			index %= ses->chan_count;
 		}
+		spin_unlock(&ses->chan_lock);
 		return ses->chans[index].server;
 	} else {
+		spin_unlock(&ses->chan_lock);
 		return cifs_ses_server(ses);
 	}
 }
diff --git a/fs/erofs/utils.c b/fs/erofs/utils.c
index 84da2c280012..ec9a1d780dc1 100644
--- a/fs/erofs/utils.c
+++ b/fs/erofs/utils.c
@@ -150,7 +150,7 @@ static bool erofs_try_to_release_workgroup(struct erofs_sb_info *sbi,
 	 * however in order to avoid some race conditions, add a
 	 * DBG_BUGON to observe this in advance.
 	 */
-	DBG_BUGON(xa_erase(&sbi->managed_pslots, grp->index) != grp);
+	DBG_BUGON(__xa_erase(&sbi->managed_pslots, grp->index) != grp);
 
 	/* last refcount should be connected with its managed pslot.  */
 	erofs_workgroup_unfreeze(grp, 0);
@@ -165,15 +165,19 @@ static unsigned long erofs_shrink_workstation(struct erofs_sb_info *sbi,
 	unsigned int freed = 0;
 	unsigned long index;
 
+	xa_lock(&sbi->managed_pslots);
 	xa_for_each(&sbi->managed_pslots, index, grp) {
 		/* try to shrink each valid workgroup */
 		if (!erofs_try_to_release_workgroup(sbi, grp))
 			continue;
+		xa_unlock(&sbi->managed_pslots);
 
 		++freed;
 		if (!--nr_shrink)
-			break;
+			return freed;
+		xa_lock(&sbi->managed_pslots);
 	}
+	xa_unlock(&sbi->managed_pslots);
 	return freed;
 }
 
diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c
index bcb1b91b234f..9a249bfc2770 100644
--- a/fs/erofs/zdata.c
+++ b/fs/erofs/zdata.c
@@ -96,16 +96,9 @@ static void z_erofs_free_pcluster(struct z_erofs_pcluster *pcl)
 	DBG_BUGON(1);
 }
 
-/*
- * a compressed_pages[] placeholder in order to avoid
- * being filled with file pages for in-place decompression.
- */
-#define PAGE_UNALLOCATED     ((void *)0x5F0E4B1D)
-
 /* how to allocate cached pages for a pcluster */
 enum z_erofs_cache_alloctype {
 	DONTALLOC,	/* don't allocate any cached pages */
-	DELAYEDALLOC,	/* delayed allocation (at the time of submitting io) */
 	/*
 	 * try to use cached I/O if page allocation succeeds or fallback
 	 * to in-place I/O instead to avoid any direct reclaim.
@@ -267,10 +260,6 @@ static void preload_compressed_pages(struct z_erofs_collector *clt,
 			/* I/O is needed, no possible to decompress directly */
 			standalone = false;
 			switch (type) {
-			case DELAYEDALLOC:
-				t = tagptr_init(compressed_page_t,
-						PAGE_UNALLOCATED);
-				break;
 			case TRYALLOC:
 				newpage = erofs_allocpage(pagepool, gfp);
 				if (!newpage)
@@ -371,8 +360,8 @@ static bool z_erofs_try_inplace_io(struct z_erofs_collector *clt,
 
 /* callers must be with collection lock held */
 static int z_erofs_attach_page(struct z_erofs_collector *clt,
-			       struct page *page,
-			       enum z_erofs_page_type type)
+			       struct page *page, enum z_erofs_page_type type,
+			       bool pvec_safereuse)
 {
 	int ret;
 
@@ -382,9 +371,9 @@ static int z_erofs_attach_page(struct z_erofs_collector *clt,
 	    z_erofs_try_inplace_io(clt, page))
 		return 0;
 
-	ret = z_erofs_pagevec_enqueue(&clt->vector, page, type);
+	ret = z_erofs_pagevec_enqueue(&clt->vector, page, type,
+				      pvec_safereuse);
 	clt->cl->vcnt += (unsigned int)ret;
-
 	return ret ? 0 : -EAGAIN;
 }
 
@@ -727,7 +716,8 @@ hitted:
 		tight &= (clt->mode >= COLLECT_PRIMARY_FOLLOWED);
 
 retry:
-	err = z_erofs_attach_page(clt, page, page_type);
+	err = z_erofs_attach_page(clt, page, page_type,
+				  clt->mode >= COLLECT_PRIMARY_FOLLOWED);
 	/* should allocate an additional short-lived page for pagevec */
 	if (err == -EAGAIN) {
 		struct page *const newpage =
@@ -735,7 +725,7 @@ retry:
 
 		set_page_private(newpage, Z_EROFS_SHORTLIVED_PAGE);
 		err = z_erofs_attach_page(clt, newpage,
-					  Z_EROFS_PAGE_TYPE_EXCLUSIVE);
+					  Z_EROFS_PAGE_TYPE_EXCLUSIVE, true);
 		if (!err)
 			goto retry;
 	}
@@ -1089,15 +1079,6 @@ repeat:
 	if (!page)
 		goto out_allocpage;
 
-	/*
-	 * the cached page has not been allocated and
-	 * an placeholder is out there, prepare it now.
-	 */
-	if (page == PAGE_UNALLOCATED) {
-		tocache = true;
-		goto out_allocpage;
-	}
-
 	/* process the target tagged pointer */
 	t = tagptr_init(compressed_page_t, page);
 	justfound = tagptr_unfold_tags(t);
diff --git a/fs/erofs/zdata.h b/fs/erofs/zdata.h
index 879df5362777..4a69515dea75 100644
--- a/fs/erofs/zdata.h
+++ b/fs/erofs/zdata.h
@@ -179,4 +179,3 @@ static inline void z_erofs_onlinepage_endio(struct page *page)
 #define Z_EROFS_VMAP_GLOBAL_PAGES	2048
 
 #endif
-
diff --git a/fs/erofs/zpvec.h b/fs/erofs/zpvec.h
index dfd7fe0503bb..b05464f4a808 100644
--- a/fs/erofs/zpvec.h
+++ b/fs/erofs/zpvec.h
@@ -106,11 +106,18 @@ static inline void z_erofs_pagevec_ctor_init(struct z_erofs_pagevec_ctor *ctor,
 
 static inline bool z_erofs_pagevec_enqueue(struct z_erofs_pagevec_ctor *ctor,
 					   struct page *page,
-					   enum z_erofs_page_type type)
+					   enum z_erofs_page_type type,
+					   bool pvec_safereuse)
 {
-	if (!ctor->next && type)
-		if (ctor->index + 1 == ctor->nr)
+	if (!ctor->next) {
+		/* some pages cannot be reused as pvec safely without I/O */
+		if (type == Z_EROFS_PAGE_TYPE_EXCLUSIVE && !pvec_safereuse)
+			type = Z_EROFS_VLE_PAGE_TYPE_TAIL_SHARED;
+
+		if (type != Z_EROFS_PAGE_TYPE_EXCLUSIVE &&
+		    ctor->index + 1 == ctor->nr)
 			return false;
+	}
 
 	if (ctor->index >= ctor->nr)
 		z_erofs_pagevec_ctor_pagedown(ctor, false);
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index 83e9bc0f91ff..f1693d45bb78 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -653,7 +653,7 @@ static int recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
 		return PTR_ERR(inode);
 	}
 
-	err = dquot_initialize(inode);
+	err = f2fs_dquot_initialize(inode);
 	if (err) {
 		iput(inode);
 		goto err_out;
@@ -705,9 +705,6 @@ int f2fs_recover_orphan_inodes(struct f2fs_sb_info *sbi)
 	}
 
 #ifdef CONFIG_QUOTA
-	/* Needed for iput() to work correctly and not trash data */
-	sbi->sb->s_flags |= SB_ACTIVE;
-
 	/*
 	 * Turn on quotas which were not enabled for read-only mounts if
 	 * filesystem has quota feature, so that they are updated correctly.
@@ -1162,7 +1159,8 @@ static bool __need_flush_quota(struct f2fs_sb_info *sbi)
 	if (!is_journalled_quota(sbi))
 		return false;
 
-	down_write(&sbi->quota_sem);
+	if (!down_write_trylock(&sbi->quota_sem))
+		return true;
 	if (is_sbi_flag_set(sbi, SBI_QUOTA_SKIP_FLUSH)) {
 		ret = false;
 	} else if (is_sbi_flag_set(sbi, SBI_QUOTA_NEED_REPAIR)) {
diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c
index 20a083dc9042..49121a21f749 100644
--- a/fs/f2fs/compress.c
+++ b/fs/f2fs/compress.c
@@ -336,8 +336,8 @@ static const struct f2fs_compress_ops f2fs_lz4_ops = {
 
 static int zstd_init_compress_ctx(struct compress_ctx *cc)
 {
-	ZSTD_parameters params;
-	ZSTD_CStream *stream;
+	zstd_parameters params;
+	zstd_cstream *stream;
 	void *workspace;
 	unsigned int workspace_size;
 	unsigned char level = F2FS_I(cc->inode)->i_compress_flag >>
@@ -346,17 +346,17 @@ static int zstd_init_compress_ctx(struct compress_ctx *cc)
 	if (!level)
 		level = F2FS_ZSTD_DEFAULT_CLEVEL;
 
-	params = ZSTD_getParams(level, cc->rlen, 0);
-	workspace_size = ZSTD_CStreamWorkspaceBound(params.cParams);
+	params = zstd_get_params(F2FS_ZSTD_DEFAULT_CLEVEL, cc->rlen);
+	workspace_size = zstd_cstream_workspace_bound(&params.cParams);
 
 	workspace = f2fs_kvmalloc(F2FS_I_SB(cc->inode),
 					workspace_size, GFP_NOFS);
 	if (!workspace)
 		return -ENOMEM;
 
-	stream = ZSTD_initCStream(params, 0, workspace, workspace_size);
+	stream = zstd_init_cstream(&params, 0, workspace, workspace_size);
 	if (!stream) {
-		printk_ratelimited("%sF2FS-fs (%s): %s ZSTD_initCStream failed\n",
+		printk_ratelimited("%sF2FS-fs (%s): %s zstd_init_cstream failed\n",
 				KERN_ERR, F2FS_I_SB(cc->inode)->sb->s_id,
 				__func__);
 		kvfree(workspace);
@@ -379,9 +379,9 @@ static void zstd_destroy_compress_ctx(struct compress_ctx *cc)
 
 static int zstd_compress_pages(struct compress_ctx *cc)
 {
-	ZSTD_CStream *stream = cc->private2;
-	ZSTD_inBuffer inbuf;
-	ZSTD_outBuffer outbuf;
+	zstd_cstream *stream = cc->private2;
+	zstd_in_buffer inbuf;
+	zstd_out_buffer outbuf;
 	int src_size = cc->rlen;
 	int dst_size = src_size - PAGE_SIZE - COMPRESS_HEADER_SIZE;
 	int ret;
@@ -394,19 +394,19 @@ static int zstd_compress_pages(struct compress_ctx *cc)
 	outbuf.dst = cc->cbuf->cdata;
 	outbuf.size = dst_size;
 
-	ret = ZSTD_compressStream(stream, &outbuf, &inbuf);
-	if (ZSTD_isError(ret)) {
-		printk_ratelimited("%sF2FS-fs (%s): %s ZSTD_compressStream failed, ret: %d\n",
+	ret = zstd_compress_stream(stream, &outbuf, &inbuf);
+	if (zstd_is_error(ret)) {
+		printk_ratelimited("%sF2FS-fs (%s): %s zstd_compress_stream failed, ret: %d\n",
 				KERN_ERR, F2FS_I_SB(cc->inode)->sb->s_id,
-				__func__, ZSTD_getErrorCode(ret));
+				__func__, zstd_get_error_code(ret));
 		return -EIO;
 	}
 
-	ret = ZSTD_endStream(stream, &outbuf);
-	if (ZSTD_isError(ret)) {
-		printk_ratelimited("%sF2FS-fs (%s): %s ZSTD_endStream returned %d\n",
+	ret = zstd_end_stream(stream, &outbuf);
+	if (zstd_is_error(ret)) {
+		printk_ratelimited("%sF2FS-fs (%s): %s zstd_end_stream returned %d\n",
 				KERN_ERR, F2FS_I_SB(cc->inode)->sb->s_id,
-				__func__, ZSTD_getErrorCode(ret));
+				__func__, zstd_get_error_code(ret));
 		return -EIO;
 	}
 
@@ -423,22 +423,22 @@ static int zstd_compress_pages(struct compress_ctx *cc)
 
 static int zstd_init_decompress_ctx(struct decompress_io_ctx *dic)
 {
-	ZSTD_DStream *stream;
+	zstd_dstream *stream;
 	void *workspace;
 	unsigned int workspace_size;
 	unsigned int max_window_size =
 			MAX_COMPRESS_WINDOW_SIZE(dic->log_cluster_size);
 
-	workspace_size = ZSTD_DStreamWorkspaceBound(max_window_size);
+	workspace_size = zstd_dstream_workspace_bound(max_window_size);
 
 	workspace = f2fs_kvmalloc(F2FS_I_SB(dic->inode),
 					workspace_size, GFP_NOFS);
 	if (!workspace)
 		return -ENOMEM;
 
-	stream = ZSTD_initDStream(max_window_size, workspace, workspace_size);
+	stream = zstd_init_dstream(max_window_size, workspace, workspace_size);
 	if (!stream) {
-		printk_ratelimited("%sF2FS-fs (%s): %s ZSTD_initDStream failed\n",
+		printk_ratelimited("%sF2FS-fs (%s): %s zstd_init_dstream failed\n",
 				KERN_ERR, F2FS_I_SB(dic->inode)->sb->s_id,
 				__func__);
 		kvfree(workspace);
@@ -460,9 +460,9 @@ static void zstd_destroy_decompress_ctx(struct decompress_io_ctx *dic)
 
 static int zstd_decompress_pages(struct decompress_io_ctx *dic)
 {
-	ZSTD_DStream *stream = dic->private2;
-	ZSTD_inBuffer inbuf;
-	ZSTD_outBuffer outbuf;
+	zstd_dstream *stream = dic->private2;
+	zstd_in_buffer inbuf;
+	zstd_out_buffer outbuf;
 	int ret;
 
 	inbuf.pos = 0;
@@ -473,11 +473,11 @@ static int zstd_decompress_pages(struct decompress_io_ctx *dic)
 	outbuf.dst = dic->rbuf;
 	outbuf.size = dic->rlen;
 
-	ret = ZSTD_decompressStream(stream, &outbuf, &inbuf);
-	if (ZSTD_isError(ret)) {
-		printk_ratelimited("%sF2FS-fs (%s): %s ZSTD_compressStream failed, ret: %d\n",
+	ret = zstd_decompress_stream(stream, &outbuf, &inbuf);
+	if (zstd_is_error(ret)) {
+		printk_ratelimited("%sF2FS-fs (%s): %s zstd_decompress_stream failed, ret: %d\n",
 				KERN_ERR, F2FS_I_SB(dic->inode)->sb->s_id,
-				__func__, ZSTD_getErrorCode(ret));
+				__func__, zstd_get_error_code(ret));
 		return -EIO;
 	}
 
@@ -882,6 +882,25 @@ bool f2fs_cluster_can_merge_page(struct compress_ctx *cc, pgoff_t index)
 	return is_page_in_cluster(cc, index);
 }
 
+bool f2fs_all_cluster_page_loaded(struct compress_ctx *cc, struct pagevec *pvec,
+				int index, int nr_pages)
+{
+	unsigned long pgidx;
+	int i;
+
+	if (nr_pages - index < cc->cluster_size)
+		return false;
+
+	pgidx = pvec->pages[index]->index;
+
+	for (i = 1; i < cc->cluster_size; i++) {
+		if (pvec->pages[index + i]->index != pgidx + i)
+			return false;
+	}
+
+	return true;
+}
+
 static bool cluster_has_invalid_data(struct compress_ctx *cc)
 {
 	loff_t i_size = i_size_read(cc->inode);
@@ -1531,6 +1550,7 @@ int f2fs_write_multi_pages(struct compress_ctx *cc,
 	if (cluster_may_compress(cc)) {
 		err = f2fs_compress_pages(cc);
 		if (err == -EAGAIN) {
+			add_compr_block_stat(cc->inode, cc->cluster_size);
 			goto write;
 		} else if (err) {
 			f2fs_put_rpages_wbc(cc, wbc, true, 1);
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index f4fd6c246c9a..9f754aaef558 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -1465,10 +1465,15 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
 	struct extent_info ei = {0, };
 	block_t blkaddr;
 	unsigned int start_pgofs;
+	int bidx = 0;
 
 	if (!maxblocks)
 		return 0;
 
+	map->m_bdev = inode->i_sb->s_bdev;
+	map->m_multidev_dio =
+		f2fs_allow_multi_device_dio(F2FS_I_SB(inode), flag);
+
 	map->m_len = 0;
 	map->m_flags = 0;
 
@@ -1491,6 +1496,21 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
 		if (flag == F2FS_GET_BLOCK_DIO)
 			f2fs_wait_on_block_writeback_range(inode,
 						map->m_pblk, map->m_len);
+
+		if (map->m_multidev_dio) {
+			block_t blk_addr = map->m_pblk;
+
+			bidx = f2fs_target_device_index(sbi, map->m_pblk);
+
+			map->m_bdev = FDEV(bidx).bdev;
+			map->m_pblk -= FDEV(bidx).start_blk;
+			map->m_len = min(map->m_len,
+				FDEV(bidx).end_blk + 1 - map->m_pblk);
+
+			if (map->m_may_create)
+				f2fs_update_device_state(sbi, inode->i_ino,
+							blk_addr, map->m_len);
+		}
 		goto out;
 	}
 
@@ -1609,6 +1629,9 @@ next_block:
 	if (flag == F2FS_GET_BLOCK_PRE_AIO)
 		goto skip;
 
+	if (map->m_multidev_dio)
+		bidx = f2fs_target_device_index(sbi, blkaddr);
+
 	if (map->m_len == 0) {
 		/* preallocated unwritten block should be mapped for fiemap. */
 		if (blkaddr == NEW_ADDR)
@@ -1617,10 +1640,15 @@ next_block:
 
 		map->m_pblk = blkaddr;
 		map->m_len = 1;
+
+		if (map->m_multidev_dio)
+			map->m_bdev = FDEV(bidx).bdev;
 	} else if ((map->m_pblk != NEW_ADDR &&
 			blkaddr == (map->m_pblk + ofs)) ||
 			(map->m_pblk == NEW_ADDR && blkaddr == NEW_ADDR) ||
 			flag == F2FS_GET_BLOCK_PRE_DIO) {
+		if (map->m_multidev_dio && map->m_bdev != FDEV(bidx).bdev)
+			goto sync_out;
 		ofs++;
 		map->m_len++;
 	} else {
@@ -1673,10 +1701,32 @@ skip:
 
 sync_out:
 
-	/* for hardware encryption, but to avoid potential issue in future */
-	if (flag == F2FS_GET_BLOCK_DIO && map->m_flags & F2FS_MAP_MAPPED)
+	if (flag == F2FS_GET_BLOCK_DIO && map->m_flags & F2FS_MAP_MAPPED) {
+		/*
+		 * for hardware encryption, but to avoid potential issue
+		 * in future
+		 */
 		f2fs_wait_on_block_writeback_range(inode,
 						map->m_pblk, map->m_len);
+		invalidate_mapping_pages(META_MAPPING(sbi),
+						map->m_pblk, map->m_pblk);
+
+		if (map->m_multidev_dio) {
+			block_t blk_addr = map->m_pblk;
+
+			bidx = f2fs_target_device_index(sbi, map->m_pblk);
+
+			map->m_bdev = FDEV(bidx).bdev;
+			map->m_pblk -= FDEV(bidx).start_blk;
+
+			if (map->m_may_create)
+				f2fs_update_device_state(sbi, inode->i_ino,
+							blk_addr, map->m_len);
+
+			f2fs_bug_on(sbi, blk_addr + map->m_len >
+						FDEV(bidx).end_blk + 1);
+		}
+	}
 
 	if (flag == F2FS_GET_BLOCK_PRECACHE) {
 		if (map->m_flags & F2FS_MAP_MAPPED) {
@@ -1696,7 +1746,7 @@ unlock_out:
 		f2fs_balance_fs(sbi, dn.node_changed);
 	}
 out:
-	trace_f2fs_map_blocks(inode, map, err);
+	trace_f2fs_map_blocks(inode, map, create, flag, err);
 	return err;
 }
 
@@ -1755,6 +1805,9 @@ static int __get_data_block(struct inode *inode, sector_t iblock,
 		map_bh(bh, inode->i_sb, map.m_pblk);
 		bh->b_state = (bh->b_state & ~F2FS_MAP_FLAGS) | map.m_flags;
 		bh->b_size = blks_to_bytes(inode, map.m_len);
+
+		if (map.m_multidev_dio)
+			bh->b_bdev = map.m_bdev;
 	}
 	return err;
 }
@@ -2989,6 +3042,10 @@ readd:
 			need_readd = false;
 #ifdef CONFIG_F2FS_FS_COMPRESSION
 			if (f2fs_compressed_file(inode)) {
+				void *fsdata = NULL;
+				struct page *pagep;
+				int ret2;
+
 				ret = f2fs_init_compress_ctx(&cc);
 				if (ret) {
 					done = 1;
@@ -3007,27 +3064,23 @@ readd:
 				if (unlikely(f2fs_cp_error(sbi)))
 					goto lock_page;
 
-				if (f2fs_cluster_is_empty(&cc)) {
-					void *fsdata = NULL;
-					struct page *pagep;
-					int ret2;
+				if (!f2fs_cluster_is_empty(&cc))
+					goto lock_page;
 
-					ret2 = f2fs_prepare_compress_overwrite(
+				ret2 = f2fs_prepare_compress_overwrite(
 							inode, &pagep,
 							page->index, &fsdata);
-					if (ret2 < 0) {
-						ret = ret2;
-						done = 1;
-						break;
-					} else if (ret2 &&
-						!f2fs_compress_write_end(inode,
-								fsdata, page->index,
-								1)) {
-						retry = 1;
-						break;
-					}
-				} else {
-					goto lock_page;
+				if (ret2 < 0) {
+					ret = ret2;
+					done = 1;
+					break;
+				} else if (ret2 &&
+					(!f2fs_compress_write_end(inode,
+						fsdata, page->index, 1) ||
+					 !f2fs_all_cluster_page_loaded(&cc,
+						&pvec, i, nr_pages))) {
+					retry = 1;
+					break;
 				}
 			}
 #endif
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index b339ae89c1ad..ce9fc9f13000 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -55,6 +55,7 @@ enum {
 	FAULT_DISCARD,
 	FAULT_WRITE_IO,
 	FAULT_SLAB_ALLOC,
+	FAULT_DQUOT_INIT,
 	FAULT_MAX,
 };
 
@@ -561,6 +562,9 @@ enum {
 
 #define MAX_DIR_RA_PAGES	4	/* maximum ra pages of dir */
 
+/* dirty segments threshold for triggering CP */
+#define DEFAULT_DIRTY_THRESHOLD		4
+
 /* for in-memory extent cache entry */
 #define F2FS_MIN_EXTENT_LEN	64	/* minimum extent length */
 
@@ -617,6 +621,7 @@ struct extent_tree {
 				F2FS_MAP_UNWRITTEN)
 
 struct f2fs_map_blocks {
+	struct block_device *m_bdev;	/* for multi-device dio */
 	block_t m_pblk;
 	block_t m_lblk;
 	unsigned int m_len;
@@ -625,6 +630,7 @@ struct f2fs_map_blocks {
 	pgoff_t *m_next_extent;		/* point to next possible extent */
 	int m_seg_type;
 	bool m_may_create;		/* indicate it is from write path */
+	bool m_multidev_dio;		/* indicate it allows multi-device dio */
 };
 
 /* for flag in get_data_block */
@@ -1284,8 +1290,10 @@ enum {
 };
 
 enum {
-	FS_MODE_ADAPTIVE,	/* use both lfs/ssr allocation */
-	FS_MODE_LFS,		/* use lfs allocation only */
+	FS_MODE_ADAPTIVE,		/* use both lfs/ssr allocation */
+	FS_MODE_LFS,			/* use lfs allocation only */
+	FS_MODE_FRAGMENT_SEG,		/* segment fragmentation mode */
+	FS_MODE_FRAGMENT_BLK,		/* block fragmentation mode */
 };
 
 enum {
@@ -1728,12 +1736,15 @@ struct f2fs_sb_info {
 
 	/* For shrinker support */
 	struct list_head s_list;
+	struct mutex umount_mutex;
+	unsigned int shrinker_run_no;
+
+	/* For multi devices */
 	int s_ndevs;				/* number of devices */
 	struct f2fs_dev_info *devs;		/* for device list */
 	unsigned int dirty_device;		/* for checkpoint data flush */
 	spinlock_t dev_lock;			/* protect dirty_device */
-	struct mutex umount_mutex;
-	unsigned int shrinker_run_no;
+	bool aligned_blksize;			/* all devices has the same logical blksize */
 
 	/* For write statistics */
 	u64 sectors_written_start;
@@ -1756,6 +1767,9 @@ struct f2fs_sb_info {
 
 	unsigned long seq_file_ra_mul;		/* multiplier for ra_pages of seq. files in fadvise */
 
+	int max_fragment_chunk;			/* max chunk size for block fragmentation mode */
+	int max_fragment_hole;			/* max hole size for block fragmentation mode */
+
 #ifdef CONFIG_F2FS_FS_COMPRESSION
 	struct kmem_cache *page_array_slab;	/* page array entry */
 	unsigned int page_array_slab_size;	/* default page array slab size */
@@ -3363,6 +3377,7 @@ static inline int f2fs_add_link(struct dentry *dentry, struct inode *inode)
  */
 int f2fs_inode_dirtied(struct inode *inode, bool sync);
 void f2fs_inode_synced(struct inode *inode);
+int f2fs_dquot_initialize(struct inode *inode);
 int f2fs_enable_quota_files(struct f2fs_sb_info *sbi, bool rdonly);
 int f2fs_quota_sync(struct super_block *sb, int type);
 loff_t max_file_blocks(struct inode *inode);
@@ -3492,6 +3507,8 @@ void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
 			block_t old_blkaddr, block_t *new_blkaddr,
 			struct f2fs_summary *sum, int type,
 			struct f2fs_io_info *fio);
+void f2fs_update_device_state(struct f2fs_sb_info *sbi, nid_t ino,
+					block_t blkaddr, unsigned int blkcnt);
 void f2fs_wait_on_page_writeback(struct page *page,
 			enum page_type type, bool ordered, bool locked);
 void f2fs_wait_on_block_writeback(struct inode *inode, block_t blkaddr);
@@ -3516,6 +3533,16 @@ unsigned int f2fs_usable_segs_in_sec(struct f2fs_sb_info *sbi,
 unsigned int f2fs_usable_blks_in_seg(struct f2fs_sb_info *sbi,
 			unsigned int segno);
 
+#define DEF_FRAGMENT_SIZE	4
+#define MIN_FRAGMENT_SIZE	1
+#define MAX_FRAGMENT_SIZE	512
+
+static inline bool f2fs_need_rand_seg(struct f2fs_sb_info *sbi)
+{
+	return F2FS_OPTION(sbi).fs_mode == FS_MODE_FRAGMENT_SEG ||
+		F2FS_OPTION(sbi).fs_mode == FS_MODE_FRAGMENT_BLK;
+}
+
 /*
  * checkpoint.c
  */
@@ -4027,6 +4054,8 @@ void f2fs_end_read_compressed_page(struct page *page, bool failed,
 							block_t blkaddr);
 bool f2fs_cluster_is_empty(struct compress_ctx *cc);
 bool f2fs_cluster_can_merge_page(struct compress_ctx *cc, pgoff_t index);
+bool f2fs_all_cluster_page_loaded(struct compress_ctx *cc, struct pagevec *pvec,
+				int index, int nr_pages);
 bool f2fs_sanity_check_cluster(struct dnode_of_data *dn);
 void f2fs_compress_ctx_add_page(struct compress_ctx *cc, struct page *page);
 int f2fs_write_multi_pages(struct compress_ctx *cc,
@@ -4152,8 +4181,7 @@ static inline bool f2fs_disable_compressed_file(struct inode *inode)
 
 	if (!f2fs_compressed_file(inode))
 		return true;
-	if (S_ISREG(inode->i_mode) &&
-		(get_dirty_pages(inode) || atomic_read(&fi->i_compr_blocks)))
+	if (S_ISREG(inode->i_mode) && F2FS_HAS_BLOCKS(inode))
 		return false;
 
 	fi->i_flags &= ~F2FS_COMPR_FL;
@@ -4302,6 +4330,16 @@ static inline int block_unaligned_IO(struct inode *inode,
 	return align & blocksize_mask;
 }
 
+static inline bool f2fs_allow_multi_device_dio(struct f2fs_sb_info *sbi,
+								int flag)
+{
+	if (!f2fs_is_multi_device(sbi))
+		return false;
+	if (flag != F2FS_GET_BLOCK_DIO)
+		return false;
+	return sbi->aligned_blksize;
+}
+
 static inline bool f2fs_force_buffered_io(struct inode *inode,
 				struct kiocb *iocb, struct iov_iter *iter)
 {
@@ -4310,7 +4348,9 @@ static inline bool f2fs_force_buffered_io(struct inode *inode,
 
 	if (f2fs_post_read_required(inode))
 		return true;
-	if (f2fs_is_multi_device(sbi))
+
+	/* disallow direct IO if any of devices has unaligned blksize */
+	if (f2fs_is_multi_device(sbi) && !sbi->aligned_blksize)
 		return true;
 	/*
 	 * for blkzoned device, fallback direct IO to buffered IO, so
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index eb971e1e7227..92ec2699bc85 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -786,7 +786,7 @@ int f2fs_truncate(struct inode *inode)
 		return -EIO;
 	}
 
-	err = dquot_initialize(inode);
+	err = f2fs_dquot_initialize(inode);
 	if (err)
 		return err;
 
@@ -916,7 +916,7 @@ int f2fs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
 		return err;
 
 	if (is_quota_modification(inode, attr)) {
-		err = dquot_initialize(inode);
+		err = f2fs_dquot_initialize(inode);
 		if (err)
 			return err;
 	}
@@ -3020,7 +3020,7 @@ static int f2fs_ioc_setproject(struct inode *inode, __u32 projid)
 	}
 	f2fs_put_page(ipage, 1);
 
-	err = dquot_initialize(inode);
+	err = f2fs_dquot_initialize(inode);
 	if (err)
 		return err;
 
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index 77391e3b7d68..a946ce0ead34 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -14,6 +14,7 @@
 #include <linux/delay.h>
 #include <linux/freezer.h>
 #include <linux/sched/signal.h>
+#include <linux/random.h>
 
 #include "f2fs.h"
 #include "node.h"
@@ -257,7 +258,9 @@ static void select_policy(struct f2fs_sb_info *sbi, int gc_type,
 		p->max_search = sbi->max_victim_search;
 
 	/* let's select beginning hot/small space first in no_heap mode*/
-	if (test_opt(sbi, NOHEAP) &&
+	if (f2fs_need_rand_seg(sbi))
+		p->offset = prandom_u32() % (MAIN_SECS(sbi) * sbi->segs_per_sec);
+	else if (test_opt(sbi, NOHEAP) &&
 		(type == CURSEG_HOT_DATA || IS_NODESEG(type)))
 		p->offset = 0;
 	else
diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c
index 56a20d5c15da..ea08f0dfa1bd 100644
--- a/fs/f2fs/inline.c
+++ b/fs/f2fs/inline.c
@@ -192,7 +192,7 @@ int f2fs_convert_inline_inode(struct inode *inode)
 			f2fs_hw_is_readonly(sbi) || f2fs_readonly(sbi->sb))
 		return 0;
 
-	err = dquot_initialize(inode);
+	err = f2fs_dquot_initialize(inode);
 	if (err)
 		return err;
 
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index 9141147b5bb0..0f8b2df3e1e0 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -527,7 +527,7 @@ make_now:
 		inode->i_op = &f2fs_dir_inode_operations;
 		inode->i_fop = &f2fs_dir_operations;
 		inode->i_mapping->a_ops = &f2fs_dblock_aops;
-		inode_nohighmem(inode);
+		mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS);
 	} else if (S_ISLNK(inode->i_mode)) {
 		if (file_is_encrypt(inode))
 			inode->i_op = &f2fs_encrypted_symlink_inode_operations;
@@ -754,7 +754,7 @@ void f2fs_evict_inode(struct inode *inode)
 	if (inode->i_nlink || is_bad_inode(inode))
 		goto no_delete;
 
-	err = dquot_initialize(inode);
+	err = f2fs_dquot_initialize(inode);
 	if (err) {
 		err = 0;
 		set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR);
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index 9c528e583c9d..a728a0af9ce0 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -74,7 +74,7 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode)
 	if (err)
 		goto fail_drop;
 
-	err = dquot_initialize(inode);
+	err = f2fs_dquot_initialize(inode);
 	if (err)
 		goto fail_drop;
 
@@ -345,7 +345,7 @@ static int f2fs_create(struct user_namespace *mnt_userns, struct inode *dir,
 	if (!f2fs_is_checkpoint_ready(sbi))
 		return -ENOSPC;
 
-	err = dquot_initialize(dir);
+	err = f2fs_dquot_initialize(dir);
 	if (err)
 		return err;
 
@@ -404,7 +404,7 @@ static int f2fs_link(struct dentry *old_dentry, struct inode *dir,
 			F2FS_I(old_dentry->d_inode)->i_projid)))
 		return -EXDEV;
 
-	err = dquot_initialize(dir);
+	err = f2fs_dquot_initialize(dir);
 	if (err)
 		return err;
 
@@ -460,7 +460,7 @@ static int __recover_dot_dentries(struct inode *dir, nid_t pino)
 		return 0;
 	}
 
-	err = dquot_initialize(dir);
+	err = f2fs_dquot_initialize(dir);
 	if (err)
 		return err;
 
@@ -598,10 +598,10 @@ static int f2fs_unlink(struct inode *dir, struct dentry *dentry)
 		goto fail;
 	}
 
-	err = dquot_initialize(dir);
+	err = f2fs_dquot_initialize(dir);
 	if (err)
 		goto fail;
-	err = dquot_initialize(inode);
+	err = f2fs_dquot_initialize(inode);
 	if (err)
 		goto fail;
 
@@ -675,7 +675,7 @@ static int f2fs_symlink(struct user_namespace *mnt_userns, struct inode *dir,
 	if (err)
 		return err;
 
-	err = dquot_initialize(dir);
+	err = f2fs_dquot_initialize(dir);
 	if (err)
 		return err;
 
@@ -746,7 +746,7 @@ static int f2fs_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
 	if (unlikely(f2fs_cp_error(sbi)))
 		return -EIO;
 
-	err = dquot_initialize(dir);
+	err = f2fs_dquot_initialize(dir);
 	if (err)
 		return err;
 
@@ -757,7 +757,7 @@ static int f2fs_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
 	inode->i_op = &f2fs_dir_inode_operations;
 	inode->i_fop = &f2fs_dir_operations;
 	inode->i_mapping->a_ops = &f2fs_dblock_aops;
-	inode_nohighmem(inode);
+	mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS);
 
 	set_inode_flag(inode, FI_INC_LINK);
 	f2fs_lock_op(sbi);
@@ -803,7 +803,7 @@ static int f2fs_mknod(struct user_namespace *mnt_userns, struct inode *dir,
 	if (!f2fs_is_checkpoint_ready(sbi))
 		return -ENOSPC;
 
-	err = dquot_initialize(dir);
+	err = f2fs_dquot_initialize(dir);
 	if (err)
 		return err;
 
@@ -841,7 +841,7 @@ static int __f2fs_tmpfile(struct inode *dir, struct dentry *dentry,
 	struct inode *inode;
 	int err;
 
-	err = dquot_initialize(dir);
+	err = f2fs_dquot_initialize(dir);
 	if (err)
 		return err;
 
@@ -965,16 +965,16 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 			return err;
 	}
 
-	err = dquot_initialize(old_dir);
+	err = f2fs_dquot_initialize(old_dir);
 	if (err)
 		goto out;
 
-	err = dquot_initialize(new_dir);
+	err = f2fs_dquot_initialize(new_dir);
 	if (err)
 		goto out;
 
 	if (new_inode) {
-		err = dquot_initialize(new_inode);
+		err = f2fs_dquot_initialize(new_inode);
 		if (err)
 			goto out;
 	}
@@ -1138,11 +1138,11 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
 			F2FS_I(new_dentry->d_inode)->i_projid)))
 		return -EXDEV;
 
-	err = dquot_initialize(old_dir);
+	err = f2fs_dquot_initialize(old_dir);
 	if (err)
 		goto out;
 
-	err = dquot_initialize(new_dir);
+	err = f2fs_dquot_initialize(new_dir);
 	if (err)
 		goto out;
 
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index e863136081b4..556fcd8457f3 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -1443,6 +1443,7 @@ page_hit:
 			  nid, nid_of_node(page), ino_of_node(page),
 			  ofs_of_node(page), cpver_of_node(page),
 			  next_blkaddr_of_node(page));
+		set_sbi_flag(sbi, SBI_NEED_FSCK);
 		err = -EINVAL;
 out_err:
 		ClearPageUptodate(page);
diff --git a/fs/f2fs/node.h b/fs/f2fs/node.h
index ff14a6e5ac1c..18b98cf0465b 100644
--- a/fs/f2fs/node.h
+++ b/fs/f2fs/node.h
@@ -138,11 +138,6 @@ static inline bool excess_cached_nats(struct f2fs_sb_info *sbi)
 	return NM_I(sbi)->nat_cnt[TOTAL_NAT] >= DEF_NAT_CACHE_THRESHOLD;
 }
 
-static inline bool excess_dirty_nodes(struct f2fs_sb_info *sbi)
-{
-	return get_pages(sbi, F2FS_DIRTY_NODES) >= sbi->blocks_per_seg * 8;
-}
-
 enum mem_type {
 	FREE_NIDS,	/* indicates the free nid list */
 	NAT_ENTRIES,	/* indicates the cached nat entry */
diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
index 04655511d7f5..6a1b4668d933 100644
--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -81,7 +81,7 @@ static struct fsync_inode_entry *add_fsync_inode(struct f2fs_sb_info *sbi,
 	if (IS_ERR(inode))
 		return ERR_CAST(inode);
 
-	err = dquot_initialize(inode);
+	err = f2fs_dquot_initialize(inode);
 	if (err)
 		goto err_out;
 
@@ -203,7 +203,7 @@ retry:
 			goto out_put;
 		}
 
-		err = dquot_initialize(einode);
+		err = f2fs_dquot_initialize(einode);
 		if (err) {
 			iput(einode);
 			goto out_put;
@@ -508,7 +508,7 @@ got_it:
 		if (IS_ERR(inode))
 			return PTR_ERR(inode);
 
-		ret = dquot_initialize(inode);
+		ret = f2fs_dquot_initialize(inode);
 		if (ret) {
 			iput(inode);
 			return ret;
@@ -787,8 +787,6 @@ int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only)
 	}
 
 #ifdef CONFIG_QUOTA
-	/* Needed for iput() to work correctly and not trash data */
-	sbi->sb->s_flags |= SB_ACTIVE;
 	/* Turn on quotas so that they are updated correctly */
 	quota_enabled = f2fs_enable_quota_files(sbi, s_flags & SB_RDONLY);
 #endif
@@ -816,10 +814,8 @@ int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only)
 	err = recover_data(sbi, &inode_list, &tmp_inode_list, &dir_list);
 	if (!err)
 		f2fs_bug_on(sbi, !list_empty(&inode_list));
-	else {
-		/* restore s_flags to let iput() trash data */
-		sbi->sb->s_flags = s_flags;
-	}
+	else
+		f2fs_bug_on(sbi, sbi->sb->s_flags & SB_ACTIVE);
 skip:
 	fix_curseg_write_pointer = !check_only || list_empty(&inode_list);
 
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index a135d2247415..df9ed75f0b7a 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -15,6 +15,7 @@
 #include <linux/timer.h>
 #include <linux/freezer.h>
 #include <linux/sched/signal.h>
+#include <linux/random.h>
 
 #include "f2fs.h"
 #include "segment.h"
@@ -529,6 +530,25 @@ void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need)
 	}
 }
 
+static inline bool excess_dirty_threshold(struct f2fs_sb_info *sbi)
+{
+	int factor = rwsem_is_locked(&sbi->cp_rwsem) ? 3 : 2;
+	unsigned int dents = get_pages(sbi, F2FS_DIRTY_DENTS);
+	unsigned int qdata = get_pages(sbi, F2FS_DIRTY_QDATA);
+	unsigned int nodes = get_pages(sbi, F2FS_DIRTY_NODES);
+	unsigned int meta = get_pages(sbi, F2FS_DIRTY_META);
+	unsigned int imeta = get_pages(sbi, F2FS_DIRTY_IMETA);
+	unsigned int threshold = sbi->blocks_per_seg * factor *
+					DEFAULT_DIRTY_THRESHOLD;
+	unsigned int global_threshold = threshold * 3 / 2;
+
+	if (dents >= threshold || qdata >= threshold ||
+		nodes >= threshold || meta >= threshold ||
+		imeta >= threshold)
+		return true;
+	return dents + qdata + nodes + meta + imeta >  global_threshold;
+}
+
 void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi, bool from_bg)
 {
 	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
@@ -547,8 +567,8 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi, bool from_bg)
 	else
 		f2fs_build_free_nids(sbi, false, false);
 
-	if (excess_dirty_nats(sbi) || excess_dirty_nodes(sbi) ||
-		excess_prefree_segs(sbi))
+	if (excess_dirty_nats(sbi) || excess_dirty_threshold(sbi) ||
+		excess_prefree_segs(sbi) || !f2fs_space_for_roll_forward(sbi))
 		goto do_sync;
 
 	/* there is background inflight IO or foreground operation recently */
@@ -561,7 +581,7 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi, bool from_bg)
 		goto do_sync;
 
 	/* checkpoint is the only way to shrink partial cached entries */
-	if (f2fs_available_free_memory(sbi, NAT_ENTRIES) ||
+	if (f2fs_available_free_memory(sbi, NAT_ENTRIES) &&
 		f2fs_available_free_memory(sbi, INO_ENTRIES))
 		return;
 
@@ -2630,6 +2650,8 @@ static unsigned int __get_next_segno(struct f2fs_sb_info *sbi, int type)
 	unsigned short seg_type = curseg->seg_type;
 
 	sanity_check_seg_type(sbi, seg_type);
+	if (f2fs_need_rand_seg(sbi))
+		return prandom_u32() % (MAIN_SECS(sbi) * sbi->segs_per_sec);
 
 	/* if segs_per_sec is large than 1, we need to keep original policy. */
 	if (__is_large_section(sbi))
@@ -2681,6 +2703,9 @@ static void new_curseg(struct f2fs_sb_info *sbi, int type, bool new_sec)
 	curseg->next_segno = segno;
 	reset_curseg(sbi, type, 1);
 	curseg->alloc_type = LFS;
+	if (F2FS_OPTION(sbi).fs_mode == FS_MODE_FRAGMENT_BLK)
+		curseg->fragment_remained_chunk =
+				prandom_u32() % sbi->max_fragment_chunk + 1;
 }
 
 static int __next_free_blkoff(struct f2fs_sb_info *sbi,
@@ -2707,12 +2732,22 @@ static int __next_free_blkoff(struct f2fs_sb_info *sbi,
 static void __refresh_next_blkoff(struct f2fs_sb_info *sbi,
 				struct curseg_info *seg)
 {
-	if (seg->alloc_type == SSR)
+	if (seg->alloc_type == SSR) {
 		seg->next_blkoff =
 			__next_free_blkoff(sbi, seg->segno,
 						seg->next_blkoff + 1);
-	else
+	} else {
 		seg->next_blkoff++;
+		if (F2FS_OPTION(sbi).fs_mode == FS_MODE_FRAGMENT_BLK) {
+			/* To allocate block chunks in different sizes, use random number */
+			if (--seg->fragment_remained_chunk <= 0) {
+				seg->fragment_remained_chunk =
+				   prandom_u32() % sbi->max_fragment_chunk + 1;
+				seg->next_blkoff +=
+				   prandom_u32() % sbi->max_fragment_hole + 1;
+			}
+		}
+	}
 }
 
 bool f2fs_segment_has_free_slot(struct f2fs_sb_info *sbi, int segno)
@@ -3485,24 +3520,30 @@ void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
 	up_read(&SM_I(sbi)->curseg_lock);
 }
 
-static void update_device_state(struct f2fs_io_info *fio)
+void f2fs_update_device_state(struct f2fs_sb_info *sbi, nid_t ino,
+					block_t blkaddr, unsigned int blkcnt)
 {
-	struct f2fs_sb_info *sbi = fio->sbi;
-	unsigned int devidx;
-
 	if (!f2fs_is_multi_device(sbi))
 		return;
 
-	devidx = f2fs_target_device_index(sbi, fio->new_blkaddr);
+	while (1) {
+		unsigned int devidx = f2fs_target_device_index(sbi, blkaddr);
+		unsigned int blks = FDEV(devidx).end_blk - blkaddr + 1;
 
-	/* update device state for fsync */
-	f2fs_set_dirty_device(sbi, fio->ino, devidx, FLUSH_INO);
+		/* update device state for fsync */
+		f2fs_set_dirty_device(sbi, ino, devidx, FLUSH_INO);
 
-	/* update device state for checkpoint */
-	if (!f2fs_test_bit(devidx, (char *)&sbi->dirty_device)) {
-		spin_lock(&sbi->dev_lock);
-		f2fs_set_bit(devidx, (char *)&sbi->dirty_device);
-		spin_unlock(&sbi->dev_lock);
+		/* update device state for checkpoint */
+		if (!f2fs_test_bit(devidx, (char *)&sbi->dirty_device)) {
+			spin_lock(&sbi->dev_lock);
+			f2fs_set_bit(devidx, (char *)&sbi->dirty_device);
+			spin_unlock(&sbi->dev_lock);
+		}
+
+		if (blkcnt <= blks)
+			break;
+		blkcnt -= blks;
+		blkaddr += blks;
 	}
 }
 
@@ -3529,7 +3570,7 @@ reallocate:
 		goto reallocate;
 	}
 
-	update_device_state(fio);
+	f2fs_update_device_state(fio->sbi, fio->ino, fio->new_blkaddr, 1);
 
 	if (keep_order)
 		up_read(&fio->sbi->io_order_lock);
@@ -3611,6 +3652,9 @@ int f2fs_inplace_write_data(struct f2fs_io_info *fio)
 		goto drop_bio;
 	}
 
+	invalidate_mapping_pages(META_MAPPING(sbi),
+				fio->new_blkaddr, fio->new_blkaddr);
+
 	stat_inc_inplace_blocks(fio->sbi);
 
 	if (fio->bio && !(SM_I(sbi)->ipu_policy & (1 << F2FS_IPU_NOCACHE)))
@@ -3618,7 +3662,8 @@ int f2fs_inplace_write_data(struct f2fs_io_info *fio)
 	else
 		err = f2fs_submit_page_bio(fio);
 	if (!err) {
-		update_device_state(fio);
+		f2fs_update_device_state(fio->sbi, fio->ino,
+						fio->new_blkaddr, 1);
 		f2fs_update_iostat(fio->sbi, fio->io_type, F2FS_BLKSIZE);
 	}
 
diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
index 89fff258727d..46fde9f3f28e 100644
--- a/fs/f2fs/segment.h
+++ b/fs/f2fs/segment.h
@@ -314,6 +314,7 @@ struct curseg_info {
 	unsigned short next_blkoff;		/* next block offset to write */
 	unsigned int zone;			/* current zone number */
 	unsigned int next_segno;		/* preallocated segment */
+	int fragment_remained_chunk;		/* remained block size in a chunk for block fragmentation mode */
 	bool inited;				/* indicate inmem log is inited */
 };
 
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index cf049a042482..040b6d02e1d8 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -58,6 +58,7 @@ const char *f2fs_fault_name[FAULT_MAX] = {
 	[FAULT_DISCARD]		= "discard error",
 	[FAULT_WRITE_IO]	= "write IO error",
 	[FAULT_SLAB_ALLOC]	= "slab alloc",
+	[FAULT_DQUOT_INIT]	= "dquot initialize",
 };
 
 void f2fs_build_fault_attr(struct f2fs_sb_info *sbi, unsigned int rate,
@@ -592,7 +593,7 @@ static int f2fs_set_zstd_level(struct f2fs_sb_info *sbi, const char *str)
 	if (kstrtouint(str + 1, 10, &level))
 		return -EINVAL;
 
-	if (!level || level > ZSTD_maxCLevel()) {
+	if (!level || level > zstd_max_clevel()) {
 		f2fs_info(sbi, "invalid zstd compress level: %d", level);
 		return -EINVAL;
 	}
@@ -817,6 +818,10 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount)
 				F2FS_OPTION(sbi).fs_mode = FS_MODE_ADAPTIVE;
 			} else if (!strcmp(name, "lfs")) {
 				F2FS_OPTION(sbi).fs_mode = FS_MODE_LFS;
+			} else if (!strcmp(name, "fragment:segment")) {
+				F2FS_OPTION(sbi).fs_mode = FS_MODE_FRAGMENT_SEG;
+			} else if (!strcmp(name, "fragment:block")) {
+				F2FS_OPTION(sbi).fs_mode = FS_MODE_FRAGMENT_BLK;
 			} else {
 				kfree(name);
 				return -EINVAL;
@@ -1292,7 +1297,7 @@ default_check:
 	/* Not pass down write hints if the number of active logs is lesser
 	 * than NR_CURSEG_PERSIST_TYPE.
 	 */
-	if (F2FS_OPTION(sbi).active_logs != NR_CURSEG_TYPE)
+	if (F2FS_OPTION(sbi).active_logs != NR_CURSEG_PERSIST_TYPE)
 		F2FS_OPTION(sbi).whint_mode = WHINT_MODE_OFF;
 
 	if (f2fs_sb_has_readonly(sbi) && !f2fs_readonly(sbi->sb)) {
@@ -1896,6 +1901,10 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
 		seq_puts(seq, "adaptive");
 	else if (F2FS_OPTION(sbi).fs_mode == FS_MODE_LFS)
 		seq_puts(seq, "lfs");
+	else if (F2FS_OPTION(sbi).fs_mode == FS_MODE_FRAGMENT_SEG)
+		seq_puts(seq, "fragment:segment");
+	else if (F2FS_OPTION(sbi).fs_mode == FS_MODE_FRAGMENT_BLK)
+		seq_puts(seq, "fragment:block");
 	seq_printf(seq, ",active_logs=%u", F2FS_OPTION(sbi).active_logs);
 	if (test_opt(sbi, RESERVE_ROOT))
 		seq_printf(seq, ",reserve_root=%u,resuid=%u,resgid=%u",
@@ -2491,6 +2500,16 @@ retry:
 	return len - towrite;
 }
 
+int f2fs_dquot_initialize(struct inode *inode)
+{
+	if (time_to_inject(F2FS_I_SB(inode), FAULT_DQUOT_INIT)) {
+		f2fs_show_injection_info(F2FS_I_SB(inode), FAULT_DQUOT_INIT);
+		return -ESRCH;
+	}
+
+	return dquot_initialize(inode);
+}
+
 static struct dquot **f2fs_get_dquots(struct inode *inode)
 {
 	return F2FS_I(inode)->i_dquot;
@@ -2875,6 +2894,11 @@ static const struct quotactl_ops f2fs_quotactl_ops = {
 	.get_nextdqblk	= dquot_get_next_dqblk,
 };
 #else
+int f2fs_dquot_initialize(struct inode *inode)
+{
+	return 0;
+}
+
 int f2fs_quota_sync(struct super_block *sb, int type)
 {
 	return 0;
@@ -3486,7 +3510,7 @@ skip_cross:
 		NR_CURSEG_PERSIST_TYPE + nat_bits_blocks >= blocks_per_seg)) {
 		f2fs_warn(sbi, "Insane cp_payload: %u, nat_bits_blocks: %u)",
 			  cp_payload, nat_bits_blocks);
-		return -EFSCORRUPTED;
+		return 1;
 	}
 
 	if (unlikely(f2fs_cp_error(sbi))) {
@@ -3522,6 +3546,8 @@ static void init_sb_info(struct f2fs_sb_info *sbi)
 	sbi->max_victim_search = DEF_MAX_VICTIM_SEARCH;
 	sbi->migration_granularity = sbi->segs_per_sec;
 	sbi->seq_file_ra_mul = MIN_RA_MUL;
+	sbi->max_fragment_chunk = DEF_FRAGMENT_SIZE;
+	sbi->max_fragment_hole = DEF_FRAGMENT_SIZE;
 
 	sbi->dir_level = DEF_DIR_LEVEL;
 	sbi->interval_time[CP_TIME] = DEF_CP_INTERVAL;
@@ -3746,6 +3772,7 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
 {
 	struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
 	unsigned int max_devices = MAX_DEVICES;
+	unsigned int logical_blksize;
 	int i;
 
 	/* Initialize single device information */
@@ -3766,6 +3793,9 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
 	if (!sbi->devs)
 		return -ENOMEM;
 
+	logical_blksize = bdev_logical_block_size(sbi->sb->s_bdev);
+	sbi->aligned_blksize = true;
+
 	for (i = 0; i < max_devices; i++) {
 
 		if (i > 0 && !RDEV(i).path[0])
@@ -3802,6 +3832,9 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
 		/* to release errored devices */
 		sbi->s_ndevs = i + 1;
 
+		if (logical_blksize != bdev_logical_block_size(FDEV(i).bdev))
+			sbi->aligned_blksize = false;
+
 #ifdef CONFIG_BLK_DEV_ZONED
 		if (bdev_zoned_model(FDEV(i).bdev) == BLK_ZONED_HM &&
 				!f2fs_sb_has_blkzoned(sbi)) {
@@ -4351,6 +4384,8 @@ free_node_inode:
 free_stats:
 	f2fs_destroy_stats(sbi);
 free_nm:
+	/* stop discard thread before destroying node manager */
+	f2fs_stop_discard_thread(sbi);
 	f2fs_destroy_node_manager(sbi);
 free_sm:
 	f2fs_destroy_segment_manager(sbi);
diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c
index a32fe31c33b8..7d289249cd7e 100644
--- a/fs/f2fs/sysfs.c
+++ b/fs/f2fs/sysfs.c
@@ -196,7 +196,7 @@ static ssize_t encoding_show(struct f2fs_attr *a,
 	struct super_block *sb = sbi->sb;
 
 	if (f2fs_sb_has_casefold(sbi))
-		return snprintf(buf, PAGE_SIZE, "%s (%d.%d.%d)\n",
+		return sysfs_emit(buf, "%s (%d.%d.%d)\n",
 			sb->s_encoding->charset,
 			(sb->s_encoding->version >> 16) & 0xff,
 			(sb->s_encoding->version >> 8) & 0xff,
@@ -245,7 +245,7 @@ static ssize_t avg_vblocks_show(struct f2fs_attr *a,
 static ssize_t main_blkaddr_show(struct f2fs_attr *a,
 				struct f2fs_sb_info *sbi, char *buf)
 {
-	return snprintf(buf, PAGE_SIZE, "%llu\n",
+	return sysfs_emit(buf, "%llu\n",
 			(unsigned long long)MAIN_BLKADDR(sbi));
 }
 
@@ -551,6 +551,22 @@ out:
 		return count;
 	}
 
+	if (!strcmp(a->attr.name, "max_fragment_chunk")) {
+		if (t >= MIN_FRAGMENT_SIZE && t <= MAX_FRAGMENT_SIZE)
+			sbi->max_fragment_chunk = t;
+		else
+			return -EINVAL;
+		return count;
+	}
+
+	if (!strcmp(a->attr.name, "max_fragment_hole")) {
+		if (t >= MIN_FRAGMENT_SIZE && t <= MAX_FRAGMENT_SIZE)
+			sbi->max_fragment_hole = t;
+		else
+			return -EINVAL;
+		return count;
+	}
+
 	*ui = (unsigned int)t;
 
 	return count;
@@ -781,6 +797,8 @@ F2FS_RW_ATTR(ATGC_INFO, atgc_management, atgc_age_threshold, age_threshold);
 F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, seq_file_ra_mul, seq_file_ra_mul);
 F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_segment_mode, gc_segment_mode);
 F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_reclaimed_segments, gc_reclaimed_segs);
+F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, max_fragment_chunk, max_fragment_chunk);
+F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, max_fragment_hole, max_fragment_hole);
 
 #define ATTR_LIST(name) (&f2fs_attr_##name.attr)
 static struct attribute *f2fs_attrs[] = {
@@ -859,6 +877,8 @@ static struct attribute *f2fs_attrs[] = {
 	ATTR_LIST(seq_file_ra_mul),
 	ATTR_LIST(gc_segment_mode),
 	ATTR_LIST(gc_reclaimed_segments),
+	ATTR_LIST(max_fragment_chunk),
+	ATTR_LIST(max_fragment_hole),
 	NULL,
 };
 ATTRIBUTE_GROUPS(f2fs);
diff --git a/fs/f2fs/verity.c b/fs/f2fs/verity.c
index 03549b5ba204..fe5acdccaae1 100644
--- a/fs/f2fs/verity.c
+++ b/fs/f2fs/verity.c
@@ -136,7 +136,7 @@ static int f2fs_begin_enable_verity(struct file *filp)
 	 * here and not rely on ->open() doing it.  This must be done before
 	 * evicting the inline data.
 	 */
-	err = dquot_initialize(inode);
+	err = f2fs_dquot_initialize(inode);
 	if (err)
 		return err;
 
diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c
index 1d2d29dcd41c..e348f33bcb2b 100644
--- a/fs/f2fs/xattr.c
+++ b/fs/f2fs/xattr.c
@@ -773,7 +773,7 @@ int f2fs_setxattr(struct inode *inode, int index, const char *name,
 	if (!f2fs_is_checkpoint_ready(sbi))
 		return -ENOSPC;
 
-	err = dquot_initialize(inode);
+	err = f2fs_dquot_initialize(inode);
 	if (err)
 		return err;
 
diff --git a/fs/file.c b/fs/file.c
index 8627dacfc424..97d212a9b814 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -841,24 +841,68 @@ void do_close_on_exec(struct files_struct *files)
 	spin_unlock(&files->file_lock);
 }
 
+static inline struct file *__fget_files_rcu(struct files_struct *files,
+	unsigned int fd, fmode_t mask, unsigned int refs)
+{
+	for (;;) {
+		struct file *file;
+		struct fdtable *fdt = rcu_dereference_raw(files->fdt);
+		struct file __rcu **fdentry;
+
+		if (unlikely(fd >= fdt->max_fds))
+			return NULL;
+
+		fdentry = fdt->fd + array_index_nospec(fd, fdt->max_fds);
+		file = rcu_dereference_raw(*fdentry);
+		if (unlikely(!file))
+			return NULL;
+
+		if (unlikely(file->f_mode & mask))
+			return NULL;
+
+		/*
+		 * Ok, we have a file pointer. However, because we do
+		 * this all locklessly under RCU, we may be racing with
+		 * that file being closed.
+		 *
+		 * Such a race can take two forms:
+		 *
+		 *  (a) the file ref already went down to zero,
+		 *      and get_file_rcu_many() fails. Just try
+		 *      again:
+		 */
+		if (unlikely(!get_file_rcu_many(file, refs)))
+			continue;
+
+		/*
+		 *  (b) the file table entry has changed under us.
+		 *       Note that we don't need to re-check the 'fdt->fd'
+		 *       pointer having changed, because it always goes
+		 *       hand-in-hand with 'fdt'.
+		 *
+		 * If so, we need to put our refs and try again.
+		 */
+		if (unlikely(rcu_dereference_raw(files->fdt) != fdt) ||
+		    unlikely(rcu_dereference_raw(*fdentry) != file)) {
+			fput_many(file, refs);
+			continue;
+		}
+
+		/*
+		 * Ok, we have a ref to the file, and checked that it
+		 * still exists.
+		 */
+		return file;
+	}
+}
+
 static struct file *__fget_files(struct files_struct *files, unsigned int fd,
 				 fmode_t mask, unsigned int refs)
 {
 	struct file *file;
 
 	rcu_read_lock();
-loop:
-	file = files_lookup_fd_rcu(files, fd);
-	if (file) {
-		/* File object ref couldn't be taken.
-		 * dup2() atomicity guarantee is the reason
-		 * we loop to catch the new file (or NULL pointer)
-		 */
-		if (file->f_mode & mask)
-			file = NULL;
-		else if (!get_file_rcu_many(file, refs))
-			goto loop;
-	}
+	file = __fget_files_rcu(files, fd, mask, refs);
 	rcu_read_unlock();
 
 	return file;
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 79f7eda49e06..cd54a529460d 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -847,17 +847,17 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep)
 
 	replace_page_cache_page(oldpage, newpage);
 
+	get_page(newpage);
+
+	if (!(buf->flags & PIPE_BUF_FLAG_LRU))
+		lru_cache_add(newpage);
+
 	/*
 	 * Release while we have extra ref on stolen page.  Otherwise
 	 * anon_pipe_buf_release() might think the page can be reused.
 	 */
 	pipe_buf_release(cs->pipe, buf);
 
-	get_page(newpage);
-
-	if (!(buf->flags & PIPE_BUF_FLAG_LRU))
-		lru_cache_add(newpage);
-
 	err = 0;
 	spin_lock(&cs->req->waitq.lock);
 	if (test_bit(FR_ABORTED, &cs->req->flags))
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 7235d539e969..d67108489148 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -940,7 +940,7 @@ do_alloc:
 		else if (height == ip->i_height)
 			ret = gfs2_hole_size(inode, lblock, len, mp, iomap);
 		else
-			iomap->length = size - pos;
+			iomap->length = size - iomap->offset;
 	} else if (flags & IOMAP_WRITE) {
 		u64 alloc_size;
 
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index adafaaf7d24d..3e718cfc19a7 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -773,8 +773,8 @@ static inline bool should_fault_in_pages(ssize_t ret, struct iov_iter *i,
 					 size_t *prev_count,
 					 size_t *window_size)
 {
-	char __user *p = i->iov[0].iov_base + i->iov_offset;
 	size_t count = iov_iter_count(i);
+	char __user *p;
 	int pages = 1;
 
 	if (likely(!count))
@@ -787,14 +787,14 @@ static inline bool should_fault_in_pages(ssize_t ret, struct iov_iter *i,
 	if (*prev_count != count || !*window_size) {
 		int pages, nr_dirtied;
 
-		pages = min_t(int, BIO_MAX_VECS,
-			      DIV_ROUND_UP(iov_iter_count(i), PAGE_SIZE));
+		pages = min_t(int, BIO_MAX_VECS, DIV_ROUND_UP(count, PAGE_SIZE));
 		nr_dirtied = max(current->nr_dirtied_pause -
 				 current->nr_dirtied, 1);
 		pages = min(pages, nr_dirtied);
 	}
 
 	*prev_count = count;
+	p = i->iov[0].iov_base + i->iov_offset;
 	*window_size = (size_t)PAGE_SIZE * pages - offset_in_page(p);
 	return true;
 }
@@ -1013,6 +1013,7 @@ static ssize_t gfs2_file_buffered_write(struct kiocb *iocb,
 	struct gfs2_sbd *sdp = GFS2_SB(inode);
 	struct gfs2_holder *statfs_gh = NULL;
 	size_t prev_count = 0, window_size = 0;
+	size_t orig_count = iov_iter_count(from);
 	size_t read = 0;
 	ssize_t ret;
 
@@ -1057,6 +1058,7 @@ retry_under_glock:
 	if (inode == sdp->sd_rindex)
 		gfs2_glock_dq_uninit(statfs_gh);
 
+	from->count = orig_count - read;
 	if (should_fault_in_pages(ret, from, &prev_count, &window_size)) {
 		size_t leftover;
 
@@ -1064,6 +1066,7 @@ retry_under_glock:
 		leftover = fault_in_iov_iter_readable(from, window_size);
 		gfs2_holder_disallow_demote(gh);
 		if (leftover != window_size) {
+			from->count = min(from->count, window_size - leftover);
 			if (!gfs2_holder_queued(gh)) {
 				if (read)
 					goto out_uninit;
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 19f38aee1b61..44a7a4288956 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -411,14 +411,14 @@ static void do_error(struct gfs2_glock *gl, const int ret)
 static void demote_incompat_holders(struct gfs2_glock *gl,
 				    struct gfs2_holder *new_gh)
 {
-	struct gfs2_holder *gh;
+	struct gfs2_holder *gh, *tmp;
 
 	/*
 	 * Demote incompatible holders before we make ourselves eligible.
 	 * (This holder may or may not allow auto-demoting, but we don't want
 	 * to demote the new holder before it's even granted.)
 	 */
-	list_for_each_entry(gh, &gl->gl_holders, gh_list) {
+	list_for_each_entry_safe(gh, tmp, &gl->gl_holders, gh_list) {
 		/*
 		 * Since holders are at the front of the list, we stop when we
 		 * find the first non-holder.
@@ -496,7 +496,7 @@ again:
 	 * Since we unlock the lockref lock, we set a flag to indicate
 	 * instantiate is in progress.
 	 */
-	if (test_bit(GLF_INSTANTIATE_IN_PROG, &gl->gl_flags)) {
+	if (test_and_set_bit(GLF_INSTANTIATE_IN_PROG, &gl->gl_flags)) {
 		wait_on_bit(&gl->gl_flags, GLF_INSTANTIATE_IN_PROG,
 			    TASK_UNINTERRUPTIBLE);
 		/*
@@ -509,14 +509,10 @@ again:
 		goto again;
 	}
 
-	set_bit(GLF_INSTANTIATE_IN_PROG, &gl->gl_flags);
-
 	ret = glops->go_instantiate(gh);
 	if (!ret)
 		clear_bit(GLF_INSTANTIATE_NEEDED, &gl->gl_flags);
-	clear_bit(GLF_INSTANTIATE_IN_PROG, &gl->gl_flags);
-	smp_mb__after_atomic();
-	wake_up_bit(&gl->gl_flags, GLF_INSTANTIATE_IN_PROG);
+	clear_and_wake_up_bit(GLF_INSTANTIATE_IN_PROG, &gl->gl_flags);
 	return ret;
 }
 
@@ -1861,7 +1857,6 @@ void gfs2_glock_dq_m(unsigned int num_gh, struct gfs2_holder *ghs)
 
 void gfs2_glock_cb(struct gfs2_glock *gl, unsigned int state)
 {
-	struct gfs2_holder mock_gh = { .gh_gl = gl, .gh_state = state, };
 	unsigned long delay = 0;
 	unsigned long holdtime;
 	unsigned long now = jiffies;
@@ -1894,8 +1889,13 @@ void gfs2_glock_cb(struct gfs2_glock *gl, unsigned int state)
 	 * keep the glock until the last strong holder is done with it.
 	 */
 	if (!find_first_strong_holder(gl)) {
-		if (state == LM_ST_UNLOCKED)
-			mock_gh.gh_state = LM_ST_EXCLUSIVE;
+		struct gfs2_holder mock_gh = {
+			.gh_gl = gl,
+			.gh_state = (state == LM_ST_UNLOCKED) ?
+				    LM_ST_EXCLUSIVE : state,
+			.gh_iflags = BIT(HIF_HOLDER)
+		};
+
 		demote_incompat_holders(gl, &mock_gh);
 	}
 	handle_callback(gl, state, delay, true);
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 6424b903e885..89905f4f29bb 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -40,37 +40,6 @@ static const struct inode_operations gfs2_file_iops;
 static const struct inode_operations gfs2_dir_iops;
 static const struct inode_operations gfs2_symlink_iops;
 
-static int iget_test(struct inode *inode, void *opaque)
-{
-	u64 no_addr = *(u64 *)opaque;
-
-	return GFS2_I(inode)->i_no_addr == no_addr;
-}
-
-static int iget_set(struct inode *inode, void *opaque)
-{
-	u64 no_addr = *(u64 *)opaque;
-
-	GFS2_I(inode)->i_no_addr = no_addr;
-	inode->i_ino = no_addr;
-	return 0;
-}
-
-static struct inode *gfs2_iget(struct super_block *sb, u64 no_addr)
-{
-	struct inode *inode;
-
-repeat:
-	inode = iget5_locked(sb, no_addr, iget_test, iget_set, &no_addr);
-	if (!inode)
-		return inode;
-	if (is_bad_inode(inode)) {
-		iput(inode);
-		goto repeat;
-	}
-	return inode;
-}
-
 /**
  * gfs2_set_iop - Sets inode operations
  * @inode: The inode with correct i_mode filled in
@@ -104,6 +73,22 @@ static void gfs2_set_iop(struct inode *inode)
 	}
 }
 
+static int iget_test(struct inode *inode, void *opaque)
+{
+	u64 no_addr = *(u64 *)opaque;
+
+	return GFS2_I(inode)->i_no_addr == no_addr;
+}
+
+static int iget_set(struct inode *inode, void *opaque)
+{
+	u64 no_addr = *(u64 *)opaque;
+
+	GFS2_I(inode)->i_no_addr = no_addr;
+	inode->i_ino = no_addr;
+	return 0;
+}
+
 /**
  * gfs2_inode_lookup - Lookup an inode
  * @sb: The super block
@@ -132,12 +117,11 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type,
 {
 	struct inode *inode;
 	struct gfs2_inode *ip;
-	struct gfs2_glock *io_gl = NULL;
 	struct gfs2_holder i_gh;
 	int error;
 
 	gfs2_holder_mark_uninitialized(&i_gh);
-	inode = gfs2_iget(sb, no_addr);
+	inode = iget5_locked(sb, no_addr, iget_test, iget_set, &no_addr);
 	if (!inode)
 		return ERR_PTR(-ENOMEM);
 
@@ -145,22 +129,16 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type,
 
 	if (inode->i_state & I_NEW) {
 		struct gfs2_sbd *sdp = GFS2_SB(inode);
+		struct gfs2_glock *io_gl;
 
 		error = gfs2_glock_get(sdp, no_addr, &gfs2_inode_glops, CREATE, &ip->i_gl);
 		if (unlikely(error))
 			goto fail;
-		flush_delayed_work(&ip->i_gl->gl_work);
-
-		error = gfs2_glock_get(sdp, no_addr, &gfs2_iopen_glops, CREATE, &io_gl);
-		if (unlikely(error))
-			goto fail;
-		if (blktype != GFS2_BLKST_UNLINKED)
-			gfs2_cancel_delete_work(io_gl);
 
 		if (type == DT_UNKNOWN || blktype != GFS2_BLKST_FREE) {
 			/*
 			 * The GL_SKIP flag indicates to skip reading the inode
-			 * block.  We read the inode with gfs2_inode_refresh
+			 * block.  We read the inode when instantiating it
 			 * after possibly checking the block type.
 			 */
 			error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE,
@@ -181,24 +159,31 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type,
 			}
 		}
 
-		glock_set_object(ip->i_gl, ip);
 		set_bit(GLF_INSTANTIATE_NEEDED, &ip->i_gl->gl_flags);
-		error = gfs2_glock_nq_init(io_gl, LM_ST_SHARED, GL_EXACT, &ip->i_iopen_gh);
+
+		error = gfs2_glock_get(sdp, no_addr, &gfs2_iopen_glops, CREATE, &io_gl);
 		if (unlikely(error))
 			goto fail;
-		glock_set_object(ip->i_iopen_gh.gh_gl, ip);
+		if (blktype != GFS2_BLKST_UNLINKED)
+			gfs2_cancel_delete_work(io_gl);
+		error = gfs2_glock_nq_init(io_gl, LM_ST_SHARED, GL_EXACT, &ip->i_iopen_gh);
 		gfs2_glock_put(io_gl);
-		io_gl = NULL;
+		if (unlikely(error))
+			goto fail;
 
 		/* Lowest possible timestamp; will be overwritten in gfs2_dinode_in. */
 		inode->i_atime.tv_sec = 1LL << (8 * sizeof(inode->i_atime.tv_sec) - 1);
 		inode->i_atime.tv_nsec = 0;
 
+		glock_set_object(ip->i_gl, ip);
+
 		if (type == DT_UNKNOWN) {
 			/* Inode glock must be locked already */
 			error = gfs2_instantiate(&i_gh);
-			if (error)
+			if (error) {
+				glock_clear_object(ip->i_gl, ip);
 				goto fail;
+			}
 		} else {
 			ip->i_no_formal_ino = no_formal_ino;
 			inode->i_mode = DT2IF(type);
@@ -206,31 +191,23 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type,
 
 		if (gfs2_holder_initialized(&i_gh))
 			gfs2_glock_dq_uninit(&i_gh);
+		glock_set_object(ip->i_iopen_gh.gh_gl, ip);
 
 		gfs2_set_iop(inode);
+		unlock_new_inode(inode);
 	}
 
 	if (no_formal_ino && ip->i_no_formal_ino &&
 	    no_formal_ino != ip->i_no_formal_ino) {
-		error = -ESTALE;
-		if (inode->i_state & I_NEW)
-			goto fail;
 		iput(inode);
-		return ERR_PTR(error);
+		return ERR_PTR(-ESTALE);
 	}
 
-	if (inode->i_state & I_NEW)
-		unlock_new_inode(inode);
-
 	return inode;
 
 fail:
-	if (gfs2_holder_initialized(&ip->i_iopen_gh)) {
-		glock_clear_object(ip->i_iopen_gh.gh_gl, ip);
+	if (gfs2_holder_initialized(&ip->i_iopen_gh))
 		gfs2_glock_dq_uninit(&ip->i_iopen_gh);
-	}
-	if (io_gl)
-		gfs2_glock_put(io_gl);
 	if (gfs2_holder_initialized(&i_gh))
 		gfs2_glock_dq_uninit(&i_gh);
 	iget_failed(inode);
@@ -730,18 +707,19 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 	error = gfs2_glock_get(sdp, ip->i_no_addr, &gfs2_inode_glops, CREATE, &ip->i_gl);
 	if (error)
 		goto fail_free_inode;
-	flush_delayed_work(&ip->i_gl->gl_work);
 
 	error = gfs2_glock_get(sdp, ip->i_no_addr, &gfs2_iopen_glops, CREATE, &io_gl);
 	if (error)
 		goto fail_free_inode;
 	gfs2_cancel_delete_work(io_gl);
 
+	error = insert_inode_locked4(inode, ip->i_no_addr, iget_test, &ip->i_no_addr);
+	BUG_ON(error);
+
 	error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_SKIP, ghs + 1);
 	if (error)
 		goto fail_gunlock2;
 
-	glock_set_object(ip->i_gl, ip);
 	error = gfs2_trans_begin(sdp, blocks, 0);
 	if (error)
 		goto fail_gunlock2;
@@ -757,9 +735,9 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 	if (error)
 		goto fail_gunlock2;
 
+	glock_set_object(ip->i_gl, ip);
 	glock_set_object(io_gl, ip);
 	gfs2_set_iop(inode);
-	insert_inode_hash(inode);
 
 	free_vfs_inode = 0; /* After this point, the inode is no longer
 			       considered free. Any failures need to undo
@@ -801,17 +779,17 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 	gfs2_glock_dq_uninit(ghs + 1);
 	gfs2_glock_put(io_gl);
 	gfs2_qa_put(dip);
+	unlock_new_inode(inode);
 	return error;
 
 fail_gunlock3:
+	glock_clear_object(ip->i_gl, ip);
 	glock_clear_object(io_gl, ip);
 	gfs2_glock_dq_uninit(&ip->i_iopen_gh);
 fail_gunlock2:
-	glock_clear_object(io_gl, ip);
 	gfs2_glock_put(io_gl);
 fail_free_inode:
 	if (ip->i_gl) {
-		glock_clear_object(ip->i_gl, ip);
 		if (free_vfs_inode) /* else evict will do the put for us */
 			gfs2_glock_put(ip->i_gl);
 	}
@@ -829,7 +807,10 @@ fail_gunlock:
 			mark_inode_dirty(inode);
 		set_bit(free_vfs_inode ? GIF_FREE_VFS_INODE : GIF_ALLOC_FAILED,
 			&GFS2_I(inode)->i_flags);
-		iput(inode);
+		if (inode->i_state & I_NEW)
+			iget_failed(inode);
+		else
+			iput(inode);
 	}
 	if (gfs2_holder_initialized(ghs + 1))
 		gfs2_glock_dq_uninit(ghs + 1);
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 5b121371508a..0f93e8beca4d 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -1402,13 +1402,6 @@ out:
 	gfs2_ordered_del_inode(ip);
 	clear_inode(inode);
 	gfs2_dir_hash_inval(ip);
-	if (ip->i_gl) {
-		glock_clear_object(ip->i_gl, ip);
-		wait_on_bit_io(&ip->i_flags, GIF_GLOP_PENDING, TASK_UNINTERRUPTIBLE);
-		gfs2_glock_add_to_lru(ip->i_gl);
-		gfs2_glock_put_eventually(ip->i_gl);
-		ip->i_gl = NULL;
-	}
 	if (gfs2_holder_initialized(&ip->i_iopen_gh)) {
 		struct gfs2_glock *gl = ip->i_iopen_gh.gh_gl;
 
@@ -1421,6 +1414,13 @@ out:
 		gfs2_holder_uninit(&ip->i_iopen_gh);
 		gfs2_glock_put_eventually(gl);
 	}
+	if (ip->i_gl) {
+		glock_clear_object(ip->i_gl, ip);
+		wait_on_bit_io(&ip->i_flags, GIF_GLOP_PENDING, TASK_UNINTERRUPTIBLE);
+		gfs2_glock_add_to_lru(ip->i_gl);
+		gfs2_glock_put_eventually(ip->i_gl);
+		ip->i_gl = NULL;
+	}
 }
 
 static struct inode *gfs2_alloc_inode(struct super_block *sb)
diff --git a/fs/inode.c b/fs/inode.c
index 3eba0940ffcf..6b80a51129d5 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -180,8 +180,6 @@ int inode_init_always(struct super_block *sb, struct inode *inode)
 	mapping->a_ops = &empty_aops;
 	mapping->host = inode;
 	mapping->flags = 0;
-	if (sb->s_type->fs_flags & FS_THP_SUPPORT)
-		__set_bit(AS_THP_SUPPORT, &mapping->flags);
 	mapping->wb_err = 0;
 	atomic_set(&mapping->i_mmap_writable, 0);
 #ifdef CONFIG_READ_ONLY_THP_FOR_FS
diff --git a/fs/io-wq.c b/fs/io-wq.c
index afd955d53db9..5c4f582d6549 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -142,6 +142,7 @@ static bool io_acct_cancel_pending_work(struct io_wqe *wqe,
 					struct io_wqe_acct *acct,
 					struct io_cb_cancel_data *match);
 static void create_worker_cb(struct callback_head *cb);
+static void io_wq_cancel_tw_create(struct io_wq *wq);
 
 static bool io_worker_get(struct io_worker *worker)
 {
@@ -357,12 +358,22 @@ static bool io_queue_worker_create(struct io_worker *worker,
 	    test_and_set_bit_lock(0, &worker->create_state))
 		goto fail_release;
 
+	atomic_inc(&wq->worker_refs);
 	init_task_work(&worker->create_work, func);
 	worker->create_index = acct->index;
 	if (!task_work_add(wq->task, &worker->create_work, TWA_SIGNAL)) {
-		clear_bit_unlock(0, &worker->create_state);
+		/*
+		 * EXIT may have been set after checking it above, check after
+		 * adding the task_work and remove any creation item if it is
+		 * now set. wq exit does that too, but we can have added this
+		 * work item after we canceled in io_wq_exit_workers().
+		 */
+		if (test_bit(IO_WQ_BIT_EXIT, &wq->state))
+			io_wq_cancel_tw_create(wq);
+		io_worker_ref_put(wq);
 		return true;
 	}
+	io_worker_ref_put(wq);
 	clear_bit_unlock(0, &worker->create_state);
 fail_release:
 	io_worker_release(worker);
@@ -384,7 +395,9 @@ static void io_wqe_dec_running(struct io_worker *worker)
 	if (atomic_dec_and_test(&acct->nr_running) && io_acct_run_queue(acct)) {
 		atomic_inc(&acct->nr_running);
 		atomic_inc(&wqe->wq->worker_refs);
+		raw_spin_unlock(&wqe->lock);
 		io_queue_worker_create(worker, acct, create_worker_cb);
+		raw_spin_lock(&wqe->lock);
 	}
 }
 
@@ -423,9 +436,10 @@ static inline unsigned int io_get_work_hash(struct io_wq_work *work)
 	return work->flags >> IO_WQ_HASH_SHIFT;
 }
 
-static void io_wait_on_hash(struct io_wqe *wqe, unsigned int hash)
+static bool io_wait_on_hash(struct io_wqe *wqe, unsigned int hash)
 {
 	struct io_wq *wq = wqe->wq;
+	bool ret = false;
 
 	spin_lock_irq(&wq->hash->wait.lock);
 	if (list_empty(&wqe->wait.entry)) {
@@ -433,9 +447,11 @@ static void io_wait_on_hash(struct io_wqe *wqe, unsigned int hash)
 		if (!test_bit(hash, &wq->hash->map)) {
 			__set_current_state(TASK_RUNNING);
 			list_del_init(&wqe->wait.entry);
+			ret = true;
 		}
 	}
 	spin_unlock_irq(&wq->hash->wait.lock);
+	return ret;
 }
 
 static struct io_wq_work *io_get_next_work(struct io_wqe_acct *acct,
@@ -475,14 +491,21 @@ static struct io_wq_work *io_get_next_work(struct io_wqe_acct *acct,
 	}
 
 	if (stall_hash != -1U) {
+		bool unstalled;
+
 		/*
 		 * Set this before dropping the lock to avoid racing with new
 		 * work being added and clearing the stalled bit.
 		 */
 		set_bit(IO_ACCT_STALLED_BIT, &acct->flags);
 		raw_spin_unlock(&wqe->lock);
-		io_wait_on_hash(wqe, stall_hash);
+		unstalled = io_wait_on_hash(wqe, stall_hash);
 		raw_spin_lock(&wqe->lock);
+		if (unstalled) {
+			clear_bit(IO_ACCT_STALLED_BIT, &acct->flags);
+			if (wq_has_sleeper(&wqe->wq->hash->wait))
+				wake_up(&wqe->wq->hash->wait);
+		}
 	}
 
 	return NULL;
@@ -564,8 +587,11 @@ get_next:
 				io_wqe_enqueue(wqe, linked);
 
 			if (hash != -1U && !next_hashed) {
+				/* serialize hash clear with wake_up() */
+				spin_lock_irq(&wq->hash->wait.lock);
 				clear_bit(hash, &wq->hash->map);
 				clear_bit(IO_ACCT_STALLED_BIT, &acct->flags);
+				spin_unlock_irq(&wq->hash->wait.lock);
 				if (wq_has_sleeper(&wq->hash->wait))
 					wake_up(&wq->hash->wait);
 				raw_spin_lock(&wqe->lock);
@@ -701,6 +727,13 @@ static bool io_wq_work_match_all(struct io_wq_work *work, void *data)
 
 static inline bool io_should_retry_thread(long err)
 {
+	/*
+	 * Prevent perpetual task_work retry, if the task (or its group) is
+	 * exiting.
+	 */
+	if (fatal_signal_pending(current))
+		return false;
+
 	switch (err) {
 	case -EAGAIN:
 	case -ERESTARTSYS:
@@ -1178,13 +1211,9 @@ void io_wq_exit_start(struct io_wq *wq)
 	set_bit(IO_WQ_BIT_EXIT, &wq->state);
 }
 
-static void io_wq_exit_workers(struct io_wq *wq)
+static void io_wq_cancel_tw_create(struct io_wq *wq)
 {
 	struct callback_head *cb;
-	int node;
-
-	if (!wq->task)
-		return;
 
 	while ((cb = task_work_cancel_match(wq->task, io_task_work_match, wq)) != NULL) {
 		struct io_worker *worker;
@@ -1192,6 +1221,16 @@ static void io_wq_exit_workers(struct io_wq *wq)
 		worker = container_of(cb, struct io_worker, create_work);
 		io_worker_cancel_cb(worker);
 	}
+}
+
+static void io_wq_exit_workers(struct io_wq *wq)
+{
+	int node;
+
+	if (!wq->task)
+		return;
+
+	io_wq_cancel_tw_create(wq);
 
 	rcu_read_lock();
 	for_each_node(node) {
diff --git a/fs/io_uring.c b/fs/io_uring.c
index b07196b4511c..fb2a0cb4aaf8 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1278,6 +1278,7 @@ static void io_refs_resurrect(struct percpu_ref *ref, struct completion *compl)
 
 static bool io_match_task(struct io_kiocb *head, struct task_struct *task,
 			  bool cancel_all)
+	__must_hold(&req->ctx->timeout_lock)
 {
 	struct io_kiocb *req;
 
@@ -1293,6 +1294,44 @@ static bool io_match_task(struct io_kiocb *head, struct task_struct *task,
 	return false;
 }
 
+static bool io_match_linked(struct io_kiocb *head)
+{
+	struct io_kiocb *req;
+
+	io_for_each_link(req, head) {
+		if (req->flags & REQ_F_INFLIGHT)
+			return true;
+	}
+	return false;
+}
+
+/*
+ * As io_match_task() but protected against racing with linked timeouts.
+ * User must not hold timeout_lock.
+ */
+static bool io_match_task_safe(struct io_kiocb *head, struct task_struct *task,
+			       bool cancel_all)
+{
+	bool matched;
+
+	if (task && head->task != task)
+		return false;
+	if (cancel_all)
+		return true;
+
+	if (head->flags & REQ_F_LINK_TIMEOUT) {
+		struct io_ring_ctx *ctx = head->ctx;
+
+		/* protect against races with linked timeouts */
+		spin_lock_irq(&ctx->timeout_lock);
+		matched = io_match_linked(head);
+		spin_unlock_irq(&ctx->timeout_lock);
+	} else {
+		matched = io_match_linked(head);
+	}
+	return matched;
+}
+
 static inline bool req_has_async_data(struct io_kiocb *req)
 {
 	return req->flags & REQ_F_ASYNC_DATA;
@@ -1502,10 +1541,10 @@ static void io_prep_async_link(struct io_kiocb *req)
 	if (req->flags & REQ_F_LINK_TIMEOUT) {
 		struct io_ring_ctx *ctx = req->ctx;
 
-		spin_lock(&ctx->completion_lock);
+		spin_lock_irq(&ctx->timeout_lock);
 		io_for_each_link(cur, req)
 			io_prep_async_work(cur);
-		spin_unlock(&ctx->completion_lock);
+		spin_unlock_irq(&ctx->timeout_lock);
 	} else {
 		io_for_each_link(cur, req)
 			io_prep_async_work(cur);
@@ -2852,9 +2891,13 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 		req->flags |= io_file_get_flags(file) << REQ_F_SUPPORT_NOWAIT_BIT;
 
 	kiocb->ki_pos = READ_ONCE(sqe->off);
-	if (kiocb->ki_pos == -1 && !(file->f_mode & FMODE_STREAM)) {
-		req->flags |= REQ_F_CUR_POS;
-		kiocb->ki_pos = file->f_pos;
+	if (kiocb->ki_pos == -1) {
+		if (!(file->f_mode & FMODE_STREAM)) {
+			req->flags |= REQ_F_CUR_POS;
+			kiocb->ki_pos = file->f_pos;
+		} else {
+			kiocb->ki_pos = 0;
+		}
 	}
 	kiocb->ki_flags = iocb_flags(file);
 	ret = kiocb_set_rw_flags(kiocb, READ_ONCE(sqe->rw_flags));
@@ -4327,6 +4370,7 @@ static int __io_remove_buffers(struct io_ring_ctx *ctx, struct io_buffer *buf,
 		kfree(nxt);
 		if (++i == nbufs)
 			return i;
+		cond_resched();
 	}
 	i++;
 	kfree(buf);
@@ -5704,7 +5748,7 @@ static __cold bool io_poll_remove_all(struct io_ring_ctx *ctx,
 
 		list = &ctx->cancel_hash[i];
 		hlist_for_each_entry_safe(req, tmp, list, hash_node) {
-			if (io_match_task(req, tsk, cancel_all))
+			if (io_match_task_safe(req, tsk, cancel_all))
 				posted += io_poll_remove_one(req);
 		}
 	}
@@ -6156,6 +6200,9 @@ static int io_timeout_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 	if (get_timespec64(&data->ts, u64_to_user_ptr(sqe->addr)))
 		return -EFAULT;
 
+	if (data->ts.tv_sec < 0 || data->ts.tv_nsec < 0)
+		return -EINVAL;
+
 	data->mode = io_translate_timeout_mode(flags);
 	hrtimer_init(&data->timer, io_timeout_get_clock(data), data->mode);
 
@@ -6880,10 +6927,11 @@ static inline struct file *io_file_get(struct io_ring_ctx *ctx,
 static void io_req_task_link_timeout(struct io_kiocb *req, bool *locked)
 {
 	struct io_kiocb *prev = req->timeout.prev;
-	int ret;
+	int ret = -ENOENT;
 
 	if (prev) {
-		ret = io_try_cancel_userdata(req, prev->user_data);
+		if (!(req->task->flags & PF_EXITING))
+			ret = io_try_cancel_userdata(req, prev->user_data);
 		io_req_complete_post(req, ret ?: -ETIME, 0);
 		io_put_req(prev);
 	} else {
@@ -9255,10 +9303,8 @@ static void io_destroy_buffers(struct io_ring_ctx *ctx)
 	struct io_buffer *buf;
 	unsigned long index;
 
-	xa_for_each(&ctx->io_buffers, index, buf) {
+	xa_for_each(&ctx->io_buffers, index, buf)
 		__io_remove_buffers(ctx, buf, index, -1U);
-		cond_resched();
-	}
 }
 
 static void io_req_caches_free(struct io_ring_ctx *ctx)
@@ -9562,19 +9608,8 @@ static bool io_cancel_task_cb(struct io_wq_work *work, void *data)
 {
 	struct io_kiocb *req = container_of(work, struct io_kiocb, work);
 	struct io_task_cancel *cancel = data;
-	bool ret;
 
-	if (!cancel->all && (req->flags & REQ_F_LINK_TIMEOUT)) {
-		struct io_ring_ctx *ctx = req->ctx;
-
-		/* protect against races with linked timeouts */
-		spin_lock(&ctx->completion_lock);
-		ret = io_match_task(req, cancel->task, cancel->all);
-		spin_unlock(&ctx->completion_lock);
-	} else {
-		ret = io_match_task(req, cancel->task, cancel->all);
-	}
-	return ret;
+	return io_match_task_safe(req, cancel->task, cancel->all);
 }
 
 static __cold bool io_cancel_defer_files(struct io_ring_ctx *ctx,
@@ -9586,7 +9621,7 @@ static __cold bool io_cancel_defer_files(struct io_ring_ctx *ctx,
 
 	spin_lock(&ctx->completion_lock);
 	list_for_each_entry_reverse(de, &ctx->defer_list, list) {
-		if (io_match_task(de->req, task, cancel_all)) {
+		if (io_match_task_safe(de->req, task, cancel_all)) {
 			list_cut_position(&list, &ctx->defer_list, &de->list);
 			break;
 		}
@@ -9764,7 +9799,7 @@ static __cold void io_uring_clean_tctx(struct io_uring_task *tctx)
 	}
 	if (wq) {
 		/*
-		 * Must be after io_uring_del_task_file() (removes nodes under
+		 * Must be after io_uring_del_tctx_node() (removes nodes under
 		 * uring_lock) to avoid race with io_uring_try_cancel_iowq().
 		 */
 		io_wq_put_and_exit(wq);
@@ -9793,7 +9828,7 @@ static __cold void io_uring_drop_tctx_refs(struct task_struct *task)
 
 /*
  * Find any io_uring ctx that this task has registered or done IO on, and cancel
- * requests. @sqd should be not-null IIF it's an SQPOLL thread cancellation.
+ * requests. @sqd should be not-null IFF it's an SQPOLL thread cancellation.
  */
 static __cold void io_uring_cancel_generic(bool cancel_all,
 					   struct io_sq_data *sqd)
@@ -9835,8 +9870,10 @@ static __cold void io_uring_cancel_generic(bool cancel_all,
 							     cancel_all);
 		}
 
-		prepare_to_wait(&tctx->wait, &wait, TASK_UNINTERRUPTIBLE);
+		prepare_to_wait(&tctx->wait, &wait, TASK_INTERRUPTIBLE);
+		io_run_task_work();
 		io_uring_drop_tctx_refs(current);
+
 		/*
 		 * If we've seen completions, retry without waiting. This
 		 * avoids a race where a completion comes in before we did
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 1753c26c8e76..71a36ae120ee 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -205,7 +205,16 @@ struct iomap_readpage_ctx {
 	struct readahead_control *rac;
 };
 
-static loff_t iomap_read_inline_data(const struct iomap_iter *iter,
+/**
+ * iomap_read_inline_data - copy inline data into the page cache
+ * @iter: iteration structure
+ * @page: page to copy to
+ *
+ * Copy the inline data in @iter into @page and zero out the rest of the page.
+ * Only a single IOMAP_INLINE extent is allowed at the end of each file.
+ * Returns zero for success to complete the read, or the usual negative errno.
+ */
+static int iomap_read_inline_data(const struct iomap_iter *iter,
 		struct page *page)
 {
 	const struct iomap *iomap = iomap_iter_srcmap(iter);
@@ -214,7 +223,7 @@ static loff_t iomap_read_inline_data(const struct iomap_iter *iter,
 	void *addr;
 
 	if (PageUptodate(page))
-		return PAGE_SIZE - poff;
+		return 0;
 
 	if (WARN_ON_ONCE(size > PAGE_SIZE - poff))
 		return -EIO;
@@ -231,7 +240,7 @@ static loff_t iomap_read_inline_data(const struct iomap_iter *iter,
 	memset(addr + size, 0, PAGE_SIZE - poff - size);
 	kunmap_local(addr);
 	iomap_set_range_uptodate(page, poff, PAGE_SIZE - poff);
-	return PAGE_SIZE - poff;
+	return 0;
 }
 
 static inline bool iomap_block_needs_zeroing(const struct iomap_iter *iter,
@@ -257,7 +266,7 @@ static loff_t iomap_readpage_iter(const struct iomap_iter *iter,
 	sector_t sector;
 
 	if (iomap->type == IOMAP_INLINE)
-		return min(iomap_read_inline_data(iter, page), length);
+		return iomap_read_inline_data(iter, page);
 
 	/* zero post-eof blocks as the page may be mapped */
 	iop = iomap_page_create(iter->inode, page);
@@ -370,6 +379,8 @@ static loff_t iomap_readahead_iter(const struct iomap_iter *iter,
 			ctx->cur_page_in_bio = false;
 		}
 		ret = iomap_readpage_iter(iter, ctx, done);
+		if (ret <= 0)
+			return ret;
 	}
 
 	return done;
@@ -580,15 +591,10 @@ static int __iomap_write_begin(const struct iomap_iter *iter, loff_t pos,
 static int iomap_write_begin_inline(const struct iomap_iter *iter,
 		struct page *page)
 {
-	int ret;
-
 	/* needs more work for the tailpacking case; disable for now */
 	if (WARN_ON_ONCE(iomap_iter_srcmap(iter)->offset != 0))
 		return -EIO;
-	ret = iomap_read_inline_data(iter, page);
-	if (ret < 0)
-		return ret;
-	return 0;
+	return iomap_read_inline_data(iter, page);
 }
 
 static int iomap_write_begin(const struct iomap_iter *iter, loff_t pos,
diff --git a/fs/ksmbd/Kconfig b/fs/ksmbd/Kconfig
index b83cbd756ae5..e1fe17747ed6 100644
--- a/fs/ksmbd/Kconfig
+++ b/fs/ksmbd/Kconfig
@@ -6,7 +6,6 @@ config SMB_SERVER
 	select NLS
 	select NLS_UTF8
 	select CRYPTO
-	select CRYPTO_MD4
 	select CRYPTO_MD5
 	select CRYPTO_HMAC
 	select CRYPTO_ECB
@@ -19,6 +18,7 @@ config SMB_SERVER
 	select CRYPTO_GCM
 	select ASN1
 	select OID_REGISTRY
+	select CRC32
 	default n
 	help
 	  Choose Y here if you want to allow SMB3 compliant clients
diff --git a/fs/ksmbd/auth.c b/fs/ksmbd/auth.c
index 30a92ddc1817..3503b1c48cb4 100644
--- a/fs/ksmbd/auth.c
+++ b/fs/ksmbd/auth.c
@@ -873,9 +873,9 @@ int ksmbd_gen_preauth_integrity_hash(struct ksmbd_conn *conn, char *buf,
 				     __u8 *pi_hash)
 {
 	int rc;
-	struct smb2_hdr *rcv_hdr = (struct smb2_hdr *)buf;
+	struct smb2_hdr *rcv_hdr = smb2_get_msg(buf);
 	char *all_bytes_msg = (char *)&rcv_hdr->ProtocolId;
-	int msg_size = be32_to_cpu(rcv_hdr->smb2_buf_length);
+	int msg_size = get_rfc1002_len(buf);
 	struct ksmbd_crypto_ctx *ctx = NULL;
 
 	if (conn->preauth_info->Preauth_HashId !=
@@ -983,7 +983,7 @@ static struct scatterlist *ksmbd_init_sg(struct kvec *iov, unsigned int nvec,
 					 u8 *sign)
 {
 	struct scatterlist *sg;
-	unsigned int assoc_data_len = sizeof(struct smb2_transform_hdr) - 24;
+	unsigned int assoc_data_len = sizeof(struct smb2_transform_hdr) - 20;
 	int i, nr_entries[3] = {0}, total_entries = 0, sg_idx = 0;
 
 	if (!nvec)
@@ -1047,9 +1047,8 @@ static struct scatterlist *ksmbd_init_sg(struct kvec *iov, unsigned int nvec,
 int ksmbd_crypt_message(struct ksmbd_conn *conn, struct kvec *iov,
 			unsigned int nvec, int enc)
 {
-	struct smb2_transform_hdr *tr_hdr =
-		(struct smb2_transform_hdr *)iov[0].iov_base;
-	unsigned int assoc_data_len = sizeof(struct smb2_transform_hdr) - 24;
+	struct smb2_transform_hdr *tr_hdr = smb2_get_msg(iov[0].iov_base);
+	unsigned int assoc_data_len = sizeof(struct smb2_transform_hdr) - 20;
 	int rc;
 	struct scatterlist *sg;
 	u8 sign[SMB2_SIGNATURE_SIZE] = {};
diff --git a/fs/ksmbd/connection.c b/fs/ksmbd/connection.c
index b57a0d8a392f..83a94d0bb480 100644
--- a/fs/ksmbd/connection.c
+++ b/fs/ksmbd/connection.c
@@ -158,26 +158,25 @@ void ksmbd_conn_wait_idle(struct ksmbd_conn *conn)
 int ksmbd_conn_write(struct ksmbd_work *work)
 {
 	struct ksmbd_conn *conn = work->conn;
-	struct smb_hdr *rsp_hdr = work->response_buf;
 	size_t len = 0;
 	int sent;
 	struct kvec iov[3];
 	int iov_idx = 0;
 
 	ksmbd_conn_try_dequeue_request(work);
-	if (!rsp_hdr) {
+	if (!work->response_buf) {
 		pr_err("NULL response header\n");
 		return -EINVAL;
 	}
 
 	if (work->tr_buf) {
 		iov[iov_idx] = (struct kvec) { work->tr_buf,
-				sizeof(struct smb2_transform_hdr) };
+				sizeof(struct smb2_transform_hdr) + 4 };
 		len += iov[iov_idx++].iov_len;
 	}
 
 	if (work->aux_payload_sz) {
-		iov[iov_idx] = (struct kvec) { rsp_hdr, work->resp_hdr_sz };
+		iov[iov_idx] = (struct kvec) { work->response_buf, work->resp_hdr_sz };
 		len += iov[iov_idx++].iov_len;
 		iov[iov_idx] = (struct kvec) { work->aux_payload_buf, work->aux_payload_sz };
 		len += iov[iov_idx++].iov_len;
@@ -185,8 +184,8 @@ int ksmbd_conn_write(struct ksmbd_work *work)
 		if (work->tr_buf)
 			iov[iov_idx].iov_len = work->resp_hdr_sz;
 		else
-			iov[iov_idx].iov_len = get_rfc1002_len(rsp_hdr) + 4;
-		iov[iov_idx].iov_base = rsp_hdr;
+			iov[iov_idx].iov_len = get_rfc1002_len(work->response_buf) + 4;
+		iov[iov_idx].iov_base = work->response_buf;
 		len += iov[iov_idx++].iov_len;
 	}
 
diff --git a/fs/ksmbd/ksmbd_work.c b/fs/ksmbd/ksmbd_work.c
index fd58eb4809f6..14b9caebf7a4 100644
--- a/fs/ksmbd/ksmbd_work.c
+++ b/fs/ksmbd/ksmbd_work.c
@@ -69,7 +69,6 @@ int ksmbd_workqueue_init(void)
 
 void ksmbd_workqueue_destroy(void)
 {
-	flush_workqueue(ksmbd_wq);
 	destroy_workqueue(ksmbd_wq);
 	ksmbd_wq = NULL;
 }
diff --git a/fs/ksmbd/ksmbd_work.h b/fs/ksmbd/ksmbd_work.h
index f7156bc50049..5ece58e40c97 100644
--- a/fs/ksmbd/ksmbd_work.h
+++ b/fs/ksmbd/ksmbd_work.h
@@ -92,7 +92,7 @@ struct ksmbd_work {
  */
 static inline void *ksmbd_resp_buf_next(struct ksmbd_work *work)
 {
-	return work->response_buf + work->next_smb2_rsp_hdr_off;
+	return work->response_buf + work->next_smb2_rsp_hdr_off + 4;
 }
 
 /**
@@ -101,7 +101,7 @@ static inline void *ksmbd_resp_buf_next(struct ksmbd_work *work)
  */
 static inline void *ksmbd_req_buf_next(struct ksmbd_work *work)
 {
-	return work->request_buf + work->next_smb2_rcv_hdr_off;
+	return work->request_buf + work->next_smb2_rcv_hdr_off + 4;
 }
 
 struct ksmbd_work *ksmbd_alloc_work_struct(void);
diff --git a/fs/ksmbd/ndr.c b/fs/ksmbd/ndr.c
index 8317f7ca402b..5052be9261d9 100644
--- a/fs/ksmbd/ndr.c
+++ b/fs/ksmbd/ndr.c
@@ -148,7 +148,7 @@ static int ndr_read_int16(struct ndr *n, __u16 *value)
 static int ndr_read_int32(struct ndr *n, __u32 *value)
 {
 	if (n->offset + sizeof(__u32) > n->length)
-		return 0;
+		return -EINVAL;
 
 	if (value)
 		*value = le32_to_cpu(*(__le32 *)ndr_get_field(n));
diff --git a/fs/ksmbd/oplock.c b/fs/ksmbd/oplock.c
index f9dae6ef2115..077b8761d099 100644
--- a/fs/ksmbd/oplock.c
+++ b/fs/ksmbd/oplock.c
@@ -629,10 +629,10 @@ static void __smb2_oplock_break_noti(struct work_struct *wk)
 		return;
 	}
 
-	rsp_hdr = work->response_buf;
+	rsp_hdr = smb2_get_msg(work->response_buf);
 	memset(rsp_hdr, 0, sizeof(struct smb2_hdr) + 2);
-	rsp_hdr->smb2_buf_length =
-		cpu_to_be32(smb2_hdr_size_no_buflen(conn->vals));
+	*(__be32 *)work->response_buf =
+		cpu_to_be32(conn->vals->header_size);
 	rsp_hdr->ProtocolId = SMB2_PROTO_NUMBER;
 	rsp_hdr->StructureSize = SMB2_HEADER_STRUCTURE_SIZE;
 	rsp_hdr->CreditRequest = cpu_to_le16(0);
@@ -645,7 +645,7 @@ static void __smb2_oplock_break_noti(struct work_struct *wk)
 	rsp_hdr->SessionId = 0;
 	memset(rsp_hdr->Signature, 0, 16);
 
-	rsp = work->response_buf;
+	rsp = smb2_get_msg(work->response_buf);
 
 	rsp->StructureSize = cpu_to_le16(24);
 	if (!br_info->open_trunc &&
@@ -659,7 +659,7 @@ static void __smb2_oplock_break_noti(struct work_struct *wk)
 	rsp->PersistentFid = cpu_to_le64(fp->persistent_id);
 	rsp->VolatileFid = cpu_to_le64(fp->volatile_id);
 
-	inc_rfc1001_len(rsp, 24);
+	inc_rfc1001_len(work->response_buf, 24);
 
 	ksmbd_debug(OPLOCK,
 		    "sending oplock break v_id %llu p_id = %llu lock level = %d\n",
@@ -736,10 +736,10 @@ static void __smb2_lease_break_noti(struct work_struct *wk)
 		return;
 	}
 
-	rsp_hdr = work->response_buf;
+	rsp_hdr = smb2_get_msg(work->response_buf);
 	memset(rsp_hdr, 0, sizeof(struct smb2_hdr) + 2);
-	rsp_hdr->smb2_buf_length =
-		cpu_to_be32(smb2_hdr_size_no_buflen(conn->vals));
+	*(__be32 *)work->response_buf =
+		cpu_to_be32(conn->vals->header_size);
 	rsp_hdr->ProtocolId = SMB2_PROTO_NUMBER;
 	rsp_hdr->StructureSize = SMB2_HEADER_STRUCTURE_SIZE;
 	rsp_hdr->CreditRequest = cpu_to_le16(0);
@@ -752,7 +752,7 @@ static void __smb2_lease_break_noti(struct work_struct *wk)
 	rsp_hdr->SessionId = 0;
 	memset(rsp_hdr->Signature, 0, 16);
 
-	rsp = work->response_buf;
+	rsp = smb2_get_msg(work->response_buf);
 	rsp->StructureSize = cpu_to_le16(44);
 	rsp->Epoch = br_info->epoch;
 	rsp->Flags = 0;
@@ -768,7 +768,7 @@ static void __smb2_lease_break_noti(struct work_struct *wk)
 	rsp->AccessMaskHint = 0;
 	rsp->ShareMaskHint = 0;
 
-	inc_rfc1001_len(rsp, 44);
+	inc_rfc1001_len(work->response_buf, 44);
 
 	ksmbd_conn_write(work);
 	ksmbd_free_work_struct(work);
@@ -1335,19 +1335,16 @@ __u8 smb2_map_lease_to_oplock(__le32 lease_state)
  */
 void create_lease_buf(u8 *rbuf, struct lease *lease)
 {
-	char *LeaseKey = (char *)&lease->lease_key;
-
 	if (lease->version == 2) {
 		struct create_lease_v2 *buf = (struct create_lease_v2 *)rbuf;
-		char *ParentLeaseKey = (char *)&lease->parent_lease_key;
 
 		memset(buf, 0, sizeof(struct create_lease_v2));
-		buf->lcontext.LeaseKeyLow = *((__le64 *)LeaseKey);
-		buf->lcontext.LeaseKeyHigh = *((__le64 *)(LeaseKey + 8));
+		memcpy(buf->lcontext.LeaseKey, lease->lease_key,
+		       SMB2_LEASE_KEY_SIZE);
 		buf->lcontext.LeaseFlags = lease->flags;
 		buf->lcontext.LeaseState = lease->state;
-		buf->lcontext.ParentLeaseKeyLow = *((__le64 *)ParentLeaseKey);
-		buf->lcontext.ParentLeaseKeyHigh = *((__le64 *)(ParentLeaseKey + 8));
+		memcpy(buf->lcontext.ParentLeaseKey, lease->parent_lease_key,
+		       SMB2_LEASE_KEY_SIZE);
 		buf->ccontext.DataOffset = cpu_to_le16(offsetof
 				(struct create_lease_v2, lcontext));
 		buf->ccontext.DataLength = cpu_to_le32(sizeof(struct lease_context_v2));
@@ -1362,8 +1359,7 @@ void create_lease_buf(u8 *rbuf, struct lease *lease)
 		struct create_lease *buf = (struct create_lease *)rbuf;
 
 		memset(buf, 0, sizeof(struct create_lease));
-		buf->lcontext.LeaseKeyLow = *((__le64 *)LeaseKey);
-		buf->lcontext.LeaseKeyHigh = *((__le64 *)(LeaseKey + 8));
+		memcpy(buf->lcontext.LeaseKey, lease->lease_key, SMB2_LEASE_KEY_SIZE);
 		buf->lcontext.LeaseFlags = lease->flags;
 		buf->lcontext.LeaseState = lease->state;
 		buf->ccontext.DataOffset = cpu_to_le16(offsetof
@@ -1398,7 +1394,7 @@ struct lease_ctx_info *parse_lease_state(void *open_req)
 	if (!lreq)
 		return NULL;
 
-	data_offset = (char *)req + 4 + le32_to_cpu(req->CreateContextsOffset);
+	data_offset = (char *)req + le32_to_cpu(req->CreateContextsOffset);
 	cc = (struct create_context *)data_offset;
 	do {
 		cc = (struct create_context *)((char *)cc + next);
@@ -1416,19 +1412,17 @@ struct lease_ctx_info *parse_lease_state(void *open_req)
 		if (sizeof(struct lease_context_v2) == le32_to_cpu(cc->DataLength)) {
 			struct create_lease_v2 *lc = (struct create_lease_v2 *)cc;
 
-			*((__le64 *)lreq->lease_key) = lc->lcontext.LeaseKeyLow;
-			*((__le64 *)(lreq->lease_key + 8)) = lc->lcontext.LeaseKeyHigh;
+			memcpy(lreq->lease_key, lc->lcontext.LeaseKey, SMB2_LEASE_KEY_SIZE);
 			lreq->req_state = lc->lcontext.LeaseState;
 			lreq->flags = lc->lcontext.LeaseFlags;
 			lreq->duration = lc->lcontext.LeaseDuration;
-			*((__le64 *)lreq->parent_lease_key) = lc->lcontext.ParentLeaseKeyLow;
-			*((__le64 *)(lreq->parent_lease_key + 8)) = lc->lcontext.ParentLeaseKeyHigh;
+			memcpy(lreq->parent_lease_key, lc->lcontext.ParentLeaseKey,
+			       SMB2_LEASE_KEY_SIZE);
 			lreq->version = 2;
 		} else {
 			struct create_lease *lc = (struct create_lease *)cc;
 
-			*((__le64 *)lreq->lease_key) = lc->lcontext.LeaseKeyLow;
-			*((__le64 *)(lreq->lease_key + 8)) = lc->lcontext.LeaseKeyHigh;
+			memcpy(lreq->lease_key, lc->lcontext.LeaseKey, SMB2_LEASE_KEY_SIZE);
 			lreq->req_state = lc->lcontext.LeaseState;
 			lreq->flags = lc->lcontext.LeaseFlags;
 			lreq->duration = lc->lcontext.LeaseDuration;
@@ -1462,7 +1456,7 @@ struct create_context *smb2_find_context_vals(void *open_req, const char *tag)
 	 * CreateContextsOffset and CreateContextsLength are guaranteed to
 	 * be valid because of ksmbd_smb2_check_message().
 	 */
-	cc = (struct create_context *)((char *)req + 4 +
+	cc = (struct create_context *)((char *)req +
 				       le32_to_cpu(req->CreateContextsOffset));
 	remain_len = le32_to_cpu(req->CreateContextsLength);
 	do {
diff --git a/fs/ksmbd/oplock.h b/fs/ksmbd/oplock.h
index 119b8047cfbd..0cf7a2b5bbc0 100644
--- a/fs/ksmbd/oplock.h
+++ b/fs/ksmbd/oplock.h
@@ -28,8 +28,6 @@
 #define OPLOCK_WRITE_TO_NONE		0x04
 #define OPLOCK_READ_TO_NONE		0x08
 
-#define SMB2_LEASE_KEY_SIZE		16
-
 struct lease_ctx_info {
 	__u8			lease_key[SMB2_LEASE_KEY_SIZE];
 	__le32			req_state;
diff --git a/fs/ksmbd/server.c b/fs/ksmbd/server.c
index 2a2b2135bfde..2e12f6d8483b 100644
--- a/fs/ksmbd/server.c
+++ b/fs/ksmbd/server.c
@@ -622,7 +622,6 @@ MODULE_DESCRIPTION("Linux kernel CIFS/SMB SERVER");
 MODULE_LICENSE("GPL");
 MODULE_SOFTDEP("pre: ecb");
 MODULE_SOFTDEP("pre: hmac");
-MODULE_SOFTDEP("pre: md4");
 MODULE_SOFTDEP("pre: md5");
 MODULE_SOFTDEP("pre: nls");
 MODULE_SOFTDEP("pre: aes");
@@ -632,5 +631,6 @@ MODULE_SOFTDEP("pre: sha512");
 MODULE_SOFTDEP("pre: aead2");
 MODULE_SOFTDEP("pre: ccm");
 MODULE_SOFTDEP("pre: gcm");
+MODULE_SOFTDEP("pre: crc32");
 module_init(ksmbd_server_init)
 module_exit(ksmbd_server_exit)
diff --git a/fs/ksmbd/smb2misc.c b/fs/ksmbd/smb2misc.c
index 030ca57c3784..50d0b1022289 100644
--- a/fs/ksmbd/smb2misc.c
+++ b/fs/ksmbd/smb2misc.c
@@ -6,7 +6,6 @@
 
 #include "glob.h"
 #include "nterr.h"
-#include "smb2pdu.h"
 #include "smb_common.h"
 #include "smbstatus.h"
 #include "mgmt/user_session.h"
@@ -347,23 +346,16 @@ static int smb2_validate_credit_charge(struct ksmbd_conn *conn,
 
 int ksmbd_smb2_check_message(struct ksmbd_work *work)
 {
-	struct smb2_pdu *pdu = work->request_buf;
+	struct smb2_pdu *pdu = ksmbd_req_buf_next(work);
 	struct smb2_hdr *hdr = &pdu->hdr;
 	int command;
 	__u32 clc_len;  /* calculated length */
-	__u32 len = get_rfc1002_len(pdu);
+	__u32 len = get_rfc1002_len(work->request_buf);
 
-	if (work->next_smb2_rcv_hdr_off) {
-		pdu = ksmbd_req_buf_next(work);
-		hdr = &pdu->hdr;
-	}
-
-	if (le32_to_cpu(hdr->NextCommand) > 0) {
+	if (le32_to_cpu(hdr->NextCommand) > 0)
 		len = le32_to_cpu(hdr->NextCommand);
-	} else if (work->next_smb2_rcv_hdr_off) {
+	else if (work->next_smb2_rcv_hdr_off)
 		len -= work->next_smb2_rcv_hdr_off;
-		len = round_up(len, 8);
-	}
 
 	if (check_smb2_hdr(hdr))
 		return 1;
diff --git a/fs/ksmbd/smb2ops.c b/fs/ksmbd/smb2ops.c
index fb6a65d23139..02a44d28bdaf 100644
--- a/fs/ksmbd/smb2ops.c
+++ b/fs/ksmbd/smb2ops.c
@@ -6,7 +6,6 @@
 
 #include <linux/slab.h>
 #include "glob.h"
-#include "smb2pdu.h"
 
 #include "auth.h"
 #include "connection.h"
@@ -199,7 +198,7 @@ void init_smb2_1_server(struct ksmbd_conn *conn)
 	conn->cmds = smb2_0_server_cmds;
 	conn->max_cmds = ARRAY_SIZE(smb2_0_server_cmds);
 	conn->max_credits = SMB2_MAX_CREDITS;
-	conn->signing_algorithm = SIGNING_ALG_HMAC_SHA256;
+	conn->signing_algorithm = SIGNING_ALG_HMAC_SHA256_LE;
 
 	if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_LEASES)
 		conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING;
@@ -217,7 +216,7 @@ void init_smb3_0_server(struct ksmbd_conn *conn)
 	conn->cmds = smb2_0_server_cmds;
 	conn->max_cmds = ARRAY_SIZE(smb2_0_server_cmds);
 	conn->max_credits = SMB2_MAX_CREDITS;
-	conn->signing_algorithm = SIGNING_ALG_AES_CMAC;
+	conn->signing_algorithm = SIGNING_ALG_AES_CMAC_LE;
 
 	if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_LEASES)
 		conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING;
@@ -242,7 +241,7 @@ void init_smb3_02_server(struct ksmbd_conn *conn)
 	conn->cmds = smb2_0_server_cmds;
 	conn->max_cmds = ARRAY_SIZE(smb2_0_server_cmds);
 	conn->max_credits = SMB2_MAX_CREDITS;
-	conn->signing_algorithm = SIGNING_ALG_AES_CMAC;
+	conn->signing_algorithm = SIGNING_ALG_AES_CMAC_LE;
 
 	if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_LEASES)
 		conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING;
@@ -267,14 +266,11 @@ int init_smb3_11_server(struct ksmbd_conn *conn)
 	conn->cmds = smb2_0_server_cmds;
 	conn->max_cmds = ARRAY_SIZE(smb2_0_server_cmds);
 	conn->max_credits = SMB2_MAX_CREDITS;
-	conn->signing_algorithm = SIGNING_ALG_AES_CMAC;
+	conn->signing_algorithm = SIGNING_ALG_AES_CMAC_LE;
 
 	if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_LEASES)
 		conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING;
 
-	if (conn->cipher_type)
-		conn->vals->capabilities |= SMB2_GLOBAL_CAP_ENCRYPTION;
-
 	if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB3_MULTICHANNEL)
 		conn->vals->capabilities |= SMB2_GLOBAL_CAP_MULTI_CHANNEL;
 
diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c
index 7e448df3f847..b8b3a4c28b74 100644
--- a/fs/ksmbd/smb2pdu.c
+++ b/fs/ksmbd/smb2pdu.c
@@ -13,7 +13,6 @@
 #include <linux/falloc.h>
 
 #include "glob.h"
-#include "smb2pdu.h"
 #include "smbfsctl.h"
 #include "oplock.h"
 #include "smbacl.h"
@@ -44,8 +43,8 @@ static void __wbuf(struct ksmbd_work *work, void **req, void **rsp)
 		*req = ksmbd_req_buf_next(work);
 		*rsp = ksmbd_resp_buf_next(work);
 	} else {
-		*req = work->request_buf;
-		*rsp = work->response_buf;
+		*req = smb2_get_msg(work->request_buf);
+		*rsp = smb2_get_msg(work->response_buf);
 	}
 }
 
@@ -93,13 +92,14 @@ struct channel *lookup_chann_list(struct ksmbd_session *sess, struct ksmbd_conn
  */
 int smb2_get_ksmbd_tcon(struct ksmbd_work *work)
 {
-	struct smb2_hdr *req_hdr = work->request_buf;
+	struct smb2_hdr *req_hdr = smb2_get_msg(work->request_buf);
+	unsigned int cmd = le16_to_cpu(req_hdr->Command);
 	int tree_id;
 
 	work->tcon = NULL;
-	if (work->conn->ops->get_cmd_val(work) == SMB2_TREE_CONNECT_HE ||
-	    work->conn->ops->get_cmd_val(work) ==  SMB2_CANCEL_HE ||
-	    work->conn->ops->get_cmd_val(work) ==  SMB2_LOGOFF_HE) {
+	if (cmd == SMB2_TREE_CONNECT_HE ||
+	    cmd ==  SMB2_CANCEL_HE ||
+	    cmd ==  SMB2_LOGOFF_HE) {
 		ksmbd_debug(SMB, "skip to check tree connect request\n");
 		return 0;
 	}
@@ -130,7 +130,7 @@ void smb2_set_err_rsp(struct ksmbd_work *work)
 	if (work->next_smb2_rcv_hdr_off)
 		err_rsp = ksmbd_resp_buf_next(work);
 	else
-		err_rsp = work->response_buf;
+		err_rsp = smb2_get_msg(work->response_buf);
 
 	if (err_rsp->hdr.Status != STATUS_STOPPED_ON_SYMLINK) {
 		err_rsp->StructureSize = SMB2_ERROR_STRUCTURE_SIZE2_LE;
@@ -150,7 +150,7 @@ void smb2_set_err_rsp(struct ksmbd_work *work)
  */
 bool is_smb2_neg_cmd(struct ksmbd_work *work)
 {
-	struct smb2_hdr *hdr = work->request_buf;
+	struct smb2_hdr *hdr = smb2_get_msg(work->request_buf);
 
 	/* is it SMB2 header ? */
 	if (hdr->ProtocolId != SMB2_PROTO_NUMBER)
@@ -174,7 +174,7 @@ bool is_smb2_neg_cmd(struct ksmbd_work *work)
  */
 bool is_smb2_rsp(struct ksmbd_work *work)
 {
-	struct smb2_hdr *hdr = work->response_buf;
+	struct smb2_hdr *hdr = smb2_get_msg(work->response_buf);
 
 	/* is it SMB2 header ? */
 	if (hdr->ProtocolId != SMB2_PROTO_NUMBER)
@@ -200,7 +200,7 @@ u16 get_smb2_cmd_val(struct ksmbd_work *work)
 	if (work->next_smb2_rcv_hdr_off)
 		rcv_hdr = ksmbd_req_buf_next(work);
 	else
-		rcv_hdr = work->request_buf;
+		rcv_hdr = smb2_get_msg(work->request_buf);
 	return le16_to_cpu(rcv_hdr->Command);
 }
 
@@ -216,7 +216,7 @@ void set_smb2_rsp_status(struct ksmbd_work *work, __le32 err)
 	if (work->next_smb2_rcv_hdr_off)
 		rsp_hdr = ksmbd_resp_buf_next(work);
 	else
-		rsp_hdr = work->response_buf;
+		rsp_hdr = smb2_get_msg(work->response_buf);
 	rsp_hdr->Status = err;
 	smb2_set_err_rsp(work);
 }
@@ -237,13 +237,11 @@ int init_smb2_neg_rsp(struct ksmbd_work *work)
 	if (conn->need_neg == false)
 		return -EINVAL;
 
-	rsp_hdr = work->response_buf;
+	*(__be32 *)work->response_buf =
+		cpu_to_be32(conn->vals->header_size);
 
+	rsp_hdr = smb2_get_msg(work->response_buf);
 	memset(rsp_hdr, 0, sizeof(struct smb2_hdr) + 2);
-
-	rsp_hdr->smb2_buf_length =
-		cpu_to_be32(smb2_hdr_size_no_buflen(conn->vals));
-
 	rsp_hdr->ProtocolId = SMB2_PROTO_NUMBER;
 	rsp_hdr->StructureSize = SMB2_HEADER_STRUCTURE_SIZE;
 	rsp_hdr->CreditRequest = cpu_to_le16(2);
@@ -256,7 +254,7 @@ int init_smb2_neg_rsp(struct ksmbd_work *work)
 	rsp_hdr->SessionId = 0;
 	memset(rsp_hdr->Signature, 0, 16);
 
-	rsp = work->response_buf;
+	rsp = smb2_get_msg(work->response_buf);
 
 	WARN_ON(ksmbd_conn_good(work));
 
@@ -277,12 +275,12 @@ int init_smb2_neg_rsp(struct ksmbd_work *work)
 
 	rsp->SecurityBufferOffset = cpu_to_le16(128);
 	rsp->SecurityBufferLength = cpu_to_le16(AUTH_GSS_LENGTH);
-	ksmbd_copy_gss_neg_header(((char *)(&rsp->hdr) +
-		sizeof(rsp->hdr.smb2_buf_length)) +
+	ksmbd_copy_gss_neg_header((char *)(&rsp->hdr) +
 		le16_to_cpu(rsp->SecurityBufferOffset));
-	inc_rfc1001_len(rsp, sizeof(struct smb2_negotiate_rsp) -
-		sizeof(struct smb2_hdr) - sizeof(rsp->Buffer) +
-		AUTH_GSS_LENGTH);
+	inc_rfc1001_len(work->response_buf,
+			sizeof(struct smb2_negotiate_rsp) -
+			sizeof(struct smb2_hdr) - sizeof(rsp->Buffer) +
+			AUTH_GSS_LENGTH);
 	rsp->SecurityMode = SMB2_NEGOTIATE_SIGNING_ENABLED_LE;
 	if (server_conf.signing == KSMBD_CONFIG_OPT_MANDATORY)
 		rsp->SecurityMode |= SMB2_NEGOTIATE_SIGNING_REQUIRED_LE;
@@ -387,8 +385,8 @@ static void init_chained_smb2_rsp(struct ksmbd_work *work)
 	next_hdr_offset = le32_to_cpu(req->NextCommand);
 
 	new_len = ALIGN(len, 8);
-	inc_rfc1001_len(work->response_buf, ((sizeof(struct smb2_hdr) - 4)
-			+ new_len - len));
+	inc_rfc1001_len(work->response_buf,
+			sizeof(struct smb2_hdr) + new_len - len);
 	rsp->NextCommand = cpu_to_le32(new_len);
 
 	work->next_smb2_rcv_hdr_off += next_hdr_offset;
@@ -406,7 +404,7 @@ static void init_chained_smb2_rsp(struct ksmbd_work *work)
 		work->compound_fid = KSMBD_NO_FID;
 		work->compound_pfid = KSMBD_NO_FID;
 	}
-	memset((char *)rsp_hdr + 4, 0, sizeof(struct smb2_hdr) + 2);
+	memset((char *)rsp_hdr, 0, sizeof(struct smb2_hdr) + 2);
 	rsp_hdr->ProtocolId = SMB2_PROTO_NUMBER;
 	rsp_hdr->StructureSize = SMB2_HEADER_STRUCTURE_SIZE;
 	rsp_hdr->Command = rcv_hdr->Command;
@@ -432,7 +430,7 @@ static void init_chained_smb2_rsp(struct ksmbd_work *work)
  */
 bool is_chained_smb2_message(struct ksmbd_work *work)
 {
-	struct smb2_hdr *hdr = work->request_buf;
+	struct smb2_hdr *hdr = smb2_get_msg(work->request_buf);
 	unsigned int len, next_cmd;
 
 	if (hdr->ProtocolId != SMB2_PROTO_NUMBER)
@@ -483,13 +481,13 @@ bool is_chained_smb2_message(struct ksmbd_work *work)
  */
 int init_smb2_rsp_hdr(struct ksmbd_work *work)
 {
-	struct smb2_hdr *rsp_hdr = work->response_buf;
-	struct smb2_hdr *rcv_hdr = work->request_buf;
+	struct smb2_hdr *rsp_hdr = smb2_get_msg(work->response_buf);
+	struct smb2_hdr *rcv_hdr = smb2_get_msg(work->request_buf);
 	struct ksmbd_conn *conn = work->conn;
 
 	memset(rsp_hdr, 0, sizeof(struct smb2_hdr) + 2);
-	rsp_hdr->smb2_buf_length =
-		cpu_to_be32(smb2_hdr_size_no_buflen(conn->vals));
+	*(__be32 *)work->response_buf =
+		cpu_to_be32(conn->vals->header_size);
 	rsp_hdr->ProtocolId = rcv_hdr->ProtocolId;
 	rsp_hdr->StructureSize = SMB2_HEADER_STRUCTURE_SIZE;
 	rsp_hdr->Command = rcv_hdr->Command;
@@ -522,7 +520,7 @@ int init_smb2_rsp_hdr(struct ksmbd_work *work)
  */
 int smb2_allocate_rsp_buf(struct ksmbd_work *work)
 {
-	struct smb2_hdr *hdr = work->request_buf;
+	struct smb2_hdr *hdr = smb2_get_msg(work->request_buf);
 	size_t small_sz = MAX_CIFS_SMALL_BUFFER_SIZE;
 	size_t large_sz = small_sz + work->conn->vals->max_trans_size;
 	size_t sz = small_sz;
@@ -534,7 +532,7 @@ int smb2_allocate_rsp_buf(struct ksmbd_work *work)
 	if (cmd == SMB2_QUERY_INFO_HE) {
 		struct smb2_query_info_req *req;
 
-		req = work->request_buf;
+		req = smb2_get_msg(work->request_buf);
 		if (req->InfoType == SMB2_O_INFO_FILE &&
 		    (req->FileInfoClass == FILE_FULL_EA_INFORMATION ||
 		     req->FileInfoClass == FILE_ALL_INFORMATION))
@@ -561,7 +559,7 @@ int smb2_allocate_rsp_buf(struct ksmbd_work *work)
  */
 int smb2_check_user_session(struct ksmbd_work *work)
 {
-	struct smb2_hdr *req_hdr = work->request_buf;
+	struct smb2_hdr *req_hdr = smb2_get_msg(work->request_buf);
 	struct ksmbd_conn *conn = work->conn;
 	unsigned int cmd = conn->ops->get_cmd_val(work);
 	unsigned long long sess_id;
@@ -642,7 +640,7 @@ int setup_async_work(struct ksmbd_work *work, void (*fn)(void **), void **arg)
 	struct ksmbd_conn *conn = work->conn;
 	int id;
 
-	rsp_hdr = work->response_buf;
+	rsp_hdr = smb2_get_msg(work->response_buf);
 	rsp_hdr->Flags |= SMB2_FLAGS_ASYNC_COMMAND;
 
 	id = ksmbd_acquire_async_msg_id(&conn->async_ida);
@@ -674,7 +672,7 @@ void smb2_send_interim_resp(struct ksmbd_work *work, __le32 status)
 {
 	struct smb2_hdr *rsp_hdr;
 
-	rsp_hdr = work->response_buf;
+	rsp_hdr = smb2_get_msg(work->response_buf);
 	smb2_set_err_rsp(work);
 	rsp_hdr->Status = status;
 
@@ -715,17 +713,17 @@ static int smb2_get_dos_mode(struct kstat *stat, int attribute)
 	int attr = 0;
 
 	if (S_ISDIR(stat->mode)) {
-		attr = ATTR_DIRECTORY |
-			(attribute & (ATTR_HIDDEN | ATTR_SYSTEM));
+		attr = FILE_ATTRIBUTE_DIRECTORY |
+			(attribute & (FILE_ATTRIBUTE_HIDDEN | FILE_ATTRIBUTE_SYSTEM));
 	} else {
-		attr = (attribute & 0x00005137) | ATTR_ARCHIVE;
-		attr &= ~(ATTR_DIRECTORY);
+		attr = (attribute & 0x00005137) | FILE_ATTRIBUTE_ARCHIVE;
+		attr &= ~(FILE_ATTRIBUTE_DIRECTORY);
 		if (S_ISREG(stat->mode) && (server_conf.share_fake_fscaps &
 				FILE_SUPPORTS_SPARSE_FILES))
-			attr |= ATTR_SPARSE;
+			attr |= FILE_ATTRIBUTE_SPARSE_FILE;
 
 		if (smb2_get_reparse_tag_special_file(stat->mode))
-			attr |= ATTR_REPARSE;
+			attr |= FILE_ATTRIBUTE_REPARSE_POINT;
 	}
 
 	return attr;
@@ -753,16 +751,16 @@ static void build_encrypt_ctxt(struct smb2_encryption_neg_context *pneg_ctxt,
 	pneg_ctxt->Ciphers[0] = cipher_type;
 }
 
-static void build_compression_ctxt(struct smb2_compression_ctx *pneg_ctxt,
+static void build_compression_ctxt(struct smb2_compression_capabilities_context *pneg_ctxt,
 				   __le16 comp_algo)
 {
 	pneg_ctxt->ContextType = SMB2_COMPRESSION_CAPABILITIES;
 	pneg_ctxt->DataLength =
-		cpu_to_le16(sizeof(struct smb2_compression_ctx)
+		cpu_to_le16(sizeof(struct smb2_compression_capabilities_context)
 			- sizeof(struct smb2_neg_context));
 	pneg_ctxt->Reserved = cpu_to_le32(0);
 	pneg_ctxt->CompressionAlgorithmCount = cpu_to_le16(1);
-	pneg_ctxt->Reserved1 = cpu_to_le32(0);
+	pneg_ctxt->Flags = cpu_to_le32(0);
 	pneg_ctxt->CompressionAlgorithms[0] = comp_algo;
 }
 
@@ -802,11 +800,11 @@ static void build_posix_ctxt(struct smb2_posix_neg_context *pneg_ctxt)
 }
 
 static void assemble_neg_contexts(struct ksmbd_conn *conn,
-				  struct smb2_negotiate_rsp *rsp)
+				  struct smb2_negotiate_rsp *rsp,
+				  void *smb2_buf_len)
 {
-	/* +4 is to account for the RFC1001 len field */
 	char *pneg_ctxt = (char *)rsp +
-			le32_to_cpu(rsp->NegotiateContextOffset) + 4;
+			le32_to_cpu(rsp->NegotiateContextOffset);
 	int neg_ctxt_cnt = 1;
 	int ctxt_size;
 
@@ -815,7 +813,7 @@ static void assemble_neg_contexts(struct ksmbd_conn *conn,
 	build_preauth_ctxt((struct smb2_preauth_neg_context *)pneg_ctxt,
 			   conn->preauth_info->Preauth_HashId);
 	rsp->NegotiateContextCount = cpu_to_le16(neg_ctxt_cnt);
-	inc_rfc1001_len(rsp, AUTH_GSS_PADDING);
+	inc_rfc1001_len(smb2_buf_len, AUTH_GSS_PADDING);
 	ctxt_size = sizeof(struct smb2_preauth_neg_context);
 	/* Round to 8 byte boundary */
 	pneg_ctxt += round_up(sizeof(struct smb2_preauth_neg_context), 8);
@@ -839,12 +837,12 @@ static void assemble_neg_contexts(struct ksmbd_conn *conn,
 		ksmbd_debug(SMB,
 			    "assemble SMB2_COMPRESSION_CAPABILITIES context\n");
 		/* Temporarily set to SMB3_COMPRESS_NONE */
-		build_compression_ctxt((struct smb2_compression_ctx *)pneg_ctxt,
+		build_compression_ctxt((struct smb2_compression_capabilities_context *)pneg_ctxt,
 				       conn->compress_algorithm);
 		rsp->NegotiateContextCount = cpu_to_le16(++neg_ctxt_cnt);
-		ctxt_size += sizeof(struct smb2_compression_ctx) + 2;
+		ctxt_size += sizeof(struct smb2_compression_capabilities_context) + 2;
 		/* Round to 8 byte boundary */
-		pneg_ctxt += round_up(sizeof(struct smb2_compression_ctx) + 2,
+		pneg_ctxt += round_up(sizeof(struct smb2_compression_capabilities_context) + 2,
 				      8);
 	}
 
@@ -869,7 +867,7 @@ static void assemble_neg_contexts(struct ksmbd_conn *conn,
 		ctxt_size += sizeof(struct smb2_signing_capabilities) + 2;
 	}
 
-	inc_rfc1001_len(rsp, ctxt_size);
+	inc_rfc1001_len(smb2_buf_len, ctxt_size);
 }
 
 static __le32 decode_preauth_ctxt(struct ksmbd_conn *conn,
@@ -917,8 +915,27 @@ static void decode_encrypt_ctxt(struct ksmbd_conn *conn,
 	}
 }
 
+/**
+ * smb3_encryption_negotiated() - checks if server and client agreed on enabling encryption
+ * @conn:	smb connection
+ *
+ * Return:	true if connection should be encrypted, else false
+ */
+static bool smb3_encryption_negotiated(struct ksmbd_conn *conn)
+{
+	if (!conn->ops->generate_encryptionkey)
+		return false;
+
+	/*
+	 * SMB 3.0 and 3.0.2 dialects use the SMB2_GLOBAL_CAP_ENCRYPTION flag.
+	 * SMB 3.1.1 uses the cipher_type field.
+	 */
+	return (conn->vals->capabilities & SMB2_GLOBAL_CAP_ENCRYPTION) ||
+	    conn->cipher_type;
+}
+
 static void decode_compress_ctxt(struct ksmbd_conn *conn,
-				 struct smb2_compression_ctx *pneg_ctxt)
+				 struct smb2_compression_capabilities_context *pneg_ctxt)
 {
 	conn->compress_algorithm = SMB3_COMPRESS_NONE;
 }
@@ -939,8 +956,8 @@ static void decode_sign_cap_ctxt(struct ksmbd_conn *conn,
 	}
 
 	for (i = 0; i < sign_algo_cnt; i++) {
-		if (pneg_ctxt->SigningAlgorithms[i] == SIGNING_ALG_HMAC_SHA256 ||
-		    pneg_ctxt->SigningAlgorithms[i] == SIGNING_ALG_AES_CMAC) {
+		if (pneg_ctxt->SigningAlgorithms[i] == SIGNING_ALG_HMAC_SHA256_LE ||
+		    pneg_ctxt->SigningAlgorithms[i] == SIGNING_ALG_AES_CMAC_LE) {
 			ksmbd_debug(SMB, "Signing Algorithm ID = 0x%x\n",
 				    pneg_ctxt->SigningAlgorithms[i]);
 			conn->signing_negotiated = true;
@@ -952,14 +969,14 @@ static void decode_sign_cap_ctxt(struct ksmbd_conn *conn,
 }
 
 static __le32 deassemble_neg_contexts(struct ksmbd_conn *conn,
-				      struct smb2_negotiate_req *req)
+				      struct smb2_negotiate_req *req,
+				      int len_of_smb)
 {
 	/* +4 is to account for the RFC1001 len field */
-	struct smb2_neg_context *pctx = (struct smb2_neg_context *)((char *)req + 4);
+	struct smb2_neg_context *pctx = (struct smb2_neg_context *)req;
 	int i = 0, len_of_ctxts;
 	int offset = le32_to_cpu(req->NegotiateContextOffset);
 	int neg_ctxt_cnt = le16_to_cpu(req->NegotiateContextCount);
-	int len_of_smb = be32_to_cpu(req->hdr.smb2_buf_length);
 	__le32 status = STATUS_INVALID_PARAMETER;
 
 	ksmbd_debug(SMB, "decoding %d negotiate contexts\n", neg_ctxt_cnt);
@@ -1011,7 +1028,7 @@ static __le32 deassemble_neg_contexts(struct ksmbd_conn *conn,
 				break;
 
 			decode_compress_ctxt(conn,
-					     (struct smb2_compression_ctx *)pctx);
+					     (struct smb2_compression_capabilities_context *)pctx);
 		} else if (pctx->ContextType == SMB2_NETNAME_NEGOTIATE_CONTEXT_ID) {
 			ksmbd_debug(SMB,
 				    "deassemble SMB2_NETNAME_NEGOTIATE_CONTEXT_ID context\n");
@@ -1044,8 +1061,8 @@ static __le32 deassemble_neg_contexts(struct ksmbd_conn *conn,
 int smb2_handle_negotiate(struct ksmbd_work *work)
 {
 	struct ksmbd_conn *conn = work->conn;
-	struct smb2_negotiate_req *req = work->request_buf;
-	struct smb2_negotiate_rsp *rsp = work->response_buf;
+	struct smb2_negotiate_req *req = smb2_get_msg(work->request_buf);
+	struct smb2_negotiate_rsp *rsp = smb2_get_msg(work->response_buf);
 	int rc = 0;
 	unsigned int smb2_buf_len, smb2_neg_size;
 	__le32 status;
@@ -1066,7 +1083,7 @@ int smb2_handle_negotiate(struct ksmbd_work *work)
 	}
 
 	smb2_buf_len = get_rfc1002_len(work->request_buf);
-	smb2_neg_size = offsetof(struct smb2_negotiate_req, Dialects) - 4;
+	smb2_neg_size = offsetof(struct smb2_negotiate_req, Dialects);
 	if (smb2_neg_size > smb2_buf_len) {
 		rsp->hdr.Status = STATUS_INVALID_PARAMETER;
 		rc = -EINVAL;
@@ -1115,7 +1132,8 @@ int smb2_handle_negotiate(struct ksmbd_work *work)
 			goto err_out;
 		}
 
-		status = deassemble_neg_contexts(conn, req);
+		status = deassemble_neg_contexts(conn, req,
+						 get_rfc1002_len(work->request_buf));
 		if (status != STATUS_SUCCESS) {
 			pr_err("deassemble_neg_contexts error(0x%x)\n",
 			       status);
@@ -1135,7 +1153,7 @@ int smb2_handle_negotiate(struct ksmbd_work *work)
 						 conn->preauth_info->Preauth_HashValue);
 		rsp->NegotiateContextOffset =
 				cpu_to_le32(OFFSET_OF_NEG_CONTEXT);
-		assemble_neg_contexts(conn, rsp);
+		assemble_neg_contexts(conn, rsp, work->response_buf);
 		break;
 	case SMB302_PROT_ID:
 		init_smb3_02_server(conn);
@@ -1183,10 +1201,9 @@ int smb2_handle_negotiate(struct ksmbd_work *work)
 
 	rsp->SecurityBufferOffset = cpu_to_le16(128);
 	rsp->SecurityBufferLength = cpu_to_le16(AUTH_GSS_LENGTH);
-	ksmbd_copy_gss_neg_header(((char *)(&rsp->hdr) +
-				  sizeof(rsp->hdr.smb2_buf_length)) +
-				   le16_to_cpu(rsp->SecurityBufferOffset));
-	inc_rfc1001_len(rsp, sizeof(struct smb2_negotiate_rsp) -
+	ksmbd_copy_gss_neg_header((char *)(&rsp->hdr) +
+				  le16_to_cpu(rsp->SecurityBufferOffset));
+	inc_rfc1001_len(work->response_buf, sizeof(struct smb2_negotiate_rsp) -
 			sizeof(struct smb2_hdr) - sizeof(rsp->Buffer) +
 			 AUTH_GSS_LENGTH);
 	rsp->SecurityMode = SMB2_NEGOTIATE_SIGNING_ENABLED_LE;
@@ -1278,7 +1295,7 @@ static int ntlm_negotiate(struct ksmbd_work *work,
 			  struct negotiate_message *negblob,
 			  size_t negblob_len)
 {
-	struct smb2_sess_setup_rsp *rsp = work->response_buf;
+	struct smb2_sess_setup_rsp *rsp = smb2_get_msg(work->response_buf);
 	struct challenge_message *chgblob;
 	unsigned char *spnego_blob = NULL;
 	u16 spnego_blob_len;
@@ -1386,8 +1403,8 @@ static struct ksmbd_user *session_user(struct ksmbd_conn *conn,
 
 static int ntlm_authenticate(struct ksmbd_work *work)
 {
-	struct smb2_sess_setup_req *req = work->request_buf;
-	struct smb2_sess_setup_rsp *rsp = work->response_buf;
+	struct smb2_sess_setup_req *req = smb2_get_msg(work->request_buf);
+	struct smb2_sess_setup_rsp *rsp = smb2_get_msg(work->response_buf);
 	struct ksmbd_conn *conn = work->conn;
 	struct ksmbd_session *sess = work->sess;
 	struct channel *chann = NULL;
@@ -1410,7 +1427,7 @@ static int ntlm_authenticate(struct ksmbd_work *work)
 		memcpy((char *)&rsp->hdr.ProtocolId + sz, spnego_blob, spnego_blob_len);
 		rsp->SecurityBufferLength = cpu_to_le16(spnego_blob_len);
 		kfree(spnego_blob);
-		inc_rfc1001_len(rsp, spnego_blob_len - 1);
+		inc_rfc1001_len(work->response_buf, spnego_blob_len - 1);
 	}
 
 	user = session_user(conn, req);
@@ -1471,8 +1488,7 @@ static int ntlm_authenticate(struct ksmbd_work *work)
 		    (req->SecurityMode & SMB2_NEGOTIATE_SIGNING_REQUIRED))
 			sess->sign = true;
 
-		if (conn->vals->capabilities & SMB2_GLOBAL_CAP_ENCRYPTION &&
-		    conn->ops->generate_encryptionkey &&
+		if (smb3_encryption_negotiated(conn) &&
 		    !(req->Flags & SMB2_SESSION_REQ_FLAG_BINDING)) {
 			rc = conn->ops->generate_encryptionkey(sess);
 			if (rc) {
@@ -1522,8 +1538,8 @@ binding_session:
 #ifdef CONFIG_SMB_SERVER_KERBEROS5
 static int krb5_authenticate(struct ksmbd_work *work)
 {
-	struct smb2_sess_setup_req *req = work->request_buf;
-	struct smb2_sess_setup_rsp *rsp = work->response_buf;
+	struct smb2_sess_setup_req *req = smb2_get_msg(work->request_buf);
+	struct smb2_sess_setup_rsp *rsp = smb2_get_msg(work->response_buf);
 	struct ksmbd_conn *conn = work->conn;
 	struct ksmbd_session *sess = work->sess;
 	char *in_blob, *out_blob;
@@ -1538,8 +1554,7 @@ static int krb5_authenticate(struct ksmbd_work *work)
 	out_blob = (char *)&rsp->hdr.ProtocolId +
 		le16_to_cpu(rsp->SecurityBufferOffset);
 	out_len = work->response_sz -
-		offsetof(struct smb2_hdr, smb2_buf_length) -
-		le16_to_cpu(rsp->SecurityBufferOffset);
+		(le16_to_cpu(rsp->SecurityBufferOffset) + 4);
 
 	/* Check previous session */
 	prev_sess_id = le64_to_cpu(req->PreviousSessionId);
@@ -1556,14 +1571,13 @@ static int krb5_authenticate(struct ksmbd_work *work)
 		return -EINVAL;
 	}
 	rsp->SecurityBufferLength = cpu_to_le16(out_len);
-	inc_rfc1001_len(rsp, out_len - 1);
+	inc_rfc1001_len(work->response_buf, out_len - 1);
 
 	if ((conn->sign || server_conf.enforced_signing) ||
 	    (req->SecurityMode & SMB2_NEGOTIATE_SIGNING_REQUIRED))
 		sess->sign = true;
 
-	if ((conn->vals->capabilities & SMB2_GLOBAL_CAP_ENCRYPTION) &&
-	    conn->ops->generate_encryptionkey) {
+	if (smb3_encryption_negotiated(conn)) {
 		retval = conn->ops->generate_encryptionkey(sess);
 		if (retval) {
 			ksmbd_debug(SMB,
@@ -1612,8 +1626,8 @@ static int krb5_authenticate(struct ksmbd_work *work)
 int smb2_sess_setup(struct ksmbd_work *work)
 {
 	struct ksmbd_conn *conn = work->conn;
-	struct smb2_sess_setup_req *req = work->request_buf;
-	struct smb2_sess_setup_rsp *rsp = work->response_buf;
+	struct smb2_sess_setup_req *req = smb2_get_msg(work->request_buf);
+	struct smb2_sess_setup_rsp *rsp = smb2_get_msg(work->response_buf);
 	struct ksmbd_session *sess;
 	struct negotiate_message *negblob;
 	unsigned int negblob_len, negblob_off;
@@ -1625,7 +1639,7 @@ int smb2_sess_setup(struct ksmbd_work *work)
 	rsp->SessionFlags = 0;
 	rsp->SecurityBufferOffset = cpu_to_le16(72);
 	rsp->SecurityBufferLength = 0;
-	inc_rfc1001_len(rsp, 9);
+	inc_rfc1001_len(work->response_buf, 9);
 
 	if (!req->hdr.SessionId) {
 		sess = ksmbd_smb2_session_create();
@@ -1699,9 +1713,11 @@ int smb2_sess_setup(struct ksmbd_work *work)
 
 	negblob_off = le16_to_cpu(req->SecurityBufferOffset);
 	negblob_len = le16_to_cpu(req->SecurityBufferLength);
-	if (negblob_off < (offsetof(struct smb2_sess_setup_req, Buffer) - 4) ||
-	    negblob_len < offsetof(struct negotiate_message, NegotiateFlags))
-		return -EINVAL;
+	if (negblob_off < offsetof(struct smb2_sess_setup_req, Buffer) ||
+	    negblob_len < offsetof(struct negotiate_message, NegotiateFlags)) {
+		rc = -EINVAL;
+		goto out_err;
+	}
 
 	negblob = (struct negotiate_message *)((char *)&req->hdr.ProtocolId +
 			negblob_off);
@@ -1739,7 +1755,8 @@ int smb2_sess_setup(struct ksmbd_work *work)
 				 * Note: here total size -1 is done as an
 				 * adjustment for 0 size blob
 				 */
-				inc_rfc1001_len(rsp, le16_to_cpu(rsp->SecurityBufferLength) - 1);
+				inc_rfc1001_len(work->response_buf,
+						le16_to_cpu(rsp->SecurityBufferLength) - 1);
 
 			} else if (negblob->MessageType == NtLmAuthenticate) {
 				rc = ntlm_authenticate(work);
@@ -1828,8 +1845,8 @@ out_err:
 int smb2_tree_connect(struct ksmbd_work *work)
 {
 	struct ksmbd_conn *conn = work->conn;
-	struct smb2_tree_connect_req *req = work->request_buf;
-	struct smb2_tree_connect_rsp *rsp = work->response_buf;
+	struct smb2_tree_connect_req *req = smb2_get_msg(work->request_buf);
+	struct smb2_tree_connect_rsp *rsp = smb2_get_msg(work->response_buf);
 	struct ksmbd_session *sess = work->sess;
 	char *treename = NULL, *name = NULL;
 	struct ksmbd_tree_conn_status status;
@@ -1894,7 +1911,7 @@ out_err1:
 	rsp->Reserved = 0;
 	/* default manual caching */
 	rsp->ShareFlags = SMB2_SHAREFLAG_MANUAL_CACHING;
-	inc_rfc1001_len(rsp, 16);
+	inc_rfc1001_len(work->response_buf, 16);
 
 	if (!IS_ERR(treename))
 		kfree(treename);
@@ -1999,17 +2016,18 @@ static int smb2_create_open_flags(bool file_present, __le32 access,
  */
 int smb2_tree_disconnect(struct ksmbd_work *work)
 {
-	struct smb2_tree_disconnect_rsp *rsp = work->response_buf;
+	struct smb2_tree_disconnect_rsp *rsp = smb2_get_msg(work->response_buf);
 	struct ksmbd_session *sess = work->sess;
 	struct ksmbd_tree_connect *tcon = work->tcon;
 
 	rsp->StructureSize = cpu_to_le16(4);
-	inc_rfc1001_len(rsp, 4);
+	inc_rfc1001_len(work->response_buf, 4);
 
 	ksmbd_debug(SMB, "request\n");
 
 	if (!tcon) {
-		struct smb2_tree_disconnect_req *req = work->request_buf;
+		struct smb2_tree_disconnect_req *req =
+			smb2_get_msg(work->request_buf);
 
 		ksmbd_debug(SMB, "Invalid tid %d\n", req->hdr.Id.SyncId.TreeId);
 		rsp->hdr.Status = STATUS_NETWORK_NAME_DELETED;
@@ -2031,11 +2049,11 @@ int smb2_tree_disconnect(struct ksmbd_work *work)
 int smb2_session_logoff(struct ksmbd_work *work)
 {
 	struct ksmbd_conn *conn = work->conn;
-	struct smb2_logoff_rsp *rsp = work->response_buf;
+	struct smb2_logoff_rsp *rsp = smb2_get_msg(work->response_buf);
 	struct ksmbd_session *sess = work->sess;
 
 	rsp->StructureSize = cpu_to_le16(4);
-	inc_rfc1001_len(rsp, 4);
+	inc_rfc1001_len(work->response_buf, 4);
 
 	ksmbd_debug(SMB, "request\n");
 
@@ -2048,7 +2066,7 @@ int smb2_session_logoff(struct ksmbd_work *work)
 	ksmbd_conn_wait_idle(conn);
 
 	if (ksmbd_tree_conn_session_logoff(sess)) {
-		struct smb2_logoff_req *req = work->request_buf;
+		struct smb2_logoff_req *req = smb2_get_msg(work->request_buf);
 
 		ksmbd_debug(SMB, "Invalid tid %d\n", req->hdr.Id.SyncId.TreeId);
 		rsp->hdr.Status = STATUS_NETWORK_NAME_DELETED;
@@ -2075,8 +2093,8 @@ int smb2_session_logoff(struct ksmbd_work *work)
  */
 static noinline int create_smb2_pipe(struct ksmbd_work *work)
 {
-	struct smb2_create_rsp *rsp = work->response_buf;
-	struct smb2_create_req *req = work->request_buf;
+	struct smb2_create_rsp *rsp = smb2_get_msg(work->response_buf);
+	struct smb2_create_req *req = smb2_get_msg(work->request_buf);
 	int id;
 	int err;
 	char *name;
@@ -2099,7 +2117,7 @@ static noinline int create_smb2_pipe(struct ksmbd_work *work)
 	rsp->hdr.Status = STATUS_SUCCESS;
 	rsp->StructureSize = cpu_to_le16(89);
 	rsp->OplockLevel = SMB2_OPLOCK_LEVEL_NONE;
-	rsp->Reserved = 0;
+	rsp->Flags = 0;
 	rsp->CreateAction = cpu_to_le32(FILE_OPENED);
 
 	rsp->CreationTime = cpu_to_le64(0);
@@ -2107,14 +2125,14 @@ static noinline int create_smb2_pipe(struct ksmbd_work *work)
 	rsp->ChangeTime = cpu_to_le64(0);
 	rsp->AllocationSize = cpu_to_le64(0);
 	rsp->EndofFile = cpu_to_le64(0);
-	rsp->FileAttributes = ATTR_NORMAL_LE;
+	rsp->FileAttributes = FILE_ATTRIBUTE_NORMAL_LE;
 	rsp->Reserved2 = 0;
 	rsp->VolatileFileId = cpu_to_le64(id);
 	rsp->PersistentFileId = 0;
 	rsp->CreateContextsOffset = 0;
 	rsp->CreateContextsLength = 0;
 
-	inc_rfc1001_len(rsp, 88); /* StructureSize - 1*/
+	inc_rfc1001_len(work->response_buf, 88); /* StructureSize - 1*/
 	kfree(name);
 	return 0;
 
@@ -2353,7 +2371,7 @@ static void smb2_update_xattrs(struct ksmbd_tree_connect *tcon,
 	struct xattr_dos_attrib da;
 	int rc;
 
-	fp->f_ci->m_fattr &= ~(ATTR_HIDDEN_LE | ATTR_SYSTEM_LE);
+	fp->f_ci->m_fattr &= ~(FILE_ATTRIBUTE_HIDDEN_LE | FILE_ATTRIBUTE_SYSTEM_LE);
 
 	/* get FileAttributes from XATTR_NAME_DOS_ATTRIBUTE */
 	if (!test_share_config_flag(tcon->share_conf,
@@ -2463,7 +2481,7 @@ int smb2_open(struct ksmbd_work *work)
 	struct ksmbd_session *sess = work->sess;
 	struct ksmbd_tree_connect *tcon = work->tcon;
 	struct smb2_create_req *req;
-	struct smb2_create_rsp *rsp, *rsp_org;
+	struct smb2_create_rsp *rsp;
 	struct path path;
 	struct ksmbd_share_config *share = tcon->share_conf;
 	struct ksmbd_file *fp = NULL;
@@ -2489,7 +2507,6 @@ int smb2_open(struct ksmbd_work *work)
 	umode_t posix_mode = 0;
 	__le32 daccess, maximal_access = 0;
 
-	rsp_org = work->response_buf;
 	WORK_BUFFERS(work, req, rsp);
 
 	if (req->hdr.NextCommand && !work->next_smb2_rcv_hdr_off &&
@@ -2559,7 +2576,7 @@ int smb2_open(struct ksmbd_work *work)
 	if (req_op_level == SMB2_OPLOCK_LEVEL_LEASE)
 		lc = parse_lease_state(req);
 
-	if (le32_to_cpu(req->ImpersonationLevel) > le32_to_cpu(IL_DELEGATE_LE)) {
+	if (le32_to_cpu(req->ImpersonationLevel) > le32_to_cpu(IL_DELEGATE)) {
 		pr_err("Invalid impersonationlevel : 0x%x\n",
 		       le32_to_cpu(req->ImpersonationLevel));
 		rc = -EIO;
@@ -2567,7 +2584,7 @@ int smb2_open(struct ksmbd_work *work)
 		goto err_out1;
 	}
 
-	if (req->CreateOptions && !(req->CreateOptions & CREATE_OPTIONS_MASK)) {
+	if (req->CreateOptions && !(req->CreateOptions & CREATE_OPTIONS_MASK_LE)) {
 		pr_err("Invalid create options : 0x%x\n",
 		       le32_to_cpu(req->CreateOptions));
 		rc = -EINVAL;
@@ -2609,7 +2626,7 @@ int smb2_open(struct ksmbd_work *work)
 		goto err_out1;
 	}
 
-	if (req->FileAttributes && !(req->FileAttributes & ATTR_MASK_LE)) {
+	if (req->FileAttributes && !(req->FileAttributes & FILE_ATTRIBUTE_MASK_LE)) {
 		pr_err("Invalid file attribute : 0x%x\n",
 		       le32_to_cpu(req->FileAttributes));
 		rc = -EINVAL;
@@ -2740,7 +2757,7 @@ int smb2_open(struct ksmbd_work *work)
 		}
 
 		if (req->CreateOptions & FILE_DIRECTORY_FILE_LE &&
-		    req->FileAttributes & ATTR_NORMAL_LE) {
+		    req->FileAttributes & FILE_ATTRIBUTE_NORMAL_LE) {
 			rsp->hdr.Status = STATUS_NOT_A_DIRECTORY;
 			rc = -EIO;
 		}
@@ -2962,6 +2979,10 @@ int smb2_open(struct ksmbd_work *work)
 							    &pntsd_size, &fattr);
 					posix_acl_release(fattr.cf_acls);
 					posix_acl_release(fattr.cf_dacls);
+					if (rc) {
+						kfree(pntsd);
+						goto err_out;
+					}
 
 					rc = ksmbd_vfs_set_sd_xattr(conn,
 								    user_ns,
@@ -3119,7 +3140,7 @@ int smb2_open(struct ksmbd_work *work)
 	opinfo = rcu_dereference(fp->f_opinfo);
 	rsp->OplockLevel = opinfo != NULL ? opinfo->level : 0;
 	rcu_read_unlock();
-	rsp->Reserved = 0;
+	rsp->Flags = 0;
 	rsp->CreateAction = cpu_to_le32(file_info);
 	rsp->CreationTime = cpu_to_le64(fp->create_time);
 	time = ksmbd_UnixTimeToNT(stat.atime);
@@ -3140,7 +3161,7 @@ int smb2_open(struct ksmbd_work *work)
 
 	rsp->CreateContextsOffset = 0;
 	rsp->CreateContextsLength = 0;
-	inc_rfc1001_len(rsp_org, 88); /* StructureSize - 1*/
+	inc_rfc1001_len(work->response_buf, 88); /* StructureSize - 1*/
 
 	/* If lease is request send lease context response */
 	if (opinfo && opinfo->is_lease) {
@@ -3155,7 +3176,8 @@ int smb2_open(struct ksmbd_work *work)
 		create_lease_buf(rsp->Buffer, opinfo->o_lease);
 		le32_add_cpu(&rsp->CreateContextsLength,
 			     conn->vals->create_lease_size);
-		inc_rfc1001_len(rsp_org, conn->vals->create_lease_size);
+		inc_rfc1001_len(work->response_buf,
+				conn->vals->create_lease_size);
 		next_ptr = &lease_ccontext->Next;
 		next_off = conn->vals->create_lease_size;
 	}
@@ -3175,7 +3197,8 @@ int smb2_open(struct ksmbd_work *work)
 				le32_to_cpu(maximal_access));
 		le32_add_cpu(&rsp->CreateContextsLength,
 			     conn->vals->create_mxac_size);
-		inc_rfc1001_len(rsp_org, conn->vals->create_mxac_size);
+		inc_rfc1001_len(work->response_buf,
+				conn->vals->create_mxac_size);
 		if (next_ptr)
 			*next_ptr = cpu_to_le32(next_off);
 		next_ptr = &mxac_ccontext->Next;
@@ -3193,7 +3216,8 @@ int smb2_open(struct ksmbd_work *work)
 				stat.ino, tcon->id);
 		le32_add_cpu(&rsp->CreateContextsLength,
 			     conn->vals->create_disk_id_size);
-		inc_rfc1001_len(rsp_org, conn->vals->create_disk_id_size);
+		inc_rfc1001_len(work->response_buf,
+				conn->vals->create_disk_id_size);
 		if (next_ptr)
 			*next_ptr = cpu_to_le32(next_off);
 		next_ptr = &disk_id_ccontext->Next;
@@ -3207,15 +3231,15 @@ int smb2_open(struct ksmbd_work *work)
 				fp);
 		le32_add_cpu(&rsp->CreateContextsLength,
 			     conn->vals->create_posix_size);
-		inc_rfc1001_len(rsp_org, conn->vals->create_posix_size);
+		inc_rfc1001_len(work->response_buf,
+				conn->vals->create_posix_size);
 		if (next_ptr)
 			*next_ptr = cpu_to_le32(next_off);
 	}
 
 	if (contxt_cnt > 0) {
 		rsp->CreateContextsOffset =
-			cpu_to_le32(offsetof(struct smb2_create_rsp, Buffer)
-			- 4);
+			cpu_to_le32(offsetof(struct smb2_create_rsp, Buffer));
 	}
 
 err_out:
@@ -3422,9 +3446,9 @@ static int smb2_populate_readdir_entry(struct ksmbd_conn *conn, int info_level,
 		ffdinfo->EaSize =
 			smb2_get_reparse_tag_special_file(ksmbd_kstat->kstat->mode);
 		if (ffdinfo->EaSize)
-			ffdinfo->ExtFileAttributes = ATTR_REPARSE_POINT_LE;
+			ffdinfo->ExtFileAttributes = FILE_ATTRIBUTE_REPARSE_POINT_LE;
 		if (d_info->hide_dot_file && d_info->name[0] == '.')
-			ffdinfo->ExtFileAttributes |= ATTR_HIDDEN_LE;
+			ffdinfo->ExtFileAttributes |= FILE_ATTRIBUTE_HIDDEN_LE;
 		memcpy(ffdinfo->FileName, conv_name, conv_len);
 		ffdinfo->NextEntryOffset = cpu_to_le32(next_entry_offset);
 		break;
@@ -3438,11 +3462,11 @@ static int smb2_populate_readdir_entry(struct ksmbd_conn *conn, int info_level,
 		fbdinfo->EaSize =
 			smb2_get_reparse_tag_special_file(ksmbd_kstat->kstat->mode);
 		if (fbdinfo->EaSize)
-			fbdinfo->ExtFileAttributes = ATTR_REPARSE_POINT_LE;
+			fbdinfo->ExtFileAttributes = FILE_ATTRIBUTE_REPARSE_POINT_LE;
 		fbdinfo->ShortNameLength = 0;
 		fbdinfo->Reserved = 0;
 		if (d_info->hide_dot_file && d_info->name[0] == '.')
-			fbdinfo->ExtFileAttributes |= ATTR_HIDDEN_LE;
+			fbdinfo->ExtFileAttributes |= FILE_ATTRIBUTE_HIDDEN_LE;
 		memcpy(fbdinfo->FileName, conv_name, conv_len);
 		fbdinfo->NextEntryOffset = cpu_to_le32(next_entry_offset);
 		break;
@@ -3454,7 +3478,7 @@ static int smb2_populate_readdir_entry(struct ksmbd_conn *conn, int info_level,
 		fdinfo = (struct file_directory_info *)kstat;
 		fdinfo->FileNameLength = cpu_to_le32(conv_len);
 		if (d_info->hide_dot_file && d_info->name[0] == '.')
-			fdinfo->ExtFileAttributes |= ATTR_HIDDEN_LE;
+			fdinfo->ExtFileAttributes |= FILE_ATTRIBUTE_HIDDEN_LE;
 		memcpy(fdinfo->FileName, conv_name, conv_len);
 		fdinfo->NextEntryOffset = cpu_to_le32(next_entry_offset);
 		break;
@@ -3478,11 +3502,11 @@ static int smb2_populate_readdir_entry(struct ksmbd_conn *conn, int info_level,
 		dinfo->EaSize =
 			smb2_get_reparse_tag_special_file(ksmbd_kstat->kstat->mode);
 		if (dinfo->EaSize)
-			dinfo->ExtFileAttributes = ATTR_REPARSE_POINT_LE;
+			dinfo->ExtFileAttributes = FILE_ATTRIBUTE_REPARSE_POINT_LE;
 		dinfo->Reserved = 0;
 		dinfo->UniqueId = cpu_to_le64(ksmbd_kstat->kstat->ino);
 		if (d_info->hide_dot_file && d_info->name[0] == '.')
-			dinfo->ExtFileAttributes |= ATTR_HIDDEN_LE;
+			dinfo->ExtFileAttributes |= FILE_ATTRIBUTE_HIDDEN_LE;
 		memcpy(dinfo->FileName, conv_name, conv_len);
 		dinfo->NextEntryOffset = cpu_to_le32(next_entry_offset);
 		break;
@@ -3496,13 +3520,13 @@ static int smb2_populate_readdir_entry(struct ksmbd_conn *conn, int info_level,
 		fibdinfo->EaSize =
 			smb2_get_reparse_tag_special_file(ksmbd_kstat->kstat->mode);
 		if (fibdinfo->EaSize)
-			fibdinfo->ExtFileAttributes = ATTR_REPARSE_POINT_LE;
+			fibdinfo->ExtFileAttributes = FILE_ATTRIBUTE_REPARSE_POINT_LE;
 		fibdinfo->UniqueId = cpu_to_le64(ksmbd_kstat->kstat->ino);
 		fibdinfo->ShortNameLength = 0;
 		fibdinfo->Reserved = 0;
 		fibdinfo->Reserved2 = cpu_to_le16(0);
 		if (d_info->hide_dot_file && d_info->name[0] == '.')
-			fibdinfo->ExtFileAttributes |= ATTR_HIDDEN_LE;
+			fibdinfo->ExtFileAttributes |= FILE_ATTRIBUTE_HIDDEN_LE;
 		memcpy(fibdinfo->FileName, conv_name, conv_len);
 		fibdinfo->NextEntryOffset = cpu_to_le32(next_entry_offset);
 		break;
@@ -3528,9 +3552,10 @@ static int smb2_populate_readdir_entry(struct ksmbd_conn *conn, int info_level,
 		posix_info->Mode = cpu_to_le32(ksmbd_kstat->kstat->mode);
 		posix_info->Inode = cpu_to_le64(ksmbd_kstat->kstat->ino);
 		posix_info->DosAttributes =
-			S_ISDIR(ksmbd_kstat->kstat->mode) ? ATTR_DIRECTORY_LE : ATTR_ARCHIVE_LE;
+			S_ISDIR(ksmbd_kstat->kstat->mode) ?
+				FILE_ATTRIBUTE_DIRECTORY_LE : FILE_ATTRIBUTE_ARCHIVE_LE;
 		if (d_info->hide_dot_file && d_info->name[0] == '.')
-			posix_info->DosAttributes |= ATTR_HIDDEN_LE;
+			posix_info->DosAttributes |= FILE_ATTRIBUTE_HIDDEN_LE;
 		id_to_sid(from_kuid_munged(&init_user_ns, ksmbd_kstat->kstat->uid),
 			  SIDNFS_USER, (struct smb_sid *)&posix_info->SidBuffer[0]);
 		id_to_sid(from_kgid_munged(&init_user_ns, ksmbd_kstat->kstat->gid),
@@ -3816,7 +3841,7 @@ int smb2_query_dir(struct ksmbd_work *work)
 {
 	struct ksmbd_conn *conn = work->conn;
 	struct smb2_query_directory_req *req;
-	struct smb2_query_directory_rsp *rsp, *rsp_org;
+	struct smb2_query_directory_rsp *rsp;
 	struct ksmbd_share_config *share = work->tcon->share_conf;
 	struct ksmbd_file *dir_fp = NULL;
 	struct ksmbd_dir_info d_info;
@@ -3826,7 +3851,6 @@ int smb2_query_dir(struct ksmbd_work *work)
 	int buffer_sz;
 	struct smb2_query_dir_private query_dir_private = {NULL, };
 
-	rsp_org = work->response_buf;
 	WORK_BUFFERS(work, req, rsp);
 
 	if (ksmbd_override_fsids(work)) {
@@ -3947,7 +3971,7 @@ int smb2_query_dir(struct ksmbd_work *work)
 		rsp->OutputBufferOffset = cpu_to_le16(0);
 		rsp->OutputBufferLength = cpu_to_le32(0);
 		rsp->Buffer[0] = 0;
-		inc_rfc1001_len(rsp_org, 9);
+		inc_rfc1001_len(work->response_buf, 9);
 	} else {
 		((struct file_directory_info *)
 		((char *)rsp->Buffer + d_info.last_entry_offset))
@@ -3956,7 +3980,7 @@ int smb2_query_dir(struct ksmbd_work *work)
 		rsp->StructureSize = cpu_to_le16(9);
 		rsp->OutputBufferOffset = cpu_to_le16(72);
 		rsp->OutputBufferLength = cpu_to_le32(d_info.data_count);
-		inc_rfc1001_len(rsp_org, 8 + d_info.data_count);
+		inc_rfc1001_len(work->response_buf, 8 + d_info.data_count);
 	}
 
 	kfree(srch_ptr);
@@ -3999,26 +4023,28 @@ err_out2:
  * Return:	0 on success, otherwise error
  */
 static int buffer_check_err(int reqOutputBufferLength,
-			    struct smb2_query_info_rsp *rsp, int infoclass_size)
+			    struct smb2_query_info_rsp *rsp,
+			    void *rsp_org, int infoclass_size)
 {
 	if (reqOutputBufferLength < le32_to_cpu(rsp->OutputBufferLength)) {
 		if (reqOutputBufferLength < infoclass_size) {
 			pr_err("Invalid Buffer Size Requested\n");
 			rsp->hdr.Status = STATUS_INFO_LENGTH_MISMATCH;
-			rsp->hdr.smb2_buf_length = cpu_to_be32(sizeof(struct smb2_hdr) - 4);
+			*(__be32 *)rsp_org = cpu_to_be32(sizeof(struct smb2_hdr));
 			return -EINVAL;
 		}
 
 		ksmbd_debug(SMB, "Buffer Overflow\n");
 		rsp->hdr.Status = STATUS_BUFFER_OVERFLOW;
-		rsp->hdr.smb2_buf_length = cpu_to_be32(sizeof(struct smb2_hdr) - 4 +
+		*(__be32 *)rsp_org = cpu_to_be32(sizeof(struct smb2_hdr) +
 				reqOutputBufferLength);
 		rsp->OutputBufferLength = cpu_to_le32(reqOutputBufferLength);
 	}
 	return 0;
 }
 
-static void get_standard_info_pipe(struct smb2_query_info_rsp *rsp)
+static void get_standard_info_pipe(struct smb2_query_info_rsp *rsp,
+				   void *rsp_org)
 {
 	struct smb2_file_standard_info *sinfo;
 
@@ -4031,10 +4057,11 @@ static void get_standard_info_pipe(struct smb2_query_info_rsp *rsp)
 	sinfo->Directory = 0;
 	rsp->OutputBufferLength =
 		cpu_to_le32(sizeof(struct smb2_file_standard_info));
-	inc_rfc1001_len(rsp, sizeof(struct smb2_file_standard_info));
+	inc_rfc1001_len(rsp_org, sizeof(struct smb2_file_standard_info));
 }
 
-static void get_internal_info_pipe(struct smb2_query_info_rsp *rsp, u64 num)
+static void get_internal_info_pipe(struct smb2_query_info_rsp *rsp, u64 num,
+				   void *rsp_org)
 {
 	struct smb2_file_internal_info *file_info;
 
@@ -4044,12 +4071,13 @@ static void get_internal_info_pipe(struct smb2_query_info_rsp *rsp, u64 num)
 	file_info->IndexNumber = cpu_to_le64(num | (1ULL << 63));
 	rsp->OutputBufferLength =
 		cpu_to_le32(sizeof(struct smb2_file_internal_info));
-	inc_rfc1001_len(rsp, sizeof(struct smb2_file_internal_info));
+	inc_rfc1001_len(rsp_org, sizeof(struct smb2_file_internal_info));
 }
 
 static int smb2_get_info_file_pipe(struct ksmbd_session *sess,
 				   struct smb2_query_info_req *req,
-				   struct smb2_query_info_rsp *rsp)
+				   struct smb2_query_info_rsp *rsp,
+				   void *rsp_org)
 {
 	u64 id;
 	int rc;
@@ -4067,14 +4095,16 @@ static int smb2_get_info_file_pipe(struct ksmbd_session *sess,
 
 	switch (req->FileInfoClass) {
 	case FILE_STANDARD_INFORMATION:
-		get_standard_info_pipe(rsp);
+		get_standard_info_pipe(rsp, rsp_org);
 		rc = buffer_check_err(le32_to_cpu(req->OutputBufferLength),
-				      rsp, FILE_STANDARD_INFORMATION_SIZE);
+				      rsp, rsp_org,
+				      FILE_STANDARD_INFORMATION_SIZE);
 		break;
 	case FILE_INTERNAL_INFORMATION:
-		get_internal_info_pipe(rsp, id);
+		get_internal_info_pipe(rsp, id, rsp_org);
 		rc = buffer_check_err(le32_to_cpu(req->OutputBufferLength),
-				      rsp, FILE_INTERNAL_INFORMATION_SIZE);
+				      rsp, rsp_org,
+				      FILE_INTERNAL_INFORMATION_SIZE);
 		break;
 	default:
 		ksmbd_debug(SMB, "smb2_info_file_pipe for %u not supported\n",
@@ -4450,6 +4480,12 @@ static void get_file_stream_info(struct ksmbd_work *work,
 			 &stat);
 	file_info = (struct smb2_file_stream_info *)rsp->Buffer;
 
+	buf_free_len =
+		smb2_calc_max_out_buf_len(work, 8,
+					  le32_to_cpu(req->OutputBufferLength));
+	if (buf_free_len < 0)
+		goto out;
+
 	xattr_list_len = ksmbd_vfs_listxattr(path->dentry, &xattr_list);
 	if (xattr_list_len < 0) {
 		goto out;
@@ -4458,12 +4494,6 @@ static void get_file_stream_info(struct ksmbd_work *work,
 		goto out;
 	}
 
-	buf_free_len =
-		smb2_calc_max_out_buf_len(work, 8,
-					  le32_to_cpu(req->OutputBufferLength));
-	if (buf_free_len < 0)
-		goto out;
-
 	while (idx < xattr_list_len) {
 		stream_name = xattr_list + idx;
 		streamlen = strlen(stream_name);
@@ -4489,8 +4519,10 @@ static void get_file_stream_info(struct ksmbd_work *work,
 				     ":%s", &stream_name[XATTR_NAME_STREAM_LEN]);
 
 		next = sizeof(struct smb2_file_stream_info) + streamlen * 2;
-		if (next > buf_free_len)
+		if (next > buf_free_len) {
+			kfree(stream_buf);
 			break;
+		}
 
 		file_info = (struct smb2_file_stream_info *)&rsp->Buffer[nbytes];
 		streamlen  = smbConvertToUTF16((__le16 *)file_info->StreamName,
@@ -4507,6 +4539,7 @@ static void get_file_stream_info(struct ksmbd_work *work,
 		file_info->NextEntryOffset = cpu_to_le32(next);
 	}
 
+out:
 	if (!S_ISDIR(stat.mode) &&
 	    buf_free_len >= sizeof(struct smb2_file_stream_info) + 7 * 2) {
 		file_info = (struct smb2_file_stream_info *)
@@ -4515,14 +4548,13 @@ static void get_file_stream_info(struct ksmbd_work *work,
 					      "::$DATA", 7, conn->local_nls, 0);
 		streamlen *= 2;
 		file_info->StreamNameLength = cpu_to_le32(streamlen);
-		file_info->StreamSize = 0;
-		file_info->StreamAllocationSize = 0;
+		file_info->StreamSize = cpu_to_le64(stat.size);
+		file_info->StreamAllocationSize = cpu_to_le64(stat.blocks << 9);
 		nbytes += sizeof(struct smb2_file_stream_info) + streamlen;
 	}
 
 	/* last entry offset should be 0 */
 	file_info->NextEntryOffset = 0;
-out:
 	kvfree(xattr_list);
 
 	rsp->OutputBufferLength = cpu_to_le32(nbytes);
@@ -4688,7 +4720,7 @@ static int find_file_posix_info(struct smb2_query_info_rsp *rsp,
 
 static int smb2_get_info_file(struct ksmbd_work *work,
 			      struct smb2_query_info_req *req,
-			      struct smb2_query_info_rsp *rsp, void *rsp_org)
+			      struct smb2_query_info_rsp *rsp)
 {
 	struct ksmbd_file *fp;
 	int fileinfoclass = 0;
@@ -4699,7 +4731,8 @@ static int smb2_get_info_file(struct ksmbd_work *work,
 	if (test_share_config_flag(work->tcon->share_conf,
 				   KSMBD_SHARE_FLAG_PIPE)) {
 		/* smb2 info file called for pipe */
-		return smb2_get_info_file_pipe(work->sess, req, rsp);
+		return smb2_get_info_file_pipe(work->sess, req, rsp,
+					       work->response_buf);
 	}
 
 	if (work->next_smb2_rcv_hdr_off) {
@@ -4724,77 +4757,77 @@ static int smb2_get_info_file(struct ksmbd_work *work,
 
 	switch (fileinfoclass) {
 	case FILE_ACCESS_INFORMATION:
-		get_file_access_info(rsp, fp, rsp_org);
+		get_file_access_info(rsp, fp, work->response_buf);
 		file_infoclass_size = FILE_ACCESS_INFORMATION_SIZE;
 		break;
 
 	case FILE_BASIC_INFORMATION:
-		rc = get_file_basic_info(rsp, fp, rsp_org);
+		rc = get_file_basic_info(rsp, fp, work->response_buf);
 		file_infoclass_size = FILE_BASIC_INFORMATION_SIZE;
 		break;
 
 	case FILE_STANDARD_INFORMATION:
-		get_file_standard_info(rsp, fp, rsp_org);
+		get_file_standard_info(rsp, fp, work->response_buf);
 		file_infoclass_size = FILE_STANDARD_INFORMATION_SIZE;
 		break;
 
 	case FILE_ALIGNMENT_INFORMATION:
-		get_file_alignment_info(rsp, rsp_org);
+		get_file_alignment_info(rsp, work->response_buf);
 		file_infoclass_size = FILE_ALIGNMENT_INFORMATION_SIZE;
 		break;
 
 	case FILE_ALL_INFORMATION:
-		rc = get_file_all_info(work, rsp, fp, rsp_org);
+		rc = get_file_all_info(work, rsp, fp, work->response_buf);
 		file_infoclass_size = FILE_ALL_INFORMATION_SIZE;
 		break;
 
 	case FILE_ALTERNATE_NAME_INFORMATION:
-		get_file_alternate_info(work, rsp, fp, rsp_org);
+		get_file_alternate_info(work, rsp, fp, work->response_buf);
 		file_infoclass_size = FILE_ALTERNATE_NAME_INFORMATION_SIZE;
 		break;
 
 	case FILE_STREAM_INFORMATION:
-		get_file_stream_info(work, rsp, fp, rsp_org);
+		get_file_stream_info(work, rsp, fp, work->response_buf);
 		file_infoclass_size = FILE_STREAM_INFORMATION_SIZE;
 		break;
 
 	case FILE_INTERNAL_INFORMATION:
-		get_file_internal_info(rsp, fp, rsp_org);
+		get_file_internal_info(rsp, fp, work->response_buf);
 		file_infoclass_size = FILE_INTERNAL_INFORMATION_SIZE;
 		break;
 
 	case FILE_NETWORK_OPEN_INFORMATION:
-		rc = get_file_network_open_info(rsp, fp, rsp_org);
+		rc = get_file_network_open_info(rsp, fp, work->response_buf);
 		file_infoclass_size = FILE_NETWORK_OPEN_INFORMATION_SIZE;
 		break;
 
 	case FILE_EA_INFORMATION:
-		get_file_ea_info(rsp, rsp_org);
+		get_file_ea_info(rsp, work->response_buf);
 		file_infoclass_size = FILE_EA_INFORMATION_SIZE;
 		break;
 
 	case FILE_FULL_EA_INFORMATION:
-		rc = smb2_get_ea(work, fp, req, rsp, rsp_org);
+		rc = smb2_get_ea(work, fp, req, rsp, work->response_buf);
 		file_infoclass_size = FILE_FULL_EA_INFORMATION_SIZE;
 		break;
 
 	case FILE_POSITION_INFORMATION:
-		get_file_position_info(rsp, fp, rsp_org);
+		get_file_position_info(rsp, fp, work->response_buf);
 		file_infoclass_size = FILE_POSITION_INFORMATION_SIZE;
 		break;
 
 	case FILE_MODE_INFORMATION:
-		get_file_mode_info(rsp, fp, rsp_org);
+		get_file_mode_info(rsp, fp, work->response_buf);
 		file_infoclass_size = FILE_MODE_INFORMATION_SIZE;
 		break;
 
 	case FILE_COMPRESSION_INFORMATION:
-		get_file_compression_info(rsp, fp, rsp_org);
+		get_file_compression_info(rsp, fp, work->response_buf);
 		file_infoclass_size = FILE_COMPRESSION_INFORMATION_SIZE;
 		break;
 
 	case FILE_ATTRIBUTE_TAG_INFORMATION:
-		rc = get_file_attribute_tag_info(rsp, fp, rsp_org);
+		rc = get_file_attribute_tag_info(rsp, fp, work->response_buf);
 		file_infoclass_size = FILE_ATTRIBUTE_TAG_INFORMATION_SIZE;
 		break;
 	case SMB_FIND_FILE_POSIX_INFO:
@@ -4802,7 +4835,7 @@ static int smb2_get_info_file(struct ksmbd_work *work,
 			pr_err("client doesn't negotiate with SMB3.1.1 POSIX Extensions\n");
 			rc = -EOPNOTSUPP;
 		} else {
-			rc = find_file_posix_info(rsp, fp, rsp_org);
+			rc = find_file_posix_info(rsp, fp, work->response_buf);
 			file_infoclass_size = sizeof(struct smb311_posix_qinfo);
 		}
 		break;
@@ -4813,7 +4846,7 @@ static int smb2_get_info_file(struct ksmbd_work *work,
 	}
 	if (!rc)
 		rc = buffer_check_err(le32_to_cpu(req->OutputBufferLength),
-				      rsp,
+				      rsp, work->response_buf,
 				      file_infoclass_size);
 	ksmbd_fd_put(work, fp);
 	return rc;
@@ -4821,7 +4854,7 @@ static int smb2_get_info_file(struct ksmbd_work *work,
 
 static int smb2_get_info_filesystem(struct ksmbd_work *work,
 				    struct smb2_query_info_req *req,
-				    struct smb2_query_info_rsp *rsp, void *rsp_org)
+				    struct smb2_query_info_rsp *rsp)
 {
 	struct ksmbd_session *sess = work->sess;
 	struct ksmbd_conn *conn = sess->conn;
@@ -4857,7 +4890,7 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work,
 		info->DeviceType = cpu_to_le32(stfs.f_type);
 		info->DeviceCharacteristics = cpu_to_le32(0x00000020);
 		rsp->OutputBufferLength = cpu_to_le32(8);
-		inc_rfc1001_len(rsp_org, 8);
+		inc_rfc1001_len(work->response_buf, 8);
 		fs_infoclass_size = FS_DEVICE_INFORMATION_SIZE;
 		break;
 	}
@@ -4883,7 +4916,7 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work,
 		info->FileSystemNameLen = cpu_to_le32(len);
 		sz = sizeof(struct filesystem_attribute_info) - 2 + len;
 		rsp->OutputBufferLength = cpu_to_le32(sz);
-		inc_rfc1001_len(rsp_org, sz);
+		inc_rfc1001_len(work->response_buf, sz);
 		fs_infoclass_size = FS_ATTRIBUTE_INFORMATION_SIZE;
 		break;
 	}
@@ -4891,11 +4924,18 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work,
 	{
 		struct filesystem_vol_info *info;
 		size_t sz;
+		unsigned int serial_crc = 0;
 
 		info = (struct filesystem_vol_info *)(rsp->Buffer);
 		info->VolumeCreationTime = 0;
+		serial_crc = crc32_le(serial_crc, share->name,
+				      strlen(share->name));
+		serial_crc = crc32_le(serial_crc, share->path,
+				      strlen(share->path));
+		serial_crc = crc32_le(serial_crc, ksmbd_netbios_name(),
+				      strlen(ksmbd_netbios_name()));
 		/* Taking dummy value of serial number*/
-		info->SerialNumber = cpu_to_le32(0xbc3ac512);
+		info->SerialNumber = cpu_to_le32(serial_crc);
 		len = smbConvertToUTF16((__le16 *)info->VolumeLabel,
 					share->name, PATH_MAX,
 					conn->local_nls, 0);
@@ -4904,7 +4944,7 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work,
 		info->Reserved = 0;
 		sz = sizeof(struct filesystem_vol_info) - 2 + len;
 		rsp->OutputBufferLength = cpu_to_le32(sz);
-		inc_rfc1001_len(rsp_org, sz);
+		inc_rfc1001_len(work->response_buf, sz);
 		fs_infoclass_size = FS_VOLUME_INFORMATION_SIZE;
 		break;
 	}
@@ -4918,7 +4958,7 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work,
 		info->SectorsPerAllocationUnit = cpu_to_le32(1);
 		info->BytesPerSector = cpu_to_le32(stfs.f_bsize);
 		rsp->OutputBufferLength = cpu_to_le32(24);
-		inc_rfc1001_len(rsp_org, 24);
+		inc_rfc1001_len(work->response_buf, 24);
 		fs_infoclass_size = FS_SIZE_INFORMATION_SIZE;
 		break;
 	}
@@ -4935,7 +4975,7 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work,
 		info->SectorsPerAllocationUnit = cpu_to_le32(1);
 		info->BytesPerSector = cpu_to_le32(stfs.f_bsize);
 		rsp->OutputBufferLength = cpu_to_le32(32);
-		inc_rfc1001_len(rsp_org, 32);
+		inc_rfc1001_len(work->response_buf, 32);
 		fs_infoclass_size = FS_FULL_SIZE_INFORMATION_SIZE;
 		break;
 	}
@@ -4956,7 +4996,7 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work,
 		info->extended_info.rel_date = 0;
 		memcpy(info->extended_info.version_string, "1.1.0", strlen("1.1.0"));
 		rsp->OutputBufferLength = cpu_to_le32(64);
-		inc_rfc1001_len(rsp_org, 64);
+		inc_rfc1001_len(work->response_buf, 64);
 		fs_infoclass_size = FS_OBJECT_ID_INFORMATION_SIZE;
 		break;
 	}
@@ -4977,7 +5017,7 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work,
 		info->ByteOffsetForSectorAlignment = 0;
 		info->ByteOffsetForPartitionAlignment = 0;
 		rsp->OutputBufferLength = cpu_to_le32(28);
-		inc_rfc1001_len(rsp_org, 28);
+		inc_rfc1001_len(work->response_buf, 28);
 		fs_infoclass_size = FS_SECTOR_SIZE_INFORMATION_SIZE;
 		break;
 	}
@@ -4999,7 +5039,7 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work,
 		info->DefaultQuotaLimit = cpu_to_le64(SMB2_NO_FID);
 		info->Padding = 0;
 		rsp->OutputBufferLength = cpu_to_le32(48);
-		inc_rfc1001_len(rsp_org, 48);
+		inc_rfc1001_len(work->response_buf, 48);
 		fs_infoclass_size = FS_CONTROL_INFORMATION_SIZE;
 		break;
 	}
@@ -5020,7 +5060,7 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work,
 			info->TotalFileNodes = cpu_to_le64(stfs.f_files);
 			info->FreeFileNodes = cpu_to_le64(stfs.f_ffree);
 			rsp->OutputBufferLength = cpu_to_le32(56);
-			inc_rfc1001_len(rsp_org, 56);
+			inc_rfc1001_len(work->response_buf, 56);
 			fs_infoclass_size = FS_POSIX_INFORMATION_SIZE;
 		}
 		break;
@@ -5030,7 +5070,7 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work,
 		return -EOPNOTSUPP;
 	}
 	rc = buffer_check_err(le32_to_cpu(req->OutputBufferLength),
-			      rsp,
+			      rsp, work->response_buf,
 			      fs_infoclass_size);
 	path_put(&path);
 	return rc;
@@ -5038,7 +5078,7 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work,
 
 static int smb2_get_info_sec(struct ksmbd_work *work,
 			     struct smb2_query_info_req *req,
-			     struct smb2_query_info_rsp *rsp, void *rsp_org)
+			     struct smb2_query_info_rsp *rsp)
 {
 	struct ksmbd_file *fp;
 	struct user_namespace *user_ns;
@@ -5053,7 +5093,7 @@ static int smb2_get_info_sec(struct ksmbd_work *work,
 	if (addition_info & ~(OWNER_SECINFO | GROUP_SECINFO | DACL_SECINFO |
 			      PROTECTED_DACL_SECINFO |
 			      UNPROTECTED_DACL_SECINFO)) {
-		pr_err("Unsupported addition info: 0x%x)\n",
+		ksmbd_debug(SMB, "Unsupported addition info: 0x%x)\n",
 		       addition_info);
 
 		pntsd->revision = cpu_to_le16(1);
@@ -5065,7 +5105,7 @@ static int smb2_get_info_sec(struct ksmbd_work *work,
 
 		secdesclen = sizeof(struct smb_ntsd);
 		rsp->OutputBufferLength = cpu_to_le32(secdesclen);
-		inc_rfc1001_len(rsp_org, secdesclen);
+		inc_rfc1001_len(work->response_buf, secdesclen);
 
 		return 0;
 	}
@@ -5107,7 +5147,7 @@ static int smb2_get_info_sec(struct ksmbd_work *work,
 		return rc;
 
 	rsp->OutputBufferLength = cpu_to_le32(secdesclen);
-	inc_rfc1001_len(rsp_org, secdesclen);
+	inc_rfc1001_len(work->response_buf, secdesclen);
 	return 0;
 }
 
@@ -5120,10 +5160,9 @@ static int smb2_get_info_sec(struct ksmbd_work *work,
 int smb2_query_info(struct ksmbd_work *work)
 {
 	struct smb2_query_info_req *req;
-	struct smb2_query_info_rsp *rsp, *rsp_org;
+	struct smb2_query_info_rsp *rsp;
 	int rc = 0;
 
-	rsp_org = work->response_buf;
 	WORK_BUFFERS(work, req, rsp);
 
 	ksmbd_debug(SMB, "GOT query info request\n");
@@ -5131,15 +5170,15 @@ int smb2_query_info(struct ksmbd_work *work)
 	switch (req->InfoType) {
 	case SMB2_O_INFO_FILE:
 		ksmbd_debug(SMB, "GOT SMB2_O_INFO_FILE\n");
-		rc = smb2_get_info_file(work, req, rsp, (void *)rsp_org);
+		rc = smb2_get_info_file(work, req, rsp);
 		break;
 	case SMB2_O_INFO_FILESYSTEM:
 		ksmbd_debug(SMB, "GOT SMB2_O_INFO_FILESYSTEM\n");
-		rc = smb2_get_info_filesystem(work, req, rsp, (void *)rsp_org);
+		rc = smb2_get_info_filesystem(work, req, rsp);
 		break;
 	case SMB2_O_INFO_SECURITY:
 		ksmbd_debug(SMB, "GOT SMB2_O_INFO_SECURITY\n");
-		rc = smb2_get_info_sec(work, req, rsp, (void *)rsp_org);
+		rc = smb2_get_info_sec(work, req, rsp);
 		break;
 	default:
 		ksmbd_debug(SMB, "InfoType %d not supported yet\n",
@@ -5164,7 +5203,7 @@ int smb2_query_info(struct ksmbd_work *work)
 	}
 	rsp->StructureSize = cpu_to_le16(9);
 	rsp->OutputBufferOffset = cpu_to_le16(72);
-	inc_rfc1001_len(rsp_org, 8);
+	inc_rfc1001_len(work->response_buf, 8);
 	return 0;
 }
 
@@ -5177,8 +5216,8 @@ int smb2_query_info(struct ksmbd_work *work)
 static noinline int smb2_close_pipe(struct ksmbd_work *work)
 {
 	u64 id;
-	struct smb2_close_req *req = work->request_buf;
-	struct smb2_close_rsp *rsp = work->response_buf;
+	struct smb2_close_req *req = smb2_get_msg(work->request_buf);
+	struct smb2_close_rsp *rsp = smb2_get_msg(work->response_buf);
 
 	id = le64_to_cpu(req->VolatileFileId);
 	ksmbd_session_rpc_close(work->sess, id);
@@ -5193,7 +5232,7 @@ static noinline int smb2_close_pipe(struct ksmbd_work *work)
 	rsp->AllocationSize = 0;
 	rsp->EndOfFile = 0;
 	rsp->Attributes = 0;
-	inc_rfc1001_len(rsp, 60);
+	inc_rfc1001_len(work->response_buf, 60);
 	return 0;
 }
 
@@ -5209,14 +5248,12 @@ int smb2_close(struct ksmbd_work *work)
 	u64 sess_id;
 	struct smb2_close_req *req;
 	struct smb2_close_rsp *rsp;
-	struct smb2_close_rsp *rsp_org;
 	struct ksmbd_conn *conn = work->conn;
 	struct ksmbd_file *fp;
 	struct inode *inode;
 	u64 time;
 	int err = 0;
 
-	rsp_org = work->response_buf;
 	WORK_BUFFERS(work, req, rsp);
 
 	if (test_share_config_flag(work->tcon->share_conf,
@@ -5306,7 +5343,7 @@ out:
 			rsp->hdr.Status = STATUS_FILE_CLOSED;
 		smb2_set_err_rsp(work);
 	} else {
-		inc_rfc1001_len(rsp_org, 60);
+		inc_rfc1001_len(work->response_buf, 60);
 	}
 
 	return 0;
@@ -5320,11 +5357,11 @@ out:
  */
 int smb2_echo(struct ksmbd_work *work)
 {
-	struct smb2_echo_rsp *rsp = work->response_buf;
+	struct smb2_echo_rsp *rsp = smb2_get_msg(work->response_buf);
 
 	rsp->StructureSize = cpu_to_le16(4);
 	rsp->Reserved = 0;
-	inc_rfc1001_len(rsp, 4);
+	inc_rfc1001_len(work->response_buf, 4);
 	return 0;
 }
 
@@ -5566,14 +5603,14 @@ static int set_file_basic_info(struct ksmbd_file *fp,
 
 	if (file_info->Attributes) {
 		if (!S_ISDIR(inode->i_mode) &&
-		    file_info->Attributes & ATTR_DIRECTORY_LE) {
+		    file_info->Attributes & FILE_ATTRIBUTE_DIRECTORY_LE) {
 			pr_err("can't change a file to a directory\n");
 			return -EINVAL;
 		}
 
-		if (!(S_ISDIR(inode->i_mode) && file_info->Attributes == ATTR_NORMAL_LE))
+		if (!(S_ISDIR(inode->i_mode) && file_info->Attributes == FILE_ATTRIBUTE_NORMAL_LE))
 			fp->f_ci->m_fattr = file_info->Attributes |
-				(fp->f_ci->m_fattr & ATTR_DIRECTORY_LE);
+				(fp->f_ci->m_fattr & FILE_ATTRIBUTE_DIRECTORY_LE);
 	}
 
 	if (test_share_config_flag(share, KSMBD_SHARE_FLAG_STORE_DOS_ATTRS) &&
@@ -5794,9 +5831,7 @@ static int set_file_mode_info(struct ksmbd_file *fp,
 
 	mode = file_info->Mode;
 
-	if ((mode & ~FILE_MODE_INFO_MASK) ||
-	    (mode & FILE_SYNCHRONOUS_IO_ALERT_LE &&
-	     mode & FILE_SYNCHRONOUS_IO_NONALERT_LE)) {
+	if ((mode & ~FILE_MODE_INFO_MASK)) {
 		pr_err("Mode is not valid : 0x%x\n", le32_to_cpu(mode));
 		return -EINVAL;
 	}
@@ -5943,14 +5978,13 @@ static int smb2_set_info_sec(struct ksmbd_file *fp, int addition_info,
 int smb2_set_info(struct ksmbd_work *work)
 {
 	struct smb2_set_info_req *req;
-	struct smb2_set_info_rsp *rsp, *rsp_org;
+	struct smb2_set_info_rsp *rsp;
 	struct ksmbd_file *fp;
 	int rc = 0;
 	unsigned int id = KSMBD_NO_FID, pid = KSMBD_NO_FID;
 
 	ksmbd_debug(SMB, "Received set info request\n");
 
-	rsp_org = work->response_buf;
 	if (work->next_smb2_rcv_hdr_off) {
 		req = ksmbd_req_buf_next(work);
 		rsp = ksmbd_resp_buf_next(work);
@@ -5961,8 +5995,8 @@ int smb2_set_info(struct ksmbd_work *work)
 			pid = work->compound_pfid;
 		}
 	} else {
-		req = work->request_buf;
-		rsp = work->response_buf;
+		req = smb2_get_msg(work->request_buf);
+		rsp = smb2_get_msg(work->response_buf);
 	}
 
 	if (!has_file_id(id)) {
@@ -6002,7 +6036,7 @@ int smb2_set_info(struct ksmbd_work *work)
 		goto err_out;
 
 	rsp->StructureSize = cpu_to_le16(2);
-	inc_rfc1001_len(rsp_org, 2);
+	inc_rfc1001_len(work->response_buf, 2);
 	ksmbd_fd_put(work, fp);
 	return 0;
 
@@ -6042,12 +6076,12 @@ static noinline int smb2_read_pipe(struct ksmbd_work *work)
 	int nbytes = 0, err;
 	u64 id;
 	struct ksmbd_rpc_command *rpc_resp;
-	struct smb2_read_req *req = work->request_buf;
-	struct smb2_read_rsp *rsp = work->response_buf;
+	struct smb2_read_req *req = smb2_get_msg(work->request_buf);
+	struct smb2_read_rsp *rsp = smb2_get_msg(work->response_buf);
 
 	id = le64_to_cpu(req->VolatileFileId);
 
-	inc_rfc1001_len(rsp, 16);
+	inc_rfc1001_len(work->response_buf, 16);
 	rpc_resp = ksmbd_rpc_read(work->sess, id);
 	if (rpc_resp) {
 		if (rpc_resp->flags != KSMBD_RPC_OK) {
@@ -6066,7 +6100,7 @@ static noinline int smb2_read_pipe(struct ksmbd_work *work)
 		       rpc_resp->payload_sz);
 
 		nbytes = rpc_resp->payload_sz;
-		work->resp_hdr_sz = get_rfc1002_len(rsp) + 4;
+		work->resp_hdr_sz = get_rfc1002_len(work->response_buf) + 4;
 		work->aux_payload_sz = nbytes;
 		kvfree(rpc_resp);
 	}
@@ -6076,8 +6110,8 @@ static noinline int smb2_read_pipe(struct ksmbd_work *work)
 	rsp->Reserved = 0;
 	rsp->DataLength = cpu_to_le32(nbytes);
 	rsp->DataRemaining = 0;
-	rsp->Reserved2 = 0;
-	inc_rfc1001_len(rsp, nbytes);
+	rsp->Flags = 0;
+	inc_rfc1001_len(work->response_buf, nbytes);
 	return 0;
 
 out:
@@ -6127,14 +6161,13 @@ int smb2_read(struct ksmbd_work *work)
 {
 	struct ksmbd_conn *conn = work->conn;
 	struct smb2_read_req *req;
-	struct smb2_read_rsp *rsp, *rsp_org;
+	struct smb2_read_rsp *rsp;
 	struct ksmbd_file *fp;
 	loff_t offset;
 	size_t length, mincount;
 	ssize_t nbytes = 0, remain_bytes = 0;
 	int err = 0;
 
-	rsp_org = work->response_buf;
 	WORK_BUFFERS(work, req, rsp);
 
 	if (test_share_config_flag(work->tcon->share_conf,
@@ -6215,11 +6248,11 @@ int smb2_read(struct ksmbd_work *work)
 	rsp->Reserved = 0;
 	rsp->DataLength = cpu_to_le32(nbytes);
 	rsp->DataRemaining = cpu_to_le32(remain_bytes);
-	rsp->Reserved2 = 0;
-	inc_rfc1001_len(rsp_org, 16);
-	work->resp_hdr_sz = get_rfc1002_len(rsp_org) + 4;
+	rsp->Flags = 0;
+	inc_rfc1001_len(work->response_buf, 16);
+	work->resp_hdr_sz = get_rfc1002_len(work->response_buf) + 4;
 	work->aux_payload_sz = nbytes;
-	inc_rfc1001_len(rsp_org, nbytes);
+	inc_rfc1001_len(work->response_buf, nbytes);
 	ksmbd_fd_put(work, fp);
 	return 0;
 
@@ -6254,8 +6287,8 @@ out:
  */
 static noinline int smb2_write_pipe(struct ksmbd_work *work)
 {
-	struct smb2_write_req *req = work->request_buf;
-	struct smb2_write_rsp *rsp = work->response_buf;
+	struct smb2_write_req *req = smb2_get_msg(work->request_buf);
+	struct smb2_write_rsp *rsp = smb2_get_msg(work->response_buf);
 	struct ksmbd_rpc_command *rpc_resp;
 	u64 id = 0;
 	int err = 0, ret = 0;
@@ -6266,13 +6299,14 @@ static noinline int smb2_write_pipe(struct ksmbd_work *work)
 	id = le64_to_cpu(req->VolatileFileId);
 
 	if (le16_to_cpu(req->DataOffset) ==
-	    (offsetof(struct smb2_write_req, Buffer) - 4)) {
+	    offsetof(struct smb2_write_req, Buffer)) {
 		data_buf = (char *)&req->Buffer[0];
 	} else {
-		if ((u64)le16_to_cpu(req->DataOffset) + length > get_rfc1002_len(req)) {
+		if ((u64)le16_to_cpu(req->DataOffset) + length >
+		    get_rfc1002_len(work->request_buf)) {
 			pr_err("invalid write data offset %u, smb_len %u\n",
 			       le16_to_cpu(req->DataOffset),
-			       get_rfc1002_len(req));
+			       get_rfc1002_len(work->request_buf));
 			err = -EINVAL;
 			goto out;
 		}
@@ -6304,7 +6338,7 @@ static noinline int smb2_write_pipe(struct ksmbd_work *work)
 	rsp->DataLength = cpu_to_le32(length);
 	rsp->DataRemaining = 0;
 	rsp->Reserved2 = 0;
-	inc_rfc1001_len(rsp, 16);
+	inc_rfc1001_len(work->response_buf, 16);
 	return 0;
 out:
 	if (err) {
@@ -6372,7 +6406,7 @@ static ssize_t smb2_write_rdma_channel(struct ksmbd_work *work,
 int smb2_write(struct ksmbd_work *work)
 {
 	struct smb2_write_req *req;
-	struct smb2_write_rsp *rsp, *rsp_org;
+	struct smb2_write_rsp *rsp;
 	struct ksmbd_file *fp = NULL;
 	loff_t offset;
 	size_t length;
@@ -6381,7 +6415,6 @@ int smb2_write(struct ksmbd_work *work)
 	bool writethrough = false;
 	int err = 0;
 
-	rsp_org = work->response_buf;
 	WORK_BUFFERS(work, req, rsp);
 
 	if (test_share_config_flag(work->tcon->share_conf, KSMBD_SHARE_FLAG_PIPE)) {
@@ -6424,13 +6457,14 @@ int smb2_write(struct ksmbd_work *work)
 	if (req->Channel != SMB2_CHANNEL_RDMA_V1 &&
 	    req->Channel != SMB2_CHANNEL_RDMA_V1_INVALIDATE) {
 		if (le16_to_cpu(req->DataOffset) ==
-		    (offsetof(struct smb2_write_req, Buffer) - 4)) {
+		    offsetof(struct smb2_write_req, Buffer)) {
 			data_buf = (char *)&req->Buffer[0];
 		} else {
-			if ((u64)le16_to_cpu(req->DataOffset) + length > get_rfc1002_len(req)) {
+			if ((u64)le16_to_cpu(req->DataOffset) + length >
+			    get_rfc1002_len(work->request_buf)) {
 				pr_err("invalid write data offset %u, smb_len %u\n",
 				       le16_to_cpu(req->DataOffset),
-				       get_rfc1002_len(req));
+				       get_rfc1002_len(work->request_buf));
 				err = -EINVAL;
 				goto out;
 			}
@@ -6468,7 +6502,7 @@ int smb2_write(struct ksmbd_work *work)
 	rsp->DataLength = cpu_to_le32(nbytes);
 	rsp->DataRemaining = 0;
 	rsp->Reserved2 = 0;
-	inc_rfc1001_len(rsp_org, 16);
+	inc_rfc1001_len(work->response_buf, 16);
 	ksmbd_fd_put(work, fp);
 	return 0;
 
@@ -6502,10 +6536,9 @@ out:
 int smb2_flush(struct ksmbd_work *work)
 {
 	struct smb2_flush_req *req;
-	struct smb2_flush_rsp *rsp, *rsp_org;
+	struct smb2_flush_rsp *rsp;
 	int err;
 
-	rsp_org = work->response_buf;
 	WORK_BUFFERS(work, req, rsp);
 
 	ksmbd_debug(SMB, "SMB2_FLUSH called for fid %llu\n",
@@ -6519,7 +6552,7 @@ int smb2_flush(struct ksmbd_work *work)
 
 	rsp->StructureSize = cpu_to_le16(4);
 	rsp->Reserved = 0;
-	inc_rfc1001_len(rsp_org, 4);
+	inc_rfc1001_len(work->response_buf, 4);
 	return 0;
 
 out:
@@ -6540,7 +6573,7 @@ out:
 int smb2_cancel(struct ksmbd_work *work)
 {
 	struct ksmbd_conn *conn = work->conn;
-	struct smb2_hdr *hdr = work->request_buf;
+	struct smb2_hdr *hdr = smb2_get_msg(work->request_buf);
 	struct smb2_hdr *chdr;
 	struct ksmbd_work *cancel_work = NULL;
 	int canceled = 0;
@@ -6555,7 +6588,7 @@ int smb2_cancel(struct ksmbd_work *work)
 		spin_lock(&conn->request_lock);
 		list_for_each_entry(cancel_work, command_list,
 				    async_request_entry) {
-			chdr = cancel_work->request_buf;
+			chdr = smb2_get_msg(cancel_work->request_buf);
 
 			if (cancel_work->async_id !=
 			    le64_to_cpu(hdr->Id.AsyncId))
@@ -6574,7 +6607,7 @@ int smb2_cancel(struct ksmbd_work *work)
 
 		spin_lock(&conn->request_lock);
 		list_for_each_entry(cancel_work, command_list, request_entry) {
-			chdr = cancel_work->request_buf;
+			chdr = smb2_get_msg(cancel_work->request_buf);
 
 			if (chdr->MessageId != hdr->MessageId ||
 			    cancel_work == work)
@@ -6709,8 +6742,8 @@ static inline bool lock_defer_pending(struct file_lock *fl)
  */
 int smb2_lock(struct ksmbd_work *work)
 {
-	struct smb2_lock_req *req = work->request_buf;
-	struct smb2_lock_rsp *rsp = work->response_buf;
+	struct smb2_lock_req *req = smb2_get_msg(work->request_buf);
+	struct smb2_lock_rsp *rsp = smb2_get_msg(work->response_buf);
 	struct smb2_lock_element *lock_ele;
 	struct ksmbd_file *fp = NULL;
 	struct file_lock *flock = NULL;
@@ -7017,7 +7050,7 @@ skip:
 	ksmbd_debug(SMB, "successful in taking lock\n");
 	rsp->hdr.Status = STATUS_SUCCESS;
 	rsp->Reserved = 0;
-	inc_rfc1001_len(rsp, 4);
+	inc_rfc1001_len(work->response_buf, 4);
 	ksmbd_fd_put(work, fp);
 	return 0;
 
@@ -7312,7 +7345,7 @@ static int fsctl_validate_negotiate_info(struct ksmbd_conn *conn,
 	int ret = 0;
 	int dialect;
 
-	if (in_buf_len < sizeof(struct validate_negotiate_info_req) +
+	if (in_buf_len < offsetof(struct validate_negotiate_info_req, Dialects) +
 			le16_to_cpu(neg_req->DialectCount) * sizeof(__le16))
 		return -EINVAL;
 
@@ -7435,9 +7468,9 @@ static inline int fsctl_set_sparse(struct ksmbd_work *work, u64 id,
 
 	old_fattr = fp->f_ci->m_fattr;
 	if (sparse->SetSparse)
-		fp->f_ci->m_fattr |= ATTR_SPARSE_FILE_LE;
+		fp->f_ci->m_fattr |= FILE_ATTRIBUTE_SPARSE_FILE_LE;
 	else
-		fp->f_ci->m_fattr &= ~ATTR_SPARSE_FILE_LE;
+		fp->f_ci->m_fattr &= ~FILE_ATTRIBUTE_SPARSE_FILE_LE;
 
 	if (fp->f_ci->m_fattr != old_fattr &&
 	    test_share_config_flag(work->tcon->share_conf,
@@ -7490,13 +7523,12 @@ static int fsctl_request_resume_key(struct ksmbd_work *work,
 int smb2_ioctl(struct ksmbd_work *work)
 {
 	struct smb2_ioctl_req *req;
-	struct smb2_ioctl_rsp *rsp, *rsp_org;
+	struct smb2_ioctl_rsp *rsp;
 	unsigned int cnt_code, nbytes = 0, out_buf_len, in_buf_len;
 	u64 id = KSMBD_NO_FID;
 	struct ksmbd_conn *conn = work->conn;
 	int ret = 0;
 
-	rsp_org = work->response_buf;
 	if (work->next_smb2_rcv_hdr_off) {
 		req = ksmbd_req_buf_next(work);
 		rsp = ksmbd_resp_buf_next(work);
@@ -7506,8 +7538,8 @@ int smb2_ioctl(struct ksmbd_work *work)
 			id = work->compound_fid;
 		}
 	} else {
-		req = work->request_buf;
-		rsp = work->response_buf;
+		req = smb2_get_msg(work->request_buf);
+		rsp = smb2_get_msg(work->response_buf);
 	}
 
 	if (!has_file_id(id))
@@ -7787,7 +7819,7 @@ dup_ext_out:
 	rsp->Reserved = cpu_to_le16(0);
 	rsp->Flags = cpu_to_le32(0);
 	rsp->Reserved2 = cpu_to_le32(0);
-	inc_rfc1001_len(rsp_org, 48 + nbytes);
+	inc_rfc1001_len(work->response_buf, 48 + nbytes);
 
 	return 0;
 
@@ -7814,8 +7846,8 @@ out:
  */
 static void smb20_oplock_break_ack(struct ksmbd_work *work)
 {
-	struct smb2_oplock_break *req = work->request_buf;
-	struct smb2_oplock_break *rsp = work->response_buf;
+	struct smb2_oplock_break *req = smb2_get_msg(work->request_buf);
+	struct smb2_oplock_break *rsp = smb2_get_msg(work->response_buf);
 	struct ksmbd_file *fp;
 	struct oplock_info *opinfo = NULL;
 	__le32 err = 0;
@@ -7922,7 +7954,7 @@ static void smb20_oplock_break_ack(struct ksmbd_work *work)
 	rsp->Reserved2 = 0;
 	rsp->VolatileFid = cpu_to_le64(volatile_id);
 	rsp->PersistentFid = cpu_to_le64(persistent_id);
-	inc_rfc1001_len(rsp, 24);
+	inc_rfc1001_len(work->response_buf, 24);
 	return;
 
 err_out:
@@ -7958,8 +7990,8 @@ static int check_lease_state(struct lease *lease, __le32 req_state)
 static void smb21_lease_break_ack(struct ksmbd_work *work)
 {
 	struct ksmbd_conn *conn = work->conn;
-	struct smb2_lease_ack *req = work->request_buf;
-	struct smb2_lease_ack *rsp = work->response_buf;
+	struct smb2_lease_ack *req = smb2_get_msg(work->request_buf);
+	struct smb2_lease_ack *rsp = smb2_get_msg(work->response_buf);
 	struct oplock_info *opinfo;
 	__le32 err = 0;
 	int ret = 0;
@@ -8071,7 +8103,7 @@ static void smb21_lease_break_ack(struct ksmbd_work *work)
 	memcpy(rsp->LeaseKey, req->LeaseKey, 16);
 	rsp->LeaseState = lease_state;
 	rsp->LeaseDuration = 0;
-	inc_rfc1001_len(rsp, 36);
+	inc_rfc1001_len(work->response_buf, 36);
 	return;
 
 err_out:
@@ -8092,8 +8124,8 @@ err_out:
  */
 int smb2_oplock_break(struct ksmbd_work *work)
 {
-	struct smb2_oplock_break *req = work->request_buf;
-	struct smb2_oplock_break *rsp = work->response_buf;
+	struct smb2_oplock_break *req = smb2_get_msg(work->request_buf);
+	struct smb2_oplock_break *rsp = smb2_get_msg(work->response_buf);
 
 	switch (le16_to_cpu(req->StructureSize)) {
 	case OP_BREAK_STRUCT_SIZE_20:
@@ -8120,8 +8152,8 @@ int smb2_oplock_break(struct ksmbd_work *work)
  */
 int smb2_notify(struct ksmbd_work *work)
 {
-	struct smb2_notify_req *req;
-	struct smb2_notify_rsp *rsp;
+	struct smb2_change_notify_req *req;
+	struct smb2_change_notify_rsp *rsp;
 
 	WORK_BUFFERS(work, req, rsp);
 
@@ -8145,7 +8177,7 @@ int smb2_notify(struct ksmbd_work *work)
  */
 bool smb2_is_sign_req(struct ksmbd_work *work, unsigned int command)
 {
-	struct smb2_hdr *rcv_hdr2 = work->request_buf;
+	struct smb2_hdr *rcv_hdr2 = smb2_get_msg(work->request_buf);
 
 	if ((rcv_hdr2->Flags & SMB2_FLAGS_SIGNED) &&
 	    command != SMB2_NEGOTIATE_HE &&
@@ -8164,22 +8196,22 @@ bool smb2_is_sign_req(struct ksmbd_work *work, unsigned int command)
  */
 int smb2_check_sign_req(struct ksmbd_work *work)
 {
-	struct smb2_hdr *hdr, *hdr_org;
+	struct smb2_hdr *hdr;
 	char signature_req[SMB2_SIGNATURE_SIZE];
 	char signature[SMB2_HMACSHA256_SIZE];
 	struct kvec iov[1];
 	size_t len;
 
-	hdr_org = hdr = work->request_buf;
+	hdr = smb2_get_msg(work->request_buf);
 	if (work->next_smb2_rcv_hdr_off)
 		hdr = ksmbd_req_buf_next(work);
 
 	if (!hdr->NextCommand && !work->next_smb2_rcv_hdr_off)
-		len = be32_to_cpu(hdr_org->smb2_buf_length);
+		len = get_rfc1002_len(work->request_buf);
 	else if (hdr->NextCommand)
 		len = le32_to_cpu(hdr->NextCommand);
 	else
-		len = be32_to_cpu(hdr_org->smb2_buf_length) -
+		len = get_rfc1002_len(work->request_buf) -
 			work->next_smb2_rcv_hdr_off;
 
 	memcpy(signature_req, hdr->Signature, SMB2_SIGNATURE_SIZE);
@@ -8207,25 +8239,26 @@ int smb2_check_sign_req(struct ksmbd_work *work)
  */
 void smb2_set_sign_rsp(struct ksmbd_work *work)
 {
-	struct smb2_hdr *hdr, *hdr_org;
+	struct smb2_hdr *hdr;
 	struct smb2_hdr *req_hdr;
 	char signature[SMB2_HMACSHA256_SIZE];
 	struct kvec iov[2];
 	size_t len;
 	int n_vec = 1;
 
-	hdr_org = hdr = work->response_buf;
+	hdr = smb2_get_msg(work->response_buf);
 	if (work->next_smb2_rsp_hdr_off)
 		hdr = ksmbd_resp_buf_next(work);
 
 	req_hdr = ksmbd_req_buf_next(work);
 
 	if (!work->next_smb2_rsp_hdr_off) {
-		len = get_rfc1002_len(hdr_org);
+		len = get_rfc1002_len(work->response_buf);
 		if (req_hdr->NextCommand)
 			len = ALIGN(len, 8);
 	} else {
-		len = get_rfc1002_len(hdr_org) - work->next_smb2_rsp_hdr_off;
+		len = get_rfc1002_len(work->response_buf) -
+			work->next_smb2_rsp_hdr_off;
 		len = ALIGN(len, 8);
 	}
 
@@ -8261,23 +8294,23 @@ int smb3_check_sign_req(struct ksmbd_work *work)
 {
 	struct ksmbd_conn *conn = work->conn;
 	char *signing_key;
-	struct smb2_hdr *hdr, *hdr_org;
+	struct smb2_hdr *hdr;
 	struct channel *chann;
 	char signature_req[SMB2_SIGNATURE_SIZE];
 	char signature[SMB2_CMACAES_SIZE];
 	struct kvec iov[1];
 	size_t len;
 
-	hdr_org = hdr = work->request_buf;
+	hdr = smb2_get_msg(work->request_buf);
 	if (work->next_smb2_rcv_hdr_off)
 		hdr = ksmbd_req_buf_next(work);
 
 	if (!hdr->NextCommand && !work->next_smb2_rcv_hdr_off)
-		len = be32_to_cpu(hdr_org->smb2_buf_length);
+		len = get_rfc1002_len(work->request_buf);
 	else if (hdr->NextCommand)
 		len = le32_to_cpu(hdr->NextCommand);
 	else
-		len = be32_to_cpu(hdr_org->smb2_buf_length) -
+		len = get_rfc1002_len(work->request_buf) -
 			work->next_smb2_rcv_hdr_off;
 
 	if (le16_to_cpu(hdr->Command) == SMB2_SESSION_SETUP_HE) {
@@ -8318,8 +8351,7 @@ int smb3_check_sign_req(struct ksmbd_work *work)
 void smb3_set_sign_rsp(struct ksmbd_work *work)
 {
 	struct ksmbd_conn *conn = work->conn;
-	struct smb2_hdr *req_hdr;
-	struct smb2_hdr *hdr, *hdr_org;
+	struct smb2_hdr *req_hdr, *hdr;
 	struct channel *chann;
 	char signature[SMB2_CMACAES_SIZE];
 	struct kvec iov[2];
@@ -8327,18 +8359,19 @@ void smb3_set_sign_rsp(struct ksmbd_work *work)
 	size_t len;
 	char *signing_key;
 
-	hdr_org = hdr = work->response_buf;
+	hdr = smb2_get_msg(work->response_buf);
 	if (work->next_smb2_rsp_hdr_off)
 		hdr = ksmbd_resp_buf_next(work);
 
 	req_hdr = ksmbd_req_buf_next(work);
 
 	if (!work->next_smb2_rsp_hdr_off) {
-		len = get_rfc1002_len(hdr_org);
+		len = get_rfc1002_len(work->response_buf);
 		if (req_hdr->NextCommand)
 			len = ALIGN(len, 8);
 	} else {
-		len = get_rfc1002_len(hdr_org) - work->next_smb2_rsp_hdr_off;
+		len = get_rfc1002_len(work->response_buf) -
+			work->next_smb2_rsp_hdr_off;
 		len = ALIGN(len, 8);
 	}
 
@@ -8391,7 +8424,7 @@ void smb3_preauth_hash_rsp(struct ksmbd_work *work)
 
 	if (le16_to_cpu(req->Command) == SMB2_NEGOTIATE_HE &&
 	    conn->preauth_info)
-		ksmbd_gen_preauth_integrity_hash(conn, (char *)rsp,
+		ksmbd_gen_preauth_integrity_hash(conn, work->response_buf,
 						 conn->preauth_info->Preauth_HashValue);
 
 	if (le16_to_cpu(rsp->Command) == SMB2_SESSION_SETUP_HE && sess) {
@@ -8409,35 +8442,34 @@ void smb3_preauth_hash_rsp(struct ksmbd_work *work)
 			if (!hash_value)
 				return;
 		}
-		ksmbd_gen_preauth_integrity_hash(conn, (char *)rsp,
+		ksmbd_gen_preauth_integrity_hash(conn, work->response_buf,
 						 hash_value);
 	}
 }
 
-static void fill_transform_hdr(struct smb2_transform_hdr *tr_hdr, char *old_buf,
-			       __le16 cipher_type)
+static void fill_transform_hdr(void *tr_buf, char *old_buf, __le16 cipher_type)
 {
-	struct smb2_hdr *hdr = (struct smb2_hdr *)old_buf;
+	struct smb2_transform_hdr *tr_hdr = tr_buf + 4;
+	struct smb2_hdr *hdr = smb2_get_msg(old_buf);
 	unsigned int orig_len = get_rfc1002_len(old_buf);
 
-	memset(tr_hdr, 0, sizeof(struct smb2_transform_hdr));
+	memset(tr_buf, 0, sizeof(struct smb2_transform_hdr) + 4);
 	tr_hdr->ProtocolId = SMB2_TRANSFORM_PROTO_NUM;
 	tr_hdr->OriginalMessageSize = cpu_to_le32(orig_len);
-	tr_hdr->Flags = cpu_to_le16(0x01);
+	tr_hdr->Flags = cpu_to_le16(TRANSFORM_FLAG_ENCRYPTED);
 	if (cipher_type == SMB2_ENCRYPTION_AES128_GCM ||
 	    cipher_type == SMB2_ENCRYPTION_AES256_GCM)
 		get_random_bytes(&tr_hdr->Nonce, SMB3_AES_GCM_NONCE);
 	else
 		get_random_bytes(&tr_hdr->Nonce, SMB3_AES_CCM_NONCE);
 	memcpy(&tr_hdr->SessionId, &hdr->SessionId, 8);
-	inc_rfc1001_len(tr_hdr, sizeof(struct smb2_transform_hdr) - 4);
-	inc_rfc1001_len(tr_hdr, orig_len);
+	inc_rfc1001_len(tr_buf, sizeof(struct smb2_transform_hdr));
+	inc_rfc1001_len(tr_buf, orig_len);
 }
 
 int smb3_encrypt_resp(struct ksmbd_work *work)
 {
 	char *buf = work->response_buf;
-	struct smb2_transform_hdr *tr_hdr;
 	struct kvec iov[3];
 	int rc = -ENOMEM;
 	int buf_size = 0, rq_nvec = 2 + (work->aux_payload_sz ? 1 : 0);
@@ -8445,15 +8477,15 @@ int smb3_encrypt_resp(struct ksmbd_work *work)
 	if (ARRAY_SIZE(iov) < rq_nvec)
 		return -ENOMEM;
 
-	tr_hdr = kzalloc(sizeof(struct smb2_transform_hdr), GFP_KERNEL);
-	if (!tr_hdr)
+	work->tr_buf = kzalloc(sizeof(struct smb2_transform_hdr) + 4, GFP_KERNEL);
+	if (!work->tr_buf)
 		return rc;
 
 	/* fill transform header */
-	fill_transform_hdr(tr_hdr, buf, work->conn->cipher_type);
+	fill_transform_hdr(work->tr_buf, buf, work->conn->cipher_type);
 
-	iov[0].iov_base = tr_hdr;
-	iov[0].iov_len = sizeof(struct smb2_transform_hdr);
+	iov[0].iov_base = work->tr_buf;
+	iov[0].iov_len = sizeof(struct smb2_transform_hdr) + 4;
 	buf_size += iov[0].iov_len - 4;
 
 	iov[1].iov_base = buf + 4;
@@ -8473,15 +8505,14 @@ int smb3_encrypt_resp(struct ksmbd_work *work)
 		return rc;
 
 	memmove(buf, iov[1].iov_base, iov[1].iov_len);
-	tr_hdr->smb2_buf_length = cpu_to_be32(buf_size);
-	work->tr_buf = tr_hdr;
+	*(__be32 *)work->tr_buf = cpu_to_be32(buf_size);
 
 	return rc;
 }
 
 bool smb3_is_transform_hdr(void *buf)
 {
-	struct smb2_transform_hdr *trhdr = buf;
+	struct smb2_transform_hdr *trhdr = smb2_get_msg(buf);
 
 	return trhdr->ProtocolId == SMB2_TRANSFORM_PROTO_NUM;
 }
@@ -8491,12 +8522,10 @@ int smb3_decrypt_req(struct ksmbd_work *work)
 	struct ksmbd_conn *conn = work->conn;
 	struct ksmbd_session *sess;
 	char *buf = work->request_buf;
-	struct smb2_hdr *hdr;
 	unsigned int pdu_length = get_rfc1002_len(buf);
 	struct kvec iov[2];
-	int buf_data_size = pdu_length + 4 -
-		sizeof(struct smb2_transform_hdr);
-	struct smb2_transform_hdr *tr_hdr = (struct smb2_transform_hdr *)buf;
+	int buf_data_size = pdu_length - sizeof(struct smb2_transform_hdr);
+	struct smb2_transform_hdr *tr_hdr = smb2_get_msg(buf);
 	int rc = 0;
 
 	if (buf_data_size < sizeof(struct smb2_hdr)) {
@@ -8518,16 +8547,15 @@ int smb3_decrypt_req(struct ksmbd_work *work)
 	}
 
 	iov[0].iov_base = buf;
-	iov[0].iov_len = sizeof(struct smb2_transform_hdr);
-	iov[1].iov_base = buf + sizeof(struct smb2_transform_hdr);
+	iov[0].iov_len = sizeof(struct smb2_transform_hdr) + 4;
+	iov[1].iov_base = buf + sizeof(struct smb2_transform_hdr) + 4;
 	iov[1].iov_len = buf_data_size;
 	rc = ksmbd_crypt_message(conn, iov, 2, 0);
 	if (rc)
 		return rc;
 
 	memmove(buf + 4, iov[1].iov_base, buf_data_size);
-	hdr = (struct smb2_hdr *)buf;
-	hdr->smb2_buf_length = cpu_to_be32(buf_data_size);
+	*(__be32 *)buf = cpu_to_be32(buf_data_size);
 
 	return rc;
 }
@@ -8535,7 +8563,7 @@ int smb3_decrypt_req(struct ksmbd_work *work)
 bool smb3_11_final_sess_setup_resp(struct ksmbd_work *work)
 {
 	struct ksmbd_conn *conn = work->conn;
-	struct smb2_hdr *rsp = work->response_buf;
+	struct smb2_hdr *rsp = smb2_get_msg(work->response_buf);
 
 	if (conn->dialect < SMB30_PROT_ID)
 		return false;
diff --git a/fs/ksmbd/smb2pdu.h b/fs/ksmbd/smb2pdu.h
index ff5a2f01d34a..4a3e4339d4c4 100644
--- a/fs/ksmbd/smb2pdu.h
+++ b/fs/ksmbd/smb2pdu.h
@@ -10,60 +10,6 @@
 #include "ntlmssp.h"
 #include "smbacl.h"
 
-/*
- * Note that, due to trying to use names similar to the protocol specifications,
- * there are many mixed case field names in the structures below.  Although
- * this does not match typical Linux kernel style, it is necessary to be
- * able to match against the protocol specfication.
- *
- * SMB2 commands
- * Some commands have minimal (wct=0,bcc=0), or uninteresting, responses
- * (ie no useful data other than the SMB error code itself) and are marked such.
- * Knowing this helps avoid response buffer allocations and copy in some cases.
- */
-
-/* List of commands in host endian */
-#define SMB2_NEGOTIATE_HE	0x0000
-#define SMB2_SESSION_SETUP_HE	0x0001
-#define SMB2_LOGOFF_HE		0x0002 /* trivial request/resp */
-#define SMB2_TREE_CONNECT_HE	0x0003
-#define SMB2_TREE_DISCONNECT_HE	0x0004 /* trivial req/resp */
-#define SMB2_CREATE_HE		0x0005
-#define SMB2_CLOSE_HE		0x0006
-#define SMB2_FLUSH_HE		0x0007 /* trivial resp */
-#define SMB2_READ_HE		0x0008
-#define SMB2_WRITE_HE		0x0009
-#define SMB2_LOCK_HE		0x000A
-#define SMB2_IOCTL_HE		0x000B
-#define SMB2_CANCEL_HE		0x000C
-#define SMB2_ECHO_HE		0x000D
-#define SMB2_QUERY_DIRECTORY_HE	0x000E
-#define SMB2_CHANGE_NOTIFY_HE	0x000F
-#define SMB2_QUERY_INFO_HE	0x0010
-#define SMB2_SET_INFO_HE	0x0011
-#define SMB2_OPLOCK_BREAK_HE	0x0012
-
-/* The same list in little endian */
-#define SMB2_NEGOTIATE		cpu_to_le16(SMB2_NEGOTIATE_HE)
-#define SMB2_SESSION_SETUP	cpu_to_le16(SMB2_SESSION_SETUP_HE)
-#define SMB2_LOGOFF		cpu_to_le16(SMB2_LOGOFF_HE)
-#define SMB2_TREE_CONNECT	cpu_to_le16(SMB2_TREE_CONNECT_HE)
-#define SMB2_TREE_DISCONNECT	cpu_to_le16(SMB2_TREE_DISCONNECT_HE)
-#define SMB2_CREATE		cpu_to_le16(SMB2_CREATE_HE)
-#define SMB2_CLOSE		cpu_to_le16(SMB2_CLOSE_HE)
-#define SMB2_FLUSH		cpu_to_le16(SMB2_FLUSH_HE)
-#define SMB2_READ		cpu_to_le16(SMB2_READ_HE)
-#define SMB2_WRITE		cpu_to_le16(SMB2_WRITE_HE)
-#define SMB2_LOCK		cpu_to_le16(SMB2_LOCK_HE)
-#define SMB2_IOCTL		cpu_to_le16(SMB2_IOCTL_HE)
-#define SMB2_CANCEL		cpu_to_le16(SMB2_CANCEL_HE)
-#define SMB2_ECHO		cpu_to_le16(SMB2_ECHO_HE)
-#define SMB2_QUERY_DIRECTORY	cpu_to_le16(SMB2_QUERY_DIRECTORY_HE)
-#define SMB2_CHANGE_NOTIFY	cpu_to_le16(SMB2_CHANGE_NOTIFY_HE)
-#define SMB2_QUERY_INFO		cpu_to_le16(SMB2_QUERY_INFO_HE)
-#define SMB2_SET_INFO		cpu_to_le16(SMB2_SET_INFO_HE)
-#define SMB2_OPLOCK_BREAK	cpu_to_le16(SMB2_OPLOCK_BREAK_HE)
-
 /*Create Action Flags*/
 #define FILE_SUPERSEDED                0x00000000
 #define FILE_OPENED            0x00000001
@@ -96,9 +42,6 @@
 /* SMB2 Max Credits */
 #define SMB2_MAX_CREDITS		8192
 
-#define SMB2_CLIENT_GUID_SIZE		16
-#define SMB2_CREATE_GUID_SIZE		16
-
 /* Maximum buffer size value we can send with 1 credit */
 #define SMB2_MAX_BUFFER_SIZE 65536
 
@@ -107,9 +50,6 @@
 /* BB FIXME - analyze following length BB */
 #define MAX_SMB2_HDR_SIZE 0x78 /* 4 len + 64 hdr + (2*24 wct) + 2 bct + 2 pad */
 
-#define SMB2_PROTO_NUMBER cpu_to_le32(0x424d53fe) /* 'B''M''S' */
-#define SMB2_TRANSFORM_PROTO_NUM cpu_to_le32(0x424d53fd)
-
 #define SMB21_DEFAULT_IOSIZE	(1024 * 1024)
 #define SMB3_DEFAULT_IOSIZE	(4 * 1024 * 1024)
 #define SMB3_DEFAULT_TRANS_SIZE	(1024 * 1024)
@@ -117,78 +57,6 @@
 #define SMB3_MAX_IOSIZE	(8 * 1024 * 1024)
 
 /*
- * SMB2 Header Definition
- *
- * "MBZ" :  Must be Zero
- * "BB"  :  BugBug, Something to check/review/analyze later
- * "PDU" :  "Protocol Data Unit" (ie a network "frame")
- *
- */
-
-#define __SMB2_HEADER_STRUCTURE_SIZE	64
-#define SMB2_HEADER_STRUCTURE_SIZE				\
-	cpu_to_le16(__SMB2_HEADER_STRUCTURE_SIZE)
-
-struct smb2_hdr {
-	__be32 smb2_buf_length;	/* big endian on wire */
-				/*
-				 * length is only two or three bytes - with
-				 * one or two byte type preceding it that MBZ
-				 */
-	__le32 ProtocolId;	/* 0xFE 'S' 'M' 'B' */
-	__le16 StructureSize;	/* 64 */
-	__le16 CreditCharge;	/* MBZ */
-	__le32 Status;		/* Error from server */
-	__le16 Command;
-	__le16 CreditRequest;	/* CreditResponse */
-	__le32 Flags;
-	__le32 NextCommand;
-	__le64 MessageId;
-	union {
-		struct {
-			__le32 ProcessId;
-			__le32  TreeId;
-		} __packed SyncId;
-		__le64  AsyncId;
-	} __packed Id;
-	__le64  SessionId;
-	__u8   Signature[16];
-} __packed;
-
-struct smb2_pdu {
-	struct smb2_hdr hdr;
-	__le16 StructureSize2; /* size of wct area (varies, request specific) */
-} __packed;
-
-#define SMB3_AES_CCM_NONCE 11
-#define SMB3_AES_GCM_NONCE 12
-
-struct smb2_transform_hdr {
-	__be32 smb2_buf_length; /* big endian on wire */
-	/*
-	 * length is only two or three bytes - with
-	 * one or two byte type preceding it that MBZ
-	 */
-	__le32 ProtocolId;      /* 0xFD 'S' 'M' 'B' */
-	__u8   Signature[16];
-	__u8   Nonce[16];
-	__le32 OriginalMessageSize;
-	__u16  Reserved1;
-	__le16 Flags; /* EncryptionAlgorithm */
-	__le64  SessionId;
-} __packed;
-
-/*
- *	SMB2 flag definitions
- */
-#define SMB2_FLAGS_SERVER_TO_REDIR	cpu_to_le32(0x00000001)
-#define SMB2_FLAGS_ASYNC_COMMAND	cpu_to_le32(0x00000002)
-#define SMB2_FLAGS_RELATED_OPERATIONS	cpu_to_le32(0x00000004)
-#define SMB2_FLAGS_SIGNED		cpu_to_le32(0x00000008)
-#define SMB2_FLAGS_DFS_OPERATIONS	cpu_to_le32(0x10000000)
-#define SMB2_FLAGS_REPLAY_OPERATIONS	cpu_to_le32(0x20000000)
-
-/*
  *	Definitions for SMB2 Protocol Data Units (network frames)
  *
  *  See MS-SMB2.PDF specification for protocol details.
@@ -209,425 +77,30 @@ struct smb2_err_rsp {
 	__u8   ErrorData[1];  /* variable length */
 } __packed;
 
-struct smb2_negotiate_req {
-	struct smb2_hdr hdr;
-	__le16 StructureSize; /* Must be 36 */
-	__le16 DialectCount;
-	__le16 SecurityMode;
-	__le16 Reserved;	/* MBZ */
-	__le32 Capabilities;
-	__u8   ClientGUID[SMB2_CLIENT_GUID_SIZE];
-	/* In SMB3.02 and earlier next three were MBZ le64 ClientStartTime */
-	__le32 NegotiateContextOffset; /* SMB3.1.1 only. MBZ earlier */
-	__le16 NegotiateContextCount;  /* SMB3.1.1 only. MBZ earlier */
-	__le16 Reserved2;
-	__le16 Dialects[1]; /* One dialect (vers=) at a time for now */
-} __packed;
-
-/* SecurityMode flags */
-#define SMB2_NEGOTIATE_SIGNING_ENABLED_LE	cpu_to_le16(0x0001)
-#define SMB2_NEGOTIATE_SIGNING_REQUIRED		0x0002
-#define SMB2_NEGOTIATE_SIGNING_REQUIRED_LE	cpu_to_le16(0x0002)
-/* Capabilities flags */
-#define SMB2_GLOBAL_CAP_DFS		0x00000001
-#define SMB2_GLOBAL_CAP_LEASING		0x00000002 /* Resp only New to SMB2.1 */
-#define SMB2_GLOBAL_CAP_LARGE_MTU	0X00000004 /* Resp only New to SMB2.1 */
-#define SMB2_GLOBAL_CAP_MULTI_CHANNEL	0x00000008 /* New to SMB3 */
-#define SMB2_GLOBAL_CAP_PERSISTENT_HANDLES 0x00000010 /* New to SMB3 */
-#define SMB2_GLOBAL_CAP_DIRECTORY_LEASING  0x00000020 /* New to SMB3 */
-#define SMB2_GLOBAL_CAP_ENCRYPTION	0x00000040 /* New to SMB3 */
-/* Internal types */
-#define SMB2_NT_FIND			0x00100000
-#define SMB2_LARGE_FILES		0x00200000
-
-#define SMB311_SALT_SIZE			32
-/* Hash Algorithm Types */
-#define SMB2_PREAUTH_INTEGRITY_SHA512	cpu_to_le16(0x0001)
-
-#define PREAUTH_HASHVALUE_SIZE		64
-
 struct preauth_integrity_info {
 	/* PreAuth integrity Hash ID */
 	__le16			Preauth_HashId;
 	/* PreAuth integrity Hash Value */
-	__u8			Preauth_HashValue[PREAUTH_HASHVALUE_SIZE];
+	__u8			Preauth_HashValue[SMB2_PREAUTH_HASH_SIZE];
 };
 
-/* offset is sizeof smb2_negotiate_rsp - 4 but rounded up to 8 bytes. */
+/* offset is sizeof smb2_negotiate_rsp but rounded up to 8 bytes. */
 #ifdef CONFIG_SMB_SERVER_KERBEROS5
-/* sizeof(struct smb2_negotiate_rsp) - 4 =
+/* sizeof(struct smb2_negotiate_rsp) =
  * header(64) + response(64) + GSS_LENGTH(96) + GSS_PADDING(0)
  */
 #define OFFSET_OF_NEG_CONTEXT	0xe0
 #else
-/* sizeof(struct smb2_negotiate_rsp) - 4 =
+/* sizeof(struct smb2_negotiate_rsp) =
  * header(64) + response(64) + GSS_LENGTH(74) + GSS_PADDING(6)
  */
 #define OFFSET_OF_NEG_CONTEXT	0xd0
 #endif
 
-#define SMB2_PREAUTH_INTEGRITY_CAPABILITIES	cpu_to_le16(1)
-#define SMB2_ENCRYPTION_CAPABILITIES		cpu_to_le16(2)
-#define SMB2_COMPRESSION_CAPABILITIES		cpu_to_le16(3)
-#define SMB2_NETNAME_NEGOTIATE_CONTEXT_ID	cpu_to_le16(5)
-#define SMB2_SIGNING_CAPABILITIES		cpu_to_le16(8)
-#define SMB2_POSIX_EXTENSIONS_AVAILABLE		cpu_to_le16(0x100)
-
-struct smb2_neg_context {
-	__le16  ContextType;
-	__le16  DataLength;
-	__le32  Reserved;
-	/* Followed by array of data */
-} __packed;
-
-struct smb2_preauth_neg_context {
-	__le16	ContextType; /* 1 */
-	__le16	DataLength;
-	__le32	Reserved;
-	__le16	HashAlgorithmCount; /* 1 */
-	__le16	SaltLength;
-	__le16	HashAlgorithms; /* HashAlgorithms[0] since only one defined */
-	__u8	Salt[SMB311_SALT_SIZE];
-} __packed;
-
-/* Encryption Algorithms Ciphers */
-#define SMB2_ENCRYPTION_AES128_CCM	cpu_to_le16(0x0001)
-#define SMB2_ENCRYPTION_AES128_GCM	cpu_to_le16(0x0002)
-#define SMB2_ENCRYPTION_AES256_CCM	cpu_to_le16(0x0003)
-#define SMB2_ENCRYPTION_AES256_GCM	cpu_to_le16(0x0004)
-
-struct smb2_encryption_neg_context {
-	__le16	ContextType; /* 2 */
-	__le16	DataLength;
-	__le32	Reserved;
-	/* CipherCount usally 2, but can be 3 when AES256-GCM enabled */
-	__le16	CipherCount; /* AES-128-GCM and AES-128-CCM by default */
-	__le16	Ciphers[];
-} __packed;
-
-#define SMB3_COMPRESS_NONE	cpu_to_le16(0x0000)
-#define SMB3_COMPRESS_LZNT1	cpu_to_le16(0x0001)
-#define SMB3_COMPRESS_LZ77	cpu_to_le16(0x0002)
-#define SMB3_COMPRESS_LZ77_HUFF	cpu_to_le16(0x0003)
-
-struct smb2_compression_ctx {
-	__le16	ContextType; /* 3 */
-	__le16  DataLength;
-	__le32	Reserved;
-	__le16	CompressionAlgorithmCount;
-	__u16	Padding;
-	__le32	Reserved1;
-	__le16	CompressionAlgorithms[];
-} __packed;
-
-#define POSIX_CTXT_DATA_LEN     16
-struct smb2_posix_neg_context {
-	__le16	ContextType; /* 0x100 */
-	__le16	DataLength;
-	__le32	Reserved;
-	__u8	Name[16]; /* POSIX ctxt GUID 93AD25509CB411E7B42383DE968BCD7C */
-} __packed;
-
-struct smb2_netname_neg_context {
-	__le16	ContextType; /* 0x100 */
-	__le16	DataLength;
-	__le32	Reserved;
-	__le16	NetName[]; /* hostname of target converted to UCS-2 */
-} __packed;
-
-/* Signing algorithms */
-#define SIGNING_ALG_HMAC_SHA256		cpu_to_le16(0)
-#define SIGNING_ALG_AES_CMAC		cpu_to_le16(1)
-#define SIGNING_ALG_AES_GMAC		cpu_to_le16(2)
-
-struct smb2_signing_capabilities {
-	__le16	ContextType; /* 8 */
-	__le16	DataLength;
-	__le32	Reserved;
-	__le16	SigningAlgorithmCount;
-	__le16	SigningAlgorithms[];
-} __packed;
-
-struct smb2_negotiate_rsp {
-	struct smb2_hdr hdr;
-	__le16 StructureSize;	/* Must be 65 */
-	__le16 SecurityMode;
-	__le16 DialectRevision;
-	__le16 NegotiateContextCount; /* Prior to SMB3.1.1 was Reserved & MBZ */
-	__u8   ServerGUID[16];
-	__le32 Capabilities;
-	__le32 MaxTransactSize;
-	__le32 MaxReadSize;
-	__le32 MaxWriteSize;
-	__le64 SystemTime;	/* MBZ */
-	__le64 ServerStartTime;
-	__le16 SecurityBufferOffset;
-	__le16 SecurityBufferLength;
-	__le32 NegotiateContextOffset;	/* Pre:SMB3.1.1 was reserved/ignored */
-	__u8   Buffer[1];	/* variable length GSS security buffer */
-} __packed;
-
-/* Flags */
-#define SMB2_SESSION_REQ_FLAG_BINDING		0x01
-#define SMB2_SESSION_REQ_FLAG_ENCRYPT_DATA	0x04
-
 #define SMB2_SESSION_EXPIRED		(0)
 #define SMB2_SESSION_IN_PROGRESS	BIT(0)
 #define SMB2_SESSION_VALID		BIT(1)
 
-/* Flags */
-#define SMB2_SESSION_REQ_FLAG_BINDING		0x01
-#define SMB2_SESSION_REQ_FLAG_ENCRYPT_DATA	0x04
-
-struct smb2_sess_setup_req {
-	struct smb2_hdr hdr;
-	__le16 StructureSize; /* Must be 25 */
-	__u8   Flags;
-	__u8   SecurityMode;
-	__le32 Capabilities;
-	__le32 Channel;
-	__le16 SecurityBufferOffset;
-	__le16 SecurityBufferLength;
-	__le64 PreviousSessionId;
-	__u8   Buffer[1];	/* variable length GSS security buffer */
-} __packed;
-
-/* Flags/Reserved for SMB3.1.1 */
-#define SMB2_SHAREFLAG_CLUSTER_RECONNECT	0x0001
-
-/* Currently defined SessionFlags */
-#define SMB2_SESSION_FLAG_IS_GUEST_LE		cpu_to_le16(0x0001)
-#define SMB2_SESSION_FLAG_IS_NULL_LE		cpu_to_le16(0x0002)
-#define SMB2_SESSION_FLAG_ENCRYPT_DATA_LE	cpu_to_le16(0x0004)
-struct smb2_sess_setup_rsp {
-	struct smb2_hdr hdr;
-	__le16 StructureSize; /* Must be 9 */
-	__le16 SessionFlags;
-	__le16 SecurityBufferOffset;
-	__le16 SecurityBufferLength;
-	__u8   Buffer[1];	/* variable length GSS security buffer */
-} __packed;
-
-struct smb2_logoff_req {
-	struct smb2_hdr hdr;
-	__le16 StructureSize;	/* Must be 4 */
-	__le16 Reserved;
-} __packed;
-
-struct smb2_logoff_rsp {
-	struct smb2_hdr hdr;
-	__le16 StructureSize;	/* Must be 4 */
-	__le16 Reserved;
-} __packed;
-
-struct smb2_tree_connect_req {
-	struct smb2_hdr hdr;
-	__le16 StructureSize;	/* Must be 9 */
-	__le16 Reserved;	/* Flags in SMB3.1.1 */
-	__le16 PathOffset;
-	__le16 PathLength;
-	__u8   Buffer[1];	/* variable length */
-} __packed;
-
-struct smb2_tree_connect_rsp {
-	struct smb2_hdr hdr;
-	__le16 StructureSize;	/* Must be 16 */
-	__u8   ShareType;  /* see below */
-	__u8   Reserved;
-	__le32 ShareFlags; /* see below */
-	__le32 Capabilities; /* see below */
-	__le32 MaximalAccess;
-} __packed;
-
-/* Possible ShareType values */
-#define SMB2_SHARE_TYPE_DISK	0x01
-#define SMB2_SHARE_TYPE_PIPE	0x02
-#define	SMB2_SHARE_TYPE_PRINT	0x03
-
-/*
- * Possible ShareFlags - exactly one and only one of the first 4 caching flags
- * must be set (any of the remaining, SHI1005, flags may be set individually
- * or in combination.
- */
-#define SMB2_SHAREFLAG_MANUAL_CACHING			0x00000000
-#define SMB2_SHAREFLAG_AUTO_CACHING			0x00000010
-#define SMB2_SHAREFLAG_VDO_CACHING			0x00000020
-#define SMB2_SHAREFLAG_NO_CACHING			0x00000030
-#define SHI1005_FLAGS_DFS				0x00000001
-#define SHI1005_FLAGS_DFS_ROOT				0x00000002
-#define SHI1005_FLAGS_RESTRICT_EXCLUSIVE_OPENS		0x00000100
-#define SHI1005_FLAGS_FORCE_SHARED_DELETE		0x00000200
-#define SHI1005_FLAGS_ALLOW_NAMESPACE_CACHING		0x00000400
-#define SHI1005_FLAGS_ACCESS_BASED_DIRECTORY_ENUM	0x00000800
-#define SHI1005_FLAGS_FORCE_LEVELII_OPLOCK		0x00001000
-#define SHI1005_FLAGS_ENABLE_HASH			0x00002000
-
-/* Possible share capabilities */
-#define SMB2_SHARE_CAP_DFS	cpu_to_le32(0x00000008)
-
-struct smb2_tree_disconnect_req {
-	struct smb2_hdr hdr;
-	__le16 StructureSize;	/* Must be 4 */
-	__le16 Reserved;
-} __packed;
-
-struct smb2_tree_disconnect_rsp {
-	struct smb2_hdr hdr;
-	__le16 StructureSize;	/* Must be 4 */
-	__le16 Reserved;
-} __packed;
-
-#define ATTR_READONLY_LE	cpu_to_le32(ATTR_READONLY)
-#define ATTR_HIDDEN_LE		cpu_to_le32(ATTR_HIDDEN)
-#define ATTR_SYSTEM_LE		cpu_to_le32(ATTR_SYSTEM)
-#define ATTR_DIRECTORY_LE	cpu_to_le32(ATTR_DIRECTORY)
-#define ATTR_ARCHIVE_LE		cpu_to_le32(ATTR_ARCHIVE)
-#define ATTR_NORMAL_LE		cpu_to_le32(ATTR_NORMAL)
-#define ATTR_TEMPORARY_LE	cpu_to_le32(ATTR_TEMPORARY)
-#define ATTR_SPARSE_FILE_LE	cpu_to_le32(ATTR_SPARSE)
-#define ATTR_REPARSE_POINT_LE	cpu_to_le32(ATTR_REPARSE)
-#define ATTR_COMPRESSED_LE	cpu_to_le32(ATTR_COMPRESSED)
-#define ATTR_OFFLINE_LE		cpu_to_le32(ATTR_OFFLINE)
-#define ATTR_NOT_CONTENT_INDEXED_LE	cpu_to_le32(ATTR_NOT_CONTENT_INDEXED)
-#define ATTR_ENCRYPTED_LE	cpu_to_le32(ATTR_ENCRYPTED)
-#define ATTR_INTEGRITY_STREAML_LE	cpu_to_le32(0x00008000)
-#define ATTR_NO_SCRUB_DATA_LE	cpu_to_le32(0x00020000)
-#define ATTR_MASK_LE		cpu_to_le32(0x00007FB7)
-
-/* Oplock levels */
-#define SMB2_OPLOCK_LEVEL_NONE		0x00
-#define SMB2_OPLOCK_LEVEL_II		0x01
-#define SMB2_OPLOCK_LEVEL_EXCLUSIVE	0x08
-#define SMB2_OPLOCK_LEVEL_BATCH		0x09
-#define SMB2_OPLOCK_LEVEL_LEASE		0xFF
-/* Non-spec internal type */
-#define SMB2_OPLOCK_LEVEL_NOCHANGE	0x99
-
-/* Desired Access Flags */
-#define FILE_READ_DATA_LE		cpu_to_le32(0x00000001)
-#define FILE_LIST_DIRECTORY_LE		cpu_to_le32(0x00000001)
-#define FILE_WRITE_DATA_LE		cpu_to_le32(0x00000002)
-#define FILE_ADD_FILE_LE		cpu_to_le32(0x00000002)
-#define FILE_APPEND_DATA_LE		cpu_to_le32(0x00000004)
-#define FILE_ADD_SUBDIRECTORY_LE	cpu_to_le32(0x00000004)
-#define FILE_READ_EA_LE			cpu_to_le32(0x00000008)
-#define FILE_WRITE_EA_LE		cpu_to_le32(0x00000010)
-#define FILE_EXECUTE_LE			cpu_to_le32(0x00000020)
-#define FILE_TRAVERSE_LE		cpu_to_le32(0x00000020)
-#define FILE_DELETE_CHILD_LE		cpu_to_le32(0x00000040)
-#define FILE_READ_ATTRIBUTES_LE		cpu_to_le32(0x00000080)
-#define FILE_WRITE_ATTRIBUTES_LE	cpu_to_le32(0x00000100)
-#define FILE_DELETE_LE			cpu_to_le32(0x00010000)
-#define FILE_READ_CONTROL_LE		cpu_to_le32(0x00020000)
-#define FILE_WRITE_DAC_LE		cpu_to_le32(0x00040000)
-#define FILE_WRITE_OWNER_LE		cpu_to_le32(0x00080000)
-#define FILE_SYNCHRONIZE_LE		cpu_to_le32(0x00100000)
-#define FILE_ACCESS_SYSTEM_SECURITY_LE	cpu_to_le32(0x01000000)
-#define FILE_MAXIMAL_ACCESS_LE		cpu_to_le32(0x02000000)
-#define FILE_GENERIC_ALL_LE		cpu_to_le32(0x10000000)
-#define FILE_GENERIC_EXECUTE_LE		cpu_to_le32(0x20000000)
-#define FILE_GENERIC_WRITE_LE		cpu_to_le32(0x40000000)
-#define FILE_GENERIC_READ_LE		cpu_to_le32(0x80000000)
-#define DESIRED_ACCESS_MASK		cpu_to_le32(0xF21F01FF)
-
-/* ShareAccess Flags */
-#define FILE_SHARE_READ_LE		cpu_to_le32(0x00000001)
-#define FILE_SHARE_WRITE_LE		cpu_to_le32(0x00000002)
-#define FILE_SHARE_DELETE_LE		cpu_to_le32(0x00000004)
-#define FILE_SHARE_ALL_LE		cpu_to_le32(0x00000007)
-
-/* CreateDisposition Flags */
-#define FILE_SUPERSEDE_LE		cpu_to_le32(0x00000000)
-#define FILE_OPEN_LE			cpu_to_le32(0x00000001)
-#define FILE_CREATE_LE			cpu_to_le32(0x00000002)
-#define	FILE_OPEN_IF_LE			cpu_to_le32(0x00000003)
-#define FILE_OVERWRITE_LE		cpu_to_le32(0x00000004)
-#define FILE_OVERWRITE_IF_LE		cpu_to_le32(0x00000005)
-#define FILE_CREATE_MASK_LE		cpu_to_le32(0x00000007)
-
-#define FILE_READ_DESIRED_ACCESS_LE	(FILE_READ_DATA_LE |		\
-					FILE_READ_EA_LE |		\
-					FILE_GENERIC_READ_LE)
-#define FILE_WRITE_DESIRE_ACCESS_LE	(FILE_WRITE_DATA_LE |		\
-					FILE_APPEND_DATA_LE |		\
-					FILE_WRITE_EA_LE |		\
-					FILE_WRITE_ATTRIBUTES_LE |	\
-					FILE_GENERIC_WRITE_LE)
-
-/* Impersonation Levels */
-#define IL_ANONYMOUS_LE		cpu_to_le32(0x00000000)
-#define IL_IDENTIFICATION_LE	cpu_to_le32(0x00000001)
-#define IL_IMPERSONATION_LE	cpu_to_le32(0x00000002)
-#define IL_DELEGATE_LE		cpu_to_le32(0x00000003)
-
-/* Create Context Values */
-#define SMB2_CREATE_EA_BUFFER			"ExtA" /* extended attributes */
-#define SMB2_CREATE_SD_BUFFER			"SecD" /* security descriptor */
-#define SMB2_CREATE_DURABLE_HANDLE_REQUEST	"DHnQ"
-#define SMB2_CREATE_DURABLE_HANDLE_RECONNECT	"DHnC"
-#define SMB2_CREATE_ALLOCATION_SIZE		"AlSi"
-#define SMB2_CREATE_QUERY_MAXIMAL_ACCESS_REQUEST "MxAc"
-#define SMB2_CREATE_TIMEWARP_REQUEST		"TWrp"
-#define SMB2_CREATE_QUERY_ON_DISK_ID		"QFid"
-#define SMB2_CREATE_REQUEST_LEASE		"RqLs"
-#define SMB2_CREATE_DURABLE_HANDLE_REQUEST_V2   "DH2Q"
-#define SMB2_CREATE_DURABLE_HANDLE_RECONNECT_V2 "DH2C"
-#define SMB2_CREATE_APP_INSTANCE_ID     "\x45\xBC\xA6\x6A\xEF\xA7\xF7\x4A\x90\x08\xFA\x46\x2E\x14\x4D\x74"
- #define SMB2_CREATE_APP_INSTANCE_VERSION	"\xB9\x82\xD0\xB7\x3B\x56\x07\x4F\xA0\x7B\x52\x4A\x81\x16\xA0\x10"
-#define SVHDX_OPEN_DEVICE_CONTEXT       0x83CE6F1AD851E0986E34401CC9BCFCE9
-#define SMB2_CREATE_TAG_POSIX		"\x93\xAD\x25\x50\x9C\xB4\x11\xE7\xB4\x23\x83\xDE\x96\x8B\xCD\x7C"
-
-struct smb2_create_req {
-	struct smb2_hdr hdr;
-	__le16 StructureSize;	/* Must be 57 */
-	__u8   SecurityFlags;
-	__u8   RequestedOplockLevel;
-	__le32 ImpersonationLevel;
-	__le64 SmbCreateFlags;
-	__le64 Reserved;
-	__le32 DesiredAccess;
-	__le32 FileAttributes;
-	__le32 ShareAccess;
-	__le32 CreateDisposition;
-	__le32 CreateOptions;
-	__le16 NameOffset;
-	__le16 NameLength;
-	__le32 CreateContextsOffset;
-	__le32 CreateContextsLength;
-	__u8   Buffer[0];
-} __packed;
-
-struct smb2_create_rsp {
-	struct smb2_hdr hdr;
-	__le16 StructureSize;	/* Must be 89 */
-	__u8   OplockLevel;
-	__u8   Reserved;
-	__le32 CreateAction;
-	__le64 CreationTime;
-	__le64 LastAccessTime;
-	__le64 LastWriteTime;
-	__le64 ChangeTime;
-	__le64 AllocationSize;
-	__le64 EndofFile;
-	__le32 FileAttributes;
-	__le32 Reserved2;
-	__le64  PersistentFileId;
-	__le64  VolatileFileId;
-	__le32 CreateContextsOffset;
-	__le32 CreateContextsLength;
-	__u8   Buffer[1];
-} __packed;
-
-struct create_context {
-	__le32 Next;
-	__le16 NameOffset;
-	__le16 NameLength;
-	__le16 Reserved;
-	__le16 DataOffset;
-	__le32 DataLength;
-	__u8 Buffer[0];
-} __packed;
-
 struct create_durable_req_v2 {
 	struct create_context ccontext;
 	__u8   Name[8];
@@ -743,22 +216,21 @@ struct create_posix_rsp {
 
 #define SMB2_LEASE_FLAG_BREAK_IN_PROGRESS_LE	cpu_to_le32(0x02)
 
+#define SMB2_LEASE_KEY_SIZE			16
+
 struct lease_context {
-	__le64 LeaseKeyLow;
-	__le64 LeaseKeyHigh;
+	__u8 LeaseKey[SMB2_LEASE_KEY_SIZE];
 	__le32 LeaseState;
 	__le32 LeaseFlags;
 	__le64 LeaseDuration;
 } __packed;
 
 struct lease_context_v2 {
-	__le64 LeaseKeyLow;
-	__le64 LeaseKeyHigh;
+	__u8 LeaseKey[SMB2_LEASE_KEY_SIZE];
 	__le32 LeaseState;
 	__le32 LeaseFlags;
 	__le64 LeaseDuration;
-	__le64 ParentLeaseKeyLow;
-	__le64 ParentLeaseKeyHigh;
+	__u8 ParentLeaseKey[SMB2_LEASE_KEY_SIZE];
 	__le16 Epoch;
 	__le16 Reserved;
 } __packed;
@@ -776,114 +248,12 @@ struct create_lease_v2 {
 	__u8   Pad[4];
 } __packed;
 
-/* Currently defined values for close flags */
-#define SMB2_CLOSE_FLAG_POSTQUERY_ATTRIB	cpu_to_le16(0x0001)
-struct smb2_close_req {
-	struct smb2_hdr hdr;
-	__le16 StructureSize;	/* Must be 24 */
-	__le16 Flags;
-	__le32 Reserved;
-	__le64  PersistentFileId;
-	__le64  VolatileFileId;
-} __packed;
-
-struct smb2_close_rsp {
-	struct smb2_hdr hdr;
-	__le16 StructureSize; /* 60 */
-	__le16 Flags;
-	__le32 Reserved;
-	__le64 CreationTime;
-	__le64 LastAccessTime;
-	__le64 LastWriteTime;
-	__le64 ChangeTime;
-	__le64 AllocationSize;	/* Beginning of FILE_STANDARD_INFO equivalent */
-	__le64 EndOfFile;
-	__le32 Attributes;
-} __packed;
-
-struct smb2_flush_req {
-	struct smb2_hdr hdr;
-	__le16 StructureSize;	/* Must be 24 */
-	__le16 Reserved1;
-	__le32 Reserved2;
-	__le64  PersistentFileId;
-	__le64  VolatileFileId;
-} __packed;
-
-struct smb2_flush_rsp {
-	struct smb2_hdr hdr;
-	__le16 StructureSize;
-	__le16 Reserved;
-} __packed;
-
 struct smb2_buffer_desc_v1 {
 	__le64 offset;
 	__le32 token;
 	__le32 length;
 } __packed;
 
-#define SMB2_CHANNEL_NONE		cpu_to_le32(0x00000000)
-#define SMB2_CHANNEL_RDMA_V1		cpu_to_le32(0x00000001)
-#define SMB2_CHANNEL_RDMA_V1_INVALIDATE cpu_to_le32(0x00000002)
-
-struct smb2_read_req {
-	struct smb2_hdr hdr;
-	__le16 StructureSize; /* Must be 49 */
-	__u8   Padding; /* offset from start of SMB2 header to place read */
-	__u8   Reserved;
-	__le32 Length;
-	__le64 Offset;
-	__le64  PersistentFileId;
-	__le64  VolatileFileId;
-	__le32 MinimumCount;
-	__le32 Channel; /* Reserved MBZ */
-	__le32 RemainingBytes;
-	__le16 ReadChannelInfoOffset; /* Reserved MBZ */
-	__le16 ReadChannelInfoLength; /* Reserved MBZ */
-	__u8   Buffer[1];
-} __packed;
-
-struct smb2_read_rsp {
-	struct smb2_hdr hdr;
-	__le16 StructureSize; /* Must be 17 */
-	__u8   DataOffset;
-	__u8   Reserved;
-	__le32 DataLength;
-	__le32 DataRemaining;
-	__u32  Reserved2;
-	__u8   Buffer[1];
-} __packed;
-
-/* For write request Flags field below the following flag is defined: */
-#define SMB2_WRITEFLAG_WRITE_THROUGH 0x00000001
-
-struct smb2_write_req {
-	struct smb2_hdr hdr;
-	__le16 StructureSize; /* Must be 49 */
-	__le16 DataOffset; /* offset from start of SMB2 header to write data */
-	__le32 Length;
-	__le64 Offset;
-	__le64  PersistentFileId;
-	__le64  VolatileFileId;
-	__le32 Channel; /* Reserved MBZ */
-	__le32 RemainingBytes;
-	__le16 WriteChannelInfoOffset; /* Reserved MBZ */
-	__le16 WriteChannelInfoLength; /* Reserved MBZ */
-	__le32 Flags;
-	__u8   Buffer[1];
-} __packed;
-
-struct smb2_write_rsp {
-	struct smb2_hdr hdr;
-	__le16 StructureSize; /* Must be 17 */
-	__u8   DataOffset;
-	__u8   Reserved;
-	__le32 DataLength;
-	__le32 DataRemaining;
-	__u32  Reserved2;
-	__u8   Buffer[1];
-} __packed;
-
 #define SMB2_0_IOCTL_IS_FSCTL 0x00000001
 
 struct duplicate_extents_to_file {
@@ -1033,43 +403,6 @@ struct reparse_data_buffer {
 	__u8	DataBuffer[]; /* Variable Length */
 } __packed;
 
-/* Completion Filter flags for Notify */
-#define FILE_NOTIFY_CHANGE_FILE_NAME	0x00000001
-#define FILE_NOTIFY_CHANGE_DIR_NAME	0x00000002
-#define FILE_NOTIFY_CHANGE_NAME		0x00000003
-#define FILE_NOTIFY_CHANGE_ATTRIBUTES	0x00000004
-#define FILE_NOTIFY_CHANGE_SIZE		0x00000008
-#define FILE_NOTIFY_CHANGE_LAST_WRITE	0x00000010
-#define FILE_NOTIFY_CHANGE_LAST_ACCESS	0x00000020
-#define FILE_NOTIFY_CHANGE_CREATION	0x00000040
-#define FILE_NOTIFY_CHANGE_EA		0x00000080
-#define FILE_NOTIFY_CHANGE_SECURITY	0x00000100
-#define FILE_NOTIFY_CHANGE_STREAM_NAME	0x00000200
-#define FILE_NOTIFY_CHANGE_STREAM_SIZE	0x00000400
-#define FILE_NOTIFY_CHANGE_STREAM_WRITE	0x00000800
-
-/* Flags */
-#define SMB2_WATCH_TREE	0x0001
-
-struct smb2_notify_req {
-	struct smb2_hdr hdr;
-	__le16 StructureSize; /* Must be 32 */
-	__le16 Flags;
-	__le32 OutputBufferLength;
-	__le64 PersistentFileId;
-	__le64 VolatileFileId;
-	__u32 CompletionFileter;
-	__u32 Reserved;
-} __packed;
-
-struct smb2_notify_rsp {
-	struct smb2_hdr hdr;
-	__le16 StructureSize; /* Must be 9 */
-	__le16 OutputBufferOffset;
-	__le32 OutputBufferLength;
-	__u8 Buffer[1];
-} __packed;
-
 /* SMB2 Notify Action Flags */
 #define FILE_ACTION_ADDED		0x00000001
 #define FILE_ACTION_REMOVED		0x00000002
@@ -1528,7 +861,7 @@ struct smb2_file_pos_info {
 	__le64 CurrentByteOffset;
 } __packed;
 
-#define FILE_MODE_INFO_MASK cpu_to_le32(0x0000103e)
+#define FILE_MODE_INFO_MASK cpu_to_le32(0x0000100e)
 
 struct smb2_file_mode_info {
 	__le32 Mode;
@@ -1705,4 +1038,13 @@ int smb2_ioctl(struct ksmbd_work *work);
 int smb2_oplock_break(struct ksmbd_work *work);
 int smb2_notify(struct ksmbd_work *ksmbd_work);
 
+/*
+ * Get the body of the smb2 message excluding the 4 byte rfc1002 headers
+ * from request/response buffer.
+ */
+static inline void *smb2_get_msg(void *buf)
+{
+	return buf + 4;
+}
+
 #endif	/* _SMB2PDU_H */
diff --git a/fs/ksmbd/smb_common.c b/fs/ksmbd/smb_common.c
index 707490ab1f4c..ef7f42b0290a 100644
--- a/fs/ksmbd/smb_common.c
+++ b/fs/ksmbd/smb_common.c
@@ -132,7 +132,7 @@ int ksmbd_lookup_protocol_idx(char *str)
  */
 int ksmbd_verify_smb_message(struct ksmbd_work *work)
 {
-	struct smb2_hdr *smb2_hdr = work->request_buf + work->next_smb2_rcv_hdr_off;
+	struct smb2_hdr *smb2_hdr = ksmbd_req_buf_next(work);
 	struct smb_hdr *hdr;
 
 	if (smb2_hdr->ProtocolId == SMB2_PROTO_NUMBER)
@@ -239,14 +239,14 @@ int ksmbd_lookup_dialect_by_id(__le16 *cli_dialects, __le16 dialects_count)
 static int ksmbd_negotiate_smb_dialect(void *buf)
 {
 	int smb_buf_length = get_rfc1002_len(buf);
-	__le32 proto = ((struct smb2_hdr *)buf)->ProtocolId;
+	__le32 proto = ((struct smb2_hdr *)smb2_get_msg(buf))->ProtocolId;
 
 	if (proto == SMB2_PROTO_NUMBER) {
 		struct smb2_negotiate_req *req;
 		int smb2_neg_size =
-			offsetof(struct smb2_negotiate_req, Dialects) - 4;
+			offsetof(struct smb2_negotiate_req, Dialects);
 
-		req = (struct smb2_negotiate_req *)buf;
+		req = (struct smb2_negotiate_req *)smb2_get_msg(buf);
 		if (smb2_neg_size > smb_buf_length)
 			goto err_out;
 
@@ -445,11 +445,12 @@ int ksmbd_smb_negotiate_common(struct ksmbd_work *work, unsigned int command)
 	struct ksmbd_conn *conn = work->conn;
 	int ret;
 
-	conn->dialect = ksmbd_negotiate_smb_dialect(work->request_buf);
+	conn->dialect =
+		ksmbd_negotiate_smb_dialect(work->request_buf);
 	ksmbd_debug(SMB, "conn->dialect 0x%x\n", conn->dialect);
 
 	if (command == SMB2_NEGOTIATE_HE) {
-		struct smb2_hdr *smb2_hdr = work->request_buf;
+		struct smb2_hdr *smb2_hdr = smb2_get_msg(work->request_buf);
 
 		if (smb2_hdr->ProtocolId != SMB2_PROTO_NUMBER) {
 			ksmbd_debug(SMB, "Downgrade to SMB1 negotiation\n");
diff --git a/fs/ksmbd/smb_common.h b/fs/ksmbd/smb_common.h
index 6e79e7577f6b..50590842b651 100644
--- a/fs/ksmbd/smb_common.h
+++ b/fs/ksmbd/smb_common.h
@@ -10,6 +10,7 @@
 
 #include "glob.h"
 #include "nterr.h"
+#include "../smbfs_common/smb2pdu.h"
 #include "smb2pdu.h"
 
 /* ksmbd's Specific ERRNO */
@@ -32,17 +33,6 @@
 #define SMB302_VERSION_STRING	"3.02"
 #define SMB311_VERSION_STRING	"3.1.1"
 
-/* Dialects */
-#define SMB10_PROT_ID		0x00
-#define SMB20_PROT_ID		0x0202
-#define SMB21_PROT_ID		0x0210
-/* multi-protocol negotiate request */
-#define SMB2X_PROT_ID		0x02FF
-#define SMB30_PROT_ID		0x0300
-#define SMB302_PROT_ID		0x0302
-#define SMB311_PROT_ID		0x0311
-#define BAD_PROT_ID		0xFFFF
-
 #define SMB_ECHO_INTERVAL	(60 * HZ)
 
 #define CIFS_DEFAULT_IOSIZE	(64 * 1024)
@@ -59,21 +49,6 @@
 /*
  * File Attribute flags
  */
-#define ATTR_READONLY			0x0001
-#define ATTR_HIDDEN			0x0002
-#define ATTR_SYSTEM			0x0004
-#define ATTR_VOLUME			0x0008
-#define ATTR_DIRECTORY			0x0010
-#define ATTR_ARCHIVE			0x0020
-#define ATTR_DEVICE			0x0040
-#define ATTR_NORMAL			0x0080
-#define ATTR_TEMPORARY			0x0100
-#define ATTR_SPARSE			0x0200
-#define ATTR_REPARSE			0x0400
-#define ATTR_COMPRESSED			0x0800
-#define ATTR_OFFLINE			0x1000
-#define ATTR_NOT_CONTENT_INDEXED	0x2000
-#define ATTR_ENCRYPTED			0x4000
 #define ATTR_POSIX_SEMANTICS		0x01000000
 #define ATTR_BACKUP_SEMANTICS		0x02000000
 #define ATTR_DELETE_ON_CLOSE		0x04000000
@@ -82,23 +57,6 @@
 #define ATTR_NO_BUFFERING		0x20000000
 #define ATTR_WRITE_THROUGH		0x80000000
 
-#define ATTR_READONLY_LE		cpu_to_le32(ATTR_READONLY)
-#define ATTR_HIDDEN_LE			cpu_to_le32(ATTR_HIDDEN)
-#define ATTR_SYSTEM_LE			cpu_to_le32(ATTR_SYSTEM)
-#define ATTR_DIRECTORY_LE		cpu_to_le32(ATTR_DIRECTORY)
-#define ATTR_ARCHIVE_LE			cpu_to_le32(ATTR_ARCHIVE)
-#define ATTR_NORMAL_LE			cpu_to_le32(ATTR_NORMAL)
-#define ATTR_TEMPORARY_LE		cpu_to_le32(ATTR_TEMPORARY)
-#define ATTR_SPARSE_FILE_LE		cpu_to_le32(ATTR_SPARSE)
-#define ATTR_REPARSE_POINT_LE		cpu_to_le32(ATTR_REPARSE)
-#define ATTR_COMPRESSED_LE		cpu_to_le32(ATTR_COMPRESSED)
-#define ATTR_OFFLINE_LE			cpu_to_le32(ATTR_OFFLINE)
-#define ATTR_NOT_CONTENT_INDEXED_LE	cpu_to_le32(ATTR_NOT_CONTENT_INDEXED)
-#define ATTR_ENCRYPTED_LE		cpu_to_le32(ATTR_ENCRYPTED)
-#define ATTR_INTEGRITY_STREAML_LE	cpu_to_le32(0x00008000)
-#define ATTR_NO_SCRUB_DATA_LE		cpu_to_le32(0x00020000)
-#define ATTR_MASK_LE			cpu_to_le32(0x00007FB7)
-
 /* List of FileSystemAttributes - see 2.5.1 of MS-FSCC */
 #define FILE_SUPPORTS_SPARSE_VDL	0x10000000 /* faster nonsparse extend */
 #define FILE_SUPPORTS_BLOCK_REFCOUNTING	0x08000000 /* allow ioctl dup extents */
@@ -160,11 +118,6 @@
 /* file_execute, file_read_attributes*/
 /* write_dac, and delete.           */
 
-#define FILE_READ_RIGHTS (FILE_READ_DATA | FILE_READ_EA | FILE_READ_ATTRIBUTES)
-#define FILE_WRITE_RIGHTS (FILE_WRITE_DATA | FILE_APPEND_DATA \
-		| FILE_WRITE_EA | FILE_WRITE_ATTRIBUTES)
-#define FILE_EXEC_RIGHTS (FILE_EXECUTE)
-
 #define SET_FILE_READ_RIGHTS (FILE_READ_DATA | FILE_READ_EA \
 		| FILE_READ_ATTRIBUTES \
 		| DELETE | READ_CONTROL | WRITE_DAC \
@@ -477,12 +430,6 @@ struct smb_version_cmds {
 	int (*proc)(struct ksmbd_work *swork);
 };
 
-static inline size_t
-smb2_hdr_size_no_buflen(struct smb_version_values *vals)
-{
-	return vals->header_size - 4;
-}
-
 int ksmbd_min_protocol(void);
 int ksmbd_max_protocol(void);
 
diff --git a/fs/ksmbd/transport_rdma.c b/fs/ksmbd/transport_rdma.c
index a2fd5a4d4cd5..7e57cbb0bb35 100644
--- a/fs/ksmbd/transport_rdma.c
+++ b/fs/ksmbd/transport_rdma.c
@@ -484,7 +484,7 @@ static int smb_direct_check_recvmsg(struct smb_direct_recvmsg *recvmsg)
 		struct smb_direct_data_transfer *req =
 			(struct smb_direct_data_transfer *)recvmsg->packet;
 		struct smb2_hdr *hdr = (struct smb2_hdr *)(recvmsg->packet
-				+ le32_to_cpu(req->data_offset) - 4);
+				+ le32_to_cpu(req->data_offset));
 		ksmbd_debug(RDMA,
 			    "CreditGranted: %u, CreditRequested: %u, DataLength: %u, RemainingDataLength: %u, SMB: %x, Command: %u\n",
 			    le16_to_cpu(req->credits_granted),
@@ -2043,7 +2043,6 @@ int ksmbd_rdma_destroy(void)
 	smb_direct_listener.cm_id = NULL;
 
 	if (smb_direct_wq) {
-		flush_workqueue(smb_direct_wq);
 		destroy_workqueue(smb_direct_wq);
 		smb_direct_wq = NULL;
 	}
diff --git a/fs/ksmbd/vfs.c b/fs/ksmbd/vfs.c
index 835b384b0895..19d36393974c 100644
--- a/fs/ksmbd/vfs.c
+++ b/fs/ksmbd/vfs.c
@@ -1013,7 +1013,7 @@ int ksmbd_vfs_zero_data(struct ksmbd_work *work, struct ksmbd_file *fp,
 			loff_t off, loff_t len)
 {
 	smb_break_all_levII_oplock(work, fp, 1);
-	if (fp->f_ci->m_fattr & ATTR_SPARSE_FILE_LE)
+	if (fp->f_ci->m_fattr & FILE_ATTRIBUTE_SPARSE_FILE_LE)
 		return vfs_fallocate(fp->filp,
 				     FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
 				     off, len);
@@ -1624,7 +1624,7 @@ void *ksmbd_vfs_init_kstat(char **p, struct ksmbd_kstat *ksmbd_kstat)
 	time = ksmbd_UnixTimeToNT(kstat->ctime);
 	info->ChangeTime = cpu_to_le64(time);
 
-	if (ksmbd_kstat->file_attributes & ATTR_DIRECTORY_LE) {
+	if (ksmbd_kstat->file_attributes & FILE_ATTRIBUTE_DIRECTORY_LE) {
 		info->EndOfFile = 0;
 		info->AllocationSize = 0;
 	} else {
@@ -1654,9 +1654,9 @@ int ksmbd_vfs_fill_dentry_attrs(struct ksmbd_work *work,
 	 * or that acl is disable in server's filesystem and the config is yes.
 	 */
 	if (S_ISDIR(ksmbd_kstat->kstat->mode))
-		ksmbd_kstat->file_attributes = ATTR_DIRECTORY_LE;
+		ksmbd_kstat->file_attributes = FILE_ATTRIBUTE_DIRECTORY_LE;
 	else
-		ksmbd_kstat->file_attributes = ATTR_ARCHIVE_LE;
+		ksmbd_kstat->file_attributes = FILE_ATTRIBUTE_ARCHIVE_LE;
 
 	if (test_share_config_flag(work->tcon->share_conf,
 				   KSMBD_SHARE_FLAG_STORE_DOS_ATTRS)) {
diff --git a/fs/ksmbd/vfs.h b/fs/ksmbd/vfs.h
index b0d5b8feb4a3..adf94a4f22fa 100644
--- a/fs/ksmbd/vfs.h
+++ b/fs/ksmbd/vfs.h
@@ -25,48 +25,9 @@ enum {
 };
 
 /* CreateOptions */
-/* Flag is set, it must not be a file , valid for directory only */
-#define FILE_DIRECTORY_FILE_LE			cpu_to_le32(0x00000001)
-#define FILE_WRITE_THROUGH_LE			cpu_to_le32(0x00000002)
-#define FILE_SEQUENTIAL_ONLY_LE			cpu_to_le32(0x00000004)
-
-/* Should not buffer on server*/
-#define FILE_NO_INTERMEDIATE_BUFFERING_LE	cpu_to_le32(0x00000008)
-/* MBZ */
-#define FILE_SYNCHRONOUS_IO_ALERT_LE		cpu_to_le32(0x00000010)
-/* MBZ */
-#define FILE_SYNCHRONOUS_IO_NONALERT_LE		cpu_to_le32(0x00000020)
-
-/* Flaf must not be set for directory */
-#define FILE_NON_DIRECTORY_FILE_LE		cpu_to_le32(0x00000040)
-
-/* Should be zero */
 #define CREATE_TREE_CONNECTION			cpu_to_le32(0x00000080)
-#define FILE_COMPLETE_IF_OPLOCKED_LE		cpu_to_le32(0x00000100)
-#define FILE_NO_EA_KNOWLEDGE_LE			cpu_to_le32(0x00000200)
-#define FILE_OPEN_REMOTE_INSTANCE		cpu_to_le32(0x00000400)
-
-/**
- * Doc says this is obsolete "open for recovery" flag should be zero
- * in any case.
- */
-#define CREATE_OPEN_FOR_RECOVERY		cpu_to_le32(0x00000400)
-#define FILE_RANDOM_ACCESS_LE			cpu_to_le32(0x00000800)
-#define FILE_DELETE_ON_CLOSE_LE			cpu_to_le32(0x00001000)
-#define FILE_OPEN_BY_FILE_ID_LE			cpu_to_le32(0x00002000)
-#define FILE_OPEN_FOR_BACKUP_INTENT_LE		cpu_to_le32(0x00004000)
-#define FILE_NO_COMPRESSION_LE			cpu_to_le32(0x00008000)
-
-/* Should be zero*/
-#define FILE_OPEN_REQUIRING_OPLOCK		cpu_to_le32(0x00010000)
-#define FILE_DISALLOW_EXCLUSIVE			cpu_to_le32(0x00020000)
 #define FILE_RESERVE_OPFILTER_LE		cpu_to_le32(0x00100000)
-#define FILE_OPEN_REPARSE_POINT_LE		cpu_to_le32(0x00200000)
-#define FILE_OPEN_NO_RECALL_LE			cpu_to_le32(0x00400000)
 
-/* Should be zero */
-#define FILE_OPEN_FOR_FREE_SPACE_QUERY_LE	cpu_to_le32(0x00800000)
-#define CREATE_OPTIONS_MASK			cpu_to_le32(0x00FFFFFF)
 #define CREATE_OPTION_READONLY			0x10000000
 /* system. NB not sent over wire */
 #define CREATE_OPTION_SPECIAL			0x20000000
diff --git a/fs/netfs/read_helper.c b/fs/netfs/read_helper.c
index 994ec22d4040..75c76cbb27cc 100644
--- a/fs/netfs/read_helper.c
+++ b/fs/netfs/read_helper.c
@@ -230,7 +230,7 @@ static void netfs_rreq_completed(struct netfs_read_request *rreq, bool was_async
 
 /*
  * Deal with the completion of writing the data to the cache.  We have to clear
- * the PG_fscache bits on the pages involved and release the caller's ref.
+ * the PG_fscache bits on the folios involved and release the caller's ref.
  *
  * May be called in softirq mode and we inherit a ref from the caller.
  */
@@ -238,7 +238,7 @@ static void netfs_rreq_unmark_after_write(struct netfs_read_request *rreq,
 					  bool was_async)
 {
 	struct netfs_read_subrequest *subreq;
-	struct page *page;
+	struct folio *folio;
 	pgoff_t unlocked = 0;
 	bool have_unlocked = false;
 
@@ -247,14 +247,14 @@ static void netfs_rreq_unmark_after_write(struct netfs_read_request *rreq,
 	list_for_each_entry(subreq, &rreq->subrequests, rreq_link) {
 		XA_STATE(xas, &rreq->mapping->i_pages, subreq->start / PAGE_SIZE);
 
-		xas_for_each(&xas, page, (subreq->start + subreq->len - 1) / PAGE_SIZE) {
+		xas_for_each(&xas, folio, (subreq->start + subreq->len - 1) / PAGE_SIZE) {
 			/* We might have multiple writes from the same huge
-			 * page, but we mustn't unlock a page more than once.
+			 * folio, but we mustn't unlock a folio more than once.
 			 */
-			if (have_unlocked && page->index <= unlocked)
+			if (have_unlocked && folio_index(folio) <= unlocked)
 				continue;
-			unlocked = page->index;
-			end_page_fscache(page);
+			unlocked = folio_index(folio);
+			folio_end_fscache(folio);
 			have_unlocked = true;
 		}
 	}
@@ -354,31 +354,25 @@ static void netfs_rreq_write_to_cache_work(struct work_struct *work)
 	netfs_rreq_do_write_to_cache(rreq);
 }
 
-static void netfs_rreq_write_to_cache(struct netfs_read_request *rreq,
-				      bool was_async)
+static void netfs_rreq_write_to_cache(struct netfs_read_request *rreq)
 {
-	if (was_async) {
-		rreq->work.func = netfs_rreq_write_to_cache_work;
-		if (!queue_work(system_unbound_wq, &rreq->work))
-			BUG();
-	} else {
-		netfs_rreq_do_write_to_cache(rreq);
-	}
+	rreq->work.func = netfs_rreq_write_to_cache_work;
+	if (!queue_work(system_unbound_wq, &rreq->work))
+		BUG();
 }
 
 /*
- * Unlock the pages in a read operation.  We need to set PG_fscache on any
- * pages we're going to write back before we unlock them.
+ * Unlock the folios in a read operation.  We need to set PG_fscache on any
+ * folios we're going to write back before we unlock them.
  */
 static void netfs_rreq_unlock(struct netfs_read_request *rreq)
 {
 	struct netfs_read_subrequest *subreq;
-	struct page *page;
+	struct folio *folio;
 	unsigned int iopos, account = 0;
 	pgoff_t start_page = rreq->start / PAGE_SIZE;
 	pgoff_t last_page = ((rreq->start + rreq->len) / PAGE_SIZE) - 1;
 	bool subreq_failed = false;
-	int i;
 
 	XA_STATE(xas, &rreq->mapping->i_pages, start_page);
 
@@ -403,9 +397,9 @@ static void netfs_rreq_unlock(struct netfs_read_request *rreq)
 	trace_netfs_rreq(rreq, netfs_rreq_trace_unlock);
 
 	rcu_read_lock();
-	xas_for_each(&xas, page, last_page) {
-		unsigned int pgpos = (page->index - start_page) * PAGE_SIZE;
-		unsigned int pgend = pgpos + thp_size(page);
+	xas_for_each(&xas, folio, last_page) {
+		unsigned int pgpos = (folio_index(folio) - start_page) * PAGE_SIZE;
+		unsigned int pgend = pgpos + folio_size(folio);
 		bool pg_failed = false;
 
 		for (;;) {
@@ -414,7 +408,7 @@ static void netfs_rreq_unlock(struct netfs_read_request *rreq)
 				break;
 			}
 			if (test_bit(NETFS_SREQ_WRITE_TO_CACHE, &subreq->flags))
-				set_page_fscache(page);
+				folio_start_fscache(folio);
 			pg_failed |= subreq_failed;
 			if (pgend < iopos + subreq->len)
 				break;
@@ -433,17 +427,16 @@ static void netfs_rreq_unlock(struct netfs_read_request *rreq)
 		}
 
 		if (!pg_failed) {
-			for (i = 0; i < thp_nr_pages(page); i++)
-				flush_dcache_page(page);
-			SetPageUptodate(page);
+			flush_dcache_folio(folio);
+			folio_mark_uptodate(folio);
 		}
 
-		if (!test_bit(NETFS_RREQ_DONT_UNLOCK_PAGES, &rreq->flags)) {
-			if (page->index == rreq->no_unlock_page &&
-			    test_bit(NETFS_RREQ_NO_UNLOCK_PAGE, &rreq->flags))
+		if (!test_bit(NETFS_RREQ_DONT_UNLOCK_FOLIOS, &rreq->flags)) {
+			if (folio_index(folio) == rreq->no_unlock_folio &&
+			    test_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags))
 				_debug("no unlock");
 			else
-				unlock_page(page);
+				folio_unlock(folio);
 		}
 	}
 	rcu_read_unlock();
@@ -560,7 +553,7 @@ again:
 	wake_up_bit(&rreq->flags, NETFS_RREQ_IN_PROGRESS);
 
 	if (test_bit(NETFS_RREQ_WRITE_TO_CACHE, &rreq->flags))
-		return netfs_rreq_write_to_cache(rreq, was_async);
+		return netfs_rreq_write_to_cache(rreq);
 
 	netfs_rreq_completed(rreq, was_async);
 }
@@ -876,7 +869,6 @@ void netfs_readahead(struct readahead_control *ractl,
 		     void *netfs_priv)
 {
 	struct netfs_read_request *rreq;
-	struct page *page;
 	unsigned int debug_index = 0;
 	int ret;
 
@@ -911,11 +903,11 @@ void netfs_readahead(struct readahead_control *ractl,
 
 	} while (rreq->submitted < rreq->len);
 
-	/* Drop the refs on the pages here rather than in the cache or
+	/* Drop the refs on the folios here rather than in the cache or
 	 * filesystem.  The locks will be dropped in netfs_rreq_unlock().
 	 */
-	while ((page = readahead_page(ractl)))
-		put_page(page);
+	while (readahead_folio(ractl))
+		;
 
 	/* If we decrement nr_rd_ops to 0, the ref belongs to us. */
 	if (atomic_dec_and_test(&rreq->nr_rd_ops))
@@ -935,7 +927,7 @@ EXPORT_SYMBOL(netfs_readahead);
 /**
  * netfs_readpage - Helper to manage a readpage request
  * @file: The file to read from
- * @page: The page to read
+ * @folio: The folio to read
  * @ops: The network filesystem's operations for the helper to use
  * @netfs_priv: Private netfs data to be retained in the request
  *
@@ -950,7 +942,7 @@ EXPORT_SYMBOL(netfs_readahead);
  * This is usable whether or not caching is enabled.
  */
 int netfs_readpage(struct file *file,
-		   struct page *page,
+		   struct folio *folio,
 		   const struct netfs_read_request_ops *ops,
 		   void *netfs_priv)
 {
@@ -958,23 +950,23 @@ int netfs_readpage(struct file *file,
 	unsigned int debug_index = 0;
 	int ret;
 
-	_enter("%lx", page_index(page));
+	_enter("%lx", folio_index(folio));
 
 	rreq = netfs_alloc_read_request(ops, netfs_priv, file);
 	if (!rreq) {
 		if (netfs_priv)
-			ops->cleanup(netfs_priv, page_file_mapping(page));
-		unlock_page(page);
+			ops->cleanup(folio_file_mapping(folio), netfs_priv);
+		folio_unlock(folio);
 		return -ENOMEM;
 	}
-	rreq->mapping	= page_file_mapping(page);
-	rreq->start	= page_file_offset(page);
-	rreq->len	= thp_size(page);
+	rreq->mapping	= folio_file_mapping(folio);
+	rreq->start	= folio_file_pos(folio);
+	rreq->len	= folio_size(folio);
 
 	if (ops->begin_cache_operation) {
 		ret = ops->begin_cache_operation(rreq);
 		if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS) {
-			unlock_page(page);
+			folio_unlock(folio);
 			goto out;
 		}
 	}
@@ -1011,41 +1003,41 @@ out:
 }
 EXPORT_SYMBOL(netfs_readpage);
 
-/**
- * netfs_skip_page_read - prep a page for writing without reading first
- * @page: page being prepared
+/*
+ * Prepare a folio for writing without reading first
+ * @folio: The folio being prepared
  * @pos: starting position for the write
  * @len: length of write
  *
  * In some cases, write_begin doesn't need to read at all:
- * - full page write
- * - write that lies in a page that is completely beyond EOF
- * - write that covers the the page from start to EOF or beyond it
+ * - full folio write
+ * - write that lies in a folio that is completely beyond EOF
+ * - write that covers the folio from start to EOF or beyond it
  *
  * If any of these criteria are met, then zero out the unwritten parts
- * of the page and return true. Otherwise, return false.
+ * of the folio and return true. Otherwise, return false.
  */
-static bool netfs_skip_page_read(struct page *page, loff_t pos, size_t len)
+static bool netfs_skip_folio_read(struct folio *folio, loff_t pos, size_t len)
 {
-	struct inode *inode = page->mapping->host;
+	struct inode *inode = folio_inode(folio);
 	loff_t i_size = i_size_read(inode);
-	size_t offset = offset_in_thp(page, pos);
+	size_t offset = offset_in_folio(folio, pos);
 
-	/* Full page write */
-	if (offset == 0 && len >= thp_size(page))
+	/* Full folio write */
+	if (offset == 0 && len >= folio_size(folio))
 		return true;
 
-	/* pos beyond last page in the file */
+	/* pos beyond last folio in the file */
 	if (pos - offset >= i_size)
 		goto zero_out;
 
-	/* Write that covers from the start of the page to EOF or beyond */
+	/* Write that covers from the start of the folio to EOF or beyond */
 	if (offset == 0 && (pos + len) >= i_size)
 		goto zero_out;
 
 	return false;
 zero_out:
-	zero_user_segments(page, 0, offset, offset + len, thp_size(page));
+	zero_user_segments(&folio->page, 0, offset, offset + len, folio_size(folio));
 	return true;
 }
 
@@ -1054,9 +1046,9 @@ zero_out:
  * @file: The file to read from
  * @mapping: The mapping to read from
  * @pos: File position at which the write will begin
- * @len: The length of the write (may extend beyond the end of the page chosen)
- * @flags: AOP_* flags
- * @_page: Where to put the resultant page
+ * @len: The length of the write (may extend beyond the end of the folio chosen)
+ * @aop_flags: AOP_* flags
+ * @_folio: Where to put the resultant folio
  * @_fsdata: Place for the netfs to store a cookie
  * @ops: The network filesystem's operations for the helper to use
  * @netfs_priv: Private netfs data to be retained in the request
@@ -1072,37 +1064,41 @@ zero_out:
  * issue_op, is mandatory.
  *
  * The check_write_begin() operation can be provided to check for and flush
- * conflicting writes once the page is grabbed and locked.  It is passed a
+ * conflicting writes once the folio is grabbed and locked.  It is passed a
  * pointer to the fsdata cookie that gets returned to the VM to be passed to
  * write_end.  It is permitted to sleep.  It should return 0 if the request
- * should go ahead; unlock the page and return -EAGAIN to cause the page to be
- * regot; or return an error.
+ * should go ahead; unlock the folio and return -EAGAIN to cause the folio to
+ * be regot; or return an error.
  *
  * This is usable whether or not caching is enabled.
  */
 int netfs_write_begin(struct file *file, struct address_space *mapping,
-		      loff_t pos, unsigned int len, unsigned int flags,
-		      struct page **_page, void **_fsdata,
+		      loff_t pos, unsigned int len, unsigned int aop_flags,
+		      struct folio **_folio, void **_fsdata,
 		      const struct netfs_read_request_ops *ops,
 		      void *netfs_priv)
 {
 	struct netfs_read_request *rreq;
-	struct page *page, *xpage;
+	struct folio *folio;
 	struct inode *inode = file_inode(file);
-	unsigned int debug_index = 0;
+	unsigned int debug_index = 0, fgp_flags;
 	pgoff_t index = pos >> PAGE_SHIFT;
 	int ret;
 
 	DEFINE_READAHEAD(ractl, file, NULL, mapping, index);
 
 retry:
-	page = grab_cache_page_write_begin(mapping, index, flags);
-	if (!page)
+	fgp_flags = FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE;
+	if (aop_flags & AOP_FLAG_NOFS)
+		fgp_flags |= FGP_NOFS;
+	folio = __filemap_get_folio(mapping, index, fgp_flags,
+				    mapping_gfp_mask(mapping));
+	if (!folio)
 		return -ENOMEM;
 
 	if (ops->check_write_begin) {
 		/* Allow the netfs (eg. ceph) to flush conflicts. */
-		ret = ops->check_write_begin(file, pos, len, page, _fsdata);
+		ret = ops->check_write_begin(file, pos, len, folio, _fsdata);
 		if (ret < 0) {
 			trace_netfs_failure(NULL, NULL, ret, netfs_fail_check_write_begin);
 			if (ret == -EAGAIN)
@@ -1111,28 +1107,28 @@ retry:
 		}
 	}
 
-	if (PageUptodate(page))
-		goto have_page;
+	if (folio_test_uptodate(folio))
+		goto have_folio;
 
 	/* If the page is beyond the EOF, we want to clear it - unless it's
 	 * within the cache granule containing the EOF, in which case we need
 	 * to preload the granule.
 	 */
 	if (!ops->is_cache_enabled(inode) &&
-	    netfs_skip_page_read(page, pos, len)) {
+	    netfs_skip_folio_read(folio, pos, len)) {
 		netfs_stat(&netfs_n_rh_write_zskip);
-		goto have_page_no_wait;
+		goto have_folio_no_wait;
 	}
 
 	ret = -ENOMEM;
 	rreq = netfs_alloc_read_request(ops, netfs_priv, file);
 	if (!rreq)
 		goto error;
-	rreq->mapping		= page->mapping;
-	rreq->start		= page_offset(page);
-	rreq->len		= thp_size(page);
-	rreq->no_unlock_page	= page->index;
-	__set_bit(NETFS_RREQ_NO_UNLOCK_PAGE, &rreq->flags);
+	rreq->mapping		= folio_file_mapping(folio);
+	rreq->start		= folio_file_pos(folio);
+	rreq->len		= folio_size(folio);
+	rreq->no_unlock_folio	= folio_index(folio);
+	__set_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags);
 	netfs_priv = NULL;
 
 	if (ops->begin_cache_operation) {
@@ -1147,14 +1143,14 @@ retry:
 	/* Expand the request to meet caching requirements and download
 	 * preferences.
 	 */
-	ractl._nr_pages = thp_nr_pages(page);
+	ractl._nr_pages = folio_nr_pages(folio);
 	netfs_rreq_expand(rreq, &ractl);
 	netfs_get_read_request(rreq);
 
-	/* We hold the page locks, so we can drop the references */
-	while ((xpage = readahead_page(&ractl)))
-		if (xpage != page)
-			put_page(xpage);
+	/* We hold the folio locks, so we can drop the references */
+	folio_get(folio);
+	while (readahead_folio(&ractl))
+		;
 
 	atomic_set(&rreq->nr_rd_ops, 1);
 	do {
@@ -1184,24 +1180,24 @@ retry:
 	if (ret < 0)
 		goto error;
 
-have_page:
-	ret = wait_on_page_fscache_killable(page);
+have_folio:
+	ret = folio_wait_fscache_killable(folio);
 	if (ret < 0)
 		goto error;
-have_page_no_wait:
+have_folio_no_wait:
 	if (netfs_priv)
-		ops->cleanup(netfs_priv, mapping);
-	*_page = page;
+		ops->cleanup(mapping, netfs_priv);
+	*_folio = folio;
 	_leave(" = 0");
 	return 0;
 
 error_put:
 	netfs_put_read_request(rreq, false);
 error:
-	unlock_page(page);
-	put_page(page);
+	folio_unlock(folio);
+	folio_put(folio);
 	if (netfs_priv)
-		ops->cleanup(netfs_priv, mapping);
+		ops->cleanup(mapping, netfs_priv);
 	_leave(" = %d", ret);
 	return ret;
 }
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index dd53704c3f40..fda530d5e764 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -219,6 +219,7 @@ void nfs_set_cache_invalid(struct inode *inode, unsigned long flags)
 					  NFS_INO_DATA_INVAL_DEFER);
 	else if (nfsi->cache_validity & NFS_INO_INVALID_DATA)
 		nfsi->cache_validity &= ~NFS_INO_DATA_INVAL_DEFER;
+	trace_nfs_set_cache_invalid(inode, 0);
 }
 EXPORT_SYMBOL_GPL(nfs_set_cache_invalid);
 
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index 08355b66e7cb..8b21ff1be717 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -289,7 +289,9 @@ static void nfs42_copy_dest_done(struct inode *inode, loff_t pos, loff_t len)
 	loff_t newsize = pos + len;
 	loff_t end = newsize - 1;
 
-	truncate_pagecache_range(inode, pos, end);
+	WARN_ON_ONCE(invalidate_inode_pages2_range(inode->i_mapping,
+				pos >> PAGE_SHIFT, end >> PAGE_SHIFT));
+
 	spin_lock(&inode->i_lock);
 	if (newsize > i_size_read(inode))
 		i_size_write(inode, newsize);
diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c
index c8bad735e4c1..271e5f92ed01 100644
--- a/fs/nfs/nfs42xdr.c
+++ b/fs/nfs/nfs42xdr.c
@@ -1434,8 +1434,7 @@ static int nfs4_xdr_dec_clone(struct rpc_rqst *rqstp,
 	status = decode_clone(xdr);
 	if (status)
 		goto out;
-	status = decode_getfattr(xdr, res->dst_fattr, res->server);
-
+	decode_getfattr(xdr, res->dst_fattr, res->server);
 out:
 	res->rpc_status = status;
 	return status;
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index ecc4594299d6..f63dfa01001c 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1998,6 +1998,10 @@ static int nfs4_handle_reclaim_lease_error(struct nfs_client *clp, int status)
 		dprintk("%s: exit with error %d for server %s\n",
 				__func__, -EPROTONOSUPPORT, clp->cl_hostname);
 		return -EPROTONOSUPPORT;
+	case -ENOSPC:
+		if (clp->cl_cons_state == NFS_CS_SESSION_INITING)
+			nfs_mark_client_ready(clp, -EIO);
+		return -EIO;
 	case -NFS4ERR_NOT_SAME: /* FixMe: implement recovery
 				 * in nfs4_exchange_id */
 	default:
diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h
index 21dac847f1e4..b3aee261801e 100644
--- a/fs/nfs/nfstrace.h
+++ b/fs/nfs/nfstrace.h
@@ -162,6 +162,7 @@ DEFINE_NFS_INODE_EVENT_DONE(nfs_writeback_inode_exit);
 DEFINE_NFS_INODE_EVENT(nfs_fsync_enter);
 DEFINE_NFS_INODE_EVENT_DONE(nfs_fsync_exit);
 DEFINE_NFS_INODE_EVENT(nfs_access_enter);
+DEFINE_NFS_INODE_EVENT_DONE(nfs_set_cache_invalid);
 
 TRACE_EVENT(nfs_access_exit,
 		TP_PROTO(
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index 4418517f6f12..15dac36ca852 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -438,22 +438,19 @@ nfsd3_proc_link(struct svc_rqst *rqstp)
 
 static void nfsd3_init_dirlist_pages(struct svc_rqst *rqstp,
 				     struct nfsd3_readdirres *resp,
-				     int count)
+				     u32 count)
 {
 	struct xdr_buf *buf = &resp->dirlist;
 	struct xdr_stream *xdr = &resp->xdr;
 
-	count = min_t(u32, count, svc_max_payload(rqstp));
+	count = clamp(count, (u32)(XDR_UNIT * 2), svc_max_payload(rqstp));
 
 	memset(buf, 0, sizeof(*buf));
 
 	/* Reserve room for the NULL ptr & eof flag (-2 words) */
 	buf->buflen = count - XDR_UNIT * 2;
 	buf->pages = rqstp->rq_next_page;
-	while (count > 0) {
-		rqstp->rq_next_page++;
-		count -= PAGE_SIZE;
-	}
+	rqstp->rq_next_page += (buf->buflen + PAGE_SIZE - 1) >> PAGE_SHIFT;
 
 	/* This is xdr_init_encode(), but it assumes that
 	 * the head kvec has already been consumed. */
@@ -462,7 +459,7 @@ static void nfsd3_init_dirlist_pages(struct svc_rqst *rqstp,
 	xdr->page_ptr = buf->pages;
 	xdr->iov = NULL;
 	xdr->p = page_address(*buf->pages);
-	xdr->end = xdr->p + (PAGE_SIZE >> 2);
+	xdr->end = (void *)xdr->p + min_t(u32, buf->buflen, PAGE_SIZE);
 	xdr->rqst = NULL;
 }
 
diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index 6fedc49726bf..c634483d85d2 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -2156,6 +2156,7 @@ static struct notifier_block nfsd4_cld_block = {
 int
 register_cld_notifier(void)
 {
+	WARN_ON(!nfsd_net_id);
 	return rpc_pipefs_notifier_register(&nfsd4_cld_block);
 }
 
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index bfad94c70b84..1956d377d1a6 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -1207,6 +1207,11 @@ hash_delegation_locked(struct nfs4_delegation *dp, struct nfs4_file *fp)
 	return 0;
 }
 
+static bool delegation_hashed(struct nfs4_delegation *dp)
+{
+	return !(list_empty(&dp->dl_perfile));
+}
+
 static bool
 unhash_delegation_locked(struct nfs4_delegation *dp)
 {
@@ -1214,7 +1219,7 @@ unhash_delegation_locked(struct nfs4_delegation *dp)
 
 	lockdep_assert_held(&state_lock);
 
-	if (list_empty(&dp->dl_perfile))
+	if (!delegation_hashed(dp))
 		return false;
 
 	dp->dl_stid.sc_type = NFS4_CLOSED_DELEG_STID;
@@ -4598,7 +4603,7 @@ static void nfsd4_cb_recall_prepare(struct nfsd4_callback *cb)
 	 * queued for a lease break. Don't queue it again.
 	 */
 	spin_lock(&state_lock);
-	if (dp->dl_time == 0) {
+	if (delegation_hashed(dp) && dp->dl_time == 0) {
 		dp->dl_time = ktime_get_boottime_seconds();
 		list_add_tail(&dp->dl_recall_lru, &nn->del_recall_lru);
 	}
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index b2a1d969a172..5a93a5db4fb0 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -288,11 +288,8 @@ nfsd4_decode_bitmap4(struct nfsd4_compoundargs *argp, u32 *bmval, u32 bmlen)
 	p = xdr_inline_decode(argp->xdr, count << 2);
 	if (!p)
 		return nfserr_bad_xdr;
-	i = 0;
-	while (i < count)
-		bmval[i++] = be32_to_cpup(p++);
-	while (i < bmlen)
-		bmval[i++] = 0;
+	for (i = 0; i < bmlen; i++)
+		bmval[i] = (i < count) ? be32_to_cpup(p++) : 0;
 
 	return nfs_ok;
 }
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index af8531c3854a..51a49e0cfe37 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -1521,12 +1521,9 @@ static int __init init_nfsd(void)
 	int retval;
 	printk(KERN_INFO "Installing knfsd (copyright (C) 1996 okir@monad.swb.de).\n");
 
-	retval = register_cld_notifier();
-	if (retval)
-		return retval;
 	retval = nfsd4_init_slabs();
 	if (retval)
-		goto out_unregister_notifier;
+		return retval;
 	retval = nfsd4_init_pnfs();
 	if (retval)
 		goto out_free_slabs;
@@ -1545,9 +1542,14 @@ static int __init init_nfsd(void)
 		goto out_free_exports;
 	retval = register_pernet_subsys(&nfsd_net_ops);
 	if (retval < 0)
+		goto out_free_filesystem;
+	retval = register_cld_notifier();
+	if (retval)
 		goto out_free_all;
 	return 0;
 out_free_all:
+	unregister_pernet_subsys(&nfsd_net_ops);
+out_free_filesystem:
 	unregister_filesystem(&nfsd_fs_type);
 out_free_exports:
 	remove_proc_entry("fs/nfs/exports", NULL);
@@ -1561,13 +1563,12 @@ out_free_pnfs:
 	nfsd4_exit_pnfs();
 out_free_slabs:
 	nfsd4_free_slabs();
-out_unregister_notifier:
-	unregister_cld_notifier();
 	return retval;
 }
 
 static void __exit exit_nfsd(void)
 {
+	unregister_cld_notifier();
 	unregister_pernet_subsys(&nfsd_net_ops);
 	nfsd_drc_slab_free();
 	remove_proc_entry("fs/nfs/exports", NULL);
@@ -1577,7 +1578,6 @@ static void __exit exit_nfsd(void)
 	nfsd4_free_slabs();
 	nfsd4_exit_pnfs();
 	unregister_filesystem(&nfsd_fs_type);
-	unregister_cld_notifier();
 }
 
 MODULE_AUTHOR("Olaf Kirch <okir@monad.swb.de>");
diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c
index eea5b59b6a6c..de282f3273c5 100644
--- a/fs/nfsd/nfsproc.c
+++ b/fs/nfsd/nfsproc.c
@@ -556,17 +556,17 @@ nfsd_proc_rmdir(struct svc_rqst *rqstp)
 
 static void nfsd_init_dirlist_pages(struct svc_rqst *rqstp,
 				    struct nfsd_readdirres *resp,
-				    int count)
+				    u32 count)
 {
 	struct xdr_buf *buf = &resp->dirlist;
 	struct xdr_stream *xdr = &resp->xdr;
 
-	count = min_t(u32, count, PAGE_SIZE);
+	count = clamp(count, (u32)(XDR_UNIT * 2), svc_max_payload(rqstp));
 
 	memset(buf, 0, sizeof(*buf));
 
 	/* Reserve room for the NULL ptr & eof flag (-2 words) */
-	buf->buflen = count - sizeof(__be32) * 2;
+	buf->buflen = count - XDR_UNIT * 2;
 	buf->pages = rqstp->rq_next_page;
 	rqstp->rq_next_page++;
 
@@ -577,7 +577,7 @@ static void nfsd_init_dirlist_pages(struct svc_rqst *rqstp,
 	xdr->page_ptr = buf->pages;
 	xdr->iov = NULL;
 	xdr->p = page_address(*buf->pages);
-	xdr->end = xdr->p + (PAGE_SIZE >> 2);
+	xdr->end = (void *)xdr->p + min_t(u32, buf->buflen, PAGE_SIZE);
 	xdr->rqst = NULL;
 }
 
diff --git a/fs/ntfs/Kconfig b/fs/ntfs/Kconfig
index 1667a7e590d8..f93e69a61283 100644
--- a/fs/ntfs/Kconfig
+++ b/fs/ntfs/Kconfig
@@ -52,6 +52,7 @@ config NTFS_DEBUG
 config NTFS_RW
 	bool "NTFS write support"
 	depends on NTFS_FS
+	depends on PAGE_SIZE_LESS_THAN_64KB
 	help
 	  This enables the partial, but safe, write support in the NTFS driver.
 
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index 30a3b66f475a..509f85148fee 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -154,9 +154,13 @@ ssize_t read_from_oldmem(char *buf, size_t count,
 			nr_bytes = count;
 
 		/* If pfn is not ram, return zeros for sparse dump files */
-		if (!pfn_is_ram(pfn))
-			memset(buf, 0, nr_bytes);
-		else {
+		if (!pfn_is_ram(pfn)) {
+			tmp = 0;
+			if (!userbuf)
+				memset(buf, 0, nr_bytes);
+			else if (clear_user(buf, nr_bytes))
+				tmp = -EFAULT;
+		} else {
 			if (encrypted)
 				tmp = copy_oldmem_page_encrypted(pfn, buf,
 								 nr_bytes,
@@ -165,12 +169,12 @@ ssize_t read_from_oldmem(char *buf, size_t count,
 			else
 				tmp = copy_oldmem_page(pfn, buf, nr_bytes,
 						       offset, userbuf);
-
-			if (tmp < 0) {
-				up_read(&vmcore_cb_rwsem);
-				return tmp;
-			}
 		}
+		if (tmp < 0) {
+			up_read(&vmcore_cb_rwsem);
+			return tmp;
+		}
+
 		*ppos += nr_bytes;
 		count -= nr_bytes;
 		buf += nr_bytes;
diff --git a/fs/pstore/Kconfig b/fs/pstore/Kconfig
index 328da35da390..8adabde685f1 100644
--- a/fs/pstore/Kconfig
+++ b/fs/pstore/Kconfig
@@ -173,7 +173,6 @@ config PSTORE_BLK
 	tristate "Log panic/oops to a block device"
 	depends on PSTORE
 	depends on BLOCK
-	depends on BROKEN
 	select PSTORE_ZONE
 	default n
 	help
diff --git a/fs/pstore/blk.c b/fs/pstore/blk.c
index 5d1fbaffd66a..4ae0cfcd15f2 100644
--- a/fs/pstore/blk.c
+++ b/fs/pstore/blk.c
@@ -309,7 +309,7 @@ static int __init __best_effort_init(void)
 	if (ret)
 		kfree(best_effort_dev);
 	else
-		pr_info("attached %s (%zu) (no dedicated panic_write!)\n",
+		pr_info("attached %s (%lu) (no dedicated panic_write!)\n",
 			blkdev, best_effort_dev->zone.total_size);
 
 	return ret;
diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c
index b9614db48b1d..f243cb5e6a4f 100644
--- a/fs/pstore/platform.c
+++ b/fs/pstore/platform.c
@@ -218,7 +218,7 @@ static int zbufsize_842(size_t size)
 #if IS_ENABLED(CONFIG_PSTORE_ZSTD_COMPRESS)
 static int zbufsize_zstd(size_t size)
 {
-	return ZSTD_compressBound(size);
+	return zstd_compress_bound(size);
 }
 #endif
 
diff --git a/fs/signalfd.c b/fs/signalfd.c
index 040e1cf90528..65ce0e72e7b9 100644
--- a/fs/signalfd.c
+++ b/fs/signalfd.c
@@ -35,17 +35,7 @@
 
 void signalfd_cleanup(struct sighand_struct *sighand)
 {
-	wait_queue_head_t *wqh = &sighand->signalfd_wqh;
-	/*
-	 * The lockless check can race with remove_wait_queue() in progress,
-	 * but in this case its caller should run under rcu_read_lock() and
-	 * sighand_cachep is SLAB_TYPESAFE_BY_RCU, we can safely return.
-	 */
-	if (likely(!waitqueue_active(wqh)))
-		return;
-
-	/* wait_queue_entry_t->func(POLLFREE) should do remove_wait_queue() */
-	wake_up_poll(wqh, EPOLLHUP | POLLFREE);
+	wake_up_pollfree(&sighand->signalfd_wqh);
 }
 
 struct signalfd_ctx {
diff --git a/fs/smbfs_common/cifs_arc4.c b/fs/smbfs_common/cifs_arc4.c
index 85ba15a60b13..043e4cb839fa 100644
--- a/fs/smbfs_common/cifs_arc4.c
+++ b/fs/smbfs_common/cifs_arc4.c
@@ -72,16 +72,3 @@ void cifs_arc4_crypt(struct arc4_ctx *ctx, u8 *out, const u8 *in, unsigned int l
 	ctx->y = y;
 }
 EXPORT_SYMBOL_GPL(cifs_arc4_crypt);
-
-static int __init
-init_smbfs_common(void)
-{
-	return 0;
-}
-static void __init
-exit_smbfs_common(void)
-{
-}
-
-module_init(init_smbfs_common)
-module_exit(exit_smbfs_common)
diff --git a/fs/squashfs/zstd_wrapper.c b/fs/squashfs/zstd_wrapper.c
index 0015cf8b5582..c40445dbf38c 100644
--- a/fs/squashfs/zstd_wrapper.c
+++ b/fs/squashfs/zstd_wrapper.c
@@ -34,7 +34,7 @@ static void *zstd_init(struct squashfs_sb_info *msblk, void *buff)
 		goto failed;
 	wksp->window_size = max_t(size_t,
 			msblk->block_size, SQUASHFS_METADATA_SIZE);
-	wksp->mem_size = ZSTD_DStreamWorkspaceBound(wksp->window_size);
+	wksp->mem_size = zstd_dstream_workspace_bound(wksp->window_size);
 	wksp->mem = vmalloc(wksp->mem_size);
 	if (wksp->mem == NULL)
 		goto failed;
@@ -63,15 +63,15 @@ static int zstd_uncompress(struct squashfs_sb_info *msblk, void *strm,
 	struct squashfs_page_actor *output)
 {
 	struct workspace *wksp = strm;
-	ZSTD_DStream *stream;
+	zstd_dstream *stream;
 	size_t total_out = 0;
 	int error = 0;
-	ZSTD_inBuffer in_buf = { NULL, 0, 0 };
-	ZSTD_outBuffer out_buf = { NULL, 0, 0 };
+	zstd_in_buffer in_buf = { NULL, 0, 0 };
+	zstd_out_buffer out_buf = { NULL, 0, 0 };
 	struct bvec_iter_all iter_all = {};
 	struct bio_vec *bvec = bvec_init_iter_all(&iter_all);
 
-	stream = ZSTD_initDStream(wksp->window_size, wksp->mem, wksp->mem_size);
+	stream = zstd_init_dstream(wksp->window_size, wksp->mem, wksp->mem_size);
 
 	if (!stream) {
 		ERROR("Failed to initialize zstd decompressor\n");
@@ -116,14 +116,14 @@ static int zstd_uncompress(struct squashfs_sb_info *msblk, void *strm,
 		}
 
 		total_out -= out_buf.pos;
-		zstd_err = ZSTD_decompressStream(stream, &out_buf, &in_buf);
+		zstd_err = zstd_decompress_stream(stream, &out_buf, &in_buf);
 		total_out += out_buf.pos; /* add the additional data produced */
 		if (zstd_err == 0)
 			break;
 
-		if (ZSTD_isError(zstd_err)) {
+		if (zstd_is_error(zstd_err)) {
 			ERROR("zstd decompression error: %d\n",
-					(int)ZSTD_getErrorCode(zstd_err));
+					(int)zstd_get_error_code(zstd_err));
 			error = -EIO;
 			break;
 		}
diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c
index 925a621b432e..3616839c5c4b 100644
--- a/fs/tracefs/inode.c
+++ b/fs/tracefs/inode.c
@@ -161,6 +161,77 @@ struct tracefs_fs_info {
 	struct tracefs_mount_opts mount_opts;
 };
 
+static void change_gid(struct dentry *dentry, kgid_t gid)
+{
+	if (!dentry->d_inode)
+		return;
+	dentry->d_inode->i_gid = gid;
+}
+
+/*
+ * Taken from d_walk, but without he need for handling renames.
+ * Nothing can be renamed while walking the list, as tracefs
+ * does not support renames. This is only called when mounting
+ * or remounting the file system, to set all the files to
+ * the given gid.
+ */
+static void set_gid(struct dentry *parent, kgid_t gid)
+{
+	struct dentry *this_parent;
+	struct list_head *next;
+
+	this_parent = parent;
+	spin_lock(&this_parent->d_lock);
+
+	change_gid(this_parent, gid);
+repeat:
+	next = this_parent->d_subdirs.next;
+resume:
+	while (next != &this_parent->d_subdirs) {
+		struct list_head *tmp = next;
+		struct dentry *dentry = list_entry(tmp, struct dentry, d_child);
+		next = tmp->next;
+
+		spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
+
+		change_gid(dentry, gid);
+
+		if (!list_empty(&dentry->d_subdirs)) {
+			spin_unlock(&this_parent->d_lock);
+			spin_release(&dentry->d_lock.dep_map, _RET_IP_);
+			this_parent = dentry;
+			spin_acquire(&this_parent->d_lock.dep_map, 0, 1, _RET_IP_);
+			goto repeat;
+		}
+		spin_unlock(&dentry->d_lock);
+	}
+	/*
+	 * All done at this level ... ascend and resume the search.
+	 */
+	rcu_read_lock();
+ascend:
+	if (this_parent != parent) {
+		struct dentry *child = this_parent;
+		this_parent = child->d_parent;
+
+		spin_unlock(&child->d_lock);
+		spin_lock(&this_parent->d_lock);
+
+		/* go into the first sibling still alive */
+		do {
+			next = child->d_child.next;
+			if (next == &this_parent->d_subdirs)
+				goto ascend;
+			child = list_entry(next, struct dentry, d_child);
+		} while (unlikely(child->d_flags & DCACHE_DENTRY_KILLED));
+		rcu_read_unlock();
+		goto resume;
+	}
+	rcu_read_unlock();
+	spin_unlock(&this_parent->d_lock);
+	return;
+}
+
 static int tracefs_parse_options(char *data, struct tracefs_mount_opts *opts)
 {
 	substring_t args[MAX_OPT_ARGS];
@@ -193,6 +264,7 @@ static int tracefs_parse_options(char *data, struct tracefs_mount_opts *opts)
 			if (!gid_valid(gid))
 				return -EINVAL;
 			opts->gid = gid;
+			set_gid(tracefs_mount->mnt_root, gid);
 			break;
 		case Opt_mode:
 			if (match_octal(&args[0], &option))
@@ -414,6 +486,8 @@ struct dentry *tracefs_create_file(const char *name, umode_t mode,
 	inode->i_mode = mode;
 	inode->i_fop = fops ? fops : &tracefs_file_operations;
 	inode->i_private = data;
+	inode->i_uid = d_inode(dentry->d_parent)->i_uid;
+	inode->i_gid = d_inode(dentry->d_parent)->i_gid;
 	d_instantiate(dentry, inode);
 	fsnotify_create(dentry->d_parent->d_inode, dentry);
 	return end_creating(dentry);
@@ -436,6 +510,8 @@ static struct dentry *__create_dir(const char *name, struct dentry *parent,
 	inode->i_mode = S_IFDIR | S_IRWXU | S_IRUSR| S_IRGRP | S_IXUSR | S_IXGRP;
 	inode->i_op = ops;
 	inode->i_fop = &simple_dir_operations;
+	inode->i_uid = d_inode(dentry->d_parent)->i_uid;
+	inode->i_gid = d_inode(dentry->d_parent)->i_gid;
 
 	/* directory inodes start off with i_nlink == 2 (for "." entry) */
 	inc_nlink(inode);
diff --git a/fs/udf/dir.c b/fs/udf/dir.c
index 70abdfad2df1..42e3e551fa4c 100644
--- a/fs/udf/dir.c
+++ b/fs/udf/dir.c
@@ -31,6 +31,7 @@
 #include <linux/mm.h>
 #include <linux/slab.h>
 #include <linux/bio.h>
+#include <linux/iversion.h>
 
 #include "udf_i.h"
 #include "udf_sb.h"
@@ -43,7 +44,7 @@ static int udf_readdir(struct file *file, struct dir_context *ctx)
 	struct fileIdentDesc *fi = NULL;
 	struct fileIdentDesc cfi;
 	udf_pblk_t block, iblock;
-	loff_t nf_pos;
+	loff_t nf_pos, emit_pos = 0;
 	int flen;
 	unsigned char *fname = NULL, *copy_name = NULL;
 	unsigned char *nameptr;
@@ -57,6 +58,7 @@ static int udf_readdir(struct file *file, struct dir_context *ctx)
 	int i, num, ret = 0;
 	struct extent_position epos = { NULL, 0, {0, 0} };
 	struct super_block *sb = dir->i_sb;
+	bool pos_valid = false;
 
 	if (ctx->pos == 0) {
 		if (!dir_emit_dot(file, ctx))
@@ -67,6 +69,21 @@ static int udf_readdir(struct file *file, struct dir_context *ctx)
 	if (nf_pos >= size)
 		goto out;
 
+	/*
+	 * Something changed since last readdir (either lseek was called or dir
+	 * changed)?  We need to verify the position correctly points at the
+	 * beginning of some dir entry so that the directory parsing code does
+	 * not get confused. Since UDF does not have any reliable way of
+	 * identifying beginning of dir entry (names are under user control),
+	 * we need to scan the directory from the beginning.
+	 */
+	if (!inode_eq_iversion(dir, file->f_version)) {
+		emit_pos = nf_pos;
+		nf_pos = 0;
+	} else {
+		pos_valid = true;
+	}
+
 	fname = kmalloc(UDF_NAME_LEN, GFP_NOFS);
 	if (!fname) {
 		ret = -ENOMEM;
@@ -122,13 +139,21 @@ static int udf_readdir(struct file *file, struct dir_context *ctx)
 
 	while (nf_pos < size) {
 		struct kernel_lb_addr tloc;
+		loff_t cur_pos = nf_pos;
 
-		ctx->pos = (nf_pos >> 2) + 1;
+		/* Update file position only if we got past the current one */
+		if (nf_pos >= emit_pos) {
+			ctx->pos = (nf_pos >> 2) + 1;
+			pos_valid = true;
+		}
 
 		fi = udf_fileident_read(dir, &nf_pos, &fibh, &cfi, &epos, &eloc,
 					&elen, &offset);
 		if (!fi)
 			goto out;
+		/* Still not at offset where user asked us to read from? */
+		if (cur_pos < emit_pos)
+			continue;
 
 		liu = le16_to_cpu(cfi.lengthOfImpUse);
 		lfi = cfi.lengthFileIdent;
@@ -186,8 +211,11 @@ static int udf_readdir(struct file *file, struct dir_context *ctx)
 	} /* end while */
 
 	ctx->pos = (nf_pos >> 2) + 1;
+	pos_valid = true;
 
 out:
+	if (pos_valid)
+		file->f_version = inode_query_iversion(dir);
 	if (fibh.sbh != fibh.ebh)
 		brelse(fibh.ebh);
 	brelse(fibh.sbh);
diff --git a/fs/udf/namei.c b/fs/udf/namei.c
index caeef08efed2..0ed4861b038f 100644
--- a/fs/udf/namei.c
+++ b/fs/udf/namei.c
@@ -30,6 +30,7 @@
 #include <linux/sched.h>
 #include <linux/crc-itu-t.h>
 #include <linux/exportfs.h>
+#include <linux/iversion.h>
 
 static inline int udf_match(int len1, const unsigned char *name1, int len2,
 			    const unsigned char *name2)
@@ -134,6 +135,8 @@ int udf_write_fi(struct inode *inode, struct fileIdentDesc *cfi,
 			mark_buffer_dirty_inode(fibh->ebh, inode);
 		mark_buffer_dirty_inode(fibh->sbh, inode);
 	}
+	inode_inc_iversion(inode);
+
 	return 0;
 }
 
diff --git a/fs/udf/super.c b/fs/udf/super.c
index 34247fba6df9..f26b5e0b84b6 100644
--- a/fs/udf/super.c
+++ b/fs/udf/super.c
@@ -57,6 +57,7 @@
 #include <linux/crc-itu-t.h>
 #include <linux/log2.h>
 #include <asm/byteorder.h>
+#include <linux/iversion.h>
 
 #include "udf_sb.h"
 #include "udf_i.h"
@@ -149,6 +150,7 @@ static struct inode *udf_alloc_inode(struct super_block *sb)
 	init_rwsem(&ei->i_data_sem);
 	ei->cached_extent.lstart = -1;
 	spin_lock_init(&ei->i_extent_cache_lock);
+	inode_set_iversion(&ei->vfs_inode, 1);
 
 	return &ei->vfs_inode;
 }
diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c
index d7d875cef07a..1e4ee042d52f 100644
--- a/fs/xfs/libxfs/xfs_ag.c
+++ b/fs/xfs/libxfs/xfs_ag.c
@@ -248,6 +248,7 @@ xfs_initialize_perag(
 		spin_unlock(&mp->m_perag_lock);
 		radix_tree_preload_end();
 
+#ifdef __KERNEL__
 		/* Place kernel structure only init below this point. */
 		spin_lock_init(&pag->pag_ici_lock);
 		spin_lock_init(&pag->pagb_lock);
@@ -257,6 +258,7 @@ xfs_initialize_perag(
 		init_waitqueue_head(&pag->pagb_wait);
 		pag->pagb_count = 0;
 		pag->pagb_tree = RB_ROOT;
+#endif /* __KERNEL__ */
 
 		error = xfs_buf_hash_init(pag);
 		if (error)
diff --git a/fs/xfs/libxfs/xfs_ag.h b/fs/xfs/libxfs/xfs_ag.h
index 3f597cad2c33..e411d51c2589 100644
--- a/fs/xfs/libxfs/xfs_ag.h
+++ b/fs/xfs/libxfs/xfs_ag.h
@@ -64,6 +64,10 @@ struct xfs_perag {
 	/* Blocks reserved for the reverse mapping btree. */
 	struct xfs_ag_resv	pag_rmapbt_resv;
 
+	/* for rcu-safe freeing */
+	struct rcu_head	rcu_head;
+
+#ifdef __KERNEL__
 	/* -- kernel only structures below this line -- */
 
 	/*
@@ -90,9 +94,6 @@ struct xfs_perag {
 	spinlock_t	pag_buf_lock;	/* lock for pag_buf_hash */
 	struct rhashtable pag_buf_hash;
 
-	/* for rcu-safe freeing */
-	struct rcu_head	rcu_head;
-
 	/* background prealloc block trimming */
 	struct delayed_work	pag_blockgc_work;
 
@@ -102,6 +103,7 @@ struct xfs_perag {
 	 * or have some other means to control concurrency.
 	 */
 	struct rhashtable	pagi_unlinked_hash;
+#endif /* __KERNEL__ */
 };
 
 int xfs_initialize_perag(struct xfs_mount *mp, xfs_agnumber_t agcount,
diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c
index fbc9d816882c..23523b802539 100644
--- a/fs/xfs/libxfs/xfs_attr.c
+++ b/fs/xfs/libxfs/xfs_attr.c
@@ -1077,21 +1077,18 @@ xfs_attr_node_hasname(
 
 	state = xfs_da_state_alloc(args);
 	if (statep != NULL)
-		*statep = NULL;
+		*statep = state;
 
 	/*
 	 * Search to see if name exists, and get back a pointer to it.
 	 */
 	error = xfs_da3_node_lookup_int(state, &retval);
-	if (error) {
-		xfs_da_state_free(state);
-		return error;
-	}
+	if (error)
+		retval = error;
 
-	if (statep != NULL)
-		*statep = state;
-	else
+	if (!statep)
 		xfs_da_state_free(state);
+
 	return retval;
 }
 
@@ -1112,7 +1109,7 @@ xfs_attr_node_addname_find_attr(
 	 */
 	retval = xfs_attr_node_hasname(args, &dac->da_state);
 	if (retval != -ENOATTR && retval != -EEXIST)
-		return retval;
+		goto error;
 
 	if (retval == -ENOATTR && (args->attr_flags & XATTR_REPLACE))
 		goto error;
@@ -1337,7 +1334,7 @@ int xfs_attr_node_removename_setup(
 
 	error = xfs_attr_node_hasname(args, state);
 	if (error != -EEXIST)
-		return error;
+		goto out;
 	error = 0;
 
 	ASSERT((*state)->path.blk[(*state)->path.active - 1].bp != NULL);
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index b4e19aacb9de..f18a875f51c6 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -2785,6 +2785,7 @@ error0:
 	return error;
 }
 
+#ifdef __KERNEL__
 struct xfs_btree_split_args {
 	struct xfs_btree_cur	*cur;
 	int			level;
@@ -2870,6 +2871,9 @@ xfs_btree_split(
 	destroy_work_on_stack(&args.work);
 	return args.result;
 }
+#else
+#define xfs_btree_split	__xfs_btree_split
+#endif /* __KERNEL__ */
 
 
 /*
diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c
index dd7a2dbce1d1..9dc1ecb9713d 100644
--- a/fs/xfs/libxfs/xfs_da_btree.c
+++ b/fs/xfs/libxfs/xfs_da_btree.c
@@ -864,7 +864,6 @@ xfs_da3_node_rebalance(
 {
 	struct xfs_da_intnode	*node1;
 	struct xfs_da_intnode	*node2;
-	struct xfs_da_intnode	*tmpnode;
 	struct xfs_da_node_entry *btree1;
 	struct xfs_da_node_entry *btree2;
 	struct xfs_da_node_entry *btree_s;
@@ -894,9 +893,7 @@ xfs_da3_node_rebalance(
 	    ((be32_to_cpu(btree2[0].hashval) < be32_to_cpu(btree1[0].hashval)) ||
 	     (be32_to_cpu(btree2[nodehdr2.count - 1].hashval) <
 			be32_to_cpu(btree1[nodehdr1.count - 1].hashval)))) {
-		tmpnode = node1;
-		node1 = node2;
-		node2 = tmpnode;
+		swap(node1, node2);
 		xfs_da3_node_hdr_from_disk(dp->i_mount, &nodehdr1, node1);
 		xfs_da3_node_hdr_from_disk(dp->i_mount, &nodehdr2, node2);
 		btree1 = nodehdr1.btree;
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index e1472004170e..da4af2142a2b 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -289,22 +289,6 @@ xfs_perag_clear_inode_tag(
 	trace_xfs_perag_clear_inode_tag(mp, pag->pag_agno, tag, _RET_IP_);
 }
 
-static inline void
-xfs_inew_wait(
-	struct xfs_inode	*ip)
-{
-	wait_queue_head_t *wq = bit_waitqueue(&ip->i_flags, __XFS_INEW_BIT);
-	DEFINE_WAIT_BIT(wait, &ip->i_flags, __XFS_INEW_BIT);
-
-	do {
-		prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE);
-		if (!xfs_iflags_test(ip, XFS_INEW))
-			break;
-		schedule();
-	} while (true);
-	finish_wait(wq, &wait.wq_entry);
-}
-
 /*
  * When we recycle a reclaimable inode, we need to re-initialise the VFS inode
  * part of the structure. This is made more complex by the fact we store
@@ -368,18 +352,13 @@ xfs_iget_recycle(
 	ASSERT(!rwsem_is_locked(&inode->i_rwsem));
 	error = xfs_reinit_inode(mp, inode);
 	if (error) {
-		bool	wake;
-
 		/*
 		 * Re-initializing the inode failed, and we are in deep
 		 * trouble.  Try to re-add it to the reclaim list.
 		 */
 		rcu_read_lock();
 		spin_lock(&ip->i_flags_lock);
-		wake = !!__xfs_iflags_test(ip, XFS_INEW);
 		ip->i_flags &= ~(XFS_INEW | XFS_IRECLAIM);
-		if (wake)
-			wake_up_bit(&ip->i_flags, __XFS_INEW_BIT);
 		ASSERT(ip->i_flags & XFS_IRECLAIMABLE);
 		spin_unlock(&ip->i_flags_lock);
 		rcu_read_unlock();
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 64b9bf334806..6771f357ad2c 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -3122,7 +3122,6 @@ xfs_rename(
 	 * appropriately.
 	 */
 	if (flags & RENAME_WHITEOUT) {
-		ASSERT(!(flags & (RENAME_NOREPLACE | RENAME_EXCHANGE)));
 		error = xfs_rename_alloc_whiteout(mnt_userns, target_dp, &wip);
 		if (error)
 			return error;
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index e635a3d64cba..c447bf04205a 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -231,8 +231,7 @@ static inline bool xfs_inode_has_bigtime(struct xfs_inode *ip)
 #define XFS_IRECLAIM		(1 << 0) /* started reclaiming this inode */
 #define XFS_ISTALE		(1 << 1) /* inode has been staled */
 #define XFS_IRECLAIMABLE	(1 << 2) /* inode can be reclaimed */
-#define __XFS_INEW_BIT		3	 /* inode has just been allocated */
-#define XFS_INEW		(1 << __XFS_INEW_BIT)
+#define XFS_INEW		(1 << 3) /* inode has just been allocated */
 #define XFS_IPRESERVE_DM_FIELDS	(1 << 4) /* has legacy DMAPI fields set */
 #define XFS_ITRUNCATED		(1 << 5) /* truncated down so flush-on-close */
 #define XFS_IDIRTY_RELEASE	(1 << 6) /* dirty release already seen */
@@ -492,7 +491,6 @@ static inline void xfs_finish_inode_setup(struct xfs_inode *ip)
 	xfs_iflags_clear(ip, XFS_INEW);
 	barrier();
 	unlock_new_inode(VFS_I(ip));
-	wake_up_bit(&ip->i_flags, __XFS_INEW_BIT);
 }
 
 static inline void xfs_setup_existing_inode(struct xfs_inode *ip)
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index e21459f9923a..778b57b1f020 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -1765,7 +1765,10 @@ static int
 xfs_remount_ro(
 	struct xfs_mount	*mp)
 {
-	int error;
+	struct xfs_icwalk	icw = {
+		.icw_flags	= XFS_ICWALK_FLAG_SYNC,
+	};
+	int			error;
 
 	/*
 	 * Cancel background eofb scanning so it cannot race with the final
@@ -1773,8 +1776,13 @@ xfs_remount_ro(
 	 */
 	xfs_blockgc_stop(mp);
 
-	/* Get rid of any leftover CoW reservations... */
-	error = xfs_blockgc_free_space(mp, NULL);
+	/*
+	 * Clear out all remaining COW staging extents and speculative post-EOF
+	 * preallocations so that we don't leave inodes requiring inactivation
+	 * cleanups during reclaim on a read-only mount.  We must process every
+	 * cached inode, so this requires a synchronous cache scan.
+	 */
+	error = xfs_blockgc_free_space(mp, &icw);
 	if (error) {
 		xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
 		return error;
diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c
index 259ee2bda492..b76dfb310ab6 100644
--- a/fs/zonefs/super.c
+++ b/fs/zonefs/super.c
@@ -1787,5 +1787,6 @@ static void __exit zonefs_exit(void)
 MODULE_AUTHOR("Damien Le Moal");
 MODULE_DESCRIPTION("Zone file system for zoned block devices");
 MODULE_LICENSE("GPL");
+MODULE_ALIAS_FS("zonefs");
 module_init(zonefs_init);
 module_exit(zonefs_exit);
diff --git a/include/asm-generic/cacheflush.h b/include/asm-generic/cacheflush.h
index fedc0dfa4877..4f07afacbc23 100644
--- a/include/asm-generic/cacheflush.h
+++ b/include/asm-generic/cacheflush.h
@@ -50,13 +50,7 @@ static inline void flush_dcache_page(struct page *page)
 {
 }
 
-static inline void flush_dcache_folio(struct folio *folio) { }
 #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0
-#define ARCH_IMPLEMENTS_FLUSH_DCACHE_FOLIO
-#endif
-
-#ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_FOLIO
-void flush_dcache_folio(struct folio *folio);
 #endif
 
 #ifndef flush_dcache_mmap_lock
diff --git a/include/dt-bindings/clock/jz4725b-cgu.h b/include/dt-bindings/clock/ingenic,jz4725b-cgu.h
index 31f1ab0fe42c..31f1ab0fe42c 100644
--- a/include/dt-bindings/clock/jz4725b-cgu.h
+++ b/include/dt-bindings/clock/ingenic,jz4725b-cgu.h
diff --git a/include/dt-bindings/clock/jz4740-cgu.h b/include/dt-bindings/clock/ingenic,jz4740-cgu.h
index e82d77028581..e82d77028581 100644
--- a/include/dt-bindings/clock/jz4740-cgu.h
+++ b/include/dt-bindings/clock/ingenic,jz4740-cgu.h
diff --git a/include/dt-bindings/clock/jz4760-cgu.h b/include/dt-bindings/clock/ingenic,jz4760-cgu.h
index 4bb2e19c4743..4bb2e19c4743 100644
--- a/include/dt-bindings/clock/jz4760-cgu.h
+++ b/include/dt-bindings/clock/ingenic,jz4760-cgu.h
diff --git a/include/dt-bindings/clock/jz4770-cgu.h b/include/dt-bindings/clock/ingenic,jz4770-cgu.h
index d68a7695a1f8..d68a7695a1f8 100644
--- a/include/dt-bindings/clock/jz4770-cgu.h
+++ b/include/dt-bindings/clock/ingenic,jz4770-cgu.h
diff --git a/include/dt-bindings/clock/jz4780-cgu.h b/include/dt-bindings/clock/ingenic,jz4780-cgu.h
index 85cf8eb5081b..85cf8eb5081b 100644
--- a/include/dt-bindings/clock/jz4780-cgu.h
+++ b/include/dt-bindings/clock/ingenic,jz4780-cgu.h
diff --git a/include/dt-bindings/clock/x1000-cgu.h b/include/dt-bindings/clock/ingenic,x1000-cgu.h
index f187e0719fd3..f187e0719fd3 100644
--- a/include/dt-bindings/clock/x1000-cgu.h
+++ b/include/dt-bindings/clock/ingenic,x1000-cgu.h
diff --git a/include/dt-bindings/clock/x1830-cgu.h b/include/dt-bindings/clock/ingenic,x1830-cgu.h
index 88455376a950..88455376a950 100644
--- a/include/dt-bindings/clock/x1830-cgu.h
+++ b/include/dt-bindings/clock/ingenic,x1830-cgu.h
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 143ce7e0bee1..b28f8790192a 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -974,6 +974,15 @@ static inline int acpi_get_local_address(acpi_handle handle, u32 *addr)
 	return -ENODEV;
 }
 
+static inline int acpi_register_wakeup_handler(int wake_irq,
+	bool (*wakeup)(void *context), void *context)
+{
+	return -ENXIO;
+}
+
+static inline void acpi_unregister_wakeup_handler(
+	bool (*wakeup)(void *context), void *context) { }
+
 #endif	/* !CONFIG_ACPI */
 
 #ifdef CONFIG_ACPI_HOTPLUG_IOAPIC
@@ -1173,7 +1182,6 @@ int acpi_node_prop_get(const struct fwnode_handle *fwnode, const char *propname,
 
 struct fwnode_handle *acpi_get_next_subnode(const struct fwnode_handle *fwnode,
 					    struct fwnode_handle *child);
-struct fwnode_handle *acpi_node_get_parent(const struct fwnode_handle *fwnode);
 
 struct acpi_probe_entry;
 typedef bool (*acpi_probe_entry_validate_subtbl)(struct acpi_subtable_header *,
@@ -1279,12 +1287,6 @@ acpi_get_next_subnode(const struct fwnode_handle *fwnode,
 }
 
 static inline struct fwnode_handle *
-acpi_node_get_parent(const struct fwnode_handle *fwnode)
-{
-	return NULL;
-}
-
-static inline struct fwnode_handle *
 acpi_graph_get_next_endpoint(const struct fwnode_handle *fwnode,
 			     struct fwnode_handle *prev)
 {
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index f715e8863f4d..755f38e893be 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -193,7 +193,7 @@ struct bpf_map {
 	atomic64_t usercnt;
 	struct work_struct work;
 	struct mutex freeze_mutex;
-	u64 writecnt; /* writable mmap cnt; protected by freeze_mutex */
+	atomic64_t writecnt;
 };
 
 static inline bool map_value_has_spin_lock(const struct bpf_map *map)
@@ -732,6 +732,7 @@ int bpf_trampoline_unlink_prog(struct bpf_prog *prog, struct bpf_trampoline *tr)
 struct bpf_trampoline *bpf_trampoline_get(u64 key,
 					  struct bpf_attach_target_info *tgt_info);
 void bpf_trampoline_put(struct bpf_trampoline *tr);
+int arch_prepare_bpf_dispatcher(void *image, s64 *funcs, int num_funcs);
 #define BPF_DISPATCHER_INIT(_name) {				\
 	.mutex = __MUTEX_INITIALIZER(_name.mutex),		\
 	.func = &_name##_func,					\
@@ -1352,28 +1353,16 @@ extern struct mutex bpf_stats_enabled_mutex;
  * kprobes, tracepoints) to prevent deadlocks on map operations as any of
  * these events can happen inside a region which holds a map bucket lock
  * and can deadlock on it.
- *
- * Use the preemption safe inc/dec variants on RT because migrate disable
- * is preemptible on RT and preemption in the middle of the RMW operation
- * might lead to inconsistent state. Use the raw variants for non RT
- * kernels as migrate_disable() maps to preempt_disable() so the slightly
- * more expensive save operation can be avoided.
  */
 static inline void bpf_disable_instrumentation(void)
 {
 	migrate_disable();
-	if (IS_ENABLED(CONFIG_PREEMPT_RT))
-		this_cpu_inc(bpf_prog_active);
-	else
-		__this_cpu_inc(bpf_prog_active);
+	this_cpu_inc(bpf_prog_active);
 }
 
 static inline void bpf_enable_instrumentation(void)
 {
-	if (IS_ENABLED(CONFIG_PREEMPT_RT))
-		this_cpu_dec(bpf_prog_active);
-	else
-		__this_cpu_dec(bpf_prog_active);
+	this_cpu_dec(bpf_prog_active);
 	migrate_enable();
 }
 
@@ -1419,6 +1408,7 @@ void bpf_map_put(struct bpf_map *map);
 void *bpf_map_area_alloc(u64 size, int numa_node);
 void *bpf_map_area_mmapable_alloc(u64 size, int numa_node);
 void bpf_map_area_free(void *base);
+bool bpf_map_write_active(const struct bpf_map *map);
 void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr);
 int  generic_map_lookup_batch(struct bpf_map *map,
 			      const union bpf_attr *attr,
diff --git a/include/linux/btf.h b/include/linux/btf.h
index 203eef993d76..0e1b6281fd8f 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -245,7 +245,10 @@ struct kfunc_btf_id_set {
 	struct module *owner;
 };
 
-struct kfunc_btf_id_list;
+struct kfunc_btf_id_list {
+	struct list_head list;
+	struct mutex mutex;
+};
 
 #ifdef CONFIG_DEBUG_INFO_BTF_MODULES
 void register_kfunc_btf_id_set(struct kfunc_btf_id_list *l,
@@ -254,6 +257,9 @@ void unregister_kfunc_btf_id_set(struct kfunc_btf_id_list *l,
 				 struct kfunc_btf_id_set *s);
 bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, u32 kfunc_id,
 			      struct module *owner);
+
+extern struct kfunc_btf_id_list bpf_tcp_ca_kfunc_list;
+extern struct kfunc_btf_id_list prog_test_kfunc_list;
 #else
 static inline void register_kfunc_btf_id_set(struct kfunc_btf_id_list *l,
 					     struct kfunc_btf_id_set *s)
@@ -268,13 +274,13 @@ static inline bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist,
 {
 	return false;
 }
+
+static struct kfunc_btf_id_list bpf_tcp_ca_kfunc_list __maybe_unused;
+static struct kfunc_btf_id_list prog_test_kfunc_list __maybe_unused;
 #endif
 
 #define DEFINE_KFUNC_BTF_ID_SET(set, name)                                     \
 	struct kfunc_btf_id_set name = { LIST_HEAD_INIT(name.list), (set),     \
 					 THIS_MODULE }
 
-extern struct kfunc_btf_id_list bpf_tcp_ca_kfunc_list;
-extern struct kfunc_btf_id_list prog_test_kfunc_list;
-
 #endif
diff --git a/include/linux/cacheflush.h b/include/linux/cacheflush.h
new file mode 100644
index 000000000000..fef8b607f97e
--- /dev/null
+++ b/include/linux/cacheflush.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_CACHEFLUSH_H
+#define _LINUX_CACHEFLUSH_H
+
+#include <asm/cacheflush.h>
+
+#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE
+#ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_FOLIO
+void flush_dcache_folio(struct folio *folio);
+#endif
+#else
+static inline void flush_dcache_folio(struct folio *folio)
+{
+}
+#define ARCH_IMPLEMENTS_FLUSH_DCACHE_FOLIO 0
+#endif /* ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE */
+
+#endif /* _LINUX_CACHEFLUSH_H */
diff --git a/include/linux/cacheinfo.h b/include/linux/cacheinfo.h
index 2f909ed084c6..4ff37cb763ae 100644
--- a/include/linux/cacheinfo.h
+++ b/include/linux/cacheinfo.h
@@ -3,7 +3,6 @@
 #define _LINUX_CACHEINFO_H
 
 #include <linux/bitops.h>
-#include <linux/cpu.h>
 #include <linux/cpumask.h>
 #include <linux/smp.h>
 
diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h
index bc2699feddbe..7ad6c3d0db7d 100644
--- a/include/linux/ceph/ceph_fs.h
+++ b/include/linux/ceph/ceph_fs.h
@@ -302,6 +302,8 @@ enum {
 	CEPH_SESSION_REQUEST_FLUSH_MDLOG,
 };
 
+#define CEPH_SESSION_BLOCKLISTED	(1 << 0)  /* session blocklisted */
+
 extern const char *ceph_session_op_name(int op);
 
 struct ceph_mds_session_head {
diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index 83fa08a06507..3431011f364d 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -475,6 +475,14 @@ extern void osd_req_op_alloc_hint_init(struct ceph_osd_request *osd_req,
 				       u64 expected_object_size,
 				       u64 expected_write_size,
 				       u32 flags);
+extern int osd_req_op_copy_from_init(struct ceph_osd_request *req,
+				     u64 src_snapid, u64 src_version,
+				     struct ceph_object_id *src_oid,
+				     struct ceph_object_locator *src_oloc,
+				     u32 src_fadvise_flags,
+				     u32 dst_fadvise_flags,
+				     u32 truncate_seq, u64 truncate_size,
+				     u8 copy_from_flags);
 
 extern struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc,
 					       struct ceph_snap_context *snapc,
@@ -515,17 +523,6 @@ int ceph_osdc_call(struct ceph_osd_client *osdc,
 		   struct page *req_page, size_t req_len,
 		   struct page **resp_pages, size_t *resp_len);
 
-int ceph_osdc_copy_from(struct ceph_osd_client *osdc,
-			u64 src_snapid, u64 src_version,
-			struct ceph_object_id *src_oid,
-			struct ceph_object_locator *src_oloc,
-			u32 src_fadvise_flags,
-			struct ceph_object_id *dst_oid,
-			struct ceph_object_locator *dst_oloc,
-			u32 dst_fadvise_flags,
-			u32 truncate_seq, u64 truncate_size,
-			u8 copy_from_flags);
-
 /* watch/notify */
 struct ceph_osd_linger_request *
 ceph_osdc_watch(struct ceph_osd_client *osdc,
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 3d5af56337bd..429dcebe2b99 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -121,7 +121,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 	asm volatile(__stringify_label(c) ":\n\t"			\
 		     ".pushsection .discard.reachable\n\t"		\
 		     ".long " __stringify_label(c) "b - .\n\t"		\
-		     ".popsection\n\t");				\
+		     ".popsection\n\t" : : "i" (c));			\
 })
 #define annotate_reachable() __annotate_reachable(__COUNTER__)
 
@@ -129,7 +129,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 	asm volatile(__stringify_label(c) ":\n\t"			\
 		     ".pushsection .discard.unreachable\n\t"		\
 		     ".long " __stringify_label(c) "b - .\n\t"		\
-		     ".popsection\n\t");				\
+		     ".popsection\n\t" : : "i" (c));			\
 })
 #define annotate_unreachable() __annotate_unreachable(__COUNTER__)
 
diff --git a/include/linux/delay.h b/include/linux/delay.h
index 8eacf67eb212..039e7e0c7378 100644
--- a/include/linux/delay.h
+++ b/include/linux/delay.h
@@ -20,6 +20,7 @@
  */
 
 #include <linux/math.h>
+#include <linux/sched.h>
 
 extern unsigned long loops_per_jiffy;
 
@@ -58,7 +59,18 @@ void calibrate_delay(void);
 void __attribute__((weak)) calibration_delay_done(void);
 void msleep(unsigned int msecs);
 unsigned long msleep_interruptible(unsigned int msecs);
-void usleep_range(unsigned long min, unsigned long max);
+void usleep_range_state(unsigned long min, unsigned long max,
+			unsigned int state);
+
+static inline void usleep_range(unsigned long min, unsigned long max)
+{
+	usleep_range_state(min, max, TASK_UNINTERRUPTIBLE);
+}
+
+static inline void usleep_idle_range(unsigned long min, unsigned long max)
+{
+	usleep_range_state(min, max, TASK_IDLE);
+}
 
 static inline void ssleep(unsigned int seconds)
 {
diff --git a/include/linux/device/driver.h b/include/linux/device/driver.h
index a498ebcf4993..15e7c5e15d62 100644
--- a/include/linux/device/driver.h
+++ b/include/linux/device/driver.h
@@ -18,6 +18,7 @@
 #include <linux/klist.h>
 #include <linux/pm.h>
 #include <linux/device/bus.h>
+#include <linux/module.h>
 
 /**
  * enum probe_type - device driver probe type to try
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 6b5d36babfcc..ef8dbc0a1522 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -362,6 +362,7 @@ void efi_native_runtime_setup(void);
 
 /* OEM GUIDs */
 #define DELLEMC_EFI_RCI2_TABLE_GUID		EFI_GUID(0x2d9f28a2, 0xa886, 0x456a,  0x97, 0xa8, 0xf1, 0x1e, 0xf2, 0x4f, 0xf4, 0x55)
+#define AMD_SEV_MEM_ENCRYPT_GUID		EFI_GUID(0x0cf29b71, 0x9e51, 0x433a,  0xa3, 0xb7, 0x81, 0xf3, 0xab, 0x16, 0xb8, 0x75)
 
 typedef struct {
 	efi_guid_t guid;
@@ -1282,4 +1283,10 @@ static inline struct efi_mokvar_table_entry *efi_mokvar_entry_find(
 }
 #endif
 
+#ifdef CONFIG_SYSFB
+extern void efifb_setup_from_dmi(struct screen_info *si, const char *opt);
+#else
+static inline void efifb_setup_from_dmi(struct screen_info *si, const char *opt) { }
+#endif
+
 #endif /* _LINUX_EFI_H */
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 24b7ed2677af..7f1e88e3e2b5 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -6,6 +6,7 @@
 #define __LINUX_FILTER_H__
 
 #include <linux/atomic.h>
+#include <linux/bpf.h>
 #include <linux/refcount.h>
 #include <linux/compat.h>
 #include <linux/skbuff.h>
@@ -26,7 +27,6 @@
 
 #include <asm/byteorder.h>
 #include <uapi/linux/filter.h>
-#include <uapi/linux/bpf.h>
 
 struct sk_buff;
 struct sock;
@@ -640,9 +640,6 @@ static __always_inline u32 bpf_prog_run(const struct bpf_prog *prog, const void
  * This uses migrate_disable/enable() explicitly to document that the
  * invocation of a BPF program does not require reentrancy protection
  * against a BPF program which is invoked from a preempting task.
- *
- * For non RT enabled kernels migrate_disable/enable() maps to
- * preempt_disable/enable(), i.e. it disables also preemption.
  */
 static inline u32 bpf_prog_run_pin_on_cpu(const struct bpf_prog *prog,
 					  const void *ctx)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 1cb616fc1105..bbf812ce89a8 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2518,7 +2518,6 @@ struct file_system_type {
 #define FS_USERNS_MOUNT		8	/* Can be mounted by userns root */
 #define FS_DISALLOW_NOTIFY_PERM	16	/* Disable fanotify permission events */
 #define FS_ALLOW_IDMAP         32      /* FS has been updated to handle vfs idmappings. */
-#define FS_THP_SUPPORT		8192	/* Remove once all fs converted */
 #define FS_RENAME_DOES_D_MOVE	32768	/* FS will handle d_move() during rename() internally. */
 	int (*init_fs_context)(struct fs_context *);
 	const struct fs_parameter_spec *parameters;
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 462634b4b48f..74c410263113 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -205,9 +205,9 @@ static inline dev_t disk_devt(struct gendisk *disk)
 void disk_uevent(struct gendisk *disk, enum kobject_action action);
 
 /* block/genhd.c */
-int device_add_disk(struct device *parent, struct gendisk *disk,
-		const struct attribute_group **groups);
-static inline int add_disk(struct gendisk *disk)
+int __must_check device_add_disk(struct device *parent, struct gendisk *disk,
+				 const struct attribute_group **groups);
+static inline int __must_check add_disk(struct gendisk *disk)
 {
 	return device_add_disk(NULL, disk, NULL);
 }
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index b976c4177299..8fcc38467af6 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -624,7 +624,7 @@ extern unsigned long get_zeroed_page(gfp_t gfp_mask);
 
 void *alloc_pages_exact(size_t size, gfp_t gfp_mask) __alloc_size(1);
 void free_pages_exact(void *virt, size_t size);
-__meminit void *alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask) __alloc_size(1);
+__meminit void *alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask) __alloc_size(2);
 
 #define __get_free_page(gfp_mask) \
 		__get_free_pages((gfp_mask), 0)
diff --git a/include/linux/hid.h b/include/linux/hid.h
index 9e067f937dbc..f453be385bd4 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -840,6 +840,11 @@ static inline bool hid_is_using_ll_driver(struct hid_device *hdev,
 	return hdev->ll_driver == driver;
 }
 
+static inline bool hid_is_usb(struct hid_device *hdev)
+{
+	return hid_is_using_ll_driver(hdev, &usb_hid_driver);
+}
+
 #define	PM_HINT_FULLON	1<<5
 #define PM_HINT_NORMAL	1<<1
 
diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index 25aff0f2ed0b..39bb9b47fa9c 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -5,12 +5,11 @@
 #include <linux/fs.h>
 #include <linux/kernel.h>
 #include <linux/bug.h>
+#include <linux/cacheflush.h>
 #include <linux/mm.h>
 #include <linux/uaccess.h>
 #include <linux/hardirq.h>
 
-#include <asm/cacheflush.h>
-
 #include "highmem-internal.h"
 
 /**
@@ -231,10 +230,10 @@ static inline void tag_clear_highpage(struct page *page)
  * If we pass in a base or tail page, we can zero up to PAGE_SIZE.
  * If we pass in a head page, we can zero up to the size of the compound page.
  */
-#if defined(CONFIG_HIGHMEM) && defined(CONFIG_TRANSPARENT_HUGEPAGE)
+#ifdef CONFIG_HIGHMEM
 void zero_user_segments(struct page *page, unsigned start1, unsigned end1,
 		unsigned start2, unsigned end2);
-#else /* !HIGHMEM || !TRANSPARENT_HUGEPAGE */
+#else
 static inline void zero_user_segments(struct page *page,
 		unsigned start1, unsigned end1,
 		unsigned start2, unsigned end2)
@@ -254,7 +253,7 @@ static inline void zero_user_segments(struct page *page,
 	for (i = 0; i < compound_nr(page); i++)
 		flush_dcache_page(page + i);
 }
-#endif /* !HIGHMEM || !TRANSPARENT_HUGEPAGE */
+#endif
 
 static inline void zero_user_segment(struct page *page,
 	unsigned start, unsigned end)
@@ -364,4 +363,42 @@ static inline void memzero_page(struct page *page, size_t offset, size_t len)
 	kunmap_local(addr);
 }
 
+/**
+ * folio_zero_segments() - Zero two byte ranges in a folio.
+ * @folio: The folio to write to.
+ * @start1: The first byte to zero.
+ * @xend1: One more than the last byte in the first range.
+ * @start2: The first byte to zero in the second range.
+ * @xend2: One more than the last byte in the second range.
+ */
+static inline void folio_zero_segments(struct folio *folio,
+		size_t start1, size_t xend1, size_t start2, size_t xend2)
+{
+	zero_user_segments(&folio->page, start1, xend1, start2, xend2);
+}
+
+/**
+ * folio_zero_segment() - Zero a byte range in a folio.
+ * @folio: The folio to write to.
+ * @start: The first byte to zero.
+ * @xend: One more than the last byte to zero.
+ */
+static inline void folio_zero_segment(struct folio *folio,
+		size_t start, size_t xend)
+{
+	zero_user_segments(&folio->page, start, xend, 0, 0);
+}
+
+/**
+ * folio_zero_range() - Zero a byte range in a folio.
+ * @folio: The folio to write to.
+ * @start: The first byte to zero.
+ * @length: The number of bytes to zero.
+ */
+static inline void folio_zero_range(struct folio *folio,
+		size_t start, size_t length)
+{
+	zero_user_segments(&folio->page, start, start + length, 0, 0);
+}
+
 #endif /* _LINUX_HIGHMEM_H */
diff --git a/include/linux/hugetlb_cgroup.h b/include/linux/hugetlb_cgroup.h
index c137396129db..ba025ae27882 100644
--- a/include/linux/hugetlb_cgroup.h
+++ b/include/linux/hugetlb_cgroup.h
@@ -128,6 +128,13 @@ static inline void resv_map_dup_hugetlb_cgroup_uncharge_info(
 		css_get(resv_map->css);
 }
 
+static inline void resv_map_put_hugetlb_cgroup_uncharge_info(
+						struct resv_map *resv_map)
+{
+	if (resv_map->css)
+		css_put(resv_map->css);
+}
+
 extern int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages,
 					struct hugetlb_cgroup **ptr);
 extern int hugetlb_cgroup_charge_cgroup_rsvd(int idx, unsigned long nr_pages,
@@ -211,6 +218,11 @@ static inline void resv_map_dup_hugetlb_cgroup_uncharge_info(
 {
 }
 
+static inline void resv_map_put_hugetlb_cgroup_uncharge_info(
+						struct resv_map *resv_map)
+{
+}
+
 static inline int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages,
 					       struct hugetlb_cgroup **ptr)
 {
diff --git a/include/linux/instrumentation.h b/include/linux/instrumentation.h
index fa2cd8c63dcc..24359b4a9605 100644
--- a/include/linux/instrumentation.h
+++ b/include/linux/instrumentation.h
@@ -11,7 +11,7 @@
 	asm volatile(__stringify(c) ": nop\n\t"				\
 		     ".pushsection .discard.instr_begin\n\t"		\
 		     ".long " __stringify(c) "b - .\n\t"		\
-		     ".popsection\n\t");				\
+		     ".popsection\n\t" : : "i" (c));			\
 })
 #define instrumentation_begin() __instrumentation_begin(__COUNTER__)
 
@@ -50,7 +50,7 @@
 	asm volatile(__stringify(c) ": nop\n\t"				\
 		     ".pushsection .discard.instr_end\n\t"		\
 		     ".long " __stringify(c) "b - .\n\t"		\
-		     ".popsection\n\t");				\
+		     ".popsection\n\t" : : "i" (c));			\
 })
 #define instrumentation_end() __instrumentation_end(__COUNTER__)
 #else
diff --git a/include/linux/intel-ish-client-if.h b/include/linux/intel-ish-client-if.h
index aee8ff4739b1..f45f13304add 100644
--- a/include/linux/intel-ish-client-if.h
+++ b/include/linux/intel-ish-client-if.h
@@ -9,7 +9,7 @@
 #define _INTEL_ISH_CLIENT_IF_H_
 
 #include <linux/device.h>
-#include <linux/uuid.h>
+#include <linux/mod_devicetable.h>
 
 struct ishtp_cl_device;
 struct ishtp_device;
@@ -40,7 +40,7 @@ enum cl_state {
 struct ishtp_cl_driver {
 	struct device_driver driver;
 	const char *name;
-	const guid_t *guid;
+	const struct ishtp_device_id *id;
 	int (*probe)(struct ishtp_cl_device *dev);
 	void (*remove)(struct ishtp_cl_device *dev);
 	int (*reset)(struct ishtp_cl_device *dev);
diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h
index 05e22770af51..b75395ec8d52 100644
--- a/include/linux/ipc_namespace.h
+++ b/include/linux/ipc_namespace.h
@@ -131,6 +131,16 @@ static inline struct ipc_namespace *get_ipc_ns(struct ipc_namespace *ns)
 	return ns;
 }
 
+static inline struct ipc_namespace *get_ipc_ns_not_zero(struct ipc_namespace *ns)
+{
+	if (ns) {
+		if (refcount_inc_not_zero(&ns->ns.count))
+			return ns;
+	}
+
+	return NULL;
+}
+
 extern void put_ipc_ns(struct ipc_namespace *ns);
 #else
 static inline struct ipc_namespace *copy_ipcs(unsigned long flags,
@@ -147,6 +157,11 @@ static inline struct ipc_namespace *get_ipc_ns(struct ipc_namespace *ns)
 	return ns;
 }
 
+static inline struct ipc_namespace *get_ipc_ns_not_zero(struct ipc_namespace *ns)
+{
+	return ns;
+}
+
 static inline void put_ipc_ns(struct ipc_namespace *ns)
 {
 }
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 968b4c4fe65b..77755ac3e189 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -85,7 +85,7 @@
 struct completion;
 struct user;
 
-#ifdef CONFIG_PREEMPT_VOLUNTARY
+#ifdef CONFIG_PREEMPT_VOLUNTARY_BUILD
 
 extern int __cond_resched(void);
 # define might_resched() __cond_resched()
diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index e974caf39d3e..8c8f7a4d93af 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -153,6 +153,8 @@ struct kretprobe {
 	struct kretprobe_holder *rph;
 };
 
+#define KRETPROBE_MAX_DATA_SIZE	4096
+
 struct kretprobe_instance {
 	union {
 		struct freelist_node freelist;
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 60a35d9fe259..c310648cc8f1 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -150,7 +150,7 @@ static inline bool is_error_page(struct page *page)
 #define KVM_REQ_MMU_RELOAD        (1 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
 #define KVM_REQ_UNBLOCK           2
 #define KVM_REQ_UNHALT            3
-#define KVM_REQ_VM_BUGGED         (4 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
+#define KVM_REQ_VM_DEAD           (4 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
 #define KVM_REQUEST_ARCH_BASE     8
 
 #define KVM_ARCH_REQ_FLAGS(nr, flags) ({ \
@@ -617,6 +617,7 @@ struct kvm {
 	unsigned int max_halt_poll_ns;
 	u32 dirty_ring_size;
 	bool vm_bugged;
+	bool vm_dead;
 
 #ifdef CONFIG_HAVE_KVM_PM_NOTIFIER
 	struct notifier_block pm_notifier;
@@ -650,12 +651,19 @@ struct kvm {
 #define vcpu_err(vcpu, fmt, ...)					\
 	kvm_err("vcpu%i " fmt, (vcpu)->vcpu_id, ## __VA_ARGS__)
 
+static inline void kvm_vm_dead(struct kvm *kvm)
+{
+	kvm->vm_dead = true;
+	kvm_make_all_cpus_request(kvm, KVM_REQ_VM_DEAD);
+}
+
 static inline void kvm_vm_bugged(struct kvm *kvm)
 {
 	kvm->vm_bugged = true;
-	kvm_make_all_cpus_request(kvm, KVM_REQ_VM_BUGGED);
+	kvm_vm_dead(kvm);
 }
 
+
 #define KVM_BUG(cond, kvm, fmt...)				\
 ({								\
 	int __ret = (cond);					\
@@ -866,7 +874,7 @@ void kvm_release_pfn_dirty(kvm_pfn_t pfn);
 void kvm_set_pfn_dirty(kvm_pfn_t pfn);
 void kvm_set_pfn_accessed(kvm_pfn_t pfn);
 
-void kvm_release_pfn(kvm_pfn_t pfn, bool dirty, struct gfn_to_pfn_cache *cache);
+void kvm_release_pfn(kvm_pfn_t pfn, bool dirty);
 int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset,
 			int len);
 int kvm_read_guest(struct kvm *kvm, gpa_t gpa, void *data, unsigned long len);
@@ -942,12 +950,8 @@ struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn
 kvm_pfn_t kvm_vcpu_gfn_to_pfn_atomic(struct kvm_vcpu *vcpu, gfn_t gfn);
 kvm_pfn_t kvm_vcpu_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn);
 int kvm_vcpu_map(struct kvm_vcpu *vcpu, gpa_t gpa, struct kvm_host_map *map);
-int kvm_map_gfn(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map,
-		struct gfn_to_pfn_cache *cache, bool atomic);
 struct page *kvm_vcpu_gfn_to_page(struct kvm_vcpu *vcpu, gfn_t gfn);
 void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty);
-int kvm_unmap_gfn(struct kvm_vcpu *vcpu, struct kvm_host_map *map,
-		  struct gfn_to_pfn_cache *cache, bool dirty, bool atomic);
 unsigned long kvm_vcpu_gfn_to_hva(struct kvm_vcpu *vcpu, gfn_t gfn);
 unsigned long kvm_vcpu_gfn_to_hva_prot(struct kvm_vcpu *vcpu, gfn_t gfn, bool *writable);
 int kvm_vcpu_read_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, void *data, int offset,
diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h
index 2237abb93ccd..234eab059839 100644
--- a/include/linux/kvm_types.h
+++ b/include/linux/kvm_types.h
@@ -53,13 +53,6 @@ struct gfn_to_hva_cache {
 	struct kvm_memory_slot *memslot;
 };
 
-struct gfn_to_pfn_cache {
-	u64 generation;
-	gfn_t gfn;
-	kvm_pfn_t pfn;
-	bool dirty;
-};
-
 #ifdef KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE
 /*
  * Memory caches are used to preallocate memory ahead of various MMU flows,
diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h
index 442a611fa0fb..df8de62f4710 100644
--- a/include/linux/lsm_hook_defs.h
+++ b/include/linux/lsm_hook_defs.h
@@ -335,8 +335,6 @@ LSM_HOOK(int, 0, sctp_bind_connect, struct sock *sk, int optname,
 	 struct sockaddr *address, int addrlen)
 LSM_HOOK(void, LSM_RET_VOID, sctp_sk_clone, struct sctp_association *asoc,
 	 struct sock *sk, struct sock *newsk)
-LSM_HOOK(void, LSM_RET_VOID, sctp_assoc_established, struct sctp_association *asoc,
-	 struct sk_buff *skb)
 #endif /* CONFIG_SECURITY_NETWORK */
 
 #ifdef CONFIG_SECURITY_INFINIBAND
diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h
index d6823214d5c1..d45b6f6e27fd 100644
--- a/include/linux/lsm_hooks.h
+++ b/include/linux/lsm_hooks.h
@@ -1050,11 +1050,6 @@
  *	@asoc pointer to current sctp association structure.
  *	@sk pointer to current sock structure.
  *	@newsk pointer to new sock structure.
- * @sctp_assoc_established:
- *	Passes the @asoc and @chunk->skb of the association COOKIE_ACK packet
- *	to the security module.
- *	@asoc pointer to sctp association structure.
- *	@skb pointer to skbuff of association packet.
  *
  * Security hooks for Infiniband
  *
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index 8adcf1fa8096..9dc7cb239d21 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -405,8 +405,8 @@ phys_addr_t memblock_alloc_range_nid(phys_addr_t size,
 				      phys_addr_t end, int nid, bool exact_nid);
 phys_addr_t memblock_phys_alloc_try_nid(phys_addr_t size, phys_addr_t align, int nid);
 
-static inline phys_addr_t memblock_phys_alloc(phys_addr_t size,
-					      phys_addr_t align)
+static __always_inline phys_addr_t memblock_phys_alloc(phys_addr_t size,
+						       phys_addr_t align)
 {
 	return memblock_phys_alloc_range(size, align, 0,
 					 MEMBLOCK_ALLOC_ACCESSIBLE);
diff --git a/include/linux/mhi.h b/include/linux/mhi.h
index 723985879035..a5cc4cdf9cc8 100644
--- a/include/linux/mhi.h
+++ b/include/linux/mhi.h
@@ -664,6 +664,19 @@ int mhi_pm_suspend(struct mhi_controller *mhi_cntrl);
 int mhi_pm_resume(struct mhi_controller *mhi_cntrl);
 
 /**
+ * mhi_pm_resume_force - Force resume MHI from suspended state
+ * @mhi_cntrl: MHI controller
+ *
+ * Resume the device irrespective of its MHI state. As per the MHI spec, devices
+ * has to be in M3 state during resume. But some devices seem to be in a
+ * different MHI state other than M3 but they continue working fine if allowed.
+ * This API is intented to be used for such devices.
+ *
+ * Return: 0 if the resume succeeds, a negative error code otherwise
+ */
+int mhi_pm_resume_force(struct mhi_controller *mhi_cntrl);
+
+/**
  * mhi_download_rddm_image - Download ramdump image from device for
  *                           debugging purpose.
  * @mhi_cntrl: MHI controller
diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h
index 97afcea39a7b..8b18fe9771f9 100644
--- a/include/linux/mlx5/eswitch.h
+++ b/include/linux/mlx5/eswitch.h
@@ -145,13 +145,13 @@ u32 mlx5_eswitch_get_vport_metadata_for_set(struct mlx5_eswitch *esw,
 	GENMASK(31 - ESW_TUN_ID_BITS - ESW_RESERVED_BITS, \
 		ESW_TUN_OPTS_OFFSET + 1)
 
-u8 mlx5_eswitch_mode(struct mlx5_core_dev *dev);
+u8 mlx5_eswitch_mode(const struct mlx5_core_dev *dev);
 u16 mlx5_eswitch_get_total_vports(const struct mlx5_core_dev *dev);
 struct mlx5_core_dev *mlx5_eswitch_get_core_dev(struct mlx5_eswitch *esw);
 
 #else  /* CONFIG_MLX5_ESWITCH */
 
-static inline u8 mlx5_eswitch_mode(struct mlx5_core_dev *dev)
+static inline u8 mlx5_eswitch_mode(const struct mlx5_core_dev *dev)
 {
 	return MLX5_ESWITCH_NONE;
 }
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 3636df90899a..fbaab440a484 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -9698,7 +9698,10 @@ struct mlx5_ifc_mcam_access_reg_bits {
 	u8         regs_84_to_68[0x11];
 	u8         tracer_registers[0x4];
 
-	u8         regs_63_to_32[0x20];
+	u8         regs_63_to_46[0x12];
+	u8         mrtc[0x1];
+	u8         regs_44_to_32[0xd];
+
 	u8         regs_31_to_0[0x20];
 };
 
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index bb8c6f5f19bc..c3a6e6209600 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -105,7 +105,18 @@ struct page {
 			struct page_pool *pp;
 			unsigned long _pp_mapping_pad;
 			unsigned long dma_addr;
-			atomic_long_t pp_frag_count;
+			union {
+				/**
+				 * dma_addr_upper: might require a 64-bit
+				 * value on 32-bit architectures.
+				 */
+				unsigned long dma_addr_upper;
+				/**
+				 * For frag page support, not supported in
+				 * 32-bit architectures with 64-bit DMA.
+				 */
+				atomic_long_t pp_frag_count;
+			};
 		};
 		struct {	/* slab, slob and slub */
 			union {
diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h
index ae2e75d15b21..4bb71979a8fd 100644
--- a/include/linux/mod_devicetable.h
+++ b/include/linux/mod_devicetable.h
@@ -895,4 +895,18 @@ struct dfl_device_id {
 	kernel_ulong_t driver_data;
 };
 
+/* ISHTP (Integrated Sensor Hub Transport Protocol) */
+
+#define ISHTP_MODULE_PREFIX	"ishtp:"
+
+/**
+ * struct ishtp_device_id - ISHTP device identifier
+ * @guid: GUID of the device.
+ * @driver_data: pointer to driver specific data
+ */
+struct ishtp_device_id {
+	guid_t guid;
+	kernel_ulong_t driver_data;
+};
+
 #endif /* LINUX_MOD_DEVICETABLE_H */
diff --git a/include/linux/msi.h b/include/linux/msi.h
index 49cf6eb222e7..e616f94c7c58 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -148,7 +148,7 @@ struct msi_desc {
 				u8	is_msix		: 1;
 				u8	multiple	: 3;
 				u8	multi_cap	: 3;
-				u8	maskbit		: 1;
+				u8	can_mask	: 1;
 				u8	is_64		: 1;
 				u8	is_virtual	: 1;
 				u16	entry_nr;
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 3ec42495a43a..6aadcc0ecb5b 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1937,7 +1937,7 @@ enum netdev_ml_priv_type {
  *	@udp_tunnel_nic:	UDP tunnel offload state
  *	@xdp_state:		stores info on attached XDP BPF programs
  *
- *	@nested_level:	Used as as a parameter of spin_lock_nested() of
+ *	@nested_level:	Used as a parameter of spin_lock_nested() of
  *			dev->addr_list_lock.
  *	@unlink_list:	As netif_addr_lock() can be called recursively,
  *			keep a list of interfaces to be deleted.
@@ -4404,7 +4404,8 @@ static inline u32 netif_msg_init(int debug_value, int default_msg_enable_bits)
 static inline void __netif_tx_lock(struct netdev_queue *txq, int cpu)
 {
 	spin_lock(&txq->_xmit_lock);
-	txq->xmit_lock_owner = cpu;
+	/* Pairs with READ_ONCE() in __dev_queue_xmit() */
+	WRITE_ONCE(txq->xmit_lock_owner, cpu);
 }
 
 static inline bool __netif_tx_acquire(struct netdev_queue *txq)
@@ -4421,26 +4422,32 @@ static inline void __netif_tx_release(struct netdev_queue *txq)
 static inline void __netif_tx_lock_bh(struct netdev_queue *txq)
 {
 	spin_lock_bh(&txq->_xmit_lock);
-	txq->xmit_lock_owner = smp_processor_id();
+	/* Pairs with READ_ONCE() in __dev_queue_xmit() */
+	WRITE_ONCE(txq->xmit_lock_owner, smp_processor_id());
 }
 
 static inline bool __netif_tx_trylock(struct netdev_queue *txq)
 {
 	bool ok = spin_trylock(&txq->_xmit_lock);
-	if (likely(ok))
-		txq->xmit_lock_owner = smp_processor_id();
+
+	if (likely(ok)) {
+		/* Pairs with READ_ONCE() in __dev_queue_xmit() */
+		WRITE_ONCE(txq->xmit_lock_owner, smp_processor_id());
+	}
 	return ok;
 }
 
 static inline void __netif_tx_unlock(struct netdev_queue *txq)
 {
-	txq->xmit_lock_owner = -1;
+	/* Pairs with READ_ONCE() in __dev_queue_xmit() */
+	WRITE_ONCE(txq->xmit_lock_owner, -1);
 	spin_unlock(&txq->_xmit_lock);
 }
 
 static inline void __netif_tx_unlock_bh(struct netdev_queue *txq)
 {
-	txq->xmit_lock_owner = -1;
+	/* Pairs with READ_ONCE() in __dev_queue_xmit() */
+	WRITE_ONCE(txq->xmit_lock_owner, -1);
 	spin_unlock_bh(&txq->_xmit_lock);
 }
 
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 12c4177f7703..ca0683b9e3d1 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -166,13 +166,13 @@ struct netfs_read_request {
 	short			error;		/* 0 or error that occurred */
 	loff_t			i_size;		/* Size of the file */
 	loff_t			start;		/* Start position */
-	pgoff_t			no_unlock_page;	/* Don't unlock this page after read */
+	pgoff_t			no_unlock_folio; /* Don't unlock this folio after read */
 	refcount_t		usage;
 	unsigned long		flags;
 #define NETFS_RREQ_INCOMPLETE_IO	0	/* Some ioreqs terminated short or with error */
 #define NETFS_RREQ_WRITE_TO_CACHE	1	/* Need to write to the cache */
-#define NETFS_RREQ_NO_UNLOCK_PAGE	2	/* Don't unlock no_unlock_page on completion */
-#define NETFS_RREQ_DONT_UNLOCK_PAGES	3	/* Don't unlock the pages on completion */
+#define NETFS_RREQ_NO_UNLOCK_FOLIO	2	/* Don't unlock no_unlock_folio on completion */
+#define NETFS_RREQ_DONT_UNLOCK_FOLIOS	3	/* Don't unlock the folios on completion */
 #define NETFS_RREQ_FAILED		4	/* The request failed */
 #define NETFS_RREQ_IN_PROGRESS		5	/* Unlocked when the request completes */
 	const struct netfs_read_request_ops *netfs_ops;
@@ -190,7 +190,7 @@ struct netfs_read_request_ops {
 	void (*issue_op)(struct netfs_read_subrequest *subreq);
 	bool (*is_still_valid)(struct netfs_read_request *rreq);
 	int (*check_write_begin)(struct file *file, loff_t pos, unsigned len,
-				 struct page *page, void **_fsdata);
+				 struct folio *folio, void **_fsdata);
 	void (*done)(struct netfs_read_request *rreq);
 	void (*cleanup)(struct address_space *mapping, void *netfs_priv);
 };
@@ -240,11 +240,11 @@ extern void netfs_readahead(struct readahead_control *,
 			    const struct netfs_read_request_ops *,
 			    void *);
 extern int netfs_readpage(struct file *,
-			  struct page *,
+			  struct folio *,
 			  const struct netfs_read_request_ops *,
 			  void *);
 extern int netfs_write_begin(struct file *, struct address_space *,
-			     loff_t, unsigned int, unsigned int, struct page **,
+			     loff_t, unsigned int, unsigned int, struct folio **,
 			     void **,
 			     const struct netfs_read_request_ops *,
 			     void *);
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 52ec4b5e5615..b5f14d581113 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -686,13 +686,13 @@ static inline bool test_set_page_writeback(struct page *page)
 
 __PAGEFLAG(Head, head, PF_ANY) CLEARPAGEFLAG(Head, head, PF_ANY)
 
-/* Whether there are one or multiple pages in a folio */
-static inline bool folio_test_single(struct folio *folio)
-{
-	return !folio_test_head(folio);
-}
-
-static inline bool folio_test_multi(struct folio *folio)
+/**
+ * folio_test_large() - Does this folio contain more than one page?
+ * @folio: The folio to test.
+ *
+ * Return: True if the folio is larger than one page.
+ */
+static inline bool folio_test_large(struct folio *folio)
 {
 	return folio_test_head(folio);
 }
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 6a30916b76e5..d150a9082b31 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -84,7 +84,7 @@ enum mapping_flags {
 	AS_EXITING	= 4, 	/* final truncate in progress */
 	/* writeback related tags are not used */
 	AS_NO_WRITEBACK_TAGS = 5,
-	AS_THP_SUPPORT = 6,	/* THPs supported */
+	AS_LARGE_FOLIO_SUPPORT = 6,
 };
 
 /**
@@ -176,9 +176,25 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask)
 	m->gfp_mask = mask;
 }
 
-static inline bool mapping_thp_support(struct address_space *mapping)
+/**
+ * mapping_set_large_folios() - Indicate the file supports large folios.
+ * @mapping: The file.
+ *
+ * The filesystem should call this function in its inode constructor to
+ * indicate that the VFS can use large folios to cache the contents of
+ * the file.
+ *
+ * Context: This should not be called while the inode is active as it
+ * is non-atomic.
+ */
+static inline void mapping_set_large_folios(struct address_space *mapping)
+{
+	__set_bit(AS_LARGE_FOLIO_SUPPORT, &mapping->flags);
+}
+
+static inline bool mapping_large_folio_support(struct address_space *mapping)
 {
-	return test_bit(AS_THP_SUPPORT, &mapping->flags);
+	return test_bit(AS_LARGE_FOLIO_SUPPORT, &mapping->flags);
 }
 
 static inline int filemap_nr_thps(struct address_space *mapping)
@@ -193,7 +209,7 @@ static inline int filemap_nr_thps(struct address_space *mapping)
 static inline void filemap_nr_thps_inc(struct address_space *mapping)
 {
 #ifdef CONFIG_READ_ONLY_THP_FOR_FS
-	if (!mapping_thp_support(mapping))
+	if (!mapping_large_folio_support(mapping))
 		atomic_inc(&mapping->nr_thps);
 #else
 	WARN_ON_ONCE(1);
@@ -203,7 +219,7 @@ static inline void filemap_nr_thps_inc(struct address_space *mapping)
 static inline void filemap_nr_thps_dec(struct address_space *mapping)
 {
 #ifdef CONFIG_READ_ONLY_THP_FOR_FS
-	if (!mapping_thp_support(mapping))
+	if (!mapping_large_folio_support(mapping))
 		atomic_dec(&mapping->nr_thps);
 #else
 	WARN_ON_ONCE(1);
@@ -253,9 +269,22 @@ static inline struct address_space *page_mapping_file(struct page *page)
 	return folio_mapping(folio);
 }
 
+/**
+ * folio_inode - Get the host inode for this folio.
+ * @folio: The folio.
+ *
+ * For folios which are in the page cache, return the inode that this folio
+ * belongs to.
+ *
+ * Do not call this for folios which aren't in the page cache.
+ */
+static inline struct inode *folio_inode(struct folio *folio)
+{
+	return folio->mapping->host;
+}
+
 static inline bool page_cache_add_speculative(struct page *page, int count)
 {
-	VM_BUG_ON_PAGE(PageTail(page), page);
 	return folio_ref_try_add_rcu((struct folio *)page, count);
 }
 
@@ -280,6 +309,25 @@ static inline void folio_attach_private(struct folio *folio, void *data)
 }
 
 /**
+ * folio_change_private - Change private data on a folio.
+ * @folio: Folio to change the data on.
+ * @data: Data to set on the folio.
+ *
+ * Change the private data attached to a folio and return the old
+ * data.  The page must previously have had data attached and the data
+ * must be detached before the folio will be freed.
+ *
+ * Return: Data that was previously attached to the folio.
+ */
+static inline void *folio_change_private(struct folio *folio, void *data)
+{
+	void *old = folio_get_private(folio);
+
+	folio->private = data;
+	return old;
+}
+
+/**
  * folio_detach_private - Detach private data from a folio.
  * @folio: Folio to detach data from.
  *
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 138d764c1c35..18a75c8e615c 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -233,6 +233,8 @@ enum pci_dev_flags {
 	PCI_DEV_FLAGS_NO_FLR_RESET = (__force pci_dev_flags_t) (1 << 10),
 	/* Don't use Relaxed Ordering for TLPs directed at this device */
 	PCI_DEV_FLAGS_NO_RELAXED_ORDERING = (__force pci_dev_flags_t) (1 << 11),
+	/* Device does honor MSI masking despite saying otherwise */
+	PCI_DEV_FLAGS_HAS_MSI_MASKING = (__force pci_dev_flags_t) (1 << 12),
 };
 
 enum pci_irq_reroute_variant {
@@ -1666,6 +1668,7 @@ void pci_cfg_access_lock(struct pci_dev *dev);
 bool pci_cfg_access_trylock(struct pci_dev *dev);
 void pci_cfg_access_unlock(struct pci_dev *dev);
 
+void pci_dev_lock(struct pci_dev *dev);
 int pci_dev_trylock(struct pci_dev *dev);
 void pci_dev_unlock(struct pci_dev *dev);
 
diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h
index b31d3f3312ce..d73a1c08c3e3 100644
--- a/include/linux/percpu-refcount.h
+++ b/include/linux/percpu-refcount.h
@@ -51,9 +51,9 @@
 #define _LINUX_PERCPU_REFCOUNT_H
 
 #include <linux/atomic.h>
-#include <linux/kernel.h>
 #include <linux/percpu.h>
 #include <linux/rcupdate.h>
+#include <linux/types.h>
 #include <linux/gfp.h>
 
 struct percpu_ref;
diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index 98a9371133f8..ae4004e7957e 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -6,7 +6,6 @@
 #include <linux/preempt.h>
 #include <linux/smp.h>
 #include <linux/cpumask.h>
-#include <linux/printk.h>
 #include <linux/pfn.h>
 #include <linux/init.h>
 
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 96e43fbb2dd8..cbf03a5f9cf5 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -538,11 +538,12 @@ struct macsec_ops;
  * @mac_managed_pm: Set true if MAC driver takes of suspending/resuming PHY
  * @state: State of the PHY for management purposes
  * @dev_flags: Device-specific flags used by the PHY driver.
- *		Bits [15:0] are free to use by the PHY driver to communicate
- *			    driver specific behavior.
- *		Bits [23:16] are currently reserved for future use.
- *		Bits [31:24] are reserved for defining generic
- *			     PHY driver behavior.
+ *
+ *      - Bits [15:0] are free to use by the PHY driver to communicate
+ *        driver specific behavior.
+ *      - Bits [23:16] are currently reserved for future use.
+ *      - Bits [31:24] are reserved for defining generic
+ *        PHY driver behavior.
  * @irq: IRQ number of the PHY's interrupt (-1 if none)
  * @phy_timer: The timer for handling the state machine
  * @phylink: Pointer to phylink instance for this PHY
diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h
index 222da43b7096..eddd66d426ca 100644
--- a/include/linux/pm_runtime.h
+++ b/include/linux/pm_runtime.h
@@ -129,7 +129,7 @@ static inline bool pm_runtime_suspended(struct device *dev)
  * pm_runtime_active - Check whether or not a device is runtime-active.
  * @dev: Target device.
  *
- * Return %true if runtime PM is enabled for @dev and its runtime PM status is
+ * Return %true if runtime PM is disabled for @dev or its runtime PM status is
  * %RPM_ACTIVE, or %false otherwise.
  *
  * Note that the return value of this function can only be trusted if it is
diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h
index 00fef0064355..5bbcd280bfd2 100644
--- a/include/linux/posix-timers.h
+++ b/include/linux/posix-timers.h
@@ -184,8 +184,10 @@ static inline void posix_cputimers_group_init(struct posix_cputimers *pct,
 #endif
 
 #ifdef CONFIG_POSIX_CPU_TIMERS_TASK_WORK
+void clear_posix_cputimers_work(struct task_struct *p);
 void posix_cputimers_init_work(void);
 #else
+static inline void clear_posix_cputimers_work(struct task_struct *p) { }
 static inline void posix_cputimers_init_work(void) { }
 #endif
 
diff --git a/include/linux/printk.h b/include/linux/printk.h
index 85b656f82d75..9497f6b98339 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -198,6 +198,7 @@ void dump_stack_print_info(const char *log_lvl);
 void show_regs_print_info(const char *log_lvl);
 extern asmlinkage void dump_stack_lvl(const char *log_lvl) __cold;
 extern asmlinkage void dump_stack(void) __cold;
+void printk_trigger_flush(void);
 #else
 static inline __printf(1, 0)
 int vprintk(const char *s, va_list args)
@@ -274,6 +275,9 @@ static inline void dump_stack_lvl(const char *log_lvl)
 static inline void dump_stack(void)
 {
 }
+static inline void printk_trigger_flush(void)
+{
+}
 #endif
 
 #ifdef CONFIG_SMP
diff --git a/include/linux/ptp_classify.h b/include/linux/ptp_classify.h
index ae04968a3a47..9afd34a2d36c 100644
--- a/include/linux/ptp_classify.h
+++ b/include/linux/ptp_classify.h
@@ -37,6 +37,7 @@
 #define PTP_MSGTYPE_PDELAY_RESP 0x3
 
 #define PTP_EV_PORT 319
+#define PTP_GEN_PORT 320
 #define PTP_GEN_BIT 0x08 /* indicates general message, if set in message type */
 
 #define OFF_PTP_SOURCE_UUID	22 /* PTPv1 only */
diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h
index bd7a73db2e66..54cf566616ae 100644
--- a/include/linux/regulator/driver.h
+++ b/include/linux/regulator/driver.h
@@ -499,7 +499,8 @@ struct regulator_irq_data {
  *		best to shut-down regulator(s) or reboot the SOC if error
  *		handling is repeatedly failing. If fatal_cnt is given the IRQ
  *		handling is aborted if it fails for fatal_cnt times and die()
- *		callback (if populated) or BUG() is called to try to prevent
+ *		callback (if populated) is called. If die() is not populated
+ *		poweroff for the system is attempted in order to prevent any
  *		further damage.
  * @reread_ms:	The time which is waited before attempting to re-read status
  *		at the worker if IC reading fails. Immediate re-read is done
@@ -516,11 +517,12 @@ struct regulator_irq_data {
  * @data:	Driver private data pointer which will be passed as such to
  *		the renable, map_event and die callbacks in regulator_irq_data.
  * @die:	Protection callback. If IC status reading or recovery actions
- *		fail fatal_cnt times this callback or BUG() is called. This
- *		callback should implement a final protection attempt like
- *		disabling the regulator. If protection succeeded this may
- *		return 0. If anything else is returned the core assumes final
- *		protection failed and calls BUG() as a last resort.
+ *		fail fatal_cnt times this callback is called or system is
+ *		powered off. This callback should implement a final protection
+ *		attempt like disabling the regulator. If protection succeeded
+ *		die() may return 0. If anything else is returned the core
+ *		assumes final protection failed and attempts to perform a
+ *		poweroff as a last resort.
  * @map_event:	Driver callback to map IRQ status into regulator devices with
  *		events / errors. NOTE: callback MUST initialize both the
  *		errors and notifs for all rdevs which it signals having
diff --git a/include/linux/sched/cputime.h b/include/linux/sched/cputime.h
index 6c9f19a33865..ce3c58286062 100644
--- a/include/linux/sched/cputime.h
+++ b/include/linux/sched/cputime.h
@@ -18,15 +18,16 @@
 #endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
-extern void task_cputime(struct task_struct *t,
+extern bool task_cputime(struct task_struct *t,
 			 u64 *utime, u64 *stime);
 extern u64 task_gtime(struct task_struct *t);
 #else
-static inline void task_cputime(struct task_struct *t,
+static inline bool task_cputime(struct task_struct *t,
 				u64 *utime, u64 *stime)
 {
 	*utime = t->utime;
 	*stime = t->stime;
+	return false;
 }
 
 static inline u64 task_gtime(struct task_struct *t)
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index 23505394ef70..33a50642cf41 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -352,6 +352,7 @@ extern __must_check bool do_notify_parent(struct task_struct *, int);
 extern void __wake_up_parent(struct task_struct *p, struct task_struct *parent);
 extern void force_sig(int);
 extern void force_fatal_sig(int);
+extern void force_exit_sig(int);
 extern int send_sig(int, struct task_struct *, int);
 extern int zap_other_threads(struct task_struct *p);
 extern struct sigqueue *sigqueue_alloc(void);
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index ba88a6987400..058d7f371e25 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -158,7 +158,7 @@ static inline struct vm_struct *task_stack_vm_area(const struct task_struct *t)
  * Protects ->fs, ->files, ->mm, ->group_info, ->comm, keyring
  * subscriptions and synchronises with wait4().  Also used in procfs.  Also
  * pins the final release of task.io_context.  Also protects ->cpuset and
- * ->cgroup.subsys[]. And ->vfork_done.
+ * ->cgroup.subsys[]. And ->vfork_done. And ->sysvshm.shm_clist.
  *
  * Nests both inside and outside of read_lock(&tasklist_lock).
  * It must not be nested with write_lock_irq(&tasklist_lock),
diff --git a/include/linux/sdb.h b/include/linux/sdb.h
deleted file mode 100644
index a2404a2bbd10..000000000000
--- a/include/linux/sdb.h
+++ /dev/null
@@ -1,160 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * This is the official version 1.1 of sdb.h
- */
-#ifndef __SDB_H__
-#define __SDB_H__
-#ifdef __KERNEL__
-#include <linux/types.h>
-#else
-#include <stdint.h>
-#endif
-
-/*
- * All structures are 64 bytes long and are expected
- * to live in an array, one for each interconnect.
- * Most fields of the structures are shared among the
- * various types, and most-specific fields are at the
- * beginning (for alignment reasons, and to keep the
- * magic number at the head of the interconnect record
- */
-
-/* Product, 40 bytes at offset 24, 8-byte aligned
- *
- * device_id is vendor-assigned; version is device-specific,
- * date is hex (e.g 0x20120501), name is UTF-8, blank-filled
- * and not terminated with a 0 byte.
- */
-struct sdb_product {
-	uint64_t		vendor_id;	/* 0x18..0x1f */
-	uint32_t		device_id;	/* 0x20..0x23 */
-	uint32_t		version;	/* 0x24..0x27 */
-	uint32_t		date;		/* 0x28..0x2b */
-	uint8_t			name[19];	/* 0x2c..0x3e */
-	uint8_t			record_type;	/* 0x3f */
-};
-
-/*
- * Component, 56 bytes at offset 8, 8-byte aligned
- *
- * The address range is first to last, inclusive
- * (for example 0x100000 - 0x10ffff)
- */
-struct sdb_component {
-	uint64_t		addr_first;	/* 0x08..0x0f */
-	uint64_t		addr_last;	/* 0x10..0x17 */
-	struct sdb_product	product;	/* 0x18..0x3f */
-};
-
-/* Type of the SDB record */
-enum sdb_record_type {
-	sdb_type_interconnect	= 0x00,
-	sdb_type_device		= 0x01,
-	sdb_type_bridge		= 0x02,
-	sdb_type_integration	= 0x80,
-	sdb_type_repo_url	= 0x81,
-	sdb_type_synthesis	= 0x82,
-	sdb_type_empty		= 0xFF,
-};
-
-/* Type 0: interconnect (first of the array)
- *
- * sdb_records is the length of the table including this first
- * record, version is 1. The bus type is enumerated later.
- */
-#define				SDB_MAGIC	0x5344422d /* "SDB-" */
-struct sdb_interconnect {
-	uint32_t		sdb_magic;	/* 0x00-0x03 */
-	uint16_t		sdb_records;	/* 0x04-0x05 */
-	uint8_t			sdb_version;	/* 0x06 */
-	uint8_t			sdb_bus_type;	/* 0x07 */
-	struct sdb_component	sdb_component;	/* 0x08-0x3f */
-};
-
-/* Type 1: device
- *
- * class is 0 for "custom device", other values are
- * to be standardized; ABI version is for the driver,
- * bus-specific bits are defined by each bus (see below)
- */
-struct sdb_device {
-	uint16_t		abi_class;	/* 0x00-0x01 */
-	uint8_t			abi_ver_major;	/* 0x02 */
-	uint8_t			abi_ver_minor;	/* 0x03 */
-	uint32_t		bus_specific;	/* 0x04-0x07 */
-	struct sdb_component	sdb_component;	/* 0x08-0x3f */
-};
-
-/* Type 2: bridge
- *
- * child is the address of the nested SDB table
- */
-struct sdb_bridge {
-	uint64_t		sdb_child;	/* 0x00-0x07 */
-	struct sdb_component	sdb_component;	/* 0x08-0x3f */
-};
-
-/* Type 0x80: integration
- *
- * all types with bit 7 set are meta-information, so
- * software can ignore the types it doesn't know. Here we
- * just provide product information for an aggregate device
- */
-struct sdb_integration {
-	uint8_t			reserved[24];	/* 0x00-0x17 */
-	struct sdb_product	product;	/* 0x08-0x3f */
-};
-
-/* Type 0x81: Top module repository url
- *
- * again, an informative field that software can ignore
- */
-struct sdb_repo_url {
-	uint8_t			repo_url[63];	/* 0x00-0x3e */
-	uint8_t			record_type;	/* 0x3f */
-};
-
-/* Type 0x82: Synthesis tool information
- *
- * this informative record
- */
-struct sdb_synthesis {
-	uint8_t			syn_name[16];	/* 0x00-0x0f */
-	uint8_t			commit_id[16];	/* 0x10-0x1f */
-	uint8_t			tool_name[8];	/* 0x20-0x27 */
-	uint32_t		tool_version;	/* 0x28-0x2b */
-	uint32_t		date;		/* 0x2c-0x2f */
-	uint8_t			user_name[15];	/* 0x30-0x3e */
-	uint8_t			record_type;	/* 0x3f */
-};
-
-/* Type 0xff: empty
- *
- * this allows keeping empty slots during development,
- * so they can be filled later with minimal efforts and
- * no misleading description is ever shipped -- hopefully.
- * It can also be used to pad a table to a desired length.
- */
-struct sdb_empty {
-	uint8_t			reserved[63];	/* 0x00-0x3e */
-	uint8_t			record_type;	/* 0x3f */
-};
-
-/* The type of bus, for bus-specific flags */
-enum sdb_bus_type {
-	sdb_wishbone = 0x00,
-	sdb_data     = 0x01,
-};
-
-#define SDB_WB_WIDTH_MASK	0x0f
-#define SDB_WB_ACCESS8			0x01
-#define SDB_WB_ACCESS16			0x02
-#define SDB_WB_ACCESS32			0x04
-#define SDB_WB_ACCESS64			0x08
-#define SDB_WB_LITTLE_ENDIAN	0x80
-
-#define SDB_DATA_READ		0x04
-#define SDB_DATA_WRITE		0x02
-#define SDB_DATA_EXEC		0x01
-
-#endif /* __SDB_H__ */
diff --git a/include/linux/security.h b/include/linux/security.h
index 06eac4e61a13..bbf44a466832 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -1430,8 +1430,6 @@ int security_sctp_bind_connect(struct sock *sk, int optname,
 			       struct sockaddr *address, int addrlen);
 void security_sctp_sk_clone(struct sctp_association *asoc, struct sock *sk,
 			    struct sock *newsk);
-void security_sctp_assoc_established(struct sctp_association *asoc,
-				     struct sk_buff *skb);
 
 #else	/* CONFIG_SECURITY_NETWORK */
 static inline int security_unix_stream_connect(struct sock *sock,
@@ -1651,11 +1649,6 @@ static inline void security_sctp_sk_clone(struct sctp_association *asoc,
 					  struct sock *newsk)
 {
 }
-
-static inline void security_sctp_assoc_established(struct sctp_association *asoc,
-						   struct sk_buff *skb)
-{
-}
 #endif	/* CONFIG_SECURITY_NETWORK */
 
 #ifdef CONFIG_SECURITY_INFINIBAND
diff --git a/include/linux/siphash.h b/include/linux/siphash.h
index bf21591a9e5e..0cda61855d90 100644
--- a/include/linux/siphash.h
+++ b/include/linux/siphash.h
@@ -27,9 +27,7 @@ static inline bool siphash_key_is_zero(const siphash_key_t *key)
 }
 
 u64 __siphash_aligned(const void *data, size_t len, const siphash_key_t *key);
-#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
 u64 __siphash_unaligned(const void *data, size_t len, const siphash_key_t *key);
-#endif
 
 u64 siphash_1u64(const u64 a, const siphash_key_t *key);
 u64 siphash_2u64(const u64 a, const u64 b, const siphash_key_t *key);
@@ -82,10 +80,9 @@ static inline u64 ___siphash_aligned(const __le64 *data, size_t len,
 static inline u64 siphash(const void *data, size_t len,
 			  const siphash_key_t *key)
 {
-#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
-	if (!IS_ALIGNED((unsigned long)data, SIPHASH_ALIGNMENT))
+	if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) ||
+	    !IS_ALIGNED((unsigned long)data, SIPHASH_ALIGNMENT))
 		return __siphash_unaligned(data, len, key);
-#endif
 	return ___siphash_aligned(data, len, key);
 }
 
@@ -96,10 +93,8 @@ typedef struct {
 
 u32 __hsiphash_aligned(const void *data, size_t len,
 		       const hsiphash_key_t *key);
-#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
 u32 __hsiphash_unaligned(const void *data, size_t len,
 			 const hsiphash_key_t *key);
-#endif
 
 u32 hsiphash_1u32(const u32 a, const hsiphash_key_t *key);
 u32 hsiphash_2u32(const u32 a, const u32 b, const hsiphash_key_t *key);
@@ -135,10 +130,9 @@ static inline u32 ___hsiphash_aligned(const __le32 *data, size_t len,
 static inline u32 hsiphash(const void *data, size_t len,
 			   const hsiphash_key_t *key)
 {
-#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
-	if (!IS_ALIGNED((unsigned long)data, HSIPHASH_ALIGNMENT))
+	if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) ||
+	    !IS_ALIGNED((unsigned long)data, HSIPHASH_ALIGNMENT))
 		return __hsiphash_unaligned(data, len, key);
-#endif
 	return ___hsiphash_aligned(data, len, key);
 }
 
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 686a666d073d..4507d77d6941 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -286,6 +286,7 @@ struct nf_bridge_info {
 struct tc_skb_ext {
 	__u32 chain;
 	__u16 mru;
+	__u16 zone;
 	bool post_ct;
 };
 #endif
@@ -1380,7 +1381,7 @@ skb_flow_dissect_ct(const struct sk_buff *skb,
 		    struct flow_dissector *flow_dissector,
 		    void *target_container,
 		    u16 *ctinfo_map, size_t mapsize,
-		    bool post_ct);
+		    bool post_ct, u16 zone);
 void
 skb_flow_dissect_tunnel_info(const struct sk_buff *skb,
 			     struct flow_dissector *flow_dissector,
@@ -4226,7 +4227,7 @@ static inline void skb_remcsum_process(struct sk_buff *skb, void *ptr,
 		return;
 	}
 
-	 if (unlikely(skb->ip_summed != CHECKSUM_COMPLETE)) {
+	if (unlikely(skb->ip_summed != CHECKSUM_COMPLETE)) {
 		__skb_checksum_complete(skb);
 		skb_postpull_rcsum(skb, skb->data, ptr - (void *)skb->data);
 	}
diff --git a/include/linux/tee_drv.h b/include/linux/tee_drv.h
index a1f03461369b..cf5999626e28 100644
--- a/include/linux/tee_drv.h
+++ b/include/linux/tee_drv.h
@@ -195,7 +195,7 @@ int tee_session_calc_client_uuid(uuid_t *uuid, u32 connection_method,
  * @offset:	offset of buffer in user space
  * @pages:	locked pages from userspace
  * @num_pages:	number of locked pages
- * @dmabuf:	dmabuf used to for exporting to user space
+ * @refcount:	reference counter
  * @flags:	defined by TEE_SHM_* in tee_drv.h
  * @id:		unique id of a shared memory object on this device, shared
  *		with user space
@@ -214,7 +214,7 @@ struct tee_shm {
 	unsigned int offset;
 	struct page **pages;
 	size_t num_pages;
-	struct dma_buf *dmabuf;
+	refcount_t refcount;
 	u32 flags;
 	int id;
 	u64 sec_world_id;
diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index 50453b287615..2d167ac3452c 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -673,7 +673,7 @@ struct trace_event_file {
 
 #define PERF_MAX_TRACE_SIZE	8192
 
-#define MAX_FILTER_STR_VAL	256	/* Should handle KSYM_SYMBOL_LEN */
+#define MAX_FILTER_STR_VAL	256U	/* Should handle KSYM_SYMBOL_LEN */
 
 enum event_trigger_type {
 	ETT_NONE		= (0),
diff --git a/include/linux/vermagic.h b/include/linux/vermagic.h
index 1eaaa93c37bf..329d63babaeb 100644
--- a/include/linux/vermagic.h
+++ b/include/linux/vermagic.h
@@ -15,7 +15,7 @@
 #else
 #define MODULE_VERMAGIC_SMP ""
 #endif
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPT_BUILD
 #define MODULE_VERMAGIC_PREEMPT "preempt "
 #elif defined(CONFIG_PREEMPT_RT)
 #define MODULE_VERMAGIC_PREEMPT "preempt_rt "
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index 44d0e09da2d9..41edbc01ffa4 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -152,7 +152,6 @@ size_t virtio_max_dma_size(struct virtio_device *vdev);
  * @feature_table_size: number of entries in the feature table array.
  * @feature_table_legacy: same as feature_table but when working in legacy mode.
  * @feature_table_size_legacy: number of entries in feature table legacy array.
- * @suppress_used_validation: set to not have core validate used length
  * @probe: the function to call when a device is found.  Returns 0 or -errno.
  * @scan: optional function to call after successful probe; intended
  *    for virtio-scsi to invoke a scan.
@@ -169,7 +168,6 @@ struct virtio_driver {
 	unsigned int feature_table_size;
 	const unsigned int *feature_table_legacy;
 	unsigned int feature_table_size_legacy;
-	bool suppress_used_validation;
 	int (*validate)(struct virtio_device *dev);
 	int (*probe)(struct virtio_device *dev);
 	void (*scan)(struct virtio_device *dev);
diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
index b465f8f3e554..a960de68ac69 100644
--- a/include/linux/virtio_net.h
+++ b/include/linux/virtio_net.h
@@ -7,9 +7,27 @@
 #include <uapi/linux/udp.h>
 #include <uapi/linux/virtio_net.h>
 
+static inline bool virtio_net_hdr_match_proto(__be16 protocol, __u8 gso_type)
+{
+	switch (gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
+	case VIRTIO_NET_HDR_GSO_TCPV4:
+		return protocol == cpu_to_be16(ETH_P_IP);
+	case VIRTIO_NET_HDR_GSO_TCPV6:
+		return protocol == cpu_to_be16(ETH_P_IPV6);
+	case VIRTIO_NET_HDR_GSO_UDP:
+		return protocol == cpu_to_be16(ETH_P_IP) ||
+		       protocol == cpu_to_be16(ETH_P_IPV6);
+	default:
+		return false;
+	}
+}
+
 static inline int virtio_net_hdr_set_proto(struct sk_buff *skb,
 					   const struct virtio_net_hdr *hdr)
 {
+	if (skb->protocol)
+		return 0;
+
 	switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
 	case VIRTIO_NET_HDR_GSO_TCPV4:
 	case VIRTIO_NET_HDR_GSO_UDP:
@@ -88,9 +106,12 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 			if (!skb->protocol) {
 				__be16 protocol = dev_parse_header_protocol(skb);
 
-				virtio_net_hdr_set_proto(skb, hdr);
-				if (protocol && protocol != skb->protocol)
+				if (!protocol)
+					virtio_net_hdr_set_proto(skb, hdr);
+				else if (!virtio_net_hdr_match_proto(protocol, hdr->gso_type))
 					return -EINVAL;
+				else
+					skb->protocol = protocol;
 			}
 retry:
 			if (!skb_flow_dissect_flow_keys_basic(NULL, skb, &keys,
@@ -120,10 +141,15 @@ retry:
 
 	if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
 		u16 gso_size = __virtio16_to_cpu(little_endian, hdr->gso_size);
+		unsigned int nh_off = p_off;
 		struct skb_shared_info *shinfo = skb_shinfo(skb);
 
+		/* UFO may not include transport header in gso_size. */
+		if (gso_type & SKB_GSO_UDP)
+			nh_off -= thlen;
+
 		/* Too small packets are not really GSO ones. */
-		if (skb->len - p_off > gso_size) {
+		if (skb->len - nh_off > gso_size) {
 			shinfo->gso_size = gso_size;
 			shinfo->gso_type = gso_type;
 
diff --git a/include/linux/wait.h b/include/linux/wait.h
index 2d0df57c9902..851e07da2583 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -217,6 +217,7 @@ void __wake_up_sync_key(struct wait_queue_head *wq_head, unsigned int mode, void
 void __wake_up_locked_sync_key(struct wait_queue_head *wq_head, unsigned int mode, void *key);
 void __wake_up_locked(struct wait_queue_head *wq_head, unsigned int mode, int nr);
 void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode);
+void __wake_up_pollfree(struct wait_queue_head *wq_head);
 
 #define wake_up(x)			__wake_up(x, TASK_NORMAL, 1, NULL)
 #define wake_up_nr(x, nr)		__wake_up(x, TASK_NORMAL, nr, NULL)
@@ -245,6 +246,31 @@ void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode);
 #define wake_up_interruptible_sync_poll_locked(x, m)				\
 	__wake_up_locked_sync_key((x), TASK_INTERRUPTIBLE, poll_to_key(m))
 
+/**
+ * wake_up_pollfree - signal that a polled waitqueue is going away
+ * @wq_head: the wait queue head
+ *
+ * In the very rare cases where a ->poll() implementation uses a waitqueue whose
+ * lifetime is tied to a task rather than to the 'struct file' being polled,
+ * this function must be called before the waitqueue is freed so that
+ * non-blocking polls (e.g. epoll) are notified that the queue is going away.
+ *
+ * The caller must also RCU-delay the freeing of the wait_queue_head, e.g. via
+ * an explicit synchronize_rcu() or call_rcu(), or via SLAB_TYPESAFE_BY_RCU.
+ */
+static inline void wake_up_pollfree(struct wait_queue_head *wq_head)
+{
+	/*
+	 * For performance reasons, we don't always take the queue lock here.
+	 * Therefore, we might race with someone removing the last entry from
+	 * the queue, and proceed while they still hold the queue lock.
+	 * However, rcu_read_lock() is required to be held in such cases, so we
+	 * can safely proceed with an RCU-delayed free.
+	 */
+	if (waitqueue_active(wq_head))
+		__wake_up_pollfree(wq_head);
+}
+
 #define ___wait_cond_timeout(condition)						\
 ({										\
 	bool __cond = (condition);						\
diff --git a/include/linux/zstd.h b/include/linux/zstd.h
index e87f78c9b19c..113408eef6ec 100644
--- a/include/linux/zstd.h
+++ b/include/linux/zstd.h
@@ -1,138 +1,97 @@
+/* SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause */
 /*
- * Copyright (c) 2016-present, Yann Collet, Facebook, Inc.
+ * Copyright (c) Yann Collet, Facebook, Inc.
  * All rights reserved.
  *
- * This source code is licensed under the BSD-style license found in the
- * LICENSE file in the root directory of https://github.com/facebook/zstd.
- * An additional grant of patent rights can be found in the PATENTS file in the
- * same directory.
- *
- * 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. This program is dual-licensed; you may select
- * either version 2 of the GNU General Public License ("GPL") or BSD license
- * ("BSD").
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of https://github.com/facebook/zstd) and
+ * the GPLv2 (found in the COPYING file in the root directory of
+ * https://github.com/facebook/zstd). You may select, at your option, one of the
+ * above-listed licenses.
  */
 
-#ifndef ZSTD_H
-#define ZSTD_H
+#ifndef LINUX_ZSTD_H
+#define LINUX_ZSTD_H
 
-/* ======   Dependency   ======*/
-#include <linux/types.h>   /* size_t */
+/**
+ * This is a kernel-style API that wraps the upstream zstd API, which cannot be
+ * used directly because the symbols aren't exported. It exposes the minimal
+ * functionality which is currently required by users of zstd in the kernel.
+ * Expose extra functions from lib/zstd/zstd.h as needed.
+ */
 
+/* ======   Dependency   ====== */
+#include <linux/types.h>
+#include <linux/zstd_errors.h>
+#include <linux/zstd_lib.h>
 
-/*-*****************************************************************************
- * Introduction
+/* ======   Helper Functions   ====== */
+/**
+ * zstd_compress_bound() - maximum compressed size in worst case scenario
+ * @src_size: The size of the data to compress.
  *
- * zstd, short for Zstandard, is a fast lossless compression algorithm,
- * targeting real-time compression scenarios at zlib-level and better
- * compression ratios. The zstd compression library provides in-memory
- * compression and decompression functions. The library supports compression
- * levels from 1 up to ZSTD_maxCLevel() which is 22. Levels >= 20, labeled
- * ultra, should be used with caution, as they require more memory.
- * Compression can be done in:
- *  - a single step, reusing a context (described as Explicit memory management)
- *  - unbounded multiple steps (described as Streaming compression)
- * The compression ratio achievable on small data can be highly improved using
- * compression with a dictionary in:
- *  - a single step (described as Simple dictionary API)
- *  - a single step, reusing a dictionary (described as Fast dictionary API)
- ******************************************************************************/
-
-/*======  Helper functions  ======*/
+ * Return:    The maximum compressed size in the worst case scenario.
+ */
+size_t zstd_compress_bound(size_t src_size);
 
 /**
- * enum ZSTD_ErrorCode - zstd error codes
+ * zstd_is_error() - tells if a size_t function result is an error code
+ * @code:  The function result to check for error.
  *
- * Functions that return size_t can be checked for errors using ZSTD_isError()
- * and the ZSTD_ErrorCode can be extracted using ZSTD_getErrorCode().
+ * Return: Non-zero iff the code is an error.
+ */
+unsigned int zstd_is_error(size_t code);
+
+/**
+ * enum zstd_error_code - zstd error codes
  */
-typedef enum {
-	ZSTD_error_no_error,
-	ZSTD_error_GENERIC,
-	ZSTD_error_prefix_unknown,
-	ZSTD_error_version_unsupported,
-	ZSTD_error_parameter_unknown,
-	ZSTD_error_frameParameter_unsupported,
-	ZSTD_error_frameParameter_unsupportedBy32bits,
-	ZSTD_error_frameParameter_windowTooLarge,
-	ZSTD_error_compressionParameter_unsupported,
-	ZSTD_error_init_missing,
-	ZSTD_error_memory_allocation,
-	ZSTD_error_stage_wrong,
-	ZSTD_error_dstSize_tooSmall,
-	ZSTD_error_srcSize_wrong,
-	ZSTD_error_corruption_detected,
-	ZSTD_error_checksum_wrong,
-	ZSTD_error_tableLog_tooLarge,
-	ZSTD_error_maxSymbolValue_tooLarge,
-	ZSTD_error_maxSymbolValue_tooSmall,
-	ZSTD_error_dictionary_corrupted,
-	ZSTD_error_dictionary_wrong,
-	ZSTD_error_dictionaryCreation_failed,
-	ZSTD_error_maxCode
-} ZSTD_ErrorCode;
+typedef ZSTD_ErrorCode zstd_error_code;
 
 /**
- * ZSTD_maxCLevel() - maximum compression level available
+ * zstd_get_error_code() - translates an error function result to an error code
+ * @code:  The function result for which zstd_is_error(code) is true.
  *
- * Return: Maximum compression level available.
+ * Return: A unique error code for this error.
  */
-int ZSTD_maxCLevel(void);
+zstd_error_code zstd_get_error_code(size_t code);
+
 /**
- * ZSTD_compressBound() - maximum compressed size in worst case scenario
- * @srcSize: The size of the data to compress.
+ * zstd_get_error_name() - translates an error function result to a string
+ * @code:  The function result for which zstd_is_error(code) is true.
  *
- * Return:   The maximum compressed size in the worst case scenario.
+ * Return: An error string corresponding to the error code.
  */
-size_t ZSTD_compressBound(size_t srcSize);
+const char *zstd_get_error_name(size_t code);
+
 /**
- * ZSTD_isError() - tells if a size_t function result is an error code
- * @code:  The function result to check for error.
+ * zstd_min_clevel() - minimum allowed compression level
  *
- * Return: Non-zero iff the code is an error.
+ * Return: The minimum allowed compression level.
  */
-static __attribute__((unused)) unsigned int ZSTD_isError(size_t code)
-{
-	return code > (size_t)-ZSTD_error_maxCode;
-}
+int zstd_min_clevel(void);
+
 /**
- * ZSTD_getErrorCode() - translates an error function result to a ZSTD_ErrorCode
- * @functionResult: The result of a function for which ZSTD_isError() is true.
+ * zstd_max_clevel() - maximum allowed compression level
  *
- * Return:          The ZSTD_ErrorCode corresponding to the functionResult or 0
- *                  if the functionResult isn't an error.
+ * Return: The maximum allowed compression level.
  */
-static __attribute__((unused)) ZSTD_ErrorCode ZSTD_getErrorCode(
-	size_t functionResult)
-{
-	if (!ZSTD_isError(functionResult))
-		return (ZSTD_ErrorCode)0;
-	return (ZSTD_ErrorCode)(0 - functionResult);
-}
+int zstd_max_clevel(void);
+
+/* ======   Parameter Selection   ====== */
 
 /**
- * enum ZSTD_strategy - zstd compression search strategy
+ * enum zstd_strategy - zstd compression search strategy
  *
- * From faster to stronger.
+ * From faster to stronger. See zstd_lib.h.
  */
-typedef enum {
-	ZSTD_fast,
-	ZSTD_dfast,
-	ZSTD_greedy,
-	ZSTD_lazy,
-	ZSTD_lazy2,
-	ZSTD_btlazy2,
-	ZSTD_btopt,
-	ZSTD_btopt2
-} ZSTD_strategy;
+typedef ZSTD_strategy zstd_strategy;
 
 /**
- * struct ZSTD_compressionParameters - zstd compression parameters
+ * struct zstd_compression_parameters - zstd compression parameters
  * @windowLog:    Log of the largest match distance. Larger means more
  *                compression, and more memory needed during decompression.
- * @chainLog:     Fully searched segment. Larger means more compression, slower,
- *                and more memory (useless for fast).
+ * @chainLog:     Fully searched segment. Larger means more compression,
+ *                slower, and more memory (useless for fast).
  * @hashLog:      Dispatch table. Larger means more compression,
  *                slower, and more memory.
  * @searchLog:    Number of searches. Larger means more compression and slower.
@@ -141,1017 +100,348 @@ typedef enum {
  * @targetLength: Acceptable match size for optimal parser (only). Larger means
  *                more compression, and slower.
  * @strategy:     The zstd compression strategy.
+ *
+ * See zstd_lib.h.
  */
-typedef struct {
-	unsigned int windowLog;
-	unsigned int chainLog;
-	unsigned int hashLog;
-	unsigned int searchLog;
-	unsigned int searchLength;
-	unsigned int targetLength;
-	ZSTD_strategy strategy;
-} ZSTD_compressionParameters;
+typedef ZSTD_compressionParameters zstd_compression_parameters;
 
 /**
- * struct ZSTD_frameParameters - zstd frame parameters
- * @contentSizeFlag: Controls whether content size will be present in the frame
- *                   header (when known).
- * @checksumFlag:    Controls whether a 32-bit checksum is generated at the end
- *                   of the frame for error detection.
- * @noDictIDFlag:    Controls whether dictID will be saved into the frame header
- *                   when using dictionary compression.
+ * struct zstd_frame_parameters - zstd frame parameters
+ * @contentSizeFlag: Controls whether content size will be present in the
+ *                   frame header (when known).
+ * @checksumFlag:    Controls whether a 32-bit checksum is generated at the
+ *                   end of the frame for error detection.
+ * @noDictIDFlag:    Controls whether dictID will be saved into the frame
+ *                   header when using dictionary compression.
  *
- * The default value is all fields set to 0.
+ * The default value is all fields set to 0. See zstd_lib.h.
  */
-typedef struct {
-	unsigned int contentSizeFlag;
-	unsigned int checksumFlag;
-	unsigned int noDictIDFlag;
-} ZSTD_frameParameters;
+typedef ZSTD_frameParameters zstd_frame_parameters;
 
 /**
- * struct ZSTD_parameters - zstd parameters
+ * struct zstd_parameters - zstd parameters
  * @cParams: The compression parameters.
  * @fParams: The frame parameters.
  */
-typedef struct {
-	ZSTD_compressionParameters cParams;
-	ZSTD_frameParameters fParams;
-} ZSTD_parameters;
+typedef ZSTD_parameters zstd_parameters;
 
 /**
- * ZSTD_getCParams() - returns ZSTD_compressionParameters for selected level
- * @compressionLevel: The compression level from 1 to ZSTD_maxCLevel().
- * @estimatedSrcSize: The estimated source size to compress or 0 if unknown.
- * @dictSize:         The dictionary size or 0 if a dictionary isn't being used.
+ * zstd_get_params() - returns zstd_parameters for selected level
+ * @level:              The compression level
+ * @estimated_src_size: The estimated source size to compress or 0
+ *                      if unknown.
  *
- * Return:            The selected ZSTD_compressionParameters.
+ * Return:              The selected zstd_parameters.
  */
-ZSTD_compressionParameters ZSTD_getCParams(int compressionLevel,
-	unsigned long long estimatedSrcSize, size_t dictSize);
+zstd_parameters zstd_get_params(int level,
+	unsigned long long estimated_src_size);
 
-/**
- * ZSTD_getParams() - returns ZSTD_parameters for selected level
- * @compressionLevel: The compression level from 1 to ZSTD_maxCLevel().
- * @estimatedSrcSize: The estimated source size to compress or 0 if unknown.
- * @dictSize:         The dictionary size or 0 if a dictionary isn't being used.
- *
- * The same as ZSTD_getCParams() except also selects the default frame
- * parameters (all zero).
- *
- * Return:            The selected ZSTD_parameters.
- */
-ZSTD_parameters ZSTD_getParams(int compressionLevel,
-	unsigned long long estimatedSrcSize, size_t dictSize);
+/* ======   Single-pass Compression   ====== */
 
-/*-*************************************
- * Explicit memory management
- **************************************/
+typedef ZSTD_CCtx zstd_cctx;
 
 /**
- * ZSTD_CCtxWorkspaceBound() - amount of memory needed to initialize a ZSTD_CCtx
- * @cParams: The compression parameters to be used for compression.
+ * zstd_cctx_workspace_bound() - max memory needed to initialize a zstd_cctx
+ * @parameters: The compression parameters to be used.
  *
  * If multiple compression parameters might be used, the caller must call
- * ZSTD_CCtxWorkspaceBound() for each set of parameters and use the maximum
+ * zstd_cctx_workspace_bound() for each set of parameters and use the maximum
  * size.
  *
- * Return:   A lower bound on the size of the workspace that is passed to
- *           ZSTD_initCCtx().
+ * Return:      A lower bound on the size of the workspace that is passed to
+ *              zstd_init_cctx().
  */
-size_t ZSTD_CCtxWorkspaceBound(ZSTD_compressionParameters cParams);
+size_t zstd_cctx_workspace_bound(const zstd_compression_parameters *parameters);
 
 /**
- * struct ZSTD_CCtx - the zstd compression context
- *
- * When compressing many times it is recommended to allocate a context just once
- * and reuse it for each successive compression operation.
- */
-typedef struct ZSTD_CCtx_s ZSTD_CCtx;
-/**
- * ZSTD_initCCtx() - initialize a zstd compression context
- * @workspace:     The workspace to emplace the context into. It must outlive
- *                 the returned context.
- * @workspaceSize: The size of workspace. Use ZSTD_CCtxWorkspaceBound() to
- *                 determine how large the workspace must be.
- *
- * Return:         A compression context emplaced into workspace.
- */
-ZSTD_CCtx *ZSTD_initCCtx(void *workspace, size_t workspaceSize);
-
-/**
- * ZSTD_compressCCtx() - compress src into dst
- * @ctx:         The context. Must have been initialized with a workspace at
- *               least as large as ZSTD_CCtxWorkspaceBound(params.cParams).
- * @dst:         The buffer to compress src into.
- * @dstCapacity: The size of the destination buffer. May be any size, but
- *               ZSTD_compressBound(srcSize) is guaranteed to be large enough.
- * @src:         The data to compress.
- * @srcSize:     The size of the data to compress.
- * @params:      The parameters to use for compression. See ZSTD_getParams().
- *
- * Return:       The compressed size or an error, which can be checked using
- *               ZSTD_isError().
- */
-size_t ZSTD_compressCCtx(ZSTD_CCtx *ctx, void *dst, size_t dstCapacity,
-	const void *src, size_t srcSize, ZSTD_parameters params);
-
-/**
- * ZSTD_DCtxWorkspaceBound() - amount of memory needed to initialize a ZSTD_DCtx
- *
- * Return: A lower bound on the size of the workspace that is passed to
- *         ZSTD_initDCtx().
- */
-size_t ZSTD_DCtxWorkspaceBound(void);
-
-/**
- * struct ZSTD_DCtx - the zstd decompression context
- *
- * When decompressing many times it is recommended to allocate a context just
- * once and reuse it for each successive decompression operation.
- */
-typedef struct ZSTD_DCtx_s ZSTD_DCtx;
-/**
- * ZSTD_initDCtx() - initialize a zstd decompression context
- * @workspace:     The workspace to emplace the context into. It must outlive
- *                 the returned context.
- * @workspaceSize: The size of workspace. Use ZSTD_DCtxWorkspaceBound() to
- *                 determine how large the workspace must be.
- *
- * Return:         A decompression context emplaced into workspace.
- */
-ZSTD_DCtx *ZSTD_initDCtx(void *workspace, size_t workspaceSize);
-
-/**
- * ZSTD_decompressDCtx() - decompress zstd compressed src into dst
- * @ctx:         The decompression context.
- * @dst:         The buffer to decompress src into.
- * @dstCapacity: The size of the destination buffer. Must be at least as large
- *               as the decompressed size. If the caller cannot upper bound the
- *               decompressed size, then it's better to use the streaming API.
- * @src:         The zstd compressed data to decompress. Multiple concatenated
- *               frames and skippable frames are allowed.
- * @srcSize:     The exact size of the data to decompress.
- *
- * Return:       The decompressed size or an error, which can be checked using
- *               ZSTD_isError().
- */
-size_t ZSTD_decompressDCtx(ZSTD_DCtx *ctx, void *dst, size_t dstCapacity,
-	const void *src, size_t srcSize);
-
-/*-************************
- * Simple dictionary API
- **************************/
-
-/**
- * ZSTD_compress_usingDict() - compress src into dst using a dictionary
- * @ctx:         The context. Must have been initialized with a workspace at
- *               least as large as ZSTD_CCtxWorkspaceBound(params.cParams).
- * @dst:         The buffer to compress src into.
- * @dstCapacity: The size of the destination buffer. May be any size, but
- *               ZSTD_compressBound(srcSize) is guaranteed to be large enough.
- * @src:         The data to compress.
- * @srcSize:     The size of the data to compress.
- * @dict:        The dictionary to use for compression.
- * @dictSize:    The size of the dictionary.
- * @params:      The parameters to use for compression. See ZSTD_getParams().
- *
- * Compression using a predefined dictionary. The same dictionary must be used
- * during decompression.
- *
- * Return:       The compressed size or an error, which can be checked using
- *               ZSTD_isError().
- */
-size_t ZSTD_compress_usingDict(ZSTD_CCtx *ctx, void *dst, size_t dstCapacity,
-	const void *src, size_t srcSize, const void *dict, size_t dictSize,
-	ZSTD_parameters params);
-
-/**
- * ZSTD_decompress_usingDict() - decompress src into dst using a dictionary
- * @ctx:         The decompression context.
- * @dst:         The buffer to decompress src into.
- * @dstCapacity: The size of the destination buffer. Must be at least as large
- *               as the decompressed size. If the caller cannot upper bound the
- *               decompressed size, then it's better to use the streaming API.
- * @src:         The zstd compressed data to decompress. Multiple concatenated
- *               frames and skippable frames are allowed.
- * @srcSize:     The exact size of the data to decompress.
- * @dict:        The dictionary to use for decompression. The same dictionary
- *               must've been used to compress the data.
- * @dictSize:    The size of the dictionary.
- *
- * Return:       The decompressed size or an error, which can be checked using
- *               ZSTD_isError().
- */
-size_t ZSTD_decompress_usingDict(ZSTD_DCtx *ctx, void *dst, size_t dstCapacity,
-	const void *src, size_t srcSize, const void *dict, size_t dictSize);
-
-/*-**************************
- * Fast dictionary API
- ***************************/
-
-/**
- * ZSTD_CDictWorkspaceBound() - memory needed to initialize a ZSTD_CDict
- * @cParams: The compression parameters to be used for compression.
+ * zstd_init_cctx() - initialize a zstd compression context
+ * @workspace:      The workspace to emplace the context into. It must outlive
+ *                  the returned context.
+ * @workspace_size: The size of workspace. Use zstd_cctx_workspace_bound() to
+ *                  determine how large the workspace must be.
  *
- * Return:   A lower bound on the size of the workspace that is passed to
- *           ZSTD_initCDict().
- */
-size_t ZSTD_CDictWorkspaceBound(ZSTD_compressionParameters cParams);
-
-/**
- * struct ZSTD_CDict - a digested dictionary to be used for compression
+ * Return:          A zstd compression context or NULL on error.
  */
-typedef struct ZSTD_CDict_s ZSTD_CDict;
+zstd_cctx *zstd_init_cctx(void *workspace, size_t workspace_size);
 
 /**
- * ZSTD_initCDict() - initialize a digested dictionary for compression
- * @dictBuffer:    The dictionary to digest. The buffer is referenced by the
- *                 ZSTD_CDict so it must outlive the returned ZSTD_CDict.
- * @dictSize:      The size of the dictionary.
- * @params:        The parameters to use for compression. See ZSTD_getParams().
- * @workspace:     The workspace. It must outlive the returned ZSTD_CDict.
- * @workspaceSize: The workspace size. Must be at least
- *                 ZSTD_CDictWorkspaceBound(params.cParams).
+ * zstd_compress_cctx() - compress src into dst with the initialized parameters
+ * @cctx:         The context. Must have been initialized with zstd_init_cctx().
+ * @dst:          The buffer to compress src into.
+ * @dst_capacity: The size of the destination buffer. May be any size, but
+ *                ZSTD_compressBound(srcSize) is guaranteed to be large enough.
+ * @src:          The data to compress.
+ * @src_size:     The size of the data to compress.
+ * @parameters:   The compression parameters to be used.
  *
- * When compressing multiple messages / blocks with the same dictionary it is
- * recommended to load it just once. The ZSTD_CDict merely references the
- * dictBuffer, so it must outlive the returned ZSTD_CDict.
- *
- * Return:         The digested dictionary emplaced into workspace.
+ * Return:        The compressed size or an error, which can be checked using
+ *                zstd_is_error().
  */
-ZSTD_CDict *ZSTD_initCDict(const void *dictBuffer, size_t dictSize,
-	ZSTD_parameters params, void *workspace, size_t workspaceSize);
+size_t zstd_compress_cctx(zstd_cctx *cctx, void *dst, size_t dst_capacity,
+	const void *src, size_t src_size, const zstd_parameters *parameters);
 
-/**
- * ZSTD_compress_usingCDict() - compress src into dst using a ZSTD_CDict
- * @ctx:         The context. Must have been initialized with a workspace at
- *               least as large as ZSTD_CCtxWorkspaceBound(cParams) where
- *               cParams are the compression parameters used to initialize the
- *               cdict.
- * @dst:         The buffer to compress src into.
- * @dstCapacity: The size of the destination buffer. May be any size, but
- *               ZSTD_compressBound(srcSize) is guaranteed to be large enough.
- * @src:         The data to compress.
- * @srcSize:     The size of the data to compress.
- * @cdict:       The digested dictionary to use for compression.
- * @params:      The parameters to use for compression. See ZSTD_getParams().
- *
- * Compression using a digested dictionary. The same dictionary must be used
- * during decompression.
- *
- * Return:       The compressed size or an error, which can be checked using
- *               ZSTD_isError().
- */
-size_t ZSTD_compress_usingCDict(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity,
-	const void *src, size_t srcSize, const ZSTD_CDict *cdict);
+/* ======   Single-pass Decompression   ====== */
 
+typedef ZSTD_DCtx zstd_dctx;
 
 /**
- * ZSTD_DDictWorkspaceBound() - memory needed to initialize a ZSTD_DDict
+ * zstd_dctx_workspace_bound() - max memory needed to initialize a zstd_dctx
  *
- * Return:  A lower bound on the size of the workspace that is passed to
- *          ZSTD_initDDict().
- */
-size_t ZSTD_DDictWorkspaceBound(void);
-
-/**
- * struct ZSTD_DDict - a digested dictionary to be used for decompression
+ * Return: A lower bound on the size of the workspace that is passed to
+ *         zstd_init_dctx().
  */
-typedef struct ZSTD_DDict_s ZSTD_DDict;
+size_t zstd_dctx_workspace_bound(void);
 
 /**
- * ZSTD_initDDict() - initialize a digested dictionary for decompression
- * @dictBuffer:    The dictionary to digest. The buffer is referenced by the
- *                 ZSTD_DDict so it must outlive the returned ZSTD_DDict.
- * @dictSize:      The size of the dictionary.
- * @workspace:     The workspace. It must outlive the returned ZSTD_DDict.
- * @workspaceSize: The workspace size. Must be at least
- *                 ZSTD_DDictWorkspaceBound().
- *
- * When decompressing multiple messages / blocks with the same dictionary it is
- * recommended to load it just once. The ZSTD_DDict merely references the
- * dictBuffer, so it must outlive the returned ZSTD_DDict.
+ * zstd_init_dctx() - initialize a zstd decompression context
+ * @workspace:      The workspace to emplace the context into. It must outlive
+ *                  the returned context.
+ * @workspace_size: The size of workspace. Use zstd_dctx_workspace_bound() to
+ *                  determine how large the workspace must be.
  *
- * Return:         The digested dictionary emplaced into workspace.
+ * Return:          A zstd decompression context or NULL on error.
  */
-ZSTD_DDict *ZSTD_initDDict(const void *dictBuffer, size_t dictSize,
-	void *workspace, size_t workspaceSize);
+zstd_dctx *zstd_init_dctx(void *workspace, size_t workspace_size);
 
 /**
- * ZSTD_decompress_usingDDict() - decompress src into dst using a ZSTD_DDict
- * @ctx:         The decompression context.
- * @dst:         The buffer to decompress src into.
- * @dstCapacity: The size of the destination buffer. Must be at least as large
- *               as the decompressed size. If the caller cannot upper bound the
- *               decompressed size, then it's better to use the streaming API.
- * @src:         The zstd compressed data to decompress. Multiple concatenated
- *               frames and skippable frames are allowed.
- * @srcSize:     The exact size of the data to decompress.
- * @ddict:       The digested dictionary to use for decompression. The same
- *               dictionary must've been used to compress the data.
+ * zstd_decompress_dctx() - decompress zstd compressed src into dst
+ * @dctx:         The decompression context.
+ * @dst:          The buffer to decompress src into.
+ * @dst_capacity: The size of the destination buffer. Must be at least as large
+ *                as the decompressed size. If the caller cannot upper bound the
+ *                decompressed size, then it's better to use the streaming API.
+ * @src:          The zstd compressed data to decompress. Multiple concatenated
+ *                frames and skippable frames are allowed.
+ * @src_size:     The exact size of the data to decompress.
  *
- * Return:       The decompressed size or an error, which can be checked using
- *               ZSTD_isError().
+ * Return:        The decompressed size or an error, which can be checked using
+ *                zstd_is_error().
  */
-size_t ZSTD_decompress_usingDDict(ZSTD_DCtx *dctx, void *dst,
-	size_t dstCapacity, const void *src, size_t srcSize,
-	const ZSTD_DDict *ddict);
+size_t zstd_decompress_dctx(zstd_dctx *dctx, void *dst, size_t dst_capacity,
+	const void *src, size_t src_size);
 
-
-/*-**************************
- * Streaming
- ***************************/
+/* ======   Streaming Buffers   ====== */
 
 /**
- * struct ZSTD_inBuffer - input buffer for streaming
+ * struct zstd_in_buffer - input buffer for streaming
  * @src:  Start of the input buffer.
  * @size: Size of the input buffer.
  * @pos:  Position where reading stopped. Will be updated.
  *        Necessarily 0 <= pos <= size.
+ *
+ * See zstd_lib.h.
  */
-typedef struct ZSTD_inBuffer_s {
-	const void *src;
-	size_t size;
-	size_t pos;
-} ZSTD_inBuffer;
+typedef ZSTD_inBuffer zstd_in_buffer;
 
 /**
- * struct ZSTD_outBuffer - output buffer for streaming
+ * struct zstd_out_buffer - output buffer for streaming
  * @dst:  Start of the output buffer.
  * @size: Size of the output buffer.
  * @pos:  Position where writing stopped. Will be updated.
  *        Necessarily 0 <= pos <= size.
+ *
+ * See zstd_lib.h.
  */
-typedef struct ZSTD_outBuffer_s {
-	void *dst;
-	size_t size;
-	size_t pos;
-} ZSTD_outBuffer;
+typedef ZSTD_outBuffer zstd_out_buffer;
 
+/* ======   Streaming Compression   ====== */
 
-
-/*-*****************************************************************************
- * Streaming compression - HowTo
- *
- * A ZSTD_CStream object is required to track streaming operation.
- * Use ZSTD_initCStream() to initialize a ZSTD_CStream object.
- * ZSTD_CStream objects can be reused multiple times on consecutive compression
- * operations. It is recommended to re-use ZSTD_CStream in situations where many
- * streaming operations will be achieved consecutively. Use one separate
- * ZSTD_CStream per thread for parallel execution.
- *
- * Use ZSTD_compressStream() repetitively to consume input stream.
- * The function will automatically update both `pos` fields.
- * Note that it may not consume the entire input, in which case `pos < size`,
- * and it's up to the caller to present again remaining data.
- * It returns a hint for the preferred number of bytes to use as an input for
- * the next function call.
- *
- * At any moment, it's possible to flush whatever data remains within internal
- * buffer, using ZSTD_flushStream(). `output->pos` will be updated. There might
- * still be some content left within the internal buffer if `output->size` is
- * too small. It returns the number of bytes left in the internal buffer and
- * must be called until it returns 0.
- *
- * ZSTD_endStream() instructs to finish a frame. It will perform a flush and
- * write frame epilogue. The epilogue is required for decoders to consider a
- * frame completed. Similar to ZSTD_flushStream(), it may not be able to flush
- * the full content if `output->size` is too small. In which case, call again
- * ZSTD_endStream() to complete the flush. It returns the number of bytes left
- * in the internal buffer and must be called until it returns 0.
- ******************************************************************************/
+typedef ZSTD_CStream zstd_cstream;
 
 /**
- * ZSTD_CStreamWorkspaceBound() - memory needed to initialize a ZSTD_CStream
- * @cParams: The compression parameters to be used for compression.
+ * zstd_cstream_workspace_bound() - memory needed to initialize a zstd_cstream
+ * @cparams: The compression parameters to be used for compression.
  *
  * Return:   A lower bound on the size of the workspace that is passed to
- *           ZSTD_initCStream() and ZSTD_initCStream_usingCDict().
- */
-size_t ZSTD_CStreamWorkspaceBound(ZSTD_compressionParameters cParams);
-
-/**
- * struct ZSTD_CStream - the zstd streaming compression context
- */
-typedef struct ZSTD_CStream_s ZSTD_CStream;
-
-/*===== ZSTD_CStream management functions =====*/
-/**
- * ZSTD_initCStream() - initialize a zstd streaming compression context
- * @params:         The zstd compression parameters.
- * @pledgedSrcSize: If params.fParams.contentSizeFlag == 1 then the caller must
- *                  pass the source size (zero means empty source). Otherwise,
- *                  the caller may optionally pass the source size, or zero if
- *                  unknown.
- * @workspace:      The workspace to emplace the context into. It must outlive
- *                  the returned context.
- * @workspaceSize:  The size of workspace.
- *                  Use ZSTD_CStreamWorkspaceBound(params.cParams) to determine
- *                  how large the workspace must be.
- *
- * Return:          The zstd streaming compression context.
+ *           zstd_init_cstream().
  */
-ZSTD_CStream *ZSTD_initCStream(ZSTD_parameters params,
-	unsigned long long pledgedSrcSize, void *workspace,
-	size_t workspaceSize);
+size_t zstd_cstream_workspace_bound(const zstd_compression_parameters *cparams);
 
 /**
- * ZSTD_initCStream_usingCDict() - initialize a streaming compression context
- * @cdict:          The digested dictionary to use for compression.
- * @pledgedSrcSize: Optionally the source size, or zero if unknown.
- * @workspace:      The workspace to emplace the context into. It must outlive
- *                  the returned context.
- * @workspaceSize:  The size of workspace. Call ZSTD_CStreamWorkspaceBound()
- *                  with the cParams used to initialize the cdict to determine
- *                  how large the workspace must be.
+ * zstd_init_cstream() - initialize a zstd streaming compression context
+ * @parameters        The zstd parameters to use for compression.
+ * @pledged_src_size: If params.fParams.contentSizeFlag == 1 then the caller
+ *                    must pass the source size (zero means empty source).
+ *                    Otherwise, the caller may optionally pass the source
+ *                    size, or zero if unknown.
+ * @workspace:        The workspace to emplace the context into. It must outlive
+ *                    the returned context.
+ * @workspace_size:   The size of workspace.
+ *                    Use zstd_cstream_workspace_bound(params->cparams) to
+ *                    determine how large the workspace must be.
  *
- * Return:          The zstd streaming compression context.
+ * Return:            The zstd streaming compression context or NULL on error.
  */
-ZSTD_CStream *ZSTD_initCStream_usingCDict(const ZSTD_CDict *cdict,
-	unsigned long long pledgedSrcSize, void *workspace,
-	size_t workspaceSize);
+zstd_cstream *zstd_init_cstream(const zstd_parameters *parameters,
+	unsigned long long pledged_src_size, void *workspace, size_t workspace_size);
 
-/*===== Streaming compression functions =====*/
 /**
- * ZSTD_resetCStream() - reset the context using parameters from creation
- * @zcs:            The zstd streaming compression context to reset.
- * @pledgedSrcSize: Optionally the source size, or zero if unknown.
+ * zstd_reset_cstream() - reset the context using parameters from creation
+ * @cstream:          The zstd streaming compression context to reset.
+ * @pledged_src_size: Optionally the source size, or zero if unknown.
  *
  * Resets the context using the parameters from creation. Skips dictionary
- * loading, since it can be reused. If `pledgedSrcSize` is non-zero the frame
+ * loading, since it can be reused. If `pledged_src_size` is non-zero the frame
  * content size is always written into the frame header.
  *
- * Return:          Zero or an error, which can be checked using ZSTD_isError().
+ * Return:            Zero or an error, which can be checked using
+ *                    zstd_is_error().
  */
-size_t ZSTD_resetCStream(ZSTD_CStream *zcs, unsigned long long pledgedSrcSize);
+size_t zstd_reset_cstream(zstd_cstream *cstream,
+	unsigned long long pledged_src_size);
+
 /**
- * ZSTD_compressStream() - streaming compress some of input into output
- * @zcs:    The zstd streaming compression context.
- * @output: Destination buffer. `output->pos` is updated to indicate how much
- *          compressed data was written.
- * @input:  Source buffer. `input->pos` is updated to indicate how much data was
- *          read. Note that it may not consume the entire input, in which case
- *          `input->pos < input->size`, and it's up to the caller to present
- *          remaining data again.
+ * zstd_compress_stream() - streaming compress some of input into output
+ * @cstream: The zstd streaming compression context.
+ * @output:  Destination buffer. `output->pos` is updated to indicate how much
+ *           compressed data was written.
+ * @input:   Source buffer. `input->pos` is updated to indicate how much data
+ *           was read. Note that it may not consume the entire input, in which
+ *           case `input->pos < input->size`, and it's up to the caller to
+ *           present remaining data again.
  *
  * The `input` and `output` buffers may be any size. Guaranteed to make some
  * forward progress if `input` and `output` are not empty.
  *
- * Return:  A hint for the number of bytes to use as the input for the next
- *          function call or an error, which can be checked using
- *          ZSTD_isError().
+ * Return:   A hint for the number of bytes to use as the input for the next
+ *           function call or an error, which can be checked using
+ *           zstd_is_error().
  */
-size_t ZSTD_compressStream(ZSTD_CStream *zcs, ZSTD_outBuffer *output,
-	ZSTD_inBuffer *input);
+size_t zstd_compress_stream(zstd_cstream *cstream, zstd_out_buffer *output,
+	zstd_in_buffer *input);
+
 /**
- * ZSTD_flushStream() - flush internal buffers into output
- * @zcs:    The zstd streaming compression context.
- * @output: Destination buffer. `output->pos` is updated to indicate how much
- *          compressed data was written.
+ * zstd_flush_stream() - flush internal buffers into output
+ * @cstream: The zstd streaming compression context.
+ * @output:  Destination buffer. `output->pos` is updated to indicate how much
+ *           compressed data was written.
  *
- * ZSTD_flushStream() must be called until it returns 0, meaning all the data
- * has been flushed. Since ZSTD_flushStream() causes a block to be ended,
+ * zstd_flush_stream() must be called until it returns 0, meaning all the data
+ * has been flushed. Since zstd_flush_stream() causes a block to be ended,
  * calling it too often will degrade the compression ratio.
  *
- * Return:  The number of bytes still present within internal buffers or an
- *          error, which can be checked using ZSTD_isError().
+ * Return:   The number of bytes still present within internal buffers or an
+ *           error, which can be checked using zstd_is_error().
  */
-size_t ZSTD_flushStream(ZSTD_CStream *zcs, ZSTD_outBuffer *output);
-/**
- * ZSTD_endStream() - flush internal buffers into output and end the frame
- * @zcs:    The zstd streaming compression context.
- * @output: Destination buffer. `output->pos` is updated to indicate how much
- *          compressed data was written.
- *
- * ZSTD_endStream() must be called until it returns 0, meaning all the data has
- * been flushed and the frame epilogue has been written.
- *
- * Return:  The number of bytes still present within internal buffers or an
- *          error, which can be checked using ZSTD_isError().
- */
-size_t ZSTD_endStream(ZSTD_CStream *zcs, ZSTD_outBuffer *output);
+size_t zstd_flush_stream(zstd_cstream *cstream, zstd_out_buffer *output);
 
 /**
- * ZSTD_CStreamInSize() - recommended size for the input buffer
- *
- * Return: The recommended size for the input buffer.
- */
-size_t ZSTD_CStreamInSize(void);
-/**
- * ZSTD_CStreamOutSize() - recommended size for the output buffer
+ * zstd_end_stream() - flush internal buffers into output and end the frame
+ * @cstream: The zstd streaming compression context.
+ * @output:  Destination buffer. `output->pos` is updated to indicate how much
+ *           compressed data was written.
  *
- * When the output buffer is at least this large, it is guaranteed to be large
- * enough to flush at least one complete compressed block.
+ * zstd_end_stream() must be called until it returns 0, meaning all the data has
+ * been flushed and the frame epilogue has been written.
  *
- * Return: The recommended size for the output buffer.
+ * Return:   The number of bytes still present within internal buffers or an
+ *           error, which can be checked using zstd_is_error().
  */
-size_t ZSTD_CStreamOutSize(void);
+size_t zstd_end_stream(zstd_cstream *cstream, zstd_out_buffer *output);
 
+/* ======   Streaming Decompression   ====== */
 
-
-/*-*****************************************************************************
- * Streaming decompression - HowTo
- *
- * A ZSTD_DStream object is required to track streaming operations.
- * Use ZSTD_initDStream() to initialize a ZSTD_DStream object.
- * ZSTD_DStream objects can be re-used multiple times.
- *
- * Use ZSTD_decompressStream() repetitively to consume your input.
- * The function will update both `pos` fields.
- * If `input->pos < input->size`, some input has not been consumed.
- * It's up to the caller to present again remaining data.
- * If `output->pos < output->size`, decoder has flushed everything it could.
- * Returns 0 iff a frame is completely decoded and fully flushed.
- * Otherwise it returns a suggested next input size that will never load more
- * than the current frame.
- ******************************************************************************/
+typedef ZSTD_DStream zstd_dstream;
 
 /**
- * ZSTD_DStreamWorkspaceBound() - memory needed to initialize a ZSTD_DStream
- * @maxWindowSize: The maximum window size allowed for compressed frames.
+ * zstd_dstream_workspace_bound() - memory needed to initialize a zstd_dstream
+ * @max_window_size: The maximum window size allowed for compressed frames.
  *
- * Return:         A lower bound on the size of the workspace that is passed to
- *                 ZSTD_initDStream() and ZSTD_initDStream_usingDDict().
+ * Return:           A lower bound on the size of the workspace that is passed
+ *                   to zstd_init_dstream().
  */
-size_t ZSTD_DStreamWorkspaceBound(size_t maxWindowSize);
+size_t zstd_dstream_workspace_bound(size_t max_window_size);
 
 /**
- * struct ZSTD_DStream - the zstd streaming decompression context
- */
-typedef struct ZSTD_DStream_s ZSTD_DStream;
-/*===== ZSTD_DStream management functions =====*/
-/**
- * ZSTD_initDStream() - initialize a zstd streaming decompression context
- * @maxWindowSize: The maximum window size allowed for compressed frames.
- * @workspace:     The workspace to emplace the context into. It must outlive
- *                 the returned context.
- * @workspaceSize: The size of workspace.
- *                 Use ZSTD_DStreamWorkspaceBound(maxWindowSize) to determine
- *                 how large the workspace must be.
- *
- * Return:         The zstd streaming decompression context.
- */
-ZSTD_DStream *ZSTD_initDStream(size_t maxWindowSize, void *workspace,
-	size_t workspaceSize);
-/**
- * ZSTD_initDStream_usingDDict() - initialize streaming decompression context
- * @maxWindowSize: The maximum window size allowed for compressed frames.
- * @ddict:         The digested dictionary to use for decompression.
- * @workspace:     The workspace to emplace the context into. It must outlive
- *                 the returned context.
- * @workspaceSize: The size of workspace.
- *                 Use ZSTD_DStreamWorkspaceBound(maxWindowSize) to determine
- *                 how large the workspace must be.
+ * zstd_init_dstream() - initialize a zstd streaming decompression context
+ * @max_window_size: The maximum window size allowed for compressed frames.
+ * @workspace:       The workspace to emplace the context into. It must outlive
+ *                   the returned context.
+ * @workspaceSize:   The size of workspace.
+ *                   Use zstd_dstream_workspace_bound(max_window_size) to
+ *                   determine how large the workspace must be.
  *
- * Return:         The zstd streaming decompression context.
+ * Return:           The zstd streaming decompression context.
  */
-ZSTD_DStream *ZSTD_initDStream_usingDDict(size_t maxWindowSize,
-	const ZSTD_DDict *ddict, void *workspace, size_t workspaceSize);
+zstd_dstream *zstd_init_dstream(size_t max_window_size, void *workspace,
+	size_t workspace_size);
 
-/*===== Streaming decompression functions =====*/
 /**
- * ZSTD_resetDStream() - reset the context using parameters from creation
- * @zds:   The zstd streaming decompression context to reset.
+ * zstd_reset_dstream() - reset the context using parameters from creation
+ * @dstream: The zstd streaming decompression context to reset.
  *
  * Resets the context using the parameters from creation. Skips dictionary
  * loading, since it can be reused.
  *
- * Return: Zero or an error, which can be checked using ZSTD_isError().
+ * Return:   Zero or an error, which can be checked using zstd_is_error().
  */
-size_t ZSTD_resetDStream(ZSTD_DStream *zds);
+size_t zstd_reset_dstream(zstd_dstream *dstream);
+
 /**
- * ZSTD_decompressStream() - streaming decompress some of input into output
- * @zds:    The zstd streaming decompression context.
- * @output: Destination buffer. `output.pos` is updated to indicate how much
- *          decompressed data was written.
- * @input:  Source buffer. `input.pos` is updated to indicate how much data was
- *          read. Note that it may not consume the entire input, in which case
- *          `input.pos < input.size`, and it's up to the caller to present
- *          remaining data again.
+ * zstd_decompress_stream() - streaming decompress some of input into output
+ * @dstream: The zstd streaming decompression context.
+ * @output:  Destination buffer. `output.pos` is updated to indicate how much
+ *           decompressed data was written.
+ * @input:   Source buffer. `input.pos` is updated to indicate how much data was
+ *           read. Note that it may not consume the entire input, in which case
+ *           `input.pos < input.size`, and it's up to the caller to present
+ *           remaining data again.
  *
  * The `input` and `output` buffers may be any size. Guaranteed to make some
  * forward progress if `input` and `output` are not empty.
- * ZSTD_decompressStream() will not consume the last byte of the frame until
+ * zstd_decompress_stream() will not consume the last byte of the frame until
  * the entire frame is flushed.
  *
- * Return:  Returns 0 iff a frame is completely decoded and fully flushed.
- *          Otherwise returns a hint for the number of bytes to use as the input
- *          for the next function call or an error, which can be checked using
- *          ZSTD_isError(). The size hint will never load more than the frame.
+ * Return:   Returns 0 iff a frame is completely decoded and fully flushed.
+ *           Otherwise returns a hint for the number of bytes to use as the
+ *           input for the next function call or an error, which can be checked
+ *           using zstd_is_error(). The size hint will never load more than the
+ *           frame.
  */
-size_t ZSTD_decompressStream(ZSTD_DStream *zds, ZSTD_outBuffer *output,
-	ZSTD_inBuffer *input);
+size_t zstd_decompress_stream(zstd_dstream *dstream, zstd_out_buffer *output,
+	zstd_in_buffer *input);
 
-/**
- * ZSTD_DStreamInSize() - recommended size for the input buffer
- *
- * Return: The recommended size for the input buffer.
- */
-size_t ZSTD_DStreamInSize(void);
-/**
- * ZSTD_DStreamOutSize() - recommended size for the output buffer
- *
- * When the output buffer is at least this large, it is guaranteed to be large
- * enough to flush at least one complete decompressed block.
- *
- * Return: The recommended size for the output buffer.
- */
-size_t ZSTD_DStreamOutSize(void);
-
-
-/* --- Constants ---*/
-#define ZSTD_MAGICNUMBER            0xFD2FB528   /* >= v0.8.0 */
-#define ZSTD_MAGIC_SKIPPABLE_START  0x184D2A50U
-
-#define ZSTD_CONTENTSIZE_UNKNOWN (0ULL - 1)
-#define ZSTD_CONTENTSIZE_ERROR   (0ULL - 2)
-
-#define ZSTD_WINDOWLOG_MAX_32  27
-#define ZSTD_WINDOWLOG_MAX_64  27
-#define ZSTD_WINDOWLOG_MAX \
-	((unsigned int)(sizeof(size_t) == 4 \
-		? ZSTD_WINDOWLOG_MAX_32 \
-		: ZSTD_WINDOWLOG_MAX_64))
-#define ZSTD_WINDOWLOG_MIN 10
-#define ZSTD_HASHLOG_MAX ZSTD_WINDOWLOG_MAX
-#define ZSTD_HASHLOG_MIN        6
-#define ZSTD_CHAINLOG_MAX     (ZSTD_WINDOWLOG_MAX+1)
-#define ZSTD_CHAINLOG_MIN      ZSTD_HASHLOG_MIN
-#define ZSTD_HASHLOG3_MAX      17
-#define ZSTD_SEARCHLOG_MAX    (ZSTD_WINDOWLOG_MAX-1)
-#define ZSTD_SEARCHLOG_MIN      1
-/* only for ZSTD_fast, other strategies are limited to 6 */
-#define ZSTD_SEARCHLENGTH_MAX   7
-/* only for ZSTD_btopt, other strategies are limited to 4 */
-#define ZSTD_SEARCHLENGTH_MIN   3
-#define ZSTD_TARGETLENGTH_MIN   4
-#define ZSTD_TARGETLENGTH_MAX 999
-
-/* for static allocation */
-#define ZSTD_FRAMEHEADERSIZE_MAX 18
-#define ZSTD_FRAMEHEADERSIZE_MIN  6
-#define ZSTD_frameHeaderSize_prefix 5
-#define ZSTD_frameHeaderSize_min ZSTD_FRAMEHEADERSIZE_MIN
-#define ZSTD_frameHeaderSize_max ZSTD_FRAMEHEADERSIZE_MAX
-/* magic number + skippable frame length */
-#define ZSTD_skippableHeaderSize 8
-
-
-/*-*************************************
- * Compressed size functions
- **************************************/
-
-/**
- * ZSTD_findFrameCompressedSize() - returns the size of a compressed frame
- * @src:     Source buffer. It should point to the start of a zstd encoded frame
- *           or a skippable frame.
- * @srcSize: The size of the source buffer. It must be at least as large as the
- *           size of the frame.
- *
- * Return:   The compressed size of the frame pointed to by `src` or an error,
- *           which can be check with ZSTD_isError().
- *           Suitable to pass to ZSTD_decompress() or similar functions.
- */
-size_t ZSTD_findFrameCompressedSize(const void *src, size_t srcSize);
-
-/*-*************************************
- * Decompressed size functions
- **************************************/
-/**
- * ZSTD_getFrameContentSize() - returns the content size in a zstd frame header
- * @src:     It should point to the start of a zstd encoded frame.
- * @srcSize: The size of the source buffer. It must be at least as large as the
- *           frame header. `ZSTD_frameHeaderSize_max` is always large enough.
- *
- * Return:   The frame content size stored in the frame header if known.
- *           `ZSTD_CONTENTSIZE_UNKNOWN` if the content size isn't stored in the
- *           frame header. `ZSTD_CONTENTSIZE_ERROR` on invalid input.
- */
-unsigned long long ZSTD_getFrameContentSize(const void *src, size_t srcSize);
+/* ======   Frame Inspection Functions ====== */
 
 /**
- * ZSTD_findDecompressedSize() - returns decompressed size of a series of frames
- * @src:     It should point to the start of a series of zstd encoded and/or
- *           skippable frames.
- * @srcSize: The exact size of the series of frames.
+ * zstd_find_frame_compressed_size() - returns the size of a compressed frame
+ * @src:      Source buffer. It should point to the start of a zstd encoded
+ *            frame or a skippable frame.
+ * @src_size: The size of the source buffer. It must be at least as large as the
+ *            size of the frame.
  *
- * If any zstd encoded frame in the series doesn't have the frame content size
- * set, `ZSTD_CONTENTSIZE_UNKNOWN` is returned. But frame content size is always
- * set when using ZSTD_compress(). The decompressed size can be very large.
- * If the source is untrusted, the decompressed size could be wrong or
- * intentionally modified. Always ensure the result fits within the
- * application's authorized limits. ZSTD_findDecompressedSize() handles multiple
- * frames, and so it must traverse the input to read each frame header. This is
- * efficient as most of the data is skipped, however it does mean that all frame
- * data must be present and valid.
- *
- * Return:   Decompressed size of all the data contained in the frames if known.
- *           `ZSTD_CONTENTSIZE_UNKNOWN` if the decompressed size is unknown.
- *           `ZSTD_CONTENTSIZE_ERROR` if an error occurred.
- */
-unsigned long long ZSTD_findDecompressedSize(const void *src, size_t srcSize);
-
-/*-*************************************
- * Advanced compression functions
- **************************************/
-/**
- * ZSTD_checkCParams() - ensure parameter values remain within authorized range
- * @cParams: The zstd compression parameters.
- *
- * Return:   Zero or an error, which can be checked using ZSTD_isError().
+ * Return:    The compressed size of the frame pointed to by `src` or an error,
+ *            which can be check with zstd_is_error().
+ *            Suitable to pass to ZSTD_decompress() or similar functions.
  */
-size_t ZSTD_checkCParams(ZSTD_compressionParameters cParams);
+size_t zstd_find_frame_compressed_size(const void *src, size_t src_size);
 
 /**
- * ZSTD_adjustCParams() - optimize parameters for a given srcSize and dictSize
- * @srcSize:  Optionally the estimated source size, or zero if unknown.
- * @dictSize: Optionally the estimated dictionary size, or zero if unknown.
- *
- * Return:    The optimized parameters.
- */
-ZSTD_compressionParameters ZSTD_adjustCParams(
-	ZSTD_compressionParameters cParams, unsigned long long srcSize,
-	size_t dictSize);
-
-/*--- Advanced decompression functions ---*/
-
-/**
- * ZSTD_isFrame() - returns true iff the buffer starts with a valid frame
- * @buffer: The source buffer to check.
- * @size:   The size of the source buffer, must be at least 4 bytes.
- *
- * Return: True iff the buffer starts with a zstd or skippable frame identifier.
- */
-unsigned int ZSTD_isFrame(const void *buffer, size_t size);
-
-/**
- * ZSTD_getDictID_fromDict() - returns the dictionary id stored in a dictionary
- * @dict:     The dictionary buffer.
- * @dictSize: The size of the dictionary buffer.
- *
- * Return:    The dictionary id stored within the dictionary or 0 if the
- *            dictionary is not a zstd dictionary. If it returns 0 the
- *            dictionary can still be loaded as a content-only dictionary.
- */
-unsigned int ZSTD_getDictID_fromDict(const void *dict, size_t dictSize);
-
-/**
- * ZSTD_getDictID_fromDDict() - returns the dictionary id stored in a ZSTD_DDict
- * @ddict: The ddict to find the id of.
- *
- * Return: The dictionary id stored within `ddict` or 0 if the dictionary is not
- *         a zstd dictionary. If it returns 0 `ddict` will be loaded as a
- *         content-only dictionary.
- */
-unsigned int ZSTD_getDictID_fromDDict(const ZSTD_DDict *ddict);
-
-/**
- * ZSTD_getDictID_fromFrame() - returns the dictionary id stored in a zstd frame
- * @src:     Source buffer. It must be a zstd encoded frame.
- * @srcSize: The size of the source buffer. It must be at least as large as the
- *           frame header. `ZSTD_frameHeaderSize_max` is always large enough.
- *
- * Return:   The dictionary id required to decompress the frame stored within
- *           `src` or 0 if the dictionary id could not be decoded. It can return
- *           0 if the frame does not require a dictionary, the dictionary id
- *           wasn't stored in the frame, `src` is not a zstd frame, or `srcSize`
- *           is too small.
- */
-unsigned int ZSTD_getDictID_fromFrame(const void *src, size_t srcSize);
-
-/**
- * struct ZSTD_frameParams - zstd frame parameters stored in the frame header
- * @frameContentSize: The frame content size, or 0 if not present.
+ * struct zstd_frame_params - zstd frame parameters stored in the frame header
+ * @frameContentSize: The frame content size, or ZSTD_CONTENTSIZE_UNKNOWN if not
+ *                    present.
  * @windowSize:       The window size, or 0 if the frame is a skippable frame.
+ * @blockSizeMax:     The maximum block size.
+ * @frameType:        The frame type (zstd or skippable)
+ * @headerSize:       The size of the frame header.
  * @dictID:           The dictionary id, or 0 if not present.
  * @checksumFlag:     Whether a checksum was used.
+ *
+ * See zstd_lib.h.
  */
-typedef struct {
-	unsigned long long frameContentSize;
-	unsigned int windowSize;
-	unsigned int dictID;
-	unsigned int checksumFlag;
-} ZSTD_frameParams;
+typedef ZSTD_frameHeader zstd_frame_header;
 
 /**
- * ZSTD_getFrameParams() - extracts parameters from a zstd or skippable frame
- * @fparamsPtr: On success the frame parameters are written here.
- * @src:        The source buffer. It must point to a zstd or skippable frame.
- * @srcSize:    The size of the source buffer. `ZSTD_frameHeaderSize_max` is
- *              always large enough to succeed.
+ * zstd_get_frame_header() - extracts parameters from a zstd or skippable frame
+ * @params:   On success the frame parameters are written here.
+ * @src:      The source buffer. It must point to a zstd or skippable frame.
+ * @src_size: The size of the source buffer.
  *
- * Return:      0 on success. If more data is required it returns how many bytes
- *              must be provided to make forward progress. Otherwise it returns
- *              an error, which can be checked using ZSTD_isError().
+ * Return:    0 on success. If more data is required it returns how many bytes
+ *            must be provided to make forward progress. Otherwise it returns
+ *            an error, which can be checked using zstd_is_error().
  */
-size_t ZSTD_getFrameParams(ZSTD_frameParams *fparamsPtr, const void *src,
-	size_t srcSize);
-
-/*-*****************************************************************************
- * Buffer-less and synchronous inner streaming functions
- *
- * This is an advanced API, giving full control over buffer management, for
- * users which need direct control over memory.
- * But it's also a complex one, with many restrictions (documented below).
- * Prefer using normal streaming API for an easier experience
- ******************************************************************************/
-
-/*-*****************************************************************************
- * Buffer-less streaming compression (synchronous mode)
- *
- * A ZSTD_CCtx object is required to track streaming operations.
- * Use ZSTD_initCCtx() to initialize a context.
- * ZSTD_CCtx object can be re-used multiple times within successive compression
- * operations.
- *
- * Start by initializing a context.
- * Use ZSTD_compressBegin(), or ZSTD_compressBegin_usingDict() for dictionary
- * compression,
- * or ZSTD_compressBegin_advanced(), for finer parameter control.
- * It's also possible to duplicate a reference context which has already been
- * initialized, using ZSTD_copyCCtx()
- *
- * Then, consume your input using ZSTD_compressContinue().
- * There are some important considerations to keep in mind when using this
- * advanced function :
- * - ZSTD_compressContinue() has no internal buffer. It uses externally provided
- *   buffer only.
- * - Interface is synchronous : input is consumed entirely and produce 1+
- *   (or more) compressed blocks.
- * - Caller must ensure there is enough space in `dst` to store compressed data
- *   under worst case scenario. Worst case evaluation is provided by
- *   ZSTD_compressBound().
- *   ZSTD_compressContinue() doesn't guarantee recover after a failed
- *   compression.
- * - ZSTD_compressContinue() presumes prior input ***is still accessible and
- *   unmodified*** (up to maximum distance size, see WindowLog).
- *   It remembers all previous contiguous blocks, plus one separated memory
- *   segment (which can itself consists of multiple contiguous blocks)
- * - ZSTD_compressContinue() detects that prior input has been overwritten when
- *   `src` buffer overlaps. In which case, it will "discard" the relevant memory
- *   section from its history.
- *
- * Finish a frame with ZSTD_compressEnd(), which will write the last block(s)
- * and optional checksum. It's possible to use srcSize==0, in which case, it
- * will write a final empty block to end the frame. Without last block mark,
- * frames will be considered unfinished (corrupted) by decoders.
- *
- * `ZSTD_CCtx` object can be re-used (ZSTD_compressBegin()) to compress some new
- * frame.
- ******************************************************************************/
-
-/*=====   Buffer-less streaming compression functions  =====*/
-size_t ZSTD_compressBegin(ZSTD_CCtx *cctx, int compressionLevel);
-size_t ZSTD_compressBegin_usingDict(ZSTD_CCtx *cctx, const void *dict,
-	size_t dictSize, int compressionLevel);
-size_t ZSTD_compressBegin_advanced(ZSTD_CCtx *cctx, const void *dict,
-	size_t dictSize, ZSTD_parameters params,
-	unsigned long long pledgedSrcSize);
-size_t ZSTD_copyCCtx(ZSTD_CCtx *cctx, const ZSTD_CCtx *preparedCCtx,
-	unsigned long long pledgedSrcSize);
-size_t ZSTD_compressBegin_usingCDict(ZSTD_CCtx *cctx, const ZSTD_CDict *cdict,
-	unsigned long long pledgedSrcSize);
-size_t ZSTD_compressContinue(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity,
-	const void *src, size_t srcSize);
-size_t ZSTD_compressEnd(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity,
-	const void *src, size_t srcSize);
-
-
-
-/*-*****************************************************************************
- * Buffer-less streaming decompression (synchronous mode)
- *
- * A ZSTD_DCtx object is required to track streaming operations.
- * Use ZSTD_initDCtx() to initialize a context.
- * A ZSTD_DCtx object can be re-used multiple times.
- *
- * First typical operation is to retrieve frame parameters, using
- * ZSTD_getFrameParams(). It fills a ZSTD_frameParams structure which provide
- * important information to correctly decode the frame, such as the minimum
- * rolling buffer size to allocate to decompress data (`windowSize`), and the
- * dictionary ID used.
- * Note: content size is optional, it may not be present. 0 means unknown.
- * Note that these values could be wrong, either because of data malformation,
- * or because an attacker is spoofing deliberate false information. As a
- * consequence, check that values remain within valid application range,
- * especially `windowSize`, before allocation. Each application can set its own
- * limit, depending on local restrictions. For extended interoperability, it is
- * recommended to support at least 8 MB.
- * Frame parameters are extracted from the beginning of the compressed frame.
- * Data fragment must be large enough to ensure successful decoding, typically
- * `ZSTD_frameHeaderSize_max` bytes.
- * Result: 0: successful decoding, the `ZSTD_frameParams` structure is filled.
- *        >0: `srcSize` is too small, provide at least this many bytes.
- *        errorCode, which can be tested using ZSTD_isError().
- *
- * Start decompression, with ZSTD_decompressBegin() or
- * ZSTD_decompressBegin_usingDict(). Alternatively, you can copy a prepared
- * context, using ZSTD_copyDCtx().
- *
- * Then use ZSTD_nextSrcSizeToDecompress() and ZSTD_decompressContinue()
- * alternatively.
- * ZSTD_nextSrcSizeToDecompress() tells how many bytes to provide as 'srcSize'
- * to ZSTD_decompressContinue().
- * ZSTD_decompressContinue() requires this _exact_ amount of bytes, or it will
- * fail.
- *
- * The result of ZSTD_decompressContinue() is the number of bytes regenerated
- * within 'dst' (necessarily <= dstCapacity). It can be zero, which is not an
- * error; it just means ZSTD_decompressContinue() has decoded some metadata
- * item. It can also be an error code, which can be tested with ZSTD_isError().
- *
- * ZSTD_decompressContinue() needs previous data blocks during decompression, up
- * to `windowSize`. They should preferably be located contiguously, prior to
- * current block. Alternatively, a round buffer of sufficient size is also
- * possible. Sufficient size is determined by frame parameters.
- * ZSTD_decompressContinue() is very sensitive to contiguity, if 2 blocks don't
- * follow each other, make sure that either the compressor breaks contiguity at
- * the same place, or that previous contiguous segment is large enough to
- * properly handle maximum back-reference.
- *
- * A frame is fully decoded when ZSTD_nextSrcSizeToDecompress() returns zero.
- * Context can then be reset to start a new decompression.
- *
- * Note: it's possible to know if next input to present is a header or a block,
- * using ZSTD_nextInputType(). This information is not required to properly
- * decode a frame.
- *
- * == Special case: skippable frames ==
- *
- * Skippable frames allow integration of user-defined data into a flow of
- * concatenated frames. Skippable frames will be ignored (skipped) by a
- * decompressor. The format of skippable frames is as follows:
- * a) Skippable frame ID - 4 Bytes, Little endian format, any value from
- *    0x184D2A50 to 0x184D2A5F
- * b) Frame Size - 4 Bytes, Little endian format, unsigned 32-bits
- * c) Frame Content - any content (User Data) of length equal to Frame Size
- * For skippable frames ZSTD_decompressContinue() always returns 0.
- * For skippable frames ZSTD_getFrameParams() returns fparamsPtr->windowLog==0
- * what means that a frame is skippable.
- * Note: If fparamsPtr->frameContentSize==0, it is ambiguous: the frame might
- *       actually be a zstd encoded frame with no content. For purposes of
- *       decompression, it is valid in both cases to skip the frame using
- *       ZSTD_findFrameCompressedSize() to find its size in bytes.
- * It also returns frame size as fparamsPtr->frameContentSize.
- ******************************************************************************/
-
-/*=====   Buffer-less streaming decompression functions  =====*/
-size_t ZSTD_decompressBegin(ZSTD_DCtx *dctx);
-size_t ZSTD_decompressBegin_usingDict(ZSTD_DCtx *dctx, const void *dict,
-	size_t dictSize);
-void   ZSTD_copyDCtx(ZSTD_DCtx *dctx, const ZSTD_DCtx *preparedDCtx);
-size_t ZSTD_nextSrcSizeToDecompress(ZSTD_DCtx *dctx);
-size_t ZSTD_decompressContinue(ZSTD_DCtx *dctx, void *dst, size_t dstCapacity,
-	const void *src, size_t srcSize);
-typedef enum {
-	ZSTDnit_frameHeader,
-	ZSTDnit_blockHeader,
-	ZSTDnit_block,
-	ZSTDnit_lastBlock,
-	ZSTDnit_checksum,
-	ZSTDnit_skippableFrame
-} ZSTD_nextInputType_e;
-ZSTD_nextInputType_e ZSTD_nextInputType(ZSTD_DCtx *dctx);
-
-/*-*****************************************************************************
- * Block functions
- *
- * Block functions produce and decode raw zstd blocks, without frame metadata.
- * Frame metadata cost is typically ~18 bytes, which can be non-negligible for
- * very small blocks (< 100 bytes). User will have to take in charge required
- * information to regenerate data, such as compressed and content sizes.
- *
- * A few rules to respect:
- * - Compressing and decompressing require a context structure
- *   + Use ZSTD_initCCtx() and ZSTD_initDCtx()
- * - It is necessary to init context before starting
- *   + compression : ZSTD_compressBegin()
- *   + decompression : ZSTD_decompressBegin()
- *   + variants _usingDict() are also allowed
- *   + copyCCtx() and copyDCtx() work too
- * - Block size is limited, it must be <= ZSTD_getBlockSizeMax()
- *   + If you need to compress more, cut data into multiple blocks
- *   + Consider using the regular ZSTD_compress() instead, as frame metadata
- *     costs become negligible when source size is large.
- * - When a block is considered not compressible enough, ZSTD_compressBlock()
- *   result will be zero. In which case, nothing is produced into `dst`.
- *   + User must test for such outcome and deal directly with uncompressed data
- *   + ZSTD_decompressBlock() doesn't accept uncompressed data as input!!!
- *   + In case of multiple successive blocks, decoder must be informed of
- *     uncompressed block existence to follow proper history. Use
- *     ZSTD_insertBlock() in such a case.
- ******************************************************************************/
-
-/* Define for static allocation */
-#define ZSTD_BLOCKSIZE_ABSOLUTEMAX (128 * 1024)
-/*=====   Raw zstd block functions  =====*/
-size_t ZSTD_getBlockSizeMax(ZSTD_CCtx *cctx);
-size_t ZSTD_compressBlock(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity,
-	const void *src, size_t srcSize);
-size_t ZSTD_decompressBlock(ZSTD_DCtx *dctx, void *dst, size_t dstCapacity,
-	const void *src, size_t srcSize);
-size_t ZSTD_insertBlock(ZSTD_DCtx *dctx, const void *blockStart,
-	size_t blockSize);
+size_t zstd_get_frame_header(zstd_frame_header *params, const void *src,
+	size_t src_size);
 
-#endif  /* ZSTD_H */
+#endif  /* LINUX_ZSTD_H */
diff --git a/include/linux/zstd_errors.h b/include/linux/zstd_errors.h
new file mode 100644
index 000000000000..58b6dd45a969
--- /dev/null
+++ b/include/linux/zstd_errors.h
@@ -0,0 +1,77 @@
+/*
+ * Copyright (c) Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+#ifndef ZSTD_ERRORS_H_398273423
+#define ZSTD_ERRORS_H_398273423
+
+
+/*===== dependency =====*/
+#include <linux/types.h>   /* size_t */
+
+
+/* =====   ZSTDERRORLIB_API : control library symbols visibility   ===== */
+#define ZSTDERRORLIB_VISIBILITY 
+#define ZSTDERRORLIB_API ZSTDERRORLIB_VISIBILITY
+
+/*-*********************************************
+ *  Error codes list
+ *-*********************************************
+ *  Error codes _values_ are pinned down since v1.3.1 only.
+ *  Therefore, don't rely on values if you may link to any version < v1.3.1.
+ *
+ *  Only values < 100 are considered stable.
+ *
+ *  note 1 : this API shall be used with static linking only.
+ *           dynamic linking is not yet officially supported.
+ *  note 2 : Prefer relying on the enum than on its value whenever possible
+ *           This is the only supported way to use the error list < v1.3.1
+ *  note 3 : ZSTD_isError() is always correct, whatever the library version.
+ **********************************************/
+typedef enum {
+  ZSTD_error_no_error = 0,
+  ZSTD_error_GENERIC  = 1,
+  ZSTD_error_prefix_unknown                = 10,
+  ZSTD_error_version_unsupported           = 12,
+  ZSTD_error_frameParameter_unsupported    = 14,
+  ZSTD_error_frameParameter_windowTooLarge = 16,
+  ZSTD_error_corruption_detected = 20,
+  ZSTD_error_checksum_wrong      = 22,
+  ZSTD_error_dictionary_corrupted      = 30,
+  ZSTD_error_dictionary_wrong          = 32,
+  ZSTD_error_dictionaryCreation_failed = 34,
+  ZSTD_error_parameter_unsupported   = 40,
+  ZSTD_error_parameter_outOfBound    = 42,
+  ZSTD_error_tableLog_tooLarge       = 44,
+  ZSTD_error_maxSymbolValue_tooLarge = 46,
+  ZSTD_error_maxSymbolValue_tooSmall = 48,
+  ZSTD_error_stage_wrong       = 60,
+  ZSTD_error_init_missing      = 62,
+  ZSTD_error_memory_allocation = 64,
+  ZSTD_error_workSpace_tooSmall= 66,
+  ZSTD_error_dstSize_tooSmall = 70,
+  ZSTD_error_srcSize_wrong    = 72,
+  ZSTD_error_dstBuffer_null   = 74,
+  /* following error codes are __NOT STABLE__, they can be removed or changed in future versions */
+  ZSTD_error_frameIndex_tooLarge = 100,
+  ZSTD_error_seekableIO          = 102,
+  ZSTD_error_dstBuffer_wrong     = 104,
+  ZSTD_error_srcBuffer_wrong     = 105,
+  ZSTD_error_maxCode = 120  /* never EVER use this value directly, it can change in future versions! Use ZSTD_isError() instead */
+} ZSTD_ErrorCode;
+
+/*! ZSTD_getErrorCode() :
+    convert a `size_t` function result into a `ZSTD_ErrorCode` enum type,
+    which can be used to compare with enum list published above */
+ZSTDERRORLIB_API ZSTD_ErrorCode ZSTD_getErrorCode(size_t functionResult);
+ZSTDERRORLIB_API const char* ZSTD_getErrorString(ZSTD_ErrorCode code);   /*< Same as ZSTD_getErrorName, but using a `ZSTD_ErrorCode` enum argument */
+
+
+
+#endif /* ZSTD_ERRORS_H_398273423 */
diff --git a/include/linux/zstd_lib.h b/include/linux/zstd_lib.h
new file mode 100644
index 000000000000..b8c7dbf98390
--- /dev/null
+++ b/include/linux/zstd_lib.h
@@ -0,0 +1,2432 @@
+/*
+ * Copyright (c) Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+#ifndef ZSTD_H_235446
+#define ZSTD_H_235446
+
+/* ======   Dependency   ======*/
+#include <linux/limits.h>   /* INT_MAX */
+#include <linux/types.h>   /* size_t */
+
+
+/* =====   ZSTDLIB_API : control library symbols visibility   ===== */
+#define ZSTDLIB_VISIBILITY 
+#define ZSTDLIB_API ZSTDLIB_VISIBILITY
+
+
+/* *****************************************************************************
+  Introduction
+
+  zstd, short for Zstandard, is a fast lossless compression algorithm, targeting
+  real-time compression scenarios at zlib-level and better compression ratios.
+  The zstd compression library provides in-memory compression and decompression
+  functions.
+
+  The library supports regular compression levels from 1 up to ZSTD_maxCLevel(),
+  which is currently 22. Levels >= 20, labeled `--ultra`, should be used with
+  caution, as they require more memory. The library also offers negative
+  compression levels, which extend the range of speed vs. ratio preferences.
+  The lower the level, the faster the speed (at the cost of compression).
+
+  Compression can be done in:
+    - a single step (described as Simple API)
+    - a single step, reusing a context (described as Explicit context)
+    - unbounded multiple steps (described as Streaming compression)
+
+  The compression ratio achievable on small data can be highly improved using
+  a dictionary. Dictionary compression can be performed in:
+    - a single step (described as Simple dictionary API)
+    - a single step, reusing a dictionary (described as Bulk-processing
+      dictionary API)
+
+  Advanced experimental functions can be accessed using
+  `#define ZSTD_STATIC_LINKING_ONLY` before including zstd.h.
+
+  Advanced experimental APIs should never be used with a dynamically-linked
+  library. They are not "stable"; their definitions or signatures may change in
+  the future. Only static linking is allowed.
+*******************************************************************************/
+
+/*------   Version   ------*/
+#define ZSTD_VERSION_MAJOR    1
+#define ZSTD_VERSION_MINOR    4
+#define ZSTD_VERSION_RELEASE  10
+#define ZSTD_VERSION_NUMBER  (ZSTD_VERSION_MAJOR *100*100 + ZSTD_VERSION_MINOR *100 + ZSTD_VERSION_RELEASE)
+
+/*! ZSTD_versionNumber() :
+ *  Return runtime library version, the value is (MAJOR*100*100 + MINOR*100 + RELEASE). */
+ZSTDLIB_API unsigned ZSTD_versionNumber(void);
+
+#define ZSTD_LIB_VERSION ZSTD_VERSION_MAJOR.ZSTD_VERSION_MINOR.ZSTD_VERSION_RELEASE
+#define ZSTD_QUOTE(str) #str
+#define ZSTD_EXPAND_AND_QUOTE(str) ZSTD_QUOTE(str)
+#define ZSTD_VERSION_STRING ZSTD_EXPAND_AND_QUOTE(ZSTD_LIB_VERSION)
+
+/*! ZSTD_versionString() :
+ *  Return runtime library version, like "1.4.5". Requires v1.3.0+. */
+ZSTDLIB_API const char* ZSTD_versionString(void);
+
+/* *************************************
+ *  Default constant
+ ***************************************/
+#ifndef ZSTD_CLEVEL_DEFAULT
+#  define ZSTD_CLEVEL_DEFAULT 3
+#endif
+
+/* *************************************
+ *  Constants
+ ***************************************/
+
+/* All magic numbers are supposed read/written to/from files/memory using little-endian convention */
+#define ZSTD_MAGICNUMBER            0xFD2FB528    /* valid since v0.8.0 */
+#define ZSTD_MAGIC_DICTIONARY       0xEC30A437    /* valid since v0.7.0 */
+#define ZSTD_MAGIC_SKIPPABLE_START  0x184D2A50    /* all 16 values, from 0x184D2A50 to 0x184D2A5F, signal the beginning of a skippable frame */
+#define ZSTD_MAGIC_SKIPPABLE_MASK   0xFFFFFFF0
+
+#define ZSTD_BLOCKSIZELOG_MAX  17
+#define ZSTD_BLOCKSIZE_MAX     (1<<ZSTD_BLOCKSIZELOG_MAX)
+
+
+
+/* *************************************
+*  Simple API
+***************************************/
+/*! ZSTD_compress() :
+ *  Compresses `src` content as a single zstd compressed frame into already allocated `dst`.
+ *  Hint : compression runs faster if `dstCapacity` >=  `ZSTD_compressBound(srcSize)`.
+ *  @return : compressed size written into `dst` (<= `dstCapacity),
+ *            or an error code if it fails (which can be tested using ZSTD_isError()). */
+ZSTDLIB_API size_t ZSTD_compress( void* dst, size_t dstCapacity,
+                            const void* src, size_t srcSize,
+                                  int compressionLevel);
+
+/*! ZSTD_decompress() :
+ *  `compressedSize` : must be the _exact_ size of some number of compressed and/or skippable frames.
+ *  `dstCapacity` is an upper bound of originalSize to regenerate.
+ *  If user cannot imply a maximum upper bound, it's better to use streaming mode to decompress data.
+ *  @return : the number of bytes decompressed into `dst` (<= `dstCapacity`),
+ *            or an errorCode if it fails (which can be tested using ZSTD_isError()). */
+ZSTDLIB_API size_t ZSTD_decompress( void* dst, size_t dstCapacity,
+                              const void* src, size_t compressedSize);
+
+/*! ZSTD_getFrameContentSize() : requires v1.3.0+
+ *  `src` should point to the start of a ZSTD encoded frame.
+ *  `srcSize` must be at least as large as the frame header.
+ *            hint : any size >= `ZSTD_frameHeaderSize_max` is large enough.
+ *  @return : - decompressed size of `src` frame content, if known
+ *            - ZSTD_CONTENTSIZE_UNKNOWN if the size cannot be determined
+ *            - ZSTD_CONTENTSIZE_ERROR if an error occurred (e.g. invalid magic number, srcSize too small)
+ *   note 1 : a 0 return value means the frame is valid but "empty".
+ *   note 2 : decompressed size is an optional field, it may not be present, typically in streaming mode.
+ *            When `return==ZSTD_CONTENTSIZE_UNKNOWN`, data to decompress could be any size.
+ *            In which case, it's necessary to use streaming mode to decompress data.
+ *            Optionally, application can rely on some implicit limit,
+ *            as ZSTD_decompress() only needs an upper bound of decompressed size.
+ *            (For example, data could be necessarily cut into blocks <= 16 KB).
+ *   note 3 : decompressed size is always present when compression is completed using single-pass functions,
+ *            such as ZSTD_compress(), ZSTD_compressCCtx() ZSTD_compress_usingDict() or ZSTD_compress_usingCDict().
+ *   note 4 : decompressed size can be very large (64-bits value),
+ *            potentially larger than what local system can handle as a single memory segment.
+ *            In which case, it's necessary to use streaming mode to decompress data.
+ *   note 5 : If source is untrusted, decompressed size could be wrong or intentionally modified.
+ *            Always ensure return value fits within application's authorized limits.
+ *            Each application can set its own limits.
+ *   note 6 : This function replaces ZSTD_getDecompressedSize() */
+#define ZSTD_CONTENTSIZE_UNKNOWN (0ULL - 1)
+#define ZSTD_CONTENTSIZE_ERROR   (0ULL - 2)
+ZSTDLIB_API unsigned long long ZSTD_getFrameContentSize(const void *src, size_t srcSize);
+
+/*! ZSTD_getDecompressedSize() :
+ *  NOTE: This function is now obsolete, in favor of ZSTD_getFrameContentSize().
+ *  Both functions work the same way, but ZSTD_getDecompressedSize() blends
+ *  "empty", "unknown" and "error" results to the same return value (0),
+ *  while ZSTD_getFrameContentSize() gives them separate return values.
+ * @return : decompressed size of `src` frame content _if known and not empty_, 0 otherwise. */
+ZSTDLIB_API unsigned long long ZSTD_getDecompressedSize(const void* src, size_t srcSize);
+
+/*! ZSTD_findFrameCompressedSize() :
+ * `src` should point to the start of a ZSTD frame or skippable frame.
+ * `srcSize` must be >= first frame size
+ * @return : the compressed size of the first frame starting at `src`,
+ *           suitable to pass as `srcSize` to `ZSTD_decompress` or similar,
+ *        or an error code if input is invalid */
+ZSTDLIB_API size_t ZSTD_findFrameCompressedSize(const void* src, size_t srcSize);
+
+
+/*======  Helper functions  ======*/
+#define ZSTD_COMPRESSBOUND(srcSize)   ((srcSize) + ((srcSize)>>8) + (((srcSize) < (128<<10)) ? (((128<<10) - (srcSize)) >> 11) /* margin, from 64 to 0 */ : 0))  /* this formula ensures that bound(A) + bound(B) <= bound(A+B) as long as A and B >= 128 KB */
+ZSTDLIB_API size_t      ZSTD_compressBound(size_t srcSize); /*!< maximum compressed size in worst case single-pass scenario */
+ZSTDLIB_API unsigned    ZSTD_isError(size_t code);          /*!< tells if a `size_t` function result is an error code */
+ZSTDLIB_API const char* ZSTD_getErrorName(size_t code);     /*!< provides readable string from an error code */
+ZSTDLIB_API int         ZSTD_minCLevel(void);               /*!< minimum negative compression level allowed */
+ZSTDLIB_API int         ZSTD_maxCLevel(void);               /*!< maximum compression level available */
+
+
+/* *************************************
+*  Explicit context
+***************************************/
+/*= Compression context
+ *  When compressing many times,
+ *  it is recommended to allocate a context just once,
+ *  and re-use it for each successive compression operation.
+ *  This will make workload friendlier for system's memory.
+ *  Note : re-using context is just a speed / resource optimization.
+ *         It doesn't change the compression ratio, which remains identical.
+ *  Note 2 : In multi-threaded environments,
+ *         use one different context per thread for parallel execution.
+ */
+typedef struct ZSTD_CCtx_s ZSTD_CCtx;
+ZSTDLIB_API ZSTD_CCtx* ZSTD_createCCtx(void);
+ZSTDLIB_API size_t     ZSTD_freeCCtx(ZSTD_CCtx* cctx);  /* accept NULL pointer */
+
+/*! ZSTD_compressCCtx() :
+ *  Same as ZSTD_compress(), using an explicit ZSTD_CCtx.
+ *  Important : in order to behave similarly to `ZSTD_compress()`,
+ *  this function compresses at requested compression level,
+ *  __ignoring any other parameter__ .
+ *  If any advanced parameter was set using the advanced API,
+ *  they will all be reset. Only `compressionLevel` remains.
+ */
+ZSTDLIB_API size_t ZSTD_compressCCtx(ZSTD_CCtx* cctx,
+                                     void* dst, size_t dstCapacity,
+                               const void* src, size_t srcSize,
+                                     int compressionLevel);
+
+/*= Decompression context
+ *  When decompressing many times,
+ *  it is recommended to allocate a context only once,
+ *  and re-use it for each successive compression operation.
+ *  This will make workload friendlier for system's memory.
+ *  Use one context per thread for parallel execution. */
+typedef struct ZSTD_DCtx_s ZSTD_DCtx;
+ZSTDLIB_API ZSTD_DCtx* ZSTD_createDCtx(void);
+ZSTDLIB_API size_t     ZSTD_freeDCtx(ZSTD_DCtx* dctx);  /* accept NULL pointer */
+
+/*! ZSTD_decompressDCtx() :
+ *  Same as ZSTD_decompress(),
+ *  requires an allocated ZSTD_DCtx.
+ *  Compatible with sticky parameters.
+ */
+ZSTDLIB_API size_t ZSTD_decompressDCtx(ZSTD_DCtx* dctx,
+                                       void* dst, size_t dstCapacity,
+                                 const void* src, size_t srcSize);
+
+
+/* *************************************
+*  Advanced compression API
+***************************************/
+
+/* API design :
+ *   Parameters are pushed one by one into an existing context,
+ *   using ZSTD_CCtx_set*() functions.
+ *   Pushed parameters are sticky : they are valid for next compressed frame, and any subsequent frame.
+ *   "sticky" parameters are applicable to `ZSTD_compress2()` and `ZSTD_compressStream*()` !
+ *   __They do not apply to "simple" one-shot variants such as ZSTD_compressCCtx()__ .
+ *
+ *   It's possible to reset all parameters to "default" using ZSTD_CCtx_reset().
+ *
+ *   This API supercedes all other "advanced" API entry points in the experimental section.
+ *   In the future, we expect to remove from experimental API entry points which are redundant with this API.
+ */
+
+
+/* Compression strategies, listed from fastest to strongest */
+typedef enum { ZSTD_fast=1,
+               ZSTD_dfast=2,
+               ZSTD_greedy=3,
+               ZSTD_lazy=4,
+               ZSTD_lazy2=5,
+               ZSTD_btlazy2=6,
+               ZSTD_btopt=7,
+               ZSTD_btultra=8,
+               ZSTD_btultra2=9
+               /* note : new strategies _might_ be added in the future.
+                         Only the order (from fast to strong) is guaranteed */
+} ZSTD_strategy;
+
+
+typedef enum {
+
+    /* compression parameters
+     * Note: When compressing with a ZSTD_CDict these parameters are superseded
+     * by the parameters used to construct the ZSTD_CDict.
+     * See ZSTD_CCtx_refCDict() for more info (superseded-by-cdict). */
+    ZSTD_c_compressionLevel=100, /* Set compression parameters according to pre-defined cLevel table.
+                              * Note that exact compression parameters are dynamically determined,
+                              * depending on both compression level and srcSize (when known).
+                              * Default level is ZSTD_CLEVEL_DEFAULT==3.
+                              * Special: value 0 means default, which is controlled by ZSTD_CLEVEL_DEFAULT.
+                              * Note 1 : it's possible to pass a negative compression level.
+                              * Note 2 : setting a level does not automatically set all other compression parameters
+                              *   to default. Setting this will however eventually dynamically impact the compression
+                              *   parameters which have not been manually set. The manually set
+                              *   ones will 'stick'. */
+    /* Advanced compression parameters :
+     * It's possible to pin down compression parameters to some specific values.
+     * In which case, these values are no longer dynamically selected by the compressor */
+    ZSTD_c_windowLog=101,    /* Maximum allowed back-reference distance, expressed as power of 2.
+                              * This will set a memory budget for streaming decompression,
+                              * with larger values requiring more memory
+                              * and typically compressing more.
+                              * Must be clamped between ZSTD_WINDOWLOG_MIN and ZSTD_WINDOWLOG_MAX.
+                              * Special: value 0 means "use default windowLog".
+                              * Note: Using a windowLog greater than ZSTD_WINDOWLOG_LIMIT_DEFAULT
+                              *       requires explicitly allowing such size at streaming decompression stage. */
+    ZSTD_c_hashLog=102,      /* Size of the initial probe table, as a power of 2.
+                              * Resulting memory usage is (1 << (hashLog+2)).
+                              * Must be clamped between ZSTD_HASHLOG_MIN and ZSTD_HASHLOG_MAX.
+                              * Larger tables improve compression ratio of strategies <= dFast,
+                              * and improve speed of strategies > dFast.
+                              * Special: value 0 means "use default hashLog". */
+    ZSTD_c_chainLog=103,     /* Size of the multi-probe search table, as a power of 2.
+                              * Resulting memory usage is (1 << (chainLog+2)).
+                              * Must be clamped between ZSTD_CHAINLOG_MIN and ZSTD_CHAINLOG_MAX.
+                              * Larger tables result in better and slower compression.
+                              * This parameter is useless for "fast" strategy.
+                              * It's still useful when using "dfast" strategy,
+                              * in which case it defines a secondary probe table.
+                              * Special: value 0 means "use default chainLog". */
+    ZSTD_c_searchLog=104,    /* Number of search attempts, as a power of 2.
+                              * More attempts result in better and slower compression.
+                              * This parameter is useless for "fast" and "dFast" strategies.
+                              * Special: value 0 means "use default searchLog". */
+    ZSTD_c_minMatch=105,     /* Minimum size of searched matches.
+                              * Note that Zstandard can still find matches of smaller size,
+                              * it just tweaks its search algorithm to look for this size and larger.
+                              * Larger values increase compression and decompression speed, but decrease ratio.
+                              * Must be clamped between ZSTD_MINMATCH_MIN and ZSTD_MINMATCH_MAX.
+                              * Note that currently, for all strategies < btopt, effective minimum is 4.
+                              *                    , for all strategies > fast, effective maximum is 6.
+                              * Special: value 0 means "use default minMatchLength". */
+    ZSTD_c_targetLength=106, /* Impact of this field depends on strategy.
+                              * For strategies btopt, btultra & btultra2:
+                              *     Length of Match considered "good enough" to stop search.
+                              *     Larger values make compression stronger, and slower.
+                              * For strategy fast:
+                              *     Distance between match sampling.
+                              *     Larger values make compression faster, and weaker.
+                              * Special: value 0 means "use default targetLength". */
+    ZSTD_c_strategy=107,     /* See ZSTD_strategy enum definition.
+                              * The higher the value of selected strategy, the more complex it is,
+                              * resulting in stronger and slower compression.
+                              * Special: value 0 means "use default strategy". */
+
+    /* LDM mode parameters */
+    ZSTD_c_enableLongDistanceMatching=160, /* Enable long distance matching.
+                                     * This parameter is designed to improve compression ratio
+                                     * for large inputs, by finding large matches at long distance.
+                                     * It increases memory usage and window size.
+                                     * Note: enabling this parameter increases default ZSTD_c_windowLog to 128 MB
+                                     * except when expressly set to a different value.
+                                     * Note: will be enabled by default if ZSTD_c_windowLog >= 128 MB and
+                                     * compression strategy >= ZSTD_btopt (== compression level 16+) */
+    ZSTD_c_ldmHashLog=161,   /* Size of the table for long distance matching, as a power of 2.
+                              * Larger values increase memory usage and compression ratio,
+                              * but decrease compression speed.
+                              * Must be clamped between ZSTD_HASHLOG_MIN and ZSTD_HASHLOG_MAX
+                              * default: windowlog - 7.
+                              * Special: value 0 means "automatically determine hashlog". */
+    ZSTD_c_ldmMinMatch=162,  /* Minimum match size for long distance matcher.
+                              * Larger/too small values usually decrease compression ratio.
+                              * Must be clamped between ZSTD_LDM_MINMATCH_MIN and ZSTD_LDM_MINMATCH_MAX.
+                              * Special: value 0 means "use default value" (default: 64). */
+    ZSTD_c_ldmBucketSizeLog=163, /* Log size of each bucket in the LDM hash table for collision resolution.
+                              * Larger values improve collision resolution but decrease compression speed.
+                              * The maximum value is ZSTD_LDM_BUCKETSIZELOG_MAX.
+                              * Special: value 0 means "use default value" (default: 3). */
+    ZSTD_c_ldmHashRateLog=164, /* Frequency of inserting/looking up entries into the LDM hash table.
+                              * Must be clamped between 0 and (ZSTD_WINDOWLOG_MAX - ZSTD_HASHLOG_MIN).
+                              * Default is MAX(0, (windowLog - ldmHashLog)), optimizing hash table usage.
+                              * Larger values improve compression speed.
+                              * Deviating far from default value will likely result in a compression ratio decrease.
+                              * Special: value 0 means "automatically determine hashRateLog". */
+
+    /* frame parameters */
+    ZSTD_c_contentSizeFlag=200, /* Content size will be written into frame header _whenever known_ (default:1)
+                              * Content size must be known at the beginning of compression.
+                              * This is automatically the case when using ZSTD_compress2(),
+                              * For streaming scenarios, content size must be provided with ZSTD_CCtx_setPledgedSrcSize() */
+    ZSTD_c_checksumFlag=201, /* A 32-bits checksum of content is written at end of frame (default:0) */
+    ZSTD_c_dictIDFlag=202,   /* When applicable, dictionary's ID is written into frame header (default:1) */
+
+    /* multi-threading parameters */
+    /* These parameters are only active if multi-threading is enabled (compiled with build macro ZSTD_MULTITHREAD).
+     * Otherwise, trying to set any other value than default (0) will be a no-op and return an error.
+     * In a situation where it's unknown if the linked library supports multi-threading or not,
+     * setting ZSTD_c_nbWorkers to any value >= 1 and consulting the return value provides a quick way to check this property.
+     */
+    ZSTD_c_nbWorkers=400,    /* Select how many threads will be spawned to compress in parallel.
+                              * When nbWorkers >= 1, triggers asynchronous mode when invoking ZSTD_compressStream*() :
+                              * ZSTD_compressStream*() consumes input and flush output if possible, but immediately gives back control to caller,
+                              * while compression is performed in parallel, within worker thread(s).
+                              * (note : a strong exception to this rule is when first invocation of ZSTD_compressStream2() sets ZSTD_e_end :
+                              *  in which case, ZSTD_compressStream2() delegates to ZSTD_compress2(), which is always a blocking call).
+                              * More workers improve speed, but also increase memory usage.
+                              * Default value is `0`, aka "single-threaded mode" : no worker is spawned,
+                              * compression is performed inside Caller's thread, and all invocations are blocking */
+    ZSTD_c_jobSize=401,      /* Size of a compression job. This value is enforced only when nbWorkers >= 1.
+                              * Each compression job is completed in parallel, so this value can indirectly impact the nb of active threads.
+                              * 0 means default, which is dynamically determined based on compression parameters.
+                              * Job size must be a minimum of overlap size, or 1 MB, whichever is largest.
+                              * The minimum size is automatically and transparently enforced. */
+    ZSTD_c_overlapLog=402,   /* Control the overlap size, as a fraction of window size.
+                              * The overlap size is an amount of data reloaded from previous job at the beginning of a new job.
+                              * It helps preserve compression ratio, while each job is compressed in parallel.
+                              * This value is enforced only when nbWorkers >= 1.
+                              * Larger values increase compression ratio, but decrease speed.
+                              * Possible values range from 0 to 9 :
+                              * - 0 means "default" : value will be determined by the library, depending on strategy
+                              * - 1 means "no overlap"
+                              * - 9 means "full overlap", using a full window size.
+                              * Each intermediate rank increases/decreases load size by a factor 2 :
+                              * 9: full window;  8: w/2;  7: w/4;  6: w/8;  5:w/16;  4: w/32;  3:w/64;  2:w/128;  1:no overlap;  0:default
+                              * default value varies between 6 and 9, depending on strategy */
+
+    /* note : additional experimental parameters are also available
+     * within the experimental section of the API.
+     * At the time of this writing, they include :
+     * ZSTD_c_rsyncable
+     * ZSTD_c_format
+     * ZSTD_c_forceMaxWindow
+     * ZSTD_c_forceAttachDict
+     * ZSTD_c_literalCompressionMode
+     * ZSTD_c_targetCBlockSize
+     * ZSTD_c_srcSizeHint
+     * ZSTD_c_enableDedicatedDictSearch
+     * ZSTD_c_stableInBuffer
+     * ZSTD_c_stableOutBuffer
+     * ZSTD_c_blockDelimiters
+     * ZSTD_c_validateSequences
+     * Because they are not stable, it's necessary to define ZSTD_STATIC_LINKING_ONLY to access them.
+     * note : never ever use experimentalParam? names directly;
+     *        also, the enums values themselves are unstable and can still change.
+     */
+     ZSTD_c_experimentalParam1=500,
+     ZSTD_c_experimentalParam2=10,
+     ZSTD_c_experimentalParam3=1000,
+     ZSTD_c_experimentalParam4=1001,
+     ZSTD_c_experimentalParam5=1002,
+     ZSTD_c_experimentalParam6=1003,
+     ZSTD_c_experimentalParam7=1004,
+     ZSTD_c_experimentalParam8=1005,
+     ZSTD_c_experimentalParam9=1006,
+     ZSTD_c_experimentalParam10=1007,
+     ZSTD_c_experimentalParam11=1008,
+     ZSTD_c_experimentalParam12=1009
+} ZSTD_cParameter;
+
+typedef struct {
+    size_t error;
+    int lowerBound;
+    int upperBound;
+} ZSTD_bounds;
+
+/*! ZSTD_cParam_getBounds() :
+ *  All parameters must belong to an interval with lower and upper bounds,
+ *  otherwise they will either trigger an error or be automatically clamped.
+ * @return : a structure, ZSTD_bounds, which contains
+ *         - an error status field, which must be tested using ZSTD_isError()
+ *         - lower and upper bounds, both inclusive
+ */
+ZSTDLIB_API ZSTD_bounds ZSTD_cParam_getBounds(ZSTD_cParameter cParam);
+
+/*! ZSTD_CCtx_setParameter() :
+ *  Set one compression parameter, selected by enum ZSTD_cParameter.
+ *  All parameters have valid bounds. Bounds can be queried using ZSTD_cParam_getBounds().
+ *  Providing a value beyond bound will either clamp it, or trigger an error (depending on parameter).
+ *  Setting a parameter is generally only possible during frame initialization (before starting compression).
+ *  Exception : when using multi-threading mode (nbWorkers >= 1),
+ *              the following parameters can be updated _during_ compression (within same frame):
+ *              => compressionLevel, hashLog, chainLog, searchLog, minMatch, targetLength and strategy.
+ *              new parameters will be active for next job only (after a flush()).
+ * @return : an error code (which can be tested using ZSTD_isError()).
+ */
+ZSTDLIB_API size_t ZSTD_CCtx_setParameter(ZSTD_CCtx* cctx, ZSTD_cParameter param, int value);
+
+/*! ZSTD_CCtx_setPledgedSrcSize() :
+ *  Total input data size to be compressed as a single frame.
+ *  Value will be written in frame header, unless if explicitly forbidden using ZSTD_c_contentSizeFlag.
+ *  This value will also be controlled at end of frame, and trigger an error if not respected.
+ * @result : 0, or an error code (which can be tested with ZSTD_isError()).
+ *  Note 1 : pledgedSrcSize==0 actually means zero, aka an empty frame.
+ *           In order to mean "unknown content size", pass constant ZSTD_CONTENTSIZE_UNKNOWN.
+ *           ZSTD_CONTENTSIZE_UNKNOWN is default value for any new frame.
+ *  Note 2 : pledgedSrcSize is only valid once, for the next frame.
+ *           It's discarded at the end of the frame, and replaced by ZSTD_CONTENTSIZE_UNKNOWN.
+ *  Note 3 : Whenever all input data is provided and consumed in a single round,
+ *           for example with ZSTD_compress2(),
+ *           or invoking immediately ZSTD_compressStream2(,,,ZSTD_e_end),
+ *           this value is automatically overridden by srcSize instead.
+ */
+ZSTDLIB_API size_t ZSTD_CCtx_setPledgedSrcSize(ZSTD_CCtx* cctx, unsigned long long pledgedSrcSize);
+
+typedef enum {
+    ZSTD_reset_session_only = 1,
+    ZSTD_reset_parameters = 2,
+    ZSTD_reset_session_and_parameters = 3
+} ZSTD_ResetDirective;
+
+/*! ZSTD_CCtx_reset() :
+ *  There are 2 different things that can be reset, independently or jointly :
+ *  - The session : will stop compressing current frame, and make CCtx ready to start a new one.
+ *                  Useful after an error, or to interrupt any ongoing compression.
+ *                  Any internal data not yet flushed is cancelled.
+ *                  Compression parameters and dictionary remain unchanged.
+ *                  They will be used to compress next frame.
+ *                  Resetting session never fails.
+ *  - The parameters : changes all parameters back to "default".
+ *                  This removes any reference to any dictionary too.
+ *                  Parameters can only be changed between 2 sessions (i.e. no compression is currently ongoing)
+ *                  otherwise the reset fails, and function returns an error value (which can be tested using ZSTD_isError())
+ *  - Both : similar to resetting the session, followed by resetting parameters.
+ */
+ZSTDLIB_API size_t ZSTD_CCtx_reset(ZSTD_CCtx* cctx, ZSTD_ResetDirective reset);
+
+/*! ZSTD_compress2() :
+ *  Behave the same as ZSTD_compressCCtx(), but compression parameters are set using the advanced API.
+ *  ZSTD_compress2() always starts a new frame.
+ *  Should cctx hold data from a previously unfinished frame, everything about it is forgotten.
+ *  - Compression parameters are pushed into CCtx before starting compression, using ZSTD_CCtx_set*()
+ *  - The function is always blocking, returns when compression is completed.
+ *  Hint : compression runs faster if `dstCapacity` >=  `ZSTD_compressBound(srcSize)`.
+ * @return : compressed size written into `dst` (<= `dstCapacity),
+ *           or an error code if it fails (which can be tested using ZSTD_isError()).
+ */
+ZSTDLIB_API size_t ZSTD_compress2( ZSTD_CCtx* cctx,
+                                   void* dst, size_t dstCapacity,
+                             const void* src, size_t srcSize);
+
+
+/* *************************************
+*  Advanced decompression API
+***************************************/
+
+/* The advanced API pushes parameters one by one into an existing DCtx context.
+ * Parameters are sticky, and remain valid for all following frames
+ * using the same DCtx context.
+ * It's possible to reset parameters to default values using ZSTD_DCtx_reset().
+ * Note : This API is compatible with existing ZSTD_decompressDCtx() and ZSTD_decompressStream().
+ *        Therefore, no new decompression function is necessary.
+ */
+
+typedef enum {
+
+    ZSTD_d_windowLogMax=100, /* Select a size limit (in power of 2) beyond which
+                              * the streaming API will refuse to allocate memory buffer
+                              * in order to protect the host from unreasonable memory requirements.
+                              * This parameter is only useful in streaming mode, since no internal buffer is allocated in single-pass mode.
+                              * By default, a decompression context accepts window sizes <= (1 << ZSTD_WINDOWLOG_LIMIT_DEFAULT).
+                              * Special: value 0 means "use default maximum windowLog". */
+
+    /* note : additional experimental parameters are also available
+     * within the experimental section of the API.
+     * At the time of this writing, they include :
+     * ZSTD_d_format
+     * ZSTD_d_stableOutBuffer
+     * ZSTD_d_forceIgnoreChecksum
+     * ZSTD_d_refMultipleDDicts
+     * Because they are not stable, it's necessary to define ZSTD_STATIC_LINKING_ONLY to access them.
+     * note : never ever use experimentalParam? names directly
+     */
+     ZSTD_d_experimentalParam1=1000,
+     ZSTD_d_experimentalParam2=1001,
+     ZSTD_d_experimentalParam3=1002,
+     ZSTD_d_experimentalParam4=1003
+
+} ZSTD_dParameter;
+
+/*! ZSTD_dParam_getBounds() :
+ *  All parameters must belong to an interval with lower and upper bounds,
+ *  otherwise they will either trigger an error or be automatically clamped.
+ * @return : a structure, ZSTD_bounds, which contains
+ *         - an error status field, which must be tested using ZSTD_isError()
+ *         - both lower and upper bounds, inclusive
+ */
+ZSTDLIB_API ZSTD_bounds ZSTD_dParam_getBounds(ZSTD_dParameter dParam);
+
+/*! ZSTD_DCtx_setParameter() :
+ *  Set one compression parameter, selected by enum ZSTD_dParameter.
+ *  All parameters have valid bounds. Bounds can be queried using ZSTD_dParam_getBounds().
+ *  Providing a value beyond bound will either clamp it, or trigger an error (depending on parameter).
+ *  Setting a parameter is only possible during frame initialization (before starting decompression).
+ * @return : 0, or an error code (which can be tested using ZSTD_isError()).
+ */
+ZSTDLIB_API size_t ZSTD_DCtx_setParameter(ZSTD_DCtx* dctx, ZSTD_dParameter param, int value);
+
+/*! ZSTD_DCtx_reset() :
+ *  Return a DCtx to clean state.
+ *  Session and parameters can be reset jointly or separately.
+ *  Parameters can only be reset when no active frame is being decompressed.
+ * @return : 0, or an error code, which can be tested with ZSTD_isError()
+ */
+ZSTDLIB_API size_t ZSTD_DCtx_reset(ZSTD_DCtx* dctx, ZSTD_ResetDirective reset);
+
+
+/* **************************
+*  Streaming
+****************************/
+
+typedef struct ZSTD_inBuffer_s {
+  const void* src;    /*< start of input buffer */
+  size_t size;        /*< size of input buffer */
+  size_t pos;         /*< position where reading stopped. Will be updated. Necessarily 0 <= pos <= size */
+} ZSTD_inBuffer;
+
+typedef struct ZSTD_outBuffer_s {
+  void*  dst;         /*< start of output buffer */
+  size_t size;        /*< size of output buffer */
+  size_t pos;         /*< position where writing stopped. Will be updated. Necessarily 0 <= pos <= size */
+} ZSTD_outBuffer;
+
+
+
+/*-***********************************************************************
+*  Streaming compression - HowTo
+*
+*  A ZSTD_CStream object is required to track streaming operation.
+*  Use ZSTD_createCStream() and ZSTD_freeCStream() to create/release resources.
+*  ZSTD_CStream objects can be reused multiple times on consecutive compression operations.
+*  It is recommended to re-use ZSTD_CStream since it will play nicer with system's memory, by re-using already allocated memory.
+*
+*  For parallel execution, use one separate ZSTD_CStream per thread.
+*
+*  note : since v1.3.0, ZSTD_CStream and ZSTD_CCtx are the same thing.
+*
+*  Parameters are sticky : when starting a new compression on the same context,
+*  it will re-use the same sticky parameters as previous compression session.
+*  When in doubt, it's recommended to fully initialize the context before usage.
+*  Use ZSTD_CCtx_reset() to reset the context and ZSTD_CCtx_setParameter(),
+*  ZSTD_CCtx_setPledgedSrcSize(), or ZSTD_CCtx_loadDictionary() and friends to
+*  set more specific parameters, the pledged source size, or load a dictionary.
+*
+*  Use ZSTD_compressStream2() with ZSTD_e_continue as many times as necessary to
+*  consume input stream. The function will automatically update both `pos`
+*  fields within `input` and `output`.
+*  Note that the function may not consume the entire input, for example, because
+*  the output buffer is already full, in which case `input.pos < input.size`.
+*  The caller must check if input has been entirely consumed.
+*  If not, the caller must make some room to receive more compressed data,
+*  and then present again remaining input data.
+*  note: ZSTD_e_continue is guaranteed to make some forward progress when called,
+*        but doesn't guarantee maximal forward progress. This is especially relevant
+*        when compressing with multiple threads. The call won't block if it can
+*        consume some input, but if it can't it will wait for some, but not all,
+*        output to be flushed.
+* @return : provides a minimum amount of data remaining to be flushed from internal buffers
+*           or an error code, which can be tested using ZSTD_isError().
+*
+*  At any moment, it's possible to flush whatever data might remain stuck within internal buffer,
+*  using ZSTD_compressStream2() with ZSTD_e_flush. `output->pos` will be updated.
+*  Note that, if `output->size` is too small, a single invocation with ZSTD_e_flush might not be enough (return code > 0).
+*  In which case, make some room to receive more compressed data, and call again ZSTD_compressStream2() with ZSTD_e_flush.
+*  You must continue calling ZSTD_compressStream2() with ZSTD_e_flush until it returns 0, at which point you can change the
+*  operation.
+*  note: ZSTD_e_flush will flush as much output as possible, meaning when compressing with multiple threads, it will
+*        block until the flush is complete or the output buffer is full.
+*  @return : 0 if internal buffers are entirely flushed,
+*            >0 if some data still present within internal buffer (the value is minimal estimation of remaining size),
+*            or an error code, which can be tested using ZSTD_isError().
+*
+*  Calling ZSTD_compressStream2() with ZSTD_e_end instructs to finish a frame.
+*  It will perform a flush and write frame epilogue.
+*  The epilogue is required for decoders to consider a frame completed.
+*  flush operation is the same, and follows same rules as calling ZSTD_compressStream2() with ZSTD_e_flush.
+*  You must continue calling ZSTD_compressStream2() with ZSTD_e_end until it returns 0, at which point you are free to
+*  start a new frame.
+*  note: ZSTD_e_end will flush as much output as possible, meaning when compressing with multiple threads, it will
+*        block until the flush is complete or the output buffer is full.
+*  @return : 0 if frame fully completed and fully flushed,
+*            >0 if some data still present within internal buffer (the value is minimal estimation of remaining size),
+*            or an error code, which can be tested using ZSTD_isError().
+*
+* *******************************************************************/
+
+typedef ZSTD_CCtx ZSTD_CStream;  /*< CCtx and CStream are now effectively same object (>= v1.3.0) */
+                                 /* Continue to distinguish them for compatibility with older versions <= v1.2.0 */
+/*===== ZSTD_CStream management functions =====*/
+ZSTDLIB_API ZSTD_CStream* ZSTD_createCStream(void);
+ZSTDLIB_API size_t ZSTD_freeCStream(ZSTD_CStream* zcs);  /* accept NULL pointer */
+
+/*===== Streaming compression functions =====*/
+typedef enum {
+    ZSTD_e_continue=0, /* collect more data, encoder decides when to output compressed result, for optimal compression ratio */
+    ZSTD_e_flush=1,    /* flush any data provided so far,
+                        * it creates (at least) one new block, that can be decoded immediately on reception;
+                        * frame will continue: any future data can still reference previously compressed data, improving compression.
+                        * note : multithreaded compression will block to flush as much output as possible. */
+    ZSTD_e_end=2       /* flush any remaining data _and_ close current frame.
+                        * note that frame is only closed after compressed data is fully flushed (return value == 0).
+                        * After that point, any additional data starts a new frame.
+                        * note : each frame is independent (does not reference any content from previous frame).
+                        : note : multithreaded compression will block to flush as much output as possible. */
+} ZSTD_EndDirective;
+
+/*! ZSTD_compressStream2() :
+ *  Behaves about the same as ZSTD_compressStream, with additional control on end directive.
+ *  - Compression parameters are pushed into CCtx before starting compression, using ZSTD_CCtx_set*()
+ *  - Compression parameters cannot be changed once compression is started (save a list of exceptions in multi-threading mode)
+ *  - output->pos must be <= dstCapacity, input->pos must be <= srcSize
+ *  - output->pos and input->pos will be updated. They are guaranteed to remain below their respective limit.
+ *  - endOp must be a valid directive
+ *  - When nbWorkers==0 (default), function is blocking : it completes its job before returning to caller.
+ *  - When nbWorkers>=1, function is non-blocking : it copies a portion of input, distributes jobs to internal worker threads, flush to output whatever is available,
+ *                                                  and then immediately returns, just indicating that there is some data remaining to be flushed.
+ *                                                  The function nonetheless guarantees forward progress : it will return only after it reads or write at least 1+ byte.
+ *  - Exception : if the first call requests a ZSTD_e_end directive and provides enough dstCapacity, the function delegates to ZSTD_compress2() which is always blocking.
+ *  - @return provides a minimum amount of data remaining to be flushed from internal buffers
+ *            or an error code, which can be tested using ZSTD_isError().
+ *            if @return != 0, flush is not fully completed, there is still some data left within internal buffers.
+ *            This is useful for ZSTD_e_flush, since in this case more flushes are necessary to empty all buffers.
+ *            For ZSTD_e_end, @return == 0 when internal buffers are fully flushed and frame is completed.
+ *  - after a ZSTD_e_end directive, if internal buffer is not fully flushed (@return != 0),
+ *            only ZSTD_e_end or ZSTD_e_flush operations are allowed.
+ *            Before starting a new compression job, or changing compression parameters,
+ *            it is required to fully flush internal buffers.
+ */
+ZSTDLIB_API size_t ZSTD_compressStream2( ZSTD_CCtx* cctx,
+                                         ZSTD_outBuffer* output,
+                                         ZSTD_inBuffer* input,
+                                         ZSTD_EndDirective endOp);
+
+
+/* These buffer sizes are softly recommended.
+ * They are not required : ZSTD_compressStream*() happily accepts any buffer size, for both input and output.
+ * Respecting the recommended size just makes it a bit easier for ZSTD_compressStream*(),
+ * reducing the amount of memory shuffling and buffering, resulting in minor performance savings.
+ *
+ * However, note that these recommendations are from the perspective of a C caller program.
+ * If the streaming interface is invoked from some other language,
+ * especially managed ones such as Java or Go, through a foreign function interface such as jni or cgo,
+ * a major performance rule is to reduce crossing such interface to an absolute minimum.
+ * It's not rare that performance ends being spent more into the interface, rather than compression itself.
+ * In which cases, prefer using large buffers, as large as practical,
+ * for both input and output, to reduce the nb of roundtrips.
+ */
+ZSTDLIB_API size_t ZSTD_CStreamInSize(void);    /*< recommended size for input buffer */
+ZSTDLIB_API size_t ZSTD_CStreamOutSize(void);   /*< recommended size for output buffer. Guarantee to successfully flush at least one complete compressed block. */
+
+
+/* *****************************************************************************
+ * This following is a legacy streaming API.
+ * It can be replaced by ZSTD_CCtx_reset() and ZSTD_compressStream2().
+ * It is redundant, but remains fully supported.
+ * Advanced parameters and dictionary compression can only be used through the
+ * new API.
+ ******************************************************************************/
+
+/*!
+ * Equivalent to:
+ *
+ *     ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only);
+ *     ZSTD_CCtx_refCDict(zcs, NULL); // clear the dictionary (if any)
+ *     ZSTD_CCtx_setParameter(zcs, ZSTD_c_compressionLevel, compressionLevel);
+ */
+ZSTDLIB_API size_t ZSTD_initCStream(ZSTD_CStream* zcs, int compressionLevel);
+/*!
+ * Alternative for ZSTD_compressStream2(zcs, output, input, ZSTD_e_continue).
+ * NOTE: The return value is different. ZSTD_compressStream() returns a hint for
+ * the next read size (if non-zero and not an error). ZSTD_compressStream2()
+ * returns the minimum nb of bytes left to flush (if non-zero and not an error).
+ */
+ZSTDLIB_API size_t ZSTD_compressStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output, ZSTD_inBuffer* input);
+/*! Equivalent to ZSTD_compressStream2(zcs, output, &emptyInput, ZSTD_e_flush). */
+ZSTDLIB_API size_t ZSTD_flushStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output);
+/*! Equivalent to ZSTD_compressStream2(zcs, output, &emptyInput, ZSTD_e_end). */
+ZSTDLIB_API size_t ZSTD_endStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output);
+
+
+/*-***************************************************************************
+*  Streaming decompression - HowTo
+*
+*  A ZSTD_DStream object is required to track streaming operations.
+*  Use ZSTD_createDStream() and ZSTD_freeDStream() to create/release resources.
+*  ZSTD_DStream objects can be re-used multiple times.
+*
+*  Use ZSTD_initDStream() to start a new decompression operation.
+* @return : recommended first input size
+*  Alternatively, use advanced API to set specific properties.
+*
+*  Use ZSTD_decompressStream() repetitively to consume your input.
+*  The function will update both `pos` fields.
+*  If `input.pos < input.size`, some input has not been consumed.
+*  It's up to the caller to present again remaining data.
+*  The function tries to flush all data decoded immediately, respecting output buffer size.
+*  If `output.pos < output.size`, decoder has flushed everything it could.
+*  But if `output.pos == output.size`, there might be some data left within internal buffers.,
+*  In which case, call ZSTD_decompressStream() again to flush whatever remains in the buffer.
+*  Note : with no additional input provided, amount of data flushed is necessarily <= ZSTD_BLOCKSIZE_MAX.
+* @return : 0 when a frame is completely decoded and fully flushed,
+*        or an error code, which can be tested using ZSTD_isError(),
+*        or any other value > 0, which means there is still some decoding or flushing to do to complete current frame :
+*                                the return value is a suggested next input size (just a hint for better latency)
+*                                that will never request more than the remaining frame size.
+* *******************************************************************************/
+
+typedef ZSTD_DCtx ZSTD_DStream;  /*< DCtx and DStream are now effectively same object (>= v1.3.0) */
+                                 /* For compatibility with versions <= v1.2.0, prefer differentiating them. */
+/*===== ZSTD_DStream management functions =====*/
+ZSTDLIB_API ZSTD_DStream* ZSTD_createDStream(void);
+ZSTDLIB_API size_t ZSTD_freeDStream(ZSTD_DStream* zds);  /* accept NULL pointer */
+
+/*===== Streaming decompression functions =====*/
+
+/* This function is redundant with the advanced API and equivalent to:
+ *
+ *     ZSTD_DCtx_reset(zds, ZSTD_reset_session_only);
+ *     ZSTD_DCtx_refDDict(zds, NULL);
+ */
+ZSTDLIB_API size_t ZSTD_initDStream(ZSTD_DStream* zds);
+
+ZSTDLIB_API size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inBuffer* input);
+
+ZSTDLIB_API size_t ZSTD_DStreamInSize(void);    /*!< recommended size for input buffer */
+ZSTDLIB_API size_t ZSTD_DStreamOutSize(void);   /*!< recommended size for output buffer. Guarantee to successfully flush at least one complete block in all circumstances. */
+
+
+/* ************************
+*  Simple dictionary API
+***************************/
+/*! ZSTD_compress_usingDict() :
+ *  Compression at an explicit compression level using a Dictionary.
+ *  A dictionary can be any arbitrary data segment (also called a prefix),
+ *  or a buffer with specified information (see dictBuilder/zdict.h).
+ *  Note : This function loads the dictionary, resulting in significant startup delay.
+ *         It's intended for a dictionary used only once.
+ *  Note 2 : When `dict == NULL || dictSize < 8` no dictionary is used. */
+ZSTDLIB_API size_t ZSTD_compress_usingDict(ZSTD_CCtx* ctx,
+                                           void* dst, size_t dstCapacity,
+                                     const void* src, size_t srcSize,
+                                     const void* dict,size_t dictSize,
+                                           int compressionLevel);
+
+/*! ZSTD_decompress_usingDict() :
+ *  Decompression using a known Dictionary.
+ *  Dictionary must be identical to the one used during compression.
+ *  Note : This function loads the dictionary, resulting in significant startup delay.
+ *         It's intended for a dictionary used only once.
+ *  Note : When `dict == NULL || dictSize < 8` no dictionary is used. */
+ZSTDLIB_API size_t ZSTD_decompress_usingDict(ZSTD_DCtx* dctx,
+                                             void* dst, size_t dstCapacity,
+                                       const void* src, size_t srcSize,
+                                       const void* dict,size_t dictSize);
+
+
+/* *********************************
+ *  Bulk processing dictionary API
+ **********************************/
+typedef struct ZSTD_CDict_s ZSTD_CDict;
+
+/*! ZSTD_createCDict() :
+ *  When compressing multiple messages or blocks using the same dictionary,
+ *  it's recommended to digest the dictionary only once, since it's a costly operation.
+ *  ZSTD_createCDict() will create a state from digesting a dictionary.
+ *  The resulting state can be used for future compression operations with very limited startup cost.
+ *  ZSTD_CDict can be created once and shared by multiple threads concurrently, since its usage is read-only.
+ * @dictBuffer can be released after ZSTD_CDict creation, because its content is copied within CDict.
+ *  Note 1 : Consider experimental function `ZSTD_createCDict_byReference()` if you prefer to not duplicate @dictBuffer content.
+ *  Note 2 : A ZSTD_CDict can be created from an empty @dictBuffer,
+ *      in which case the only thing that it transports is the @compressionLevel.
+ *      This can be useful in a pipeline featuring ZSTD_compress_usingCDict() exclusively,
+ *      expecting a ZSTD_CDict parameter with any data, including those without a known dictionary. */
+ZSTDLIB_API ZSTD_CDict* ZSTD_createCDict(const void* dictBuffer, size_t dictSize,
+                                         int compressionLevel);
+
+/*! ZSTD_freeCDict() :
+ *  Function frees memory allocated by ZSTD_createCDict().
+ *  If a NULL pointer is passed, no operation is performed. */
+ZSTDLIB_API size_t      ZSTD_freeCDict(ZSTD_CDict* CDict);
+
+/*! ZSTD_compress_usingCDict() :
+ *  Compression using a digested Dictionary.
+ *  Recommended when same dictionary is used multiple times.
+ *  Note : compression level is _decided at dictionary creation time_,
+ *     and frame parameters are hardcoded (dictID=yes, contentSize=yes, checksum=no) */
+ZSTDLIB_API size_t ZSTD_compress_usingCDict(ZSTD_CCtx* cctx,
+                                            void* dst, size_t dstCapacity,
+                                      const void* src, size_t srcSize,
+                                      const ZSTD_CDict* cdict);
+
+
+typedef struct ZSTD_DDict_s ZSTD_DDict;
+
+/*! ZSTD_createDDict() :
+ *  Create a digested dictionary, ready to start decompression operation without startup delay.
+ *  dictBuffer can be released after DDict creation, as its content is copied inside DDict. */
+ZSTDLIB_API ZSTD_DDict* ZSTD_createDDict(const void* dictBuffer, size_t dictSize);
+
+/*! ZSTD_freeDDict() :
+ *  Function frees memory allocated with ZSTD_createDDict()
+ *  If a NULL pointer is passed, no operation is performed. */
+ZSTDLIB_API size_t      ZSTD_freeDDict(ZSTD_DDict* ddict);
+
+/*! ZSTD_decompress_usingDDict() :
+ *  Decompression using a digested Dictionary.
+ *  Recommended when same dictionary is used multiple times. */
+ZSTDLIB_API size_t ZSTD_decompress_usingDDict(ZSTD_DCtx* dctx,
+                                              void* dst, size_t dstCapacity,
+                                        const void* src, size_t srcSize,
+                                        const ZSTD_DDict* ddict);
+
+
+/* ******************************
+ *  Dictionary helper functions
+ *******************************/
+
+/*! ZSTD_getDictID_fromDict() :
+ *  Provides the dictID stored within dictionary.
+ *  if @return == 0, the dictionary is not conformant with Zstandard specification.
+ *  It can still be loaded, but as a content-only dictionary. */
+ZSTDLIB_API unsigned ZSTD_getDictID_fromDict(const void* dict, size_t dictSize);
+
+/*! ZSTD_getDictID_fromDDict() :
+ *  Provides the dictID of the dictionary loaded into `ddict`.
+ *  If @return == 0, the dictionary is not conformant to Zstandard specification, or empty.
+ *  Non-conformant dictionaries can still be loaded, but as content-only dictionaries. */
+ZSTDLIB_API unsigned ZSTD_getDictID_fromDDict(const ZSTD_DDict* ddict);
+
+/*! ZSTD_getDictID_fromFrame() :
+ *  Provides the dictID required to decompressed the frame stored within `src`.
+ *  If @return == 0, the dictID could not be decoded.
+ *  This could for one of the following reasons :
+ *  - The frame does not require a dictionary to be decoded (most common case).
+ *  - The frame was built with dictID intentionally removed. Whatever dictionary is necessary is a hidden information.
+ *    Note : this use case also happens when using a non-conformant dictionary.
+ *  - `srcSize` is too small, and as a result, the frame header could not be decoded (only possible if `srcSize < ZSTD_FRAMEHEADERSIZE_MAX`).
+ *  - This is not a Zstandard frame.
+ *  When identifying the exact failure cause, it's possible to use ZSTD_getFrameHeader(), which will provide a more precise error code. */
+ZSTDLIB_API unsigned ZSTD_getDictID_fromFrame(const void* src, size_t srcSize);
+
+
+/* *****************************************************************************
+ * Advanced dictionary and prefix API
+ *
+ * This API allows dictionaries to be used with ZSTD_compress2(),
+ * ZSTD_compressStream2(), and ZSTD_decompress(). Dictionaries are sticky, and
+ * only reset with the context is reset with ZSTD_reset_parameters or
+ * ZSTD_reset_session_and_parameters. Prefixes are single-use.
+ ******************************************************************************/
+
+
+/*! ZSTD_CCtx_loadDictionary() :
+ *  Create an internal CDict from `dict` buffer.
+ *  Decompression will have to use same dictionary.
+ * @result : 0, or an error code (which can be tested with ZSTD_isError()).
+ *  Special: Loading a NULL (or 0-size) dictionary invalidates previous dictionary,
+ *           meaning "return to no-dictionary mode".
+ *  Note 1 : Dictionary is sticky, it will be used for all future compressed frames.
+ *           To return to "no-dictionary" situation, load a NULL dictionary (or reset parameters).
+ *  Note 2 : Loading a dictionary involves building tables.
+ *           It's also a CPU consuming operation, with non-negligible impact on latency.
+ *           Tables are dependent on compression parameters, and for this reason,
+ *           compression parameters can no longer be changed after loading a dictionary.
+ *  Note 3 :`dict` content will be copied internally.
+ *           Use experimental ZSTD_CCtx_loadDictionary_byReference() to reference content instead.
+ *           In such a case, dictionary buffer must outlive its users.
+ *  Note 4 : Use ZSTD_CCtx_loadDictionary_advanced()
+ *           to precisely select how dictionary content must be interpreted. */
+ZSTDLIB_API size_t ZSTD_CCtx_loadDictionary(ZSTD_CCtx* cctx, const void* dict, size_t dictSize);
+
+/*! ZSTD_CCtx_refCDict() :
+ *  Reference a prepared dictionary, to be used for all next compressed frames.
+ *  Note that compression parameters are enforced from within CDict,
+ *  and supersede any compression parameter previously set within CCtx.
+ *  The parameters ignored are labelled as "superseded-by-cdict" in the ZSTD_cParameter enum docs.
+ *  The ignored parameters will be used again if the CCtx is returned to no-dictionary mode.
+ *  The dictionary will remain valid for future compressed frames using same CCtx.
+ * @result : 0, or an error code (which can be tested with ZSTD_isError()).
+ *  Special : Referencing a NULL CDict means "return to no-dictionary mode".
+ *  Note 1 : Currently, only one dictionary can be managed.
+ *           Referencing a new dictionary effectively "discards" any previous one.
+ *  Note 2 : CDict is just referenced, its lifetime must outlive its usage within CCtx. */
+ZSTDLIB_API size_t ZSTD_CCtx_refCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict);
+
+/*! ZSTD_CCtx_refPrefix() :
+ *  Reference a prefix (single-usage dictionary) for next compressed frame.
+ *  A prefix is **only used once**. Tables are discarded at end of frame (ZSTD_e_end).
+ *  Decompression will need same prefix to properly regenerate data.
+ *  Compressing with a prefix is similar in outcome as performing a diff and compressing it,
+ *  but performs much faster, especially during decompression (compression speed is tunable with compression level).
+ * @result : 0, or an error code (which can be tested with ZSTD_isError()).
+ *  Special: Adding any prefix (including NULL) invalidates any previous prefix or dictionary
+ *  Note 1 : Prefix buffer is referenced. It **must** outlive compression.
+ *           Its content must remain unmodified during compression.
+ *  Note 2 : If the intention is to diff some large src data blob with some prior version of itself,
+ *           ensure that the window size is large enough to contain the entire source.
+ *           See ZSTD_c_windowLog.
+ *  Note 3 : Referencing a prefix involves building tables, which are dependent on compression parameters.
+ *           It's a CPU consuming operation, with non-negligible impact on latency.
+ *           If there is a need to use the same prefix multiple times, consider loadDictionary instead.
+ *  Note 4 : By default, the prefix is interpreted as raw content (ZSTD_dct_rawContent).
+ *           Use experimental ZSTD_CCtx_refPrefix_advanced() to alter dictionary interpretation. */
+ZSTDLIB_API size_t ZSTD_CCtx_refPrefix(ZSTD_CCtx* cctx,
+                                 const void* prefix, size_t prefixSize);
+
+/*! ZSTD_DCtx_loadDictionary() :
+ *  Create an internal DDict from dict buffer,
+ *  to be used to decompress next frames.
+ *  The dictionary remains valid for all future frames, until explicitly invalidated.
+ * @result : 0, or an error code (which can be tested with ZSTD_isError()).
+ *  Special : Adding a NULL (or 0-size) dictionary invalidates any previous dictionary,
+ *            meaning "return to no-dictionary mode".
+ *  Note 1 : Loading a dictionary involves building tables,
+ *           which has a non-negligible impact on CPU usage and latency.
+ *           It's recommended to "load once, use many times", to amortize the cost
+ *  Note 2 :`dict` content will be copied internally, so `dict` can be released after loading.
+ *           Use ZSTD_DCtx_loadDictionary_byReference() to reference dictionary content instead.
+ *  Note 3 : Use ZSTD_DCtx_loadDictionary_advanced() to take control of
+ *           how dictionary content is loaded and interpreted.
+ */
+ZSTDLIB_API size_t ZSTD_DCtx_loadDictionary(ZSTD_DCtx* dctx, const void* dict, size_t dictSize);
+
+/*! ZSTD_DCtx_refDDict() :
+ *  Reference a prepared dictionary, to be used to decompress next frames.
+ *  The dictionary remains active for decompression of future frames using same DCtx.
+ *
+ *  If called with ZSTD_d_refMultipleDDicts enabled, repeated calls of this function
+ *  will store the DDict references in a table, and the DDict used for decompression
+ *  will be determined at decompression time, as per the dict ID in the frame.
+ *  The memory for the table is allocated on the first call to refDDict, and can be
+ *  freed with ZSTD_freeDCtx().
+ *
+ * @result : 0, or an error code (which can be tested with ZSTD_isError()).
+ *  Note 1 : Currently, only one dictionary can be managed.
+ *           Referencing a new dictionary effectively "discards" any previous one.
+ *  Special: referencing a NULL DDict means "return to no-dictionary mode".
+ *  Note 2 : DDict is just referenced, its lifetime must outlive its usage from DCtx.
+ */
+ZSTDLIB_API size_t ZSTD_DCtx_refDDict(ZSTD_DCtx* dctx, const ZSTD_DDict* ddict);
+
+/*! ZSTD_DCtx_refPrefix() :
+ *  Reference a prefix (single-usage dictionary) to decompress next frame.
+ *  This is the reverse operation of ZSTD_CCtx_refPrefix(),
+ *  and must use the same prefix as the one used during compression.
+ *  Prefix is **only used once**. Reference is discarded at end of frame.
+ *  End of frame is reached when ZSTD_decompressStream() returns 0.
+ * @result : 0, or an error code (which can be tested with ZSTD_isError()).
+ *  Note 1 : Adding any prefix (including NULL) invalidates any previously set prefix or dictionary
+ *  Note 2 : Prefix buffer is referenced. It **must** outlive decompression.
+ *           Prefix buffer must remain unmodified up to the end of frame,
+ *           reached when ZSTD_decompressStream() returns 0.
+ *  Note 3 : By default, the prefix is treated as raw content (ZSTD_dct_rawContent).
+ *           Use ZSTD_CCtx_refPrefix_advanced() to alter dictMode (Experimental section)
+ *  Note 4 : Referencing a raw content prefix has almost no cpu nor memory cost.
+ *           A full dictionary is more costly, as it requires building tables.
+ */
+ZSTDLIB_API size_t ZSTD_DCtx_refPrefix(ZSTD_DCtx* dctx,
+                                 const void* prefix, size_t prefixSize);
+
+/* ===   Memory management   === */
+
+/*! ZSTD_sizeof_*() :
+ *  These functions give the _current_ memory usage of selected object.
+ *  Note that object memory usage can evolve (increase or decrease) over time. */
+ZSTDLIB_API size_t ZSTD_sizeof_CCtx(const ZSTD_CCtx* cctx);
+ZSTDLIB_API size_t ZSTD_sizeof_DCtx(const ZSTD_DCtx* dctx);
+ZSTDLIB_API size_t ZSTD_sizeof_CStream(const ZSTD_CStream* zcs);
+ZSTDLIB_API size_t ZSTD_sizeof_DStream(const ZSTD_DStream* zds);
+ZSTDLIB_API size_t ZSTD_sizeof_CDict(const ZSTD_CDict* cdict);
+ZSTDLIB_API size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict);
+
+#endif  /* ZSTD_H_235446 */
+
+
+/* **************************************************************************************
+ *   ADVANCED AND EXPERIMENTAL FUNCTIONS
+ ****************************************************************************************
+ * The definitions in the following section are considered experimental.
+ * They are provided for advanced scenarios.
+ * They should never be used with a dynamic library, as prototypes may change in the future.
+ * Use them only in association with static linking.
+ * ***************************************************************************************/
+
+#if !defined(ZSTD_H_ZSTD_STATIC_LINKING_ONLY)
+#define ZSTD_H_ZSTD_STATIC_LINKING_ONLY
+
+/* **************************************************************************************
+ *   experimental API (static linking only)
+ ****************************************************************************************
+ * The following symbols and constants
+ * are not planned to join "stable API" status in the near future.
+ * They can still change in future versions.
+ * Some of them are planned to remain in the static_only section indefinitely.
+ * Some of them might be removed in the future (especially when redundant with existing stable functions)
+ * ***************************************************************************************/
+
+#define ZSTD_FRAMEHEADERSIZE_PREFIX(format) ((format) == ZSTD_f_zstd1 ? 5 : 1)   /* minimum input size required to query frame header size */
+#define ZSTD_FRAMEHEADERSIZE_MIN(format)    ((format) == ZSTD_f_zstd1 ? 6 : 2)
+#define ZSTD_FRAMEHEADERSIZE_MAX   18   /* can be useful for static allocation */
+#define ZSTD_SKIPPABLEHEADERSIZE    8
+
+/* compression parameter bounds */
+#define ZSTD_WINDOWLOG_MAX_32    30
+#define ZSTD_WINDOWLOG_MAX_64    31
+#define ZSTD_WINDOWLOG_MAX     ((int)(sizeof(size_t) == 4 ? ZSTD_WINDOWLOG_MAX_32 : ZSTD_WINDOWLOG_MAX_64))
+#define ZSTD_WINDOWLOG_MIN       10
+#define ZSTD_HASHLOG_MAX       ((ZSTD_WINDOWLOG_MAX < 30) ? ZSTD_WINDOWLOG_MAX : 30)
+#define ZSTD_HASHLOG_MIN          6
+#define ZSTD_CHAINLOG_MAX_32     29
+#define ZSTD_CHAINLOG_MAX_64     30
+#define ZSTD_CHAINLOG_MAX      ((int)(sizeof(size_t) == 4 ? ZSTD_CHAINLOG_MAX_32 : ZSTD_CHAINLOG_MAX_64))
+#define ZSTD_CHAINLOG_MIN        ZSTD_HASHLOG_MIN
+#define ZSTD_SEARCHLOG_MAX      (ZSTD_WINDOWLOG_MAX-1)
+#define ZSTD_SEARCHLOG_MIN        1
+#define ZSTD_MINMATCH_MAX         7   /* only for ZSTD_fast, other strategies are limited to 6 */
+#define ZSTD_MINMATCH_MIN         3   /* only for ZSTD_btopt+, faster strategies are limited to 4 */
+#define ZSTD_TARGETLENGTH_MAX    ZSTD_BLOCKSIZE_MAX
+#define ZSTD_TARGETLENGTH_MIN     0   /* note : comparing this constant to an unsigned results in a tautological test */
+#define ZSTD_STRATEGY_MIN        ZSTD_fast
+#define ZSTD_STRATEGY_MAX        ZSTD_btultra2
+
+
+#define ZSTD_OVERLAPLOG_MIN       0
+#define ZSTD_OVERLAPLOG_MAX       9
+
+#define ZSTD_WINDOWLOG_LIMIT_DEFAULT 27   /* by default, the streaming decoder will refuse any frame
+                                           * requiring larger than (1<<ZSTD_WINDOWLOG_LIMIT_DEFAULT) window size,
+                                           * to preserve host's memory from unreasonable requirements.
+                                           * This limit can be overridden using ZSTD_DCtx_setParameter(,ZSTD_d_windowLogMax,).
+                                           * The limit does not apply for one-pass decoders (such as ZSTD_decompress()), since no additional memory is allocated */
+
+
+/* LDM parameter bounds */
+#define ZSTD_LDM_HASHLOG_MIN      ZSTD_HASHLOG_MIN
+#define ZSTD_LDM_HASHLOG_MAX      ZSTD_HASHLOG_MAX
+#define ZSTD_LDM_MINMATCH_MIN        4
+#define ZSTD_LDM_MINMATCH_MAX     4096
+#define ZSTD_LDM_BUCKETSIZELOG_MIN   1
+#define ZSTD_LDM_BUCKETSIZELOG_MAX   8
+#define ZSTD_LDM_HASHRATELOG_MIN     0
+#define ZSTD_LDM_HASHRATELOG_MAX (ZSTD_WINDOWLOG_MAX - ZSTD_HASHLOG_MIN)
+
+/* Advanced parameter bounds */
+#define ZSTD_TARGETCBLOCKSIZE_MIN   64
+#define ZSTD_TARGETCBLOCKSIZE_MAX   ZSTD_BLOCKSIZE_MAX
+#define ZSTD_SRCSIZEHINT_MIN        0
+#define ZSTD_SRCSIZEHINT_MAX        INT_MAX
+
+/* internal */
+#define ZSTD_HASHLOG3_MAX           17
+
+
+/* ---  Advanced types  --- */
+
+typedef struct ZSTD_CCtx_params_s ZSTD_CCtx_params;
+
+typedef struct {
+    unsigned int offset;      /* The offset of the match. (NOT the same as the offset code)
+                               * If offset == 0 and matchLength == 0, this sequence represents the last
+                               * literals in the block of litLength size.
+                               */
+
+    unsigned int litLength;   /* Literal length of the sequence. */
+    unsigned int matchLength; /* Match length of the sequence. */
+
+                              /* Note: Users of this API may provide a sequence with matchLength == litLength == offset == 0.
+                               * In this case, we will treat the sequence as a marker for a block boundary.
+                               */
+
+    unsigned int rep;         /* Represents which repeat offset is represented by the field 'offset'.
+                               * Ranges from [0, 3].
+                               *
+                               * Repeat offsets are essentially previous offsets from previous sequences sorted in
+                               * recency order. For more detail, see doc/zstd_compression_format.md
+                               *
+                               * If rep == 0, then 'offset' does not contain a repeat offset.
+                               * If rep > 0:
+                               *  If litLength != 0:
+                               *      rep == 1 --> offset == repeat_offset_1
+                               *      rep == 2 --> offset == repeat_offset_2
+                               *      rep == 3 --> offset == repeat_offset_3
+                               *  If litLength == 0:
+                               *      rep == 1 --> offset == repeat_offset_2
+                               *      rep == 2 --> offset == repeat_offset_3
+                               *      rep == 3 --> offset == repeat_offset_1 - 1
+                               *
+                               * Note: This field is optional. ZSTD_generateSequences() will calculate the value of
+                               * 'rep', but repeat offsets do not necessarily need to be calculated from an external
+                               * sequence provider's perspective. For example, ZSTD_compressSequences() does not
+                               * use this 'rep' field at all (as of now).
+                               */
+} ZSTD_Sequence;
+
+typedef struct {
+    unsigned windowLog;       /*< largest match distance : larger == more compression, more memory needed during decompression */
+    unsigned chainLog;        /*< fully searched segment : larger == more compression, slower, more memory (useless for fast) */
+    unsigned hashLog;         /*< dispatch table : larger == faster, more memory */
+    unsigned searchLog;       /*< nb of searches : larger == more compression, slower */
+    unsigned minMatch;        /*< match length searched : larger == faster decompression, sometimes less compression */
+    unsigned targetLength;    /*< acceptable match size for optimal parser (only) : larger == more compression, slower */
+    ZSTD_strategy strategy;   /*< see ZSTD_strategy definition above */
+} ZSTD_compressionParameters;
+
+typedef struct {
+    int contentSizeFlag; /*< 1: content size will be in frame header (when known) */
+    int checksumFlag;    /*< 1: generate a 32-bits checksum using XXH64 algorithm at end of frame, for error detection */
+    int noDictIDFlag;    /*< 1: no dictID will be saved into frame header (dictID is only useful for dictionary compression) */
+} ZSTD_frameParameters;
+
+typedef struct {
+    ZSTD_compressionParameters cParams;
+    ZSTD_frameParameters fParams;
+} ZSTD_parameters;
+
+typedef enum {
+    ZSTD_dct_auto = 0,       /* dictionary is "full" when starting with ZSTD_MAGIC_DICTIONARY, otherwise it is "rawContent" */
+    ZSTD_dct_rawContent = 1, /* ensures dictionary is always loaded as rawContent, even if it starts with ZSTD_MAGIC_DICTIONARY */
+    ZSTD_dct_fullDict = 2    /* refuses to load a dictionary if it does not respect Zstandard's specification, starting with ZSTD_MAGIC_DICTIONARY */
+} ZSTD_dictContentType_e;
+
+typedef enum {
+    ZSTD_dlm_byCopy = 0,  /*< Copy dictionary content internally */
+    ZSTD_dlm_byRef = 1    /*< Reference dictionary content -- the dictionary buffer must outlive its users. */
+} ZSTD_dictLoadMethod_e;
+
+typedef enum {
+    ZSTD_f_zstd1 = 0,           /* zstd frame format, specified in zstd_compression_format.md (default) */
+    ZSTD_f_zstd1_magicless = 1  /* Variant of zstd frame format, without initial 4-bytes magic number.
+                                 * Useful to save 4 bytes per generated frame.
+                                 * Decoder cannot recognise automatically this format, requiring this instruction. */
+} ZSTD_format_e;
+
+typedef enum {
+    /* Note: this enum controls ZSTD_d_forceIgnoreChecksum */
+    ZSTD_d_validateChecksum = 0,
+    ZSTD_d_ignoreChecksum = 1
+} ZSTD_forceIgnoreChecksum_e;
+
+typedef enum {
+    /* Note: this enum controls ZSTD_d_refMultipleDDicts */
+    ZSTD_rmd_refSingleDDict = 0,
+    ZSTD_rmd_refMultipleDDicts = 1
+} ZSTD_refMultipleDDicts_e;
+
+typedef enum {
+    /* Note: this enum and the behavior it controls are effectively internal
+     * implementation details of the compressor. They are expected to continue
+     * to evolve and should be considered only in the context of extremely
+     * advanced performance tuning.
+     *
+     * Zstd currently supports the use of a CDict in three ways:
+     *
+     * - The contents of the CDict can be copied into the working context. This
+     *   means that the compression can search both the dictionary and input
+     *   while operating on a single set of internal tables. This makes
+     *   the compression faster per-byte of input. However, the initial copy of
+     *   the CDict's tables incurs a fixed cost at the beginning of the
+     *   compression. For small compressions (< 8 KB), that copy can dominate
+     *   the cost of the compression.
+     *
+     * - The CDict's tables can be used in-place. In this model, compression is
+     *   slower per input byte, because the compressor has to search two sets of
+     *   tables. However, this model incurs no start-up cost (as long as the
+     *   working context's tables can be reused). For small inputs, this can be
+     *   faster than copying the CDict's tables.
+     *
+     * - The CDict's tables are not used at all, and instead we use the working
+     *   context alone to reload the dictionary and use params based on the source
+     *   size. See ZSTD_compress_insertDictionary() and ZSTD_compress_usingDict().
+     *   This method is effective when the dictionary sizes are very small relative
+     *   to the input size, and the input size is fairly large to begin with.
+     *
+     * Zstd has a simple internal heuristic that selects which strategy to use
+     * at the beginning of a compression. However, if experimentation shows that
+     * Zstd is making poor choices, it is possible to override that choice with
+     * this enum.
+     */
+    ZSTD_dictDefaultAttach = 0, /* Use the default heuristic. */
+    ZSTD_dictForceAttach   = 1, /* Never copy the dictionary. */
+    ZSTD_dictForceCopy     = 2, /* Always copy the dictionary. */
+    ZSTD_dictForceLoad     = 3  /* Always reload the dictionary */
+} ZSTD_dictAttachPref_e;
+
+typedef enum {
+  ZSTD_lcm_auto = 0,          /*< Automatically determine the compression mode based on the compression level.
+                               *   Negative compression levels will be uncompressed, and positive compression
+                               *   levels will be compressed. */
+  ZSTD_lcm_huffman = 1,       /*< Always attempt Huffman compression. Uncompressed literals will still be
+                               *   emitted if Huffman compression is not profitable. */
+  ZSTD_lcm_uncompressed = 2   /*< Always emit uncompressed literals. */
+} ZSTD_literalCompressionMode_e;
+
+
+/* *************************************
+*  Frame size functions
+***************************************/
+
+/*! ZSTD_findDecompressedSize() :
+ *  `src` should point to the start of a series of ZSTD encoded and/or skippable frames
+ *  `srcSize` must be the _exact_ size of this series
+ *       (i.e. there should be a frame boundary at `src + srcSize`)
+ *  @return : - decompressed size of all data in all successive frames
+ *            - if the decompressed size cannot be determined: ZSTD_CONTENTSIZE_UNKNOWN
+ *            - if an error occurred: ZSTD_CONTENTSIZE_ERROR
+ *
+ *   note 1 : decompressed size is an optional field, that may not be present, especially in streaming mode.
+ *            When `return==ZSTD_CONTENTSIZE_UNKNOWN`, data to decompress could be any size.
+ *            In which case, it's necessary to use streaming mode to decompress data.
+ *   note 2 : decompressed size is always present when compression is done with ZSTD_compress()
+ *   note 3 : decompressed size can be very large (64-bits value),
+ *            potentially larger than what local system can handle as a single memory segment.
+ *            In which case, it's necessary to use streaming mode to decompress data.
+ *   note 4 : If source is untrusted, decompressed size could be wrong or intentionally modified.
+ *            Always ensure result fits within application's authorized limits.
+ *            Each application can set its own limits.
+ *   note 5 : ZSTD_findDecompressedSize handles multiple frames, and so it must traverse the input to
+ *            read each contained frame header.  This is fast as most of the data is skipped,
+ *            however it does mean that all frame data must be present and valid. */
+ZSTDLIB_API unsigned long long ZSTD_findDecompressedSize(const void* src, size_t srcSize);
+
+/*! ZSTD_decompressBound() :
+ *  `src` should point to the start of a series of ZSTD encoded and/or skippable frames
+ *  `srcSize` must be the _exact_ size of this series
+ *       (i.e. there should be a frame boundary at `src + srcSize`)
+ *  @return : - upper-bound for the decompressed size of all data in all successive frames
+ *            - if an error occurred: ZSTD_CONTENTSIZE_ERROR
+ *
+ *  note 1  : an error can occur if `src` contains an invalid or incorrectly formatted frame.
+ *  note 2  : the upper-bound is exact when the decompressed size field is available in every ZSTD encoded frame of `src`.
+ *            in this case, `ZSTD_findDecompressedSize` and `ZSTD_decompressBound` return the same value.
+ *  note 3  : when the decompressed size field isn't available, the upper-bound for that frame is calculated by:
+ *              upper-bound = # blocks * min(128 KB, Window_Size)
+ */
+ZSTDLIB_API unsigned long long ZSTD_decompressBound(const void* src, size_t srcSize);
+
+/*! ZSTD_frameHeaderSize() :
+ *  srcSize must be >= ZSTD_FRAMEHEADERSIZE_PREFIX.
+ * @return : size of the Frame Header,
+ *           or an error code (if srcSize is too small) */
+ZSTDLIB_API size_t ZSTD_frameHeaderSize(const void* src, size_t srcSize);
+
+typedef enum {
+  ZSTD_sf_noBlockDelimiters = 0,         /* Representation of ZSTD_Sequence has no block delimiters, sequences only */
+  ZSTD_sf_explicitBlockDelimiters = 1    /* Representation of ZSTD_Sequence contains explicit block delimiters */
+} ZSTD_sequenceFormat_e;
+
+/*! ZSTD_generateSequences() :
+ * Generate sequences using ZSTD_compress2, given a source buffer.
+ *
+ * Each block will end with a dummy sequence
+ * with offset == 0, matchLength == 0, and litLength == length of last literals.
+ * litLength may be == 0, and if so, then the sequence of (of: 0 ml: 0 ll: 0)
+ * simply acts as a block delimiter.
+ *
+ * zc can be used to insert custom compression params.
+ * This function invokes ZSTD_compress2
+ *
+ * The output of this function can be fed into ZSTD_compressSequences() with CCtx
+ * setting of ZSTD_c_blockDelimiters as ZSTD_sf_explicitBlockDelimiters
+ * @return : number of sequences generated
+ */
+
+ZSTDLIB_API size_t ZSTD_generateSequences(ZSTD_CCtx* zc, ZSTD_Sequence* outSeqs,
+                                          size_t outSeqsSize, const void* src, size_t srcSize);
+
+/*! ZSTD_mergeBlockDelimiters() :
+ * Given an array of ZSTD_Sequence, remove all sequences that represent block delimiters/last literals
+ * by merging them into into the literals of the next sequence.
+ *
+ * As such, the final generated result has no explicit representation of block boundaries,
+ * and the final last literals segment is not represented in the sequences.
+ *
+ * The output of this function can be fed into ZSTD_compressSequences() with CCtx
+ * setting of ZSTD_c_blockDelimiters as ZSTD_sf_noBlockDelimiters
+ * @return : number of sequences left after merging
+ */
+ZSTDLIB_API size_t ZSTD_mergeBlockDelimiters(ZSTD_Sequence* sequences, size_t seqsSize);
+
+/*! ZSTD_compressSequences() :
+ * Compress an array of ZSTD_Sequence, generated from the original source buffer, into dst.
+ * If a dictionary is included, then the cctx should reference the dict. (see: ZSTD_CCtx_refCDict(), ZSTD_CCtx_loadDictionary(), etc.)
+ * The entire source is compressed into a single frame.
+ *
+ * The compression behavior changes based on cctx params. In particular:
+ *    If ZSTD_c_blockDelimiters == ZSTD_sf_noBlockDelimiters, the array of ZSTD_Sequence is expected to contain
+ *    no block delimiters (defined in ZSTD_Sequence). Block boundaries are roughly determined based on
+ *    the block size derived from the cctx, and sequences may be split. This is the default setting.
+ *
+ *    If ZSTD_c_blockDelimiters == ZSTD_sf_explicitBlockDelimiters, the array of ZSTD_Sequence is expected to contain
+ *    block delimiters (defined in ZSTD_Sequence). Behavior is undefined if no block delimiters are provided.
+ *
+ *    If ZSTD_c_validateSequences == 0, this function will blindly accept the sequences provided. Invalid sequences cause undefined
+ *    behavior. If ZSTD_c_validateSequences == 1, then if sequence is invalid (see doc/zstd_compression_format.md for
+ *    specifics regarding offset/matchlength requirements) then the function will bail out and return an error.
+ *
+ *    In addition to the two adjustable experimental params, there are other important cctx params.
+ *    - ZSTD_c_minMatch MUST be set as less than or equal to the smallest match generated by the match finder. It has a minimum value of ZSTD_MINMATCH_MIN.
+ *    - ZSTD_c_compressionLevel accordingly adjusts the strength of the entropy coder, as it would in typical compression.
+ *    - ZSTD_c_windowLog affects offset validation: this function will return an error at higher debug levels if a provided offset
+ *      is larger than what the spec allows for a given window log and dictionary (if present). See: doc/zstd_compression_format.md
+ *
+ * Note: Repcodes are, as of now, always re-calculated within this function, so ZSTD_Sequence::rep is unused.
+ * Note 2: Once we integrate ability to ingest repcodes, the explicit block delims mode must respect those repcodes exactly,
+ *         and cannot emit an RLE block that disagrees with the repcode history
+ * @return : final compressed size or a ZSTD error.
+ */
+ZSTDLIB_API size_t ZSTD_compressSequences(ZSTD_CCtx* const cctx, void* dst, size_t dstSize,
+                                  const ZSTD_Sequence* inSeqs, size_t inSeqsSize,
+                                  const void* src, size_t srcSize);
+
+
+/*! ZSTD_writeSkippableFrame() :
+ * Generates a zstd skippable frame containing data given by src, and writes it to dst buffer.
+ *
+ * Skippable frames begin with a a 4-byte magic number. There are 16 possible choices of magic number,
+ * ranging from ZSTD_MAGIC_SKIPPABLE_START to ZSTD_MAGIC_SKIPPABLE_START+15.
+ * As such, the parameter magicVariant controls the exact skippable frame magic number variant used, so
+ * the magic number used will be ZSTD_MAGIC_SKIPPABLE_START + magicVariant.
+ *
+ * Returns an error if destination buffer is not large enough, if the source size is not representable
+ * with a 4-byte unsigned int, or if the parameter magicVariant is greater than 15 (and therefore invalid).
+ *
+ * @return : number of bytes written or a ZSTD error.
+ */
+ZSTDLIB_API size_t ZSTD_writeSkippableFrame(void* dst, size_t dstCapacity,
+                                            const void* src, size_t srcSize, unsigned magicVariant);
+
+
+/* *************************************
+*  Memory management
+***************************************/
+
+/*! ZSTD_estimate*() :
+ *  These functions make it possible to estimate memory usage
+ *  of a future {D,C}Ctx, before its creation.
+ *
+ *  ZSTD_estimateCCtxSize() will provide a memory budget large enough
+ *  for any compression level up to selected one.
+ *  Note : Unlike ZSTD_estimateCStreamSize*(), this estimate
+ *         does not include space for a window buffer.
+ *         Therefore, the estimation is only guaranteed for single-shot compressions, not streaming.
+ *  The estimate will assume the input may be arbitrarily large,
+ *  which is the worst case.
+ *
+ *  When srcSize can be bound by a known and rather "small" value,
+ *  this fact can be used to provide a tighter estimation
+ *  because the CCtx compression context will need less memory.
+ *  This tighter estimation can be provided by more advanced functions
+ *  ZSTD_estimateCCtxSize_usingCParams(), which can be used in tandem with ZSTD_getCParams(),
+ *  and ZSTD_estimateCCtxSize_usingCCtxParams(), which can be used in tandem with ZSTD_CCtxParams_setParameter().
+ *  Both can be used to estimate memory using custom compression parameters and arbitrary srcSize limits.
+ *
+ *  Note 2 : only single-threaded compression is supported.
+ *  ZSTD_estimateCCtxSize_usingCCtxParams() will return an error code if ZSTD_c_nbWorkers is >= 1.
+ */
+ZSTDLIB_API size_t ZSTD_estimateCCtxSize(int compressionLevel);
+ZSTDLIB_API size_t ZSTD_estimateCCtxSize_usingCParams(ZSTD_compressionParameters cParams);
+ZSTDLIB_API size_t ZSTD_estimateCCtxSize_usingCCtxParams(const ZSTD_CCtx_params* params);
+ZSTDLIB_API size_t ZSTD_estimateDCtxSize(void);
+
+/*! ZSTD_estimateCStreamSize() :
+ *  ZSTD_estimateCStreamSize() will provide a budget large enough for any compression level up to selected one.
+ *  It will also consider src size to be arbitrarily "large", which is worst case.
+ *  If srcSize is known to always be small, ZSTD_estimateCStreamSize_usingCParams() can provide a tighter estimation.
+ *  ZSTD_estimateCStreamSize_usingCParams() can be used in tandem with ZSTD_getCParams() to create cParams from compressionLevel.
+ *  ZSTD_estimateCStreamSize_usingCCtxParams() can be used in tandem with ZSTD_CCtxParams_setParameter(). Only single-threaded compression is supported. This function will return an error code if ZSTD_c_nbWorkers is >= 1.
+ *  Note : CStream size estimation is only correct for single-threaded compression.
+ *  ZSTD_DStream memory budget depends on window Size.
+ *  This information can be passed manually, using ZSTD_estimateDStreamSize,
+ *  or deducted from a valid frame Header, using ZSTD_estimateDStreamSize_fromFrame();
+ *  Note : if streaming is init with function ZSTD_init?Stream_usingDict(),
+ *         an internal ?Dict will be created, which additional size is not estimated here.
+ *         In this case, get total size by adding ZSTD_estimate?DictSize */
+ZSTDLIB_API size_t ZSTD_estimateCStreamSize(int compressionLevel);
+ZSTDLIB_API size_t ZSTD_estimateCStreamSize_usingCParams(ZSTD_compressionParameters cParams);
+ZSTDLIB_API size_t ZSTD_estimateCStreamSize_usingCCtxParams(const ZSTD_CCtx_params* params);
+ZSTDLIB_API size_t ZSTD_estimateDStreamSize(size_t windowSize);
+ZSTDLIB_API size_t ZSTD_estimateDStreamSize_fromFrame(const void* src, size_t srcSize);
+
+/*! ZSTD_estimate?DictSize() :
+ *  ZSTD_estimateCDictSize() will bet that src size is relatively "small", and content is copied, like ZSTD_createCDict().
+ *  ZSTD_estimateCDictSize_advanced() makes it possible to control compression parameters precisely, like ZSTD_createCDict_advanced().
+ *  Note : dictionaries created by reference (`ZSTD_dlm_byRef`) are logically smaller.
+ */
+ZSTDLIB_API size_t ZSTD_estimateCDictSize(size_t dictSize, int compressionLevel);
+ZSTDLIB_API size_t ZSTD_estimateCDictSize_advanced(size_t dictSize, ZSTD_compressionParameters cParams, ZSTD_dictLoadMethod_e dictLoadMethod);
+ZSTDLIB_API size_t ZSTD_estimateDDictSize(size_t dictSize, ZSTD_dictLoadMethod_e dictLoadMethod);
+
+/*! ZSTD_initStatic*() :
+ *  Initialize an object using a pre-allocated fixed-size buffer.
+ *  workspace: The memory area to emplace the object into.
+ *             Provided pointer *must be 8-bytes aligned*.
+ *             Buffer must outlive object.
+ *  workspaceSize: Use ZSTD_estimate*Size() to determine
+ *                 how large workspace must be to support target scenario.
+ * @return : pointer to object (same address as workspace, just different type),
+ *           or NULL if error (size too small, incorrect alignment, etc.)
+ *  Note : zstd will never resize nor malloc() when using a static buffer.
+ *         If the object requires more memory than available,
+ *         zstd will just error out (typically ZSTD_error_memory_allocation).
+ *  Note 2 : there is no corresponding "free" function.
+ *           Since workspace is allocated externally, it must be freed externally too.
+ *  Note 3 : cParams : use ZSTD_getCParams() to convert a compression level
+ *           into its associated cParams.
+ *  Limitation 1 : currently not compatible with internal dictionary creation, triggered by
+ *                 ZSTD_CCtx_loadDictionary(), ZSTD_initCStream_usingDict() or ZSTD_initDStream_usingDict().
+ *  Limitation 2 : static cctx currently not compatible with multi-threading.
+ *  Limitation 3 : static dctx is incompatible with legacy support.
+ */
+ZSTDLIB_API ZSTD_CCtx*    ZSTD_initStaticCCtx(void* workspace, size_t workspaceSize);
+ZSTDLIB_API ZSTD_CStream* ZSTD_initStaticCStream(void* workspace, size_t workspaceSize);    /*< same as ZSTD_initStaticCCtx() */
+
+ZSTDLIB_API ZSTD_DCtx*    ZSTD_initStaticDCtx(void* workspace, size_t workspaceSize);
+ZSTDLIB_API ZSTD_DStream* ZSTD_initStaticDStream(void* workspace, size_t workspaceSize);    /*< same as ZSTD_initStaticDCtx() */
+
+ZSTDLIB_API const ZSTD_CDict* ZSTD_initStaticCDict(
+                                        void* workspace, size_t workspaceSize,
+                                        const void* dict, size_t dictSize,
+                                        ZSTD_dictLoadMethod_e dictLoadMethod,
+                                        ZSTD_dictContentType_e dictContentType,
+                                        ZSTD_compressionParameters cParams);
+
+ZSTDLIB_API const ZSTD_DDict* ZSTD_initStaticDDict(
+                                        void* workspace, size_t workspaceSize,
+                                        const void* dict, size_t dictSize,
+                                        ZSTD_dictLoadMethod_e dictLoadMethod,
+                                        ZSTD_dictContentType_e dictContentType);
+
+
+/*! Custom memory allocation :
+ *  These prototypes make it possible to pass your own allocation/free functions.
+ *  ZSTD_customMem is provided at creation time, using ZSTD_create*_advanced() variants listed below.
+ *  All allocation/free operations will be completed using these custom variants instead of regular <stdlib.h> ones.
+ */
+typedef void* (*ZSTD_allocFunction) (void* opaque, size_t size);
+typedef void  (*ZSTD_freeFunction) (void* opaque, void* address);
+typedef struct { ZSTD_allocFunction customAlloc; ZSTD_freeFunction customFree; void* opaque; } ZSTD_customMem;
+static
+__attribute__((__unused__))
+ZSTD_customMem const ZSTD_defaultCMem = { NULL, NULL, NULL };  /*< this constant defers to stdlib's functions */
+
+ZSTDLIB_API ZSTD_CCtx*    ZSTD_createCCtx_advanced(ZSTD_customMem customMem);
+ZSTDLIB_API ZSTD_CStream* ZSTD_createCStream_advanced(ZSTD_customMem customMem);
+ZSTDLIB_API ZSTD_DCtx*    ZSTD_createDCtx_advanced(ZSTD_customMem customMem);
+ZSTDLIB_API ZSTD_DStream* ZSTD_createDStream_advanced(ZSTD_customMem customMem);
+
+ZSTDLIB_API ZSTD_CDict* ZSTD_createCDict_advanced(const void* dict, size_t dictSize,
+                                                  ZSTD_dictLoadMethod_e dictLoadMethod,
+                                                  ZSTD_dictContentType_e dictContentType,
+                                                  ZSTD_compressionParameters cParams,
+                                                  ZSTD_customMem customMem);
+
+/* ! Thread pool :
+ * These prototypes make it possible to share a thread pool among multiple compression contexts.
+ * This can limit resources for applications with multiple threads where each one uses
+ * a threaded compression mode (via ZSTD_c_nbWorkers parameter).
+ * ZSTD_createThreadPool creates a new thread pool with a given number of threads.
+ * Note that the lifetime of such pool must exist while being used.
+ * ZSTD_CCtx_refThreadPool assigns a thread pool to a context (use NULL argument value
+ * to use an internal thread pool).
+ * ZSTD_freeThreadPool frees a thread pool, accepts NULL pointer.
+ */
+typedef struct POOL_ctx_s ZSTD_threadPool;
+ZSTDLIB_API ZSTD_threadPool* ZSTD_createThreadPool(size_t numThreads);
+ZSTDLIB_API void ZSTD_freeThreadPool (ZSTD_threadPool* pool);  /* accept NULL pointer */
+ZSTDLIB_API size_t ZSTD_CCtx_refThreadPool(ZSTD_CCtx* cctx, ZSTD_threadPool* pool);
+
+
+/*
+ * This API is temporary and is expected to change or disappear in the future!
+ */
+ZSTDLIB_API ZSTD_CDict* ZSTD_createCDict_advanced2(
+    const void* dict, size_t dictSize,
+    ZSTD_dictLoadMethod_e dictLoadMethod,
+    ZSTD_dictContentType_e dictContentType,
+    const ZSTD_CCtx_params* cctxParams,
+    ZSTD_customMem customMem);
+
+ZSTDLIB_API ZSTD_DDict* ZSTD_createDDict_advanced(
+    const void* dict, size_t dictSize,
+    ZSTD_dictLoadMethod_e dictLoadMethod,
+    ZSTD_dictContentType_e dictContentType,
+    ZSTD_customMem customMem);
+
+
+/* *************************************
+*  Advanced compression functions
+***************************************/
+
+/*! ZSTD_createCDict_byReference() :
+ *  Create a digested dictionary for compression
+ *  Dictionary content is just referenced, not duplicated.
+ *  As a consequence, `dictBuffer` **must** outlive CDict,
+ *  and its content must remain unmodified throughout the lifetime of CDict.
+ *  note: equivalent to ZSTD_createCDict_advanced(), with dictLoadMethod==ZSTD_dlm_byRef */
+ZSTDLIB_API ZSTD_CDict* ZSTD_createCDict_byReference(const void* dictBuffer, size_t dictSize, int compressionLevel);
+
+/*! ZSTD_getDictID_fromCDict() :
+ *  Provides the dictID of the dictionary loaded into `cdict`.
+ *  If @return == 0, the dictionary is not conformant to Zstandard specification, or empty.
+ *  Non-conformant dictionaries can still be loaded, but as content-only dictionaries. */
+ZSTDLIB_API unsigned ZSTD_getDictID_fromCDict(const ZSTD_CDict* cdict);
+
+/*! ZSTD_getCParams() :
+ * @return ZSTD_compressionParameters structure for a selected compression level and estimated srcSize.
+ * `estimatedSrcSize` value is optional, select 0 if not known */
+ZSTDLIB_API ZSTD_compressionParameters ZSTD_getCParams(int compressionLevel, unsigned long long estimatedSrcSize, size_t dictSize);
+
+/*! ZSTD_getParams() :
+ *  same as ZSTD_getCParams(), but @return a full `ZSTD_parameters` object instead of sub-component `ZSTD_compressionParameters`.
+ *  All fields of `ZSTD_frameParameters` are set to default : contentSize=1, checksum=0, noDictID=0 */
+ZSTDLIB_API ZSTD_parameters ZSTD_getParams(int compressionLevel, unsigned long long estimatedSrcSize, size_t dictSize);
+
+/*! ZSTD_checkCParams() :
+ *  Ensure param values remain within authorized range.
+ * @return 0 on success, or an error code (can be checked with ZSTD_isError()) */
+ZSTDLIB_API size_t ZSTD_checkCParams(ZSTD_compressionParameters params);
+
+/*! ZSTD_adjustCParams() :
+ *  optimize params for a given `srcSize` and `dictSize`.
+ * `srcSize` can be unknown, in which case use ZSTD_CONTENTSIZE_UNKNOWN.
+ * `dictSize` must be `0` when there is no dictionary.
+ *  cPar can be invalid : all parameters will be clamped within valid range in the @return struct.
+ *  This function never fails (wide contract) */
+ZSTDLIB_API ZSTD_compressionParameters ZSTD_adjustCParams(ZSTD_compressionParameters cPar, unsigned long long srcSize, size_t dictSize);
+
+/*! ZSTD_compress_advanced() :
+ *  Note : this function is now DEPRECATED.
+ *         It can be replaced by ZSTD_compress2(), in combination with ZSTD_CCtx_setParameter() and other parameter setters.
+ *  This prototype will be marked as deprecated and generate compilation warning on reaching v1.5.x */
+ZSTDLIB_API size_t ZSTD_compress_advanced(ZSTD_CCtx* cctx,
+                                          void* dst, size_t dstCapacity,
+                                    const void* src, size_t srcSize,
+                                    const void* dict,size_t dictSize,
+                                          ZSTD_parameters params);
+
+/*! ZSTD_compress_usingCDict_advanced() :
+ *  Note : this function is now REDUNDANT.
+ *         It can be replaced by ZSTD_compress2(), in combination with ZSTD_CCtx_loadDictionary() and other parameter setters.
+ *  This prototype will be marked as deprecated and generate compilation warning in some future version */
+ZSTDLIB_API size_t ZSTD_compress_usingCDict_advanced(ZSTD_CCtx* cctx,
+                                              void* dst, size_t dstCapacity,
+                                        const void* src, size_t srcSize,
+                                        const ZSTD_CDict* cdict,
+                                              ZSTD_frameParameters fParams);
+
+
+/*! ZSTD_CCtx_loadDictionary_byReference() :
+ *  Same as ZSTD_CCtx_loadDictionary(), but dictionary content is referenced, instead of being copied into CCtx.
+ *  It saves some memory, but also requires that `dict` outlives its usage within `cctx` */
+ZSTDLIB_API size_t ZSTD_CCtx_loadDictionary_byReference(ZSTD_CCtx* cctx, const void* dict, size_t dictSize);
+
+/*! ZSTD_CCtx_loadDictionary_advanced() :
+ *  Same as ZSTD_CCtx_loadDictionary(), but gives finer control over
+ *  how to load the dictionary (by copy ? by reference ?)
+ *  and how to interpret it (automatic ? force raw mode ? full mode only ?) */
+ZSTDLIB_API size_t ZSTD_CCtx_loadDictionary_advanced(ZSTD_CCtx* cctx, const void* dict, size_t dictSize, ZSTD_dictLoadMethod_e dictLoadMethod, ZSTD_dictContentType_e dictContentType);
+
+/*! ZSTD_CCtx_refPrefix_advanced() :
+ *  Same as ZSTD_CCtx_refPrefix(), but gives finer control over
+ *  how to interpret prefix content (automatic ? force raw mode (default) ? full mode only ?) */
+ZSTDLIB_API size_t ZSTD_CCtx_refPrefix_advanced(ZSTD_CCtx* cctx, const void* prefix, size_t prefixSize, ZSTD_dictContentType_e dictContentType);
+
+/* ===   experimental parameters   === */
+/* these parameters can be used with ZSTD_setParameter()
+ * they are not guaranteed to remain supported in the future */
+
+ /* Enables rsyncable mode,
+  * which makes compressed files more rsync friendly
+  * by adding periodic synchronization points to the compressed data.
+  * The target average block size is ZSTD_c_jobSize / 2.
+  * It's possible to modify the job size to increase or decrease
+  * the granularity of the synchronization point.
+  * Once the jobSize is smaller than the window size,
+  * it will result in compression ratio degradation.
+  * NOTE 1: rsyncable mode only works when multithreading is enabled.
+  * NOTE 2: rsyncable performs poorly in combination with long range mode,
+  * since it will decrease the effectiveness of synchronization points,
+  * though mileage may vary.
+  * NOTE 3: Rsyncable mode limits maximum compression speed to ~400 MB/s.
+  * If the selected compression level is already running significantly slower,
+  * the overall speed won't be significantly impacted.
+  */
+ #define ZSTD_c_rsyncable ZSTD_c_experimentalParam1
+
+/* Select a compression format.
+ * The value must be of type ZSTD_format_e.
+ * See ZSTD_format_e enum definition for details */
+#define ZSTD_c_format ZSTD_c_experimentalParam2
+
+/* Force back-reference distances to remain < windowSize,
+ * even when referencing into Dictionary content (default:0) */
+#define ZSTD_c_forceMaxWindow ZSTD_c_experimentalParam3
+
+/* Controls whether the contents of a CDict
+ * are used in place, or copied into the working context.
+ * Accepts values from the ZSTD_dictAttachPref_e enum.
+ * See the comments on that enum for an explanation of the feature. */
+#define ZSTD_c_forceAttachDict ZSTD_c_experimentalParam4
+
+/* Controls how the literals are compressed (default is auto).
+ * The value must be of type ZSTD_literalCompressionMode_e.
+ * See ZSTD_literalCompressionMode_t enum definition for details.
+ */
+#define ZSTD_c_literalCompressionMode ZSTD_c_experimentalParam5
+
+/* Tries to fit compressed block size to be around targetCBlockSize.
+ * No target when targetCBlockSize == 0.
+ * There is no guarantee on compressed block size (default:0) */
+#define ZSTD_c_targetCBlockSize ZSTD_c_experimentalParam6
+
+/* User's best guess of source size.
+ * Hint is not valid when srcSizeHint == 0.
+ * There is no guarantee that hint is close to actual source size,
+ * but compression ratio may regress significantly if guess considerably underestimates */
+#define ZSTD_c_srcSizeHint ZSTD_c_experimentalParam7
+
+/* Controls whether the new and experimental "dedicated dictionary search
+ * structure" can be used. This feature is still rough around the edges, be
+ * prepared for surprising behavior!
+ *
+ * How to use it:
+ *
+ * When using a CDict, whether to use this feature or not is controlled at
+ * CDict creation, and it must be set in a CCtxParams set passed into that
+ * construction (via ZSTD_createCDict_advanced2()). A compression will then
+ * use the feature or not based on how the CDict was constructed; the value of
+ * this param, set in the CCtx, will have no effect.
+ *
+ * However, when a dictionary buffer is passed into a CCtx, such as via
+ * ZSTD_CCtx_loadDictionary(), this param can be set on the CCtx to control
+ * whether the CDict that is created internally can use the feature or not.
+ *
+ * What it does:
+ *
+ * Normally, the internal data structures of the CDict are analogous to what
+ * would be stored in a CCtx after compressing the contents of a dictionary.
+ * To an approximation, a compression using a dictionary can then use those
+ * data structures to simply continue what is effectively a streaming
+ * compression where the simulated compression of the dictionary left off.
+ * Which is to say, the search structures in the CDict are normally the same
+ * format as in the CCtx.
+ *
+ * It is possible to do better, since the CDict is not like a CCtx: the search
+ * structures are written once during CDict creation, and then are only read
+ * after that, while the search structures in the CCtx are both read and
+ * written as the compression goes along. This means we can choose a search
+ * structure for the dictionary that is read-optimized.
+ *
+ * This feature enables the use of that different structure.
+ *
+ * Note that some of the members of the ZSTD_compressionParameters struct have
+ * different semantics and constraints in the dedicated search structure. It is
+ * highly recommended that you simply set a compression level in the CCtxParams
+ * you pass into the CDict creation call, and avoid messing with the cParams
+ * directly.
+ *
+ * Effects:
+ *
+ * This will only have any effect when the selected ZSTD_strategy
+ * implementation supports this feature. Currently, that's limited to
+ * ZSTD_greedy, ZSTD_lazy, and ZSTD_lazy2.
+ *
+ * Note that this means that the CDict tables can no longer be copied into the
+ * CCtx, so the dict attachment mode ZSTD_dictForceCopy will no longer be
+ * useable. The dictionary can only be attached or reloaded.
+ *
+ * In general, you should expect compression to be faster--sometimes very much
+ * so--and CDict creation to be slightly slower. Eventually, we will probably
+ * make this mode the default.
+ */
+#define ZSTD_c_enableDedicatedDictSearch ZSTD_c_experimentalParam8
+
+/* ZSTD_c_stableInBuffer
+ * Experimental parameter.
+ * Default is 0 == disabled. Set to 1 to enable.
+ *
+ * Tells the compressor that the ZSTD_inBuffer will ALWAYS be the same
+ * between calls, except for the modifications that zstd makes to pos (the
+ * caller must not modify pos). This is checked by the compressor, and
+ * compression will fail if it ever changes. This means the only flush
+ * mode that makes sense is ZSTD_e_end, so zstd will error if ZSTD_e_end
+ * is not used. The data in the ZSTD_inBuffer in the range [src, src + pos)
+ * MUST not be modified during compression or you will get data corruption.
+ *
+ * When this flag is enabled zstd won't allocate an input window buffer,
+ * because the user guarantees it can reference the ZSTD_inBuffer until
+ * the frame is complete. But, it will still allocate an output buffer
+ * large enough to fit a block (see ZSTD_c_stableOutBuffer). This will also
+ * avoid the memcpy() from the input buffer to the input window buffer.
+ *
+ * NOTE: ZSTD_compressStream2() will error if ZSTD_e_end is not used.
+ * That means this flag cannot be used with ZSTD_compressStream().
+ *
+ * NOTE: So long as the ZSTD_inBuffer always points to valid memory, using
+ * this flag is ALWAYS memory safe, and will never access out-of-bounds
+ * memory. However, compression WILL fail if you violate the preconditions.
+ *
+ * WARNING: The data in the ZSTD_inBuffer in the range [dst, dst + pos) MUST
+ * not be modified during compression or you will get data corruption. This
+ * is because zstd needs to reference data in the ZSTD_inBuffer to find
+ * matches. Normally zstd maintains its own window buffer for this purpose,
+ * but passing this flag tells zstd to use the user provided buffer.
+ */
+#define ZSTD_c_stableInBuffer ZSTD_c_experimentalParam9
+
+/* ZSTD_c_stableOutBuffer
+ * Experimental parameter.
+ * Default is 0 == disabled. Set to 1 to enable.
+ *
+ * Tells he compressor that the ZSTD_outBuffer will not be resized between
+ * calls. Specifically: (out.size - out.pos) will never grow. This gives the
+ * compressor the freedom to say: If the compressed data doesn't fit in the
+ * output buffer then return ZSTD_error_dstSizeTooSmall. This allows us to
+ * always decompress directly into the output buffer, instead of decompressing
+ * into an internal buffer and copying to the output buffer.
+ *
+ * When this flag is enabled zstd won't allocate an output buffer, because
+ * it can write directly to the ZSTD_outBuffer. It will still allocate the
+ * input window buffer (see ZSTD_c_stableInBuffer).
+ *
+ * Zstd will check that (out.size - out.pos) never grows and return an error
+ * if it does. While not strictly necessary, this should prevent surprises.
+ */
+#define ZSTD_c_stableOutBuffer ZSTD_c_experimentalParam10
+
+/* ZSTD_c_blockDelimiters
+ * Default is 0 == ZSTD_sf_noBlockDelimiters.
+ *
+ * For use with sequence compression API: ZSTD_compressSequences().
+ *
+ * Designates whether or not the given array of ZSTD_Sequence contains block delimiters
+ * and last literals, which are defined as sequences with offset == 0 and matchLength == 0.
+ * See the definition of ZSTD_Sequence for more specifics.
+ */
+#define ZSTD_c_blockDelimiters ZSTD_c_experimentalParam11
+
+/* ZSTD_c_validateSequences
+ * Default is 0 == disabled. Set to 1 to enable sequence validation.
+ *
+ * For use with sequence compression API: ZSTD_compressSequences().
+ * Designates whether or not we validate sequences provided to ZSTD_compressSequences()
+ * during function execution.
+ *
+ * Without validation, providing a sequence that does not conform to the zstd spec will cause
+ * undefined behavior, and may produce a corrupted block.
+ *
+ * With validation enabled, a if sequence is invalid (see doc/zstd_compression_format.md for
+ * specifics regarding offset/matchlength requirements) then the function will bail out and
+ * return an error.
+ *
+ */
+#define ZSTD_c_validateSequences ZSTD_c_experimentalParam12
+
+/*! ZSTD_CCtx_getParameter() :
+ *  Get the requested compression parameter value, selected by enum ZSTD_cParameter,
+ *  and store it into int* value.
+ * @return : 0, or an error code (which can be tested with ZSTD_isError()).
+ */
+ZSTDLIB_API size_t ZSTD_CCtx_getParameter(const ZSTD_CCtx* cctx, ZSTD_cParameter param, int* value);
+
+
+/*! ZSTD_CCtx_params :
+ *  Quick howto :
+ *  - ZSTD_createCCtxParams() : Create a ZSTD_CCtx_params structure
+ *  - ZSTD_CCtxParams_setParameter() : Push parameters one by one into
+ *                                     an existing ZSTD_CCtx_params structure.
+ *                                     This is similar to
+ *                                     ZSTD_CCtx_setParameter().
+ *  - ZSTD_CCtx_setParametersUsingCCtxParams() : Apply parameters to
+ *                                    an existing CCtx.
+ *                                    These parameters will be applied to
+ *                                    all subsequent frames.
+ *  - ZSTD_compressStream2() : Do compression using the CCtx.
+ *  - ZSTD_freeCCtxParams() : Free the memory, accept NULL pointer.
+ *
+ *  This can be used with ZSTD_estimateCCtxSize_advanced_usingCCtxParams()
+ *  for static allocation of CCtx for single-threaded compression.
+ */
+ZSTDLIB_API ZSTD_CCtx_params* ZSTD_createCCtxParams(void);
+ZSTDLIB_API size_t ZSTD_freeCCtxParams(ZSTD_CCtx_params* params);  /* accept NULL pointer */
+
+/*! ZSTD_CCtxParams_reset() :
+ *  Reset params to default values.
+ */
+ZSTDLIB_API size_t ZSTD_CCtxParams_reset(ZSTD_CCtx_params* params);
+
+/*! ZSTD_CCtxParams_init() :
+ *  Initializes the compression parameters of cctxParams according to
+ *  compression level. All other parameters are reset to their default values.
+ */
+ZSTDLIB_API size_t ZSTD_CCtxParams_init(ZSTD_CCtx_params* cctxParams, int compressionLevel);
+
+/*! ZSTD_CCtxParams_init_advanced() :
+ *  Initializes the compression and frame parameters of cctxParams according to
+ *  params. All other parameters are reset to their default values.
+ */
+ZSTDLIB_API size_t ZSTD_CCtxParams_init_advanced(ZSTD_CCtx_params* cctxParams, ZSTD_parameters params);
+
+/*! ZSTD_CCtxParams_setParameter() :
+ *  Similar to ZSTD_CCtx_setParameter.
+ *  Set one compression parameter, selected by enum ZSTD_cParameter.
+ *  Parameters must be applied to a ZSTD_CCtx using
+ *  ZSTD_CCtx_setParametersUsingCCtxParams().
+ * @result : a code representing success or failure (which can be tested with
+ *           ZSTD_isError()).
+ */
+ZSTDLIB_API size_t ZSTD_CCtxParams_setParameter(ZSTD_CCtx_params* params, ZSTD_cParameter param, int value);
+
+/*! ZSTD_CCtxParams_getParameter() :
+ * Similar to ZSTD_CCtx_getParameter.
+ * Get the requested value of one compression parameter, selected by enum ZSTD_cParameter.
+ * @result : 0, or an error code (which can be tested with ZSTD_isError()).
+ */
+ZSTDLIB_API size_t ZSTD_CCtxParams_getParameter(const ZSTD_CCtx_params* params, ZSTD_cParameter param, int* value);
+
+/*! ZSTD_CCtx_setParametersUsingCCtxParams() :
+ *  Apply a set of ZSTD_CCtx_params to the compression context.
+ *  This can be done even after compression is started,
+ *    if nbWorkers==0, this will have no impact until a new compression is started.
+ *    if nbWorkers>=1, new parameters will be picked up at next job,
+ *       with a few restrictions (windowLog, pledgedSrcSize, nbWorkers, jobSize, and overlapLog are not updated).
+ */
+ZSTDLIB_API size_t ZSTD_CCtx_setParametersUsingCCtxParams(
+        ZSTD_CCtx* cctx, const ZSTD_CCtx_params* params);
+
+/*! ZSTD_compressStream2_simpleArgs() :
+ *  Same as ZSTD_compressStream2(),
+ *  but using only integral types as arguments.
+ *  This variant might be helpful for binders from dynamic languages
+ *  which have troubles handling structures containing memory pointers.
+ */
+ZSTDLIB_API size_t ZSTD_compressStream2_simpleArgs (
+                            ZSTD_CCtx* cctx,
+                            void* dst, size_t dstCapacity, size_t* dstPos,
+                      const void* src, size_t srcSize, size_t* srcPos,
+                            ZSTD_EndDirective endOp);
+
+
+/* *************************************
+*  Advanced decompression functions
+***************************************/
+
+/*! ZSTD_isFrame() :
+ *  Tells if the content of `buffer` starts with a valid Frame Identifier.
+ *  Note : Frame Identifier is 4 bytes. If `size < 4`, @return will always be 0.
+ *  Note 2 : Legacy Frame Identifiers are considered valid only if Legacy Support is enabled.
+ *  Note 3 : Skippable Frame Identifiers are considered valid. */
+ZSTDLIB_API unsigned ZSTD_isFrame(const void* buffer, size_t size);
+
+/*! ZSTD_createDDict_byReference() :
+ *  Create a digested dictionary, ready to start decompression operation without startup delay.
+ *  Dictionary content is referenced, and therefore stays in dictBuffer.
+ *  It is important that dictBuffer outlives DDict,
+ *  it must remain read accessible throughout the lifetime of DDict */
+ZSTDLIB_API ZSTD_DDict* ZSTD_createDDict_byReference(const void* dictBuffer, size_t dictSize);
+
+/*! ZSTD_DCtx_loadDictionary_byReference() :
+ *  Same as ZSTD_DCtx_loadDictionary(),
+ *  but references `dict` content instead of copying it into `dctx`.
+ *  This saves memory if `dict` remains around.,
+ *  However, it's imperative that `dict` remains accessible (and unmodified) while being used, so it must outlive decompression. */
+ZSTDLIB_API size_t ZSTD_DCtx_loadDictionary_byReference(ZSTD_DCtx* dctx, const void* dict, size_t dictSize);
+
+/*! ZSTD_DCtx_loadDictionary_advanced() :
+ *  Same as ZSTD_DCtx_loadDictionary(),
+ *  but gives direct control over
+ *  how to load the dictionary (by copy ? by reference ?)
+ *  and how to interpret it (automatic ? force raw mode ? full mode only ?). */
+ZSTDLIB_API size_t ZSTD_DCtx_loadDictionary_advanced(ZSTD_DCtx* dctx, const void* dict, size_t dictSize, ZSTD_dictLoadMethod_e dictLoadMethod, ZSTD_dictContentType_e dictContentType);
+
+/*! ZSTD_DCtx_refPrefix_advanced() :
+ *  Same as ZSTD_DCtx_refPrefix(), but gives finer control over
+ *  how to interpret prefix content (automatic ? force raw mode (default) ? full mode only ?) */
+ZSTDLIB_API size_t ZSTD_DCtx_refPrefix_advanced(ZSTD_DCtx* dctx, const void* prefix, size_t prefixSize, ZSTD_dictContentType_e dictContentType);
+
+/*! ZSTD_DCtx_setMaxWindowSize() :
+ *  Refuses allocating internal buffers for frames requiring a window size larger than provided limit.
+ *  This protects a decoder context from reserving too much memory for itself (potential attack scenario).
+ *  This parameter is only useful in streaming mode, since no internal buffer is allocated in single-pass mode.
+ *  By default, a decompression context accepts all window sizes <= (1 << ZSTD_WINDOWLOG_LIMIT_DEFAULT)
+ * @return : 0, or an error code (which can be tested using ZSTD_isError()).
+ */
+ZSTDLIB_API size_t ZSTD_DCtx_setMaxWindowSize(ZSTD_DCtx* dctx, size_t maxWindowSize);
+
+/*! ZSTD_DCtx_getParameter() :
+ *  Get the requested decompression parameter value, selected by enum ZSTD_dParameter,
+ *  and store it into int* value.
+ * @return : 0, or an error code (which can be tested with ZSTD_isError()).
+ */
+ZSTDLIB_API size_t ZSTD_DCtx_getParameter(ZSTD_DCtx* dctx, ZSTD_dParameter param, int* value);
+
+/* ZSTD_d_format
+ * experimental parameter,
+ * allowing selection between ZSTD_format_e input compression formats
+ */
+#define ZSTD_d_format ZSTD_d_experimentalParam1
+/* ZSTD_d_stableOutBuffer
+ * Experimental parameter.
+ * Default is 0 == disabled. Set to 1 to enable.
+ *
+ * Tells the decompressor that the ZSTD_outBuffer will ALWAYS be the same
+ * between calls, except for the modifications that zstd makes to pos (the
+ * caller must not modify pos). This is checked by the decompressor, and
+ * decompression will fail if it ever changes. Therefore the ZSTD_outBuffer
+ * MUST be large enough to fit the entire decompressed frame. This will be
+ * checked when the frame content size is known. The data in the ZSTD_outBuffer
+ * in the range [dst, dst + pos) MUST not be modified during decompression
+ * or you will get data corruption.
+ *
+ * When this flags is enabled zstd won't allocate an output buffer, because
+ * it can write directly to the ZSTD_outBuffer, but it will still allocate
+ * an input buffer large enough to fit any compressed block. This will also
+ * avoid the memcpy() from the internal output buffer to the ZSTD_outBuffer.
+ * If you need to avoid the input buffer allocation use the buffer-less
+ * streaming API.
+ *
+ * NOTE: So long as the ZSTD_outBuffer always points to valid memory, using
+ * this flag is ALWAYS memory safe, and will never access out-of-bounds
+ * memory. However, decompression WILL fail if you violate the preconditions.
+ *
+ * WARNING: The data in the ZSTD_outBuffer in the range [dst, dst + pos) MUST
+ * not be modified during decompression or you will get data corruption. This
+ * is because zstd needs to reference data in the ZSTD_outBuffer to regenerate
+ * matches. Normally zstd maintains its own buffer for this purpose, but passing
+ * this flag tells zstd to use the user provided buffer.
+ */
+#define ZSTD_d_stableOutBuffer ZSTD_d_experimentalParam2
+
+/* ZSTD_d_forceIgnoreChecksum
+ * Experimental parameter.
+ * Default is 0 == disabled. Set to 1 to enable
+ *
+ * Tells the decompressor to skip checksum validation during decompression, regardless
+ * of whether checksumming was specified during compression. This offers some
+ * slight performance benefits, and may be useful for debugging.
+ * Param has values of type ZSTD_forceIgnoreChecksum_e
+ */
+#define ZSTD_d_forceIgnoreChecksum ZSTD_d_experimentalParam3
+
+/* ZSTD_d_refMultipleDDicts
+ * Experimental parameter.
+ * Default is 0 == disabled. Set to 1 to enable
+ *
+ * If enabled and dctx is allocated on the heap, then additional memory will be allocated
+ * to store references to multiple ZSTD_DDict. That is, multiple calls of ZSTD_refDDict()
+ * using a given ZSTD_DCtx, rather than overwriting the previous DDict reference, will instead
+ * store all references. At decompression time, the appropriate dictID is selected
+ * from the set of DDicts based on the dictID in the frame.
+ *
+ * Usage is simply calling ZSTD_refDDict() on multiple dict buffers.
+ *
+ * Param has values of byte ZSTD_refMultipleDDicts_e
+ *
+ * WARNING: Enabling this parameter and calling ZSTD_DCtx_refDDict(), will trigger memory
+ * allocation for the hash table. ZSTD_freeDCtx() also frees this memory.
+ * Memory is allocated as per ZSTD_DCtx::customMem.
+ *
+ * Although this function allocates memory for the table, the user is still responsible for
+ * memory management of the underlying ZSTD_DDict* themselves.
+ */
+#define ZSTD_d_refMultipleDDicts ZSTD_d_experimentalParam4
+
+
+/*! ZSTD_DCtx_setFormat() :
+ *  Instruct the decoder context about what kind of data to decode next.
+ *  This instruction is mandatory to decode data without a fully-formed header,
+ *  such ZSTD_f_zstd1_magicless for example.
+ * @return : 0, or an error code (which can be tested using ZSTD_isError()). */
+ZSTDLIB_API size_t ZSTD_DCtx_setFormat(ZSTD_DCtx* dctx, ZSTD_format_e format);
+
+/*! ZSTD_decompressStream_simpleArgs() :
+ *  Same as ZSTD_decompressStream(),
+ *  but using only integral types as arguments.
+ *  This can be helpful for binders from dynamic languages
+ *  which have troubles handling structures containing memory pointers.
+ */
+ZSTDLIB_API size_t ZSTD_decompressStream_simpleArgs (
+                            ZSTD_DCtx* dctx,
+                            void* dst, size_t dstCapacity, size_t* dstPos,
+                      const void* src, size_t srcSize, size_t* srcPos);
+
+
+/* ******************************************************************
+*  Advanced streaming functions
+*  Warning : most of these functions are now redundant with the Advanced API.
+*  Once Advanced API reaches "stable" status,
+*  redundant functions will be deprecated, and then at some point removed.
+********************************************************************/
+
+/*=====   Advanced Streaming compression functions  =====*/
+
+/*! ZSTD_initCStream_srcSize() :
+ * This function is deprecated, and equivalent to:
+ *     ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only);
+ *     ZSTD_CCtx_refCDict(zcs, NULL); // clear the dictionary (if any)
+ *     ZSTD_CCtx_setParameter(zcs, ZSTD_c_compressionLevel, compressionLevel);
+ *     ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize);
+ *
+ * pledgedSrcSize must be correct. If it is not known at init time, use
+ * ZSTD_CONTENTSIZE_UNKNOWN. Note that, for compatibility with older programs,
+ * "0" also disables frame content size field. It may be enabled in the future.
+ * Note : this prototype will be marked as deprecated and generate compilation warnings on reaching v1.5.x
+ */
+ZSTDLIB_API size_t
+ZSTD_initCStream_srcSize(ZSTD_CStream* zcs,
+                         int compressionLevel,
+                         unsigned long long pledgedSrcSize);
+
+/*! ZSTD_initCStream_usingDict() :
+ * This function is deprecated, and is equivalent to:
+ *     ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only);
+ *     ZSTD_CCtx_setParameter(zcs, ZSTD_c_compressionLevel, compressionLevel);
+ *     ZSTD_CCtx_loadDictionary(zcs, dict, dictSize);
+ *
+ * Creates of an internal CDict (incompatible with static CCtx), except if
+ * dict == NULL or dictSize < 8, in which case no dict is used.
+ * Note: dict is loaded with ZSTD_dct_auto (treated as a full zstd dictionary if
+ * it begins with ZSTD_MAGIC_DICTIONARY, else as raw content) and ZSTD_dlm_byCopy.
+ * Note : this prototype will be marked as deprecated and generate compilation warnings on reaching v1.5.x
+ */
+ZSTDLIB_API size_t
+ZSTD_initCStream_usingDict(ZSTD_CStream* zcs,
+                     const void* dict, size_t dictSize,
+                           int compressionLevel);
+
+/*! ZSTD_initCStream_advanced() :
+ * This function is deprecated, and is approximately equivalent to:
+ *     ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only);
+ *     // Pseudocode: Set each zstd parameter and leave the rest as-is.
+ *     for ((param, value) : params) {
+ *         ZSTD_CCtx_setParameter(zcs, param, value);
+ *     }
+ *     ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize);
+ *     ZSTD_CCtx_loadDictionary(zcs, dict, dictSize);
+ *
+ * dict is loaded with ZSTD_dct_auto and ZSTD_dlm_byCopy.
+ * pledgedSrcSize must be correct.
+ * If srcSize is not known at init time, use value ZSTD_CONTENTSIZE_UNKNOWN.
+ * Note : this prototype will be marked as deprecated and generate compilation warnings on reaching v1.5.x
+ */
+ZSTDLIB_API size_t
+ZSTD_initCStream_advanced(ZSTD_CStream* zcs,
+                    const void* dict, size_t dictSize,
+                          ZSTD_parameters params,
+                          unsigned long long pledgedSrcSize);
+
+/*! ZSTD_initCStream_usingCDict() :
+ * This function is deprecated, and equivalent to:
+ *     ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only);
+ *     ZSTD_CCtx_refCDict(zcs, cdict);
+ *
+ * note : cdict will just be referenced, and must outlive compression session
+ * Note : this prototype will be marked as deprecated and generate compilation warnings on reaching v1.5.x
+ */
+ZSTDLIB_API size_t ZSTD_initCStream_usingCDict(ZSTD_CStream* zcs, const ZSTD_CDict* cdict);
+
+/*! ZSTD_initCStream_usingCDict_advanced() :
+ *   This function is DEPRECATED, and is approximately equivalent to:
+ *     ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only);
+ *     // Pseudocode: Set each zstd frame parameter and leave the rest as-is.
+ *     for ((fParam, value) : fParams) {
+ *         ZSTD_CCtx_setParameter(zcs, fParam, value);
+ *     }
+ *     ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize);
+ *     ZSTD_CCtx_refCDict(zcs, cdict);
+ *
+ * same as ZSTD_initCStream_usingCDict(), with control over frame parameters.
+ * pledgedSrcSize must be correct. If srcSize is not known at init time, use
+ * value ZSTD_CONTENTSIZE_UNKNOWN.
+ * Note : this prototype will be marked as deprecated and generate compilation warnings on reaching v1.5.x
+ */
+ZSTDLIB_API size_t
+ZSTD_initCStream_usingCDict_advanced(ZSTD_CStream* zcs,
+                               const ZSTD_CDict* cdict,
+                                     ZSTD_frameParameters fParams,
+                                     unsigned long long pledgedSrcSize);
+
+/*! ZSTD_resetCStream() :
+ * This function is deprecated, and is equivalent to:
+ *     ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only);
+ *     ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize);
+ *
+ *  start a new frame, using same parameters from previous frame.
+ *  This is typically useful to skip dictionary loading stage, since it will re-use it in-place.
+ *  Note that zcs must be init at least once before using ZSTD_resetCStream().
+ *  If pledgedSrcSize is not known at reset time, use macro ZSTD_CONTENTSIZE_UNKNOWN.
+ *  If pledgedSrcSize > 0, its value must be correct, as it will be written in header, and controlled at the end.
+ *  For the time being, pledgedSrcSize==0 is interpreted as "srcSize unknown" for compatibility with older programs,
+ *  but it will change to mean "empty" in future version, so use macro ZSTD_CONTENTSIZE_UNKNOWN instead.
+ * @return : 0, or an error code (which can be tested using ZSTD_isError())
+ *  Note : this prototype will be marked as deprecated and generate compilation warnings on reaching v1.5.x
+ */
+ZSTDLIB_API size_t ZSTD_resetCStream(ZSTD_CStream* zcs, unsigned long long pledgedSrcSize);
+
+
+typedef struct {
+    unsigned long long ingested;   /* nb input bytes read and buffered */
+    unsigned long long consumed;   /* nb input bytes actually compressed */
+    unsigned long long produced;   /* nb of compressed bytes generated and buffered */
+    unsigned long long flushed;    /* nb of compressed bytes flushed : not provided; can be tracked from caller side */
+    unsigned currentJobID;         /* MT only : latest started job nb */
+    unsigned nbActiveWorkers;      /* MT only : nb of workers actively compressing at probe time */
+} ZSTD_frameProgression;
+
+/* ZSTD_getFrameProgression() :
+ * tells how much data has been ingested (read from input)
+ * consumed (input actually compressed) and produced (output) for current frame.
+ * Note : (ingested - consumed) is amount of input data buffered internally, not yet compressed.
+ * Aggregates progression inside active worker threads.
+ */
+ZSTDLIB_API ZSTD_frameProgression ZSTD_getFrameProgression(const ZSTD_CCtx* cctx);
+
+/*! ZSTD_toFlushNow() :
+ *  Tell how many bytes are ready to be flushed immediately.
+ *  Useful for multithreading scenarios (nbWorkers >= 1).
+ *  Probe the oldest active job, defined as oldest job not yet entirely flushed,
+ *  and check its output buffer.
+ * @return : amount of data stored in oldest job and ready to be flushed immediately.
+ *  if @return == 0, it means either :
+ *  + there is no active job (could be checked with ZSTD_frameProgression()), or
+ *  + oldest job is still actively compressing data,
+ *    but everything it has produced has also been flushed so far,
+ *    therefore flush speed is limited by production speed of oldest job
+ *    irrespective of the speed of concurrent (and newer) jobs.
+ */
+ZSTDLIB_API size_t ZSTD_toFlushNow(ZSTD_CCtx* cctx);
+
+
+/*=====   Advanced Streaming decompression functions  =====*/
+
+/*!
+ * This function is deprecated, and is equivalent to:
+ *
+ *     ZSTD_DCtx_reset(zds, ZSTD_reset_session_only);
+ *     ZSTD_DCtx_loadDictionary(zds, dict, dictSize);
+ *
+ * note: no dictionary will be used if dict == NULL or dictSize < 8
+ * Note : this prototype will be marked as deprecated and generate compilation warnings on reaching v1.5.x
+ */
+ZSTDLIB_API size_t ZSTD_initDStream_usingDict(ZSTD_DStream* zds, const void* dict, size_t dictSize);
+
+/*!
+ * This function is deprecated, and is equivalent to:
+ *
+ *     ZSTD_DCtx_reset(zds, ZSTD_reset_session_only);
+ *     ZSTD_DCtx_refDDict(zds, ddict);
+ *
+ * note : ddict is referenced, it must outlive decompression session
+ * Note : this prototype will be marked as deprecated and generate compilation warnings on reaching v1.5.x
+ */
+ZSTDLIB_API size_t ZSTD_initDStream_usingDDict(ZSTD_DStream* zds, const ZSTD_DDict* ddict);
+
+/*!
+ * This function is deprecated, and is equivalent to:
+ *
+ *     ZSTD_DCtx_reset(zds, ZSTD_reset_session_only);
+ *
+ * re-use decompression parameters from previous init; saves dictionary loading
+ * Note : this prototype will be marked as deprecated and generate compilation warnings on reaching v1.5.x
+ */
+ZSTDLIB_API size_t ZSTD_resetDStream(ZSTD_DStream* zds);
+
+
+/* *******************************************************************
+*  Buffer-less and synchronous inner streaming functions
+*
+*  This is an advanced API, giving full control over buffer management, for users which need direct control over memory.
+*  But it's also a complex one, with several restrictions, documented below.
+*  Prefer normal streaming API for an easier experience.
+********************************************************************* */
+
+/*
+  Buffer-less streaming compression (synchronous mode)
+
+  A ZSTD_CCtx object is required to track streaming operations.
+  Use ZSTD_createCCtx() / ZSTD_freeCCtx() to manage resource.
+  ZSTD_CCtx object can be re-used multiple times within successive compression operations.
+
+  Start by initializing a context.
+  Use ZSTD_compressBegin(), or ZSTD_compressBegin_usingDict() for dictionary compression,
+  or ZSTD_compressBegin_advanced(), for finer parameter control.
+  It's also possible to duplicate a reference context which has already been initialized, using ZSTD_copyCCtx()
+
+  Then, consume your input using ZSTD_compressContinue().
+  There are some important considerations to keep in mind when using this advanced function :
+  - ZSTD_compressContinue() has no internal buffer. It uses externally provided buffers only.
+  - Interface is synchronous : input is consumed entirely and produces 1+ compressed blocks.
+  - Caller must ensure there is enough space in `dst` to store compressed data under worst case scenario.
+    Worst case evaluation is provided by ZSTD_compressBound().
+    ZSTD_compressContinue() doesn't guarantee recover after a failed compression.
+  - ZSTD_compressContinue() presumes prior input ***is still accessible and unmodified*** (up to maximum distance size, see WindowLog).
+    It remembers all previous contiguous blocks, plus one separated memory segment (which can itself consists of multiple contiguous blocks)
+  - ZSTD_compressContinue() detects that prior input has been overwritten when `src` buffer overlaps.
+    In which case, it will "discard" the relevant memory section from its history.
+
+  Finish a frame with ZSTD_compressEnd(), which will write the last block(s) and optional checksum.
+  It's possible to use srcSize==0, in which case, it will write a final empty block to end the frame.
+  Without last block mark, frames are considered unfinished (hence corrupted) by compliant decoders.
+
+  `ZSTD_CCtx` object can be re-used (ZSTD_compressBegin()) to compress again.
+*/
+
+/*=====   Buffer-less streaming compression functions  =====*/
+ZSTDLIB_API size_t ZSTD_compressBegin(ZSTD_CCtx* cctx, int compressionLevel);
+ZSTDLIB_API size_t ZSTD_compressBegin_usingDict(ZSTD_CCtx* cctx, const void* dict, size_t dictSize, int compressionLevel);
+ZSTDLIB_API size_t ZSTD_compressBegin_advanced(ZSTD_CCtx* cctx, const void* dict, size_t dictSize, ZSTD_parameters params, unsigned long long pledgedSrcSize); /*< pledgedSrcSize : If srcSize is not known at init time, use ZSTD_CONTENTSIZE_UNKNOWN */
+ZSTDLIB_API size_t ZSTD_compressBegin_usingCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict); /*< note: fails if cdict==NULL */
+ZSTDLIB_API size_t ZSTD_compressBegin_usingCDict_advanced(ZSTD_CCtx* const cctx, const ZSTD_CDict* const cdict, ZSTD_frameParameters const fParams, unsigned long long const pledgedSrcSize);   /* compression parameters are already set within cdict. pledgedSrcSize must be correct. If srcSize is not known, use macro ZSTD_CONTENTSIZE_UNKNOWN */
+ZSTDLIB_API size_t ZSTD_copyCCtx(ZSTD_CCtx* cctx, const ZSTD_CCtx* preparedCCtx, unsigned long long pledgedSrcSize); /*<  note: if pledgedSrcSize is not known, use ZSTD_CONTENTSIZE_UNKNOWN */
+
+ZSTDLIB_API size_t ZSTD_compressContinue(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize);
+ZSTDLIB_API size_t ZSTD_compressEnd(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize);
+
+
+/*
+  Buffer-less streaming decompression (synchronous mode)
+
+  A ZSTD_DCtx object is required to track streaming operations.
+  Use ZSTD_createDCtx() / ZSTD_freeDCtx() to manage it.
+  A ZSTD_DCtx object can be re-used multiple times.
+
+  First typical operation is to retrieve frame parameters, using ZSTD_getFrameHeader().
+  Frame header is extracted from the beginning of compressed frame, so providing only the frame's beginning is enough.
+  Data fragment must be large enough to ensure successful decoding.
+ `ZSTD_frameHeaderSize_max` bytes is guaranteed to always be large enough.
+  @result : 0 : successful decoding, the `ZSTD_frameHeader` structure is correctly filled.
+           >0 : `srcSize` is too small, please provide at least @result bytes on next attempt.
+           errorCode, which can be tested using ZSTD_isError().
+
+  It fills a ZSTD_frameHeader structure with important information to correctly decode the frame,
+  such as the dictionary ID, content size, or maximum back-reference distance (`windowSize`).
+  Note that these values could be wrong, either because of data corruption, or because a 3rd party deliberately spoofs false information.
+  As a consequence, check that values remain within valid application range.
+  For example, do not allocate memory blindly, check that `windowSize` is within expectation.
+  Each application can set its own limits, depending on local restrictions.
+  For extended interoperability, it is recommended to support `windowSize` of at least 8 MB.
+
+  ZSTD_decompressContinue() needs previous data blocks during decompression, up to `windowSize` bytes.
+  ZSTD_decompressContinue() is very sensitive to contiguity,
+  if 2 blocks don't follow each other, make sure that either the compressor breaks contiguity at the same place,
+  or that previous contiguous segment is large enough to properly handle maximum back-reference distance.
+  There are multiple ways to guarantee this condition.
+
+  The most memory efficient way is to use a round buffer of sufficient size.
+  Sufficient size is determined by invoking ZSTD_decodingBufferSize_min(),
+  which can @return an error code if required value is too large for current system (in 32-bits mode).
+  In a round buffer methodology, ZSTD_decompressContinue() decompresses each block next to previous one,
+  up to the moment there is not enough room left in the buffer to guarantee decoding another full block,
+  which maximum size is provided in `ZSTD_frameHeader` structure, field `blockSizeMax`.
+  At which point, decoding can resume from the beginning of the buffer.
+  Note that already decoded data stored in the buffer should be flushed before being overwritten.
+
+  There are alternatives possible, for example using two or more buffers of size `windowSize` each, though they consume more memory.
+
+  Finally, if you control the compression process, you can also ignore all buffer size rules,
+  as long as the encoder and decoder progress in "lock-step",
+  aka use exactly the same buffer sizes, break contiguity at the same place, etc.
+
+  Once buffers are setup, start decompression, with ZSTD_decompressBegin().
+  If decompression requires a dictionary, use ZSTD_decompressBegin_usingDict() or ZSTD_decompressBegin_usingDDict().
+
+  Then use ZSTD_nextSrcSizeToDecompress() and ZSTD_decompressContinue() alternatively.
+  ZSTD_nextSrcSizeToDecompress() tells how many bytes to provide as 'srcSize' to ZSTD_decompressContinue().
+  ZSTD_decompressContinue() requires this _exact_ amount of bytes, or it will fail.
+
+ @result of ZSTD_decompressContinue() is the number of bytes regenerated within 'dst' (necessarily <= dstCapacity).
+  It can be zero : it just means ZSTD_decompressContinue() has decoded some metadata item.
+  It can also be an error code, which can be tested with ZSTD_isError().
+
+  A frame is fully decoded when ZSTD_nextSrcSizeToDecompress() returns zero.
+  Context can then be reset to start a new decompression.
+
+  Note : it's possible to know if next input to present is a header or a block, using ZSTD_nextInputType().
+  This information is not required to properly decode a frame.
+
+  == Special case : skippable frames ==
+
+  Skippable frames allow integration of user-defined data into a flow of concatenated frames.
+  Skippable frames will be ignored (skipped) by decompressor.
+  The format of skippable frames is as follows :
+  a) Skippable frame ID - 4 Bytes, Little endian format, any value from 0x184D2A50 to 0x184D2A5F
+  b) Frame Size - 4 Bytes, Little endian format, unsigned 32-bits
+  c) Frame Content - any content (User Data) of length equal to Frame Size
+  For skippable frames ZSTD_getFrameHeader() returns zfhPtr->frameType==ZSTD_skippableFrame.
+  For skippable frames ZSTD_decompressContinue() always returns 0 : it only skips the content.
+*/
+
+/*=====   Buffer-less streaming decompression functions  =====*/
+typedef enum { ZSTD_frame, ZSTD_skippableFrame } ZSTD_frameType_e;
+typedef struct {
+    unsigned long long frameContentSize; /* if == ZSTD_CONTENTSIZE_UNKNOWN, it means this field is not available. 0 means "empty" */
+    unsigned long long windowSize;       /* can be very large, up to <= frameContentSize */
+    unsigned blockSizeMax;
+    ZSTD_frameType_e frameType;          /* if == ZSTD_skippableFrame, frameContentSize is the size of skippable content */
+    unsigned headerSize;
+    unsigned dictID;
+    unsigned checksumFlag;
+} ZSTD_frameHeader;
+
+/*! ZSTD_getFrameHeader() :
+ *  decode Frame Header, or requires larger `srcSize`.
+ * @return : 0, `zfhPtr` is correctly filled,
+ *          >0, `srcSize` is too small, value is wanted `srcSize` amount,
+ *           or an error code, which can be tested using ZSTD_isError() */
+ZSTDLIB_API size_t ZSTD_getFrameHeader(ZSTD_frameHeader* zfhPtr, const void* src, size_t srcSize);   /*< doesn't consume input */
+/*! ZSTD_getFrameHeader_advanced() :
+ *  same as ZSTD_getFrameHeader(),
+ *  with added capability to select a format (like ZSTD_f_zstd1_magicless) */
+ZSTDLIB_API size_t ZSTD_getFrameHeader_advanced(ZSTD_frameHeader* zfhPtr, const void* src, size_t srcSize, ZSTD_format_e format);
+ZSTDLIB_API size_t ZSTD_decodingBufferSize_min(unsigned long long windowSize, unsigned long long frameContentSize);  /*< when frame content size is not known, pass in frameContentSize == ZSTD_CONTENTSIZE_UNKNOWN */
+
+ZSTDLIB_API size_t ZSTD_decompressBegin(ZSTD_DCtx* dctx);
+ZSTDLIB_API size_t ZSTD_decompressBegin_usingDict(ZSTD_DCtx* dctx, const void* dict, size_t dictSize);
+ZSTDLIB_API size_t ZSTD_decompressBegin_usingDDict(ZSTD_DCtx* dctx, const ZSTD_DDict* ddict);
+
+ZSTDLIB_API size_t ZSTD_nextSrcSizeToDecompress(ZSTD_DCtx* dctx);
+ZSTDLIB_API size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize);
+
+/* misc */
+ZSTDLIB_API void   ZSTD_copyDCtx(ZSTD_DCtx* dctx, const ZSTD_DCtx* preparedDCtx);
+typedef enum { ZSTDnit_frameHeader, ZSTDnit_blockHeader, ZSTDnit_block, ZSTDnit_lastBlock, ZSTDnit_checksum, ZSTDnit_skippableFrame } ZSTD_nextInputType_e;
+ZSTDLIB_API ZSTD_nextInputType_e ZSTD_nextInputType(ZSTD_DCtx* dctx);
+
+
+
+
+/* ============================ */
+/*       Block level API       */
+/* ============================ */
+
+/*!
+    Block functions produce and decode raw zstd blocks, without frame metadata.
+    Frame metadata cost is typically ~12 bytes, which can be non-negligible for very small blocks (< 100 bytes).
+    But users will have to take in charge needed metadata to regenerate data, such as compressed and content sizes.
+
+    A few rules to respect :
+    - Compressing and decompressing require a context structure
+      + Use ZSTD_createCCtx() and ZSTD_createDCtx()
+    - It is necessary to init context before starting
+      + compression : any ZSTD_compressBegin*() variant, including with dictionary
+      + decompression : any ZSTD_decompressBegin*() variant, including with dictionary
+      + copyCCtx() and copyDCtx() can be used too
+    - Block size is limited, it must be <= ZSTD_getBlockSize() <= ZSTD_BLOCKSIZE_MAX == 128 KB
+      + If input is larger than a block size, it's necessary to split input data into multiple blocks
+      + For inputs larger than a single block, consider using regular ZSTD_compress() instead.
+        Frame metadata is not that costly, and quickly becomes negligible as source size grows larger than a block.
+    - When a block is considered not compressible enough, ZSTD_compressBlock() result will be 0 (zero) !
+      ===> In which case, nothing is produced into `dst` !
+      + User __must__ test for such outcome and deal directly with uncompressed data
+      + A block cannot be declared incompressible if ZSTD_compressBlock() return value was != 0.
+        Doing so would mess up with statistics history, leading to potential data corruption.
+      + ZSTD_decompressBlock() _doesn't accept uncompressed data as input_ !!
+      + In case of multiple successive blocks, should some of them be uncompressed,
+        decoder must be informed of their existence in order to follow proper history.
+        Use ZSTD_insertBlock() for such a case.
+*/
+
+/*=====   Raw zstd block functions  =====*/
+ZSTDLIB_API size_t ZSTD_getBlockSize   (const ZSTD_CCtx* cctx);
+ZSTDLIB_API size_t ZSTD_compressBlock  (ZSTD_CCtx* cctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize);
+ZSTDLIB_API size_t ZSTD_decompressBlock(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize);
+ZSTDLIB_API size_t ZSTD_insertBlock    (ZSTD_DCtx* dctx, const void* blockStart, size_t blockSize);  /*< insert uncompressed block into `dctx` history. Useful for multi-blocks decompression. */
+
+
+#endif   /* ZSTD_H_ZSTD_STATIC_LINKING_ONLY */
+
diff --git a/include/net/bond_alb.h b/include/net/bond_alb.h
index f6af76c87a6c..191c36afa1f4 100644
--- a/include/net/bond_alb.h
+++ b/include/net/bond_alb.h
@@ -126,7 +126,7 @@ struct tlb_slave_info {
 struct alb_bond_info {
 	struct tlb_client_info	*tx_hashtbl; /* Dynamically allocated */
 	u32			unbalanced_load;
-	int			tx_rebalance_counter;
+	atomic_t		tx_rebalance_counter;
 	int			lp_counter;
 	/* -------- rlb parameters -------- */
 	int rlb_enabled;
diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h
index 4202c609bb0b..c4898fcbf923 100644
--- a/include/net/busy_poll.h
+++ b/include/net/busy_poll.h
@@ -133,6 +133,19 @@ static inline void sk_mark_napi_id(struct sock *sk, const struct sk_buff *skb)
 	if (unlikely(READ_ONCE(sk->sk_napi_id) != skb->napi_id))
 		WRITE_ONCE(sk->sk_napi_id, skb->napi_id);
 #endif
+	sk_rx_queue_update(sk, skb);
+}
+
+/* Variant of sk_mark_napi_id() for passive flow setup,
+ * as sk->sk_napi_id and sk->sk_rx_queue_mapping content
+ * needs to be set.
+ */
+static inline void sk_mark_napi_id_set(struct sock *sk,
+				       const struct sk_buff *skb)
+{
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	WRITE_ONCE(sk->sk_napi_id, skb->napi_id);
+#endif
 	sk_rx_queue_set(sk, skb);
 }
 
diff --git a/include/net/dst_cache.h b/include/net/dst_cache.h
index 67634675e919..df6622a5fe98 100644
--- a/include/net/dst_cache.h
+++ b/include/net/dst_cache.h
@@ -80,6 +80,17 @@ static inline void dst_cache_reset(struct dst_cache *dst_cache)
 }
 
 /**
+ *	dst_cache_reset_now - invalidate the cache contents immediately
+ *	@dst_cache: the cache
+ *
+ *	The caller must be sure there are no concurrent users, as this frees
+ *	all dst_cache users immediately, rather than waiting for the next
+ *	per-cpu usage like dst_cache_reset does. Most callers should use the
+ *	higher speed lazily-freed dst_cache_reset function instead.
+ */
+void dst_cache_reset_now(struct dst_cache *dst_cache);
+
+/**
  *	dst_cache_init - initialize the cache, allocating the required storage
  *	@dst_cache: the cache
  *	@gfp: allocation flags
diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h
index 4b10676c69d1..bd07484ab9dd 100644
--- a/include/net/fib_rules.h
+++ b/include/net/fib_rules.h
@@ -69,7 +69,7 @@ struct fib_rules_ops {
 	int			(*action)(struct fib_rule *,
 					  struct flowi *, int,
 					  struct fib_lookup_arg *);
-	bool			(*suppress)(struct fib_rule *,
+	bool			(*suppress)(struct fib_rule *, int,
 					    struct fib_lookup_arg *);
 	int			(*match)(struct fib_rule *,
 					 struct flowi *, int);
@@ -218,7 +218,9 @@ INDIRECT_CALLABLE_DECLARE(int fib4_rule_action(struct fib_rule *rule,
 			    struct fib_lookup_arg *arg));
 
 INDIRECT_CALLABLE_DECLARE(bool fib6_rule_suppress(struct fib_rule *rule,
+						int flags,
 						struct fib_lookup_arg *arg));
 INDIRECT_CALLABLE_DECLARE(bool fib4_rule_suppress(struct fib_rule *rule,
+						int flags,
 						struct fib_lookup_arg *arg));
 #endif
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index c412dde4d67d..83b8070d1cc9 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -485,6 +485,7 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh,
 		 struct fib6_config *cfg, gfp_t gfp_flags,
 		 struct netlink_ext_ack *extack);
 void fib6_nh_release(struct fib6_nh *fib6_nh);
+void fib6_nh_release_dsts(struct fib6_nh *fib6_nh);
 
 int call_fib6_entry_notifiers(struct net *net,
 			      enum fib_event_type event_type,
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index ab5348e57db1..3417ba2d27ad 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -438,7 +438,7 @@ int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
 #ifdef CONFIG_IP_ROUTE_CLASSID
 static inline int fib_num_tclassid_users(struct net *net)
 {
-	return net->ipv4.fib_num_tclassid_users;
+	return atomic_read(&net->ipv4.fib_num_tclassid_users);
 }
 #else
 static inline int fib_num_tclassid_users(struct net *net)
diff --git a/include/net/ipv6_stubs.h b/include/net/ipv6_stubs.h
index afbce90c4480..45e0339be6fa 100644
--- a/include/net/ipv6_stubs.h
+++ b/include/net/ipv6_stubs.h
@@ -47,6 +47,7 @@ struct ipv6_stub {
 			    struct fib6_config *cfg, gfp_t gfp_flags,
 			    struct netlink_ext_ack *extack);
 	void (*fib6_nh_release)(struct fib6_nh *fib6_nh);
+	void (*fib6_nh_release_dsts)(struct fib6_nh *fib6_nh);
 	void (*fib6_update_sernum)(struct net *net, struct fib6_info *rt);
 	int (*ip6_del_rt)(struct net *net, struct fib6_info *rt, bool skip_notify);
 	void (*fib6_rt_update)(struct net *net, struct fib6_info *rt,
diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index cc663c68ddc4..d24b0a34c8f0 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -276,14 +276,14 @@ static inline bool nf_is_loopback_packet(const struct sk_buff *skb)
 /* jiffies until ct expires, 0 if already expired */
 static inline unsigned long nf_ct_expires(const struct nf_conn *ct)
 {
-	s32 timeout = ct->timeout - nfct_time_stamp;
+	s32 timeout = READ_ONCE(ct->timeout) - nfct_time_stamp;
 
 	return timeout > 0 ? timeout : 0;
 }
 
 static inline bool nf_ct_is_expired(const struct nf_conn *ct)
 {
-	return (__s32)(ct->timeout - nfct_time_stamp) <= 0;
+	return (__s32)(READ_ONCE(ct->timeout) - nfct_time_stamp) <= 0;
 }
 
 /* use after obtaining a reference count */
@@ -302,7 +302,7 @@ static inline bool nf_ct_should_gc(const struct nf_conn *ct)
 static inline void nf_ct_offload_timeout(struct nf_conn *ct)
 {
 	if (nf_ct_expires(ct) < NF_CT_DAY / 2)
-		ct->timeout = nfct_time_stamp + NF_CT_DAY;
+		WRITE_ONCE(ct->timeout, nfct_time_stamp + NF_CT_DAY);
 }
 
 struct kernel_param;
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 2f65701a43c9..6c5b2efc4f17 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -65,7 +65,7 @@ struct netns_ipv4 {
 	bool			fib_has_custom_local_routes;
 	bool			fib_offload_disabled;
 #ifdef CONFIG_IP_ROUTE_CLASSID
-	int			fib_num_tclassid_users;
+	atomic_t		fib_num_tclassid_users;
 #endif
 	struct hlist_head	*fib_table_hash;
 	struct sock		*fibnl;
diff --git a/include/net/nfc/nci_core.h b/include/net/nfc/nci_core.h
index a964daedc17b..ea8595651c38 100644
--- a/include/net/nfc/nci_core.h
+++ b/include/net/nfc/nci_core.h
@@ -30,6 +30,7 @@ enum nci_flag {
 	NCI_UP,
 	NCI_DATA_EXCHANGE,
 	NCI_DATA_EXCHANGE_TO,
+	NCI_UNREG,
 };
 
 /* NCI device states */
diff --git a/include/net/nl802154.h b/include/net/nl802154.h
index ddcee128f5d9..145acb8f2509 100644
--- a/include/net/nl802154.h
+++ b/include/net/nl802154.h
@@ -19,6 +19,8 @@
  *
  */
 
+#include <linux/types.h>
+
 #define NL802154_GENL_NAME "nl802154"
 
 enum nl802154_commands {
@@ -150,10 +152,9 @@ enum nl802154_attrs {
 };
 
 enum nl802154_iftype {
-	/* for backwards compatibility TODO */
-	NL802154_IFTYPE_UNSPEC = -1,
+	NL802154_IFTYPE_UNSPEC = (~(__u32)0),
 
-	NL802154_IFTYPE_NODE,
+	NL802154_IFTYPE_NODE = 0,
 	NL802154_IFTYPE_MONITOR,
 	NL802154_IFTYPE_COORD,
 
diff --git a/include/net/page_pool.h b/include/net/page_pool.h
index 3855f069627f..a4082406a003 100644
--- a/include/net/page_pool.h
+++ b/include/net/page_pool.h
@@ -216,14 +216,24 @@ static inline void page_pool_recycle_direct(struct page_pool *pool,
 	page_pool_put_full_page(pool, page, true);
 }
 
+#define PAGE_POOL_DMA_USE_PP_FRAG_COUNT	\
+		(sizeof(dma_addr_t) > sizeof(unsigned long))
+
 static inline dma_addr_t page_pool_get_dma_addr(struct page *page)
 {
-	return page->dma_addr;
+	dma_addr_t ret = page->dma_addr;
+
+	if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT)
+		ret |= (dma_addr_t)page->dma_addr_upper << 16 << 16;
+
+	return ret;
 }
 
 static inline void page_pool_set_dma_addr(struct page *page, dma_addr_t addr)
 {
 	page->dma_addr = addr;
+	if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT)
+		page->dma_addr_upper = upper_32_bits(addr);
 }
 
 static inline void page_pool_set_frag_count(struct page *page, long nr)
diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h
index bf79f3a890af..9e71691c491b 100644
--- a/include/net/pkt_sched.h
+++ b/include/net/pkt_sched.h
@@ -193,4 +193,20 @@ static inline void skb_txtime_consumed(struct sk_buff *skb)
 	skb->tstamp = ktime_set(0, 0);
 }
 
+struct tc_skb_cb {
+	struct qdisc_skb_cb qdisc_cb;
+
+	u16 mru;
+	bool post_ct;
+	u16 zone; /* Only valid if post_ct = true */
+};
+
+static inline struct tc_skb_cb *tc_skb_cb(const struct sk_buff *skb)
+{
+	struct tc_skb_cb *cb = (struct tc_skb_cb *)skb->cb;
+
+	BUILD_BUG_ON(sizeof(*cb) > sizeof_field(struct sk_buff, cb));
+	return cb;
+}
+
 #endif
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 22179b2fda72..c70e6d2b2fdd 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -447,8 +447,6 @@ struct qdisc_skb_cb {
 	};
 #define QDISC_CB_PRIV_LEN 20
 	unsigned char		data[QDISC_CB_PRIV_LEN];
-	u16			mru;
-	bool			post_ct;
 };
 
 typedef void tcf_chain_head_change_t(struct tcf_proto *tp_head, void *priv);
diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index 189fdb9db162..3ae61ce2eabd 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -105,19 +105,18 @@ extern struct percpu_counter sctp_sockets_allocated;
 int sctp_asconf_mgmt(struct sctp_sock *, struct sctp_sockaddr_entry *);
 struct sk_buff *sctp_skb_recv_datagram(struct sock *, int, int, int *);
 
+typedef int (*sctp_callback_t)(struct sctp_endpoint *, struct sctp_transport *, void *);
 void sctp_transport_walk_start(struct rhashtable_iter *iter);
 void sctp_transport_walk_stop(struct rhashtable_iter *iter);
 struct sctp_transport *sctp_transport_get_next(struct net *net,
 			struct rhashtable_iter *iter);
 struct sctp_transport *sctp_transport_get_idx(struct net *net,
 			struct rhashtable_iter *iter, int pos);
-int sctp_transport_lookup_process(int (*cb)(struct sctp_transport *, void *),
-				  struct net *net,
+int sctp_transport_lookup_process(sctp_callback_t cb, struct net *net,
 				  const union sctp_addr *laddr,
 				  const union sctp_addr *paddr, void *p);
-int sctp_for_each_transport(int (*cb)(struct sctp_transport *, void *),
-			    int (*cb_done)(struct sctp_transport *, void *),
-			    struct net *net, int *pos, void *p);
+int sctp_transport_traverse_process(sctp_callback_t cb, sctp_callback_t cb_done,
+				    struct net *net, int *pos, void *p);
 int sctp_for_each_endpoint(int (*cb)(struct sctp_endpoint *, void *), void *p);
 int sctp_get_sctp_info(struct sock *sk, struct sctp_association *asoc,
 		       struct sctp_info *info);
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 899c29c326ba..8dabd8800006 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -1355,6 +1355,7 @@ struct sctp_endpoint {
 	      reconf_enable:1;
 
 	__u8  strreset_enable;
+	struct rcu_head rcu;
 };
 
 /* Recover the outter endpoint structure. */
@@ -1370,7 +1371,7 @@ static inline struct sctp_endpoint *sctp_ep(struct sctp_ep_common *base)
 struct sctp_endpoint *sctp_endpoint_new(struct sock *, gfp_t);
 void sctp_endpoint_free(struct sctp_endpoint *);
 void sctp_endpoint_put(struct sctp_endpoint *);
-void sctp_endpoint_hold(struct sctp_endpoint *);
+int sctp_endpoint_hold(struct sctp_endpoint *ep);
 void sctp_endpoint_add_asoc(struct sctp_endpoint *, struct sctp_association *);
 struct sctp_association *sctp_endpoint_lookup_assoc(
 	const struct sctp_endpoint *ep,
diff --git a/include/net/sock.h b/include/net/sock.h
index b32906e1ab55..d47e9658da28 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -431,7 +431,7 @@ struct sock {
 #ifdef CONFIG_XFRM
 	struct xfrm_policy __rcu *sk_policy[2];
 #endif
-	struct dst_entry	*sk_rx_dst;
+	struct dst_entry __rcu	*sk_rx_dst;
 	int			sk_rx_dst_ifindex;
 	u32			sk_rx_dst_cookie;
 
@@ -1913,18 +1913,31 @@ static inline int sk_tx_queue_get(const struct sock *sk)
 	return -1;
 }
 
-static inline void sk_rx_queue_set(struct sock *sk, const struct sk_buff *skb)
+static inline void __sk_rx_queue_set(struct sock *sk,
+				     const struct sk_buff *skb,
+				     bool force_set)
 {
 #ifdef CONFIG_SOCK_RX_QUEUE_MAPPING
 	if (skb_rx_queue_recorded(skb)) {
 		u16 rx_queue = skb_get_rx_queue(skb);
 
-		if (unlikely(READ_ONCE(sk->sk_rx_queue_mapping) != rx_queue))
+		if (force_set ||
+		    unlikely(READ_ONCE(sk->sk_rx_queue_mapping) != rx_queue))
 			WRITE_ONCE(sk->sk_rx_queue_mapping, rx_queue);
 	}
 #endif
 }
 
+static inline void sk_rx_queue_set(struct sock *sk, const struct sk_buff *skb)
+{
+	__sk_rx_queue_set(sk, skb, true);
+}
+
+static inline void sk_rx_queue_update(struct sock *sk, const struct sk_buff *skb)
+{
+	__sk_rx_queue_set(sk, skb, false);
+}
+
 static inline void sk_rx_queue_clear(struct sock *sk)
 {
 #ifdef CONFIG_SOCK_RX_QUEUE_MAPPING
@@ -2430,19 +2443,22 @@ static inline void sk_stream_moderate_sndbuf(struct sock *sk)
  * @sk: socket
  *
  * Use the per task page_frag instead of the per socket one for
- * optimization when we know that we're in the normal context and owns
+ * optimization when we know that we're in process context and own
  * everything that's associated with %current.
  *
- * gfpflags_allow_blocking() isn't enough here as direct reclaim may nest
- * inside other socket operations and end up recursing into sk_page_frag()
- * while it's already in use.
+ * Both direct reclaim and page faults can nest inside other
+ * socket operations and end up recursing into sk_page_frag()
+ * while it's already in use: explicitly avoid task page_frag
+ * usage if the caller is potentially doing any of them.
+ * This assumes that page fault handlers use the GFP_NOFS flags.
  *
  * Return: a per task page_frag if context allows that,
  * otherwise a per socket one.
  */
 static inline struct page_frag *sk_page_frag(struct sock *sk)
 {
-	if (gfpflags_normal_context(sk->sk_allocation))
+	if ((sk->sk_allocation & (__GFP_DIRECT_RECLAIM | __GFP_MEMALLOC | __GFP_FS)) ==
+	    (__GFP_DIRECT_RECLAIM | __GFP_FS))
 		return &current->task_frag;
 
 	return &sk->sk_frag;
diff --git a/include/rdma/rdma_netlink.h b/include/rdma/rdma_netlink.h
index 2758d9df71ee..c2a79aeee113 100644
--- a/include/rdma/rdma_netlink.h
+++ b/include/rdma/rdma_netlink.h
@@ -30,7 +30,7 @@ enum rdma_nl_flags {
  * constant as well and the compiler checks they are the same.
  */
 #define MODULE_ALIAS_RDMA_NETLINK(_index, _val)                                \
-	static inline void __chk_##_index(void)                                \
+	static inline void __maybe_unused __chk_##_index(void)                 \
 	{                                                                      \
 		BUILD_BUG_ON(_index != _val);                                  \
 	}                                                                      \
diff --git a/include/soc/mscc/ocelot_vcap.h b/include/soc/mscc/ocelot_vcap.h
index eeb1142aa1b1..4d1dfa1136b2 100644
--- a/include/soc/mscc/ocelot_vcap.h
+++ b/include/soc/mscc/ocelot_vcap.h
@@ -703,6 +703,8 @@ int ocelot_vcap_filter_add(struct ocelot *ocelot,
 			   struct netlink_ext_ack *extack);
 int ocelot_vcap_filter_del(struct ocelot *ocelot,
 			   struct ocelot_vcap_filter *rule);
+int ocelot_vcap_filter_replace(struct ocelot *ocelot,
+			       struct ocelot_vcap_filter *filter);
 struct ocelot_vcap_filter *
 ocelot_vcap_block_find_filter_by_id(struct ocelot_vcap_block *block,
 				    unsigned long cookie, bool tc_offload);
diff --git a/include/sound/soc-acpi.h b/include/sound/soc-acpi.h
index 31f4c4f9aeea..ac0893df9c76 100644
--- a/include/sound/soc-acpi.h
+++ b/include/sound/soc-acpi.h
@@ -147,7 +147,7 @@ struct snd_soc_acpi_link_adr {
  */
 /* Descriptor for SST ASoC machine driver */
 struct snd_soc_acpi_mach {
-	const u8 id[ACPI_ID_LEN];
+	u8 id[ACPI_ID_LEN];
 	const struct snd_soc_acpi_codecs *comp_ids;
 	const u32 link_mask;
 	const struct snd_soc_acpi_link_adr *links;
diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h
index bca73e8c8cde..499f5fabd20f 100644
--- a/include/trace/events/afs.h
+++ b/include/trace/events/afs.h
@@ -1016,31 +1016,32 @@ TRACE_EVENT(afs_dir_check_failed,
 		      __entry->vnode, __entry->off, __entry->i_size)
 	    );
 
-TRACE_EVENT(afs_page_dirty,
-	    TP_PROTO(struct afs_vnode *vnode, const char *where, struct page *page),
+TRACE_EVENT(afs_folio_dirty,
+	    TP_PROTO(struct afs_vnode *vnode, const char *where, struct folio *folio),
 
-	    TP_ARGS(vnode, where, page),
+	    TP_ARGS(vnode, where, folio),
 
 	    TP_STRUCT__entry(
 		    __field(struct afs_vnode *,		vnode		)
 		    __field(const char *,		where		)
-		    __field(pgoff_t,			page		)
+		    __field(pgoff_t,			index		)
 		    __field(unsigned long,		from		)
 		    __field(unsigned long,		to		)
 			     ),
 
 	    TP_fast_assign(
+		    unsigned long priv = (unsigned long)folio_get_private(folio);
 		    __entry->vnode = vnode;
 		    __entry->where = where;
-		    __entry->page = page->index;
-		    __entry->from = afs_page_dirty_from(page, page->private);
-		    __entry->to = afs_page_dirty_to(page, page->private);
-		    __entry->to |= (afs_is_page_dirty_mmapped(page->private) ?
-				    (1UL << (BITS_PER_LONG - 1)) : 0);
+		    __entry->index = folio_index(folio);
+		    __entry->from  = afs_folio_dirty_from(folio, priv);
+		    __entry->to    = afs_folio_dirty_to(folio, priv);
+		    __entry->to   |= (afs_is_folio_dirty_mmapped(priv) ?
+				      (1UL << (BITS_PER_LONG - 1)) : 0);
 			   ),
 
 	    TP_printk("vn=%p %lx %s %lx-%lx%s",
-		      __entry->vnode, __entry->page, __entry->where,
+		      __entry->vnode, __entry->index, __entry->where,
 		      __entry->from,
 		      __entry->to & ~(1UL << (BITS_PER_LONG - 1)),
 		      __entry->to & (1UL << (BITS_PER_LONG - 1)) ? " M" : "")
diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h
index 4e881d91c874..f8cb916f3595 100644
--- a/include/trace/events/f2fs.h
+++ b/include/trace/events/f2fs.h
@@ -570,9 +570,10 @@ TRACE_EVENT(f2fs_file_write_iter,
 );
 
 TRACE_EVENT(f2fs_map_blocks,
-	TP_PROTO(struct inode *inode, struct f2fs_map_blocks *map, int ret),
+	TP_PROTO(struct inode *inode, struct f2fs_map_blocks *map,
+				int create, int flag, int ret),
 
-	TP_ARGS(inode, map, ret),
+	TP_ARGS(inode, map, create, flag, ret),
 
 	TP_STRUCT__entry(
 		__field(dev_t,	dev)
@@ -583,11 +584,14 @@ TRACE_EVENT(f2fs_map_blocks,
 		__field(unsigned int,	m_flags)
 		__field(int,	m_seg_type)
 		__field(bool,	m_may_create)
+		__field(bool,	m_multidev_dio)
+		__field(int,	create)
+		__field(int,	flag)
 		__field(int,	ret)
 	),
 
 	TP_fast_assign(
-		__entry->dev		= inode->i_sb->s_dev;
+		__entry->dev		= map->m_bdev->bd_dev;
 		__entry->ino		= inode->i_ino;
 		__entry->m_lblk		= map->m_lblk;
 		__entry->m_pblk		= map->m_pblk;
@@ -595,12 +599,16 @@ TRACE_EVENT(f2fs_map_blocks,
 		__entry->m_flags	= map->m_flags;
 		__entry->m_seg_type	= map->m_seg_type;
 		__entry->m_may_create	= map->m_may_create;
+		__entry->m_multidev_dio	= map->m_multidev_dio;
+		__entry->create		= create;
+		__entry->flag		= flag;
 		__entry->ret		= ret;
 	),
 
 	TP_printk("dev = (%d,%d), ino = %lu, file offset = %llu, "
-		"start blkaddr = 0x%llx, len = 0x%llx, flags = %u,"
-		"seg_type = %d, may_create = %d, err = %d",
+		"start blkaddr = 0x%llx, len = 0x%llx, flags = %u, "
+		"seg_type = %d, may_create = %d, multidevice = %d, "
+		"create = %d, flag = %d, err = %d",
 		show_dev_ino(__entry),
 		(unsigned long long)__entry->m_lblk,
 		(unsigned long long)__entry->m_pblk,
@@ -608,6 +616,9 @@ TRACE_EVENT(f2fs_map_blocks,
 		__entry->m_flags,
 		__entry->m_seg_type,
 		__entry->m_may_create,
+		__entry->m_multidev_dio,
+		__entry->create,
+		__entry->flag,
 		__entry->ret)
 );
 
@@ -807,20 +818,20 @@ TRACE_EVENT(f2fs_lookup_start,
 	TP_STRUCT__entry(
 		__field(dev_t,	dev)
 		__field(ino_t,	ino)
-		__field(const char *,	name)
+		__string(name,	dentry->d_name.name)
 		__field(unsigned int, flags)
 	),
 
 	TP_fast_assign(
 		__entry->dev	= dir->i_sb->s_dev;
 		__entry->ino	= dir->i_ino;
-		__entry->name	= dentry->d_name.name;
+		__assign_str(name, dentry->d_name.name);
 		__entry->flags	= flags;
 	),
 
 	TP_printk("dev = (%d,%d), pino = %lu, name:%s, flags:%u",
 		show_dev_ino(__entry),
-		__entry->name,
+		__get_str(name),
 		__entry->flags)
 );
 
@@ -834,7 +845,7 @@ TRACE_EVENT(f2fs_lookup_end,
 	TP_STRUCT__entry(
 		__field(dev_t,	dev)
 		__field(ino_t,	ino)
-		__field(const char *,	name)
+		__string(name,	dentry->d_name.name)
 		__field(nid_t,	cino)
 		__field(int,	err)
 	),
@@ -842,14 +853,14 @@ TRACE_EVENT(f2fs_lookup_end,
 	TP_fast_assign(
 		__entry->dev	= dir->i_sb->s_dev;
 		__entry->ino	= dir->i_ino;
-		__entry->name	= dentry->d_name.name;
+		__assign_str(name, dentry->d_name.name);
 		__entry->cino	= ino;
 		__entry->err	= err;
 	),
 
 	TP_printk("dev = (%d,%d), pino = %lu, name:%s, ino:%u, err:%d",
 		show_dev_ino(__entry),
-		__entry->name,
+		__get_str(name),
 		__entry->cino,
 		__entry->err)
 );
diff --git a/include/trace/events/rpcgss.h b/include/trace/events/rpcgss.h
index 3ba63319af3c..c9048f3e471b 100644
--- a/include/trace/events/rpcgss.h
+++ b/include/trace/events/rpcgss.h
@@ -8,7 +8,7 @@
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM rpcgss
 
-#if !defined(_TRACE_RPCRDMA_H) || defined(TRACE_HEADER_MULTI_READ)
+#if !defined(_TRACE_RPCGSS_H) || defined(TRACE_HEADER_MULTI_READ)
 #define _TRACE_RPCGSS_H
 
 #include <linux/tracepoint.h>
diff --git a/include/uapi/asm-generic/poll.h b/include/uapi/asm-generic/poll.h
index 41b509f410bf..f9c520ce4bf4 100644
--- a/include/uapi/asm-generic/poll.h
+++ b/include/uapi/asm-generic/poll.h
@@ -29,7 +29,7 @@
 #define POLLRDHUP       0x2000
 #endif
 
-#define POLLFREE	(__force __poll_t)0x4000	/* currently only for epoll */
+#define POLLFREE	(__force __poll_t)0x4000
 
 #define POLL_BUSY_LOOP	(__force __poll_t)0x8000
 
diff --git a/include/uapi/drm/virtgpu_drm.h b/include/uapi/drm/virtgpu_drm.h
index a13e20cc66b4..0512fde5e697 100644
--- a/include/uapi/drm/virtgpu_drm.h
+++ b/include/uapi/drm/virtgpu_drm.h
@@ -196,6 +196,13 @@ struct drm_virtgpu_context_init {
 	__u64 ctx_set_params;
 };
 
+/*
+ * Event code that's given when VIRTGPU_CONTEXT_PARAM_POLL_RINGS_MASK is in
+ * effect.  The event size is sizeof(drm_event), since there is no additional
+ * payload.
+ */
+#define VIRTGPU_EVENT_FENCE_SIGNALED 0x90000000
+
 #define DRM_IOCTL_VIRTGPU_MAP \
 	DRM_IOWR(DRM_COMMAND_BASE + DRM_VIRTGPU_MAP, struct drm_virtgpu_map)
 
diff --git a/include/uapi/linux/byteorder/big_endian.h b/include/uapi/linux/byteorder/big_endian.h
index 2199adc6a6c2..80aa5c41a763 100644
--- a/include/uapi/linux/byteorder/big_endian.h
+++ b/include/uapi/linux/byteorder/big_endian.h
@@ -9,6 +9,7 @@
 #define __BIG_ENDIAN_BITFIELD
 #endif
 
+#include <linux/stddef.h>
 #include <linux/types.h>
 #include <linux/swab.h>
 
diff --git a/include/uapi/linux/byteorder/little_endian.h b/include/uapi/linux/byteorder/little_endian.h
index 601c904fd5cd..cd98982e7523 100644
--- a/include/uapi/linux/byteorder/little_endian.h
+++ b/include/uapi/linux/byteorder/little_endian.h
@@ -9,6 +9,7 @@
 #define __LITTLE_ENDIAN_BITFIELD
 #endif
 
+#include <linux/stddef.h>
 #include <linux/types.h>
 #include <linux/swab.h>
 
diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h
index 5da4ee234e0b..c0c2f3ed5729 100644
--- a/include/uapi/linux/if_ether.h
+++ b/include/uapi/linux/if_ether.h
@@ -117,7 +117,7 @@
 #define ETH_P_IFE	0xED3E		/* ForCES inter-FE LFB type */
 #define ETH_P_AF_IUCV   0xFBFB		/* IBM af_iucv [ NOT AN OFFICIALLY REGISTERED ID ] */
 
-#define ETH_P_802_3_MIN	0x0600		/* If the value in the ethernet type is less than this value
+#define ETH_P_802_3_MIN	0x0600		/* If the value in the ethernet type is more than this value
 					 * then the frame is Ethernet II. Else it is 802.3 */
 
 /*
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 78f0719cc2a3..1daa45268de2 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -1130,6 +1130,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_BINARY_STATS_FD 203
 #define KVM_CAP_EXIT_ON_EMULATION_FAILURE 204
 #define KVM_CAP_ARM_MTE 205
+#define KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM 206
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h
index c8cc46f80a16..f106a3941cdf 100644
--- a/include/uapi/linux/mptcp.h
+++ b/include/uapi/linux/mptcp.h
@@ -136,19 +136,21 @@ struct mptcp_info {
  * MPTCP_EVENT_REMOVED: token, rem_id
  * An address has been lost by the peer.
  *
- * MPTCP_EVENT_SUB_ESTABLISHED: token, family, saddr4 | saddr6,
- *                              daddr4 | daddr6, sport, dport, backup,
- *                              if_idx [, error]
+ * MPTCP_EVENT_SUB_ESTABLISHED: token, family, loc_id, rem_id,
+ *                              saddr4 | saddr6, daddr4 | daddr6, sport,
+ *                              dport, backup, if_idx [, error]
  * A new subflow has been established. 'error' should not be set.
  *
- * MPTCP_EVENT_SUB_CLOSED: token, family, saddr4 | saddr6, daddr4 | daddr6,
- *                         sport, dport, backup, if_idx [, error]
+ * MPTCP_EVENT_SUB_CLOSED: token, family, loc_id, rem_id, saddr4 | saddr6,
+ *                         daddr4 | daddr6, sport, dport, backup, if_idx
+ *                         [, error]
  * A subflow has been closed. An error (copy of sk_err) could be set if an
  * error has been detected for this subflow.
  *
- * MPTCP_EVENT_SUB_PRIORITY: token, family, saddr4 | saddr6, daddr4 | daddr6,
- *                           sport, dport, backup, if_idx [, error]
- *       The priority of a subflow has changed. 'error' should not be set.
+ * MPTCP_EVENT_SUB_PRIORITY: token, family, loc_id, rem_id, saddr4 | saddr6,
+ *                           daddr4 | daddr6, sport, dport, backup, if_idx
+ *                           [, error]
+ * The priority of a subflow has changed. 'error' should not be set.
  */
 enum mptcp_event_type {
 	MPTCP_EVENT_UNSPEC = 0,
diff --git a/include/uapi/linux/nfc.h b/include/uapi/linux/nfc.h
index f6e3c8c9c744..4fa4e979e948 100644
--- a/include/uapi/linux/nfc.h
+++ b/include/uapi/linux/nfc.h
@@ -263,7 +263,7 @@ enum nfc_sdp_attr {
 #define NFC_SE_ENABLED  0x1
 
 struct sockaddr_nfc {
-	sa_family_t sa_family;
+	__kernel_sa_family_t sa_family;
 	__u32 dev_idx;
 	__u32 target_idx;
 	__u32 nfc_protocol;
@@ -271,14 +271,14 @@ struct sockaddr_nfc {
 
 #define NFC_LLCP_MAX_SERVICE_NAME 63
 struct sockaddr_nfc_llcp {
-	sa_family_t sa_family;
+	__kernel_sa_family_t sa_family;
 	__u32 dev_idx;
 	__u32 target_idx;
 	__u32 nfc_protocol;
 	__u8 dsap; /* Destination SAP, if known */
 	__u8 ssap; /* Source SAP to be bound to */
 	char service_name[NFC_LLCP_MAX_SERVICE_NAME]; /* Service name URI */;
-	size_t service_name_len;
+	__kernel_size_t service_name_len;
 };
 
 /* NFC socket protocols */
diff --git a/include/uapi/linux/resource.h b/include/uapi/linux/resource.h
index 74ef57b38f9f..ac5d6a3031db 100644
--- a/include/uapi/linux/resource.h
+++ b/include/uapi/linux/resource.h
@@ -66,10 +66,17 @@ struct rlimit64 {
 #define _STK_LIM	(8*1024*1024)
 
 /*
- * GPG2 wants 64kB of mlocked memory, to make sure pass phrases
- * and other sensitive information are never written to disk.
+ * Limit the amount of locked memory by some sane default:
+ * root can always increase this limit if needed.
+ *
+ * The main use-cases are (1) preventing sensitive memory
+ * from being swapped; (2) real-time operations; (3) via
+ * IOURING_REGISTER_BUFFERS.
+ *
+ * The first two don't need much. The latter will take as
+ * much as it can get. 8MB is a reasonably sane default.
  */
-#define MLOCK_LIMIT	((PAGE_SIZE > 64*1024) ? PAGE_SIZE : 64*1024)
+#define MLOCK_LIMIT	(8*1024*1024)
 
 /*
  * Due to binary compatibility, the actual resource numbers
diff --git a/include/uapi/linux/virtio_mem.h b/include/uapi/linux/virtio_mem.h
index 70e01c687d5e..e9122f1d0e0c 100644
--- a/include/uapi/linux/virtio_mem.h
+++ b/include/uapi/linux/virtio_mem.h
@@ -68,9 +68,10 @@
  * explicitly triggered (VIRTIO_MEM_REQ_UNPLUG).
  *
  * There are no guarantees what will happen if unplugged memory is
- * read/written. Such memory should, in general, not be touched. E.g.,
- * even writing might succeed, but the values will simply be discarded at
- * random points in time.
+ * read/written. In general, unplugged memory should not be touched, because
+ * the resulting action is undefined. There is one exception: without
+ * VIRTIO_MEM_F_UNPLUGGED_INACCESSIBLE, unplugged memory inside the usable
+ * region can be read, to simplify creation of memory dumps.
  *
  * It can happen that the device cannot process a request, because it is
  * busy. The device driver has to retry later.
@@ -87,6 +88,8 @@
 
 /* node_id is an ACPI PXM and is valid */
 #define VIRTIO_MEM_F_ACPI_PXM		0
+/* unplugged memory must not be accessed */
+#define VIRTIO_MEM_F_UNPLUGGED_INACCESSIBLE	1
 
 
 /* --- virtio-mem: guest -> host requests --- */
diff --git a/include/xen/events.h b/include/xen/events.h
index c204262d9fc2..344081e71584 100644
--- a/include/xen/events.h
+++ b/include/xen/events.h
@@ -17,6 +17,7 @@ struct xenbus_device;
 unsigned xen_evtchn_nr_channels(void);
 
 int bind_evtchn_to_irq(evtchn_port_t evtchn);
+int bind_evtchn_to_irq_lateeoi(evtchn_port_t evtchn);
 int bind_evtchn_to_irqhandler(evtchn_port_t evtchn,
 			      irq_handler_t handler,
 			      unsigned long irqflags, const char *devname,
diff --git a/include/xen/xenbus.h b/include/xen/xenbus.h
index b94074c82772..b13eb86395e0 100644
--- a/include/xen/xenbus.h
+++ b/include/xen/xenbus.h
@@ -112,6 +112,7 @@ struct xenbus_driver {
 	const char *name;       /* defaults to ids[0].devicetype */
 	const struct xenbus_device_id *ids;
 	bool allow_rebind; /* avoid setting xenstore closed during remove */
+	bool not_essential;     /* is not mandatory for boot progress */
 	int (*probe)(struct xenbus_device *dev,
 		     const struct xenbus_device_id *id);
 	void (*otherend_changed)(struct xenbus_device *dev,
diff --git a/init/Kconfig b/init/Kconfig
index 45bcaa8e7481..4b7bac10c72d 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -885,6 +885,11 @@ config ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
 config CC_HAS_INT128
 	def_bool !$(cc-option,$(m64-flag) -D__SIZEOF_INT128__=0) && 64BIT
 
+config CC_IMPLICIT_FALLTHROUGH
+	string
+	default "-Wimplicit-fallthrough=5" if CC_IS_GCC && $(cc-option,-Wimplicit-fallthrough=5)
+	default "-Wimplicit-fallthrough" if CC_IS_CLANG && $(cc-option,-Wunreachable-code-fallthrough)
+
 #
 # For architectures that know their GCC __int128 support is sound
 #
diff --git a/init/Makefile b/init/Makefile
index 2846113677ee..04eeee12c076 100644
--- a/init/Makefile
+++ b/init/Makefile
@@ -30,7 +30,7 @@ $(obj)/version.o: include/generated/compile.h
 quiet_cmd_compile.h = CHK     $@
       cmd_compile.h = \
 	$(CONFIG_SHELL) $(srctree)/scripts/mkcompile_h $@	\
-	"$(UTS_MACHINE)" "$(CONFIG_SMP)" "$(CONFIG_PREEMPT)"	\
+	"$(UTS_MACHINE)" "$(CONFIG_SMP)" "$(CONFIG_PREEMPT_BUILD)"	\
 	"$(CONFIG_PREEMPT_RT)" $(CONFIG_CC_VERSION_TEXT) "$(LD)"
 
 include/generated/compile.h: FORCE
diff --git a/ipc/shm.c b/ipc/shm.c
index 4942bdd65748..b3048ebd5c31 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -62,9 +62,18 @@ struct shmid_kernel /* private to the kernel */
 	struct pid		*shm_lprid;
 	struct ucounts		*mlock_ucounts;
 
-	/* The task created the shm object.  NULL if the task is dead. */
+	/*
+	 * The task created the shm object, for
+	 * task_lock(shp->shm_creator)
+	 */
 	struct task_struct	*shm_creator;
-	struct list_head	shm_clist;	/* list by creator */
+
+	/*
+	 * List by creator. task_lock(->shm_creator) required for read/write.
+	 * If list_empty(), then the creator is dead already.
+	 */
+	struct list_head	shm_clist;
+	struct ipc_namespace	*ns;
 } __randomize_layout;
 
 /* shm_mode upper byte flags */
@@ -115,6 +124,7 @@ static void do_shm_rmid(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
 	struct shmid_kernel *shp;
 
 	shp = container_of(ipcp, struct shmid_kernel, shm_perm);
+	WARN_ON(ns != shp->ns);
 
 	if (shp->shm_nattch) {
 		shp->shm_perm.mode |= SHM_DEST;
@@ -225,10 +235,43 @@ static void shm_rcu_free(struct rcu_head *head)
 	kfree(shp);
 }
 
-static inline void shm_rmid(struct ipc_namespace *ns, struct shmid_kernel *s)
+/*
+ * It has to be called with shp locked.
+ * It must be called before ipc_rmid()
+ */
+static inline void shm_clist_rm(struct shmid_kernel *shp)
 {
-	list_del(&s->shm_clist);
-	ipc_rmid(&shm_ids(ns), &s->shm_perm);
+	struct task_struct *creator;
+
+	/* ensure that shm_creator does not disappear */
+	rcu_read_lock();
+
+	/*
+	 * A concurrent exit_shm may do a list_del_init() as well.
+	 * Just do nothing if exit_shm already did the work
+	 */
+	if (!list_empty(&shp->shm_clist)) {
+		/*
+		 * shp->shm_creator is guaranteed to be valid *only*
+		 * if shp->shm_clist is not empty.
+		 */
+		creator = shp->shm_creator;
+
+		task_lock(creator);
+		/*
+		 * list_del_init() is a nop if the entry was already removed
+		 * from the list.
+		 */
+		list_del_init(&shp->shm_clist);
+		task_unlock(creator);
+	}
+	rcu_read_unlock();
+}
+
+static inline void shm_rmid(struct shmid_kernel *s)
+{
+	shm_clist_rm(s);
+	ipc_rmid(&shm_ids(s->ns), &s->shm_perm);
 }
 
 
@@ -283,7 +326,7 @@ static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp)
 	shm_file = shp->shm_file;
 	shp->shm_file = NULL;
 	ns->shm_tot -= (shp->shm_segsz + PAGE_SIZE - 1) >> PAGE_SHIFT;
-	shm_rmid(ns, shp);
+	shm_rmid(shp);
 	shm_unlock(shp);
 	if (!is_file_hugepages(shm_file))
 		shmem_lock(shm_file, 0, shp->mlock_ucounts);
@@ -303,10 +346,10 @@ static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp)
  *
  * 2) sysctl kernel.shm_rmid_forced is set to 1.
  */
-static bool shm_may_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp)
+static bool shm_may_destroy(struct shmid_kernel *shp)
 {
 	return (shp->shm_nattch == 0) &&
-	       (ns->shm_rmid_forced ||
+	       (shp->ns->shm_rmid_forced ||
 		(shp->shm_perm.mode & SHM_DEST));
 }
 
@@ -337,7 +380,7 @@ static void shm_close(struct vm_area_struct *vma)
 	ipc_update_pid(&shp->shm_lprid, task_tgid(current));
 	shp->shm_dtim = ktime_get_real_seconds();
 	shp->shm_nattch--;
-	if (shm_may_destroy(ns, shp))
+	if (shm_may_destroy(shp))
 		shm_destroy(ns, shp);
 	else
 		shm_unlock(shp);
@@ -358,10 +401,10 @@ static int shm_try_destroy_orphaned(int id, void *p, void *data)
 	 *
 	 * As shp->* are changed under rwsem, it's safe to skip shp locking.
 	 */
-	if (shp->shm_creator != NULL)
+	if (!list_empty(&shp->shm_clist))
 		return 0;
 
-	if (shm_may_destroy(ns, shp)) {
+	if (shm_may_destroy(shp)) {
 		shm_lock_by_ptr(shp);
 		shm_destroy(ns, shp);
 	}
@@ -379,48 +422,97 @@ void shm_destroy_orphaned(struct ipc_namespace *ns)
 /* Locking assumes this will only be called with task == current */
 void exit_shm(struct task_struct *task)
 {
-	struct ipc_namespace *ns = task->nsproxy->ipc_ns;
-	struct shmid_kernel *shp, *n;
+	for (;;) {
+		struct shmid_kernel *shp;
+		struct ipc_namespace *ns;
 
-	if (list_empty(&task->sysvshm.shm_clist))
-		return;
+		task_lock(task);
+
+		if (list_empty(&task->sysvshm.shm_clist)) {
+			task_unlock(task);
+			break;
+		}
+
+		shp = list_first_entry(&task->sysvshm.shm_clist, struct shmid_kernel,
+				shm_clist);
 
-	/*
-	 * If kernel.shm_rmid_forced is not set then only keep track of
-	 * which shmids are orphaned, so that a later set of the sysctl
-	 * can clean them up.
-	 */
-	if (!ns->shm_rmid_forced) {
-		down_read(&shm_ids(ns).rwsem);
-		list_for_each_entry(shp, &task->sysvshm.shm_clist, shm_clist)
-			shp->shm_creator = NULL;
 		/*
-		 * Only under read lock but we are only called on current
-		 * so no entry on the list will be shared.
+		 * 1) Get pointer to the ipc namespace. It is worth to say
+		 * that this pointer is guaranteed to be valid because
+		 * shp lifetime is always shorter than namespace lifetime
+		 * in which shp lives.
+		 * We taken task_lock it means that shp won't be freed.
 		 */
-		list_del(&task->sysvshm.shm_clist);
-		up_read(&shm_ids(ns).rwsem);
-		return;
-	}
+		ns = shp->ns;
 
-	/*
-	 * Destroy all already created segments, that were not yet mapped,
-	 * and mark any mapped as orphan to cover the sysctl toggling.
-	 * Destroy is skipped if shm_may_destroy() returns false.
-	 */
-	down_write(&shm_ids(ns).rwsem);
-	list_for_each_entry_safe(shp, n, &task->sysvshm.shm_clist, shm_clist) {
-		shp->shm_creator = NULL;
+		/*
+		 * 2) If kernel.shm_rmid_forced is not set then only keep track of
+		 * which shmids are orphaned, so that a later set of the sysctl
+		 * can clean them up.
+		 */
+		if (!ns->shm_rmid_forced)
+			goto unlink_continue;
 
-		if (shm_may_destroy(ns, shp)) {
-			shm_lock_by_ptr(shp);
-			shm_destroy(ns, shp);
+		/*
+		 * 3) get a reference to the namespace.
+		 *    The refcount could be already 0. If it is 0, then
+		 *    the shm objects will be free by free_ipc_work().
+		 */
+		ns = get_ipc_ns_not_zero(ns);
+		if (!ns) {
+unlink_continue:
+			list_del_init(&shp->shm_clist);
+			task_unlock(task);
+			continue;
 		}
-	}
 
-	/* Remove the list head from any segments still attached. */
-	list_del(&task->sysvshm.shm_clist);
-	up_write(&shm_ids(ns).rwsem);
+		/*
+		 * 4) get a reference to shp.
+		 *   This cannot fail: shm_clist_rm() is called before
+		 *   ipc_rmid(), thus the refcount cannot be 0.
+		 */
+		WARN_ON(!ipc_rcu_getref(&shp->shm_perm));
+
+		/*
+		 * 5) unlink the shm segment from the list of segments
+		 *    created by current.
+		 *    This must be done last. After unlinking,
+		 *    only the refcounts obtained above prevent IPC_RMID
+		 *    from destroying the segment or the namespace.
+		 */
+		list_del_init(&shp->shm_clist);
+
+		task_unlock(task);
+
+		/*
+		 * 6) we have all references
+		 *    Thus lock & if needed destroy shp.
+		 */
+		down_write(&shm_ids(ns).rwsem);
+		shm_lock_by_ptr(shp);
+		/*
+		 * rcu_read_lock was implicitly taken in shm_lock_by_ptr, it's
+		 * safe to call ipc_rcu_putref here
+		 */
+		ipc_rcu_putref(&shp->shm_perm, shm_rcu_free);
+
+		if (ipc_valid_object(&shp->shm_perm)) {
+			if (shm_may_destroy(shp))
+				shm_destroy(ns, shp);
+			else
+				shm_unlock(shp);
+		} else {
+			/*
+			 * Someone else deleted the shp from namespace
+			 * idr/kht while we have waited.
+			 * Just unlock and continue.
+			 */
+			shm_unlock(shp);
+		}
+
+		up_write(&shm_ids(ns).rwsem);
+		put_ipc_ns(ns); /* paired with get_ipc_ns_not_zero */
+	}
 }
 
 static vm_fault_t shm_fault(struct vm_fault *vmf)
@@ -676,7 +768,11 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
 	if (error < 0)
 		goto no_id;
 
+	shp->ns = ns;
+
+	task_lock(current);
 	list_add(&shp->shm_clist, &current->sysvshm.shm_clist);
+	task_unlock(current);
 
 	/*
 	 * shmid gets reported as "inode#" in /proc/pid/maps.
@@ -1567,7 +1663,8 @@ out_nattch:
 	down_write(&shm_ids(ns).rwsem);
 	shp = shm_lock(ns, shmid);
 	shp->shm_nattch--;
-	if (shm_may_destroy(ns, shp))
+
+	if (shm_may_destroy(shp))
 		shm_destroy(ns, shp);
 	else
 		shm_unlock(shp);
diff --git a/ipc/util.c b/ipc/util.c
index d48d8cfa1f3f..fa2d86ef3fb8 100644
--- a/ipc/util.c
+++ b/ipc/util.c
@@ -447,8 +447,8 @@ static int ipcget_public(struct ipc_namespace *ns, struct ipc_ids *ids,
 static void ipc_kht_remove(struct ipc_ids *ids, struct kern_ipc_perm *ipcp)
 {
 	if (ipcp->key != IPC_PRIVATE)
-		rhashtable_remove_fast(&ids->key_ht, &ipcp->khtnode,
-				       ipc_kht_params);
+		WARN_ON_ONCE(rhashtable_remove_fast(&ids->key_ht, &ipcp->khtnode,
+				       ipc_kht_params));
 }
 
 /**
@@ -498,7 +498,7 @@ void ipc_rmid(struct ipc_ids *ids, struct kern_ipc_perm *ipcp)
 {
 	int idx = ipcid_to_idx(ipcp->id);
 
-	idr_remove(&ids->ipcs_idr, idx);
+	WARN_ON_ONCE(idr_remove(&ids->ipcs_idr, idx) != ipcp);
 	ipc_kht_remove(ids, ipcp);
 	ids->in_use--;
 	ipcp->deleted = true;
diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt
index 60f1bfc3c7b2..ce77f0265660 100644
--- a/kernel/Kconfig.preempt
+++ b/kernel/Kconfig.preempt
@@ -1,12 +1,23 @@
 # SPDX-License-Identifier: GPL-2.0-only
 
+config PREEMPT_NONE_BUILD
+	bool
+
+config PREEMPT_VOLUNTARY_BUILD
+	bool
+
+config PREEMPT_BUILD
+	bool
+	select PREEMPTION
+	select UNINLINE_SPIN_UNLOCK if !ARCH_INLINE_SPIN_UNLOCK
+
 choice
 	prompt "Preemption Model"
-	default PREEMPT_NONE_BEHAVIOUR
+	default PREEMPT_NONE
 
-config PREEMPT_NONE_BEHAVIOUR
+config PREEMPT_NONE
 	bool "No Forced Preemption (Server)"
-	select PREEMPT_NONE if !PREEMPT_DYNAMIC
+	select PREEMPT_NONE_BUILD if !PREEMPT_DYNAMIC
 	help
 	  This is the traditional Linux preemption model, geared towards
 	  throughput. It will still provide good latencies most of the
@@ -18,10 +29,10 @@ config PREEMPT_NONE_BEHAVIOUR
 	  raw processing power of the kernel, irrespective of scheduling
 	  latencies.
 
-config PREEMPT_VOLUNTARY_BEHAVIOUR
+config PREEMPT_VOLUNTARY
 	bool "Voluntary Kernel Preemption (Desktop)"
 	depends on !ARCH_NO_PREEMPT
-	select PREEMPT_VOLUNTARY if !PREEMPT_DYNAMIC
+	select PREEMPT_VOLUNTARY_BUILD if !PREEMPT_DYNAMIC
 	help
 	  This option reduces the latency of the kernel by adding more
 	  "explicit preemption points" to the kernel code. These new
@@ -37,10 +48,10 @@ config PREEMPT_VOLUNTARY_BEHAVIOUR
 
 	  Select this if you are building a kernel for a desktop system.
 
-config PREEMPT_BEHAVIOUR
+config PREEMPT
 	bool "Preemptible Kernel (Low-Latency Desktop)"
 	depends on !ARCH_NO_PREEMPT
-	select PREEMPT
+	select PREEMPT_BUILD
 	help
 	  This option reduces the latency of the kernel by making
 	  all kernel code (that is not executing in a critical section)
@@ -58,7 +69,7 @@ config PREEMPT_BEHAVIOUR
 
 config PREEMPT_RT
 	bool "Fully Preemptible Kernel (Real-Time)"
-	depends on EXPERT && ARCH_SUPPORTS_RT && !PREEMPT_DYNAMIC
+	depends on EXPERT && ARCH_SUPPORTS_RT
 	select PREEMPTION
 	help
 	  This option turns the kernel into a real-time kernel by replacing
@@ -75,17 +86,6 @@ config PREEMPT_RT
 
 endchoice
 
-config PREEMPT_NONE
-	bool
-
-config PREEMPT_VOLUNTARY
-	bool
-
-config PREEMPT
-	bool
-	select PREEMPTION
-	select UNINLINE_SPIN_UNLOCK if !ARCH_INLINE_SPIN_UNLOCK
-
 config PREEMPT_COUNT
        bool
 
@@ -95,8 +95,8 @@ config PREEMPTION
 
 config PREEMPT_DYNAMIC
 	bool "Preemption behaviour defined on boot"
-	depends on HAVE_PREEMPT_DYNAMIC
-	select PREEMPT
+	depends on HAVE_PREEMPT_DYNAMIC && !PREEMPT_RT
+	select PREEMPT_BUILD
 	default y
 	help
 	  This option allows to define the preemption model on the kernel
diff --git a/kernel/audit.c b/kernel/audit.c
index 121d37e700a6..4cebadb5f30d 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -718,7 +718,7 @@ static int kauditd_send_queue(struct sock *sk, u32 portid,
 {
 	int rc = 0;
 	struct sk_buff *skb;
-	static unsigned int failed = 0;
+	unsigned int failed = 0;
 
 	/* NOTE: kauditd_thread takes care of all our locking, we just use
 	 *       the netlink info passed to us (e.g. sk and portid) */
@@ -735,32 +735,30 @@ static int kauditd_send_queue(struct sock *sk, u32 portid,
 			continue;
 		}
 
+retry:
 		/* grab an extra skb reference in case of error */
 		skb_get(skb);
 		rc = netlink_unicast(sk, skb, portid, 0);
 		if (rc < 0) {
-			/* fatal failure for our queue flush attempt? */
+			/* send failed - try a few times unless fatal error */
 			if (++failed >= retry_limit ||
 			    rc == -ECONNREFUSED || rc == -EPERM) {
-				/* yes - error processing for the queue */
 				sk = NULL;
 				if (err_hook)
 					(*err_hook)(skb);
-				if (!skb_hook)
-					goto out;
-				/* keep processing with the skb_hook */
+				if (rc == -EAGAIN)
+					rc = 0;
+				/* continue to drain the queue */
 				continue;
 			} else
-				/* no - requeue to preserve ordering */
-				skb_queue_head(queue, skb);
+				goto retry;
 		} else {
-			/* it worked - drop the extra reference and continue */
+			/* skb sent - drop the extra reference and continue */
 			consume_skb(skb);
 			failed = 0;
 		}
 	}
 
-out:
 	return (rc >= 0 ? 0 : rc);
 }
 
@@ -1609,7 +1607,8 @@ static int __net_init audit_net_init(struct net *net)
 		audit_panic("cannot initialize netlink socket in namespace");
 		return -ENOMEM;
 	}
-	aunet->sk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT;
+	/* limit the timeout in case auditd is blocked/stopped */
+	aunet->sk->sk_sndtimeo = HZ / 10;
 
 	return 0;
 }
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index dbc3ad07e21b..9bdb03767db5 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -6346,11 +6346,6 @@ BTF_ID_LIST_GLOBAL_SINGLE(btf_task_struct_ids, struct, task_struct)
 
 /* BTF ID set registration API for modules */
 
-struct kfunc_btf_id_list {
-	struct list_head list;
-	struct mutex mutex;
-};
-
 #ifdef CONFIG_DEBUG_INFO_BTF_MODULES
 
 void register_kfunc_btf_id_set(struct kfunc_btf_id_list *l,
@@ -6376,8 +6371,6 @@ bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, u32 kfunc_id,
 {
 	struct kfunc_btf_id_set *s;
 
-	if (!owner)
-		return false;
 	mutex_lock(&klist->mutex);
 	list_for_each_entry(s, &klist->list, list) {
 		if (s->owner == owner && btf_id_set_contains(s->set, kfunc_id)) {
@@ -6389,8 +6382,6 @@ bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, u32 kfunc_id,
 	return false;
 }
 
-#endif
-
 #define DEFINE_KFUNC_BTF_ID_LIST(name)                                         \
 	struct kfunc_btf_id_list name = { LIST_HEAD_INIT(name.list),           \
 					  __MUTEX_INITIALIZER(name.mutex) };   \
@@ -6398,3 +6389,5 @@ bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, u32 kfunc_id,
 
 DEFINE_KFUNC_BTF_ID_LIST(bpf_tcp_ca_kfunc_list);
 DEFINE_KFUNC_BTF_ID_LIST(prog_test_kfunc_list);
+
+#endif
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 2ca643af9a54..43eb3501721b 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -1809,6 +1809,8 @@ sysctl_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_sysctl_get_new_value_proto;
 	case BPF_FUNC_sysctl_set_new_value:
 		return &bpf_sysctl_set_new_value_proto;
+	case BPF_FUNC_ktime_get_coarse_ns:
+		return &bpf_ktime_get_coarse_ns_proto;
 	default:
 		return cgroup_base_func_proto(func_id, prog);
 	}
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 1ffd469c217f..649f07623df6 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -1364,8 +1364,6 @@ bpf_base_func_proto(enum bpf_func_id func_id)
 		return &bpf_ktime_get_ns_proto;
 	case BPF_FUNC_ktime_get_boot_ns:
 		return &bpf_ktime_get_boot_ns_proto;
-	case BPF_FUNC_ktime_get_coarse_ns:
-		return &bpf_ktime_get_coarse_ns_proto;
 	case BPF_FUNC_ringbuf_output:
 		return &bpf_ringbuf_output_proto;
 	case BPF_FUNC_ringbuf_reserve:
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 50f96ea4452a..1033ee8c0caf 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -132,6 +132,21 @@ static struct bpf_map *find_and_alloc_map(union bpf_attr *attr)
 	return map;
 }
 
+static void bpf_map_write_active_inc(struct bpf_map *map)
+{
+	atomic64_inc(&map->writecnt);
+}
+
+static void bpf_map_write_active_dec(struct bpf_map *map)
+{
+	atomic64_dec(&map->writecnt);
+}
+
+bool bpf_map_write_active(const struct bpf_map *map)
+{
+	return atomic64_read(&map->writecnt) != 0;
+}
+
 static u32 bpf_map_value_size(const struct bpf_map *map)
 {
 	if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
@@ -601,11 +616,8 @@ static void bpf_map_mmap_open(struct vm_area_struct *vma)
 {
 	struct bpf_map *map = vma->vm_file->private_data;
 
-	if (vma->vm_flags & VM_MAYWRITE) {
-		mutex_lock(&map->freeze_mutex);
-		map->writecnt++;
-		mutex_unlock(&map->freeze_mutex);
-	}
+	if (vma->vm_flags & VM_MAYWRITE)
+		bpf_map_write_active_inc(map);
 }
 
 /* called for all unmapped memory region (including initial) */
@@ -613,11 +625,8 @@ static void bpf_map_mmap_close(struct vm_area_struct *vma)
 {
 	struct bpf_map *map = vma->vm_file->private_data;
 
-	if (vma->vm_flags & VM_MAYWRITE) {
-		mutex_lock(&map->freeze_mutex);
-		map->writecnt--;
-		mutex_unlock(&map->freeze_mutex);
-	}
+	if (vma->vm_flags & VM_MAYWRITE)
+		bpf_map_write_active_dec(map);
 }
 
 static const struct vm_operations_struct bpf_map_default_vmops = {
@@ -668,7 +677,7 @@ static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma)
 		goto out;
 
 	if (vma->vm_flags & VM_MAYWRITE)
-		map->writecnt++;
+		bpf_map_write_active_inc(map);
 out:
 	mutex_unlock(&map->freeze_mutex);
 	return err;
@@ -1139,6 +1148,7 @@ static int map_update_elem(union bpf_attr *attr, bpfptr_t uattr)
 	map = __bpf_map_get(f);
 	if (IS_ERR(map))
 		return PTR_ERR(map);
+	bpf_map_write_active_inc(map);
 	if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
 		err = -EPERM;
 		goto err_put;
@@ -1174,6 +1184,7 @@ free_value:
 free_key:
 	kvfree(key);
 err_put:
+	bpf_map_write_active_dec(map);
 	fdput(f);
 	return err;
 }
@@ -1196,6 +1207,7 @@ static int map_delete_elem(union bpf_attr *attr)
 	map = __bpf_map_get(f);
 	if (IS_ERR(map))
 		return PTR_ERR(map);
+	bpf_map_write_active_inc(map);
 	if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
 		err = -EPERM;
 		goto err_put;
@@ -1226,6 +1238,7 @@ static int map_delete_elem(union bpf_attr *attr)
 out:
 	kvfree(key);
 err_put:
+	bpf_map_write_active_dec(map);
 	fdput(f);
 	return err;
 }
@@ -1533,6 +1546,7 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr)
 	map = __bpf_map_get(f);
 	if (IS_ERR(map))
 		return PTR_ERR(map);
+	bpf_map_write_active_inc(map);
 	if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ) ||
 	    !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
 		err = -EPERM;
@@ -1597,6 +1611,7 @@ free_value:
 free_key:
 	kvfree(key);
 err_put:
+	bpf_map_write_active_dec(map);
 	fdput(f);
 	return err;
 }
@@ -1624,8 +1639,7 @@ static int map_freeze(const union bpf_attr *attr)
 	}
 
 	mutex_lock(&map->freeze_mutex);
-
-	if (map->writecnt) {
+	if (bpf_map_write_active(map)) {
 		err = -EBUSY;
 		goto err_put;
 	}
@@ -4171,6 +4185,9 @@ static int bpf_map_do_batch(const union bpf_attr *attr,
 			    union bpf_attr __user *uattr,
 			    int cmd)
 {
+	bool has_read  = cmd == BPF_MAP_LOOKUP_BATCH ||
+			 cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH;
+	bool has_write = cmd != BPF_MAP_LOOKUP_BATCH;
 	struct bpf_map *map;
 	int err, ufd;
 	struct fd f;
@@ -4183,16 +4200,13 @@ static int bpf_map_do_batch(const union bpf_attr *attr,
 	map = __bpf_map_get(f);
 	if (IS_ERR(map))
 		return PTR_ERR(map);
-
-	if ((cmd == BPF_MAP_LOOKUP_BATCH ||
-	     cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH) &&
-	    !(map_get_sys_perms(map, f) & FMODE_CAN_READ)) {
+	if (has_write)
+		bpf_map_write_active_inc(map);
+	if (has_read && !(map_get_sys_perms(map, f) & FMODE_CAN_READ)) {
 		err = -EPERM;
 		goto err_put;
 	}
-
-	if (cmd != BPF_MAP_LOOKUP_BATCH &&
-	    !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
+	if (has_write && !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
 		err = -EPERM;
 		goto err_put;
 	}
@@ -4205,8 +4219,9 @@ static int bpf_map_do_batch(const union bpf_attr *attr,
 		BPF_DO_BATCH(map->ops->map_update_batch);
 	else
 		BPF_DO_BATCH(map->ops->map_delete_batch);
-
 err_put:
+	if (has_write)
+		bpf_map_write_active_dec(map);
 	fdput(f);
 	return err;
 }
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 890b3ec375a3..b532f1058d35 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1151,7 +1151,8 @@ static void mark_ptr_not_null_reg(struct bpf_reg_state *reg)
 			/* transfer reg's id which is unique for every map_lookup_elem
 			 * as UID of the inner map.
 			 */
-			reg->map_uid = reg->id;
+			if (map_value_has_timer(map->inner_map_meta))
+				reg->map_uid = reg->id;
 		} else if (map->map_type == BPF_MAP_TYPE_XSKMAP) {
 			reg->type = PTR_TO_XDP_SOCK;
 		} else if (map->map_type == BPF_MAP_TYPE_SOCKMAP ||
@@ -1365,22 +1366,28 @@ static void __reg_bound_offset(struct bpf_reg_state *reg)
 	reg->var_off = tnum_or(tnum_clear_subreg(var64_off), var32_off);
 }
 
+static bool __reg32_bound_s64(s32 a)
+{
+	return a >= 0 && a <= S32_MAX;
+}
+
 static void __reg_assign_32_into_64(struct bpf_reg_state *reg)
 {
 	reg->umin_value = reg->u32_min_value;
 	reg->umax_value = reg->u32_max_value;
-	/* Attempt to pull 32-bit signed bounds into 64-bit bounds
-	 * but must be positive otherwise set to worse case bounds
-	 * and refine later from tnum.
+
+	/* Attempt to pull 32-bit signed bounds into 64-bit bounds but must
+	 * be positive otherwise set to worse case bounds and refine later
+	 * from tnum.
 	 */
-	if (reg->s32_min_value >= 0 && reg->s32_max_value >= 0)
-		reg->smax_value = reg->s32_max_value;
-	else
-		reg->smax_value = U32_MAX;
-	if (reg->s32_min_value >= 0)
+	if (__reg32_bound_s64(reg->s32_min_value) &&
+	    __reg32_bound_s64(reg->s32_max_value)) {
 		reg->smin_value = reg->s32_min_value;
-	else
+		reg->smax_value = reg->s32_max_value;
+	} else {
 		reg->smin_value = 0;
+		reg->smax_value = U32_MAX;
+	}
 }
 
 static void __reg_combine_32_into_64(struct bpf_reg_state *reg)
@@ -2378,8 +2385,6 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx,
 		 */
 		if (insn->src_reg != BPF_REG_FP)
 			return 0;
-		if (BPF_SIZE(insn->code) != BPF_DW)
-			return 0;
 
 		/* dreg = *(u64 *)[fp - off] was a fill from the stack.
 		 * that [fp - off] slot contains scalar that needs to be
@@ -2402,8 +2407,6 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx,
 		/* scalars can only be spilled into stack */
 		if (insn->dst_reg != BPF_REG_FP)
 			return 0;
-		if (BPF_SIZE(insn->code) != BPF_DW)
-			return 0;
 		spi = (-insn->off - 1) / BPF_REG_SIZE;
 		if (spi >= 64) {
 			verbose(env, "BUG spi %d\n", spi);
@@ -4055,7 +4058,22 @@ static void coerce_reg_to_size(struct bpf_reg_state *reg, int size)
 
 static bool bpf_map_is_rdonly(const struct bpf_map *map)
 {
-	return (map->map_flags & BPF_F_RDONLY_PROG) && map->frozen;
+	/* A map is considered read-only if the following condition are true:
+	 *
+	 * 1) BPF program side cannot change any of the map content. The
+	 *    BPF_F_RDONLY_PROG flag is throughout the lifetime of a map
+	 *    and was set at map creation time.
+	 * 2) The map value(s) have been initialized from user space by a
+	 *    loader and then "frozen", such that no new map update/delete
+	 *    operations from syscall side are possible for the rest of
+	 *    the map's lifetime from that point onwards.
+	 * 3) Any parallel/pending map update/delete operations from syscall
+	 *    side have been completed. Only after that point, it's safe to
+	 *    assume that map value(s) are immutable.
+	 */
+	return (map->map_flags & BPF_F_RDONLY_PROG) &&
+	       READ_ONCE(map->frozen) &&
+	       !bpf_map_write_active(map);
 }
 
 static int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val)
@@ -4535,9 +4553,16 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i
 
 	if (insn->imm == BPF_CMPXCHG) {
 		/* Check comparison of R0 with memory location */
-		err = check_reg_arg(env, BPF_REG_0, SRC_OP);
+		const u32 aux_reg = BPF_REG_0;
+
+		err = check_reg_arg(env, aux_reg, SRC_OP);
 		if (err)
 			return err;
+
+		if (is_pointer_value(env, aux_reg)) {
+			verbose(env, "R%d leaks addr into mem\n", aux_reg);
+			return -EACCES;
+		}
 	}
 
 	if (is_pointer_value(env, insn->src_reg)) {
@@ -4572,13 +4597,19 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i
 		load_reg = -1;
 	}
 
-	/* check whether we can read the memory */
+	/* Check whether we can read the memory, with second call for fetch
+	 * case to simulate the register fill.
+	 */
 	err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
-			       BPF_SIZE(insn->code), BPF_READ, load_reg, true);
+			       BPF_SIZE(insn->code), BPF_READ, -1, true);
+	if (!err && load_reg >= 0)
+		err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
+				       BPF_SIZE(insn->code), BPF_READ, load_reg,
+				       true);
 	if (err)
 		return err;
 
-	/* check whether we can write into the same memory */
+	/* Check whether we can write into the same memory. */
 	err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
 			       BPF_SIZE(insn->code), BPF_WRITE, -1, true);
 	if (err)
@@ -8292,6 +8323,10 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 							 insn->dst_reg);
 				}
 				zext_32_to_64(dst_reg);
+
+				__update_reg_bounds(dst_reg);
+				__reg_deduce_bounds(dst_reg);
+				__reg_bound_offset(dst_reg);
 			}
 		} else {
 			/* case: R = imm
@@ -8406,7 +8441,7 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *vstate,
 
 	new_range = dst_reg->off;
 	if (range_right_open)
-		new_range--;
+		new_range++;
 
 	/* Examples for register markings:
 	 *
@@ -11631,6 +11666,13 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env,
 		}
 	}
 
+	if (map_value_has_timer(map)) {
+		if (is_tracing_prog_type(prog_type)) {
+			verbose(env, "tracing progs cannot use bpf_timer yet\n");
+			return -EINVAL;
+		}
+	}
+
 	if ((bpf_prog_is_dev_bound(prog->aux) || bpf_map_is_dev_bound(map)) &&
 	    !bpf_offload_prog_map_match(prog, map)) {
 		verbose(env, "offload device mismatch between prog and map\n");
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 192e43a87407..407a2568f35e 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -31,6 +31,7 @@
 #include <linux/smpboot.h>
 #include <linux/relay.h>
 #include <linux/slab.h>
+#include <linux/scs.h>
 #include <linux/percpu-rwsem.h>
 #include <linux/cpuset.h>
 
@@ -588,6 +589,12 @@ static int bringup_cpu(unsigned int cpu)
 	int ret;
 
 	/*
+	 * Reset stale stack state from the last time this CPU was online.
+	 */
+	scs_task_reset(idle);
+	kasan_unpoison_task_stack(idle);
+
+	/*
 	 * Some architectures have to walk the irq descriptors to
 	 * setup the vector space for the cpu which comes online.
 	 * Prevent irq alloc/free across the bringup.
diff --git a/kernel/crash_core.c b/kernel/crash_core.c
index eb53f5ec62c9..256cf6db573c 100644
--- a/kernel/crash_core.c
+++ b/kernel/crash_core.c
@@ -6,6 +6,7 @@
 
 #include <linux/buildid.h>
 #include <linux/crash_core.h>
+#include <linux/init.h>
 #include <linux/utsname.h>
 #include <linux/vmalloc.h>
 
@@ -295,6 +296,16 @@ int __init parse_crashkernel_low(char *cmdline,
 				"crashkernel=", suffix_tbl[SUFFIX_LOW]);
 }
 
+/*
+ * Add a dummy early_param handler to mark crashkernel= as a known command line
+ * parameter and suppress incorrect warnings in init/main.c.
+ */
+static int __init parse_crashkernel_dummy(char *arg)
+{
+	return 0;
+}
+early_param("crashkernel", parse_crashkernel_dummy);
+
 Elf_Word *append_elf_note(Elf_Word *buf, char *name, unsigned int type,
 			  void *data, size_t data_len)
 {
diff --git a/kernel/entry/syscall_user_dispatch.c b/kernel/entry/syscall_user_dispatch.c
index 4508201847d2..0b6379adff6b 100644
--- a/kernel/entry/syscall_user_dispatch.c
+++ b/kernel/entry/syscall_user_dispatch.c
@@ -48,7 +48,7 @@ bool syscall_user_dispatch(struct pt_regs *regs)
 		 * the selector is loaded by userspace.
 		 */
 		if (unlikely(__get_user(state, sd->selector))) {
-			force_fatal_sig(SIGSEGV);
+			force_exit_sig(SIGSEGV);
 			return true;
 		}
 
@@ -56,7 +56,7 @@ bool syscall_user_dispatch(struct pt_regs *regs)
 			return false;
 
 		if (state != SYSCALL_DISPATCH_FILTER_BLOCK) {
-			force_fatal_sig(SIGSYS);
+			force_exit_sig(SIGSYS);
 			return true;
 		}
 	}
diff --git a/kernel/events/core.c b/kernel/events/core.c
index f2253ea729a2..30d94f68c5bd 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7154,7 +7154,6 @@ void perf_output_sample(struct perf_output_handle *handle,
 static u64 perf_virt_to_phys(u64 virt)
 {
 	u64 phys_addr = 0;
-	struct page *p = NULL;
 
 	if (!virt)
 		return 0;
@@ -7173,14 +7172,15 @@ static u64 perf_virt_to_phys(u64 virt)
 		 * If failed, leave phys_addr as 0.
 		 */
 		if (current->mm != NULL) {
+			struct page *p;
+
 			pagefault_disable();
-			if (get_user_page_fast_only(virt, 0, &p))
+			if (get_user_page_fast_only(virt, 0, &p)) {
 				phys_addr = page_to_phys(p) + virt % PAGE_SIZE;
+				put_page(p);
+			}
 			pagefault_enable();
 		}
-
-		if (p)
-			put_page(p);
 	}
 
 	return phys_addr;
@@ -9759,6 +9759,9 @@ void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size,
 				continue;
 			if (event->attr.config != entry->type)
 				continue;
+			/* Cannot deliver synchronous signal to other task. */
+			if (event->attr.sigtrap)
+				continue;
 			if (perf_tp_event_match(event, &data, regs))
 				perf_swevent_event(event, count, &data, regs);
 		}
diff --git a/kernel/fork.c b/kernel/fork.c
index 5de23f3e08bf..3244cc56b697 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2277,6 +2277,7 @@ static __latent_entropy struct task_struct *copy_process(
 	p->pdeath_signal = 0;
 	INIT_LIST_HEAD(&p->thread_group);
 	p->task_works = NULL;
+	clear_posix_cputimers_work(p);
 
 #ifdef CONFIG_KRETPROBES
 	p->kretprobe_instances.first = NULL;
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index 6a5ecee6e567..7f350ae59c5f 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -529,10 +529,10 @@ static bool msi_check_reservation_mode(struct irq_domain *domain,
 
 	/*
 	 * Checking the first MSI descriptor is sufficient. MSIX supports
-	 * masking and MSI does so when the maskbit is set.
+	 * masking and MSI does so when the can_mask attribute is set.
 	 */
 	desc = first_msi_entry(dev);
-	return desc->msi_attrib.is_msix || desc->msi_attrib.maskbit;
+	return desc->msi_attrib.is_msix || desc->msi_attrib.can_mask;
 }
 
 int __msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index e9db0c810554..21eccc961bba 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -2086,6 +2086,9 @@ int register_kretprobe(struct kretprobe *rp)
 		}
 	}
 
+	if (rp->data_size > KRETPROBE_MAX_DATA_SIZE)
+		return -E2BIG;
+
 	rp->kp.pre_handler = pre_handler_kretprobe;
 	rp->kp.post_handler = NULL;
 
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 0c6a48dfcecb..1f25a4d7de27 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -1380,7 +1380,7 @@ static bool rtmutex_spin_on_owner(struct rt_mutex_base *lock,
 		 *  - the VCPU on which owner runs is preempted
 		 */
 		if (!owner->on_cpu || need_resched() ||
-		    rt_mutex_waiter_is_top_waiter(lock, waiter) ||
+		    !rt_mutex_waiter_is_top_waiter(lock, waiter) ||
 		    vcpu_is_preempted(task_cpu(owner))) {
 			res = false;
 			break;
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index c51387a43265..04a74d040a6d 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -105,9 +105,9 @@
  * atomic_long_cmpxchg() will be used to obtain writer lock.
  *
  * There are three places where the lock handoff bit may be set or cleared.
- * 1) rwsem_mark_wake() for readers.
- * 2) rwsem_try_write_lock() for writers.
- * 3) Error path of rwsem_down_write_slowpath().
+ * 1) rwsem_mark_wake() for readers		-- set, clear
+ * 2) rwsem_try_write_lock() for writers	-- set, clear
+ * 3) rwsem_del_waiter()			-- clear
  *
  * For all the above cases, wait_lock will be held. A writer must also
  * be the first one in the wait_list to be eligible for setting the handoff
@@ -334,6 +334,9 @@ struct rwsem_waiter {
 	struct task_struct *task;
 	enum rwsem_waiter_type type;
 	unsigned long timeout;
+
+	/* Writer only, not initialized in reader */
+	bool handoff_set;
 };
 #define rwsem_first_waiter(sem) \
 	list_first_entry(&sem->wait_list, struct rwsem_waiter, list)
@@ -344,12 +347,6 @@ enum rwsem_wake_type {
 	RWSEM_WAKE_READ_OWNED	/* Waker thread holds the read lock */
 };
 
-enum writer_wait_state {
-	WRITER_NOT_FIRST,	/* Writer is not first in wait list */
-	WRITER_FIRST,		/* Writer is first in wait list     */
-	WRITER_HANDOFF		/* Writer is first & handoff needed */
-};
-
 /*
  * The typical HZ value is either 250 or 1000. So set the minimum waiting
  * time to at least 4ms or 1 jiffy (if it is higher than 4ms) in the wait
@@ -365,6 +362,31 @@ enum writer_wait_state {
  */
 #define MAX_READERS_WAKEUP	0x100
 
+static inline void
+rwsem_add_waiter(struct rw_semaphore *sem, struct rwsem_waiter *waiter)
+{
+	lockdep_assert_held(&sem->wait_lock);
+	list_add_tail(&waiter->list, &sem->wait_list);
+	/* caller will set RWSEM_FLAG_WAITERS */
+}
+
+/*
+ * Remove a waiter from the wait_list and clear flags.
+ *
+ * Both rwsem_mark_wake() and rwsem_try_write_lock() contain a full 'copy' of
+ * this function. Modify with care.
+ */
+static inline void
+rwsem_del_waiter(struct rw_semaphore *sem, struct rwsem_waiter *waiter)
+{
+	lockdep_assert_held(&sem->wait_lock);
+	list_del(&waiter->list);
+	if (likely(!list_empty(&sem->wait_list)))
+		return;
+
+	atomic_long_andnot(RWSEM_FLAG_HANDOFF | RWSEM_FLAG_WAITERS, &sem->count);
+}
+
 /*
  * handle the lock release when processes blocked on it that can now run
  * - if we come here from up_xxxx(), then the RWSEM_FLAG_WAITERS bit must
@@ -376,6 +398,8 @@ enum writer_wait_state {
  *   preferably when the wait_lock is released
  * - woken process blocks are discarded from the list after having task zeroed
  * - writers are only marked woken if downgrading is false
+ *
+ * Implies rwsem_del_waiter() for all woken readers.
  */
 static void rwsem_mark_wake(struct rw_semaphore *sem,
 			    enum rwsem_wake_type wake_type,
@@ -490,18 +514,25 @@ static void rwsem_mark_wake(struct rw_semaphore *sem,
 
 	adjustment = woken * RWSEM_READER_BIAS - adjustment;
 	lockevent_cond_inc(rwsem_wake_reader, woken);
+
+	oldcount = atomic_long_read(&sem->count);
 	if (list_empty(&sem->wait_list)) {
-		/* hit end of list above */
+		/*
+		 * Combined with list_move_tail() above, this implies
+		 * rwsem_del_waiter().
+		 */
 		adjustment -= RWSEM_FLAG_WAITERS;
+		if (oldcount & RWSEM_FLAG_HANDOFF)
+			adjustment -= RWSEM_FLAG_HANDOFF;
+	} else if (woken) {
+		/*
+		 * When we've woken a reader, we no longer need to force
+		 * writers to give up the lock and we can clear HANDOFF.
+		 */
+		if (oldcount & RWSEM_FLAG_HANDOFF)
+			adjustment -= RWSEM_FLAG_HANDOFF;
 	}
 
-	/*
-	 * When we've woken a reader, we no longer need to force writers
-	 * to give up the lock and we can clear HANDOFF.
-	 */
-	if (woken && (atomic_long_read(&sem->count) & RWSEM_FLAG_HANDOFF))
-		adjustment -= RWSEM_FLAG_HANDOFF;
-
 	if (adjustment)
 		atomic_long_add(adjustment, &sem->count);
 
@@ -532,12 +563,12 @@ static void rwsem_mark_wake(struct rw_semaphore *sem,
  * race conditions between checking the rwsem wait list and setting the
  * sem->count accordingly.
  *
- * If wstate is WRITER_HANDOFF, it will make sure that either the handoff
- * bit is set or the lock is acquired with handoff bit cleared.
+ * Implies rwsem_del_waiter() on success.
  */
 static inline bool rwsem_try_write_lock(struct rw_semaphore *sem,
-					enum writer_wait_state wstate)
+					struct rwsem_waiter *waiter)
 {
+	bool first = rwsem_first_waiter(sem) == waiter;
 	long count, new;
 
 	lockdep_assert_held(&sem->wait_lock);
@@ -546,13 +577,19 @@ static inline bool rwsem_try_write_lock(struct rw_semaphore *sem,
 	do {
 		bool has_handoff = !!(count & RWSEM_FLAG_HANDOFF);
 
-		if (has_handoff && wstate == WRITER_NOT_FIRST)
-			return false;
+		if (has_handoff) {
+			if (!first)
+				return false;
+
+			/* First waiter inherits a previously set handoff bit */
+			waiter->handoff_set = true;
+		}
 
 		new = count;
 
 		if (count & RWSEM_LOCK_MASK) {
-			if (has_handoff || (wstate != WRITER_HANDOFF))
+			if (has_handoff || (!rt_task(waiter->task) &&
+					    !time_after(jiffies, waiter->timeout)))
 				return false;
 
 			new |= RWSEM_FLAG_HANDOFF;
@@ -569,9 +606,17 @@ static inline bool rwsem_try_write_lock(struct rw_semaphore *sem,
 	 * We have either acquired the lock with handoff bit cleared or
 	 * set the handoff bit.
 	 */
-	if (new & RWSEM_FLAG_HANDOFF)
+	if (new & RWSEM_FLAG_HANDOFF) {
+		waiter->handoff_set = true;
+		lockevent_inc(rwsem_wlock_handoff);
 		return false;
+	}
 
+	/*
+	 * Have rwsem_try_write_lock() fully imply rwsem_del_waiter() on
+	 * success.
+	 */
+	list_del(&waiter->list);
 	rwsem_set_owner(sem);
 	return true;
 }
@@ -956,7 +1001,7 @@ queue:
 		}
 		adjustment += RWSEM_FLAG_WAITERS;
 	}
-	list_add_tail(&waiter.list, &sem->wait_list);
+	rwsem_add_waiter(sem, &waiter);
 
 	/* we're now waiting on the lock, but no longer actively locking */
 	count = atomic_long_add_return(adjustment, &sem->count);
@@ -1002,11 +1047,7 @@ queue:
 	return sem;
 
 out_nolock:
-	list_del(&waiter.list);
-	if (list_empty(&sem->wait_list)) {
-		atomic_long_andnot(RWSEM_FLAG_WAITERS|RWSEM_FLAG_HANDOFF,
-				   &sem->count);
-	}
+	rwsem_del_waiter(sem, &waiter);
 	raw_spin_unlock_irq(&sem->wait_lock);
 	__set_current_state(TASK_RUNNING);
 	lockevent_inc(rwsem_rlock_fail);
@@ -1020,9 +1061,7 @@ static struct rw_semaphore *
 rwsem_down_write_slowpath(struct rw_semaphore *sem, int state)
 {
 	long count;
-	enum writer_wait_state wstate;
 	struct rwsem_waiter waiter;
-	struct rw_semaphore *ret = sem;
 	DEFINE_WAKE_Q(wake_q);
 
 	/* do optimistic spinning and steal lock if possible */
@@ -1038,16 +1077,13 @@ rwsem_down_write_slowpath(struct rw_semaphore *sem, int state)
 	waiter.task = current;
 	waiter.type = RWSEM_WAITING_FOR_WRITE;
 	waiter.timeout = jiffies + RWSEM_WAIT_TIMEOUT;
+	waiter.handoff_set = false;
 
 	raw_spin_lock_irq(&sem->wait_lock);
-
-	/* account for this before adding a new element to the list */
-	wstate = list_empty(&sem->wait_list) ? WRITER_FIRST : WRITER_NOT_FIRST;
-
-	list_add_tail(&waiter.list, &sem->wait_list);
+	rwsem_add_waiter(sem, &waiter);
 
 	/* we're now waiting on the lock */
-	if (wstate == WRITER_NOT_FIRST) {
+	if (rwsem_first_waiter(sem) != &waiter) {
 		count = atomic_long_read(&sem->count);
 
 		/*
@@ -1083,13 +1119,16 @@ wait:
 	/* wait until we successfully acquire the lock */
 	set_current_state(state);
 	for (;;) {
-		if (rwsem_try_write_lock(sem, wstate)) {
+		if (rwsem_try_write_lock(sem, &waiter)) {
 			/* rwsem_try_write_lock() implies ACQUIRE on success */
 			break;
 		}
 
 		raw_spin_unlock_irq(&sem->wait_lock);
 
+		if (signal_pending_state(state, current))
+			goto out_nolock;
+
 		/*
 		 * After setting the handoff bit and failing to acquire
 		 * the lock, attempt to spin on owner to accelerate lock
@@ -1098,7 +1137,7 @@ wait:
 		 * In this case, we attempt to acquire the lock again
 		 * without sleeping.
 		 */
-		if (wstate == WRITER_HANDOFF) {
+		if (waiter.handoff_set) {
 			enum owner_state owner_state;
 
 			preempt_disable();
@@ -1109,66 +1148,26 @@ wait:
 				goto trylock_again;
 		}
 
-		/* Block until there are no active lockers. */
-		for (;;) {
-			if (signal_pending_state(state, current))
-				goto out_nolock;
-
-			schedule();
-			lockevent_inc(rwsem_sleep_writer);
-			set_current_state(state);
-			/*
-			 * If HANDOFF bit is set, unconditionally do
-			 * a trylock.
-			 */
-			if (wstate == WRITER_HANDOFF)
-				break;
-
-			if ((wstate == WRITER_NOT_FIRST) &&
-			    (rwsem_first_waiter(sem) == &waiter))
-				wstate = WRITER_FIRST;
-
-			count = atomic_long_read(&sem->count);
-			if (!(count & RWSEM_LOCK_MASK))
-				break;
-
-			/*
-			 * The setting of the handoff bit is deferred
-			 * until rwsem_try_write_lock() is called.
-			 */
-			if ((wstate == WRITER_FIRST) && (rt_task(current) ||
-			    time_after(jiffies, waiter.timeout))) {
-				wstate = WRITER_HANDOFF;
-				lockevent_inc(rwsem_wlock_handoff);
-				break;
-			}
-		}
+		schedule();
+		lockevent_inc(rwsem_sleep_writer);
+		set_current_state(state);
 trylock_again:
 		raw_spin_lock_irq(&sem->wait_lock);
 	}
 	__set_current_state(TASK_RUNNING);
-	list_del(&waiter.list);
 	raw_spin_unlock_irq(&sem->wait_lock);
 	lockevent_inc(rwsem_wlock);
-
-	return ret;
+	return sem;
 
 out_nolock:
 	__set_current_state(TASK_RUNNING);
 	raw_spin_lock_irq(&sem->wait_lock);
-	list_del(&waiter.list);
-
-	if (unlikely(wstate == WRITER_HANDOFF))
-		atomic_long_add(-RWSEM_FLAG_HANDOFF,  &sem->count);
-
-	if (list_empty(&sem->wait_list))
-		atomic_long_andnot(RWSEM_FLAG_WAITERS, &sem->count);
-	else
+	rwsem_del_waiter(sem, &waiter);
+	if (!list_empty(&sem->wait_list))
 		rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q);
 	raw_spin_unlock_irq(&sem->wait_lock);
 	wake_up_q(&wake_q);
 	lockevent_inc(rwsem_wlock_fail);
-
 	return ERR_PTR(-EINTR);
 }
 
@@ -1249,17 +1248,14 @@ static inline int __down_read_trylock(struct rw_semaphore *sem)
 
 	DEBUG_RWSEMS_WARN_ON(sem->magic != sem, sem);
 
-	/*
-	 * Optimize for the case when the rwsem is not locked at all.
-	 */
-	tmp = RWSEM_UNLOCKED_VALUE;
-	do {
+	tmp = atomic_long_read(&sem->count);
+	while (!(tmp & RWSEM_READ_FAILED_MASK)) {
 		if (atomic_long_try_cmpxchg_acquire(&sem->count, &tmp,
-					tmp + RWSEM_READER_BIAS)) {
+						    tmp + RWSEM_READER_BIAS)) {
 			rwsem_set_reader_owned(sem);
 			return 1;
 		}
-	} while (!(tmp & RWSEM_READ_FAILED_MASK));
+	}
 	return 0;
 }
 
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 9ed9b744876c..e6af502c2fd7 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -693,7 +693,7 @@ static int load_image_and_restore(void)
 		goto Unlock;
 
 	error = swsusp_read(&flags);
-	swsusp_close(FMODE_READ);
+	swsusp_close(FMODE_READ | FMODE_EXCL);
 	if (!error)
 		error = hibernation_restore(flags & SF_PLATFORM_MODE);
 
@@ -983,7 +983,7 @@ static int software_resume(void)
 	/* The snapshot device should not be opened while we're running */
 	if (!hibernate_acquire()) {
 		error = -EBUSY;
-		swsusp_close(FMODE_READ);
+		swsusp_close(FMODE_READ | FMODE_EXCL);
 		goto Unlock;
 	}
 
@@ -1018,7 +1018,7 @@ static int software_resume(void)
 	pm_pr_dbg("Hibernation image not present or could not be loaded.\n");
 	return error;
  Close_Finish:
-	swsusp_close(FMODE_READ);
+	swsusp_close(FMODE_READ | FMODE_EXCL);
 	goto Finish;
 }
 
diff --git a/kernel/power/user.c b/kernel/power/user.c
index 740723bb3885..ad241b4ff64c 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -177,7 +177,7 @@ static ssize_t snapshot_write(struct file *filp, const char __user *buf,
 		if (res <= 0)
 			goto unlock;
 	} else {
-		res = PAGE_SIZE - pg_offp;
+		res = PAGE_SIZE;
 	}
 
 	if (!data_of(data->handle)) {
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 013bfd6dcc34..57b132b658e1 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -3253,6 +3253,11 @@ void defer_console_output(void)
 	preempt_enable();
 }
 
+void printk_trigger_flush(void)
+{
+	defer_console_output();
+}
+
 int vprintk_deferred(const char *fmt, va_list args)
 {
 	int r;
diff --git a/kernel/sched/autogroup.c b/kernel/sched/autogroup.c
index 2067080bb235..8629b37d118e 100644
--- a/kernel/sched/autogroup.c
+++ b/kernel/sched/autogroup.c
@@ -31,7 +31,7 @@ static inline void autogroup_destroy(struct kref *kref)
 	ag->tg->rt_se = NULL;
 	ag->tg->rt_rq = NULL;
 #endif
-	sched_offline_group(ag->tg);
+	sched_release_group(ag->tg);
 	sched_destroy_group(ag->tg);
 }
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 523fd602ea90..77563109c0ea 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1918,7 +1918,7 @@ static void __init init_uclamp_rq(struct rq *rq)
 		};
 	}
 
-	rq->uclamp_flags = 0;
+	rq->uclamp_flags = UCLAMP_FLAG_IDLE;
 }
 
 static void __init init_uclamp(void)
@@ -3726,6 +3726,9 @@ out:
 
 bool cpus_share_cache(int this_cpu, int that_cpu)
 {
+	if (this_cpu == that_cpu)
+		return true;
+
 	return per_cpu(sd_llc_id, this_cpu) == per_cpu(sd_llc_id, that_cpu);
 }
 
@@ -6614,24 +6617,24 @@ static int __init setup_preempt_mode(char *str)
 	int mode = sched_dynamic_mode(str);
 	if (mode < 0) {
 		pr_warn("Dynamic Preempt: unsupported mode: %s\n", str);
-		return 1;
+		return 0;
 	}
 
 	sched_dynamic_update(mode);
-	return 0;
+	return 1;
 }
 __setup("preempt=", setup_preempt_mode);
 
 static void __init preempt_dynamic_init(void)
 {
 	if (preempt_dynamic_mode == preempt_dynamic_undefined) {
-		if (IS_ENABLED(CONFIG_PREEMPT_NONE_BEHAVIOUR)) {
+		if (IS_ENABLED(CONFIG_PREEMPT_NONE)) {
 			sched_dynamic_update(preempt_dynamic_none);
-		} else if (IS_ENABLED(CONFIG_PREEMPT_VOLUNTARY_BEHAVIOUR)) {
+		} else if (IS_ENABLED(CONFIG_PREEMPT_VOLUNTARY)) {
 			sched_dynamic_update(preempt_dynamic_voluntary);
 		} else {
 			/* Default static call setting, nothing to do */
-			WARN_ON_ONCE(!IS_ENABLED(CONFIG_PREEMPT_BEHAVIOUR));
+			WARN_ON_ONCE(!IS_ENABLED(CONFIG_PREEMPT));
 			preempt_dynamic_mode = preempt_dynamic_full;
 			pr_info("Dynamic Preempt: full\n");
 		}
@@ -8616,9 +8619,6 @@ void __init init_idle(struct task_struct *idle, int cpu)
 	idle->flags |= PF_IDLE | PF_KTHREAD | PF_NO_SETAFFINITY;
 	kthread_set_per_cpu(idle, cpu);
 
-	scs_task_reset(idle);
-	kasan_unpoison_task_stack(idle);
-
 #ifdef CONFIG_SMP
 	/*
 	 * It's possible that init_idle() gets called multiple times on a task,
@@ -8774,7 +8774,6 @@ void idle_task_exit(void)
 		finish_arch_post_lock_switch();
 	}
 
-	scs_task_reset(current);
 	/* finish_cpu(), as ran on the BP, will clean up the active_mm state */
 }
 
@@ -9716,6 +9715,22 @@ static void sched_free_group(struct task_group *tg)
 	kmem_cache_free(task_group_cache, tg);
 }
 
+static void sched_free_group_rcu(struct rcu_head *rcu)
+{
+	sched_free_group(container_of(rcu, struct task_group, rcu));
+}
+
+static void sched_unregister_group(struct task_group *tg)
+{
+	unregister_fair_sched_group(tg);
+	unregister_rt_sched_group(tg);
+	/*
+	 * We have to wait for yet another RCU grace period to expire, as
+	 * print_cfs_stats() might run concurrently.
+	 */
+	call_rcu(&tg->rcu, sched_free_group_rcu);
+}
+
 /* allocate runqueue etc for a new task group */
 struct task_group *sched_create_group(struct task_group *parent)
 {
@@ -9759,25 +9774,35 @@ void sched_online_group(struct task_group *tg, struct task_group *parent)
 }
 
 /* rcu callback to free various structures associated with a task group */
-static void sched_free_group_rcu(struct rcu_head *rhp)
+static void sched_unregister_group_rcu(struct rcu_head *rhp)
 {
 	/* Now it should be safe to free those cfs_rqs: */
-	sched_free_group(container_of(rhp, struct task_group, rcu));
+	sched_unregister_group(container_of(rhp, struct task_group, rcu));
 }
 
 void sched_destroy_group(struct task_group *tg)
 {
 	/* Wait for possible concurrent references to cfs_rqs complete: */
-	call_rcu(&tg->rcu, sched_free_group_rcu);
+	call_rcu(&tg->rcu, sched_unregister_group_rcu);
 }
 
-void sched_offline_group(struct task_group *tg)
+void sched_release_group(struct task_group *tg)
 {
 	unsigned long flags;
 
-	/* End participation in shares distribution: */
-	unregister_fair_sched_group(tg);
-
+	/*
+	 * Unlink first, to avoid walk_tg_tree_from() from finding us (via
+	 * sched_cfs_period_timer()).
+	 *
+	 * For this to be effective, we have to wait for all pending users of
+	 * this task group to leave their RCU critical section to ensure no new
+	 * user will see our dying task group any more. Specifically ensure
+	 * that tg_unthrottle_up() won't add decayed cfs_rq's to it.
+	 *
+	 * We therefore defer calling unregister_fair_sched_group() to
+	 * sched_unregister_group() which is guarantied to get called only after the
+	 * current RCU grace period has expired.
+	 */
 	spin_lock_irqsave(&task_group_lock, flags);
 	list_del_rcu(&tg->list);
 	list_del_rcu(&tg->siblings);
@@ -9896,7 +9921,7 @@ static void cpu_cgroup_css_released(struct cgroup_subsys_state *css)
 {
 	struct task_group *tg = css_tg(css);
 
-	sched_offline_group(tg);
+	sched_release_group(tg);
 }
 
 static void cpu_cgroup_css_free(struct cgroup_subsys_state *css)
@@ -9906,7 +9931,7 @@ static void cpu_cgroup_css_free(struct cgroup_subsys_state *css)
 	/*
 	 * Relies on the RCU grace period between css_released() and this.
 	 */
-	sched_free_group(tg);
+	sched_unregister_group(tg);
 }
 
 /*
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 872e481d5098..9392aea1804e 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -615,7 +615,8 @@ void task_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st)
 		.sum_exec_runtime = p->se.sum_exec_runtime,
 	};
 
-	task_cputime(p, &cputime.utime, &cputime.stime);
+	if (task_cputime(p, &cputime.utime, &cputime.stime))
+		cputime.sum_exec_runtime = task_sched_runtime(p);
 	cputime_adjust(&cputime, &p->prev_cputime, ut, st);
 }
 EXPORT_SYMBOL_GPL(task_cputime_adjusted);
@@ -828,19 +829,21 @@ u64 task_gtime(struct task_struct *t)
  * add up the pending nohz execution time since the last
  * cputime snapshot.
  */
-void task_cputime(struct task_struct *t, u64 *utime, u64 *stime)
+bool task_cputime(struct task_struct *t, u64 *utime, u64 *stime)
 {
 	struct vtime *vtime = &t->vtime;
 	unsigned int seq;
 	u64 delta;
+	int ret;
 
 	if (!vtime_accounting_enabled()) {
 		*utime = t->utime;
 		*stime = t->stime;
-		return;
+		return false;
 	}
 
 	do {
+		ret = false;
 		seq = read_seqcount_begin(&vtime->seqcount);
 
 		*utime = t->utime;
@@ -850,6 +853,7 @@ void task_cputime(struct task_struct *t, u64 *utime, u64 *stime)
 		if (vtime->state < VTIME_SYS)
 			continue;
 
+		ret = true;
 		delta = vtime_delta(vtime);
 
 		/*
@@ -861,6 +865,8 @@ void task_cputime(struct task_struct *t, u64 *utime, u64 *stime)
 		else
 			*utime += vtime->utime + delta;
 	} while (read_seqcount_retry(&vtime->seqcount, seq));
+
+	return ret;
 }
 
 static int vtime_state_fetch(struct vtime *vtime, int cpu)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 13950beb01a2..6e476f6d9435 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -11456,8 +11456,6 @@ void free_fair_sched_group(struct task_group *tg)
 {
 	int i;
 
-	destroy_cfs_bandwidth(tg_cfs_bandwidth(tg));
-
 	for_each_possible_cpu(i) {
 		if (tg->cfs_rq)
 			kfree(tg->cfs_rq[i]);
@@ -11534,6 +11532,8 @@ void unregister_fair_sched_group(struct task_group *tg)
 	struct rq *rq;
 	int cpu;
 
+	destroy_cfs_bandwidth(tg_cfs_bandwidth(tg));
+
 	for_each_possible_cpu(cpu) {
 		if (tg->se[cpu])
 			remove_entity_load_avg(tg->se[cpu]);
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index bb945f8faeca..b48baaba2fc2 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -137,13 +137,17 @@ static inline struct rq *rq_of_rt_se(struct sched_rt_entity *rt_se)
 	return rt_rq->rq;
 }
 
-void free_rt_sched_group(struct task_group *tg)
+void unregister_rt_sched_group(struct task_group *tg)
 {
-	int i;
-
 	if (tg->rt_se)
 		destroy_rt_bandwidth(&tg->rt_bandwidth);
 
+}
+
+void free_rt_sched_group(struct task_group *tg)
+{
+	int i;
+
 	for_each_possible_cpu(i) {
 		if (tg->rt_rq)
 			kfree(tg->rt_rq[i]);
@@ -250,6 +254,8 @@ static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se)
 	return &rq->rt;
 }
 
+void unregister_rt_sched_group(struct task_group *tg) { }
+
 void free_rt_sched_group(struct task_group *tg) { }
 
 int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 7f1612d26c18..0e66749486e7 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -488,6 +488,7 @@ extern void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b);
 extern void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b);
 extern void unthrottle_cfs_rq(struct cfs_rq *cfs_rq);
 
+extern void unregister_rt_sched_group(struct task_group *tg);
 extern void free_rt_sched_group(struct task_group *tg);
 extern int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent);
 extern void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq,
@@ -503,7 +504,7 @@ extern struct task_group *sched_create_group(struct task_group *parent);
 extern void sched_online_group(struct task_group *tg,
 			       struct task_group *parent);
 extern void sched_destroy_group(struct task_group *tg);
-extern void sched_offline_group(struct task_group *tg);
+extern void sched_release_group(struct task_group *tg);
 
 extern void sched_move_task(struct task_struct *tsk);
 
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index 76577d1642a5..eca38107b32f 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -238,6 +238,13 @@ void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode)
 }
 EXPORT_SYMBOL_GPL(__wake_up_sync);	/* For internal use only */
 
+void __wake_up_pollfree(struct wait_queue_head *wq_head)
+{
+	__wake_up(wq_head, TASK_NORMAL, 0, poll_to_key(EPOLLHUP | POLLFREE));
+	/* POLLFREE must have cleared the queue. */
+	WARN_ON_ONCE(waitqueue_active(wq_head));
+}
+
 /*
  * Note: we use "set_current_state()" _after_ the wait-queue add,
  * because we need a memory barrier there on SMP, so that any
diff --git a/kernel/signal.c b/kernel/signal.c
index 7c4b7ae714d4..dfcee3888b00 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1298,6 +1298,12 @@ int do_send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p
 	return ret;
 }
 
+enum sig_handler {
+	HANDLER_CURRENT, /* If reachable use the current handler */
+	HANDLER_SIG_DFL, /* Always use SIG_DFL handler semantics */
+	HANDLER_EXIT,	 /* Only visible as the process exit code */
+};
+
 /*
  * Force a signal that the process can't ignore: if necessary
  * we unblock the signal and change any SIG_IGN to SIG_DFL.
@@ -1310,7 +1316,8 @@ int do_send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p
  * that is why we also clear SIGNAL_UNKILLABLE.
  */
 static int
-force_sig_info_to_task(struct kernel_siginfo *info, struct task_struct *t, bool sigdfl)
+force_sig_info_to_task(struct kernel_siginfo *info, struct task_struct *t,
+	enum sig_handler handler)
 {
 	unsigned long int flags;
 	int ret, blocked, ignored;
@@ -1321,9 +1328,10 @@ force_sig_info_to_task(struct kernel_siginfo *info, struct task_struct *t, bool
 	action = &t->sighand->action[sig-1];
 	ignored = action->sa.sa_handler == SIG_IGN;
 	blocked = sigismember(&t->blocked, sig);
-	if (blocked || ignored || sigdfl) {
+	if (blocked || ignored || (handler != HANDLER_CURRENT)) {
 		action->sa.sa_handler = SIG_DFL;
-		action->sa.sa_flags |= SA_IMMUTABLE;
+		if (handler == HANDLER_EXIT)
+			action->sa.sa_flags |= SA_IMMUTABLE;
 		if (blocked) {
 			sigdelset(&t->blocked, sig);
 			recalc_sigpending_and_wake(t);
@@ -1343,7 +1351,7 @@ force_sig_info_to_task(struct kernel_siginfo *info, struct task_struct *t, bool
 
 int force_sig_info(struct kernel_siginfo *info)
 {
-	return force_sig_info_to_task(info, current, false);
+	return force_sig_info_to_task(info, current, HANDLER_CURRENT);
 }
 
 /*
@@ -1660,7 +1668,20 @@ void force_fatal_sig(int sig)
 	info.si_code = SI_KERNEL;
 	info.si_pid = 0;
 	info.si_uid = 0;
-	force_sig_info_to_task(&info, current, true);
+	force_sig_info_to_task(&info, current, HANDLER_SIG_DFL);
+}
+
+void force_exit_sig(int sig)
+{
+	struct kernel_siginfo info;
+
+	clear_siginfo(&info);
+	info.si_signo = sig;
+	info.si_errno = 0;
+	info.si_code = SI_KERNEL;
+	info.si_pid = 0;
+	info.si_uid = 0;
+	force_sig_info_to_task(&info, current, HANDLER_EXIT);
 }
 
 /*
@@ -1693,7 +1714,7 @@ int force_sig_fault_to_task(int sig, int code, void __user *addr
 	info.si_flags = flags;
 	info.si_isr = isr;
 #endif
-	return force_sig_info_to_task(&info, t, false);
+	return force_sig_info_to_task(&info, t, HANDLER_CURRENT);
 }
 
 int force_sig_fault(int sig, int code, void __user *addr
@@ -1813,7 +1834,8 @@ int force_sig_seccomp(int syscall, int reason, bool force_coredump)
 	info.si_errno = reason;
 	info.si_arch = syscall_get_arch(current);
 	info.si_syscall = syscall;
-	return force_sig_info_to_task(&info, current, force_coredump);
+	return force_sig_info_to_task(&info, current,
+		force_coredump ? HANDLER_EXIT : HANDLER_CURRENT);
 }
 
 /* For the crazy architectures that include trap information in
@@ -4163,6 +4185,15 @@ do_sigaltstack (const stack_t *ss, stack_t *oss, unsigned long sp,
 				ss_mode != 0))
 			return -EINVAL;
 
+		/*
+		 * Return before taking any locks if no actual
+		 * sigaltstack changes were requested.
+		 */
+		if (t->sas_ss_sp == (unsigned long)ss_sp &&
+		    t->sas_ss_size == ss_size &&
+		    t->sas_ss_flags == ss_flags)
+			return 0;
+
 		sigaltstack_lock();
 		if (ss_mode == SS_DISABLE) {
 			ss_size = 0;
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 322b65d45676..41f470929e99 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -595,7 +595,8 @@ void irq_enter_rcu(void)
 {
 	__irq_enter_raw();
 
-	if (is_idle_task(current) && (irq_count() == HARDIRQ_OFFSET))
+	if (tick_nohz_full_cpu(smp_processor_id()) ||
+	    (is_idle_task(current) && (irq_count() == HARDIRQ_OFFSET)))
 		tick_irq_enter();
 
 	account_hardirq_enter(current);
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index 643d412ac623..96b4e7810426 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -1159,13 +1159,28 @@ static void posix_cpu_timers_work(struct callback_head *work)
 }
 
 /*
+ * Clear existing posix CPU timers task work.
+ */
+void clear_posix_cputimers_work(struct task_struct *p)
+{
+	/*
+	 * A copied work entry from the old task is not meaningful, clear it.
+	 * N.B. init_task_work will not do this.
+	 */
+	memset(&p->posix_cputimers_work.work, 0,
+	       sizeof(p->posix_cputimers_work.work));
+	init_task_work(&p->posix_cputimers_work.work,
+		       posix_cpu_timers_work);
+	p->posix_cputimers_work.scheduled = false;
+}
+
+/*
  * Initialize posix CPU timers task work in init task. Out of line to
  * keep the callback static and to avoid header recursion hell.
  */
 void __init posix_cputimers_init_work(void)
 {
-	init_task_work(&current->posix_cputimers_work.work,
-		       posix_cpu_timers_work);
+	clear_posix_cputimers_work(current);
 }
 
 /*
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 6bffe5af8cb1..17a283ce2b20 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -1375,6 +1375,13 @@ static inline void tick_nohz_irq_enter(void)
 	now = ktime_get();
 	if (ts->idle_active)
 		tick_nohz_stop_idle(ts, now);
+	/*
+	 * If all CPUs are idle. We may need to update a stale jiffies value.
+	 * Note nohz_full is a special case: a timekeeper is guaranteed to stay
+	 * alive but it might be busy looping with interrupts disabled in some
+	 * rare case (typically stop machine). So we must make sure we have a
+	 * last resort.
+	 */
 	if (ts->tick_stopped)
 		tick_nohz_update_jiffies(now);
 }
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index b348749a9fc6..dcdcb85121e4 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -1306,8 +1306,7 @@ int do_settimeofday64(const struct timespec64 *ts)
 	timekeeping_forward_now(tk);
 
 	xt = tk_xtime(tk);
-	ts_delta.tv_sec = ts->tv_sec - xt.tv_sec;
-	ts_delta.tv_nsec = ts->tv_nsec - xt.tv_nsec;
+	ts_delta = timespec64_sub(*ts, xt);
 
 	if (timespec64_compare(&tk->wall_to_monotonic, &ts_delta) > 0) {
 		ret = -EINVAL;
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index e3d2c23c413d..85f1021ad459 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -2054,26 +2054,28 @@ unsigned long msleep_interruptible(unsigned int msecs)
 EXPORT_SYMBOL(msleep_interruptible);
 
 /**
- * usleep_range - Sleep for an approximate time
- * @min: Minimum time in usecs to sleep
- * @max: Maximum time in usecs to sleep
+ * usleep_range_state - Sleep for an approximate time in a given state
+ * @min:	Minimum time in usecs to sleep
+ * @max:	Maximum time in usecs to sleep
+ * @state:	State of the current task that will be while sleeping
  *
  * In non-atomic context where the exact wakeup time is flexible, use
- * usleep_range() instead of udelay().  The sleep improves responsiveness
+ * usleep_range_state() instead of udelay().  The sleep improves responsiveness
  * by avoiding the CPU-hogging busy-wait of udelay(), and the range reduces
  * power usage by allowing hrtimers to take advantage of an already-
  * scheduled interrupt instead of scheduling a new one just for this sleep.
  */
-void __sched usleep_range(unsigned long min, unsigned long max)
+void __sched usleep_range_state(unsigned long min, unsigned long max,
+				unsigned int state)
 {
 	ktime_t exp = ktime_add_us(ktime_get(), min);
 	u64 delta = (u64)(max - min) * NSEC_PER_USEC;
 
 	for (;;) {
-		__set_current_state(TASK_UNINTERRUPTIBLE);
+		__set_current_state(state);
 		/* Do not return before the requested sleep time has elapsed */
 		if (!schedule_hrtimeout_range(&exp, delta, HRTIMER_MODE_ABS))
 			break;
 	}
 }
-EXPORT_SYMBOL(usleep_range);
+EXPORT_SYMBOL(usleep_range_state);
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 7396488793ff..ae9755037b7e 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1111,8 +1111,6 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_ktime_get_ns_proto;
 	case BPF_FUNC_ktime_get_boot_ns:
 		return &bpf_ktime_get_boot_ns_proto;
-	case BPF_FUNC_ktime_get_coarse_ns:
-		return &bpf_ktime_get_coarse_ns_proto;
 	case BPF_FUNC_tail_call:
 		return &bpf_tail_call_proto;
 	case BPF_FUNC_get_current_pid_tgid:
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 30bc880c3849..be5f6b32a012 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -5217,6 +5217,7 @@ int unregister_ftrace_direct(unsigned long ip, unsigned long addr)
 {
 	struct ftrace_direct_func *direct;
 	struct ftrace_func_entry *entry;
+	struct ftrace_hash *hash;
 	int ret = -ENODEV;
 
 	mutex_lock(&direct_mutex);
@@ -5225,7 +5226,8 @@ int unregister_ftrace_direct(unsigned long ip, unsigned long addr)
 	if (!entry)
 		goto out_unlock;
 
-	if (direct_functions->count == 1)
+	hash = direct_ops.func_hash->filter_hash;
+	if (hash->count == 1)
 		unregister_ftrace_function(&direct_ops);
 
 	ret = ftrace_set_filter_ip(&direct_ops, ip, 1, 0);
@@ -5540,6 +5542,10 @@ int unregister_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr)
 	err = unregister_ftrace_function(ops);
 	remove_direct_functions_hash(hash, addr);
 	mutex_unlock(&direct_mutex);
+
+	/* cleanup for possible another register call */
+	ops->func = NULL;
+	ops->trampoline = 0;
 	return err;
 }
 EXPORT_SYMBOL_GPL(unregister_ftrace_direct_multi);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index f9139dc1262c..88de94da596b 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3812,6 +3812,18 @@ void trace_check_vprintf(struct trace_iterator *iter, const char *fmt,
 		iter->fmt[i] = '\0';
 		trace_seq_vprintf(&iter->seq, iter->fmt, ap);
 
+		/*
+		 * If iter->seq is full, the above call no longer guarantees
+		 * that ap is in sync with fmt processing, and further calls
+		 * to va_arg() can return wrong positional arguments.
+		 *
+		 * Ensure that ap is no longer used in this case.
+		 */
+		if (iter->seq.full) {
+			p = "";
+			break;
+		}
+
 		if (star)
 			len = va_arg(ap, int);
 
@@ -6706,9 +6718,7 @@ waitagain:
 		cnt = PAGE_SIZE - 1;
 
 	/* reset all but tr, trace, and overruns */
-	memset(&iter->seq, 0,
-	       sizeof(struct trace_iterator) -
-	       offsetof(struct trace_iterator, seq));
+	memset_startat(iter, 0, seq);
 	cpumask_clear(iter->started);
 	trace_seq_init(&iter->seq);
 	iter->pos = -1;
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 6b60ab9475ed..38715aa6cfdf 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -1366,14 +1366,26 @@ __event_trigger_test_discard(struct trace_event_file *file,
 	if (eflags & EVENT_FILE_FL_TRIGGER_COND)
 		*tt = event_triggers_call(file, buffer, entry, event);
 
-	if (test_bit(EVENT_FILE_FL_SOFT_DISABLED_BIT, &file->flags) ||
-	    (unlikely(file->flags & EVENT_FILE_FL_FILTERED) &&
-	     !filter_match_preds(file->filter, entry))) {
-		__trace_event_discard_commit(buffer, event);
-		return true;
-	}
+	if (likely(!(file->flags & (EVENT_FILE_FL_SOFT_DISABLED |
+				    EVENT_FILE_FL_FILTERED |
+				    EVENT_FILE_FL_PID_FILTER))))
+		return false;
+
+	if (file->flags & EVENT_FILE_FL_SOFT_DISABLED)
+		goto discard;
+
+	if (file->flags & EVENT_FILE_FL_FILTERED &&
+	    !filter_match_preds(file->filter, entry))
+		goto discard;
+
+	if ((file->flags & EVENT_FILE_FL_PID_FILTER) &&
+	    trace_event_ignore_this_pid(file))
+		goto discard;
 
 	return false;
+ discard:
+	__trace_event_discard_commit(buffer, event);
+	return true;
 }
 
 /**
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 4021b9a79f93..92be9cb1d7d4 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -2678,12 +2678,24 @@ static struct trace_event_file *
 trace_create_new_event(struct trace_event_call *call,
 		       struct trace_array *tr)
 {
+	struct trace_pid_list *no_pid_list;
+	struct trace_pid_list *pid_list;
 	struct trace_event_file *file;
+	unsigned int first;
 
 	file = kmem_cache_alloc(file_cachep, GFP_TRACE);
 	if (!file)
 		return NULL;
 
+	pid_list = rcu_dereference_protected(tr->filtered_pids,
+					     lockdep_is_held(&event_mutex));
+	no_pid_list = rcu_dereference_protected(tr->filtered_no_pids,
+					     lockdep_is_held(&event_mutex));
+
+	if (!trace_pid_list_first(pid_list, &first) ||
+	    !trace_pid_list_first(no_pid_list, &first))
+		file->flags |= EVENT_FILE_FL_PID_FILTER;
+
 	file->event_call = call;
 	file->tr = tr;
 	atomic_set(&file->sm_ref, 0);
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 0abc9a413b4d..319f9c8ca7e7 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -1953,9 +1953,10 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data,
 		if (!hist_field->type)
 			goto free;
 
-		if (field->filter_type == FILTER_STATIC_STRING)
+		if (field->filter_type == FILTER_STATIC_STRING) {
 			hist_field->fn = hist_field_string;
-		else if (field->filter_type == FILTER_DYN_STRING)
+			hist_field->size = field->size;
+		} else if (field->filter_type == FILTER_DYN_STRING)
 			hist_field->fn = hist_field_dynstring;
 		else
 			hist_field->fn = hist_field_pstring;
@@ -2575,27 +2576,27 @@ static struct hist_field *parse_expr(struct hist_trigger_data *hist_data,
 
 	/* Split the expression string at the root operator */
 	if (!sep)
-		goto free;
+		return ERR_PTR(-EINVAL);
+
 	*sep = '\0';
 	operand1_str = str;
 	str = sep+1;
 
-	if (!operand1_str || !str)
-		goto free;
+	/* Binary operator requires both operands */
+	if (*operand1_str == '\0' || *str == '\0')
+		return ERR_PTR(-EINVAL);
 
 	operand_flags = 0;
 
 	/* LHS of string is an expression e.g. a+b in a+b+c */
 	operand1 = parse_expr(hist_data, file, operand1_str, operand_flags, NULL, n_subexprs);
-	if (IS_ERR(operand1)) {
-		ret = PTR_ERR(operand1);
-		operand1 = NULL;
-		goto free;
-	}
+	if (IS_ERR(operand1))
+		return ERR_CAST(operand1);
+
 	if (operand1->flags & HIST_FIELD_FL_STRING) {
 		hist_err(file->tr, HIST_ERR_INVALID_STR_OPERAND, errpos(operand1_str));
 		ret = -EINVAL;
-		goto free;
+		goto free_op1;
 	}
 
 	/* RHS of string is another expression e.g. c in a+b+c */
@@ -2603,13 +2604,12 @@ static struct hist_field *parse_expr(struct hist_trigger_data *hist_data,
 	operand2 = parse_expr(hist_data, file, str, operand_flags, NULL, n_subexprs);
 	if (IS_ERR(operand2)) {
 		ret = PTR_ERR(operand2);
-		operand2 = NULL;
-		goto free;
+		goto free_op1;
 	}
 	if (operand2->flags & HIST_FIELD_FL_STRING) {
 		hist_err(file->tr, HIST_ERR_INVALID_STR_OPERAND, errpos(str));
 		ret = -EINVAL;
-		goto free;
+		goto free_operands;
 	}
 
 	switch (field_op) {
@@ -2627,12 +2627,12 @@ static struct hist_field *parse_expr(struct hist_trigger_data *hist_data,
 		break;
 	default:
 		ret = -EINVAL;
-		goto free;
+		goto free_operands;
 	}
 
 	ret = check_expr_operands(file->tr, operand1, operand2, &var1, &var2);
 	if (ret)
-		goto free;
+		goto free_operands;
 
 	operand_flags = var1 ? var1->flags : operand1->flags;
 	operand2_flags = var2 ? var2->flags : operand2->flags;
@@ -2651,12 +2651,13 @@ static struct hist_field *parse_expr(struct hist_trigger_data *hist_data,
 	expr = create_hist_field(hist_data, NULL, flags, var_name);
 	if (!expr) {
 		ret = -ENOMEM;
-		goto free;
+		goto free_operands;
 	}
 
 	operand1->read_once = true;
 	operand2->read_once = true;
 
+	/* The operands are now owned and free'd by 'expr' */
 	expr->operands[0] = operand1;
 	expr->operands[1] = operand2;
 
@@ -2667,7 +2668,7 @@ static struct hist_field *parse_expr(struct hist_trigger_data *hist_data,
 		if (!divisor) {
 			hist_err(file->tr, HIST_ERR_DIVISION_BY_ZERO, errpos(str));
 			ret = -EDOM;
-			goto free;
+			goto free_expr;
 		}
 
 		/*
@@ -2707,18 +2708,22 @@ static struct hist_field *parse_expr(struct hist_trigger_data *hist_data,
 		expr->type = kstrdup_const(operand1->type, GFP_KERNEL);
 		if (!expr->type) {
 			ret = -ENOMEM;
-			goto free;
+			goto free_expr;
 		}
 
 		expr->name = expr_str(expr, 0);
 	}
 
 	return expr;
-free:
-	destroy_hist_field(operand1, 0);
+
+free_operands:
 	destroy_hist_field(operand2, 0);
-	destroy_hist_field(expr, 0);
+free_op1:
+	destroy_hist_field(operand1, 0);
+	return ERR_PTR(ret);
 
+free_expr:
+	destroy_hist_field(expr, 0);
 	return ERR_PTR(ret);
 }
 
@@ -3024,8 +3029,10 @@ static inline void __update_field_vars(struct tracing_map_elt *elt,
 		if (val->flags & HIST_FIELD_FL_STRING) {
 			char *str = elt_data->field_var_str[j++];
 			char *val_str = (char *)(uintptr_t)var_val;
+			unsigned int size;
 
-			strscpy(str, val_str, STR_VAR_LEN_MAX);
+			size = min(val->size, STR_VAR_LEN_MAX);
+			strscpy(str, val_str, size);
 			var_val = (u64)(uintptr_t)str;
 		}
 		tracing_map_set_var(elt, var_idx, var_val);
@@ -3750,7 +3757,7 @@ static int check_synth_field(struct synth_event *event,
 
 	if (strcmp(field->type, hist_field->type) != 0) {
 		if (field->size != hist_field->size ||
-		    field->is_signed != hist_field->is_signed)
+		    (!field->is_string && field->is_signed != hist_field->is_signed))
 			return -EINVAL;
 	}
 
@@ -4912,6 +4919,7 @@ static void hist_trigger_elt_update(struct hist_trigger_data *hist_data,
 			if (hist_field->flags & HIST_FIELD_FL_STRING) {
 				unsigned int str_start, var_str_idx, idx;
 				char *str, *val_str;
+				unsigned int size;
 
 				str_start = hist_data->n_field_var_str +
 					hist_data->n_save_var_str;
@@ -4920,7 +4928,9 @@ static void hist_trigger_elt_update(struct hist_trigger_data *hist_data,
 
 				str = elt_data->field_var_str[idx];
 				val_str = (char *)(uintptr_t)hist_val;
-				strscpy(str, val_str, STR_VAR_LEN_MAX);
+
+				size = min(hist_field->size, STR_VAR_LEN_MAX);
+				strscpy(str, val_str, size);
 
 				hist_val = (u64)(uintptr_t)str;
 			}
diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c
index 22db3ce95e74..ca9c13b2ecf4 100644
--- a/kernel/trace/trace_events_synth.c
+++ b/kernel/trace/trace_events_synth.c
@@ -1237,9 +1237,8 @@ static int __create_synth_event(const char *name, const char *raw_fields)
 						  argv + consumed, &consumed,
 						  &field_version);
 			if (IS_ERR(field)) {
-				argv_free(argv);
 				ret = PTR_ERR(field);
-				goto err;
+				goto err_free_arg;
 			}
 
 			/*
@@ -1262,18 +1261,19 @@ static int __create_synth_event(const char *name, const char *raw_fields)
 			if (cmd_version > 1 && n_fields_this_loop >= 1) {
 				synth_err(SYNTH_ERR_INVALID_CMD, errpos(field_str));
 				ret = -EINVAL;
-				goto err;
+				goto err_free_arg;
 			}
 
 			fields[n_fields++] = field;
 			if (n_fields == SYNTH_FIELDS_MAX) {
 				synth_err(SYNTH_ERR_TOO_MANY_FIELDS, 0);
 				ret = -EINVAL;
-				goto err;
+				goto err_free_arg;
 			}
 
 			n_fields_this_loop++;
 		}
+		argv_free(argv);
 
 		if (consumed < argc) {
 			synth_err(SYNTH_ERR_INVALID_CMD, 0);
@@ -1281,7 +1281,6 @@ static int __create_synth_event(const char *name, const char *raw_fields)
 			goto err;
 		}
 
-		argv_free(argv);
 	}
 
 	if (n_fields == 0) {
@@ -1307,6 +1306,8 @@ static int __create_synth_event(const char *name, const char *raw_fields)
 	kfree(saved_fields);
 
 	return ret;
+ err_free_arg:
+	argv_free(argv);
  err:
 	for (i = 0; i < n_fields; i++)
 		free_synth_field(fields[i]);
diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c
index 3e4a1651e329..7520d43aed55 100644
--- a/kernel/trace/trace_osnoise.c
+++ b/kernel/trace/trace_osnoise.c
@@ -55,7 +55,8 @@ struct osnoise_instance {
 	struct list_head	list;
 	struct trace_array	*tr;
 };
-struct list_head osnoise_instances;
+
+static struct list_head osnoise_instances;
 
 static bool osnoise_has_registered_instances(void)
 {
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 0a5c0db3137e..f5f0039d31e5 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -1313,6 +1313,7 @@ static int uprobe_perf_open(struct trace_event_call *call,
 		return 0;
 
 	list_for_each_entry(pos, trace_probe_probe_list(tp), list) {
+		tu = container_of(pos, struct trace_uprobe, tp);
 		err = uprobe_apply(tu->inode, tu->offset, &tu->consumer, true);
 		if (err) {
 			uprobe_perf_close(call, event);
diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c
index 39bb56d2dcbe..9628b5571846 100644
--- a/kernel/trace/tracing_map.c
+++ b/kernel/trace/tracing_map.c
@@ -15,6 +15,7 @@
 #include <linux/jhash.h>
 #include <linux/slab.h>
 #include <linux/sort.h>
+#include <linux/kmemleak.h>
 
 #include "tracing_map.h"
 #include "trace.h"
@@ -307,6 +308,7 @@ static void tracing_map_array_free(struct tracing_map_array *a)
 	for (i = 0; i < a->n_pages; i++) {
 		if (!a->pages[i])
 			break;
+		kmemleak_free(a->pages[i]);
 		free_page((unsigned long)a->pages[i]);
 	}
 
@@ -342,6 +344,7 @@ static struct tracing_map_array *tracing_map_array_alloc(unsigned int n_elts,
 		a->pages[i] = (void *)get_zeroed_page(GFP_KERNEL);
 		if (!a->pages[i])
 			goto free;
+		kmemleak_alloc(a->pages[i], PAGE_SIZE, 1, GFP_KERNEL);
 	}
  out:
 	return a;
diff --git a/kernel/ucount.c b/kernel/ucount.c
index 4f5613dac227..7b32c356ebc5 100644
--- a/kernel/ucount.c
+++ b/kernel/ucount.c
@@ -264,15 +264,16 @@ void dec_ucount(struct ucounts *ucounts, enum ucount_type type)
 long inc_rlimit_ucounts(struct ucounts *ucounts, enum ucount_type type, long v)
 {
 	struct ucounts *iter;
+	long max = LONG_MAX;
 	long ret = 0;
 
 	for (iter = ucounts; iter; iter = iter->ns->ucounts) {
-		long max = READ_ONCE(iter->ns->ucount_max[type]);
 		long new = atomic_long_add_return(v, &iter->ucount[type]);
 		if (new < 0 || new > max)
 			ret = LONG_MAX;
 		else if (iter == ucounts)
 			ret = new;
+		max = READ_ONCE(iter->ns->ucount_max[type]);
 	}
 	return ret;
 }
@@ -312,15 +313,16 @@ long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum ucount_type type)
 {
 	/* Caller must hold a reference to ucounts */
 	struct ucounts *iter;
+	long max = LONG_MAX;
 	long dec, ret = 0;
 
 	for (iter = ucounts; iter; iter = iter->ns->ucounts) {
-		long max = READ_ONCE(iter->ns->ucount_max[type]);
 		long new = atomic_long_add_return(1, &iter->ucount[type]);
 		if (new < 0 || new > max)
 			goto unwind;
 		if (iter == ucounts)
 			ret = new;
+		max = READ_ONCE(iter->ns->ucount_max[type]);
 		/*
 		 * Grab an extra ucount reference for the caller when
 		 * the rlimit count was previously 0.
@@ -339,15 +341,16 @@ unwind:
 	return 0;
 }
 
-bool is_ucounts_overlimit(struct ucounts *ucounts, enum ucount_type type, unsigned long max)
+bool is_ucounts_overlimit(struct ucounts *ucounts, enum ucount_type type, unsigned long rlimit)
 {
 	struct ucounts *iter;
-	if (get_ucounts_value(ucounts, type) > max)
-		return true;
+	long max = rlimit;
+	if (rlimit > LONG_MAX)
+		max = LONG_MAX;
 	for (iter = ucounts; iter; iter = iter->ns->ucounts) {
-		max = READ_ONCE(iter->ns->ucount_max[type]);
 		if (get_ucounts_value(iter, type) > max)
 			return true;
+		max = READ_ONCE(iter->ns->ucount_max[type]);
 	}
 	return false;
 }
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 9ef7ce18b4f5..5e14e32056ad 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -316,6 +316,7 @@ config DEBUG_INFO_BTF
 	bool "Generate BTF typeinfo"
 	depends on !DEBUG_INFO_SPLIT && !DEBUG_INFO_REDUCED
 	depends on !GCC_PLUGIN_RANDSTRUCT || COMPILE_TEST
+	depends on BPF_SYSCALL
 	help
 	  Generate deduplicated BTF type information from DWARF debug info.
 	  Turning this on expects presence of pahole tool, which will convert
@@ -346,8 +347,9 @@ config FRAME_WARN
 	int "Warn for stack frames larger than"
 	range 0 8192
 	default 2048 if GCC_PLUGIN_LATENT_ENTROPY
-	default 1536 if (!64BIT && (PARISC || XTENSA))
-	default 1024 if (!64BIT && !PARISC)
+	default 2048 if PARISC
+	default 1536 if (!64BIT && XTENSA)
+	default 1024 if !64BIT
 	default 2048 if 64BIT
 	help
 	  Tell gcc to warn at build time for stack frames larger than this.
diff --git a/lib/decompress_unzstd.c b/lib/decompress_unzstd.c
index 6b629ab31c1e..a512b99ae16a 100644
--- a/lib/decompress_unzstd.c
+++ b/lib/decompress_unzstd.c
@@ -68,11 +68,7 @@
 #ifdef STATIC
 # define UNZSTD_PREBOOT
 # include "xxhash.c"
-# include "zstd/entropy_common.c"
-# include "zstd/fse_decompress.c"
-# include "zstd/huf_decompress.c"
-# include "zstd/zstd_common.c"
-# include "zstd/decompress.c"
+# include "zstd/decompress_sources.h"
 #endif
 
 #include <linux/decompress/mm.h>
@@ -91,11 +87,15 @@
 
 static int INIT handle_zstd_error(size_t ret, void (*error)(char *x))
 {
-	const int err = ZSTD_getErrorCode(ret);
+	const zstd_error_code err = zstd_get_error_code(ret);
 
-	if (!ZSTD_isError(ret))
+	if (!zstd_is_error(ret))
 		return 0;
 
+	/*
+	 * zstd_get_error_name() cannot be used because error takes a char *
+	 * not a const char *
+	 */
 	switch (err) {
 	case ZSTD_error_memory_allocation:
 		error("ZSTD decompressor ran out of memory");
@@ -124,28 +124,28 @@ static int INIT decompress_single(const u8 *in_buf, long in_len, u8 *out_buf,
 				  long out_len, long *in_pos,
 				  void (*error)(char *x))
 {
-	const size_t wksp_size = ZSTD_DCtxWorkspaceBound();
+	const size_t wksp_size = zstd_dctx_workspace_bound();
 	void *wksp = large_malloc(wksp_size);
-	ZSTD_DCtx *dctx = ZSTD_initDCtx(wksp, wksp_size);
+	zstd_dctx *dctx = zstd_init_dctx(wksp, wksp_size);
 	int err;
 	size_t ret;
 
 	if (dctx == NULL) {
-		error("Out of memory while allocating ZSTD_DCtx");
+		error("Out of memory while allocating zstd_dctx");
 		err = -1;
 		goto out;
 	}
 	/*
 	 * Find out how large the frame actually is, there may be junk at
-	 * the end of the frame that ZSTD_decompressDCtx() can't handle.
+	 * the end of the frame that zstd_decompress_dctx() can't handle.
 	 */
-	ret = ZSTD_findFrameCompressedSize(in_buf, in_len);
+	ret = zstd_find_frame_compressed_size(in_buf, in_len);
 	err = handle_zstd_error(ret, error);
 	if (err)
 		goto out;
 	in_len = (long)ret;
 
-	ret = ZSTD_decompressDCtx(dctx, out_buf, out_len, in_buf, in_len);
+	ret = zstd_decompress_dctx(dctx, out_buf, out_len, in_buf, in_len);
 	err = handle_zstd_error(ret, error);
 	if (err)
 		goto out;
@@ -167,14 +167,14 @@ static int INIT __unzstd(unsigned char *in_buf, long in_len,
 			 long *in_pos,
 			 void (*error)(char *x))
 {
-	ZSTD_inBuffer in;
-	ZSTD_outBuffer out;
-	ZSTD_frameParams params;
+	zstd_in_buffer in;
+	zstd_out_buffer out;
+	zstd_frame_header header;
 	void *in_allocated = NULL;
 	void *out_allocated = NULL;
 	void *wksp = NULL;
 	size_t wksp_size;
-	ZSTD_DStream *dstream;
+	zstd_dstream *dstream;
 	int err;
 	size_t ret;
 
@@ -238,13 +238,13 @@ static int INIT __unzstd(unsigned char *in_buf, long in_len,
 	out.size = out_len;
 
 	/*
-	 * We need to know the window size to allocate the ZSTD_DStream.
+	 * We need to know the window size to allocate the zstd_dstream.
 	 * Since we are streaming, we need to allocate a buffer for the sliding
 	 * window. The window size varies from 1 KB to ZSTD_WINDOWSIZE_MAX
 	 * (8 MB), so it is important to use the actual value so as not to
 	 * waste memory when it is smaller.
 	 */
-	ret = ZSTD_getFrameParams(&params, in.src, in.size);
+	ret = zstd_get_frame_header(&header, in.src, in.size);
 	err = handle_zstd_error(ret, error);
 	if (err)
 		goto out;
@@ -253,19 +253,19 @@ static int INIT __unzstd(unsigned char *in_buf, long in_len,
 		err = -1;
 		goto out;
 	}
-	if (params.windowSize > ZSTD_WINDOWSIZE_MAX) {
+	if (header.windowSize > ZSTD_WINDOWSIZE_MAX) {
 		error("ZSTD-compressed data has too large a window size");
 		err = -1;
 		goto out;
 	}
 
 	/*
-	 * Allocate the ZSTD_DStream now that we know how much memory is
+	 * Allocate the zstd_dstream now that we know how much memory is
 	 * required.
 	 */
-	wksp_size = ZSTD_DStreamWorkspaceBound(params.windowSize);
+	wksp_size = zstd_dstream_workspace_bound(header.windowSize);
 	wksp = large_malloc(wksp_size);
-	dstream = ZSTD_initDStream(params.windowSize, wksp, wksp_size);
+	dstream = zstd_init_dstream(header.windowSize, wksp, wksp_size);
 	if (dstream == NULL) {
 		error("Out of memory while allocating ZSTD_DStream");
 		err = -1;
@@ -298,7 +298,7 @@ static int INIT __unzstd(unsigned char *in_buf, long in_len,
 			in.size = in_len;
 		}
 		/* Returns zero when the frame is complete. */
-		ret = ZSTD_decompressStream(dstream, &out, &in);
+		ret = zstd_decompress_stream(dstream, &out, &in);
 		err = handle_zstd_error(ret, error);
 		if (err)
 			goto out;
diff --git a/lib/nmi_backtrace.c b/lib/nmi_backtrace.c
index f9e89001b52e..199ab201d501 100644
--- a/lib/nmi_backtrace.c
+++ b/lib/nmi_backtrace.c
@@ -75,6 +75,12 @@ void nmi_trigger_cpumask_backtrace(const cpumask_t *mask,
 		touch_softlockup_watchdog();
 	}
 
+	/*
+	 * Force flush any remote buffers that might be stuck in IRQ context
+	 * and therefore could not run their irq_work.
+	 */
+	printk_trigger_flush();
+
 	clear_bit_unlock(0, &backtrace_flag);
 	put_cpu();
 }
diff --git a/lib/siphash.c b/lib/siphash.c
index a90112ee72a1..72b9068ab57b 100644
--- a/lib/siphash.c
+++ b/lib/siphash.c
@@ -49,6 +49,7 @@
 	SIPROUND; \
 	return (v0 ^ v1) ^ (v2 ^ v3);
 
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
 u64 __siphash_aligned(const void *data, size_t len, const siphash_key_t *key)
 {
 	const u8 *end = data + len - (len % sizeof(u64));
@@ -80,8 +81,8 @@ u64 __siphash_aligned(const void *data, size_t len, const siphash_key_t *key)
 	POSTAMBLE
 }
 EXPORT_SYMBOL(__siphash_aligned);
+#endif
 
-#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
 u64 __siphash_unaligned(const void *data, size_t len, const siphash_key_t *key)
 {
 	const u8 *end = data + len - (len % sizeof(u64));
@@ -113,7 +114,6 @@ u64 __siphash_unaligned(const void *data, size_t len, const siphash_key_t *key)
 	POSTAMBLE
 }
 EXPORT_SYMBOL(__siphash_unaligned);
-#endif
 
 /**
  * siphash_1u64 - compute 64-bit siphash PRF value of a u64
@@ -250,6 +250,7 @@ EXPORT_SYMBOL(siphash_3u32);
 	HSIPROUND; \
 	return (v0 ^ v1) ^ (v2 ^ v3);
 
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
 u32 __hsiphash_aligned(const void *data, size_t len, const hsiphash_key_t *key)
 {
 	const u8 *end = data + len - (len % sizeof(u64));
@@ -280,8 +281,8 @@ u32 __hsiphash_aligned(const void *data, size_t len, const hsiphash_key_t *key)
 	HPOSTAMBLE
 }
 EXPORT_SYMBOL(__hsiphash_aligned);
+#endif
 
-#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
 u32 __hsiphash_unaligned(const void *data, size_t len,
 			 const hsiphash_key_t *key)
 {
@@ -313,7 +314,6 @@ u32 __hsiphash_unaligned(const void *data, size_t len,
 	HPOSTAMBLE
 }
 EXPORT_SYMBOL(__hsiphash_unaligned);
-#endif
 
 /**
  * hsiphash_1u32 - compute 64-bit hsiphash PRF value of a u32
@@ -418,6 +418,7 @@ EXPORT_SYMBOL(hsiphash_4u32);
 	HSIPROUND; \
 	return v1 ^ v3;
 
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
 u32 __hsiphash_aligned(const void *data, size_t len, const hsiphash_key_t *key)
 {
 	const u8 *end = data + len - (len % sizeof(u32));
@@ -438,8 +439,8 @@ u32 __hsiphash_aligned(const void *data, size_t len, const hsiphash_key_t *key)
 	HPOSTAMBLE
 }
 EXPORT_SYMBOL(__hsiphash_aligned);
+#endif
 
-#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
 u32 __hsiphash_unaligned(const void *data, size_t len,
 			 const hsiphash_key_t *key)
 {
@@ -461,7 +462,6 @@ u32 __hsiphash_unaligned(const void *data, size_t len,
 	HPOSTAMBLE
 }
 EXPORT_SYMBOL(__hsiphash_unaligned);
-#endif
 
 /**
  * hsiphash_1u32 - compute 32-bit hsiphash PRF value of a u32
diff --git a/lib/test_kasan.c b/lib/test_kasan.c
index 67ed689a0b1b..0643573f8686 100644
--- a/lib/test_kasan.c
+++ b/lib/test_kasan.c
@@ -869,6 +869,7 @@ static void kasan_memchr(struct kunit *test)
 	ptr = kmalloc(size, GFP_KERNEL | __GFP_ZERO);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
 
+	OPTIMIZER_HIDE_VAR(size);
 	KUNIT_EXPECT_KASAN_FAIL(test,
 		kasan_ptr_result = memchr(ptr, '1', size + 1));
 
@@ -894,6 +895,7 @@ static void kasan_memcmp(struct kunit *test)
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
 	memset(arr, 0, sizeof(arr));
 
+	OPTIMIZER_HIDE_VAR(size);
 	KUNIT_EXPECT_KASAN_FAIL(test,
 		kasan_int_result = memcmp(ptr, arr, size+1));
 	kfree(ptr);
diff --git a/lib/zstd/Makefile b/lib/zstd/Makefile
index f5d778e7e5c7..fc45339fc3a3 100644
--- a/lib/zstd/Makefile
+++ b/lib/zstd/Makefile
@@ -1,10 +1,44 @@
-# SPDX-License-Identifier: GPL-2.0-only
+# SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause
+# ################################################################
+# Copyright (c) Facebook, Inc.
+# All rights reserved.
+#
+# This source code is licensed under both the BSD-style license (found in the
+# LICENSE file in the root directory of this source tree) and the GPLv2 (found
+# in the COPYING file in the root directory of this source tree).
+# You may select, at your option, one of the above-listed licenses.
+# ################################################################
 obj-$(CONFIG_ZSTD_COMPRESS) += zstd_compress.o
 obj-$(CONFIG_ZSTD_DECOMPRESS) += zstd_decompress.o
 
-ccflags-y += -O3
+zstd_compress-y := \
+		zstd_compress_module.o \
+		common/debug.o \
+		common/entropy_common.o \
+		common/error_private.o \
+		common/fse_decompress.o \
+		common/zstd_common.o \
+		compress/fse_compress.o \
+		compress/hist.o \
+		compress/huf_compress.o \
+		compress/zstd_compress.o \
+		compress/zstd_compress_literals.o \
+		compress/zstd_compress_sequences.o \
+		compress/zstd_compress_superblock.o \
+		compress/zstd_double_fast.o \
+		compress/zstd_fast.o \
+		compress/zstd_lazy.o \
+		compress/zstd_ldm.o \
+		compress/zstd_opt.o \
 
-zstd_compress-y := fse_compress.o huf_compress.o compress.o \
-		   entropy_common.o fse_decompress.o zstd_common.o
-zstd_decompress-y := huf_decompress.o decompress.o \
-		     entropy_common.o fse_decompress.o zstd_common.o
+zstd_decompress-y := \
+		zstd_decompress_module.o \
+		common/debug.o \
+		common/entropy_common.o \
+		common/error_private.o \
+		common/fse_decompress.o \
+		common/zstd_common.o \
+		decompress/huf_decompress.o \
+		decompress/zstd_ddict.o \
+		decompress/zstd_decompress.o \
+		decompress/zstd_decompress_block.o \
diff --git a/lib/zstd/bitstream.h b/lib/zstd/bitstream.h
deleted file mode 100644
index 5d6343c1a909..000000000000
--- a/lib/zstd/bitstream.h
+++ /dev/null
@@ -1,380 +0,0 @@
-/*
- * bitstream
- * Part of FSE library
- * header file (to include)
- * Copyright (C) 2013-2016, Yann Collet.
- *
- * BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are
- * met:
- *
- *   * Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- *   * Redistributions in binary form must reproduce the above
- * copyright notice, this list of conditions and the following disclaimer
- * in the documentation and/or other materials provided with the
- * distribution.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * 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. This program is dual-licensed; you may select
- * either version 2 of the GNU General Public License ("GPL") or BSD license
- * ("BSD").
- *
- * You can contact the author at :
- * - Source repository : https://github.com/Cyan4973/FiniteStateEntropy
- */
-#ifndef BITSTREAM_H_MODULE
-#define BITSTREAM_H_MODULE
-
-/*
-*  This API consists of small unitary functions, which must be inlined for best performance.
-*  Since link-time-optimization is not available for all compilers,
-*  these functions are defined into a .h to be included.
-*/
-
-/*-****************************************
-*  Dependencies
-******************************************/
-#include "error_private.h" /* error codes and messages */
-#include "mem.h"	   /* unaligned access routines */
-
-/*=========================================
-*  Target specific
-=========================================*/
-#define STREAM_ACCUMULATOR_MIN_32 25
-#define STREAM_ACCUMULATOR_MIN_64 57
-#define STREAM_ACCUMULATOR_MIN ((U32)(ZSTD_32bits() ? STREAM_ACCUMULATOR_MIN_32 : STREAM_ACCUMULATOR_MIN_64))
-
-/*-******************************************
-*  bitStream encoding API (write forward)
-********************************************/
-/* bitStream can mix input from multiple sources.
-*  A critical property of these streams is that they encode and decode in **reverse** direction.
-*  So the first bit sequence you add will be the last to be read, like a LIFO stack.
-*/
-typedef struct {
-	size_t bitContainer;
-	int bitPos;
-	char *startPtr;
-	char *ptr;
-	char *endPtr;
-} BIT_CStream_t;
-
-ZSTD_STATIC size_t BIT_initCStream(BIT_CStream_t *bitC, void *dstBuffer, size_t dstCapacity);
-ZSTD_STATIC void BIT_addBits(BIT_CStream_t *bitC, size_t value, unsigned nbBits);
-ZSTD_STATIC void BIT_flushBits(BIT_CStream_t *bitC);
-ZSTD_STATIC size_t BIT_closeCStream(BIT_CStream_t *bitC);
-
-/* Start with initCStream, providing the size of buffer to write into.
-*  bitStream will never write outside of this buffer.
-*  `dstCapacity` must be >= sizeof(bitD->bitContainer), otherwise @return will be an error code.
-*
-*  bits are first added to a local register.
-*  Local register is size_t, hence 64-bits on 64-bits systems, or 32-bits on 32-bits systems.
-*  Writing data into memory is an explicit operation, performed by the flushBits function.
-*  Hence keep track how many bits are potentially stored into local register to avoid register overflow.
-*  After a flushBits, a maximum of 7 bits might still be stored into local register.
-*
-*  Avoid storing elements of more than 24 bits if you want compatibility with 32-bits bitstream readers.
-*
-*  Last operation is to close the bitStream.
-*  The function returns the final size of CStream in bytes.
-*  If data couldn't fit into `dstBuffer`, it will return a 0 ( == not storable)
-*/
-
-/*-********************************************
-*  bitStream decoding API (read backward)
-**********************************************/
-typedef struct {
-	size_t bitContainer;
-	unsigned bitsConsumed;
-	const char *ptr;
-	const char *start;
-} BIT_DStream_t;
-
-typedef enum {
-	BIT_DStream_unfinished = 0,
-	BIT_DStream_endOfBuffer = 1,
-	BIT_DStream_completed = 2,
-	BIT_DStream_overflow = 3
-} BIT_DStream_status; /* result of BIT_reloadDStream() */
-/* 1,2,4,8 would be better for bitmap combinations, but slows down performance a bit ... :( */
-
-ZSTD_STATIC size_t BIT_initDStream(BIT_DStream_t *bitD, const void *srcBuffer, size_t srcSize);
-ZSTD_STATIC size_t BIT_readBits(BIT_DStream_t *bitD, unsigned nbBits);
-ZSTD_STATIC BIT_DStream_status BIT_reloadDStream(BIT_DStream_t *bitD);
-ZSTD_STATIC unsigned BIT_endOfDStream(const BIT_DStream_t *bitD);
-
-/* Start by invoking BIT_initDStream().
-*  A chunk of the bitStream is then stored into a local register.
-*  Local register size is 64-bits on 64-bits systems, 32-bits on 32-bits systems (size_t).
-*  You can then retrieve bitFields stored into the local register, **in reverse order**.
-*  Local register is explicitly reloaded from memory by the BIT_reloadDStream() method.
-*  A reload guarantee a minimum of ((8*sizeof(bitD->bitContainer))-7) bits when its result is BIT_DStream_unfinished.
-*  Otherwise, it can be less than that, so proceed accordingly.
-*  Checking if DStream has reached its end can be performed with BIT_endOfDStream().
-*/
-
-/*-****************************************
-*  unsafe API
-******************************************/
-ZSTD_STATIC void BIT_addBitsFast(BIT_CStream_t *bitC, size_t value, unsigned nbBits);
-/* faster, but works only if value is "clean", meaning all high bits above nbBits are 0 */
-
-ZSTD_STATIC void BIT_flushBitsFast(BIT_CStream_t *bitC);
-/* unsafe version; does not check buffer overflow */
-
-ZSTD_STATIC size_t BIT_readBitsFast(BIT_DStream_t *bitD, unsigned nbBits);
-/* faster, but works only if nbBits >= 1 */
-
-/*-**************************************************************
-*  Internal functions
-****************************************************************/
-ZSTD_STATIC unsigned BIT_highbit32(register U32 val) { return 31 - __builtin_clz(val); }
-
-/*=====    Local Constants   =====*/
-static const unsigned BIT_mask[] = {0,       1,       3,       7,	0xF,      0x1F,     0x3F,     0x7F,      0xFF,
-				    0x1FF,   0x3FF,   0x7FF,   0xFFF,    0x1FFF,   0x3FFF,   0x7FFF,   0xFFFF,    0x1FFFF,
-				    0x3FFFF, 0x7FFFF, 0xFFFFF, 0x1FFFFF, 0x3FFFFF, 0x7FFFFF, 0xFFFFFF, 0x1FFFFFF, 0x3FFFFFF}; /* up to 26 bits */
-
-/*-**************************************************************
-*  bitStream encoding
-****************************************************************/
-/*! BIT_initCStream() :
- *  `dstCapacity` must be > sizeof(void*)
- *  @return : 0 if success,
-			  otherwise an error code (can be tested using ERR_isError() ) */
-ZSTD_STATIC size_t BIT_initCStream(BIT_CStream_t *bitC, void *startPtr, size_t dstCapacity)
-{
-	bitC->bitContainer = 0;
-	bitC->bitPos = 0;
-	bitC->startPtr = (char *)startPtr;
-	bitC->ptr = bitC->startPtr;
-	bitC->endPtr = bitC->startPtr + dstCapacity - sizeof(bitC->ptr);
-	if (dstCapacity <= sizeof(bitC->ptr))
-		return ERROR(dstSize_tooSmall);
-	return 0;
-}
-
-/*! BIT_addBits() :
-	can add up to 26 bits into `bitC`.
-	Does not check for register overflow ! */
-ZSTD_STATIC void BIT_addBits(BIT_CStream_t *bitC, size_t value, unsigned nbBits)
-{
-	bitC->bitContainer |= (value & BIT_mask[nbBits]) << bitC->bitPos;
-	bitC->bitPos += nbBits;
-}
-
-/*! BIT_addBitsFast() :
- *  works only if `value` is _clean_, meaning all high bits above nbBits are 0 */
-ZSTD_STATIC void BIT_addBitsFast(BIT_CStream_t *bitC, size_t value, unsigned nbBits)
-{
-	bitC->bitContainer |= value << bitC->bitPos;
-	bitC->bitPos += nbBits;
-}
-
-/*! BIT_flushBitsFast() :
- *  unsafe version; does not check buffer overflow */
-ZSTD_STATIC void BIT_flushBitsFast(BIT_CStream_t *bitC)
-{
-	size_t const nbBytes = bitC->bitPos >> 3;
-	ZSTD_writeLEST(bitC->ptr, bitC->bitContainer);
-	bitC->ptr += nbBytes;
-	bitC->bitPos &= 7;
-	bitC->bitContainer >>= nbBytes * 8; /* if bitPos >= sizeof(bitContainer)*8 --> undefined behavior */
-}
-
-/*! BIT_flushBits() :
- *  safe version; check for buffer overflow, and prevents it.
- *  note : does not signal buffer overflow. This will be revealed later on using BIT_closeCStream() */
-ZSTD_STATIC void BIT_flushBits(BIT_CStream_t *bitC)
-{
-	size_t const nbBytes = bitC->bitPos >> 3;
-	ZSTD_writeLEST(bitC->ptr, bitC->bitContainer);
-	bitC->ptr += nbBytes;
-	if (bitC->ptr > bitC->endPtr)
-		bitC->ptr = bitC->endPtr;
-	bitC->bitPos &= 7;
-	bitC->bitContainer >>= nbBytes * 8; /* if bitPos >= sizeof(bitContainer)*8 --> undefined behavior */
-}
-
-/*! BIT_closeCStream() :
- *  @return : size of CStream, in bytes,
-			  or 0 if it could not fit into dstBuffer */
-ZSTD_STATIC size_t BIT_closeCStream(BIT_CStream_t *bitC)
-{
-	BIT_addBitsFast(bitC, 1, 1); /* endMark */
-	BIT_flushBits(bitC);
-
-	if (bitC->ptr >= bitC->endPtr)
-		return 0; /* doesn't fit within authorized budget : cancel */
-
-	return (bitC->ptr - bitC->startPtr) + (bitC->bitPos > 0);
-}
-
-/*-********************************************************
-* bitStream decoding
-**********************************************************/
-/*! BIT_initDStream() :
-*   Initialize a BIT_DStream_t.
-*   `bitD` : a pointer to an already allocated BIT_DStream_t structure.
-*   `srcSize` must be the *exact* size of the bitStream, in bytes.
-*   @return : size of stream (== srcSize) or an errorCode if a problem is detected
-*/
-ZSTD_STATIC size_t BIT_initDStream(BIT_DStream_t *bitD, const void *srcBuffer, size_t srcSize)
-{
-	if (srcSize < 1) {
-		memset(bitD, 0, sizeof(*bitD));
-		return ERROR(srcSize_wrong);
-	}
-
-	if (srcSize >= sizeof(bitD->bitContainer)) { /* normal case */
-		bitD->start = (const char *)srcBuffer;
-		bitD->ptr = (const char *)srcBuffer + srcSize - sizeof(bitD->bitContainer);
-		bitD->bitContainer = ZSTD_readLEST(bitD->ptr);
-		{
-			BYTE const lastByte = ((const BYTE *)srcBuffer)[srcSize - 1];
-			bitD->bitsConsumed = lastByte ? 8 - BIT_highbit32(lastByte) : 0; /* ensures bitsConsumed is always set */
-			if (lastByte == 0)
-				return ERROR(GENERIC); /* endMark not present */
-		}
-	} else {
-		bitD->start = (const char *)srcBuffer;
-		bitD->ptr = bitD->start;
-		bitD->bitContainer = *(const BYTE *)(bitD->start);
-		switch (srcSize) {
-		case 7: bitD->bitContainer += (size_t)(((const BYTE *)(srcBuffer))[6]) << (sizeof(bitD->bitContainer) * 8 - 16);
-			fallthrough;
-		case 6: bitD->bitContainer += (size_t)(((const BYTE *)(srcBuffer))[5]) << (sizeof(bitD->bitContainer) * 8 - 24);
-			fallthrough;
-		case 5: bitD->bitContainer += (size_t)(((const BYTE *)(srcBuffer))[4]) << (sizeof(bitD->bitContainer) * 8 - 32);
-			fallthrough;
-		case 4: bitD->bitContainer += (size_t)(((const BYTE *)(srcBuffer))[3]) << 24;
-			fallthrough;
-		case 3: bitD->bitContainer += (size_t)(((const BYTE *)(srcBuffer))[2]) << 16;
-			fallthrough;
-		case 2: bitD->bitContainer += (size_t)(((const BYTE *)(srcBuffer))[1]) << 8;
-			fallthrough;
-		default:;
-		}
-		{
-			BYTE const lastByte = ((const BYTE *)srcBuffer)[srcSize - 1];
-			bitD->bitsConsumed = lastByte ? 8 - BIT_highbit32(lastByte) : 0;
-			if (lastByte == 0)
-				return ERROR(GENERIC); /* endMark not present */
-		}
-		bitD->bitsConsumed += (U32)(sizeof(bitD->bitContainer) - srcSize) * 8;
-	}
-
-	return srcSize;
-}
-
-ZSTD_STATIC size_t BIT_getUpperBits(size_t bitContainer, U32 const start) { return bitContainer >> start; }
-
-ZSTD_STATIC size_t BIT_getMiddleBits(size_t bitContainer, U32 const start, U32 const nbBits) { return (bitContainer >> start) & BIT_mask[nbBits]; }
-
-ZSTD_STATIC size_t BIT_getLowerBits(size_t bitContainer, U32 const nbBits) { return bitContainer & BIT_mask[nbBits]; }
-
-/*! BIT_lookBits() :
- *  Provides next n bits from local register.
- *  local register is not modified.
- *  On 32-bits, maxNbBits==24.
- *  On 64-bits, maxNbBits==56.
- *  @return : value extracted
- */
-ZSTD_STATIC size_t BIT_lookBits(const BIT_DStream_t *bitD, U32 nbBits)
-{
-	U32 const bitMask = sizeof(bitD->bitContainer) * 8 - 1;
-	return ((bitD->bitContainer << (bitD->bitsConsumed & bitMask)) >> 1) >> ((bitMask - nbBits) & bitMask);
-}
-
-/*! BIT_lookBitsFast() :
-*   unsafe version; only works only if nbBits >= 1 */
-ZSTD_STATIC size_t BIT_lookBitsFast(const BIT_DStream_t *bitD, U32 nbBits)
-{
-	U32 const bitMask = sizeof(bitD->bitContainer) * 8 - 1;
-	return (bitD->bitContainer << (bitD->bitsConsumed & bitMask)) >> (((bitMask + 1) - nbBits) & bitMask);
-}
-
-ZSTD_STATIC void BIT_skipBits(BIT_DStream_t *bitD, U32 nbBits) { bitD->bitsConsumed += nbBits; }
-
-/*! BIT_readBits() :
- *  Read (consume) next n bits from local register and update.
- *  Pay attention to not read more than nbBits contained into local register.
- *  @return : extracted value.
- */
-ZSTD_STATIC size_t BIT_readBits(BIT_DStream_t *bitD, U32 nbBits)
-{
-	size_t const value = BIT_lookBits(bitD, nbBits);
-	BIT_skipBits(bitD, nbBits);
-	return value;
-}
-
-/*! BIT_readBitsFast() :
-*   unsafe version; only works only if nbBits >= 1 */
-ZSTD_STATIC size_t BIT_readBitsFast(BIT_DStream_t *bitD, U32 nbBits)
-{
-	size_t const value = BIT_lookBitsFast(bitD, nbBits);
-	BIT_skipBits(bitD, nbBits);
-	return value;
-}
-
-/*! BIT_reloadDStream() :
-*   Refill `bitD` from buffer previously set in BIT_initDStream() .
-*   This function is safe, it guarantees it will not read beyond src buffer.
-*   @return : status of `BIT_DStream_t` internal register.
-			  if status == BIT_DStream_unfinished, internal register is filled with >= (sizeof(bitD->bitContainer)*8 - 7) bits */
-ZSTD_STATIC BIT_DStream_status BIT_reloadDStream(BIT_DStream_t *bitD)
-{
-	if (bitD->bitsConsumed > (sizeof(bitD->bitContainer) * 8)) /* should not happen => corruption detected */
-		return BIT_DStream_overflow;
-
-	if (bitD->ptr >= bitD->start + sizeof(bitD->bitContainer)) {
-		bitD->ptr -= bitD->bitsConsumed >> 3;
-		bitD->bitsConsumed &= 7;
-		bitD->bitContainer = ZSTD_readLEST(bitD->ptr);
-		return BIT_DStream_unfinished;
-	}
-	if (bitD->ptr == bitD->start) {
-		if (bitD->bitsConsumed < sizeof(bitD->bitContainer) * 8)
-			return BIT_DStream_endOfBuffer;
-		return BIT_DStream_completed;
-	}
-	{
-		U32 nbBytes = bitD->bitsConsumed >> 3;
-		BIT_DStream_status result = BIT_DStream_unfinished;
-		if (bitD->ptr - nbBytes < bitD->start) {
-			nbBytes = (U32)(bitD->ptr - bitD->start); /* ptr > start */
-			result = BIT_DStream_endOfBuffer;
-		}
-		bitD->ptr -= nbBytes;
-		bitD->bitsConsumed -= nbBytes * 8;
-		bitD->bitContainer = ZSTD_readLEST(bitD->ptr); /* reminder : srcSize > sizeof(bitD) */
-		return result;
-	}
-}
-
-/*! BIT_endOfDStream() :
-*   @return Tells if DStream has exactly reached its end (all bits consumed).
-*/
-ZSTD_STATIC unsigned BIT_endOfDStream(const BIT_DStream_t *DStream)
-{
-	return ((DStream->ptr == DStream->start) && (DStream->bitsConsumed == sizeof(DStream->bitContainer) * 8));
-}
-
-#endif /* BITSTREAM_H_MODULE */
diff --git a/lib/zstd/common/bitstream.h b/lib/zstd/common/bitstream.h
new file mode 100644
index 000000000000..28248abe8612
--- /dev/null
+++ b/lib/zstd/common/bitstream.h
@@ -0,0 +1,437 @@
+/* ******************************************************************
+ * bitstream
+ * Part of FSE library
+ * Copyright (c) Yann Collet, Facebook, Inc.
+ *
+ * You can contact the author at :
+ * - Source repository : https://github.com/Cyan4973/FiniteStateEntropy
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+****************************************************************** */
+#ifndef BITSTREAM_H_MODULE
+#define BITSTREAM_H_MODULE
+
+/*
+*  This API consists of small unitary functions, which must be inlined for best performance.
+*  Since link-time-optimization is not available for all compilers,
+*  these functions are defined into a .h to be included.
+*/
+
+/*-****************************************
+*  Dependencies
+******************************************/
+#include "mem.h"            /* unaligned access routines */
+#include "compiler.h"       /* UNLIKELY() */
+#include "debug.h"          /* assert(), DEBUGLOG(), RAWLOG() */
+#include "error_private.h"  /* error codes and messages */
+
+
+/*=========================================
+*  Target specific
+=========================================*/
+
+#define STREAM_ACCUMULATOR_MIN_32  25
+#define STREAM_ACCUMULATOR_MIN_64  57
+#define STREAM_ACCUMULATOR_MIN    ((U32)(MEM_32bits() ? STREAM_ACCUMULATOR_MIN_32 : STREAM_ACCUMULATOR_MIN_64))
+
+
+/*-******************************************
+*  bitStream encoding API (write forward)
+********************************************/
+/* bitStream can mix input from multiple sources.
+ * A critical property of these streams is that they encode and decode in **reverse** direction.
+ * So the first bit sequence you add will be the last to be read, like a LIFO stack.
+ */
+typedef struct {
+    size_t bitContainer;
+    unsigned bitPos;
+    char*  startPtr;
+    char*  ptr;
+    char*  endPtr;
+} BIT_CStream_t;
+
+MEM_STATIC size_t BIT_initCStream(BIT_CStream_t* bitC, void* dstBuffer, size_t dstCapacity);
+MEM_STATIC void   BIT_addBits(BIT_CStream_t* bitC, size_t value, unsigned nbBits);
+MEM_STATIC void   BIT_flushBits(BIT_CStream_t* bitC);
+MEM_STATIC size_t BIT_closeCStream(BIT_CStream_t* bitC);
+
+/* Start with initCStream, providing the size of buffer to write into.
+*  bitStream will never write outside of this buffer.
+*  `dstCapacity` must be >= sizeof(bitD->bitContainer), otherwise @return will be an error code.
+*
+*  bits are first added to a local register.
+*  Local register is size_t, hence 64-bits on 64-bits systems, or 32-bits on 32-bits systems.
+*  Writing data into memory is an explicit operation, performed by the flushBits function.
+*  Hence keep track how many bits are potentially stored into local register to avoid register overflow.
+*  After a flushBits, a maximum of 7 bits might still be stored into local register.
+*
+*  Avoid storing elements of more than 24 bits if you want compatibility with 32-bits bitstream readers.
+*
+*  Last operation is to close the bitStream.
+*  The function returns the final size of CStream in bytes.
+*  If data couldn't fit into `dstBuffer`, it will return a 0 ( == not storable)
+*/
+
+
+/*-********************************************
+*  bitStream decoding API (read backward)
+**********************************************/
+typedef struct {
+    size_t   bitContainer;
+    unsigned bitsConsumed;
+    const char* ptr;
+    const char* start;
+    const char* limitPtr;
+} BIT_DStream_t;
+
+typedef enum { BIT_DStream_unfinished = 0,
+               BIT_DStream_endOfBuffer = 1,
+               BIT_DStream_completed = 2,
+               BIT_DStream_overflow = 3 } BIT_DStream_status;  /* result of BIT_reloadDStream() */
+               /* 1,2,4,8 would be better for bitmap combinations, but slows down performance a bit ... :( */
+
+MEM_STATIC size_t   BIT_initDStream(BIT_DStream_t* bitD, const void* srcBuffer, size_t srcSize);
+MEM_STATIC size_t   BIT_readBits(BIT_DStream_t* bitD, unsigned nbBits);
+MEM_STATIC BIT_DStream_status BIT_reloadDStream(BIT_DStream_t* bitD);
+MEM_STATIC unsigned BIT_endOfDStream(const BIT_DStream_t* bitD);
+
+
+/* Start by invoking BIT_initDStream().
+*  A chunk of the bitStream is then stored into a local register.
+*  Local register size is 64-bits on 64-bits systems, 32-bits on 32-bits systems (size_t).
+*  You can then retrieve bitFields stored into the local register, **in reverse order**.
+*  Local register is explicitly reloaded from memory by the BIT_reloadDStream() method.
+*  A reload guarantee a minimum of ((8*sizeof(bitD->bitContainer))-7) bits when its result is BIT_DStream_unfinished.
+*  Otherwise, it can be less than that, so proceed accordingly.
+*  Checking if DStream has reached its end can be performed with BIT_endOfDStream().
+*/
+
+
+/*-****************************************
+*  unsafe API
+******************************************/
+MEM_STATIC void BIT_addBitsFast(BIT_CStream_t* bitC, size_t value, unsigned nbBits);
+/* faster, but works only if value is "clean", meaning all high bits above nbBits are 0 */
+
+MEM_STATIC void BIT_flushBitsFast(BIT_CStream_t* bitC);
+/* unsafe version; does not check buffer overflow */
+
+MEM_STATIC size_t BIT_readBitsFast(BIT_DStream_t* bitD, unsigned nbBits);
+/* faster, but works only if nbBits >= 1 */
+
+
+
+/*-**************************************************************
+*  Internal functions
+****************************************************************/
+MEM_STATIC unsigned BIT_highbit32 (U32 val)
+{
+    assert(val != 0);
+    {
+#   if (__GNUC__ >= 3)   /* Use GCC Intrinsic */
+        return __builtin_clz (val) ^ 31;
+#   else   /* Software version */
+        static const unsigned DeBruijnClz[32] = { 0,  9,  1, 10, 13, 21,  2, 29,
+                                                 11, 14, 16, 18, 22, 25,  3, 30,
+                                                  8, 12, 20, 28, 15, 17, 24,  7,
+                                                 19, 27, 23,  6, 26,  5,  4, 31 };
+        U32 v = val;
+        v |= v >> 1;
+        v |= v >> 2;
+        v |= v >> 4;
+        v |= v >> 8;
+        v |= v >> 16;
+        return DeBruijnClz[ (U32) (v * 0x07C4ACDDU) >> 27];
+#   endif
+    }
+}
+
+/*=====    Local Constants   =====*/
+static const unsigned BIT_mask[] = {
+    0,          1,         3,         7,         0xF,       0x1F,
+    0x3F,       0x7F,      0xFF,      0x1FF,     0x3FF,     0x7FF,
+    0xFFF,      0x1FFF,    0x3FFF,    0x7FFF,    0xFFFF,    0x1FFFF,
+    0x3FFFF,    0x7FFFF,   0xFFFFF,   0x1FFFFF,  0x3FFFFF,  0x7FFFFF,
+    0xFFFFFF,   0x1FFFFFF, 0x3FFFFFF, 0x7FFFFFF, 0xFFFFFFF, 0x1FFFFFFF,
+    0x3FFFFFFF, 0x7FFFFFFF}; /* up to 31 bits */
+#define BIT_MASK_SIZE (sizeof(BIT_mask) / sizeof(BIT_mask[0]))
+
+/*-**************************************************************
+*  bitStream encoding
+****************************************************************/
+/*! BIT_initCStream() :
+ *  `dstCapacity` must be > sizeof(size_t)
+ *  @return : 0 if success,
+ *            otherwise an error code (can be tested using ERR_isError()) */
+MEM_STATIC size_t BIT_initCStream(BIT_CStream_t* bitC,
+                                  void* startPtr, size_t dstCapacity)
+{
+    bitC->bitContainer = 0;
+    bitC->bitPos = 0;
+    bitC->startPtr = (char*)startPtr;
+    bitC->ptr = bitC->startPtr;
+    bitC->endPtr = bitC->startPtr + dstCapacity - sizeof(bitC->bitContainer);
+    if (dstCapacity <= sizeof(bitC->bitContainer)) return ERROR(dstSize_tooSmall);
+    return 0;
+}
+
+/*! BIT_addBits() :
+ *  can add up to 31 bits into `bitC`.
+ *  Note : does not check for register overflow ! */
+MEM_STATIC void BIT_addBits(BIT_CStream_t* bitC,
+                            size_t value, unsigned nbBits)
+{
+    DEBUG_STATIC_ASSERT(BIT_MASK_SIZE == 32);
+    assert(nbBits < BIT_MASK_SIZE);
+    assert(nbBits + bitC->bitPos < sizeof(bitC->bitContainer) * 8);
+    bitC->bitContainer |= (value & BIT_mask[nbBits]) << bitC->bitPos;
+    bitC->bitPos += nbBits;
+}
+
+/*! BIT_addBitsFast() :
+ *  works only if `value` is _clean_,
+ *  meaning all high bits above nbBits are 0 */
+MEM_STATIC void BIT_addBitsFast(BIT_CStream_t* bitC,
+                                size_t value, unsigned nbBits)
+{
+    assert((value>>nbBits) == 0);
+    assert(nbBits + bitC->bitPos < sizeof(bitC->bitContainer) * 8);
+    bitC->bitContainer |= value << bitC->bitPos;
+    bitC->bitPos += nbBits;
+}
+
+/*! BIT_flushBitsFast() :
+ *  assumption : bitContainer has not overflowed
+ *  unsafe version; does not check buffer overflow */
+MEM_STATIC void BIT_flushBitsFast(BIT_CStream_t* bitC)
+{
+    size_t const nbBytes = bitC->bitPos >> 3;
+    assert(bitC->bitPos < sizeof(bitC->bitContainer) * 8);
+    assert(bitC->ptr <= bitC->endPtr);
+    MEM_writeLEST(bitC->ptr, bitC->bitContainer);
+    bitC->ptr += nbBytes;
+    bitC->bitPos &= 7;
+    bitC->bitContainer >>= nbBytes*8;
+}
+
+/*! BIT_flushBits() :
+ *  assumption : bitContainer has not overflowed
+ *  safe version; check for buffer overflow, and prevents it.
+ *  note : does not signal buffer overflow.
+ *  overflow will be revealed later on using BIT_closeCStream() */
+MEM_STATIC void BIT_flushBits(BIT_CStream_t* bitC)
+{
+    size_t const nbBytes = bitC->bitPos >> 3;
+    assert(bitC->bitPos < sizeof(bitC->bitContainer) * 8);
+    assert(bitC->ptr <= bitC->endPtr);
+    MEM_writeLEST(bitC->ptr, bitC->bitContainer);
+    bitC->ptr += nbBytes;
+    if (bitC->ptr > bitC->endPtr) bitC->ptr = bitC->endPtr;
+    bitC->bitPos &= 7;
+    bitC->bitContainer >>= nbBytes*8;
+}
+
+/*! BIT_closeCStream() :
+ *  @return : size of CStream, in bytes,
+ *            or 0 if it could not fit into dstBuffer */
+MEM_STATIC size_t BIT_closeCStream(BIT_CStream_t* bitC)
+{
+    BIT_addBitsFast(bitC, 1, 1);   /* endMark */
+    BIT_flushBits(bitC);
+    if (bitC->ptr >= bitC->endPtr) return 0; /* overflow detected */
+    return (bitC->ptr - bitC->startPtr) + (bitC->bitPos > 0);
+}
+
+
+/*-********************************************************
+*  bitStream decoding
+**********************************************************/
+/*! BIT_initDStream() :
+ *  Initialize a BIT_DStream_t.
+ * `bitD` : a pointer to an already allocated BIT_DStream_t structure.
+ * `srcSize` must be the *exact* size of the bitStream, in bytes.
+ * @return : size of stream (== srcSize), or an errorCode if a problem is detected
+ */
+MEM_STATIC size_t BIT_initDStream(BIT_DStream_t* bitD, const void* srcBuffer, size_t srcSize)
+{
+    if (srcSize < 1) { ZSTD_memset(bitD, 0, sizeof(*bitD)); return ERROR(srcSize_wrong); }
+
+    bitD->start = (const char*)srcBuffer;
+    bitD->limitPtr = bitD->start + sizeof(bitD->bitContainer);
+
+    if (srcSize >=  sizeof(bitD->bitContainer)) {  /* normal case */
+        bitD->ptr   = (const char*)srcBuffer + srcSize - sizeof(bitD->bitContainer);
+        bitD->bitContainer = MEM_readLEST(bitD->ptr);
+        { BYTE const lastByte = ((const BYTE*)srcBuffer)[srcSize-1];
+          bitD->bitsConsumed = lastByte ? 8 - BIT_highbit32(lastByte) : 0;  /* ensures bitsConsumed is always set */
+          if (lastByte == 0) return ERROR(GENERIC); /* endMark not present */ }
+    } else {
+        bitD->ptr   = bitD->start;
+        bitD->bitContainer = *(const BYTE*)(bitD->start);
+        switch(srcSize)
+        {
+        case 7: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[6]) << (sizeof(bitD->bitContainer)*8 - 16);
+                ZSTD_FALLTHROUGH;
+
+        case 6: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[5]) << (sizeof(bitD->bitContainer)*8 - 24);
+                ZSTD_FALLTHROUGH;
+
+        case 5: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[4]) << (sizeof(bitD->bitContainer)*8 - 32);
+                ZSTD_FALLTHROUGH;
+
+        case 4: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[3]) << 24;
+                ZSTD_FALLTHROUGH;
+
+        case 3: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[2]) << 16;
+                ZSTD_FALLTHROUGH;
+
+        case 2: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[1]) <<  8;
+                ZSTD_FALLTHROUGH;
+
+        default: break;
+        }
+        {   BYTE const lastByte = ((const BYTE*)srcBuffer)[srcSize-1];
+            bitD->bitsConsumed = lastByte ? 8 - BIT_highbit32(lastByte) : 0;
+            if (lastByte == 0) return ERROR(corruption_detected);  /* endMark not present */
+        }
+        bitD->bitsConsumed += (U32)(sizeof(bitD->bitContainer) - srcSize)*8;
+    }
+
+    return srcSize;
+}
+
+MEM_STATIC FORCE_INLINE_ATTR size_t BIT_getUpperBits(size_t bitContainer, U32 const start)
+{
+    return bitContainer >> start;
+}
+
+MEM_STATIC FORCE_INLINE_ATTR size_t BIT_getMiddleBits(size_t bitContainer, U32 const start, U32 const nbBits)
+{
+    U32 const regMask = sizeof(bitContainer)*8 - 1;
+    /* if start > regMask, bitstream is corrupted, and result is undefined */
+    assert(nbBits < BIT_MASK_SIZE);
+    return (bitContainer >> (start & regMask)) & BIT_mask[nbBits];
+}
+
+MEM_STATIC FORCE_INLINE_ATTR size_t BIT_getLowerBits(size_t bitContainer, U32 const nbBits)
+{
+    assert(nbBits < BIT_MASK_SIZE);
+    return bitContainer & BIT_mask[nbBits];
+}
+
+/*! BIT_lookBits() :
+ *  Provides next n bits from local register.
+ *  local register is not modified.
+ *  On 32-bits, maxNbBits==24.
+ *  On 64-bits, maxNbBits==56.
+ * @return : value extracted */
+MEM_STATIC  FORCE_INLINE_ATTR size_t BIT_lookBits(const BIT_DStream_t*  bitD, U32 nbBits)
+{
+    /* arbitrate between double-shift and shift+mask */
+#if 1
+    /* if bitD->bitsConsumed + nbBits > sizeof(bitD->bitContainer)*8,
+     * bitstream is likely corrupted, and result is undefined */
+    return BIT_getMiddleBits(bitD->bitContainer, (sizeof(bitD->bitContainer)*8) - bitD->bitsConsumed - nbBits, nbBits);
+#else
+    /* this code path is slower on my os-x laptop */
+    U32 const regMask = sizeof(bitD->bitContainer)*8 - 1;
+    return ((bitD->bitContainer << (bitD->bitsConsumed & regMask)) >> 1) >> ((regMask-nbBits) & regMask);
+#endif
+}
+
+/*! BIT_lookBitsFast() :
+ *  unsafe version; only works if nbBits >= 1 */
+MEM_STATIC size_t BIT_lookBitsFast(const BIT_DStream_t* bitD, U32 nbBits)
+{
+    U32 const regMask = sizeof(bitD->bitContainer)*8 - 1;
+    assert(nbBits >= 1);
+    return (bitD->bitContainer << (bitD->bitsConsumed & regMask)) >> (((regMask+1)-nbBits) & regMask);
+}
+
+MEM_STATIC FORCE_INLINE_ATTR void BIT_skipBits(BIT_DStream_t* bitD, U32 nbBits)
+{
+    bitD->bitsConsumed += nbBits;
+}
+
+/*! BIT_readBits() :
+ *  Read (consume) next n bits from local register and update.
+ *  Pay attention to not read more than nbBits contained into local register.
+ * @return : extracted value. */
+MEM_STATIC FORCE_INLINE_ATTR size_t BIT_readBits(BIT_DStream_t* bitD, unsigned nbBits)
+{
+    size_t const value = BIT_lookBits(bitD, nbBits);
+    BIT_skipBits(bitD, nbBits);
+    return value;
+}
+
+/*! BIT_readBitsFast() :
+ *  unsafe version; only works only if nbBits >= 1 */
+MEM_STATIC size_t BIT_readBitsFast(BIT_DStream_t* bitD, unsigned nbBits)
+{
+    size_t const value = BIT_lookBitsFast(bitD, nbBits);
+    assert(nbBits >= 1);
+    BIT_skipBits(bitD, nbBits);
+    return value;
+}
+
+/*! BIT_reloadDStreamFast() :
+ *  Similar to BIT_reloadDStream(), but with two differences:
+ *  1. bitsConsumed <= sizeof(bitD->bitContainer)*8 must hold!
+ *  2. Returns BIT_DStream_overflow when bitD->ptr < bitD->limitPtr, at this
+ *     point you must use BIT_reloadDStream() to reload.
+ */
+MEM_STATIC BIT_DStream_status BIT_reloadDStreamFast(BIT_DStream_t* bitD)
+{
+    if (UNLIKELY(bitD->ptr < bitD->limitPtr))
+        return BIT_DStream_overflow;
+    assert(bitD->bitsConsumed <= sizeof(bitD->bitContainer)*8);
+    bitD->ptr -= bitD->bitsConsumed >> 3;
+    bitD->bitsConsumed &= 7;
+    bitD->bitContainer = MEM_readLEST(bitD->ptr);
+    return BIT_DStream_unfinished;
+}
+
+/*! BIT_reloadDStream() :
+ *  Refill `bitD` from buffer previously set in BIT_initDStream() .
+ *  This function is safe, it guarantees it will not read beyond src buffer.
+ * @return : status of `BIT_DStream_t` internal register.
+ *           when status == BIT_DStream_unfinished, internal register is filled with at least 25 or 57 bits */
+MEM_STATIC BIT_DStream_status BIT_reloadDStream(BIT_DStream_t* bitD)
+{
+    if (bitD->bitsConsumed > (sizeof(bitD->bitContainer)*8))  /* overflow detected, like end of stream */
+        return BIT_DStream_overflow;
+
+    if (bitD->ptr >= bitD->limitPtr) {
+        return BIT_reloadDStreamFast(bitD);
+    }
+    if (bitD->ptr == bitD->start) {
+        if (bitD->bitsConsumed < sizeof(bitD->bitContainer)*8) return BIT_DStream_endOfBuffer;
+        return BIT_DStream_completed;
+    }
+    /* start < ptr < limitPtr */
+    {   U32 nbBytes = bitD->bitsConsumed >> 3;
+        BIT_DStream_status result = BIT_DStream_unfinished;
+        if (bitD->ptr - nbBytes < bitD->start) {
+            nbBytes = (U32)(bitD->ptr - bitD->start);  /* ptr > start */
+            result = BIT_DStream_endOfBuffer;
+        }
+        bitD->ptr -= nbBytes;
+        bitD->bitsConsumed -= nbBytes*8;
+        bitD->bitContainer = MEM_readLEST(bitD->ptr);   /* reminder : srcSize > sizeof(bitD->bitContainer), otherwise bitD->ptr == bitD->start */
+        return result;
+    }
+}
+
+/*! BIT_endOfDStream() :
+ * @return : 1 if DStream has _exactly_ reached its end (all bits consumed).
+ */
+MEM_STATIC unsigned BIT_endOfDStream(const BIT_DStream_t* DStream)
+{
+    return ((DStream->ptr == DStream->start) && (DStream->bitsConsumed == sizeof(DStream->bitContainer)*8));
+}
+
+
+#endif /* BITSTREAM_H_MODULE */
diff --git a/lib/zstd/common/compiler.h b/lib/zstd/common/compiler.h
new file mode 100644
index 000000000000..f5a9c70a228a
--- /dev/null
+++ b/lib/zstd/common/compiler.h
@@ -0,0 +1,177 @@
+/*
+ * Copyright (c) Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+#ifndef ZSTD_COMPILER_H
+#define ZSTD_COMPILER_H
+
+/*-*******************************************************
+*  Compiler specifics
+*********************************************************/
+/* force inlining */
+
+#if !defined(ZSTD_NO_INLINE)
+#if (defined(__GNUC__) && !defined(__STRICT_ANSI__)) || defined(__cplusplus) || defined(__STDC_VERSION__) && __STDC_VERSION__ >= 199901L   /* C99 */
+#  define INLINE_KEYWORD inline
+#else
+#  define INLINE_KEYWORD
+#endif
+
+#define FORCE_INLINE_ATTR __attribute__((always_inline))
+
+#else
+
+#define INLINE_KEYWORD
+#define FORCE_INLINE_ATTR
+
+#endif
+
+/*
+  On MSVC qsort requires that functions passed into it use the __cdecl calling conversion(CC).
+  This explictly marks such functions as __cdecl so that the code will still compile
+  if a CC other than __cdecl has been made the default.
+*/
+#define WIN_CDECL
+
+/*
+ * FORCE_INLINE_TEMPLATE is used to define C "templates", which take constant
+ * parameters. They must be inlined for the compiler to eliminate the constant
+ * branches.
+ */
+#define FORCE_INLINE_TEMPLATE static INLINE_KEYWORD FORCE_INLINE_ATTR
+/*
+ * HINT_INLINE is used to help the compiler generate better code. It is *not*
+ * used for "templates", so it can be tweaked based on the compilers
+ * performance.
+ *
+ * gcc-4.8 and gcc-4.9 have been shown to benefit from leaving off the
+ * always_inline attribute.
+ *
+ * clang up to 5.0.0 (trunk) benefit tremendously from the always_inline
+ * attribute.
+ */
+#if !defined(__clang__) && defined(__GNUC__) && __GNUC__ >= 4 && __GNUC_MINOR__ >= 8 && __GNUC__ < 5
+#  define HINT_INLINE static INLINE_KEYWORD
+#else
+#  define HINT_INLINE static INLINE_KEYWORD FORCE_INLINE_ATTR
+#endif
+
+/* UNUSED_ATTR tells the compiler it is okay if the function is unused. */
+#define UNUSED_ATTR __attribute__((unused))
+
+/* force no inlining */
+#define FORCE_NOINLINE static __attribute__((__noinline__))
+
+
+/* target attribute */
+#ifndef __has_attribute
+  #define __has_attribute(x) 0  /* Compatibility with non-clang compilers. */
+#endif
+#define TARGET_ATTRIBUTE(target) __attribute__((__target__(target)))
+
+/* Enable runtime BMI2 dispatch based on the CPU.
+ * Enabled for clang & gcc >=4.8 on x86 when BMI2 isn't enabled by default.
+ */
+#ifndef DYNAMIC_BMI2
+  #if ((defined(__clang__) && __has_attribute(__target__)) \
+      || (defined(__GNUC__) \
+          && (__GNUC__ >= 5 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 8)))) \
+      && (defined(__x86_64__) || defined(_M_X86)) \
+      && !defined(__BMI2__)
+  #  define DYNAMIC_BMI2 1
+  #else
+  #  define DYNAMIC_BMI2 0
+  #endif
+#endif
+
+/* prefetch
+ * can be disabled, by declaring NO_PREFETCH build macro */
+#if ( (__GNUC__ >= 4) || ( (__GNUC__ == 3) && (__GNUC_MINOR__ >= 1) ) )
+#  define PREFETCH_L1(ptr)  __builtin_prefetch((ptr), 0 /* rw==read */, 3 /* locality */)
+#  define PREFETCH_L2(ptr)  __builtin_prefetch((ptr), 0 /* rw==read */, 2 /* locality */)
+#elif defined(__aarch64__)
+#  define PREFETCH_L1(ptr)  __asm__ __volatile__("prfm pldl1keep, %0" ::"Q"(*(ptr)))
+#  define PREFETCH_L2(ptr)  __asm__ __volatile__("prfm pldl2keep, %0" ::"Q"(*(ptr)))
+#else
+#  define PREFETCH_L1(ptr) (void)(ptr)  /* disabled */
+#  define PREFETCH_L2(ptr) (void)(ptr)  /* disabled */
+#endif  /* NO_PREFETCH */
+
+#define CACHELINE_SIZE 64
+
+#define PREFETCH_AREA(p, s)  {            \
+    const char* const _ptr = (const char*)(p);  \
+    size_t const _size = (size_t)(s);     \
+    size_t _pos;                          \
+    for (_pos=0; _pos<_size; _pos+=CACHELINE_SIZE) {  \
+        PREFETCH_L2(_ptr + _pos);         \
+    }                                     \
+}
+
+/* vectorization
+ * older GCC (pre gcc-4.3 picked as the cutoff) uses a different syntax */
+#if !defined(__INTEL_COMPILER) && !defined(__clang__) && defined(__GNUC__)
+#  if (__GNUC__ == 4 && __GNUC_MINOR__ > 3) || (__GNUC__ >= 5)
+#    define DONT_VECTORIZE __attribute__((optimize("no-tree-vectorize")))
+#  else
+#    define DONT_VECTORIZE _Pragma("GCC optimize(\"no-tree-vectorize\")")
+#  endif
+#else
+#  define DONT_VECTORIZE
+#endif
+
+/* Tell the compiler that a branch is likely or unlikely.
+ * Only use these macros if it causes the compiler to generate better code.
+ * If you can remove a LIKELY/UNLIKELY annotation without speed changes in gcc
+ * and clang, please do.
+ */
+#define LIKELY(x) (__builtin_expect((x), 1))
+#define UNLIKELY(x) (__builtin_expect((x), 0))
+
+/* disable warnings */
+
+/*Like DYNAMIC_BMI2 but for compile time determination of BMI2 support*/
+
+
+/* compat. with non-clang compilers */
+#ifndef __has_builtin
+#  define __has_builtin(x) 0
+#endif
+
+/* compat. with non-clang compilers */
+#ifndef __has_feature
+#  define __has_feature(x) 0
+#endif
+
+/* C-language Attributes are added in C23. */
+#if defined(__STDC_VERSION__) && (__STDC_VERSION__ > 201710L) && defined(__has_c_attribute)
+# define ZSTD_HAS_C_ATTRIBUTE(x) __has_c_attribute(x)
+#else
+# define ZSTD_HAS_C_ATTRIBUTE(x) 0
+#endif
+
+/* Only use C++ attributes in C++. Some compilers report support for C++
+ * attributes when compiling with C.
+ */
+#define ZSTD_HAS_CPP_ATTRIBUTE(x) 0
+
+/* Define ZSTD_FALLTHROUGH macro for annotating switch case with the 'fallthrough' attribute.
+ * - C23: https://en.cppreference.com/w/c/language/attributes/fallthrough
+ * - CPP17: https://en.cppreference.com/w/cpp/language/attributes/fallthrough
+ * - Else: __attribute__((__fallthrough__))
+ */
+#define ZSTD_FALLTHROUGH fallthrough
+
+/* detects whether we are being compiled under msan */
+
+
+/* detects whether we are being compiled under asan */
+
+
+#endif /* ZSTD_COMPILER_H */
diff --git a/lib/zstd/common/cpu.h b/lib/zstd/common/cpu.h
new file mode 100644
index 000000000000..0db7b42407ee
--- /dev/null
+++ b/lib/zstd/common/cpu.h
@@ -0,0 +1,194 @@
+/*
+ * Copyright (c) Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+#ifndef ZSTD_COMMON_CPU_H
+#define ZSTD_COMMON_CPU_H
+
+/*
+ * Implementation taken from folly/CpuId.h
+ * https://github.com/facebook/folly/blob/master/folly/CpuId.h
+ */
+
+#include "mem.h"
+
+
+typedef struct {
+    U32 f1c;
+    U32 f1d;
+    U32 f7b;
+    U32 f7c;
+} ZSTD_cpuid_t;
+
+MEM_STATIC ZSTD_cpuid_t ZSTD_cpuid(void) {
+    U32 f1c = 0;
+    U32 f1d = 0;
+    U32 f7b = 0;
+    U32 f7c = 0;
+#if defined(__i386__) && defined(__PIC__) && !defined(__clang__) && defined(__GNUC__)
+    /* The following block like the normal cpuid branch below, but gcc
+     * reserves ebx for use of its pic register so we must specially
+     * handle the save and restore to avoid clobbering the register
+     */
+    U32 n;
+    __asm__(
+        "pushl %%ebx\n\t"
+        "cpuid\n\t"
+        "popl %%ebx\n\t"
+        : "=a"(n)
+        : "a"(0)
+        : "ecx", "edx");
+    if (n >= 1) {
+      U32 f1a;
+      __asm__(
+          "pushl %%ebx\n\t"
+          "cpuid\n\t"
+          "popl %%ebx\n\t"
+          : "=a"(f1a), "=c"(f1c), "=d"(f1d)
+          : "a"(1));
+    }
+    if (n >= 7) {
+      __asm__(
+          "pushl %%ebx\n\t"
+          "cpuid\n\t"
+          "movl %%ebx, %%eax\n\t"
+          "popl %%ebx"
+          : "=a"(f7b), "=c"(f7c)
+          : "a"(7), "c"(0)
+          : "edx");
+    }
+#elif defined(__x86_64__) || defined(_M_X64) || defined(__i386__)
+    U32 n;
+    __asm__("cpuid" : "=a"(n) : "a"(0) : "ebx", "ecx", "edx");
+    if (n >= 1) {
+      U32 f1a;
+      __asm__("cpuid" : "=a"(f1a), "=c"(f1c), "=d"(f1d) : "a"(1) : "ebx");
+    }
+    if (n >= 7) {
+      U32 f7a;
+      __asm__("cpuid"
+              : "=a"(f7a), "=b"(f7b), "=c"(f7c)
+              : "a"(7), "c"(0)
+              : "edx");
+    }
+#endif
+    {
+        ZSTD_cpuid_t cpuid;
+        cpuid.f1c = f1c;
+        cpuid.f1d = f1d;
+        cpuid.f7b = f7b;
+        cpuid.f7c = f7c;
+        return cpuid;
+    }
+}
+
+#define X(name, r, bit)                                                        \
+  MEM_STATIC int ZSTD_cpuid_##name(ZSTD_cpuid_t const cpuid) {                 \
+    return ((cpuid.r) & (1U << bit)) != 0;                                     \
+  }
+
+/* cpuid(1): Processor Info and Feature Bits. */
+#define C(name, bit) X(name, f1c, bit)
+  C(sse3, 0)
+  C(pclmuldq, 1)
+  C(dtes64, 2)
+  C(monitor, 3)
+  C(dscpl, 4)
+  C(vmx, 5)
+  C(smx, 6)
+  C(eist, 7)
+  C(tm2, 8)
+  C(ssse3, 9)
+  C(cnxtid, 10)
+  C(fma, 12)
+  C(cx16, 13)
+  C(xtpr, 14)
+  C(pdcm, 15)
+  C(pcid, 17)
+  C(dca, 18)
+  C(sse41, 19)
+  C(sse42, 20)
+  C(x2apic, 21)
+  C(movbe, 22)
+  C(popcnt, 23)
+  C(tscdeadline, 24)
+  C(aes, 25)
+  C(xsave, 26)
+  C(osxsave, 27)
+  C(avx, 28)
+  C(f16c, 29)
+  C(rdrand, 30)
+#undef C
+#define D(name, bit) X(name, f1d, bit)
+  D(fpu, 0)
+  D(vme, 1)
+  D(de, 2)
+  D(pse, 3)
+  D(tsc, 4)
+  D(msr, 5)
+  D(pae, 6)
+  D(mce, 7)
+  D(cx8, 8)
+  D(apic, 9)
+  D(sep, 11)
+  D(mtrr, 12)
+  D(pge, 13)
+  D(mca, 14)
+  D(cmov, 15)
+  D(pat, 16)
+  D(pse36, 17)
+  D(psn, 18)
+  D(clfsh, 19)
+  D(ds, 21)
+  D(acpi, 22)
+  D(mmx, 23)
+  D(fxsr, 24)
+  D(sse, 25)
+  D(sse2, 26)
+  D(ss, 27)
+  D(htt, 28)
+  D(tm, 29)
+  D(pbe, 31)
+#undef D
+
+/* cpuid(7): Extended Features. */
+#define B(name, bit) X(name, f7b, bit)
+  B(bmi1, 3)
+  B(hle, 4)
+  B(avx2, 5)
+  B(smep, 7)
+  B(bmi2, 8)
+  B(erms, 9)
+  B(invpcid, 10)
+  B(rtm, 11)
+  B(mpx, 14)
+  B(avx512f, 16)
+  B(avx512dq, 17)
+  B(rdseed, 18)
+  B(adx, 19)
+  B(smap, 20)
+  B(avx512ifma, 21)
+  B(pcommit, 22)
+  B(clflushopt, 23)
+  B(clwb, 24)
+  B(avx512pf, 26)
+  B(avx512er, 27)
+  B(avx512cd, 28)
+  B(sha, 29)
+  B(avx512bw, 30)
+  B(avx512vl, 31)
+#undef B
+#define C(name, bit) X(name, f7c, bit)
+  C(prefetchwt1, 0)
+  C(avx512vbmi, 1)
+#undef C
+
+#undef X
+
+#endif /* ZSTD_COMMON_CPU_H */
diff --git a/lib/zstd/common/debug.c b/lib/zstd/common/debug.c
new file mode 100644
index 000000000000..bb863c9ea616
--- /dev/null
+++ b/lib/zstd/common/debug.c
@@ -0,0 +1,24 @@
+/* ******************************************************************
+ * debug
+ * Part of FSE library
+ * Copyright (c) Yann Collet, Facebook, Inc.
+ *
+ * You can contact the author at :
+ * - Source repository : https://github.com/Cyan4973/FiniteStateEntropy
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+****************************************************************** */
+
+
+/*
+ * This module only hosts one global variable
+ * which can be used to dynamically influence the verbosity of traces,
+ * such as DEBUGLOG and RAWLOG
+ */
+
+#include "debug.h"
+
+int g_debuglevel = DEBUGLEVEL;
diff --git a/lib/zstd/common/debug.h b/lib/zstd/common/debug.h
new file mode 100644
index 000000000000..6dd88d1fbd02
--- /dev/null
+++ b/lib/zstd/common/debug.h
@@ -0,0 +1,101 @@
+/* ******************************************************************
+ * debug
+ * Part of FSE library
+ * Copyright (c) Yann Collet, Facebook, Inc.
+ *
+ * You can contact the author at :
+ * - Source repository : https://github.com/Cyan4973/FiniteStateEntropy
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+****************************************************************** */
+
+
+/*
+ * The purpose of this header is to enable debug functions.
+ * They regroup assert(), DEBUGLOG() and RAWLOG() for run-time,
+ * and DEBUG_STATIC_ASSERT() for compile-time.
+ *
+ * By default, DEBUGLEVEL==0, which means run-time debug is disabled.
+ *
+ * Level 1 enables assert() only.
+ * Starting level 2, traces can be generated and pushed to stderr.
+ * The higher the level, the more verbose the traces.
+ *
+ * It's possible to dynamically adjust level using variable g_debug_level,
+ * which is only declared if DEBUGLEVEL>=2,
+ * and is a global variable, not multi-thread protected (use with care)
+ */
+
+#ifndef DEBUG_H_12987983217
+#define DEBUG_H_12987983217
+
+
+
+/* static assert is triggered at compile time, leaving no runtime artefact.
+ * static assert only works with compile-time constants.
+ * Also, this variant can only be used inside a function. */
+#define DEBUG_STATIC_ASSERT(c) (void)sizeof(char[(c) ? 1 : -1])
+
+
+/* DEBUGLEVEL is expected to be defined externally,
+ * typically through compiler command line.
+ * Value must be a number. */
+#ifndef DEBUGLEVEL
+#  define DEBUGLEVEL 0
+#endif
+
+
+/* recommended values for DEBUGLEVEL :
+ * 0 : release mode, no debug, all run-time checks disabled
+ * 1 : enables assert() only, no display
+ * 2 : reserved, for currently active debug path
+ * 3 : events once per object lifetime (CCtx, CDict, etc.)
+ * 4 : events once per frame
+ * 5 : events once per block
+ * 6 : events once per sequence (verbose)
+ * 7+: events at every position (*very* verbose)
+ *
+ * It's generally inconvenient to output traces > 5.
+ * In which case, it's possible to selectively trigger high verbosity levels
+ * by modifying g_debug_level.
+ */
+
+#if (DEBUGLEVEL>=1)
+#  define ZSTD_DEPS_NEED_ASSERT
+#  include "zstd_deps.h"
+#else
+#  ifndef assert   /* assert may be already defined, due to prior #include <assert.h> */
+#    define assert(condition) ((void)0)   /* disable assert (default) */
+#  endif
+#endif
+
+#if (DEBUGLEVEL>=2)
+#  define ZSTD_DEPS_NEED_IO
+#  include "zstd_deps.h"
+extern int g_debuglevel; /* the variable is only declared,
+                            it actually lives in debug.c,
+                            and is shared by the whole process.
+                            It's not thread-safe.
+                            It's useful when enabling very verbose levels
+                            on selective conditions (such as position in src) */
+
+#  define RAWLOG(l, ...) {                                       \
+                if (l<=g_debuglevel) {                           \
+                    ZSTD_DEBUG_PRINT(__VA_ARGS__);               \
+            }   }
+#  define DEBUGLOG(l, ...) {                                     \
+                if (l<=g_debuglevel) {                           \
+                    ZSTD_DEBUG_PRINT(__FILE__ ": " __VA_ARGS__); \
+                    ZSTD_DEBUG_PRINT(" \n");                     \
+            }   }
+#else
+#  define RAWLOG(l, ...)      {}    /* disabled */
+#  define DEBUGLOG(l, ...)    {}    /* disabled */
+#endif
+
+
+
+#endif /* DEBUG_H_12987983217 */
diff --git a/lib/zstd/common/entropy_common.c b/lib/zstd/common/entropy_common.c
new file mode 100644
index 000000000000..53b47a2b52ff
--- /dev/null
+++ b/lib/zstd/common/entropy_common.c
@@ -0,0 +1,357 @@
+/* ******************************************************************
+ * Common functions of New Generation Entropy library
+ * Copyright (c) Yann Collet, Facebook, Inc.
+ *
+ *  You can contact the author at :
+ *  - FSE+HUF source repository : https://github.com/Cyan4973/FiniteStateEntropy
+ *  - Public forum : https://groups.google.com/forum/#!forum/lz4c
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+****************************************************************** */
+
+/* *************************************
+*  Dependencies
+***************************************/
+#include "mem.h"
+#include "error_private.h"       /* ERR_*, ERROR */
+#define FSE_STATIC_LINKING_ONLY  /* FSE_MIN_TABLELOG */
+#include "fse.h"
+#define HUF_STATIC_LINKING_ONLY  /* HUF_TABLELOG_ABSOLUTEMAX */
+#include "huf.h"
+
+
+/*===   Version   ===*/
+unsigned FSE_versionNumber(void) { return FSE_VERSION_NUMBER; }
+
+
+/*===   Error Management   ===*/
+unsigned FSE_isError(size_t code) { return ERR_isError(code); }
+const char* FSE_getErrorName(size_t code) { return ERR_getErrorName(code); }
+
+unsigned HUF_isError(size_t code) { return ERR_isError(code); }
+const char* HUF_getErrorName(size_t code) { return ERR_getErrorName(code); }
+
+
+/*-**************************************************************
+*  FSE NCount encoding-decoding
+****************************************************************/
+static U32 FSE_ctz(U32 val)
+{
+    assert(val != 0);
+    {
+#   if (__GNUC__ >= 3)   /* GCC Intrinsic */
+        return __builtin_ctz(val);
+#   else   /* Software version */
+        U32 count = 0;
+        while ((val & 1) == 0) {
+            val >>= 1;
+            ++count;
+        }
+        return count;
+#   endif
+    }
+}
+
+FORCE_INLINE_TEMPLATE
+size_t FSE_readNCount_body(short* normalizedCounter, unsigned* maxSVPtr, unsigned* tableLogPtr,
+                           const void* headerBuffer, size_t hbSize)
+{
+    const BYTE* const istart = (const BYTE*) headerBuffer;
+    const BYTE* const iend = istart + hbSize;
+    const BYTE* ip = istart;
+    int nbBits;
+    int remaining;
+    int threshold;
+    U32 bitStream;
+    int bitCount;
+    unsigned charnum = 0;
+    unsigned const maxSV1 = *maxSVPtr + 1;
+    int previous0 = 0;
+
+    if (hbSize < 8) {
+        /* This function only works when hbSize >= 8 */
+        char buffer[8] = {0};
+        ZSTD_memcpy(buffer, headerBuffer, hbSize);
+        {   size_t const countSize = FSE_readNCount(normalizedCounter, maxSVPtr, tableLogPtr,
+                                                    buffer, sizeof(buffer));
+            if (FSE_isError(countSize)) return countSize;
+            if (countSize > hbSize) return ERROR(corruption_detected);
+            return countSize;
+    }   }
+    assert(hbSize >= 8);
+
+    /* init */
+    ZSTD_memset(normalizedCounter, 0, (*maxSVPtr+1) * sizeof(normalizedCounter[0]));   /* all symbols not present in NCount have a frequency of 0 */
+    bitStream = MEM_readLE32(ip);
+    nbBits = (bitStream & 0xF) + FSE_MIN_TABLELOG;   /* extract tableLog */
+    if (nbBits > FSE_TABLELOG_ABSOLUTE_MAX) return ERROR(tableLog_tooLarge);
+    bitStream >>= 4;
+    bitCount = 4;
+    *tableLogPtr = nbBits;
+    remaining = (1<<nbBits)+1;
+    threshold = 1<<nbBits;
+    nbBits++;
+
+    for (;;) {
+        if (previous0) {
+            /* Count the number of repeats. Each time the
+             * 2-bit repeat code is 0b11 there is another
+             * repeat.
+             * Avoid UB by setting the high bit to 1.
+             */
+            int repeats = FSE_ctz(~bitStream | 0x80000000) >> 1;
+            while (repeats >= 12) {
+                charnum += 3 * 12;
+                if (LIKELY(ip <= iend-7)) {
+                    ip += 3;
+                } else {
+                    bitCount -= (int)(8 * (iend - 7 - ip));
+                    bitCount &= 31;
+                    ip = iend - 4;
+                }
+                bitStream = MEM_readLE32(ip) >> bitCount;
+                repeats = FSE_ctz(~bitStream | 0x80000000) >> 1;
+            }
+            charnum += 3 * repeats;
+            bitStream >>= 2 * repeats;
+            bitCount += 2 * repeats;
+
+            /* Add the final repeat which isn't 0b11. */
+            assert((bitStream & 3) < 3);
+            charnum += bitStream & 3;
+            bitCount += 2;
+
+            /* This is an error, but break and return an error
+             * at the end, because returning out of a loop makes
+             * it harder for the compiler to optimize.
+             */
+            if (charnum >= maxSV1) break;
+
+            /* We don't need to set the normalized count to 0
+             * because we already memset the whole buffer to 0.
+             */
+
+            if (LIKELY(ip <= iend-7) || (ip + (bitCount>>3) <= iend-4)) {
+                assert((bitCount >> 3) <= 3); /* For first condition to work */
+                ip += bitCount>>3;
+                bitCount &= 7;
+            } else {
+                bitCount -= (int)(8 * (iend - 4 - ip));
+                bitCount &= 31;
+                ip = iend - 4;
+            }
+            bitStream = MEM_readLE32(ip) >> bitCount;
+        }
+        {
+            int const max = (2*threshold-1) - remaining;
+            int count;
+
+            if ((bitStream & (threshold-1)) < (U32)max) {
+                count = bitStream & (threshold-1);
+                bitCount += nbBits-1;
+            } else {
+                count = bitStream & (2*threshold-1);
+                if (count >= threshold) count -= max;
+                bitCount += nbBits;
+            }
+
+            count--;   /* extra accuracy */
+            /* When it matters (small blocks), this is a
+             * predictable branch, because we don't use -1.
+             */
+            if (count >= 0) {
+                remaining -= count;
+            } else {
+                assert(count == -1);
+                remaining += count;
+            }
+            normalizedCounter[charnum++] = (short)count;
+            previous0 = !count;
+
+            assert(threshold > 1);
+            if (remaining < threshold) {
+                /* This branch can be folded into the
+                 * threshold update condition because we
+                 * know that threshold > 1.
+                 */
+                if (remaining <= 1) break;
+                nbBits = BIT_highbit32(remaining) + 1;
+                threshold = 1 << (nbBits - 1);
+            }
+            if (charnum >= maxSV1) break;
+
+            if (LIKELY(ip <= iend-7) || (ip + (bitCount>>3) <= iend-4)) {
+                ip += bitCount>>3;
+                bitCount &= 7;
+            } else {
+                bitCount -= (int)(8 * (iend - 4 - ip));
+                bitCount &= 31;
+                ip = iend - 4;
+            }
+            bitStream = MEM_readLE32(ip) >> bitCount;
+    }   }
+    if (remaining != 1) return ERROR(corruption_detected);
+    /* Only possible when there are too many zeros. */
+    if (charnum > maxSV1) return ERROR(maxSymbolValue_tooSmall);
+    if (bitCount > 32) return ERROR(corruption_detected);
+    *maxSVPtr = charnum-1;
+
+    ip += (bitCount+7)>>3;
+    return ip-istart;
+}
+
+/* Avoids the FORCE_INLINE of the _body() function. */
+static size_t FSE_readNCount_body_default(
+        short* normalizedCounter, unsigned* maxSVPtr, unsigned* tableLogPtr,
+        const void* headerBuffer, size_t hbSize)
+{
+    return FSE_readNCount_body(normalizedCounter, maxSVPtr, tableLogPtr, headerBuffer, hbSize);
+}
+
+#if DYNAMIC_BMI2
+TARGET_ATTRIBUTE("bmi2") static size_t FSE_readNCount_body_bmi2(
+        short* normalizedCounter, unsigned* maxSVPtr, unsigned* tableLogPtr,
+        const void* headerBuffer, size_t hbSize)
+{
+    return FSE_readNCount_body(normalizedCounter, maxSVPtr, tableLogPtr, headerBuffer, hbSize);
+}
+#endif
+
+size_t FSE_readNCount_bmi2(
+        short* normalizedCounter, unsigned* maxSVPtr, unsigned* tableLogPtr,
+        const void* headerBuffer, size_t hbSize, int bmi2)
+{
+#if DYNAMIC_BMI2
+    if (bmi2) {
+        return FSE_readNCount_body_bmi2(normalizedCounter, maxSVPtr, tableLogPtr, headerBuffer, hbSize);
+    }
+#endif
+    (void)bmi2;
+    return FSE_readNCount_body_default(normalizedCounter, maxSVPtr, tableLogPtr, headerBuffer, hbSize);
+}
+
+size_t FSE_readNCount(
+        short* normalizedCounter, unsigned* maxSVPtr, unsigned* tableLogPtr,
+        const void* headerBuffer, size_t hbSize)
+{
+    return FSE_readNCount_bmi2(normalizedCounter, maxSVPtr, tableLogPtr, headerBuffer, hbSize, /* bmi2 */ 0);
+}
+
+
+/*! HUF_readStats() :
+    Read compact Huffman tree, saved by HUF_writeCTable().
+    `huffWeight` is destination buffer.
+    `rankStats` is assumed to be a table of at least HUF_TABLELOG_MAX U32.
+    @return : size read from `src` , or an error Code .
+    Note : Needed by HUF_readCTable() and HUF_readDTableX?() .
+*/
+size_t HUF_readStats(BYTE* huffWeight, size_t hwSize, U32* rankStats,
+                     U32* nbSymbolsPtr, U32* tableLogPtr,
+                     const void* src, size_t srcSize)
+{
+    U32 wksp[HUF_READ_STATS_WORKSPACE_SIZE_U32];
+    return HUF_readStats_wksp(huffWeight, hwSize, rankStats, nbSymbolsPtr, tableLogPtr, src, srcSize, wksp, sizeof(wksp), /* bmi2 */ 0);
+}
+
+FORCE_INLINE_TEMPLATE size_t
+HUF_readStats_body(BYTE* huffWeight, size_t hwSize, U32* rankStats,
+                   U32* nbSymbolsPtr, U32* tableLogPtr,
+                   const void* src, size_t srcSize,
+                   void* workSpace, size_t wkspSize,
+                   int bmi2)
+{
+    U32 weightTotal;
+    const BYTE* ip = (const BYTE*) src;
+    size_t iSize;
+    size_t oSize;
+
+    if (!srcSize) return ERROR(srcSize_wrong);
+    iSize = ip[0];
+    /* ZSTD_memset(huffWeight, 0, hwSize);   *//* is not necessary, even though some analyzer complain ... */
+
+    if (iSize >= 128) {  /* special header */
+        oSize = iSize - 127;
+        iSize = ((oSize+1)/2);
+        if (iSize+1 > srcSize) return ERROR(srcSize_wrong);
+        if (oSize >= hwSize) return ERROR(corruption_detected);
+        ip += 1;
+        {   U32 n;
+            for (n=0; n<oSize; n+=2) {
+                huffWeight[n]   = ip[n/2] >> 4;
+                huffWeight[n+1] = ip[n/2] & 15;
+    }   }   }
+    else  {   /* header compressed with FSE (normal case) */
+        if (iSize+1 > srcSize) return ERROR(srcSize_wrong);
+        /* max (hwSize-1) values decoded, as last one is implied */
+        oSize = FSE_decompress_wksp_bmi2(huffWeight, hwSize-1, ip+1, iSize, 6, workSpace, wkspSize, bmi2);
+        if (FSE_isError(oSize)) return oSize;
+    }
+
+    /* collect weight stats */
+    ZSTD_memset(rankStats, 0, (HUF_TABLELOG_MAX + 1) * sizeof(U32));
+    weightTotal = 0;
+    {   U32 n; for (n=0; n<oSize; n++) {
+            if (huffWeight[n] >= HUF_TABLELOG_MAX) return ERROR(corruption_detected);
+            rankStats[huffWeight[n]]++;
+            weightTotal += (1 << huffWeight[n]) >> 1;
+    }   }
+    if (weightTotal == 0) return ERROR(corruption_detected);
+
+    /* get last non-null symbol weight (implied, total must be 2^n) */
+    {   U32 const tableLog = BIT_highbit32(weightTotal) + 1;
+        if (tableLog > HUF_TABLELOG_MAX) return ERROR(corruption_detected);
+        *tableLogPtr = tableLog;
+        /* determine last weight */
+        {   U32 const total = 1 << tableLog;
+            U32 const rest = total - weightTotal;
+            U32 const verif = 1 << BIT_highbit32(rest);
+            U32 const lastWeight = BIT_highbit32(rest) + 1;
+            if (verif != rest) return ERROR(corruption_detected);    /* last value must be a clean power of 2 */
+            huffWeight[oSize] = (BYTE)lastWeight;
+            rankStats[lastWeight]++;
+    }   }
+
+    /* check tree construction validity */
+    if ((rankStats[1] < 2) || (rankStats[1] & 1)) return ERROR(corruption_detected);   /* by construction : at least 2 elts of rank 1, must be even */
+
+    /* results */
+    *nbSymbolsPtr = (U32)(oSize+1);
+    return iSize+1;
+}
+
+/* Avoids the FORCE_INLINE of the _body() function. */
+static size_t HUF_readStats_body_default(BYTE* huffWeight, size_t hwSize, U32* rankStats,
+                     U32* nbSymbolsPtr, U32* tableLogPtr,
+                     const void* src, size_t srcSize,
+                     void* workSpace, size_t wkspSize)
+{
+    return HUF_readStats_body(huffWeight, hwSize, rankStats, nbSymbolsPtr, tableLogPtr, src, srcSize, workSpace, wkspSize, 0);
+}
+
+#if DYNAMIC_BMI2
+static TARGET_ATTRIBUTE("bmi2") size_t HUF_readStats_body_bmi2(BYTE* huffWeight, size_t hwSize, U32* rankStats,
+                     U32* nbSymbolsPtr, U32* tableLogPtr,
+                     const void* src, size_t srcSize,
+                     void* workSpace, size_t wkspSize)
+{
+    return HUF_readStats_body(huffWeight, hwSize, rankStats, nbSymbolsPtr, tableLogPtr, src, srcSize, workSpace, wkspSize, 1);
+}
+#endif
+
+size_t HUF_readStats_wksp(BYTE* huffWeight, size_t hwSize, U32* rankStats,
+                     U32* nbSymbolsPtr, U32* tableLogPtr,
+                     const void* src, size_t srcSize,
+                     void* workSpace, size_t wkspSize,
+                     int bmi2)
+{
+#if DYNAMIC_BMI2
+    if (bmi2) {
+        return HUF_readStats_body_bmi2(huffWeight, hwSize, rankStats, nbSymbolsPtr, tableLogPtr, src, srcSize, workSpace, wkspSize);
+    }
+#endif
+    (void)bmi2;
+    return HUF_readStats_body_default(huffWeight, hwSize, rankStats, nbSymbolsPtr, tableLogPtr, src, srcSize, workSpace, wkspSize);
+}
diff --git a/lib/zstd/common/error_private.c b/lib/zstd/common/error_private.c
new file mode 100644
index 000000000000..6d1135f8c373
--- /dev/null
+++ b/lib/zstd/common/error_private.c
@@ -0,0 +1,56 @@
+/*
+ * Copyright (c) Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+/* The purpose of this file is to have a single list of error strings embedded in binary */
+
+#include "error_private.h"
+
+const char* ERR_getErrorString(ERR_enum code)
+{
+#ifdef ZSTD_STRIP_ERROR_STRINGS
+    (void)code;
+    return "Error strings stripped";
+#else
+    static const char* const notErrorCode = "Unspecified error code";
+    switch( code )
+    {
+    case PREFIX(no_error): return "No error detected";
+    case PREFIX(GENERIC):  return "Error (generic)";
+    case PREFIX(prefix_unknown): return "Unknown frame descriptor";
+    case PREFIX(version_unsupported): return "Version not supported";
+    case PREFIX(frameParameter_unsupported): return "Unsupported frame parameter";
+    case PREFIX(frameParameter_windowTooLarge): return "Frame requires too much memory for decoding";
+    case PREFIX(corruption_detected): return "Corrupted block detected";
+    case PREFIX(checksum_wrong): return "Restored data doesn't match checksum";
+    case PREFIX(parameter_unsupported): return "Unsupported parameter";
+    case PREFIX(parameter_outOfBound): return "Parameter is out of bound";
+    case PREFIX(init_missing): return "Context should be init first";
+    case PREFIX(memory_allocation): return "Allocation error : not enough memory";
+    case PREFIX(workSpace_tooSmall): return "workSpace buffer is not large enough";
+    case PREFIX(stage_wrong): return "Operation not authorized at current processing stage";
+    case PREFIX(tableLog_tooLarge): return "tableLog requires too much memory : unsupported";
+    case PREFIX(maxSymbolValue_tooLarge): return "Unsupported max Symbol Value : too large";
+    case PREFIX(maxSymbolValue_tooSmall): return "Specified maxSymbolValue is too small";
+    case PREFIX(dictionary_corrupted): return "Dictionary is corrupted";
+    case PREFIX(dictionary_wrong): return "Dictionary mismatch";
+    case PREFIX(dictionaryCreation_failed): return "Cannot create Dictionary from provided samples";
+    case PREFIX(dstSize_tooSmall): return "Destination buffer is too small";
+    case PREFIX(srcSize_wrong): return "Src size is incorrect";
+    case PREFIX(dstBuffer_null): return "Operation on NULL destination buffer";
+        /* following error codes are not stable and may be removed or changed in a future version */
+    case PREFIX(frameIndex_tooLarge): return "Frame index is too large";
+    case PREFIX(seekableIO): return "An I/O error occurred when reading/seeking";
+    case PREFIX(dstBuffer_wrong): return "Destination buffer is wrong";
+    case PREFIX(srcBuffer_wrong): return "Source buffer is wrong";
+    case PREFIX(maxCode):
+    default: return notErrorCode;
+    }
+#endif
+}
diff --git a/lib/zstd/common/error_private.h b/lib/zstd/common/error_private.h
new file mode 100644
index 000000000000..d14e686adf95
--- /dev/null
+++ b/lib/zstd/common/error_private.h
@@ -0,0 +1,66 @@
+/*
+ * Copyright (c) Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+/* Note : this module is expected to remain private, do not expose it */
+
+#ifndef ERROR_H_MODULE
+#define ERROR_H_MODULE
+
+
+
+/* ****************************************
+*  Dependencies
+******************************************/
+#include "zstd_deps.h"    /* size_t */
+#include <linux/zstd_errors.h>  /* enum list */
+
+
+/* ****************************************
+*  Compiler-specific
+******************************************/
+#define ERR_STATIC static __attribute__((unused))
+
+
+/*-****************************************
+*  Customization (error_public.h)
+******************************************/
+typedef ZSTD_ErrorCode ERR_enum;
+#define PREFIX(name) ZSTD_error_##name
+
+
+/*-****************************************
+*  Error codes handling
+******************************************/
+#undef ERROR   /* already defined on Visual Studio */
+#define ERROR(name) ZSTD_ERROR(name)
+#define ZSTD_ERROR(name) ((size_t)-PREFIX(name))
+
+ERR_STATIC unsigned ERR_isError(size_t code) { return (code > ERROR(maxCode)); }
+
+ERR_STATIC ERR_enum ERR_getErrorCode(size_t code) { if (!ERR_isError(code)) return (ERR_enum)0; return (ERR_enum) (0-code); }
+
+/* check and forward error code */
+#define CHECK_V_F(e, f) size_t const e = f; if (ERR_isError(e)) return e
+#define CHECK_F(f)   { CHECK_V_F(_var_err__, f); }
+
+
+/*-****************************************
+*  Error Strings
+******************************************/
+
+const char* ERR_getErrorString(ERR_enum code);   /* error_private.c */
+
+ERR_STATIC const char* ERR_getErrorName(size_t code)
+{
+    return ERR_getErrorString(ERR_getErrorCode(code));
+}
+
+
+#endif /* ERROR_H_MODULE */
diff --git a/lib/zstd/common/fse.h b/lib/zstd/common/fse.h
new file mode 100644
index 000000000000..0bb174c2c367
--- /dev/null
+++ b/lib/zstd/common/fse.h
@@ -0,0 +1,710 @@
+/* ******************************************************************
+ * FSE : Finite State Entropy codec
+ * Public Prototypes declaration
+ * Copyright (c) Yann Collet, Facebook, Inc.
+ *
+ * You can contact the author at :
+ * - Source repository : https://github.com/Cyan4973/FiniteStateEntropy
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+****************************************************************** */
+
+
+#ifndef FSE_H
+#define FSE_H
+
+
+/*-*****************************************
+*  Dependencies
+******************************************/
+#include "zstd_deps.h"    /* size_t, ptrdiff_t */
+
+
+/*-*****************************************
+*  FSE_PUBLIC_API : control library symbols visibility
+******************************************/
+#if defined(FSE_DLL_EXPORT) && (FSE_DLL_EXPORT==1) && defined(__GNUC__) && (__GNUC__ >= 4)
+#  define FSE_PUBLIC_API __attribute__ ((visibility ("default")))
+#elif defined(FSE_DLL_EXPORT) && (FSE_DLL_EXPORT==1)   /* Visual expected */
+#  define FSE_PUBLIC_API __declspec(dllexport)
+#elif defined(FSE_DLL_IMPORT) && (FSE_DLL_IMPORT==1)
+#  define FSE_PUBLIC_API __declspec(dllimport) /* It isn't required but allows to generate better code, saving a function pointer load from the IAT and an indirect jump.*/
+#else
+#  define FSE_PUBLIC_API
+#endif
+
+/*------   Version   ------*/
+#define FSE_VERSION_MAJOR    0
+#define FSE_VERSION_MINOR    9
+#define FSE_VERSION_RELEASE  0
+
+#define FSE_LIB_VERSION FSE_VERSION_MAJOR.FSE_VERSION_MINOR.FSE_VERSION_RELEASE
+#define FSE_QUOTE(str) #str
+#define FSE_EXPAND_AND_QUOTE(str) FSE_QUOTE(str)
+#define FSE_VERSION_STRING FSE_EXPAND_AND_QUOTE(FSE_LIB_VERSION)
+
+#define FSE_VERSION_NUMBER  (FSE_VERSION_MAJOR *100*100 + FSE_VERSION_MINOR *100 + FSE_VERSION_RELEASE)
+FSE_PUBLIC_API unsigned FSE_versionNumber(void);   /*< library version number; to be used when checking dll version */
+
+
+/*-****************************************
+*  FSE simple functions
+******************************************/
+/*! FSE_compress() :
+    Compress content of buffer 'src', of size 'srcSize', into destination buffer 'dst'.
+    'dst' buffer must be already allocated. Compression runs faster is dstCapacity >= FSE_compressBound(srcSize).
+    @return : size of compressed data (<= dstCapacity).
+    Special values : if return == 0, srcData is not compressible => Nothing is stored within dst !!!
+                     if return == 1, srcData is a single byte symbol * srcSize times. Use RLE compression instead.
+                     if FSE_isError(return), compression failed (more details using FSE_getErrorName())
+*/
+FSE_PUBLIC_API size_t FSE_compress(void* dst, size_t dstCapacity,
+                             const void* src, size_t srcSize);
+
+/*! FSE_decompress():
+    Decompress FSE data from buffer 'cSrc', of size 'cSrcSize',
+    into already allocated destination buffer 'dst', of size 'dstCapacity'.
+    @return : size of regenerated data (<= maxDstSize),
+              or an error code, which can be tested using FSE_isError() .
+
+    ** Important ** : FSE_decompress() does not decompress non-compressible nor RLE data !!!
+    Why ? : making this distinction requires a header.
+    Header management is intentionally delegated to the user layer, which can better manage special cases.
+*/
+FSE_PUBLIC_API size_t FSE_decompress(void* dst,  size_t dstCapacity,
+                               const void* cSrc, size_t cSrcSize);
+
+
+/*-*****************************************
+*  Tool functions
+******************************************/
+FSE_PUBLIC_API size_t FSE_compressBound(size_t size);       /* maximum compressed size */
+
+/* Error Management */
+FSE_PUBLIC_API unsigned    FSE_isError(size_t code);        /* tells if a return value is an error code */
+FSE_PUBLIC_API const char* FSE_getErrorName(size_t code);   /* provides error code string (useful for debugging) */
+
+
+/*-*****************************************
+*  FSE advanced functions
+******************************************/
+/*! FSE_compress2() :
+    Same as FSE_compress(), but allows the selection of 'maxSymbolValue' and 'tableLog'
+    Both parameters can be defined as '0' to mean : use default value
+    @return : size of compressed data
+    Special values : if return == 0, srcData is not compressible => Nothing is stored within cSrc !!!
+                     if return == 1, srcData is a single byte symbol * srcSize times. Use RLE compression.
+                     if FSE_isError(return), it's an error code.
+*/
+FSE_PUBLIC_API size_t FSE_compress2 (void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog);
+
+
+/*-*****************************************
+*  FSE detailed API
+******************************************/
+/*!
+FSE_compress() does the following:
+1. count symbol occurrence from source[] into table count[] (see hist.h)
+2. normalize counters so that sum(count[]) == Power_of_2 (2^tableLog)
+3. save normalized counters to memory buffer using writeNCount()
+4. build encoding table 'CTable' from normalized counters
+5. encode the data stream using encoding table 'CTable'
+
+FSE_decompress() does the following:
+1. read normalized counters with readNCount()
+2. build decoding table 'DTable' from normalized counters
+3. decode the data stream using decoding table 'DTable'
+
+The following API allows targeting specific sub-functions for advanced tasks.
+For example, it's possible to compress several blocks using the same 'CTable',
+or to save and provide normalized distribution using external method.
+*/
+
+/* *** COMPRESSION *** */
+
+/*! FSE_optimalTableLog():
+    dynamically downsize 'tableLog' when conditions are met.
+    It saves CPU time, by using smaller tables, while preserving or even improving compression ratio.
+    @return : recommended tableLog (necessarily <= 'maxTableLog') */
+FSE_PUBLIC_API unsigned FSE_optimalTableLog(unsigned maxTableLog, size_t srcSize, unsigned maxSymbolValue);
+
+/*! FSE_normalizeCount():
+    normalize counts so that sum(count[]) == Power_of_2 (2^tableLog)
+    'normalizedCounter' is a table of short, of minimum size (maxSymbolValue+1).
+    useLowProbCount is a boolean parameter which trades off compressed size for
+    faster header decoding. When it is set to 1, the compressed data will be slightly
+    smaller. And when it is set to 0, FSE_readNCount() and FSE_buildDTable() will be
+    faster. If you are compressing a small amount of data (< 2 KB) then useLowProbCount=0
+    is a good default, since header deserialization makes a big speed difference.
+    Otherwise, useLowProbCount=1 is a good default, since the speed difference is small.
+    @return : tableLog,
+              or an errorCode, which can be tested using FSE_isError() */
+FSE_PUBLIC_API size_t FSE_normalizeCount(short* normalizedCounter, unsigned tableLog,
+                    const unsigned* count, size_t srcSize, unsigned maxSymbolValue, unsigned useLowProbCount);
+
+/*! FSE_NCountWriteBound():
+    Provides the maximum possible size of an FSE normalized table, given 'maxSymbolValue' and 'tableLog'.
+    Typically useful for allocation purpose. */
+FSE_PUBLIC_API size_t FSE_NCountWriteBound(unsigned maxSymbolValue, unsigned tableLog);
+
+/*! FSE_writeNCount():
+    Compactly save 'normalizedCounter' into 'buffer'.
+    @return : size of the compressed table,
+              or an errorCode, which can be tested using FSE_isError(). */
+FSE_PUBLIC_API size_t FSE_writeNCount (void* buffer, size_t bufferSize,
+                                 const short* normalizedCounter,
+                                 unsigned maxSymbolValue, unsigned tableLog);
+
+/*! Constructor and Destructor of FSE_CTable.
+    Note that FSE_CTable size depends on 'tableLog' and 'maxSymbolValue' */
+typedef unsigned FSE_CTable;   /* don't allocate that. It's only meant to be more restrictive than void* */
+FSE_PUBLIC_API FSE_CTable* FSE_createCTable (unsigned maxSymbolValue, unsigned tableLog);
+FSE_PUBLIC_API void        FSE_freeCTable (FSE_CTable* ct);
+
+/*! FSE_buildCTable():
+    Builds `ct`, which must be already allocated, using FSE_createCTable().
+    @return : 0, or an errorCode, which can be tested using FSE_isError() */
+FSE_PUBLIC_API size_t FSE_buildCTable(FSE_CTable* ct, const short* normalizedCounter, unsigned maxSymbolValue, unsigned tableLog);
+
+/*! FSE_compress_usingCTable():
+    Compress `src` using `ct` into `dst` which must be already allocated.
+    @return : size of compressed data (<= `dstCapacity`),
+              or 0 if compressed data could not fit into `dst`,
+              or an errorCode, which can be tested using FSE_isError() */
+FSE_PUBLIC_API size_t FSE_compress_usingCTable (void* dst, size_t dstCapacity, const void* src, size_t srcSize, const FSE_CTable* ct);
+
+/*!
+Tutorial :
+----------
+The first step is to count all symbols. FSE_count() does this job very fast.
+Result will be saved into 'count', a table of unsigned int, which must be already allocated, and have 'maxSymbolValuePtr[0]+1' cells.
+'src' is a table of bytes of size 'srcSize'. All values within 'src' MUST be <= maxSymbolValuePtr[0]
+maxSymbolValuePtr[0] will be updated, with its real value (necessarily <= original value)
+FSE_count() will return the number of occurrence of the most frequent symbol.
+This can be used to know if there is a single symbol within 'src', and to quickly evaluate its compressibility.
+If there is an error, the function will return an ErrorCode (which can be tested using FSE_isError()).
+
+The next step is to normalize the frequencies.
+FSE_normalizeCount() will ensure that sum of frequencies is == 2 ^'tableLog'.
+It also guarantees a minimum of 1 to any Symbol with frequency >= 1.
+You can use 'tableLog'==0 to mean "use default tableLog value".
+If you are unsure of which tableLog value to use, you can ask FSE_optimalTableLog(),
+which will provide the optimal valid tableLog given sourceSize, maxSymbolValue, and a user-defined maximum (0 means "default").
+
+The result of FSE_normalizeCount() will be saved into a table,
+called 'normalizedCounter', which is a table of signed short.
+'normalizedCounter' must be already allocated, and have at least 'maxSymbolValue+1' cells.
+The return value is tableLog if everything proceeded as expected.
+It is 0 if there is a single symbol within distribution.
+If there is an error (ex: invalid tableLog value), the function will return an ErrorCode (which can be tested using FSE_isError()).
+
+'normalizedCounter' can be saved in a compact manner to a memory area using FSE_writeNCount().
+'buffer' must be already allocated.
+For guaranteed success, buffer size must be at least FSE_headerBound().
+The result of the function is the number of bytes written into 'buffer'.
+If there is an error, the function will return an ErrorCode (which can be tested using FSE_isError(); ex : buffer size too small).
+
+'normalizedCounter' can then be used to create the compression table 'CTable'.
+The space required by 'CTable' must be already allocated, using FSE_createCTable().
+You can then use FSE_buildCTable() to fill 'CTable'.
+If there is an error, both functions will return an ErrorCode (which can be tested using FSE_isError()).
+
+'CTable' can then be used to compress 'src', with FSE_compress_usingCTable().
+Similar to FSE_count(), the convention is that 'src' is assumed to be a table of char of size 'srcSize'
+The function returns the size of compressed data (without header), necessarily <= `dstCapacity`.
+If it returns '0', compressed data could not fit into 'dst'.
+If there is an error, the function will return an ErrorCode (which can be tested using FSE_isError()).
+*/
+
+
+/* *** DECOMPRESSION *** */
+
+/*! FSE_readNCount():
+    Read compactly saved 'normalizedCounter' from 'rBuffer'.
+    @return : size read from 'rBuffer',
+              or an errorCode, which can be tested using FSE_isError().
+              maxSymbolValuePtr[0] and tableLogPtr[0] will also be updated with their respective values */
+FSE_PUBLIC_API size_t FSE_readNCount (short* normalizedCounter,
+                           unsigned* maxSymbolValuePtr, unsigned* tableLogPtr,
+                           const void* rBuffer, size_t rBuffSize);
+
+/*! FSE_readNCount_bmi2():
+ * Same as FSE_readNCount() but pass bmi2=1 when your CPU supports BMI2 and 0 otherwise.
+ */
+FSE_PUBLIC_API size_t FSE_readNCount_bmi2(short* normalizedCounter,
+                           unsigned* maxSymbolValuePtr, unsigned* tableLogPtr,
+                           const void* rBuffer, size_t rBuffSize, int bmi2);
+
+/*! Constructor and Destructor of FSE_DTable.
+    Note that its size depends on 'tableLog' */
+typedef unsigned FSE_DTable;   /* don't allocate that. It's just a way to be more restrictive than void* */
+FSE_PUBLIC_API FSE_DTable* FSE_createDTable(unsigned tableLog);
+FSE_PUBLIC_API void        FSE_freeDTable(FSE_DTable* dt);
+
+/*! FSE_buildDTable():
+    Builds 'dt', which must be already allocated, using FSE_createDTable().
+    return : 0, or an errorCode, which can be tested using FSE_isError() */
+FSE_PUBLIC_API size_t FSE_buildDTable (FSE_DTable* dt, const short* normalizedCounter, unsigned maxSymbolValue, unsigned tableLog);
+
+/*! FSE_decompress_usingDTable():
+    Decompress compressed source `cSrc` of size `cSrcSize` using `dt`
+    into `dst` which must be already allocated.
+    @return : size of regenerated data (necessarily <= `dstCapacity`),
+              or an errorCode, which can be tested using FSE_isError() */
+FSE_PUBLIC_API size_t FSE_decompress_usingDTable(void* dst, size_t dstCapacity, const void* cSrc, size_t cSrcSize, const FSE_DTable* dt);
+
+/*!
+Tutorial :
+----------
+(Note : these functions only decompress FSE-compressed blocks.
+ If block is uncompressed, use memcpy() instead
+ If block is a single repeated byte, use memset() instead )
+
+The first step is to obtain the normalized frequencies of symbols.
+This can be performed by FSE_readNCount() if it was saved using FSE_writeNCount().
+'normalizedCounter' must be already allocated, and have at least 'maxSymbolValuePtr[0]+1' cells of signed short.
+In practice, that means it's necessary to know 'maxSymbolValue' beforehand,
+or size the table to handle worst case situations (typically 256).
+FSE_readNCount() will provide 'tableLog' and 'maxSymbolValue'.
+The result of FSE_readNCount() is the number of bytes read from 'rBuffer'.
+Note that 'rBufferSize' must be at least 4 bytes, even if useful information is less than that.
+If there is an error, the function will return an error code, which can be tested using FSE_isError().
+
+The next step is to build the decompression tables 'FSE_DTable' from 'normalizedCounter'.
+This is performed by the function FSE_buildDTable().
+The space required by 'FSE_DTable' must be already allocated using FSE_createDTable().
+If there is an error, the function will return an error code, which can be tested using FSE_isError().
+
+`FSE_DTable` can then be used to decompress `cSrc`, with FSE_decompress_usingDTable().
+`cSrcSize` must be strictly correct, otherwise decompression will fail.
+FSE_decompress_usingDTable() result will tell how many bytes were regenerated (<=`dstCapacity`).
+If there is an error, the function will return an error code, which can be tested using FSE_isError(). (ex: dst buffer too small)
+*/
+
+#endif  /* FSE_H */
+
+#if !defined(FSE_H_FSE_STATIC_LINKING_ONLY)
+#define FSE_H_FSE_STATIC_LINKING_ONLY
+
+/* *** Dependency *** */
+#include "bitstream.h"
+
+
+/* *****************************************
+*  Static allocation
+*******************************************/
+/* FSE buffer bounds */
+#define FSE_NCOUNTBOUND 512
+#define FSE_BLOCKBOUND(size) ((size) + ((size)>>7) + 4 /* fse states */ + sizeof(size_t) /* bitContainer */)
+#define FSE_COMPRESSBOUND(size) (FSE_NCOUNTBOUND + FSE_BLOCKBOUND(size))   /* Macro version, useful for static allocation */
+
+/* It is possible to statically allocate FSE CTable/DTable as a table of FSE_CTable/FSE_DTable using below macros */
+#define FSE_CTABLE_SIZE_U32(maxTableLog, maxSymbolValue)   (1 + (1<<((maxTableLog)-1)) + (((maxSymbolValue)+1)*2))
+#define FSE_DTABLE_SIZE_U32(maxTableLog)                   (1 + (1<<(maxTableLog)))
+
+/* or use the size to malloc() space directly. Pay attention to alignment restrictions though */
+#define FSE_CTABLE_SIZE(maxTableLog, maxSymbolValue)   (FSE_CTABLE_SIZE_U32(maxTableLog, maxSymbolValue) * sizeof(FSE_CTable))
+#define FSE_DTABLE_SIZE(maxTableLog)                   (FSE_DTABLE_SIZE_U32(maxTableLog) * sizeof(FSE_DTable))
+
+
+/* *****************************************
+ *  FSE advanced API
+ ***************************************** */
+
+unsigned FSE_optimalTableLog_internal(unsigned maxTableLog, size_t srcSize, unsigned maxSymbolValue, unsigned minus);
+/*< same as FSE_optimalTableLog(), which used `minus==2` */
+
+/* FSE_compress_wksp() :
+ * Same as FSE_compress2(), but using an externally allocated scratch buffer (`workSpace`).
+ * FSE_COMPRESS_WKSP_SIZE_U32() provides the minimum size required for `workSpace` as a table of FSE_CTable.
+ */
+#define FSE_COMPRESS_WKSP_SIZE_U32(maxTableLog, maxSymbolValue)   ( FSE_CTABLE_SIZE_U32(maxTableLog, maxSymbolValue) + ((maxTableLog > 12) ? (1 << (maxTableLog - 2)) : 1024) )
+size_t FSE_compress_wksp (void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog, void* workSpace, size_t wkspSize);
+
+size_t FSE_buildCTable_raw (FSE_CTable* ct, unsigned nbBits);
+/*< build a fake FSE_CTable, designed for a flat distribution, where each symbol uses nbBits */
+
+size_t FSE_buildCTable_rle (FSE_CTable* ct, unsigned char symbolValue);
+/*< build a fake FSE_CTable, designed to compress always the same symbolValue */
+
+/* FSE_buildCTable_wksp() :
+ * Same as FSE_buildCTable(), but using an externally allocated scratch buffer (`workSpace`).
+ * `wkspSize` must be >= `FSE_BUILD_CTABLE_WORKSPACE_SIZE_U32(maxSymbolValue, tableLog)` of `unsigned`.
+ */
+#define FSE_BUILD_CTABLE_WORKSPACE_SIZE_U32(maxSymbolValue, tableLog) (maxSymbolValue + 2 + (1ull << (tableLog - 2)))
+#define FSE_BUILD_CTABLE_WORKSPACE_SIZE(maxSymbolValue, tableLog) (sizeof(unsigned) * FSE_BUILD_CTABLE_WORKSPACE_SIZE_U32(maxSymbolValue, tableLog))
+size_t FSE_buildCTable_wksp(FSE_CTable* ct, const short* normalizedCounter, unsigned maxSymbolValue, unsigned tableLog, void* workSpace, size_t wkspSize);
+
+#define FSE_BUILD_DTABLE_WKSP_SIZE(maxTableLog, maxSymbolValue) (sizeof(short) * (maxSymbolValue + 1) + (1ULL << maxTableLog) + 8)
+#define FSE_BUILD_DTABLE_WKSP_SIZE_U32(maxTableLog, maxSymbolValue) ((FSE_BUILD_DTABLE_WKSP_SIZE(maxTableLog, maxSymbolValue) + sizeof(unsigned) - 1) / sizeof(unsigned))
+FSE_PUBLIC_API size_t FSE_buildDTable_wksp(FSE_DTable* dt, const short* normalizedCounter, unsigned maxSymbolValue, unsigned tableLog, void* workSpace, size_t wkspSize);
+/*< Same as FSE_buildDTable(), using an externally allocated `workspace` produced with `FSE_BUILD_DTABLE_WKSP_SIZE_U32(maxSymbolValue)` */
+
+size_t FSE_buildDTable_raw (FSE_DTable* dt, unsigned nbBits);
+/*< build a fake FSE_DTable, designed to read a flat distribution where each symbol uses nbBits */
+
+size_t FSE_buildDTable_rle (FSE_DTable* dt, unsigned char symbolValue);
+/*< build a fake FSE_DTable, designed to always generate the same symbolValue */
+
+#define FSE_DECOMPRESS_WKSP_SIZE_U32(maxTableLog, maxSymbolValue) (FSE_DTABLE_SIZE_U32(maxTableLog) + FSE_BUILD_DTABLE_WKSP_SIZE_U32(maxTableLog, maxSymbolValue) + (FSE_MAX_SYMBOL_VALUE + 1) / 2 + 1)
+#define FSE_DECOMPRESS_WKSP_SIZE(maxTableLog, maxSymbolValue) (FSE_DECOMPRESS_WKSP_SIZE_U32(maxTableLog, maxSymbolValue) * sizeof(unsigned))
+size_t FSE_decompress_wksp(void* dst, size_t dstCapacity, const void* cSrc, size_t cSrcSize, unsigned maxLog, void* workSpace, size_t wkspSize);
+/*< same as FSE_decompress(), using an externally allocated `workSpace` produced with `FSE_DECOMPRESS_WKSP_SIZE_U32(maxLog, maxSymbolValue)` */
+
+size_t FSE_decompress_wksp_bmi2(void* dst, size_t dstCapacity, const void* cSrc, size_t cSrcSize, unsigned maxLog, void* workSpace, size_t wkspSize, int bmi2);
+/*< Same as FSE_decompress_wksp() but with dynamic BMI2 support. Pass 1 if your CPU supports BMI2 or 0 if it doesn't. */
+
+typedef enum {
+   FSE_repeat_none,  /*< Cannot use the previous table */
+   FSE_repeat_check, /*< Can use the previous table but it must be checked */
+   FSE_repeat_valid  /*< Can use the previous table and it is assumed to be valid */
+ } FSE_repeat;
+
+/* *****************************************
+*  FSE symbol compression API
+*******************************************/
+/*!
+   This API consists of small unitary functions, which highly benefit from being inlined.
+   Hence their body are included in next section.
+*/
+typedef struct {
+    ptrdiff_t   value;
+    const void* stateTable;
+    const void* symbolTT;
+    unsigned    stateLog;
+} FSE_CState_t;
+
+static void FSE_initCState(FSE_CState_t* CStatePtr, const FSE_CTable* ct);
+
+static void FSE_encodeSymbol(BIT_CStream_t* bitC, FSE_CState_t* CStatePtr, unsigned symbol);
+
+static void FSE_flushCState(BIT_CStream_t* bitC, const FSE_CState_t* CStatePtr);
+
+/*<
+These functions are inner components of FSE_compress_usingCTable().
+They allow the creation of custom streams, mixing multiple tables and bit sources.
+
+A key property to keep in mind is that encoding and decoding are done **in reverse direction**.
+So the first symbol you will encode is the last you will decode, like a LIFO stack.
+
+You will need a few variables to track your CStream. They are :
+
+FSE_CTable    ct;         // Provided by FSE_buildCTable()
+BIT_CStream_t bitStream;  // bitStream tracking structure
+FSE_CState_t  state;      // State tracking structure (can have several)
+
+
+The first thing to do is to init bitStream and state.
+    size_t errorCode = BIT_initCStream(&bitStream, dstBuffer, maxDstSize);
+    FSE_initCState(&state, ct);
+
+Note that BIT_initCStream() can produce an error code, so its result should be tested, using FSE_isError();
+You can then encode your input data, byte after byte.
+FSE_encodeSymbol() outputs a maximum of 'tableLog' bits at a time.
+Remember decoding will be done in reverse direction.
+    FSE_encodeByte(&bitStream, &state, symbol);
+
+At any time, you can also add any bit sequence.
+Note : maximum allowed nbBits is 25, for compatibility with 32-bits decoders
+    BIT_addBits(&bitStream, bitField, nbBits);
+
+The above methods don't commit data to memory, they just store it into local register, for speed.
+Local register size is 64-bits on 64-bits systems, 32-bits on 32-bits systems (size_t).
+Writing data to memory is a manual operation, performed by the flushBits function.
+    BIT_flushBits(&bitStream);
+
+Your last FSE encoding operation shall be to flush your last state value(s).
+    FSE_flushState(&bitStream, &state);
+
+Finally, you must close the bitStream.
+The function returns the size of CStream in bytes.
+If data couldn't fit into dstBuffer, it will return a 0 ( == not compressible)
+If there is an error, it returns an errorCode (which can be tested using FSE_isError()).
+    size_t size = BIT_closeCStream(&bitStream);
+*/
+
+
+/* *****************************************
+*  FSE symbol decompression API
+*******************************************/
+typedef struct {
+    size_t      state;
+    const void* table;   /* precise table may vary, depending on U16 */
+} FSE_DState_t;
+
+
+static void     FSE_initDState(FSE_DState_t* DStatePtr, BIT_DStream_t* bitD, const FSE_DTable* dt);
+
+static unsigned char FSE_decodeSymbol(FSE_DState_t* DStatePtr, BIT_DStream_t* bitD);
+
+static unsigned FSE_endOfDState(const FSE_DState_t* DStatePtr);
+
+/*<
+Let's now decompose FSE_decompress_usingDTable() into its unitary components.
+You will decode FSE-encoded symbols from the bitStream,
+and also any other bitFields you put in, **in reverse order**.
+
+You will need a few variables to track your bitStream. They are :
+
+BIT_DStream_t DStream;    // Stream context
+FSE_DState_t  DState;     // State context. Multiple ones are possible
+FSE_DTable*   DTablePtr;  // Decoding table, provided by FSE_buildDTable()
+
+The first thing to do is to init the bitStream.
+    errorCode = BIT_initDStream(&DStream, srcBuffer, srcSize);
+
+You should then retrieve your initial state(s)
+(in reverse flushing order if you have several ones) :
+    errorCode = FSE_initDState(&DState, &DStream, DTablePtr);
+
+You can then decode your data, symbol after symbol.
+For information the maximum number of bits read by FSE_decodeSymbol() is 'tableLog'.
+Keep in mind that symbols are decoded in reverse order, like a LIFO stack (last in, first out).
+    unsigned char symbol = FSE_decodeSymbol(&DState, &DStream);
+
+You can retrieve any bitfield you eventually stored into the bitStream (in reverse order)
+Note : maximum allowed nbBits is 25, for 32-bits compatibility
+    size_t bitField = BIT_readBits(&DStream, nbBits);
+
+All above operations only read from local register (which size depends on size_t).
+Refueling the register from memory is manually performed by the reload method.
+    endSignal = FSE_reloadDStream(&DStream);
+
+BIT_reloadDStream() result tells if there is still some more data to read from DStream.
+BIT_DStream_unfinished : there is still some data left into the DStream.
+BIT_DStream_endOfBuffer : Dstream reached end of buffer. Its container may no longer be completely filled.
+BIT_DStream_completed : Dstream reached its exact end, corresponding in general to decompression completed.
+BIT_DStream_tooFar : Dstream went too far. Decompression result is corrupted.
+
+When reaching end of buffer (BIT_DStream_endOfBuffer), progress slowly, notably if you decode multiple symbols per loop,
+to properly detect the exact end of stream.
+After each decoded symbol, check if DStream is fully consumed using this simple test :
+    BIT_reloadDStream(&DStream) >= BIT_DStream_completed
+
+When it's done, verify decompression is fully completed, by checking both DStream and the relevant states.
+Checking if DStream has reached its end is performed by :
+    BIT_endOfDStream(&DStream);
+Check also the states. There might be some symbols left there, if some high probability ones (>50%) are possible.
+    FSE_endOfDState(&DState);
+*/
+
+
+/* *****************************************
+*  FSE unsafe API
+*******************************************/
+static unsigned char FSE_decodeSymbolFast(FSE_DState_t* DStatePtr, BIT_DStream_t* bitD);
+/* faster, but works only if nbBits is always >= 1 (otherwise, result will be corrupted) */
+
+
+/* *****************************************
+*  Implementation of inlined functions
+*******************************************/
+typedef struct {
+    int deltaFindState;
+    U32 deltaNbBits;
+} FSE_symbolCompressionTransform; /* total 8 bytes */
+
+MEM_STATIC void FSE_initCState(FSE_CState_t* statePtr, const FSE_CTable* ct)
+{
+    const void* ptr = ct;
+    const U16* u16ptr = (const U16*) ptr;
+    const U32 tableLog = MEM_read16(ptr);
+    statePtr->value = (ptrdiff_t)1<<tableLog;
+    statePtr->stateTable = u16ptr+2;
+    statePtr->symbolTT = ct + 1 + (tableLog ? (1<<(tableLog-1)) : 1);
+    statePtr->stateLog = tableLog;
+}
+
+
+/*! FSE_initCState2() :
+*   Same as FSE_initCState(), but the first symbol to include (which will be the last to be read)
+*   uses the smallest state value possible, saving the cost of this symbol */
+MEM_STATIC void FSE_initCState2(FSE_CState_t* statePtr, const FSE_CTable* ct, U32 symbol)
+{
+    FSE_initCState(statePtr, ct);
+    {   const FSE_symbolCompressionTransform symbolTT = ((const FSE_symbolCompressionTransform*)(statePtr->symbolTT))[symbol];
+        const U16* stateTable = (const U16*)(statePtr->stateTable);
+        U32 nbBitsOut  = (U32)((symbolTT.deltaNbBits + (1<<15)) >> 16);
+        statePtr->value = (nbBitsOut << 16) - symbolTT.deltaNbBits;
+        statePtr->value = stateTable[(statePtr->value >> nbBitsOut) + symbolTT.deltaFindState];
+    }
+}
+
+MEM_STATIC void FSE_encodeSymbol(BIT_CStream_t* bitC, FSE_CState_t* statePtr, unsigned symbol)
+{
+    FSE_symbolCompressionTransform const symbolTT = ((const FSE_symbolCompressionTransform*)(statePtr->symbolTT))[symbol];
+    const U16* const stateTable = (const U16*)(statePtr->stateTable);
+    U32 const nbBitsOut  = (U32)((statePtr->value + symbolTT.deltaNbBits) >> 16);
+    BIT_addBits(bitC, statePtr->value, nbBitsOut);
+    statePtr->value = stateTable[ (statePtr->value >> nbBitsOut) + symbolTT.deltaFindState];
+}
+
+MEM_STATIC void FSE_flushCState(BIT_CStream_t* bitC, const FSE_CState_t* statePtr)
+{
+    BIT_addBits(bitC, statePtr->value, statePtr->stateLog);
+    BIT_flushBits(bitC);
+}
+
+
+/* FSE_getMaxNbBits() :
+ * Approximate maximum cost of a symbol, in bits.
+ * Fractional get rounded up (i.e : a symbol with a normalized frequency of 3 gives the same result as a frequency of 2)
+ * note 1 : assume symbolValue is valid (<= maxSymbolValue)
+ * note 2 : if freq[symbolValue]==0, @return a fake cost of tableLog+1 bits */
+MEM_STATIC U32 FSE_getMaxNbBits(const void* symbolTTPtr, U32 symbolValue)
+{
+    const FSE_symbolCompressionTransform* symbolTT = (const FSE_symbolCompressionTransform*) symbolTTPtr;
+    return (symbolTT[symbolValue].deltaNbBits + ((1<<16)-1)) >> 16;
+}
+
+/* FSE_bitCost() :
+ * Approximate symbol cost, as fractional value, using fixed-point format (accuracyLog fractional bits)
+ * note 1 : assume symbolValue is valid (<= maxSymbolValue)
+ * note 2 : if freq[symbolValue]==0, @return a fake cost of tableLog+1 bits */
+MEM_STATIC U32 FSE_bitCost(const void* symbolTTPtr, U32 tableLog, U32 symbolValue, U32 accuracyLog)
+{
+    const FSE_symbolCompressionTransform* symbolTT = (const FSE_symbolCompressionTransform*) symbolTTPtr;
+    U32 const minNbBits = symbolTT[symbolValue].deltaNbBits >> 16;
+    U32 const threshold = (minNbBits+1) << 16;
+    assert(tableLog < 16);
+    assert(accuracyLog < 31-tableLog);  /* ensure enough room for renormalization double shift */
+    {   U32 const tableSize = 1 << tableLog;
+        U32 const deltaFromThreshold = threshold - (symbolTT[symbolValue].deltaNbBits + tableSize);
+        U32 const normalizedDeltaFromThreshold = (deltaFromThreshold << accuracyLog) >> tableLog;   /* linear interpolation (very approximate) */
+        U32 const bitMultiplier = 1 << accuracyLog;
+        assert(symbolTT[symbolValue].deltaNbBits + tableSize <= threshold);
+        assert(normalizedDeltaFromThreshold <= bitMultiplier);
+        return (minNbBits+1)*bitMultiplier - normalizedDeltaFromThreshold;
+    }
+}
+
+
+/* ======    Decompression    ====== */
+
+typedef struct {
+    U16 tableLog;
+    U16 fastMode;
+} FSE_DTableHeader;   /* sizeof U32 */
+
+typedef struct
+{
+    unsigned short newState;
+    unsigned char  symbol;
+    unsigned char  nbBits;
+} FSE_decode_t;   /* size == U32 */
+
+MEM_STATIC void FSE_initDState(FSE_DState_t* DStatePtr, BIT_DStream_t* bitD, const FSE_DTable* dt)
+{
+    const void* ptr = dt;
+    const FSE_DTableHeader* const DTableH = (const FSE_DTableHeader*)ptr;
+    DStatePtr->state = BIT_readBits(bitD, DTableH->tableLog);
+    BIT_reloadDStream(bitD);
+    DStatePtr->table = dt + 1;
+}
+
+MEM_STATIC BYTE FSE_peekSymbol(const FSE_DState_t* DStatePtr)
+{
+    FSE_decode_t const DInfo = ((const FSE_decode_t*)(DStatePtr->table))[DStatePtr->state];
+    return DInfo.symbol;
+}
+
+MEM_STATIC void FSE_updateState(FSE_DState_t* DStatePtr, BIT_DStream_t* bitD)
+{
+    FSE_decode_t const DInfo = ((const FSE_decode_t*)(DStatePtr->table))[DStatePtr->state];
+    U32 const nbBits = DInfo.nbBits;
+    size_t const lowBits = BIT_readBits(bitD, nbBits);
+    DStatePtr->state = DInfo.newState + lowBits;
+}
+
+MEM_STATIC BYTE FSE_decodeSymbol(FSE_DState_t* DStatePtr, BIT_DStream_t* bitD)
+{
+    FSE_decode_t const DInfo = ((const FSE_decode_t*)(DStatePtr->table))[DStatePtr->state];
+    U32 const nbBits = DInfo.nbBits;
+    BYTE const symbol = DInfo.symbol;
+    size_t const lowBits = BIT_readBits(bitD, nbBits);
+
+    DStatePtr->state = DInfo.newState + lowBits;
+    return symbol;
+}
+
+/*! FSE_decodeSymbolFast() :
+    unsafe, only works if no symbol has a probability > 50% */
+MEM_STATIC BYTE FSE_decodeSymbolFast(FSE_DState_t* DStatePtr, BIT_DStream_t* bitD)
+{
+    FSE_decode_t const DInfo = ((const FSE_decode_t*)(DStatePtr->table))[DStatePtr->state];
+    U32 const nbBits = DInfo.nbBits;
+    BYTE const symbol = DInfo.symbol;
+    size_t const lowBits = BIT_readBitsFast(bitD, nbBits);
+
+    DStatePtr->state = DInfo.newState + lowBits;
+    return symbol;
+}
+
+MEM_STATIC unsigned FSE_endOfDState(const FSE_DState_t* DStatePtr)
+{
+    return DStatePtr->state == 0;
+}
+
+
+
+#ifndef FSE_COMMONDEFS_ONLY
+
+/* **************************************************************
+*  Tuning parameters
+****************************************************************/
+/*!MEMORY_USAGE :
+*  Memory usage formula : N->2^N Bytes (examples : 10 -> 1KB; 12 -> 4KB ; 16 -> 64KB; 20 -> 1MB; etc.)
+*  Increasing memory usage improves compression ratio
+*  Reduced memory usage can improve speed, due to cache effect
+*  Recommended max value is 14, for 16KB, which nicely fits into Intel x86 L1 cache */
+#ifndef FSE_MAX_MEMORY_USAGE
+#  define FSE_MAX_MEMORY_USAGE 14
+#endif
+#ifndef FSE_DEFAULT_MEMORY_USAGE
+#  define FSE_DEFAULT_MEMORY_USAGE 13
+#endif
+#if (FSE_DEFAULT_MEMORY_USAGE > FSE_MAX_MEMORY_USAGE)
+#  error "FSE_DEFAULT_MEMORY_USAGE must be <= FSE_MAX_MEMORY_USAGE"
+#endif
+
+/*!FSE_MAX_SYMBOL_VALUE :
+*  Maximum symbol value authorized.
+*  Required for proper stack allocation */
+#ifndef FSE_MAX_SYMBOL_VALUE
+#  define FSE_MAX_SYMBOL_VALUE 255
+#endif
+
+/* **************************************************************
+*  template functions type & suffix
+****************************************************************/
+#define FSE_FUNCTION_TYPE BYTE
+#define FSE_FUNCTION_EXTENSION
+#define FSE_DECODE_TYPE FSE_decode_t
+
+
+#endif   /* !FSE_COMMONDEFS_ONLY */
+
+
+/* ***************************************************************
+*  Constants
+*****************************************************************/
+#define FSE_MAX_TABLELOG  (FSE_MAX_MEMORY_USAGE-2)
+#define FSE_MAX_TABLESIZE (1U<<FSE_MAX_TABLELOG)
+#define FSE_MAXTABLESIZE_MASK (FSE_MAX_TABLESIZE-1)
+#define FSE_DEFAULT_TABLELOG (FSE_DEFAULT_MEMORY_USAGE-2)
+#define FSE_MIN_TABLELOG 5
+
+#define FSE_TABLELOG_ABSOLUTE_MAX 15
+#if FSE_MAX_TABLELOG > FSE_TABLELOG_ABSOLUTE_MAX
+#  error "FSE_MAX_TABLELOG > FSE_TABLELOG_ABSOLUTE_MAX is not supported"
+#endif
+
+#define FSE_TABLESTEP(tableSize) (((tableSize)>>1) + ((tableSize)>>3) + 3)
+
+
+#endif /* FSE_STATIC_LINKING_ONLY */
+
+
diff --git a/lib/zstd/common/fse_decompress.c b/lib/zstd/common/fse_decompress.c
new file mode 100644
index 000000000000..2c8bbe3e4c14
--- /dev/null
+++ b/lib/zstd/common/fse_decompress.c
@@ -0,0 +1,390 @@
+/* ******************************************************************
+ * FSE : Finite State Entropy decoder
+ * Copyright (c) Yann Collet, Facebook, Inc.
+ *
+ *  You can contact the author at :
+ *  - FSE source repository : https://github.com/Cyan4973/FiniteStateEntropy
+ *  - Public forum : https://groups.google.com/forum/#!forum/lz4c
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+****************************************************************** */
+
+
+/* **************************************************************
+*  Includes
+****************************************************************/
+#include "debug.h"      /* assert */
+#include "bitstream.h"
+#include "compiler.h"
+#define FSE_STATIC_LINKING_ONLY
+#include "fse.h"
+#include "error_private.h"
+#define ZSTD_DEPS_NEED_MALLOC
+#include "zstd_deps.h"
+
+
+/* **************************************************************
+*  Error Management
+****************************************************************/
+#define FSE_isError ERR_isError
+#define FSE_STATIC_ASSERT(c) DEBUG_STATIC_ASSERT(c)   /* use only *after* variable declarations */
+
+
+/* **************************************************************
+*  Templates
+****************************************************************/
+/*
+  designed to be included
+  for type-specific functions (template emulation in C)
+  Objective is to write these functions only once, for improved maintenance
+*/
+
+/* safety checks */
+#ifndef FSE_FUNCTION_EXTENSION
+#  error "FSE_FUNCTION_EXTENSION must be defined"
+#endif
+#ifndef FSE_FUNCTION_TYPE
+#  error "FSE_FUNCTION_TYPE must be defined"
+#endif
+
+/* Function names */
+#define FSE_CAT(X,Y) X##Y
+#define FSE_FUNCTION_NAME(X,Y) FSE_CAT(X,Y)
+#define FSE_TYPE_NAME(X,Y) FSE_CAT(X,Y)
+
+
+/* Function templates */
+FSE_DTable* FSE_createDTable (unsigned tableLog)
+{
+    if (tableLog > FSE_TABLELOG_ABSOLUTE_MAX) tableLog = FSE_TABLELOG_ABSOLUTE_MAX;
+    return (FSE_DTable*)ZSTD_malloc( FSE_DTABLE_SIZE_U32(tableLog) * sizeof (U32) );
+}
+
+void FSE_freeDTable (FSE_DTable* dt)
+{
+    ZSTD_free(dt);
+}
+
+static size_t FSE_buildDTable_internal(FSE_DTable* dt, const short* normalizedCounter, unsigned maxSymbolValue, unsigned tableLog, void* workSpace, size_t wkspSize)
+{
+    void* const tdPtr = dt+1;   /* because *dt is unsigned, 32-bits aligned on 32-bits */
+    FSE_DECODE_TYPE* const tableDecode = (FSE_DECODE_TYPE*) (tdPtr);
+    U16* symbolNext = (U16*)workSpace;
+    BYTE* spread = (BYTE*)(symbolNext + maxSymbolValue + 1);
+
+    U32 const maxSV1 = maxSymbolValue + 1;
+    U32 const tableSize = 1 << tableLog;
+    U32 highThreshold = tableSize-1;
+
+    /* Sanity Checks */
+    if (FSE_BUILD_DTABLE_WKSP_SIZE(tableLog, maxSymbolValue) > wkspSize) return ERROR(maxSymbolValue_tooLarge);
+    if (maxSymbolValue > FSE_MAX_SYMBOL_VALUE) return ERROR(maxSymbolValue_tooLarge);
+    if (tableLog > FSE_MAX_TABLELOG) return ERROR(tableLog_tooLarge);
+
+    /* Init, lay down lowprob symbols */
+    {   FSE_DTableHeader DTableH;
+        DTableH.tableLog = (U16)tableLog;
+        DTableH.fastMode = 1;
+        {   S16 const largeLimit= (S16)(1 << (tableLog-1));
+            U32 s;
+            for (s=0; s<maxSV1; s++) {
+                if (normalizedCounter[s]==-1) {
+                    tableDecode[highThreshold--].symbol = (FSE_FUNCTION_TYPE)s;
+                    symbolNext[s] = 1;
+                } else {
+                    if (normalizedCounter[s] >= largeLimit) DTableH.fastMode=0;
+                    symbolNext[s] = normalizedCounter[s];
+        }   }   }
+        ZSTD_memcpy(dt, &DTableH, sizeof(DTableH));
+    }
+
+    /* Spread symbols */
+    if (highThreshold == tableSize - 1) {
+        size_t const tableMask = tableSize-1;
+        size_t const step = FSE_TABLESTEP(tableSize);
+        /* First lay down the symbols in order.
+         * We use a uint64_t to lay down 8 bytes at a time. This reduces branch
+         * misses since small blocks generally have small table logs, so nearly
+         * all symbols have counts <= 8. We ensure we have 8 bytes at the end of
+         * our buffer to handle the over-write.
+         */
+        {
+            U64 const add = 0x0101010101010101ull;
+            size_t pos = 0;
+            U64 sv = 0;
+            U32 s;
+            for (s=0; s<maxSV1; ++s, sv += add) {
+                int i;
+                int const n = normalizedCounter[s];
+                MEM_write64(spread + pos, sv);
+                for (i = 8; i < n; i += 8) {
+                    MEM_write64(spread + pos + i, sv);
+                }
+                pos += n;
+            }
+        }
+        /* Now we spread those positions across the table.
+         * The benefit of doing it in two stages is that we avoid the the
+         * variable size inner loop, which caused lots of branch misses.
+         * Now we can run through all the positions without any branch misses.
+         * We unroll the loop twice, since that is what emperically worked best.
+         */
+        {
+            size_t position = 0;
+            size_t s;
+            size_t const unroll = 2;
+            assert(tableSize % unroll == 0); /* FSE_MIN_TABLELOG is 5 */
+            for (s = 0; s < (size_t)tableSize; s += unroll) {
+                size_t u;
+                for (u = 0; u < unroll; ++u) {
+                    size_t const uPosition = (position + (u * step)) & tableMask;
+                    tableDecode[uPosition].symbol = spread[s + u];
+                }
+                position = (position + (unroll * step)) & tableMask;
+            }
+            assert(position == 0);
+        }
+    } else {
+        U32 const tableMask = tableSize-1;
+        U32 const step = FSE_TABLESTEP(tableSize);
+        U32 s, position = 0;
+        for (s=0; s<maxSV1; s++) {
+            int i;
+            for (i=0; i<normalizedCounter[s]; i++) {
+                tableDecode[position].symbol = (FSE_FUNCTION_TYPE)s;
+                position = (position + step) & tableMask;
+                while (position > highThreshold) position = (position + step) & tableMask;   /* lowprob area */
+        }   }
+        if (position!=0) return ERROR(GENERIC);   /* position must reach all cells once, otherwise normalizedCounter is incorrect */
+    }
+
+    /* Build Decoding table */
+    {   U32 u;
+        for (u=0; u<tableSize; u++) {
+            FSE_FUNCTION_TYPE const symbol = (FSE_FUNCTION_TYPE)(tableDecode[u].symbol);
+            U32 const nextState = symbolNext[symbol]++;
+            tableDecode[u].nbBits = (BYTE) (tableLog - BIT_highbit32(nextState) );
+            tableDecode[u].newState = (U16) ( (nextState << tableDecode[u].nbBits) - tableSize);
+    }   }
+
+    return 0;
+}
+
+size_t FSE_buildDTable_wksp(FSE_DTable* dt, const short* normalizedCounter, unsigned maxSymbolValue, unsigned tableLog, void* workSpace, size_t wkspSize)
+{
+    return FSE_buildDTable_internal(dt, normalizedCounter, maxSymbolValue, tableLog, workSpace, wkspSize);
+}
+
+
+#ifndef FSE_COMMONDEFS_ONLY
+
+/*-*******************************************************
+*  Decompression (Byte symbols)
+*********************************************************/
+size_t FSE_buildDTable_rle (FSE_DTable* dt, BYTE symbolValue)
+{
+    void* ptr = dt;
+    FSE_DTableHeader* const DTableH = (FSE_DTableHeader*)ptr;
+    void* dPtr = dt + 1;
+    FSE_decode_t* const cell = (FSE_decode_t*)dPtr;
+
+    DTableH->tableLog = 0;
+    DTableH->fastMode = 0;
+
+    cell->newState = 0;
+    cell->symbol = symbolValue;
+    cell->nbBits = 0;
+
+    return 0;
+}
+
+
+size_t FSE_buildDTable_raw (FSE_DTable* dt, unsigned nbBits)
+{
+    void* ptr = dt;
+    FSE_DTableHeader* const DTableH = (FSE_DTableHeader*)ptr;
+    void* dPtr = dt + 1;
+    FSE_decode_t* const dinfo = (FSE_decode_t*)dPtr;
+    const unsigned tableSize = 1 << nbBits;
+    const unsigned tableMask = tableSize - 1;
+    const unsigned maxSV1 = tableMask+1;
+    unsigned s;
+
+    /* Sanity checks */
+    if (nbBits < 1) return ERROR(GENERIC);         /* min size */
+
+    /* Build Decoding Table */
+    DTableH->tableLog = (U16)nbBits;
+    DTableH->fastMode = 1;
+    for (s=0; s<maxSV1; s++) {
+        dinfo[s].newState = 0;
+        dinfo[s].symbol = (BYTE)s;
+        dinfo[s].nbBits = (BYTE)nbBits;
+    }
+
+    return 0;
+}
+
+FORCE_INLINE_TEMPLATE size_t FSE_decompress_usingDTable_generic(
+          void* dst, size_t maxDstSize,
+    const void* cSrc, size_t cSrcSize,
+    const FSE_DTable* dt, const unsigned fast)
+{
+    BYTE* const ostart = (BYTE*) dst;
+    BYTE* op = ostart;
+    BYTE* const omax = op + maxDstSize;
+    BYTE* const olimit = omax-3;
+
+    BIT_DStream_t bitD;
+    FSE_DState_t state1;
+    FSE_DState_t state2;
+
+    /* Init */
+    CHECK_F(BIT_initDStream(&bitD, cSrc, cSrcSize));
+
+    FSE_initDState(&state1, &bitD, dt);
+    FSE_initDState(&state2, &bitD, dt);
+
+#define FSE_GETSYMBOL(statePtr) fast ? FSE_decodeSymbolFast(statePtr, &bitD) : FSE_decodeSymbol(statePtr, &bitD)
+
+    /* 4 symbols per loop */
+    for ( ; (BIT_reloadDStream(&bitD)==BIT_DStream_unfinished) & (op<olimit) ; op+=4) {
+        op[0] = FSE_GETSYMBOL(&state1);
+
+        if (FSE_MAX_TABLELOG*2+7 > sizeof(bitD.bitContainer)*8)    /* This test must be static */
+            BIT_reloadDStream(&bitD);
+
+        op[1] = FSE_GETSYMBOL(&state2);
+
+        if (FSE_MAX_TABLELOG*4+7 > sizeof(bitD.bitContainer)*8)    /* This test must be static */
+            { if (BIT_reloadDStream(&bitD) > BIT_DStream_unfinished) { op+=2; break; } }
+
+        op[2] = FSE_GETSYMBOL(&state1);
+
+        if (FSE_MAX_TABLELOG*2+7 > sizeof(bitD.bitContainer)*8)    /* This test must be static */
+            BIT_reloadDStream(&bitD);
+
+        op[3] = FSE_GETSYMBOL(&state2);
+    }
+
+    /* tail */
+    /* note : BIT_reloadDStream(&bitD) >= FSE_DStream_partiallyFilled; Ends at exactly BIT_DStream_completed */
+    while (1) {
+        if (op>(omax-2)) return ERROR(dstSize_tooSmall);
+        *op++ = FSE_GETSYMBOL(&state1);
+        if (BIT_reloadDStream(&bitD)==BIT_DStream_overflow) {
+            *op++ = FSE_GETSYMBOL(&state2);
+            break;
+        }
+
+        if (op>(omax-2)) return ERROR(dstSize_tooSmall);
+        *op++ = FSE_GETSYMBOL(&state2);
+        if (BIT_reloadDStream(&bitD)==BIT_DStream_overflow) {
+            *op++ = FSE_GETSYMBOL(&state1);
+            break;
+    }   }
+
+    return op-ostart;
+}
+
+
+size_t FSE_decompress_usingDTable(void* dst, size_t originalSize,
+                            const void* cSrc, size_t cSrcSize,
+                            const FSE_DTable* dt)
+{
+    const void* ptr = dt;
+    const FSE_DTableHeader* DTableH = (const FSE_DTableHeader*)ptr;
+    const U32 fastMode = DTableH->fastMode;
+
+    /* select fast mode (static) */
+    if (fastMode) return FSE_decompress_usingDTable_generic(dst, originalSize, cSrc, cSrcSize, dt, 1);
+    return FSE_decompress_usingDTable_generic(dst, originalSize, cSrc, cSrcSize, dt, 0);
+}
+
+
+size_t FSE_decompress_wksp(void* dst, size_t dstCapacity, const void* cSrc, size_t cSrcSize, unsigned maxLog, void* workSpace, size_t wkspSize)
+{
+    return FSE_decompress_wksp_bmi2(dst, dstCapacity, cSrc, cSrcSize, maxLog, workSpace, wkspSize, /* bmi2 */ 0);
+}
+
+typedef struct {
+    short ncount[FSE_MAX_SYMBOL_VALUE + 1];
+    FSE_DTable dtable[1]; /* Dynamically sized */
+} FSE_DecompressWksp;
+
+
+FORCE_INLINE_TEMPLATE size_t FSE_decompress_wksp_body(
+        void* dst, size_t dstCapacity,
+        const void* cSrc, size_t cSrcSize,
+        unsigned maxLog, void* workSpace, size_t wkspSize,
+        int bmi2)
+{
+    const BYTE* const istart = (const BYTE*)cSrc;
+    const BYTE* ip = istart;
+    unsigned tableLog;
+    unsigned maxSymbolValue = FSE_MAX_SYMBOL_VALUE;
+    FSE_DecompressWksp* const wksp = (FSE_DecompressWksp*)workSpace;
+
+    DEBUG_STATIC_ASSERT((FSE_MAX_SYMBOL_VALUE + 1) % 2 == 0);
+    if (wkspSize < sizeof(*wksp)) return ERROR(GENERIC);
+
+    /* normal FSE decoding mode */
+    {
+        size_t const NCountLength = FSE_readNCount_bmi2(wksp->ncount, &maxSymbolValue, &tableLog, istart, cSrcSize, bmi2);
+        if (FSE_isError(NCountLength)) return NCountLength;
+        if (tableLog > maxLog) return ERROR(tableLog_tooLarge);
+        assert(NCountLength <= cSrcSize);
+        ip += NCountLength;
+        cSrcSize -= NCountLength;
+    }
+
+    if (FSE_DECOMPRESS_WKSP_SIZE(tableLog, maxSymbolValue) > wkspSize) return ERROR(tableLog_tooLarge);
+    workSpace = wksp->dtable + FSE_DTABLE_SIZE_U32(tableLog);
+    wkspSize -= sizeof(*wksp) + FSE_DTABLE_SIZE(tableLog);
+
+    CHECK_F( FSE_buildDTable_internal(wksp->dtable, wksp->ncount, maxSymbolValue, tableLog, workSpace, wkspSize) );
+
+    {
+        const void* ptr = wksp->dtable;
+        const FSE_DTableHeader* DTableH = (const FSE_DTableHeader*)ptr;
+        const U32 fastMode = DTableH->fastMode;
+
+        /* select fast mode (static) */
+        if (fastMode) return FSE_decompress_usingDTable_generic(dst, dstCapacity, ip, cSrcSize, wksp->dtable, 1);
+        return FSE_decompress_usingDTable_generic(dst, dstCapacity, ip, cSrcSize, wksp->dtable, 0);
+    }
+}
+
+/* Avoids the FORCE_INLINE of the _body() function. */
+static size_t FSE_decompress_wksp_body_default(void* dst, size_t dstCapacity, const void* cSrc, size_t cSrcSize, unsigned maxLog, void* workSpace, size_t wkspSize)
+{
+    return FSE_decompress_wksp_body(dst, dstCapacity, cSrc, cSrcSize, maxLog, workSpace, wkspSize, 0);
+}
+
+#if DYNAMIC_BMI2
+TARGET_ATTRIBUTE("bmi2") static size_t FSE_decompress_wksp_body_bmi2(void* dst, size_t dstCapacity, const void* cSrc, size_t cSrcSize, unsigned maxLog, void* workSpace, size_t wkspSize)
+{
+    return FSE_decompress_wksp_body(dst, dstCapacity, cSrc, cSrcSize, maxLog, workSpace, wkspSize, 1);
+}
+#endif
+
+size_t FSE_decompress_wksp_bmi2(void* dst, size_t dstCapacity, const void* cSrc, size_t cSrcSize, unsigned maxLog, void* workSpace, size_t wkspSize, int bmi2)
+{
+#if DYNAMIC_BMI2
+    if (bmi2) {
+        return FSE_decompress_wksp_body_bmi2(dst, dstCapacity, cSrc, cSrcSize, maxLog, workSpace, wkspSize);
+    }
+#endif
+    (void)bmi2;
+    return FSE_decompress_wksp_body_default(dst, dstCapacity, cSrc, cSrcSize, maxLog, workSpace, wkspSize);
+}
+
+
+typedef FSE_DTable DTable_max_t[FSE_DTABLE_SIZE_U32(FSE_MAX_TABLELOG)];
+
+
+
+#endif   /* FSE_COMMONDEFS_ONLY */
diff --git a/lib/zstd/common/huf.h b/lib/zstd/common/huf.h
new file mode 100644
index 000000000000..88c5586646aa
--- /dev/null
+++ b/lib/zstd/common/huf.h
@@ -0,0 +1,356 @@
+/* ******************************************************************
+ * huff0 huffman codec,
+ * part of Finite State Entropy library
+ * Copyright (c) Yann Collet, Facebook, Inc.
+ *
+ * You can contact the author at :
+ * - Source repository : https://github.com/Cyan4973/FiniteStateEntropy
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+****************************************************************** */
+
+
+#ifndef HUF_H_298734234
+#define HUF_H_298734234
+
+/* *** Dependencies *** */
+#include "zstd_deps.h"    /* size_t */
+
+
+/* *** library symbols visibility *** */
+/* Note : when linking with -fvisibility=hidden on gcc, or by default on Visual,
+ *        HUF symbols remain "private" (internal symbols for library only).
+ *        Set macro FSE_DLL_EXPORT to 1 if you want HUF symbols visible on DLL interface */
+#if defined(FSE_DLL_EXPORT) && (FSE_DLL_EXPORT==1) && defined(__GNUC__) && (__GNUC__ >= 4)
+#  define HUF_PUBLIC_API __attribute__ ((visibility ("default")))
+#elif defined(FSE_DLL_EXPORT) && (FSE_DLL_EXPORT==1)   /* Visual expected */
+#  define HUF_PUBLIC_API __declspec(dllexport)
+#elif defined(FSE_DLL_IMPORT) && (FSE_DLL_IMPORT==1)
+#  define HUF_PUBLIC_API __declspec(dllimport)  /* not required, just to generate faster code (saves a function pointer load from IAT and an indirect jump) */
+#else
+#  define HUF_PUBLIC_API
+#endif
+
+
+/* ========================== */
+/* ***  simple functions  *** */
+/* ========================== */
+
+/* HUF_compress() :
+ *  Compress content from buffer 'src', of size 'srcSize', into buffer 'dst'.
+ * 'dst' buffer must be already allocated.
+ *  Compression runs faster if `dstCapacity` >= HUF_compressBound(srcSize).
+ * `srcSize` must be <= `HUF_BLOCKSIZE_MAX` == 128 KB.
+ * @return : size of compressed data (<= `dstCapacity`).
+ *  Special values : if return == 0, srcData is not compressible => Nothing is stored within dst !!!
+ *                   if HUF_isError(return), compression failed (more details using HUF_getErrorName())
+ */
+HUF_PUBLIC_API size_t HUF_compress(void* dst, size_t dstCapacity,
+                             const void* src, size_t srcSize);
+
+/* HUF_decompress() :
+ *  Decompress HUF data from buffer 'cSrc', of size 'cSrcSize',
+ *  into already allocated buffer 'dst', of minimum size 'dstSize'.
+ * `originalSize` : **must** be the ***exact*** size of original (uncompressed) data.
+ *  Note : in contrast with FSE, HUF_decompress can regenerate
+ *         RLE (cSrcSize==1) and uncompressed (cSrcSize==dstSize) data,
+ *         because it knows size to regenerate (originalSize).
+ * @return : size of regenerated data (== originalSize),
+ *           or an error code, which can be tested using HUF_isError()
+ */
+HUF_PUBLIC_API size_t HUF_decompress(void* dst,  size_t originalSize,
+                               const void* cSrc, size_t cSrcSize);
+
+
+/* ***   Tool functions *** */
+#define HUF_BLOCKSIZE_MAX (128 * 1024)                  /*< maximum input size for a single block compressed with HUF_compress */
+HUF_PUBLIC_API size_t HUF_compressBound(size_t size);   /*< maximum compressed size (worst case) */
+
+/* Error Management */
+HUF_PUBLIC_API unsigned    HUF_isError(size_t code);       /*< tells if a return value is an error code */
+HUF_PUBLIC_API const char* HUF_getErrorName(size_t code);  /*< provides error code string (useful for debugging) */
+
+
+/* ***   Advanced function   *** */
+
+/* HUF_compress2() :
+ *  Same as HUF_compress(), but offers control over `maxSymbolValue` and `tableLog`.
+ * `maxSymbolValue` must be <= HUF_SYMBOLVALUE_MAX .
+ * `tableLog` must be `<= HUF_TABLELOG_MAX` . */
+HUF_PUBLIC_API size_t HUF_compress2 (void* dst, size_t dstCapacity,
+                               const void* src, size_t srcSize,
+                               unsigned maxSymbolValue, unsigned tableLog);
+
+/* HUF_compress4X_wksp() :
+ *  Same as HUF_compress2(), but uses externally allocated `workSpace`.
+ * `workspace` must have minimum alignment of 4, and be at least as large as HUF_WORKSPACE_SIZE */
+#define HUF_WORKSPACE_SIZE ((6 << 10) + 256)
+#define HUF_WORKSPACE_SIZE_U32 (HUF_WORKSPACE_SIZE / sizeof(U32))
+HUF_PUBLIC_API size_t HUF_compress4X_wksp (void* dst, size_t dstCapacity,
+                                     const void* src, size_t srcSize,
+                                     unsigned maxSymbolValue, unsigned tableLog,
+                                     void* workSpace, size_t wkspSize);
+
+#endif   /* HUF_H_298734234 */
+
+/* ******************************************************************
+ *  WARNING !!
+ *  The following section contains advanced and experimental definitions
+ *  which shall never be used in the context of a dynamic library,
+ *  because they are not guaranteed to remain stable in the future.
+ *  Only consider them in association with static linking.
+ * *****************************************************************/
+#if !defined(HUF_H_HUF_STATIC_LINKING_ONLY)
+#define HUF_H_HUF_STATIC_LINKING_ONLY
+
+/* *** Dependencies *** */
+#include "mem.h"   /* U32 */
+#define FSE_STATIC_LINKING_ONLY
+#include "fse.h"
+
+
+/* *** Constants *** */
+#define HUF_TABLELOG_MAX      12      /* max runtime value of tableLog (due to static allocation); can be modified up to HUF_ABSOLUTEMAX_TABLELOG */
+#define HUF_TABLELOG_DEFAULT  11      /* default tableLog value when none specified */
+#define HUF_SYMBOLVALUE_MAX  255
+
+#define HUF_TABLELOG_ABSOLUTEMAX  15  /* absolute limit of HUF_MAX_TABLELOG. Beyond that value, code does not work */
+#if (HUF_TABLELOG_MAX > HUF_TABLELOG_ABSOLUTEMAX)
+#  error "HUF_TABLELOG_MAX is too large !"
+#endif
+
+
+/* ****************************************
+*  Static allocation
+******************************************/
+/* HUF buffer bounds */
+#define HUF_CTABLEBOUND 129
+#define HUF_BLOCKBOUND(size) (size + (size>>8) + 8)   /* only true when incompressible is pre-filtered with fast heuristic */
+#define HUF_COMPRESSBOUND(size) (HUF_CTABLEBOUND + HUF_BLOCKBOUND(size))   /* Macro version, useful for static allocation */
+
+/* static allocation of HUF's Compression Table */
+/* this is a private definition, just exposed for allocation and strict aliasing purpose. never EVER access its members directly */
+struct HUF_CElt_s {
+  U16  val;
+  BYTE nbBits;
+};   /* typedef'd to HUF_CElt */
+typedef struct HUF_CElt_s HUF_CElt;   /* consider it an incomplete type */
+#define HUF_CTABLE_SIZE_U32(maxSymbolValue)   ((maxSymbolValue)+1)   /* Use tables of U32, for proper alignment */
+#define HUF_CTABLE_SIZE(maxSymbolValue)       (HUF_CTABLE_SIZE_U32(maxSymbolValue) * sizeof(U32))
+#define HUF_CREATE_STATIC_CTABLE(name, maxSymbolValue) \
+    HUF_CElt name[HUF_CTABLE_SIZE_U32(maxSymbolValue)] /* no final ; */
+
+/* static allocation of HUF's DTable */
+typedef U32 HUF_DTable;
+#define HUF_DTABLE_SIZE(maxTableLog)   (1 + (1<<(maxTableLog)))
+#define HUF_CREATE_STATIC_DTABLEX1(DTable, maxTableLog) \
+        HUF_DTable DTable[HUF_DTABLE_SIZE((maxTableLog)-1)] = { ((U32)((maxTableLog)-1) * 0x01000001) }
+#define HUF_CREATE_STATIC_DTABLEX2(DTable, maxTableLog) \
+        HUF_DTable DTable[HUF_DTABLE_SIZE(maxTableLog)] = { ((U32)(maxTableLog) * 0x01000001) }
+
+
+/* ****************************************
+*  Advanced decompression functions
+******************************************/
+size_t HUF_decompress4X1 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize);   /*< single-symbol decoder */
+#ifndef HUF_FORCE_DECOMPRESS_X1
+size_t HUF_decompress4X2 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize);   /*< double-symbols decoder */
+#endif
+
+size_t HUF_decompress4X_DCtx (HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize);   /*< decodes RLE and uncompressed */
+size_t HUF_decompress4X_hufOnly(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize); /*< considers RLE and uncompressed as errors */
+size_t HUF_decompress4X_hufOnly_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize); /*< considers RLE and uncompressed as errors */
+size_t HUF_decompress4X1_DCtx(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize);   /*< single-symbol decoder */
+size_t HUF_decompress4X1_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize);   /*< single-symbol decoder */
+#ifndef HUF_FORCE_DECOMPRESS_X1
+size_t HUF_decompress4X2_DCtx(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize);   /*< double-symbols decoder */
+size_t HUF_decompress4X2_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize);   /*< double-symbols decoder */
+#endif
+
+
+/* ****************************************
+ *  HUF detailed API
+ * ****************************************/
+
+/*! HUF_compress() does the following:
+ *  1. count symbol occurrence from source[] into table count[] using FSE_count() (exposed within "fse.h")
+ *  2. (optional) refine tableLog using HUF_optimalTableLog()
+ *  3. build Huffman table from count using HUF_buildCTable()
+ *  4. save Huffman table to memory buffer using HUF_writeCTable()
+ *  5. encode the data stream using HUF_compress4X_usingCTable()
+ *
+ *  The following API allows targeting specific sub-functions for advanced tasks.
+ *  For example, it's possible to compress several blocks using the same 'CTable',
+ *  or to save and regenerate 'CTable' using external methods.
+ */
+unsigned HUF_optimalTableLog(unsigned maxTableLog, size_t srcSize, unsigned maxSymbolValue);
+size_t HUF_buildCTable (HUF_CElt* CTable, const unsigned* count, unsigned maxSymbolValue, unsigned maxNbBits);   /* @return : maxNbBits; CTable and count can overlap. In which case, CTable will overwrite count content */
+size_t HUF_writeCTable (void* dst, size_t maxDstSize, const HUF_CElt* CTable, unsigned maxSymbolValue, unsigned huffLog);
+size_t HUF_writeCTable_wksp(void* dst, size_t maxDstSize, const HUF_CElt* CTable, unsigned maxSymbolValue, unsigned huffLog, void* workspace, size_t workspaceSize);
+size_t HUF_compress4X_usingCTable(void* dst, size_t dstSize, const void* src, size_t srcSize, const HUF_CElt* CTable);
+size_t HUF_estimateCompressedSize(const HUF_CElt* CTable, const unsigned* count, unsigned maxSymbolValue);
+int HUF_validateCTable(const HUF_CElt* CTable, const unsigned* count, unsigned maxSymbolValue);
+
+typedef enum {
+   HUF_repeat_none,  /*< Cannot use the previous table */
+   HUF_repeat_check, /*< Can use the previous table but it must be checked. Note : The previous table must have been constructed by HUF_compress{1, 4}X_repeat */
+   HUF_repeat_valid  /*< Can use the previous table and it is assumed to be valid */
+ } HUF_repeat;
+/* HUF_compress4X_repeat() :
+ *  Same as HUF_compress4X_wksp(), but considers using hufTable if *repeat != HUF_repeat_none.
+ *  If it uses hufTable it does not modify hufTable or repeat.
+ *  If it doesn't, it sets *repeat = HUF_repeat_none, and it sets hufTable to the table used.
+ *  If preferRepeat then the old table will always be used if valid. */
+size_t HUF_compress4X_repeat(void* dst, size_t dstSize,
+                       const void* src, size_t srcSize,
+                       unsigned maxSymbolValue, unsigned tableLog,
+                       void* workSpace, size_t wkspSize,    /*< `workSpace` must be aligned on 4-bytes boundaries, `wkspSize` must be >= HUF_WORKSPACE_SIZE */
+                       HUF_CElt* hufTable, HUF_repeat* repeat, int preferRepeat, int bmi2);
+
+/* HUF_buildCTable_wksp() :
+ *  Same as HUF_buildCTable(), but using externally allocated scratch buffer.
+ * `workSpace` must be aligned on 4-bytes boundaries, and its size must be >= HUF_CTABLE_WORKSPACE_SIZE.
+ */
+#define HUF_CTABLE_WORKSPACE_SIZE_U32 (2*HUF_SYMBOLVALUE_MAX +1 +1)
+#define HUF_CTABLE_WORKSPACE_SIZE (HUF_CTABLE_WORKSPACE_SIZE_U32 * sizeof(unsigned))
+size_t HUF_buildCTable_wksp (HUF_CElt* tree,
+                       const unsigned* count, U32 maxSymbolValue, U32 maxNbBits,
+                             void* workSpace, size_t wkspSize);
+
+/*! HUF_readStats() :
+ *  Read compact Huffman tree, saved by HUF_writeCTable().
+ * `huffWeight` is destination buffer.
+ * @return : size read from `src` , or an error Code .
+ *  Note : Needed by HUF_readCTable() and HUF_readDTableXn() . */
+size_t HUF_readStats(BYTE* huffWeight, size_t hwSize,
+                     U32* rankStats, U32* nbSymbolsPtr, U32* tableLogPtr,
+                     const void* src, size_t srcSize);
+
+/*! HUF_readStats_wksp() :
+ * Same as HUF_readStats() but takes an external workspace which must be
+ * 4-byte aligned and its size must be >= HUF_READ_STATS_WORKSPACE_SIZE.
+ * If the CPU has BMI2 support, pass bmi2=1, otherwise pass bmi2=0.
+ */
+#define HUF_READ_STATS_WORKSPACE_SIZE_U32 FSE_DECOMPRESS_WKSP_SIZE_U32(6, HUF_TABLELOG_MAX-1)
+#define HUF_READ_STATS_WORKSPACE_SIZE (HUF_READ_STATS_WORKSPACE_SIZE_U32 * sizeof(unsigned))
+size_t HUF_readStats_wksp(BYTE* huffWeight, size_t hwSize,
+                          U32* rankStats, U32* nbSymbolsPtr, U32* tableLogPtr,
+                          const void* src, size_t srcSize,
+                          void* workspace, size_t wkspSize,
+                          int bmi2);
+
+/* HUF_readCTable() :
+ *  Loading a CTable saved with HUF_writeCTable() */
+size_t HUF_readCTable (HUF_CElt* CTable, unsigned* maxSymbolValuePtr, const void* src, size_t srcSize, unsigned *hasZeroWeights);
+
+/* HUF_getNbBits() :
+ *  Read nbBits from CTable symbolTable, for symbol `symbolValue` presumed <= HUF_SYMBOLVALUE_MAX
+ *  Note 1 : is not inlined, as HUF_CElt definition is private
+ *  Note 2 : const void* used, so that it can provide a statically allocated table as argument (which uses type U32) */
+U32 HUF_getNbBits(const void* symbolTable, U32 symbolValue);
+
+/*
+ * HUF_decompress() does the following:
+ * 1. select the decompression algorithm (X1, X2) based on pre-computed heuristics
+ * 2. build Huffman table from save, using HUF_readDTableX?()
+ * 3. decode 1 or 4 segments in parallel using HUF_decompress?X?_usingDTable()
+ */
+
+/* HUF_selectDecoder() :
+ *  Tells which decoder is likely to decode faster,
+ *  based on a set of pre-computed metrics.
+ * @return : 0==HUF_decompress4X1, 1==HUF_decompress4X2 .
+ *  Assumption : 0 < dstSize <= 128 KB */
+U32 HUF_selectDecoder (size_t dstSize, size_t cSrcSize);
+
+/*
+ *  The minimum workspace size for the `workSpace` used in
+ *  HUF_readDTableX1_wksp() and HUF_readDTableX2_wksp().
+ *
+ *  The space used depends on HUF_TABLELOG_MAX, ranging from ~1500 bytes when
+ *  HUF_TABLE_LOG_MAX=12 to ~1850 bytes when HUF_TABLE_LOG_MAX=15.
+ *  Buffer overflow errors may potentially occur if code modifications result in
+ *  a required workspace size greater than that specified in the following
+ *  macro.
+ */
+#define HUF_DECOMPRESS_WORKSPACE_SIZE ((2 << 10) + (1 << 9))
+#define HUF_DECOMPRESS_WORKSPACE_SIZE_U32 (HUF_DECOMPRESS_WORKSPACE_SIZE / sizeof(U32))
+
+#ifndef HUF_FORCE_DECOMPRESS_X2
+size_t HUF_readDTableX1 (HUF_DTable* DTable, const void* src, size_t srcSize);
+size_t HUF_readDTableX1_wksp (HUF_DTable* DTable, const void* src, size_t srcSize, void* workSpace, size_t wkspSize);
+#endif
+#ifndef HUF_FORCE_DECOMPRESS_X1
+size_t HUF_readDTableX2 (HUF_DTable* DTable, const void* src, size_t srcSize);
+size_t HUF_readDTableX2_wksp (HUF_DTable* DTable, const void* src, size_t srcSize, void* workSpace, size_t wkspSize);
+#endif
+
+size_t HUF_decompress4X_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable);
+#ifndef HUF_FORCE_DECOMPRESS_X2
+size_t HUF_decompress4X1_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable);
+#endif
+#ifndef HUF_FORCE_DECOMPRESS_X1
+size_t HUF_decompress4X2_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable);
+#endif
+
+
+/* ====================== */
+/* single stream variants */
+/* ====================== */
+
+size_t HUF_compress1X (void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog);
+size_t HUF_compress1X_wksp (void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog, void* workSpace, size_t wkspSize);  /*< `workSpace` must be a table of at least HUF_WORKSPACE_SIZE_U32 unsigned */
+size_t HUF_compress1X_usingCTable(void* dst, size_t dstSize, const void* src, size_t srcSize, const HUF_CElt* CTable);
+/* HUF_compress1X_repeat() :
+ *  Same as HUF_compress1X_wksp(), but considers using hufTable if *repeat != HUF_repeat_none.
+ *  If it uses hufTable it does not modify hufTable or repeat.
+ *  If it doesn't, it sets *repeat = HUF_repeat_none, and it sets hufTable to the table used.
+ *  If preferRepeat then the old table will always be used if valid. */
+size_t HUF_compress1X_repeat(void* dst, size_t dstSize,
+                       const void* src, size_t srcSize,
+                       unsigned maxSymbolValue, unsigned tableLog,
+                       void* workSpace, size_t wkspSize,   /*< `workSpace` must be aligned on 4-bytes boundaries, `wkspSize` must be >= HUF_WORKSPACE_SIZE */
+                       HUF_CElt* hufTable, HUF_repeat* repeat, int preferRepeat, int bmi2);
+
+size_t HUF_decompress1X1 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize);   /* single-symbol decoder */
+#ifndef HUF_FORCE_DECOMPRESS_X1
+size_t HUF_decompress1X2 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize);   /* double-symbol decoder */
+#endif
+
+size_t HUF_decompress1X_DCtx (HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize);
+size_t HUF_decompress1X_DCtx_wksp (HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize);
+#ifndef HUF_FORCE_DECOMPRESS_X2
+size_t HUF_decompress1X1_DCtx(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize);   /*< single-symbol decoder */
+size_t HUF_decompress1X1_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize);   /*< single-symbol decoder */
+#endif
+#ifndef HUF_FORCE_DECOMPRESS_X1
+size_t HUF_decompress1X2_DCtx(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize);   /*< double-symbols decoder */
+size_t HUF_decompress1X2_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize);   /*< double-symbols decoder */
+#endif
+
+size_t HUF_decompress1X_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable);   /*< automatic selection of sing or double symbol decoder, based on DTable */
+#ifndef HUF_FORCE_DECOMPRESS_X2
+size_t HUF_decompress1X1_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable);
+#endif
+#ifndef HUF_FORCE_DECOMPRESS_X1
+size_t HUF_decompress1X2_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable);
+#endif
+
+/* BMI2 variants.
+ * If the CPU has BMI2 support, pass bmi2=1, otherwise pass bmi2=0.
+ */
+size_t HUF_decompress1X_usingDTable_bmi2(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable, int bmi2);
+#ifndef HUF_FORCE_DECOMPRESS_X2
+size_t HUF_decompress1X1_DCtx_wksp_bmi2(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize, int bmi2);
+#endif
+size_t HUF_decompress4X_usingDTable_bmi2(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable, int bmi2);
+size_t HUF_decompress4X_hufOnly_wksp_bmi2(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize, int bmi2);
+#ifndef HUF_FORCE_DECOMPRESS_X2
+size_t HUF_readDTableX1_wksp_bmi2(HUF_DTable* DTable, const void* src, size_t srcSize, void* workSpace, size_t wkspSize, int bmi2);
+#endif
+
+#endif /* HUF_STATIC_LINKING_ONLY */
+
diff --git a/lib/zstd/common/mem.h b/lib/zstd/common/mem.h
new file mode 100644
index 000000000000..dcdd586a9fd9
--- /dev/null
+++ b/lib/zstd/common/mem.h
@@ -0,0 +1,259 @@
+/* SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause */
+/*
+ * Copyright (c) Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+#ifndef MEM_H_MODULE
+#define MEM_H_MODULE
+
+/*-****************************************
+*  Dependencies
+******************************************/
+#include <asm/unaligned.h>  /* get_unaligned, put_unaligned* */
+#include <linux/compiler.h>  /* inline */
+#include <linux/swab.h>  /* swab32, swab64 */
+#include <linux/types.h>  /* size_t, ptrdiff_t */
+#include "debug.h"  /* DEBUG_STATIC_ASSERT */
+
+/*-****************************************
+*  Compiler specifics
+******************************************/
+#define MEM_STATIC static inline
+
+/*-**************************************************************
+*  Basic Types
+*****************************************************************/
+typedef uint8_t  BYTE;
+typedef uint16_t U16;
+typedef int16_t  S16;
+typedef uint32_t U32;
+typedef int32_t  S32;
+typedef uint64_t U64;
+typedef int64_t  S64;
+
+/*-**************************************************************
+*  Memory I/O API
+*****************************************************************/
+/*=== Static platform detection ===*/
+MEM_STATIC unsigned MEM_32bits(void);
+MEM_STATIC unsigned MEM_64bits(void);
+MEM_STATIC unsigned MEM_isLittleEndian(void);
+
+/*=== Native unaligned read/write ===*/
+MEM_STATIC U16 MEM_read16(const void* memPtr);
+MEM_STATIC U32 MEM_read32(const void* memPtr);
+MEM_STATIC U64 MEM_read64(const void* memPtr);
+MEM_STATIC size_t MEM_readST(const void* memPtr);
+
+MEM_STATIC void MEM_write16(void* memPtr, U16 value);
+MEM_STATIC void MEM_write32(void* memPtr, U32 value);
+MEM_STATIC void MEM_write64(void* memPtr, U64 value);
+
+/*=== Little endian unaligned read/write ===*/
+MEM_STATIC U16 MEM_readLE16(const void* memPtr);
+MEM_STATIC U32 MEM_readLE24(const void* memPtr);
+MEM_STATIC U32 MEM_readLE32(const void* memPtr);
+MEM_STATIC U64 MEM_readLE64(const void* memPtr);
+MEM_STATIC size_t MEM_readLEST(const void* memPtr);
+
+MEM_STATIC void MEM_writeLE16(void* memPtr, U16 val);
+MEM_STATIC void MEM_writeLE24(void* memPtr, U32 val);
+MEM_STATIC void MEM_writeLE32(void* memPtr, U32 val32);
+MEM_STATIC void MEM_writeLE64(void* memPtr, U64 val64);
+MEM_STATIC void MEM_writeLEST(void* memPtr, size_t val);
+
+/*=== Big endian unaligned read/write ===*/
+MEM_STATIC U32 MEM_readBE32(const void* memPtr);
+MEM_STATIC U64 MEM_readBE64(const void* memPtr);
+MEM_STATIC size_t MEM_readBEST(const void* memPtr);
+
+MEM_STATIC void MEM_writeBE32(void* memPtr, U32 val32);
+MEM_STATIC void MEM_writeBE64(void* memPtr, U64 val64);
+MEM_STATIC void MEM_writeBEST(void* memPtr, size_t val);
+
+/*=== Byteswap ===*/
+MEM_STATIC U32 MEM_swap32(U32 in);
+MEM_STATIC U64 MEM_swap64(U64 in);
+MEM_STATIC size_t MEM_swapST(size_t in);
+
+/*-**************************************************************
+*  Memory I/O Implementation
+*****************************************************************/
+MEM_STATIC unsigned MEM_32bits(void)
+{
+    return sizeof(size_t) == 4;
+}
+
+MEM_STATIC unsigned MEM_64bits(void)
+{
+    return sizeof(size_t) == 8;
+}
+
+#if defined(__LITTLE_ENDIAN)
+#define MEM_LITTLE_ENDIAN 1
+#else
+#define MEM_LITTLE_ENDIAN 0
+#endif
+
+MEM_STATIC unsigned MEM_isLittleEndian(void)
+{
+    return MEM_LITTLE_ENDIAN;
+}
+
+MEM_STATIC U16 MEM_read16(const void *memPtr)
+{
+    return get_unaligned((const U16 *)memPtr);
+}
+
+MEM_STATIC U32 MEM_read32(const void *memPtr)
+{
+    return get_unaligned((const U32 *)memPtr);
+}
+
+MEM_STATIC U64 MEM_read64(const void *memPtr)
+{
+    return get_unaligned((const U64 *)memPtr);
+}
+
+MEM_STATIC size_t MEM_readST(const void *memPtr)
+{
+    return get_unaligned((const size_t *)memPtr);
+}
+
+MEM_STATIC void MEM_write16(void *memPtr, U16 value)
+{
+    put_unaligned(value, (U16 *)memPtr);
+}
+
+MEM_STATIC void MEM_write32(void *memPtr, U32 value)
+{
+    put_unaligned(value, (U32 *)memPtr);
+}
+
+MEM_STATIC void MEM_write64(void *memPtr, U64 value)
+{
+    put_unaligned(value, (U64 *)memPtr);
+}
+
+/*=== Little endian r/w ===*/
+
+MEM_STATIC U16 MEM_readLE16(const void *memPtr)
+{
+    return get_unaligned_le16(memPtr);
+}
+
+MEM_STATIC void MEM_writeLE16(void *memPtr, U16 val)
+{
+    put_unaligned_le16(val, memPtr);
+}
+
+MEM_STATIC U32 MEM_readLE24(const void *memPtr)
+{
+    return MEM_readLE16(memPtr) + (((const BYTE *)memPtr)[2] << 16);
+}
+
+MEM_STATIC void MEM_writeLE24(void *memPtr, U32 val)
+{
+	MEM_writeLE16(memPtr, (U16)val);
+	((BYTE *)memPtr)[2] = (BYTE)(val >> 16);
+}
+
+MEM_STATIC U32 MEM_readLE32(const void *memPtr)
+{
+    return get_unaligned_le32(memPtr);
+}
+
+MEM_STATIC void MEM_writeLE32(void *memPtr, U32 val32)
+{
+    put_unaligned_le32(val32, memPtr);
+}
+
+MEM_STATIC U64 MEM_readLE64(const void *memPtr)
+{
+    return get_unaligned_le64(memPtr);
+}
+
+MEM_STATIC void MEM_writeLE64(void *memPtr, U64 val64)
+{
+    put_unaligned_le64(val64, memPtr);
+}
+
+MEM_STATIC size_t MEM_readLEST(const void *memPtr)
+{
+	if (MEM_32bits())
+		return (size_t)MEM_readLE32(memPtr);
+	else
+		return (size_t)MEM_readLE64(memPtr);
+}
+
+MEM_STATIC void MEM_writeLEST(void *memPtr, size_t val)
+{
+	if (MEM_32bits())
+		MEM_writeLE32(memPtr, (U32)val);
+	else
+		MEM_writeLE64(memPtr, (U64)val);
+}
+
+/*=== Big endian r/w ===*/
+
+MEM_STATIC U32 MEM_readBE32(const void *memPtr)
+{
+    return get_unaligned_be32(memPtr);
+}
+
+MEM_STATIC void MEM_writeBE32(void *memPtr, U32 val32)
+{
+    put_unaligned_be32(val32, memPtr);
+}
+
+MEM_STATIC U64 MEM_readBE64(const void *memPtr)
+{
+    return get_unaligned_be64(memPtr);
+}
+
+MEM_STATIC void MEM_writeBE64(void *memPtr, U64 val64)
+{
+    put_unaligned_be64(val64, memPtr);
+}
+
+MEM_STATIC size_t MEM_readBEST(const void *memPtr)
+{
+	if (MEM_32bits())
+		return (size_t)MEM_readBE32(memPtr);
+	else
+		return (size_t)MEM_readBE64(memPtr);
+}
+
+MEM_STATIC void MEM_writeBEST(void *memPtr, size_t val)
+{
+	if (MEM_32bits())
+		MEM_writeBE32(memPtr, (U32)val);
+	else
+		MEM_writeBE64(memPtr, (U64)val);
+}
+
+MEM_STATIC U32 MEM_swap32(U32 in)
+{
+    return swab32(in);
+}
+
+MEM_STATIC U64 MEM_swap64(U64 in)
+{
+    return swab64(in);
+}
+
+MEM_STATIC size_t MEM_swapST(size_t in)
+{
+    if (MEM_32bits())
+        return (size_t)MEM_swap32((U32)in);
+    else
+        return (size_t)MEM_swap64((U64)in);
+}
+
+#endif /* MEM_H_MODULE */
diff --git a/lib/zstd/common/zstd_common.c b/lib/zstd/common/zstd_common.c
new file mode 100644
index 000000000000..3d7e35b309b5
--- /dev/null
+++ b/lib/zstd/common/zstd_common.c
@@ -0,0 +1,83 @@
+/*
+ * Copyright (c) Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+
+
+/*-*************************************
+*  Dependencies
+***************************************/
+#define ZSTD_DEPS_NEED_MALLOC
+#include "zstd_deps.h"   /* ZSTD_malloc, ZSTD_calloc, ZSTD_free, ZSTD_memset */
+#include "error_private.h"
+#include "zstd_internal.h"
+
+
+/*-****************************************
+*  Version
+******************************************/
+unsigned ZSTD_versionNumber(void) { return ZSTD_VERSION_NUMBER; }
+
+const char* ZSTD_versionString(void) { return ZSTD_VERSION_STRING; }
+
+
+/*-****************************************
+*  ZSTD Error Management
+******************************************/
+#undef ZSTD_isError   /* defined within zstd_internal.h */
+/*! ZSTD_isError() :
+ *  tells if a return value is an error code
+ *  symbol is required for external callers */
+unsigned ZSTD_isError(size_t code) { return ERR_isError(code); }
+
+/*! ZSTD_getErrorName() :
+ *  provides error code string from function result (useful for debugging) */
+const char* ZSTD_getErrorName(size_t code) { return ERR_getErrorName(code); }
+
+/*! ZSTD_getError() :
+ *  convert a `size_t` function result into a proper ZSTD_errorCode enum */
+ZSTD_ErrorCode ZSTD_getErrorCode(size_t code) { return ERR_getErrorCode(code); }
+
+/*! ZSTD_getErrorString() :
+ *  provides error code string from enum */
+const char* ZSTD_getErrorString(ZSTD_ErrorCode code) { return ERR_getErrorString(code); }
+
+
+
+/*=**************************************************************
+*  Custom allocator
+****************************************************************/
+void* ZSTD_customMalloc(size_t size, ZSTD_customMem customMem)
+{
+    if (customMem.customAlloc)
+        return customMem.customAlloc(customMem.opaque, size);
+    return ZSTD_malloc(size);
+}
+
+void* ZSTD_customCalloc(size_t size, ZSTD_customMem customMem)
+{
+    if (customMem.customAlloc) {
+        /* calloc implemented as malloc+memset;
+         * not as efficient as calloc, but next best guess for custom malloc */
+        void* const ptr = customMem.customAlloc(customMem.opaque, size);
+        ZSTD_memset(ptr, 0, size);
+        return ptr;
+    }
+    return ZSTD_calloc(1, size);
+}
+
+void ZSTD_customFree(void* ptr, ZSTD_customMem customMem)
+{
+    if (ptr!=NULL) {
+        if (customMem.customFree)
+            customMem.customFree(customMem.opaque, ptr);
+        else
+            ZSTD_free(ptr);
+    }
+}
diff --git a/lib/zstd/common/zstd_deps.h b/lib/zstd/common/zstd_deps.h
new file mode 100644
index 000000000000..7a5bf44839c9
--- /dev/null
+++ b/lib/zstd/common/zstd_deps.h
@@ -0,0 +1,125 @@
+/* SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause */
+/*
+ * Copyright (c) Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+/*
+ * This file provides common libc dependencies that zstd requires.
+ * The purpose is to allow replacing this file with a custom implementation
+ * to compile zstd without libc support.
+ */
+
+/* Need:
+ * NULL
+ * INT_MAX
+ * UINT_MAX
+ * ZSTD_memcpy()
+ * ZSTD_memset()
+ * ZSTD_memmove()
+ */
+#ifndef ZSTD_DEPS_COMMON
+#define ZSTD_DEPS_COMMON
+
+#include <linux/limits.h>
+#include <linux/stddef.h>
+
+#define ZSTD_memcpy(d,s,n) __builtin_memcpy((d),(s),(n))
+#define ZSTD_memmove(d,s,n) __builtin_memmove((d),(s),(n))
+#define ZSTD_memset(d,s,n) __builtin_memset((d),(s),(n))
+
+#endif /* ZSTD_DEPS_COMMON */
+
+/*
+ * Define malloc as always failing. That means the user must
+ * either use ZSTD_customMem or statically allocate memory.
+ * Need:
+ * ZSTD_malloc()
+ * ZSTD_free()
+ * ZSTD_calloc()
+ */
+#ifdef ZSTD_DEPS_NEED_MALLOC
+#ifndef ZSTD_DEPS_MALLOC
+#define ZSTD_DEPS_MALLOC
+
+#define ZSTD_malloc(s) ({ (void)(s); NULL; })
+#define ZSTD_free(p) ((void)(p))
+#define ZSTD_calloc(n,s) ({ (void)(n); (void)(s); NULL; })
+
+#endif /* ZSTD_DEPS_MALLOC */
+#endif /* ZSTD_DEPS_NEED_MALLOC */
+
+/*
+ * Provides 64-bit math support.
+ * Need:
+ * U64 ZSTD_div64(U64 dividend, U32 divisor)
+ */
+#ifdef ZSTD_DEPS_NEED_MATH64
+#ifndef ZSTD_DEPS_MATH64
+#define ZSTD_DEPS_MATH64
+
+#include <linux/math64.h>
+
+static uint64_t ZSTD_div64(uint64_t dividend, uint32_t divisor) {
+  return div_u64(dividend, divisor);
+}
+
+#endif /* ZSTD_DEPS_MATH64 */
+#endif /* ZSTD_DEPS_NEED_MATH64 */
+
+/*
+ * This is only requested when DEBUGLEVEL >= 1, meaning
+ * it is disabled in production.
+ * Need:
+ * assert()
+ */
+#ifdef ZSTD_DEPS_NEED_ASSERT
+#ifndef ZSTD_DEPS_ASSERT
+#define ZSTD_DEPS_ASSERT
+
+#include <linux/kernel.h>
+
+#define assert(x) WARN_ON((x))
+
+#endif /* ZSTD_DEPS_ASSERT */
+#endif /* ZSTD_DEPS_NEED_ASSERT */
+
+/*
+ * This is only requested when DEBUGLEVEL >= 2, meaning
+ * it is disabled in production.
+ * Need:
+ * ZSTD_DEBUG_PRINT()
+ */
+#ifdef ZSTD_DEPS_NEED_IO
+#ifndef ZSTD_DEPS_IO
+#define ZSTD_DEPS_IO
+
+#include <linux/printk.h>
+
+#define ZSTD_DEBUG_PRINT(...) pr_debug(__VA_ARGS__)
+
+#endif /* ZSTD_DEPS_IO */
+#endif /* ZSTD_DEPS_NEED_IO */
+
+/*
+ * Only requested when MSAN is enabled.
+ * Need:
+ * intptr_t
+ */
+#ifdef ZSTD_DEPS_NEED_STDINT
+#ifndef ZSTD_DEPS_STDINT
+#define ZSTD_DEPS_STDINT
+
+/*
+ * The Linux Kernel doesn't provide intptr_t, only uintptr_t, which
+ * is an unsigned long.
+ */
+typedef long intptr_t;
+
+#endif /* ZSTD_DEPS_STDINT */
+#endif /* ZSTD_DEPS_NEED_STDINT */
diff --git a/lib/zstd/common/zstd_internal.h b/lib/zstd/common/zstd_internal.h
new file mode 100644
index 000000000000..fc6f3a9b40c0
--- /dev/null
+++ b/lib/zstd/common/zstd_internal.h
@@ -0,0 +1,450 @@
+/*
+ * Copyright (c) Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+#ifndef ZSTD_CCOMMON_H_MODULE
+#define ZSTD_CCOMMON_H_MODULE
+
+/* this module contains definitions which must be identical
+ * across compression, decompression and dictBuilder.
+ * It also contains a few functions useful to at least 2 of them
+ * and which benefit from being inlined */
+
+/*-*************************************
+*  Dependencies
+***************************************/
+#include "compiler.h"
+#include "mem.h"
+#include "debug.h"                 /* assert, DEBUGLOG, RAWLOG, g_debuglevel */
+#include "error_private.h"
+#define ZSTD_STATIC_LINKING_ONLY
+#include <linux/zstd.h>
+#define FSE_STATIC_LINKING_ONLY
+#include "fse.h"
+#define HUF_STATIC_LINKING_ONLY
+#include "huf.h"
+#include <linux/xxhash.h>                /* XXH_reset, update, digest */
+#define ZSTD_TRACE 0
+
+
+/* ---- static assert (debug) --- */
+#define ZSTD_STATIC_ASSERT(c) DEBUG_STATIC_ASSERT(c)
+#define ZSTD_isError ERR_isError   /* for inlining */
+#define FSE_isError  ERR_isError
+#define HUF_isError  ERR_isError
+
+
+/*-*************************************
+*  shared macros
+***************************************/
+#undef MIN
+#undef MAX
+#define MIN(a,b) ((a)<(b) ? (a) : (b))
+#define MAX(a,b) ((a)>(b) ? (a) : (b))
+
+/*
+ * Ignore: this is an internal helper.
+ *
+ * This is a helper function to help force C99-correctness during compilation.
+ * Under strict compilation modes, variadic macro arguments can't be empty.
+ * However, variadic function arguments can be. Using a function therefore lets
+ * us statically check that at least one (string) argument was passed,
+ * independent of the compilation flags.
+ */
+static INLINE_KEYWORD UNUSED_ATTR
+void _force_has_format_string(const char *format, ...) {
+  (void)format;
+}
+
+/*
+ * Ignore: this is an internal helper.
+ *
+ * We want to force this function invocation to be syntactically correct, but
+ * we don't want to force runtime evaluation of its arguments.
+ */
+#define _FORCE_HAS_FORMAT_STRING(...) \
+  if (0) { \
+    _force_has_format_string(__VA_ARGS__); \
+  }
+
+/*
+ * Return the specified error if the condition evaluates to true.
+ *
+ * In debug modes, prints additional information.
+ * In order to do that (particularly, printing the conditional that failed),
+ * this can't just wrap RETURN_ERROR().
+ */
+#define RETURN_ERROR_IF(cond, err, ...) \
+  if (cond) { \
+    RAWLOG(3, "%s:%d: ERROR!: check %s failed, returning %s", \
+           __FILE__, __LINE__, ZSTD_QUOTE(cond), ZSTD_QUOTE(ERROR(err))); \
+    _FORCE_HAS_FORMAT_STRING(__VA_ARGS__); \
+    RAWLOG(3, ": " __VA_ARGS__); \
+    RAWLOG(3, "\n"); \
+    return ERROR(err); \
+  }
+
+/*
+ * Unconditionally return the specified error.
+ *
+ * In debug modes, prints additional information.
+ */
+#define RETURN_ERROR(err, ...) \
+  do { \
+    RAWLOG(3, "%s:%d: ERROR!: unconditional check failed, returning %s", \
+           __FILE__, __LINE__, ZSTD_QUOTE(ERROR(err))); \
+    _FORCE_HAS_FORMAT_STRING(__VA_ARGS__); \
+    RAWLOG(3, ": " __VA_ARGS__); \
+    RAWLOG(3, "\n"); \
+    return ERROR(err); \
+  } while(0);
+
+/*
+ * If the provided expression evaluates to an error code, returns that error code.
+ *
+ * In debug modes, prints additional information.
+ */
+#define FORWARD_IF_ERROR(err, ...) \
+  do { \
+    size_t const err_code = (err); \
+    if (ERR_isError(err_code)) { \
+      RAWLOG(3, "%s:%d: ERROR!: forwarding error in %s: %s", \
+             __FILE__, __LINE__, ZSTD_QUOTE(err), ERR_getErrorName(err_code)); \
+      _FORCE_HAS_FORMAT_STRING(__VA_ARGS__); \
+      RAWLOG(3, ": " __VA_ARGS__); \
+      RAWLOG(3, "\n"); \
+      return err_code; \
+    } \
+  } while(0);
+
+
+/*-*************************************
+*  Common constants
+***************************************/
+#define ZSTD_OPT_NUM    (1<<12)
+
+#define ZSTD_REP_NUM      3                 /* number of repcodes */
+#define ZSTD_REP_MOVE     (ZSTD_REP_NUM-1)
+static UNUSED_ATTR const U32 repStartValue[ZSTD_REP_NUM] = { 1, 4, 8 };
+
+#define KB *(1 <<10)
+#define MB *(1 <<20)
+#define GB *(1U<<30)
+
+#define BIT7 128
+#define BIT6  64
+#define BIT5  32
+#define BIT4  16
+#define BIT1   2
+#define BIT0   1
+
+#define ZSTD_WINDOWLOG_ABSOLUTEMIN 10
+static UNUSED_ATTR const size_t ZSTD_fcs_fieldSize[4] = { 0, 2, 4, 8 };
+static UNUSED_ATTR const size_t ZSTD_did_fieldSize[4] = { 0, 1, 2, 4 };
+
+#define ZSTD_FRAMEIDSIZE 4   /* magic number size */
+
+#define ZSTD_BLOCKHEADERSIZE 3   /* C standard doesn't allow `static const` variable to be init using another `static const` variable */
+static UNUSED_ATTR const size_t ZSTD_blockHeaderSize = ZSTD_BLOCKHEADERSIZE;
+typedef enum { bt_raw, bt_rle, bt_compressed, bt_reserved } blockType_e;
+
+#define ZSTD_FRAMECHECKSUMSIZE 4
+
+#define MIN_SEQUENCES_SIZE 1 /* nbSeq==0 */
+#define MIN_CBLOCK_SIZE (1 /*litCSize*/ + 1 /* RLE or RAW */ + MIN_SEQUENCES_SIZE /* nbSeq==0 */)   /* for a non-null block */
+
+#define HufLog 12
+typedef enum { set_basic, set_rle, set_compressed, set_repeat } symbolEncodingType_e;
+
+#define LONGNBSEQ 0x7F00
+
+#define MINMATCH 3
+
+#define Litbits  8
+#define MaxLit ((1<<Litbits) - 1)
+#define MaxML   52
+#define MaxLL   35
+#define DefaultMaxOff 28
+#define MaxOff  31
+#define MaxSeq MAX(MaxLL, MaxML)   /* Assumption : MaxOff < MaxLL,MaxML */
+#define MLFSELog    9
+#define LLFSELog    9
+#define OffFSELog   8
+#define MaxFSELog  MAX(MAX(MLFSELog, LLFSELog), OffFSELog)
+
+#define ZSTD_MAX_HUF_HEADER_SIZE 128 /* header + <= 127 byte tree description */
+/* Each table cannot take more than #symbols * FSELog bits */
+#define ZSTD_MAX_FSE_HEADERS_SIZE (((MaxML + 1) * MLFSELog + (MaxLL + 1) * LLFSELog + (MaxOff + 1) * OffFSELog + 7) / 8)
+
+static UNUSED_ATTR const U32 LL_bits[MaxLL+1] = {
+     0, 0, 0, 0, 0, 0, 0, 0,
+     0, 0, 0, 0, 0, 0, 0, 0,
+     1, 1, 1, 1, 2, 2, 3, 3,
+     4, 6, 7, 8, 9,10,11,12,
+    13,14,15,16
+};
+static UNUSED_ATTR const S16 LL_defaultNorm[MaxLL+1] = {
+     4, 3, 2, 2, 2, 2, 2, 2,
+     2, 2, 2, 2, 2, 1, 1, 1,
+     2, 2, 2, 2, 2, 2, 2, 2,
+     2, 3, 2, 1, 1, 1, 1, 1,
+    -1,-1,-1,-1
+};
+#define LL_DEFAULTNORMLOG 6  /* for static allocation */
+static UNUSED_ATTR const U32 LL_defaultNormLog = LL_DEFAULTNORMLOG;
+
+static UNUSED_ATTR const U32 ML_bits[MaxML+1] = {
+     0, 0, 0, 0, 0, 0, 0, 0,
+     0, 0, 0, 0, 0, 0, 0, 0,
+     0, 0, 0, 0, 0, 0, 0, 0,
+     0, 0, 0, 0, 0, 0, 0, 0,
+     1, 1, 1, 1, 2, 2, 3, 3,
+     4, 4, 5, 7, 8, 9,10,11,
+    12,13,14,15,16
+};
+static UNUSED_ATTR const S16 ML_defaultNorm[MaxML+1] = {
+     1, 4, 3, 2, 2, 2, 2, 2,
+     2, 1, 1, 1, 1, 1, 1, 1,
+     1, 1, 1, 1, 1, 1, 1, 1,
+     1, 1, 1, 1, 1, 1, 1, 1,
+     1, 1, 1, 1, 1, 1, 1, 1,
+     1, 1, 1, 1, 1, 1,-1,-1,
+    -1,-1,-1,-1,-1
+};
+#define ML_DEFAULTNORMLOG 6  /* for static allocation */
+static UNUSED_ATTR const U32 ML_defaultNormLog = ML_DEFAULTNORMLOG;
+
+static UNUSED_ATTR const S16 OF_defaultNorm[DefaultMaxOff+1] = {
+     1, 1, 1, 1, 1, 1, 2, 2,
+     2, 1, 1, 1, 1, 1, 1, 1,
+     1, 1, 1, 1, 1, 1, 1, 1,
+    -1,-1,-1,-1,-1
+};
+#define OF_DEFAULTNORMLOG 5  /* for static allocation */
+static UNUSED_ATTR const U32 OF_defaultNormLog = OF_DEFAULTNORMLOG;
+
+
+/*-*******************************************
+*  Shared functions to include for inlining
+*********************************************/
+static void ZSTD_copy8(void* dst, const void* src) {
+    ZSTD_memcpy(dst, src, 8);
+}
+
+#define COPY8(d,s) { ZSTD_copy8(d,s); d+=8; s+=8; }
+static void ZSTD_copy16(void* dst, const void* src) {
+    ZSTD_memcpy(dst, src, 16);
+}
+#define COPY16(d,s) { ZSTD_copy16(d,s); d+=16; s+=16; }
+
+#define WILDCOPY_OVERLENGTH 32
+#define WILDCOPY_VECLEN 16
+
+typedef enum {
+    ZSTD_no_overlap,
+    ZSTD_overlap_src_before_dst
+    /*  ZSTD_overlap_dst_before_src, */
+} ZSTD_overlap_e;
+
+/*! ZSTD_wildcopy() :
+ *  Custom version of ZSTD_memcpy(), can over read/write up to WILDCOPY_OVERLENGTH bytes (if length==0)
+ *  @param ovtype controls the overlap detection
+ *         - ZSTD_no_overlap: The source and destination are guaranteed to be at least WILDCOPY_VECLEN bytes apart.
+ *         - ZSTD_overlap_src_before_dst: The src and dst may overlap, but they MUST be at least 8 bytes apart.
+ *           The src buffer must be before the dst buffer.
+ */
+MEM_STATIC FORCE_INLINE_ATTR
+void ZSTD_wildcopy(void* dst, const void* src, ptrdiff_t length, ZSTD_overlap_e const ovtype)
+{
+    ptrdiff_t diff = (BYTE*)dst - (const BYTE*)src;
+    const BYTE* ip = (const BYTE*)src;
+    BYTE* op = (BYTE*)dst;
+    BYTE* const oend = op + length;
+
+    assert(diff >= 8 || (ovtype == ZSTD_no_overlap && diff <= -WILDCOPY_VECLEN));
+
+    if (ovtype == ZSTD_overlap_src_before_dst && diff < WILDCOPY_VECLEN) {
+        /* Handle short offset copies. */
+        do {
+            COPY8(op, ip)
+        } while (op < oend);
+    } else {
+        assert(diff >= WILDCOPY_VECLEN || diff <= -WILDCOPY_VECLEN);
+        /* Separate out the first COPY16() call because the copy length is
+         * almost certain to be short, so the branches have different
+         * probabilities. Since it is almost certain to be short, only do
+         * one COPY16() in the first call. Then, do two calls per loop since
+         * at that point it is more likely to have a high trip count.
+         */
+#ifdef __aarch64__
+        do {
+            COPY16(op, ip);
+        }
+        while (op < oend);
+#else
+        ZSTD_copy16(op, ip);
+        if (16 >= length) return;
+        op += 16;
+        ip += 16;
+        do {
+            COPY16(op, ip);
+            COPY16(op, ip);
+        }
+        while (op < oend);
+#endif
+    }
+}
+
+MEM_STATIC size_t ZSTD_limitCopy(void* dst, size_t dstCapacity, const void* src, size_t srcSize)
+{
+    size_t const length = MIN(dstCapacity, srcSize);
+    if (length > 0) {
+        ZSTD_memcpy(dst, src, length);
+    }
+    return length;
+}
+
+/* define "workspace is too large" as this number of times larger than needed */
+#define ZSTD_WORKSPACETOOLARGE_FACTOR 3
+
+/* when workspace is continuously too large
+ * during at least this number of times,
+ * context's memory usage is considered wasteful,
+ * because it's sized to handle a worst case scenario which rarely happens.
+ * In which case, resize it down to free some memory */
+#define ZSTD_WORKSPACETOOLARGE_MAXDURATION 128
+
+/* Controls whether the input/output buffer is buffered or stable. */
+typedef enum {
+    ZSTD_bm_buffered = 0,  /* Buffer the input/output */
+    ZSTD_bm_stable = 1     /* ZSTD_inBuffer/ZSTD_outBuffer is stable */
+} ZSTD_bufferMode_e;
+
+
+/*-*******************************************
+*  Private declarations
+*********************************************/
+typedef struct seqDef_s {
+    U32 offset;         /* Offset code of the sequence */
+    U16 litLength;
+    U16 matchLength;
+} seqDef;
+
+typedef struct {
+    seqDef* sequencesStart;
+    seqDef* sequences;      /* ptr to end of sequences */
+    BYTE* litStart;
+    BYTE* lit;              /* ptr to end of literals */
+    BYTE* llCode;
+    BYTE* mlCode;
+    BYTE* ofCode;
+    size_t maxNbSeq;
+    size_t maxNbLit;
+
+    /* longLengthPos and longLengthID to allow us to represent either a single litLength or matchLength
+     * in the seqStore that has a value larger than U16 (if it exists). To do so, we increment
+     * the existing value of the litLength or matchLength by 0x10000.
+     */
+    U32   longLengthID;   /* 0 == no longLength; 1 == Represent the long literal; 2 == Represent the long match; */
+    U32   longLengthPos;  /* Index of the sequence to apply long length modification to */
+} seqStore_t;
+
+typedef struct {
+    U32 litLength;
+    U32 matchLength;
+} ZSTD_sequenceLength;
+
+/*
+ * Returns the ZSTD_sequenceLength for the given sequences. It handles the decoding of long sequences
+ * indicated by longLengthPos and longLengthID, and adds MINMATCH back to matchLength.
+ */
+MEM_STATIC ZSTD_sequenceLength ZSTD_getSequenceLength(seqStore_t const* seqStore, seqDef const* seq)
+{
+    ZSTD_sequenceLength seqLen;
+    seqLen.litLength = seq->litLength;
+    seqLen.matchLength = seq->matchLength + MINMATCH;
+    if (seqStore->longLengthPos == (U32)(seq - seqStore->sequencesStart)) {
+        if (seqStore->longLengthID == 1) {
+            seqLen.litLength += 0xFFFF;
+        }
+        if (seqStore->longLengthID == 2) {
+            seqLen.matchLength += 0xFFFF;
+        }
+    }
+    return seqLen;
+}
+
+/*
+ * Contains the compressed frame size and an upper-bound for the decompressed frame size.
+ * Note: before using `compressedSize`, check for errors using ZSTD_isError().
+ *       similarly, before using `decompressedBound`, check for errors using:
+ *          `decompressedBound != ZSTD_CONTENTSIZE_ERROR`
+ */
+typedef struct {
+    size_t compressedSize;
+    unsigned long long decompressedBound;
+} ZSTD_frameSizeInfo;   /* decompress & legacy */
+
+const seqStore_t* ZSTD_getSeqStore(const ZSTD_CCtx* ctx);   /* compress & dictBuilder */
+void ZSTD_seqToCodes(const seqStore_t* seqStorePtr);   /* compress, dictBuilder, decodeCorpus (shouldn't get its definition from here) */
+
+/* custom memory allocation functions */
+void* ZSTD_customMalloc(size_t size, ZSTD_customMem customMem);
+void* ZSTD_customCalloc(size_t size, ZSTD_customMem customMem);
+void ZSTD_customFree(void* ptr, ZSTD_customMem customMem);
+
+
+MEM_STATIC U32 ZSTD_highbit32(U32 val)   /* compress, dictBuilder, decodeCorpus */
+{
+    assert(val != 0);
+    {
+#   if (__GNUC__ >= 3)   /* GCC Intrinsic */
+        return __builtin_clz (val) ^ 31;
+#   else   /* Software version */
+        static const U32 DeBruijnClz[32] = { 0, 9, 1, 10, 13, 21, 2, 29, 11, 14, 16, 18, 22, 25, 3, 30, 8, 12, 20, 28, 15, 17, 24, 7, 19, 27, 23, 6, 26, 5, 4, 31 };
+        U32 v = val;
+        v |= v >> 1;
+        v |= v >> 2;
+        v |= v >> 4;
+        v |= v >> 8;
+        v |= v >> 16;
+        return DeBruijnClz[(v * 0x07C4ACDDU) >> 27];
+#   endif
+    }
+}
+
+
+/* ZSTD_invalidateRepCodes() :
+ * ensures next compression will not use repcodes from previous block.
+ * Note : only works with regular variant;
+ *        do not use with extDict variant ! */
+void ZSTD_invalidateRepCodes(ZSTD_CCtx* cctx);   /* zstdmt, adaptive_compression (shouldn't get this definition from here) */
+
+
+typedef struct {
+    blockType_e blockType;
+    U32 lastBlock;
+    U32 origSize;
+} blockProperties_t;   /* declared here for decompress and fullbench */
+
+/*! ZSTD_getcBlockSize() :
+ *  Provides the size of compressed block from block header `src` */
+/* Used by: decompress, fullbench (does not get its definition from here) */
+size_t ZSTD_getcBlockSize(const void* src, size_t srcSize,
+                          blockProperties_t* bpPtr);
+
+/*! ZSTD_decodeSeqHeaders() :
+ *  decode sequence header from src */
+/* Used by: decompress, fullbench (does not get its definition from here) */
+size_t ZSTD_decodeSeqHeaders(ZSTD_DCtx* dctx, int* nbSeqPtr,
+                       const void* src, size_t srcSize);
+
+
+
+#endif   /* ZSTD_CCOMMON_H_MODULE */
diff --git a/lib/zstd/compress.c b/lib/zstd/compress.c
deleted file mode 100644
index b080264ed3ad..000000000000
--- a/lib/zstd/compress.c
+++ /dev/null
@@ -1,3485 +0,0 @@
-/**
- * Copyright (c) 2016-present, Yann Collet, Facebook, Inc.
- * All rights reserved.
- *
- * This source code is licensed under the BSD-style license found in the
- * LICENSE file in the root directory of https://github.com/facebook/zstd.
- * An additional grant of patent rights can be found in the PATENTS file in the
- * same directory.
- *
- * 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. This program is dual-licensed; you may select
- * either version 2 of the GNU General Public License ("GPL") or BSD license
- * ("BSD").
- */
-
-/*-*************************************
-*  Dependencies
-***************************************/
-#include "fse.h"
-#include "huf.h"
-#include "mem.h"
-#include "zstd_internal.h" /* includes zstd.h */
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/string.h> /* memset */
-
-/*-*************************************
-*  Constants
-***************************************/
-static const U32 g_searchStrength = 8; /* control skip over incompressible data */
-#define HASH_READ_SIZE 8
-typedef enum { ZSTDcs_created = 0, ZSTDcs_init, ZSTDcs_ongoing, ZSTDcs_ending } ZSTD_compressionStage_e;
-
-/*-*************************************
-*  Helper functions
-***************************************/
-size_t ZSTD_compressBound(size_t srcSize) { return FSE_compressBound(srcSize) + 12; }
-
-/*-*************************************
-*  Sequence storage
-***************************************/
-static void ZSTD_resetSeqStore(seqStore_t *ssPtr)
-{
-	ssPtr->lit = ssPtr->litStart;
-	ssPtr->sequences = ssPtr->sequencesStart;
-	ssPtr->longLengthID = 0;
-}
-
-/*-*************************************
-*  Context memory management
-***************************************/
-struct ZSTD_CCtx_s {
-	const BYTE *nextSrc;  /* next block here to continue on curr prefix */
-	const BYTE *base;     /* All regular indexes relative to this position */
-	const BYTE *dictBase; /* extDict indexes relative to this position */
-	U32 dictLimit;	/* below that point, need extDict */
-	U32 lowLimit;	 /* below that point, no more data */
-	U32 nextToUpdate;     /* index from which to continue dictionary update */
-	U32 nextToUpdate3;    /* index from which to continue dictionary update */
-	U32 hashLog3;	 /* dispatch table : larger == faster, more memory */
-	U32 loadedDictEnd;    /* index of end of dictionary */
-	U32 forceWindow;      /* force back-references to respect limit of 1<<wLog, even for dictionary */
-	U32 forceRawDict;     /* Force loading dictionary in "content-only" mode (no header analysis) */
-	ZSTD_compressionStage_e stage;
-	U32 rep[ZSTD_REP_NUM];
-	U32 repToConfirm[ZSTD_REP_NUM];
-	U32 dictID;
-	ZSTD_parameters params;
-	void *workSpace;
-	size_t workSpaceSize;
-	size_t blockSize;
-	U64 frameContentSize;
-	struct xxh64_state xxhState;
-	ZSTD_customMem customMem;
-
-	seqStore_t seqStore; /* sequences storage ptrs */
-	U32 *hashTable;
-	U32 *hashTable3;
-	U32 *chainTable;
-	HUF_CElt *hufTable;
-	U32 flagStaticTables;
-	HUF_repeat flagStaticHufTable;
-	FSE_CTable offcodeCTable[FSE_CTABLE_SIZE_U32(OffFSELog, MaxOff)];
-	FSE_CTable matchlengthCTable[FSE_CTABLE_SIZE_U32(MLFSELog, MaxML)];
-	FSE_CTable litlengthCTable[FSE_CTABLE_SIZE_U32(LLFSELog, MaxLL)];
-	unsigned tmpCounters[HUF_COMPRESS_WORKSPACE_SIZE_U32];
-};
-
-size_t ZSTD_CCtxWorkspaceBound(ZSTD_compressionParameters cParams)
-{
-	size_t const blockSize = MIN(ZSTD_BLOCKSIZE_ABSOLUTEMAX, (size_t)1 << cParams.windowLog);
-	U32 const divider = (cParams.searchLength == 3) ? 3 : 4;
-	size_t const maxNbSeq = blockSize / divider;
-	size_t const tokenSpace = blockSize + 11 * maxNbSeq;
-	size_t const chainSize = (cParams.strategy == ZSTD_fast) ? 0 : (1 << cParams.chainLog);
-	size_t const hSize = ((size_t)1) << cParams.hashLog;
-	U32 const hashLog3 = (cParams.searchLength > 3) ? 0 : MIN(ZSTD_HASHLOG3_MAX, cParams.windowLog);
-	size_t const h3Size = ((size_t)1) << hashLog3;
-	size_t const tableSpace = (chainSize + hSize + h3Size) * sizeof(U32);
-	size_t const optSpace =
-	    ((MaxML + 1) + (MaxLL + 1) + (MaxOff + 1) + (1 << Litbits)) * sizeof(U32) + (ZSTD_OPT_NUM + 1) * (sizeof(ZSTD_match_t) + sizeof(ZSTD_optimal_t));
-	size_t const workspaceSize = tableSpace + (256 * sizeof(U32)) /* huffTable */ + tokenSpace +
-				     (((cParams.strategy == ZSTD_btopt) || (cParams.strategy == ZSTD_btopt2)) ? optSpace : 0);
-
-	return ZSTD_ALIGN(sizeof(ZSTD_stack)) + ZSTD_ALIGN(sizeof(ZSTD_CCtx)) + ZSTD_ALIGN(workspaceSize);
-}
-
-static ZSTD_CCtx *ZSTD_createCCtx_advanced(ZSTD_customMem customMem)
-{
-	ZSTD_CCtx *cctx;
-	if (!customMem.customAlloc || !customMem.customFree)
-		return NULL;
-	cctx = (ZSTD_CCtx *)ZSTD_malloc(sizeof(ZSTD_CCtx), customMem);
-	if (!cctx)
-		return NULL;
-	memset(cctx, 0, sizeof(ZSTD_CCtx));
-	cctx->customMem = customMem;
-	return cctx;
-}
-
-ZSTD_CCtx *ZSTD_initCCtx(void *workspace, size_t workspaceSize)
-{
-	ZSTD_customMem const stackMem = ZSTD_initStack(workspace, workspaceSize);
-	ZSTD_CCtx *cctx = ZSTD_createCCtx_advanced(stackMem);
-	if (cctx) {
-		cctx->workSpace = ZSTD_stackAllocAll(cctx->customMem.opaque, &cctx->workSpaceSize);
-	}
-	return cctx;
-}
-
-size_t ZSTD_freeCCtx(ZSTD_CCtx *cctx)
-{
-	if (cctx == NULL)
-		return 0; /* support free on NULL */
-	ZSTD_free(cctx->workSpace, cctx->customMem);
-	ZSTD_free(cctx, cctx->customMem);
-	return 0; /* reserved as a potential error code in the future */
-}
-
-const seqStore_t *ZSTD_getSeqStore(const ZSTD_CCtx *ctx) /* hidden interface */ { return &(ctx->seqStore); }
-
-static ZSTD_parameters ZSTD_getParamsFromCCtx(const ZSTD_CCtx *cctx) { return cctx->params; }
-
-/** ZSTD_checkParams() :
-	ensure param values remain within authorized range.
-	@return : 0, or an error code if one value is beyond authorized range */
-size_t ZSTD_checkCParams(ZSTD_compressionParameters cParams)
-{
-#define CLAMPCHECK(val, min, max)                                       \
-	{                                                               \
-		if ((val < min) | (val > max))                          \
-			return ERROR(compressionParameter_unsupported); \
-	}
-	CLAMPCHECK(cParams.windowLog, ZSTD_WINDOWLOG_MIN, ZSTD_WINDOWLOG_MAX);
-	CLAMPCHECK(cParams.chainLog, ZSTD_CHAINLOG_MIN, ZSTD_CHAINLOG_MAX);
-	CLAMPCHECK(cParams.hashLog, ZSTD_HASHLOG_MIN, ZSTD_HASHLOG_MAX);
-	CLAMPCHECK(cParams.searchLog, ZSTD_SEARCHLOG_MIN, ZSTD_SEARCHLOG_MAX);
-	CLAMPCHECK(cParams.searchLength, ZSTD_SEARCHLENGTH_MIN, ZSTD_SEARCHLENGTH_MAX);
-	CLAMPCHECK(cParams.targetLength, ZSTD_TARGETLENGTH_MIN, ZSTD_TARGETLENGTH_MAX);
-	if ((U32)(cParams.strategy) > (U32)ZSTD_btopt2)
-		return ERROR(compressionParameter_unsupported);
-	return 0;
-}
-
-/** ZSTD_cycleLog() :
- *  condition for correct operation : hashLog > 1 */
-static U32 ZSTD_cycleLog(U32 hashLog, ZSTD_strategy strat)
-{
-	U32 const btScale = ((U32)strat >= (U32)ZSTD_btlazy2);
-	return hashLog - btScale;
-}
-
-/** ZSTD_adjustCParams() :
-	optimize `cPar` for a given input (`srcSize` and `dictSize`).
-	mostly downsizing to reduce memory consumption and initialization.
-	Both `srcSize` and `dictSize` are optional (use 0 if unknown),
-	but if both are 0, no optimization can be done.
-	Note : cPar is considered validated at this stage. Use ZSTD_checkParams() to ensure that. */
-ZSTD_compressionParameters ZSTD_adjustCParams(ZSTD_compressionParameters cPar, unsigned long long srcSize, size_t dictSize)
-{
-	if (srcSize + dictSize == 0)
-		return cPar; /* no size information available : no adjustment */
-
-	/* resize params, to use less memory when necessary */
-	{
-		U32 const minSrcSize = (srcSize == 0) ? 500 : 0;
-		U64 const rSize = srcSize + dictSize + minSrcSize;
-		if (rSize < ((U64)1 << ZSTD_WINDOWLOG_MAX)) {
-			U32 const srcLog = MAX(ZSTD_HASHLOG_MIN, ZSTD_highbit32((U32)(rSize)-1) + 1);
-			if (cPar.windowLog > srcLog)
-				cPar.windowLog = srcLog;
-		}
-	}
-	if (cPar.hashLog > cPar.windowLog)
-		cPar.hashLog = cPar.windowLog;
-	{
-		U32 const cycleLog = ZSTD_cycleLog(cPar.chainLog, cPar.strategy);
-		if (cycleLog > cPar.windowLog)
-			cPar.chainLog -= (cycleLog - cPar.windowLog);
-	}
-
-	if (cPar.windowLog < ZSTD_WINDOWLOG_ABSOLUTEMIN)
-		cPar.windowLog = ZSTD_WINDOWLOG_ABSOLUTEMIN; /* required for frame header */
-
-	return cPar;
-}
-
-static U32 ZSTD_equivalentParams(ZSTD_parameters param1, ZSTD_parameters param2)
-{
-	return (param1.cParams.hashLog == param2.cParams.hashLog) & (param1.cParams.chainLog == param2.cParams.chainLog) &
-	       (param1.cParams.strategy == param2.cParams.strategy) & ((param1.cParams.searchLength == 3) == (param2.cParams.searchLength == 3));
-}
-
-/*! ZSTD_continueCCtx() :
-	reuse CCtx without reset (note : requires no dictionary) */
-static size_t ZSTD_continueCCtx(ZSTD_CCtx *cctx, ZSTD_parameters params, U64 frameContentSize)
-{
-	U32 const end = (U32)(cctx->nextSrc - cctx->base);
-	cctx->params = params;
-	cctx->frameContentSize = frameContentSize;
-	cctx->lowLimit = end;
-	cctx->dictLimit = end;
-	cctx->nextToUpdate = end + 1;
-	cctx->stage = ZSTDcs_init;
-	cctx->dictID = 0;
-	cctx->loadedDictEnd = 0;
-	{
-		int i;
-		for (i = 0; i < ZSTD_REP_NUM; i++)
-			cctx->rep[i] = repStartValue[i];
-	}
-	cctx->seqStore.litLengthSum = 0; /* force reset of btopt stats */
-	xxh64_reset(&cctx->xxhState, 0);
-	return 0;
-}
-
-typedef enum { ZSTDcrp_continue, ZSTDcrp_noMemset, ZSTDcrp_fullReset } ZSTD_compResetPolicy_e;
-
-/*! ZSTD_resetCCtx_advanced() :
-	note : `params` must be validated */
-static size_t ZSTD_resetCCtx_advanced(ZSTD_CCtx *zc, ZSTD_parameters params, U64 frameContentSize, ZSTD_compResetPolicy_e const crp)
-{
-	if (crp == ZSTDcrp_continue)
-		if (ZSTD_equivalentParams(params, zc->params)) {
-			zc->flagStaticTables = 0;
-			zc->flagStaticHufTable = HUF_repeat_none;
-			return ZSTD_continueCCtx(zc, params, frameContentSize);
-		}
-
-	{
-		size_t const blockSize = MIN(ZSTD_BLOCKSIZE_ABSOLUTEMAX, (size_t)1 << params.cParams.windowLog);
-		U32 const divider = (params.cParams.searchLength == 3) ? 3 : 4;
-		size_t const maxNbSeq = blockSize / divider;
-		size_t const tokenSpace = blockSize + 11 * maxNbSeq;
-		size_t const chainSize = (params.cParams.strategy == ZSTD_fast) ? 0 : (1 << params.cParams.chainLog);
-		size_t const hSize = ((size_t)1) << params.cParams.hashLog;
-		U32 const hashLog3 = (params.cParams.searchLength > 3) ? 0 : MIN(ZSTD_HASHLOG3_MAX, params.cParams.windowLog);
-		size_t const h3Size = ((size_t)1) << hashLog3;
-		size_t const tableSpace = (chainSize + hSize + h3Size) * sizeof(U32);
-		void *ptr;
-
-		/* Check if workSpace is large enough, alloc a new one if needed */
-		{
-			size_t const optSpace = ((MaxML + 1) + (MaxLL + 1) + (MaxOff + 1) + (1 << Litbits)) * sizeof(U32) +
-						(ZSTD_OPT_NUM + 1) * (sizeof(ZSTD_match_t) + sizeof(ZSTD_optimal_t));
-			size_t const neededSpace = tableSpace + (256 * sizeof(U32)) /* huffTable */ + tokenSpace +
-						   (((params.cParams.strategy == ZSTD_btopt) || (params.cParams.strategy == ZSTD_btopt2)) ? optSpace : 0);
-			if (zc->workSpaceSize < neededSpace) {
-				ZSTD_free(zc->workSpace, zc->customMem);
-				zc->workSpace = ZSTD_malloc(neededSpace, zc->customMem);
-				if (zc->workSpace == NULL)
-					return ERROR(memory_allocation);
-				zc->workSpaceSize = neededSpace;
-			}
-		}
-
-		if (crp != ZSTDcrp_noMemset)
-			memset(zc->workSpace, 0, tableSpace); /* reset tables only */
-		xxh64_reset(&zc->xxhState, 0);
-		zc->hashLog3 = hashLog3;
-		zc->hashTable = (U32 *)(zc->workSpace);
-		zc->chainTable = zc->hashTable + hSize;
-		zc->hashTable3 = zc->chainTable + chainSize;
-		ptr = zc->hashTable3 + h3Size;
-		zc->hufTable = (HUF_CElt *)ptr;
-		zc->flagStaticTables = 0;
-		zc->flagStaticHufTable = HUF_repeat_none;
-		ptr = ((U32 *)ptr) + 256; /* note : HUF_CElt* is incomplete type, size is simulated using U32 */
-
-		zc->nextToUpdate = 1;
-		zc->nextSrc = NULL;
-		zc->base = NULL;
-		zc->dictBase = NULL;
-		zc->dictLimit = 0;
-		zc->lowLimit = 0;
-		zc->params = params;
-		zc->blockSize = blockSize;
-		zc->frameContentSize = frameContentSize;
-		{
-			int i;
-			for (i = 0; i < ZSTD_REP_NUM; i++)
-				zc->rep[i] = repStartValue[i];
-		}
-
-		if ((params.cParams.strategy == ZSTD_btopt) || (params.cParams.strategy == ZSTD_btopt2)) {
-			zc->seqStore.litFreq = (U32 *)ptr;
-			zc->seqStore.litLengthFreq = zc->seqStore.litFreq + (1 << Litbits);
-			zc->seqStore.matchLengthFreq = zc->seqStore.litLengthFreq + (MaxLL + 1);
-			zc->seqStore.offCodeFreq = zc->seqStore.matchLengthFreq + (MaxML + 1);
-			ptr = zc->seqStore.offCodeFreq + (MaxOff + 1);
-			zc->seqStore.matchTable = (ZSTD_match_t *)ptr;
-			ptr = zc->seqStore.matchTable + ZSTD_OPT_NUM + 1;
-			zc->seqStore.priceTable = (ZSTD_optimal_t *)ptr;
-			ptr = zc->seqStore.priceTable + ZSTD_OPT_NUM + 1;
-			zc->seqStore.litLengthSum = 0;
-		}
-		zc->seqStore.sequencesStart = (seqDef *)ptr;
-		ptr = zc->seqStore.sequencesStart + maxNbSeq;
-		zc->seqStore.llCode = (BYTE *)ptr;
-		zc->seqStore.mlCode = zc->seqStore.llCode + maxNbSeq;
-		zc->seqStore.ofCode = zc->seqStore.mlCode + maxNbSeq;
-		zc->seqStore.litStart = zc->seqStore.ofCode + maxNbSeq;
-
-		zc->stage = ZSTDcs_init;
-		zc->dictID = 0;
-		zc->loadedDictEnd = 0;
-
-		return 0;
-	}
-}
-
-/* ZSTD_invalidateRepCodes() :
- * ensures next compression will not use repcodes from previous block.
- * Note : only works with regular variant;
- *        do not use with extDict variant ! */
-void ZSTD_invalidateRepCodes(ZSTD_CCtx *cctx)
-{
-	int i;
-	for (i = 0; i < ZSTD_REP_NUM; i++)
-		cctx->rep[i] = 0;
-}
-
-/*! ZSTD_copyCCtx() :
-*   Duplicate an existing context `srcCCtx` into another one `dstCCtx`.
-*   Only works during stage ZSTDcs_init (i.e. after creation, but before first call to ZSTD_compressContinue()).
-*   @return : 0, or an error code */
-size_t ZSTD_copyCCtx(ZSTD_CCtx *dstCCtx, const ZSTD_CCtx *srcCCtx, unsigned long long pledgedSrcSize)
-{
-	if (srcCCtx->stage != ZSTDcs_init)
-		return ERROR(stage_wrong);
-
-	memcpy(&dstCCtx->customMem, &srcCCtx->customMem, sizeof(ZSTD_customMem));
-	{
-		ZSTD_parameters params = srcCCtx->params;
-		params.fParams.contentSizeFlag = (pledgedSrcSize > 0);
-		ZSTD_resetCCtx_advanced(dstCCtx, params, pledgedSrcSize, ZSTDcrp_noMemset);
-	}
-
-	/* copy tables */
-	{
-		size_t const chainSize = (srcCCtx->params.cParams.strategy == ZSTD_fast) ? 0 : (1 << srcCCtx->params.cParams.chainLog);
-		size_t const hSize = ((size_t)1) << srcCCtx->params.cParams.hashLog;
-		size_t const h3Size = (size_t)1 << srcCCtx->hashLog3;
-		size_t const tableSpace = (chainSize + hSize + h3Size) * sizeof(U32);
-		memcpy(dstCCtx->workSpace, srcCCtx->workSpace, tableSpace);
-	}
-
-	/* copy dictionary offsets */
-	dstCCtx->nextToUpdate = srcCCtx->nextToUpdate;
-	dstCCtx->nextToUpdate3 = srcCCtx->nextToUpdate3;
-	dstCCtx->nextSrc = srcCCtx->nextSrc;
-	dstCCtx->base = srcCCtx->base;
-	dstCCtx->dictBase = srcCCtx->dictBase;
-	dstCCtx->dictLimit = srcCCtx->dictLimit;
-	dstCCtx->lowLimit = srcCCtx->lowLimit;
-	dstCCtx->loadedDictEnd = srcCCtx->loadedDictEnd;
-	dstCCtx->dictID = srcCCtx->dictID;
-
-	/* copy entropy tables */
-	dstCCtx->flagStaticTables = srcCCtx->flagStaticTables;
-	dstCCtx->flagStaticHufTable = srcCCtx->flagStaticHufTable;
-	if (srcCCtx->flagStaticTables) {
-		memcpy(dstCCtx->litlengthCTable, srcCCtx->litlengthCTable, sizeof(dstCCtx->litlengthCTable));
-		memcpy(dstCCtx->matchlengthCTable, srcCCtx->matchlengthCTable, sizeof(dstCCtx->matchlengthCTable));
-		memcpy(dstCCtx->offcodeCTable, srcCCtx->offcodeCTable, sizeof(dstCCtx->offcodeCTable));
-	}
-	if (srcCCtx->flagStaticHufTable) {
-		memcpy(dstCCtx->hufTable, srcCCtx->hufTable, 256 * 4);
-	}
-
-	return 0;
-}
-
-/*! ZSTD_reduceTable() :
-*   reduce table indexes by `reducerValue` */
-static void ZSTD_reduceTable(U32 *const table, U32 const size, U32 const reducerValue)
-{
-	U32 u;
-	for (u = 0; u < size; u++) {
-		if (table[u] < reducerValue)
-			table[u] = 0;
-		else
-			table[u] -= reducerValue;
-	}
-}
-
-/*! ZSTD_reduceIndex() :
-*   rescale all indexes to avoid future overflow (indexes are U32) */
-static void ZSTD_reduceIndex(ZSTD_CCtx *zc, const U32 reducerValue)
-{
-	{
-		U32 const hSize = 1 << zc->params.cParams.hashLog;
-		ZSTD_reduceTable(zc->hashTable, hSize, reducerValue);
-	}
-
-	{
-		U32 const chainSize = (zc->params.cParams.strategy == ZSTD_fast) ? 0 : (1 << zc->params.cParams.chainLog);
-		ZSTD_reduceTable(zc->chainTable, chainSize, reducerValue);
-	}
-
-	{
-		U32 const h3Size = (zc->hashLog3) ? 1 << zc->hashLog3 : 0;
-		ZSTD_reduceTable(zc->hashTable3, h3Size, reducerValue);
-	}
-}
-
-/*-*******************************************************
-*  Block entropic compression
-*********************************************************/
-
-/* See doc/zstd_compression_format.md for detailed format description */
-
-size_t ZSTD_noCompressBlock(void *dst, size_t dstCapacity, const void *src, size_t srcSize)
-{
-	if (srcSize + ZSTD_blockHeaderSize > dstCapacity)
-		return ERROR(dstSize_tooSmall);
-	memcpy((BYTE *)dst + ZSTD_blockHeaderSize, src, srcSize);
-	ZSTD_writeLE24(dst, (U32)(srcSize << 2) + (U32)bt_raw);
-	return ZSTD_blockHeaderSize + srcSize;
-}
-
-static size_t ZSTD_noCompressLiterals(void *dst, size_t dstCapacity, const void *src, size_t srcSize)
-{
-	BYTE *const ostart = (BYTE * const)dst;
-	U32 const flSize = 1 + (srcSize > 31) + (srcSize > 4095);
-
-	if (srcSize + flSize > dstCapacity)
-		return ERROR(dstSize_tooSmall);
-
-	switch (flSize) {
-	case 1: /* 2 - 1 - 5 */ ostart[0] = (BYTE)((U32)set_basic + (srcSize << 3)); break;
-	case 2: /* 2 - 2 - 12 */ ZSTD_writeLE16(ostart, (U16)((U32)set_basic + (1 << 2) + (srcSize << 4))); break;
-	default: /*note : should not be necessary : flSize is within {1,2,3} */
-	case 3: /* 2 - 2 - 20 */ ZSTD_writeLE32(ostart, (U32)((U32)set_basic + (3 << 2) + (srcSize << 4))); break;
-	}
-
-	memcpy(ostart + flSize, src, srcSize);
-	return srcSize + flSize;
-}
-
-static size_t ZSTD_compressRleLiteralsBlock(void *dst, size_t dstCapacity, const void *src, size_t srcSize)
-{
-	BYTE *const ostart = (BYTE * const)dst;
-	U32 const flSize = 1 + (srcSize > 31) + (srcSize > 4095);
-
-	(void)dstCapacity; /* dstCapacity already guaranteed to be >=4, hence large enough */
-
-	switch (flSize) {
-	case 1: /* 2 - 1 - 5 */ ostart[0] = (BYTE)((U32)set_rle + (srcSize << 3)); break;
-	case 2: /* 2 - 2 - 12 */ ZSTD_writeLE16(ostart, (U16)((U32)set_rle + (1 << 2) + (srcSize << 4))); break;
-	default: /*note : should not be necessary : flSize is necessarily within {1,2,3} */
-	case 3: /* 2 - 2 - 20 */ ZSTD_writeLE32(ostart, (U32)((U32)set_rle + (3 << 2) + (srcSize << 4))); break;
-	}
-
-	ostart[flSize] = *(const BYTE *)src;
-	return flSize + 1;
-}
-
-static size_t ZSTD_minGain(size_t srcSize) { return (srcSize >> 6) + 2; }
-
-static size_t ZSTD_compressLiterals(ZSTD_CCtx *zc, void *dst, size_t dstCapacity, const void *src, size_t srcSize)
-{
-	size_t const minGain = ZSTD_minGain(srcSize);
-	size_t const lhSize = 3 + (srcSize >= 1 KB) + (srcSize >= 16 KB);
-	BYTE *const ostart = (BYTE *)dst;
-	U32 singleStream = srcSize < 256;
-	symbolEncodingType_e hType = set_compressed;
-	size_t cLitSize;
-
-/* small ? don't even attempt compression (speed opt) */
-#define LITERAL_NOENTROPY 63
-	{
-		size_t const minLitSize = zc->flagStaticHufTable == HUF_repeat_valid ? 6 : LITERAL_NOENTROPY;
-		if (srcSize <= minLitSize)
-			return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize);
-	}
-
-	if (dstCapacity < lhSize + 1)
-		return ERROR(dstSize_tooSmall); /* not enough space for compression */
-	{
-		HUF_repeat repeat = zc->flagStaticHufTable;
-		int const preferRepeat = zc->params.cParams.strategy < ZSTD_lazy ? srcSize <= 1024 : 0;
-		if (repeat == HUF_repeat_valid && lhSize == 3)
-			singleStream = 1;
-		cLitSize = singleStream ? HUF_compress1X_repeat(ostart + lhSize, dstCapacity - lhSize, src, srcSize, 255, 11, zc->tmpCounters,
-								sizeof(zc->tmpCounters), zc->hufTable, &repeat, preferRepeat)
-					: HUF_compress4X_repeat(ostart + lhSize, dstCapacity - lhSize, src, srcSize, 255, 11, zc->tmpCounters,
-								sizeof(zc->tmpCounters), zc->hufTable, &repeat, preferRepeat);
-		if (repeat != HUF_repeat_none) {
-			hType = set_repeat;
-		} /* reused the existing table */
-		else {
-			zc->flagStaticHufTable = HUF_repeat_check;
-		} /* now have a table to reuse */
-	}
-
-	if ((cLitSize == 0) | (cLitSize >= srcSize - minGain)) {
-		zc->flagStaticHufTable = HUF_repeat_none;
-		return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize);
-	}
-	if (cLitSize == 1) {
-		zc->flagStaticHufTable = HUF_repeat_none;
-		return ZSTD_compressRleLiteralsBlock(dst, dstCapacity, src, srcSize);
-	}
-
-	/* Build header */
-	switch (lhSize) {
-	case 3: /* 2 - 2 - 10 - 10 */
-	{
-		U32 const lhc = hType + ((!singleStream) << 2) + ((U32)srcSize << 4) + ((U32)cLitSize << 14);
-		ZSTD_writeLE24(ostart, lhc);
-		break;
-	}
-	case 4: /* 2 - 2 - 14 - 14 */
-	{
-		U32 const lhc = hType + (2 << 2) + ((U32)srcSize << 4) + ((U32)cLitSize << 18);
-		ZSTD_writeLE32(ostart, lhc);
-		break;
-	}
-	default: /* should not be necessary, lhSize is only {3,4,5} */
-	case 5:  /* 2 - 2 - 18 - 18 */
-	{
-		U32 const lhc = hType + (3 << 2) + ((U32)srcSize << 4) + ((U32)cLitSize << 22);
-		ZSTD_writeLE32(ostart, lhc);
-		ostart[4] = (BYTE)(cLitSize >> 10);
-		break;
-	}
-	}
-	return lhSize + cLitSize;
-}
-
-static const BYTE LL_Code[64] = {0,  1,  2,  3,  4,  5,  6,  7,  8,  9,  10, 11, 12, 13, 14, 15, 16, 16, 17, 17, 18, 18,
-				 19, 19, 20, 20, 20, 20, 21, 21, 21, 21, 22, 22, 22, 22, 22, 22, 22, 22, 23, 23, 23, 23,
-				 23, 23, 23, 23, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24};
-
-static const BYTE ML_Code[128] = {0,  1,  2,  3,  4,  5,  6,  7,  8,  9,  10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25,
-				  26, 27, 28, 29, 30, 31, 32, 32, 33, 33, 34, 34, 35, 35, 36, 36, 36, 36, 37, 37, 37, 37, 38, 38, 38, 38,
-				  38, 38, 38, 38, 39, 39, 39, 39, 39, 39, 39, 39, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40,
-				  40, 40, 41, 41, 41, 41, 41, 41, 41, 41, 41, 41, 41, 41, 41, 41, 41, 41, 42, 42, 42, 42, 42, 42, 42, 42,
-				  42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42};
-
-void ZSTD_seqToCodes(const seqStore_t *seqStorePtr)
-{
-	BYTE const LL_deltaCode = 19;
-	BYTE const ML_deltaCode = 36;
-	const seqDef *const sequences = seqStorePtr->sequencesStart;
-	BYTE *const llCodeTable = seqStorePtr->llCode;
-	BYTE *const ofCodeTable = seqStorePtr->ofCode;
-	BYTE *const mlCodeTable = seqStorePtr->mlCode;
-	U32 const nbSeq = (U32)(seqStorePtr->sequences - seqStorePtr->sequencesStart);
-	U32 u;
-	for (u = 0; u < nbSeq; u++) {
-		U32 const llv = sequences[u].litLength;
-		U32 const mlv = sequences[u].matchLength;
-		llCodeTable[u] = (llv > 63) ? (BYTE)ZSTD_highbit32(llv) + LL_deltaCode : LL_Code[llv];
-		ofCodeTable[u] = (BYTE)ZSTD_highbit32(sequences[u].offset);
-		mlCodeTable[u] = (mlv > 127) ? (BYTE)ZSTD_highbit32(mlv) + ML_deltaCode : ML_Code[mlv];
-	}
-	if (seqStorePtr->longLengthID == 1)
-		llCodeTable[seqStorePtr->longLengthPos] = MaxLL;
-	if (seqStorePtr->longLengthID == 2)
-		mlCodeTable[seqStorePtr->longLengthPos] = MaxML;
-}
-
-ZSTD_STATIC size_t ZSTD_compressSequences_internal(ZSTD_CCtx *zc, void *dst, size_t dstCapacity)
-{
-	const int longOffsets = zc->params.cParams.windowLog > STREAM_ACCUMULATOR_MIN;
-	const seqStore_t *seqStorePtr = &(zc->seqStore);
-	FSE_CTable *CTable_LitLength = zc->litlengthCTable;
-	FSE_CTable *CTable_OffsetBits = zc->offcodeCTable;
-	FSE_CTable *CTable_MatchLength = zc->matchlengthCTable;
-	U32 LLtype, Offtype, MLtype; /* compressed, raw or rle */
-	const seqDef *const sequences = seqStorePtr->sequencesStart;
-	const BYTE *const ofCodeTable = seqStorePtr->ofCode;
-	const BYTE *const llCodeTable = seqStorePtr->llCode;
-	const BYTE *const mlCodeTable = seqStorePtr->mlCode;
-	BYTE *const ostart = (BYTE *)dst;
-	BYTE *const oend = ostart + dstCapacity;
-	BYTE *op = ostart;
-	size_t const nbSeq = seqStorePtr->sequences - seqStorePtr->sequencesStart;
-	BYTE *seqHead;
-
-	U32 *count;
-	S16 *norm;
-	U32 *workspace;
-	size_t workspaceSize = sizeof(zc->tmpCounters);
-	{
-		size_t spaceUsed32 = 0;
-		count = (U32 *)zc->tmpCounters + spaceUsed32;
-		spaceUsed32 += MaxSeq + 1;
-		norm = (S16 *)((U32 *)zc->tmpCounters + spaceUsed32);
-		spaceUsed32 += ALIGN(sizeof(S16) * (MaxSeq + 1), sizeof(U32)) >> 2;
-
-		workspace = (U32 *)zc->tmpCounters + spaceUsed32;
-		workspaceSize -= (spaceUsed32 << 2);
-	}
-
-	/* Compress literals */
-	{
-		const BYTE *const literals = seqStorePtr->litStart;
-		size_t const litSize = seqStorePtr->lit - literals;
-		size_t const cSize = ZSTD_compressLiterals(zc, op, dstCapacity, literals, litSize);
-		if (ZSTD_isError(cSize))
-			return cSize;
-		op += cSize;
-	}
-
-	/* Sequences Header */
-	if ((oend - op) < 3 /*max nbSeq Size*/ + 1 /*seqHead */)
-		return ERROR(dstSize_tooSmall);
-	if (nbSeq < 0x7F)
-		*op++ = (BYTE)nbSeq;
-	else if (nbSeq < LONGNBSEQ)
-		op[0] = (BYTE)((nbSeq >> 8) + 0x80), op[1] = (BYTE)nbSeq, op += 2;
-	else
-		op[0] = 0xFF, ZSTD_writeLE16(op + 1, (U16)(nbSeq - LONGNBSEQ)), op += 3;
-	if (nbSeq == 0)
-		return op - ostart;
-
-	/* seqHead : flags for FSE encoding type */
-	seqHead = op++;
-
-#define MIN_SEQ_FOR_DYNAMIC_FSE 64
-#define MAX_SEQ_FOR_STATIC_FSE 1000
-
-	/* convert length/distances into codes */
-	ZSTD_seqToCodes(seqStorePtr);
-
-	/* CTable for Literal Lengths */
-	{
-		U32 max = MaxLL;
-		size_t const mostFrequent = FSE_countFast_wksp(count, &max, llCodeTable, nbSeq, workspace);
-		if ((mostFrequent == nbSeq) && (nbSeq > 2)) {
-			*op++ = llCodeTable[0];
-			FSE_buildCTable_rle(CTable_LitLength, (BYTE)max);
-			LLtype = set_rle;
-		} else if ((zc->flagStaticTables) && (nbSeq < MAX_SEQ_FOR_STATIC_FSE)) {
-			LLtype = set_repeat;
-		} else if ((nbSeq < MIN_SEQ_FOR_DYNAMIC_FSE) || (mostFrequent < (nbSeq >> (LL_defaultNormLog - 1)))) {
-			FSE_buildCTable_wksp(CTable_LitLength, LL_defaultNorm, MaxLL, LL_defaultNormLog, workspace, workspaceSize);
-			LLtype = set_basic;
-		} else {
-			size_t nbSeq_1 = nbSeq;
-			const U32 tableLog = FSE_optimalTableLog(LLFSELog, nbSeq, max);
-			if (count[llCodeTable[nbSeq - 1]] > 1) {
-				count[llCodeTable[nbSeq - 1]]--;
-				nbSeq_1--;
-			}
-			FSE_normalizeCount(norm, tableLog, count, nbSeq_1, max);
-			{
-				size_t const NCountSize = FSE_writeNCount(op, oend - op, norm, max, tableLog); /* overflow protected */
-				if (FSE_isError(NCountSize))
-					return NCountSize;
-				op += NCountSize;
-			}
-			FSE_buildCTable_wksp(CTable_LitLength, norm, max, tableLog, workspace, workspaceSize);
-			LLtype = set_compressed;
-		}
-	}
-
-	/* CTable for Offsets */
-	{
-		U32 max = MaxOff;
-		size_t const mostFrequent = FSE_countFast_wksp(count, &max, ofCodeTable, nbSeq, workspace);
-		if ((mostFrequent == nbSeq) && (nbSeq > 2)) {
-			*op++ = ofCodeTable[0];
-			FSE_buildCTable_rle(CTable_OffsetBits, (BYTE)max);
-			Offtype = set_rle;
-		} else if ((zc->flagStaticTables) && (nbSeq < MAX_SEQ_FOR_STATIC_FSE)) {
-			Offtype = set_repeat;
-		} else if ((nbSeq < MIN_SEQ_FOR_DYNAMIC_FSE) || (mostFrequent < (nbSeq >> (OF_defaultNormLog - 1)))) {
-			FSE_buildCTable_wksp(CTable_OffsetBits, OF_defaultNorm, MaxOff, OF_defaultNormLog, workspace, workspaceSize);
-			Offtype = set_basic;
-		} else {
-			size_t nbSeq_1 = nbSeq;
-			const U32 tableLog = FSE_optimalTableLog(OffFSELog, nbSeq, max);
-			if (count[ofCodeTable[nbSeq - 1]] > 1) {
-				count[ofCodeTable[nbSeq - 1]]--;
-				nbSeq_1--;
-			}
-			FSE_normalizeCount(norm, tableLog, count, nbSeq_1, max);
-			{
-				size_t const NCountSize = FSE_writeNCount(op, oend - op, norm, max, tableLog); /* overflow protected */
-				if (FSE_isError(NCountSize))
-					return NCountSize;
-				op += NCountSize;
-			}
-			FSE_buildCTable_wksp(CTable_OffsetBits, norm, max, tableLog, workspace, workspaceSize);
-			Offtype = set_compressed;
-		}
-	}
-
-	/* CTable for MatchLengths */
-	{
-		U32 max = MaxML;
-		size_t const mostFrequent = FSE_countFast_wksp(count, &max, mlCodeTable, nbSeq, workspace);
-		if ((mostFrequent == nbSeq) && (nbSeq > 2)) {
-			*op++ = *mlCodeTable;
-			FSE_buildCTable_rle(CTable_MatchLength, (BYTE)max);
-			MLtype = set_rle;
-		} else if ((zc->flagStaticTables) && (nbSeq < MAX_SEQ_FOR_STATIC_FSE)) {
-			MLtype = set_repeat;
-		} else if ((nbSeq < MIN_SEQ_FOR_DYNAMIC_FSE) || (mostFrequent < (nbSeq >> (ML_defaultNormLog - 1)))) {
-			FSE_buildCTable_wksp(CTable_MatchLength, ML_defaultNorm, MaxML, ML_defaultNormLog, workspace, workspaceSize);
-			MLtype = set_basic;
-		} else {
-			size_t nbSeq_1 = nbSeq;
-			const U32 tableLog = FSE_optimalTableLog(MLFSELog, nbSeq, max);
-			if (count[mlCodeTable[nbSeq - 1]] > 1) {
-				count[mlCodeTable[nbSeq - 1]]--;
-				nbSeq_1--;
-			}
-			FSE_normalizeCount(norm, tableLog, count, nbSeq_1, max);
-			{
-				size_t const NCountSize = FSE_writeNCount(op, oend - op, norm, max, tableLog); /* overflow protected */
-				if (FSE_isError(NCountSize))
-					return NCountSize;
-				op += NCountSize;
-			}
-			FSE_buildCTable_wksp(CTable_MatchLength, norm, max, tableLog, workspace, workspaceSize);
-			MLtype = set_compressed;
-		}
-	}
-
-	*seqHead = (BYTE)((LLtype << 6) + (Offtype << 4) + (MLtype << 2));
-	zc->flagStaticTables = 0;
-
-	/* Encoding Sequences */
-	{
-		BIT_CStream_t blockStream;
-		FSE_CState_t stateMatchLength;
-		FSE_CState_t stateOffsetBits;
-		FSE_CState_t stateLitLength;
-
-		CHECK_E(BIT_initCStream(&blockStream, op, oend - op), dstSize_tooSmall); /* not enough space remaining */
-
-		/* first symbols */
-		FSE_initCState2(&stateMatchLength, CTable_MatchLength, mlCodeTable[nbSeq - 1]);
-		FSE_initCState2(&stateOffsetBits, CTable_OffsetBits, ofCodeTable[nbSeq - 1]);
-		FSE_initCState2(&stateLitLength, CTable_LitLength, llCodeTable[nbSeq - 1]);
-		BIT_addBits(&blockStream, sequences[nbSeq - 1].litLength, LL_bits[llCodeTable[nbSeq - 1]]);
-		if (ZSTD_32bits())
-			BIT_flushBits(&blockStream);
-		BIT_addBits(&blockStream, sequences[nbSeq - 1].matchLength, ML_bits[mlCodeTable[nbSeq - 1]]);
-		if (ZSTD_32bits())
-			BIT_flushBits(&blockStream);
-		if (longOffsets) {
-			U32 const ofBits = ofCodeTable[nbSeq - 1];
-			int const extraBits = ofBits - MIN(ofBits, STREAM_ACCUMULATOR_MIN - 1);
-			if (extraBits) {
-				BIT_addBits(&blockStream, sequences[nbSeq - 1].offset, extraBits);
-				BIT_flushBits(&blockStream);
-			}
-			BIT_addBits(&blockStream, sequences[nbSeq - 1].offset >> extraBits, ofBits - extraBits);
-		} else {
-			BIT_addBits(&blockStream, sequences[nbSeq - 1].offset, ofCodeTable[nbSeq - 1]);
-		}
-		BIT_flushBits(&blockStream);
-
-		{
-			size_t n;
-			for (n = nbSeq - 2; n < nbSeq; n--) { /* intentional underflow */
-				BYTE const llCode = llCodeTable[n];
-				BYTE const ofCode = ofCodeTable[n];
-				BYTE const mlCode = mlCodeTable[n];
-				U32 const llBits = LL_bits[llCode];
-				U32 const ofBits = ofCode; /* 32b*/ /* 64b*/
-				U32 const mlBits = ML_bits[mlCode];
-				/* (7)*/							    /* (7)*/
-				FSE_encodeSymbol(&blockStream, &stateOffsetBits, ofCode); /* 15 */  /* 15 */
-				FSE_encodeSymbol(&blockStream, &stateMatchLength, mlCode); /* 24 */ /* 24 */
-				if (ZSTD_32bits())
-					BIT_flushBits(&blockStream);				  /* (7)*/
-				FSE_encodeSymbol(&blockStream, &stateLitLength, llCode); /* 16 */ /* 33 */
-				if (ZSTD_32bits() || (ofBits + mlBits + llBits >= 64 - 7 - (LLFSELog + MLFSELog + OffFSELog)))
-					BIT_flushBits(&blockStream); /* (7)*/
-				BIT_addBits(&blockStream, sequences[n].litLength, llBits);
-				if (ZSTD_32bits() && ((llBits + mlBits) > 24))
-					BIT_flushBits(&blockStream);
-				BIT_addBits(&blockStream, sequences[n].matchLength, mlBits);
-				if (ZSTD_32bits())
-					BIT_flushBits(&blockStream); /* (7)*/
-				if (longOffsets) {
-					int const extraBits = ofBits - MIN(ofBits, STREAM_ACCUMULATOR_MIN - 1);
-					if (extraBits) {
-						BIT_addBits(&blockStream, sequences[n].offset, extraBits);
-						BIT_flushBits(&blockStream); /* (7)*/
-					}
-					BIT_addBits(&blockStream, sequences[n].offset >> extraBits, ofBits - extraBits); /* 31 */
-				} else {
-					BIT_addBits(&blockStream, sequences[n].offset, ofBits); /* 31 */
-				}
-				BIT_flushBits(&blockStream); /* (7)*/
-			}
-		}
-
-		FSE_flushCState(&blockStream, &stateMatchLength);
-		FSE_flushCState(&blockStream, &stateOffsetBits);
-		FSE_flushCState(&blockStream, &stateLitLength);
-
-		{
-			size_t const streamSize = BIT_closeCStream(&blockStream);
-			if (streamSize == 0)
-				return ERROR(dstSize_tooSmall); /* not enough space */
-			op += streamSize;
-		}
-	}
-	return op - ostart;
-}
-
-ZSTD_STATIC size_t ZSTD_compressSequences(ZSTD_CCtx *zc, void *dst, size_t dstCapacity, size_t srcSize)
-{
-	size_t const cSize = ZSTD_compressSequences_internal(zc, dst, dstCapacity);
-	size_t const minGain = ZSTD_minGain(srcSize);
-	size_t const maxCSize = srcSize - minGain;
-	/* If the srcSize <= dstCapacity, then there is enough space to write a
-	 * raw uncompressed block. Since we ran out of space, the block must not
-	 * be compressible, so fall back to a raw uncompressed block.
-	 */
-	int const uncompressibleError = cSize == ERROR(dstSize_tooSmall) && srcSize <= dstCapacity;
-	int i;
-
-	if (ZSTD_isError(cSize) && !uncompressibleError)
-		return cSize;
-	if (cSize >= maxCSize || uncompressibleError) {
-		zc->flagStaticHufTable = HUF_repeat_none;
-		return 0;
-	}
-	/* confirm repcodes */
-	for (i = 0; i < ZSTD_REP_NUM; i++)
-		zc->rep[i] = zc->repToConfirm[i];
-	return cSize;
-}
-
-/*! ZSTD_storeSeq() :
-	Store a sequence (literal length, literals, offset code and match length code) into seqStore_t.
-	`offsetCode` : distance to match, or 0 == repCode.
-	`matchCode` : matchLength - MINMATCH
-*/
-ZSTD_STATIC void ZSTD_storeSeq(seqStore_t *seqStorePtr, size_t litLength, const void *literals, U32 offsetCode, size_t matchCode)
-{
-	/* copy Literals */
-	ZSTD_wildcopy(seqStorePtr->lit, literals, litLength);
-	seqStorePtr->lit += litLength;
-
-	/* literal Length */
-	if (litLength > 0xFFFF) {
-		seqStorePtr->longLengthID = 1;
-		seqStorePtr->longLengthPos = (U32)(seqStorePtr->sequences - seqStorePtr->sequencesStart);
-	}
-	seqStorePtr->sequences[0].litLength = (U16)litLength;
-
-	/* match offset */
-	seqStorePtr->sequences[0].offset = offsetCode + 1;
-
-	/* match Length */
-	if (matchCode > 0xFFFF) {
-		seqStorePtr->longLengthID = 2;
-		seqStorePtr->longLengthPos = (U32)(seqStorePtr->sequences - seqStorePtr->sequencesStart);
-	}
-	seqStorePtr->sequences[0].matchLength = (U16)matchCode;
-
-	seqStorePtr->sequences++;
-}
-
-/*-*************************************
-*  Match length counter
-***************************************/
-static unsigned ZSTD_NbCommonBytes(register size_t val)
-{
-	if (ZSTD_isLittleEndian()) {
-		if (ZSTD_64bits()) {
-			return (__builtin_ctzll((U64)val) >> 3);
-		} else { /* 32 bits */
-			return (__builtin_ctz((U32)val) >> 3);
-		}
-	} else { /* Big Endian CPU */
-		if (ZSTD_64bits()) {
-			return (__builtin_clzll(val) >> 3);
-		} else { /* 32 bits */
-			return (__builtin_clz((U32)val) >> 3);
-		}
-	}
-}
-
-static size_t ZSTD_count(const BYTE *pIn, const BYTE *pMatch, const BYTE *const pInLimit)
-{
-	const BYTE *const pStart = pIn;
-	const BYTE *const pInLoopLimit = pInLimit - (sizeof(size_t) - 1);
-
-	while (pIn < pInLoopLimit) {
-		size_t const diff = ZSTD_readST(pMatch) ^ ZSTD_readST(pIn);
-		if (!diff) {
-			pIn += sizeof(size_t);
-			pMatch += sizeof(size_t);
-			continue;
-		}
-		pIn += ZSTD_NbCommonBytes(diff);
-		return (size_t)(pIn - pStart);
-	}
-	if (ZSTD_64bits())
-		if ((pIn < (pInLimit - 3)) && (ZSTD_read32(pMatch) == ZSTD_read32(pIn))) {
-			pIn += 4;
-			pMatch += 4;
-		}
-	if ((pIn < (pInLimit - 1)) && (ZSTD_read16(pMatch) == ZSTD_read16(pIn))) {
-		pIn += 2;
-		pMatch += 2;
-	}
-	if ((pIn < pInLimit) && (*pMatch == *pIn))
-		pIn++;
-	return (size_t)(pIn - pStart);
-}
-
-/** ZSTD_count_2segments() :
-*   can count match length with `ip` & `match` in 2 different segments.
-*   convention : on reaching mEnd, match count continue starting from iStart
-*/
-static size_t ZSTD_count_2segments(const BYTE *ip, const BYTE *match, const BYTE *iEnd, const BYTE *mEnd, const BYTE *iStart)
-{
-	const BYTE *const vEnd = MIN(ip + (mEnd - match), iEnd);
-	size_t const matchLength = ZSTD_count(ip, match, vEnd);
-	if (match + matchLength != mEnd)
-		return matchLength;
-	return matchLength + ZSTD_count(ip + matchLength, iStart, iEnd);
-}
-
-/*-*************************************
-*  Hashes
-***************************************/
-static const U32 prime3bytes = 506832829U;
-static U32 ZSTD_hash3(U32 u, U32 h) { return ((u << (32 - 24)) * prime3bytes) >> (32 - h); }
-ZSTD_STATIC size_t ZSTD_hash3Ptr(const void *ptr, U32 h) { return ZSTD_hash3(ZSTD_readLE32(ptr), h); } /* only in zstd_opt.h */
-
-static const U32 prime4bytes = 2654435761U;
-static U32 ZSTD_hash4(U32 u, U32 h) { return (u * prime4bytes) >> (32 - h); }
-static size_t ZSTD_hash4Ptr(const void *ptr, U32 h) { return ZSTD_hash4(ZSTD_read32(ptr), h); }
-
-static const U64 prime5bytes = 889523592379ULL;
-static size_t ZSTD_hash5(U64 u, U32 h) { return (size_t)(((u << (64 - 40)) * prime5bytes) >> (64 - h)); }
-static size_t ZSTD_hash5Ptr(const void *p, U32 h) { return ZSTD_hash5(ZSTD_readLE64(p), h); }
-
-static const U64 prime6bytes = 227718039650203ULL;
-static size_t ZSTD_hash6(U64 u, U32 h) { return (size_t)(((u << (64 - 48)) * prime6bytes) >> (64 - h)); }
-static size_t ZSTD_hash6Ptr(const void *p, U32 h) { return ZSTD_hash6(ZSTD_readLE64(p), h); }
-
-static const U64 prime7bytes = 58295818150454627ULL;
-static size_t ZSTD_hash7(U64 u, U32 h) { return (size_t)(((u << (64 - 56)) * prime7bytes) >> (64 - h)); }
-static size_t ZSTD_hash7Ptr(const void *p, U32 h) { return ZSTD_hash7(ZSTD_readLE64(p), h); }
-
-static const U64 prime8bytes = 0xCF1BBCDCB7A56463ULL;
-static size_t ZSTD_hash8(U64 u, U32 h) { return (size_t)(((u)*prime8bytes) >> (64 - h)); }
-static size_t ZSTD_hash8Ptr(const void *p, U32 h) { return ZSTD_hash8(ZSTD_readLE64(p), h); }
-
-static size_t ZSTD_hashPtr(const void *p, U32 hBits, U32 mls)
-{
-	switch (mls) {
-	// case 3: return ZSTD_hash3Ptr(p, hBits);
-	default:
-	case 4: return ZSTD_hash4Ptr(p, hBits);
-	case 5: return ZSTD_hash5Ptr(p, hBits);
-	case 6: return ZSTD_hash6Ptr(p, hBits);
-	case 7: return ZSTD_hash7Ptr(p, hBits);
-	case 8: return ZSTD_hash8Ptr(p, hBits);
-	}
-}
-
-/*-*************************************
-*  Fast Scan
-***************************************/
-static void ZSTD_fillHashTable(ZSTD_CCtx *zc, const void *end, const U32 mls)
-{
-	U32 *const hashTable = zc->hashTable;
-	U32 const hBits = zc->params.cParams.hashLog;
-	const BYTE *const base = zc->base;
-	const BYTE *ip = base + zc->nextToUpdate;
-	const BYTE *const iend = ((const BYTE *)end) - HASH_READ_SIZE;
-	const size_t fastHashFillStep = 3;
-
-	while (ip <= iend) {
-		hashTable[ZSTD_hashPtr(ip, hBits, mls)] = (U32)(ip - base);
-		ip += fastHashFillStep;
-	}
-}
-
-FORCE_INLINE
-void ZSTD_compressBlock_fast_generic(ZSTD_CCtx *cctx, const void *src, size_t srcSize, const U32 mls)
-{
-	U32 *const hashTable = cctx->hashTable;
-	U32 const hBits = cctx->params.cParams.hashLog;
-	seqStore_t *seqStorePtr = &(cctx->seqStore);
-	const BYTE *const base = cctx->base;
-	const BYTE *const istart = (const BYTE *)src;
-	const BYTE *ip = istart;
-	const BYTE *anchor = istart;
-	const U32 lowestIndex = cctx->dictLimit;
-	const BYTE *const lowest = base + lowestIndex;
-	const BYTE *const iend = istart + srcSize;
-	const BYTE *const ilimit = iend - HASH_READ_SIZE;
-	U32 offset_1 = cctx->rep[0], offset_2 = cctx->rep[1];
-	U32 offsetSaved = 0;
-
-	/* init */
-	ip += (ip == lowest);
-	{
-		U32 const maxRep = (U32)(ip - lowest);
-		if (offset_2 > maxRep)
-			offsetSaved = offset_2, offset_2 = 0;
-		if (offset_1 > maxRep)
-			offsetSaved = offset_1, offset_1 = 0;
-	}
-
-	/* Main Search Loop */
-	while (ip < ilimit) { /* < instead of <=, because repcode check at (ip+1) */
-		size_t mLength;
-		size_t const h = ZSTD_hashPtr(ip, hBits, mls);
-		U32 const curr = (U32)(ip - base);
-		U32 const matchIndex = hashTable[h];
-		const BYTE *match = base + matchIndex;
-		hashTable[h] = curr; /* update hash table */
-
-		if ((offset_1 > 0) & (ZSTD_read32(ip + 1 - offset_1) == ZSTD_read32(ip + 1))) {
-			mLength = ZSTD_count(ip + 1 + 4, ip + 1 + 4 - offset_1, iend) + 4;
-			ip++;
-			ZSTD_storeSeq(seqStorePtr, ip - anchor, anchor, 0, mLength - MINMATCH);
-		} else {
-			U32 offset;
-			if ((matchIndex <= lowestIndex) || (ZSTD_read32(match) != ZSTD_read32(ip))) {
-				ip += ((ip - anchor) >> g_searchStrength) + 1;
-				continue;
-			}
-			mLength = ZSTD_count(ip + 4, match + 4, iend) + 4;
-			offset = (U32)(ip - match);
-			while (((ip > anchor) & (match > lowest)) && (ip[-1] == match[-1])) {
-				ip--;
-				match--;
-				mLength++;
-			} /* catch up */
-			offset_2 = offset_1;
-			offset_1 = offset;
-
-			ZSTD_storeSeq(seqStorePtr, ip - anchor, anchor, offset + ZSTD_REP_MOVE, mLength - MINMATCH);
-		}
-
-		/* match found */
-		ip += mLength;
-		anchor = ip;
-
-		if (ip <= ilimit) {
-			/* Fill Table */
-			hashTable[ZSTD_hashPtr(base + curr + 2, hBits, mls)] = curr + 2; /* here because curr+2 could be > iend-8 */
-			hashTable[ZSTD_hashPtr(ip - 2, hBits, mls)] = (U32)(ip - 2 - base);
-			/* check immediate repcode */
-			while ((ip <= ilimit) && ((offset_2 > 0) & (ZSTD_read32(ip) == ZSTD_read32(ip - offset_2)))) {
-				/* store sequence */
-				size_t const rLength = ZSTD_count(ip + 4, ip + 4 - offset_2, iend) + 4;
-				{
-					U32 const tmpOff = offset_2;
-					offset_2 = offset_1;
-					offset_1 = tmpOff;
-				} /* swap offset_2 <=> offset_1 */
-				hashTable[ZSTD_hashPtr(ip, hBits, mls)] = (U32)(ip - base);
-				ZSTD_storeSeq(seqStorePtr, 0, anchor, 0, rLength - MINMATCH);
-				ip += rLength;
-				anchor = ip;
-				continue; /* faster when present ... (?) */
-			}
-		}
-	}
-
-	/* save reps for next block */
-	cctx->repToConfirm[0] = offset_1 ? offset_1 : offsetSaved;
-	cctx->repToConfirm[1] = offset_2 ? offset_2 : offsetSaved;
-
-	/* Last Literals */
-	{
-		size_t const lastLLSize = iend - anchor;
-		memcpy(seqStorePtr->lit, anchor, lastLLSize);
-		seqStorePtr->lit += lastLLSize;
-	}
-}
-
-static void ZSTD_compressBlock_fast(ZSTD_CCtx *ctx, const void *src, size_t srcSize)
-{
-	const U32 mls = ctx->params.cParams.searchLength;
-	switch (mls) {
-	default: /* includes case 3 */
-	case 4: ZSTD_compressBlock_fast_generic(ctx, src, srcSize, 4); return;
-	case 5: ZSTD_compressBlock_fast_generic(ctx, src, srcSize, 5); return;
-	case 6: ZSTD_compressBlock_fast_generic(ctx, src, srcSize, 6); return;
-	case 7: ZSTD_compressBlock_fast_generic(ctx, src, srcSize, 7); return;
-	}
-}
-
-static void ZSTD_compressBlock_fast_extDict_generic(ZSTD_CCtx *ctx, const void *src, size_t srcSize, const U32 mls)
-{
-	U32 *hashTable = ctx->hashTable;
-	const U32 hBits = ctx->params.cParams.hashLog;
-	seqStore_t *seqStorePtr = &(ctx->seqStore);
-	const BYTE *const base = ctx->base;
-	const BYTE *const dictBase = ctx->dictBase;
-	const BYTE *const istart = (const BYTE *)src;
-	const BYTE *ip = istart;
-	const BYTE *anchor = istart;
-	const U32 lowestIndex = ctx->lowLimit;
-	const BYTE *const dictStart = dictBase + lowestIndex;
-	const U32 dictLimit = ctx->dictLimit;
-	const BYTE *const lowPrefixPtr = base + dictLimit;
-	const BYTE *const dictEnd = dictBase + dictLimit;
-	const BYTE *const iend = istart + srcSize;
-	const BYTE *const ilimit = iend - 8;
-	U32 offset_1 = ctx->rep[0], offset_2 = ctx->rep[1];
-
-	/* Search Loop */
-	while (ip < ilimit) { /* < instead of <=, because (ip+1) */
-		const size_t h = ZSTD_hashPtr(ip, hBits, mls);
-		const U32 matchIndex = hashTable[h];
-		const BYTE *matchBase = matchIndex < dictLimit ? dictBase : base;
-		const BYTE *match = matchBase + matchIndex;
-		const U32 curr = (U32)(ip - base);
-		const U32 repIndex = curr + 1 - offset_1; /* offset_1 expected <= curr +1 */
-		const BYTE *repBase = repIndex < dictLimit ? dictBase : base;
-		const BYTE *repMatch = repBase + repIndex;
-		size_t mLength;
-		hashTable[h] = curr; /* update hash table */
-
-		if ((((U32)((dictLimit - 1) - repIndex) >= 3) /* intentional underflow */ & (repIndex > lowestIndex)) &&
-		    (ZSTD_read32(repMatch) == ZSTD_read32(ip + 1))) {
-			const BYTE *repMatchEnd = repIndex < dictLimit ? dictEnd : iend;
-			mLength = ZSTD_count_2segments(ip + 1 + EQUAL_READ32, repMatch + EQUAL_READ32, iend, repMatchEnd, lowPrefixPtr) + EQUAL_READ32;
-			ip++;
-			ZSTD_storeSeq(seqStorePtr, ip - anchor, anchor, 0, mLength - MINMATCH);
-		} else {
-			if ((matchIndex < lowestIndex) || (ZSTD_read32(match) != ZSTD_read32(ip))) {
-				ip += ((ip - anchor) >> g_searchStrength) + 1;
-				continue;
-			}
-			{
-				const BYTE *matchEnd = matchIndex < dictLimit ? dictEnd : iend;
-				const BYTE *lowMatchPtr = matchIndex < dictLimit ? dictStart : lowPrefixPtr;
-				U32 offset;
-				mLength = ZSTD_count_2segments(ip + EQUAL_READ32, match + EQUAL_READ32, iend, matchEnd, lowPrefixPtr) + EQUAL_READ32;
-				while (((ip > anchor) & (match > lowMatchPtr)) && (ip[-1] == match[-1])) {
-					ip--;
-					match--;
-					mLength++;
-				} /* catch up */
-				offset = curr - matchIndex;
-				offset_2 = offset_1;
-				offset_1 = offset;
-				ZSTD_storeSeq(seqStorePtr, ip - anchor, anchor, offset + ZSTD_REP_MOVE, mLength - MINMATCH);
-			}
-		}
-
-		/* found a match : store it */
-		ip += mLength;
-		anchor = ip;
-
-		if (ip <= ilimit) {
-			/* Fill Table */
-			hashTable[ZSTD_hashPtr(base + curr + 2, hBits, mls)] = curr + 2;
-			hashTable[ZSTD_hashPtr(ip - 2, hBits, mls)] = (U32)(ip - 2 - base);
-			/* check immediate repcode */
-			while (ip <= ilimit) {
-				U32 const curr2 = (U32)(ip - base);
-				U32 const repIndex2 = curr2 - offset_2;
-				const BYTE *repMatch2 = repIndex2 < dictLimit ? dictBase + repIndex2 : base + repIndex2;
-				if ((((U32)((dictLimit - 1) - repIndex2) >= 3) & (repIndex2 > lowestIndex)) /* intentional overflow */
-				    && (ZSTD_read32(repMatch2) == ZSTD_read32(ip))) {
-					const BYTE *const repEnd2 = repIndex2 < dictLimit ? dictEnd : iend;
-					size_t repLength2 =
-					    ZSTD_count_2segments(ip + EQUAL_READ32, repMatch2 + EQUAL_READ32, iend, repEnd2, lowPrefixPtr) + EQUAL_READ32;
-					U32 tmpOffset = offset_2;
-					offset_2 = offset_1;
-					offset_1 = tmpOffset; /* swap offset_2 <=> offset_1 */
-					ZSTD_storeSeq(seqStorePtr, 0, anchor, 0, repLength2 - MINMATCH);
-					hashTable[ZSTD_hashPtr(ip, hBits, mls)] = curr2;
-					ip += repLength2;
-					anchor = ip;
-					continue;
-				}
-				break;
-			}
-		}
-	}
-
-	/* save reps for next block */
-	ctx->repToConfirm[0] = offset_1;
-	ctx->repToConfirm[1] = offset_2;
-
-	/* Last Literals */
-	{
-		size_t const lastLLSize = iend - anchor;
-		memcpy(seqStorePtr->lit, anchor, lastLLSize);
-		seqStorePtr->lit += lastLLSize;
-	}
-}
-
-static void ZSTD_compressBlock_fast_extDict(ZSTD_CCtx *ctx, const void *src, size_t srcSize)
-{
-	U32 const mls = ctx->params.cParams.searchLength;
-	switch (mls) {
-	default: /* includes case 3 */
-	case 4: ZSTD_compressBlock_fast_extDict_generic(ctx, src, srcSize, 4); return;
-	case 5: ZSTD_compressBlock_fast_extDict_generic(ctx, src, srcSize, 5); return;
-	case 6: ZSTD_compressBlock_fast_extDict_generic(ctx, src, srcSize, 6); return;
-	case 7: ZSTD_compressBlock_fast_extDict_generic(ctx, src, srcSize, 7); return;
-	}
-}
-
-/*-*************************************
-*  Double Fast
-***************************************/
-static void ZSTD_fillDoubleHashTable(ZSTD_CCtx *cctx, const void *end, const U32 mls)
-{
-	U32 *const hashLarge = cctx->hashTable;
-	U32 const hBitsL = cctx->params.cParams.hashLog;
-	U32 *const hashSmall = cctx->chainTable;
-	U32 const hBitsS = cctx->params.cParams.chainLog;
-	const BYTE *const base = cctx->base;
-	const BYTE *ip = base + cctx->nextToUpdate;
-	const BYTE *const iend = ((const BYTE *)end) - HASH_READ_SIZE;
-	const size_t fastHashFillStep = 3;
-
-	while (ip <= iend) {
-		hashSmall[ZSTD_hashPtr(ip, hBitsS, mls)] = (U32)(ip - base);
-		hashLarge[ZSTD_hashPtr(ip, hBitsL, 8)] = (U32)(ip - base);
-		ip += fastHashFillStep;
-	}
-}
-
-FORCE_INLINE
-void ZSTD_compressBlock_doubleFast_generic(ZSTD_CCtx *cctx, const void *src, size_t srcSize, const U32 mls)
-{
-	U32 *const hashLong = cctx->hashTable;
-	const U32 hBitsL = cctx->params.cParams.hashLog;
-	U32 *const hashSmall = cctx->chainTable;
-	const U32 hBitsS = cctx->params.cParams.chainLog;
-	seqStore_t *seqStorePtr = &(cctx->seqStore);
-	const BYTE *const base = cctx->base;
-	const BYTE *const istart = (const BYTE *)src;
-	const BYTE *ip = istart;
-	const BYTE *anchor = istart;
-	const U32 lowestIndex = cctx->dictLimit;
-	const BYTE *const lowest = base + lowestIndex;
-	const BYTE *const iend = istart + srcSize;
-	const BYTE *const ilimit = iend - HASH_READ_SIZE;
-	U32 offset_1 = cctx->rep[0], offset_2 = cctx->rep[1];
-	U32 offsetSaved = 0;
-
-	/* init */
-	ip += (ip == lowest);
-	{
-		U32 const maxRep = (U32)(ip - lowest);
-		if (offset_2 > maxRep)
-			offsetSaved = offset_2, offset_2 = 0;
-		if (offset_1 > maxRep)
-			offsetSaved = offset_1, offset_1 = 0;
-	}
-
-	/* Main Search Loop */
-	while (ip < ilimit) { /* < instead of <=, because repcode check at (ip+1) */
-		size_t mLength;
-		size_t const h2 = ZSTD_hashPtr(ip, hBitsL, 8);
-		size_t const h = ZSTD_hashPtr(ip, hBitsS, mls);
-		U32 const curr = (U32)(ip - base);
-		U32 const matchIndexL = hashLong[h2];
-		U32 const matchIndexS = hashSmall[h];
-		const BYTE *matchLong = base + matchIndexL;
-		const BYTE *match = base + matchIndexS;
-		hashLong[h2] = hashSmall[h] = curr; /* update hash tables */
-
-		if ((offset_1 > 0) & (ZSTD_read32(ip + 1 - offset_1) == ZSTD_read32(ip + 1))) { /* note : by construction, offset_1 <= curr */
-			mLength = ZSTD_count(ip + 1 + 4, ip + 1 + 4 - offset_1, iend) + 4;
-			ip++;
-			ZSTD_storeSeq(seqStorePtr, ip - anchor, anchor, 0, mLength - MINMATCH);
-		} else {
-			U32 offset;
-			if ((matchIndexL > lowestIndex) && (ZSTD_read64(matchLong) == ZSTD_read64(ip))) {
-				mLength = ZSTD_count(ip + 8, matchLong + 8, iend) + 8;
-				offset = (U32)(ip - matchLong);
-				while (((ip > anchor) & (matchLong > lowest)) && (ip[-1] == matchLong[-1])) {
-					ip--;
-					matchLong--;
-					mLength++;
-				} /* catch up */
-			} else if ((matchIndexS > lowestIndex) && (ZSTD_read32(match) == ZSTD_read32(ip))) {
-				size_t const h3 = ZSTD_hashPtr(ip + 1, hBitsL, 8);
-				U32 const matchIndex3 = hashLong[h3];
-				const BYTE *match3 = base + matchIndex3;
-				hashLong[h3] = curr + 1;
-				if ((matchIndex3 > lowestIndex) && (ZSTD_read64(match3) == ZSTD_read64(ip + 1))) {
-					mLength = ZSTD_count(ip + 9, match3 + 8, iend) + 8;
-					ip++;
-					offset = (U32)(ip - match3);
-					while (((ip > anchor) & (match3 > lowest)) && (ip[-1] == match3[-1])) {
-						ip--;
-						match3--;
-						mLength++;
-					} /* catch up */
-				} else {
-					mLength = ZSTD_count(ip + 4, match + 4, iend) + 4;
-					offset = (U32)(ip - match);
-					while (((ip > anchor) & (match > lowest)) && (ip[-1] == match[-1])) {
-						ip--;
-						match--;
-						mLength++;
-					} /* catch up */
-				}
-			} else {
-				ip += ((ip - anchor) >> g_searchStrength) + 1;
-				continue;
-			}
-
-			offset_2 = offset_1;
-			offset_1 = offset;
-
-			ZSTD_storeSeq(seqStorePtr, ip - anchor, anchor, offset + ZSTD_REP_MOVE, mLength - MINMATCH);
-		}
-
-		/* match found */
-		ip += mLength;
-		anchor = ip;
-
-		if (ip <= ilimit) {
-			/* Fill Table */
-			hashLong[ZSTD_hashPtr(base + curr + 2, hBitsL, 8)] = hashSmall[ZSTD_hashPtr(base + curr + 2, hBitsS, mls)] =
-			    curr + 2; /* here because curr+2 could be > iend-8 */
-			hashLong[ZSTD_hashPtr(ip - 2, hBitsL, 8)] = hashSmall[ZSTD_hashPtr(ip - 2, hBitsS, mls)] = (U32)(ip - 2 - base);
-
-			/* check immediate repcode */
-			while ((ip <= ilimit) && ((offset_2 > 0) & (ZSTD_read32(ip) == ZSTD_read32(ip - offset_2)))) {
-				/* store sequence */
-				size_t const rLength = ZSTD_count(ip + 4, ip + 4 - offset_2, iend) + 4;
-				{
-					U32 const tmpOff = offset_2;
-					offset_2 = offset_1;
-					offset_1 = tmpOff;
-				} /* swap offset_2 <=> offset_1 */
-				hashSmall[ZSTD_hashPtr(ip, hBitsS, mls)] = (U32)(ip - base);
-				hashLong[ZSTD_hashPtr(ip, hBitsL, 8)] = (U32)(ip - base);
-				ZSTD_storeSeq(seqStorePtr, 0, anchor, 0, rLength - MINMATCH);
-				ip += rLength;
-				anchor = ip;
-				continue; /* faster when present ... (?) */
-			}
-		}
-	}
-
-	/* save reps for next block */
-	cctx->repToConfirm[0] = offset_1 ? offset_1 : offsetSaved;
-	cctx->repToConfirm[1] = offset_2 ? offset_2 : offsetSaved;
-
-	/* Last Literals */
-	{
-		size_t const lastLLSize = iend - anchor;
-		memcpy(seqStorePtr->lit, anchor, lastLLSize);
-		seqStorePtr->lit += lastLLSize;
-	}
-}
-
-static void ZSTD_compressBlock_doubleFast(ZSTD_CCtx *ctx, const void *src, size_t srcSize)
-{
-	const U32 mls = ctx->params.cParams.searchLength;
-	switch (mls) {
-	default: /* includes case 3 */
-	case 4: ZSTD_compressBlock_doubleFast_generic(ctx, src, srcSize, 4); return;
-	case 5: ZSTD_compressBlock_doubleFast_generic(ctx, src, srcSize, 5); return;
-	case 6: ZSTD_compressBlock_doubleFast_generic(ctx, src, srcSize, 6); return;
-	case 7: ZSTD_compressBlock_doubleFast_generic(ctx, src, srcSize, 7); return;
-	}
-}
-
-static void ZSTD_compressBlock_doubleFast_extDict_generic(ZSTD_CCtx *ctx, const void *src, size_t srcSize, const U32 mls)
-{
-	U32 *const hashLong = ctx->hashTable;
-	U32 const hBitsL = ctx->params.cParams.hashLog;
-	U32 *const hashSmall = ctx->chainTable;
-	U32 const hBitsS = ctx->params.cParams.chainLog;
-	seqStore_t *seqStorePtr = &(ctx->seqStore);
-	const BYTE *const base = ctx->base;
-	const BYTE *const dictBase = ctx->dictBase;
-	const BYTE *const istart = (const BYTE *)src;
-	const BYTE *ip = istart;
-	const BYTE *anchor = istart;
-	const U32 lowestIndex = ctx->lowLimit;
-	const BYTE *const dictStart = dictBase + lowestIndex;
-	const U32 dictLimit = ctx->dictLimit;
-	const BYTE *const lowPrefixPtr = base + dictLimit;
-	const BYTE *const dictEnd = dictBase + dictLimit;
-	const BYTE *const iend = istart + srcSize;
-	const BYTE *const ilimit = iend - 8;
-	U32 offset_1 = ctx->rep[0], offset_2 = ctx->rep[1];
-
-	/* Search Loop */
-	while (ip < ilimit) { /* < instead of <=, because (ip+1) */
-		const size_t hSmall = ZSTD_hashPtr(ip, hBitsS, mls);
-		const U32 matchIndex = hashSmall[hSmall];
-		const BYTE *matchBase = matchIndex < dictLimit ? dictBase : base;
-		const BYTE *match = matchBase + matchIndex;
-
-		const size_t hLong = ZSTD_hashPtr(ip, hBitsL, 8);
-		const U32 matchLongIndex = hashLong[hLong];
-		const BYTE *matchLongBase = matchLongIndex < dictLimit ? dictBase : base;
-		const BYTE *matchLong = matchLongBase + matchLongIndex;
-
-		const U32 curr = (U32)(ip - base);
-		const U32 repIndex = curr + 1 - offset_1; /* offset_1 expected <= curr +1 */
-		const BYTE *repBase = repIndex < dictLimit ? dictBase : base;
-		const BYTE *repMatch = repBase + repIndex;
-		size_t mLength;
-		hashSmall[hSmall] = hashLong[hLong] = curr; /* update hash table */
-
-		if ((((U32)((dictLimit - 1) - repIndex) >= 3) /* intentional underflow */ & (repIndex > lowestIndex)) &&
-		    (ZSTD_read32(repMatch) == ZSTD_read32(ip + 1))) {
-			const BYTE *repMatchEnd = repIndex < dictLimit ? dictEnd : iend;
-			mLength = ZSTD_count_2segments(ip + 1 + 4, repMatch + 4, iend, repMatchEnd, lowPrefixPtr) + 4;
-			ip++;
-			ZSTD_storeSeq(seqStorePtr, ip - anchor, anchor, 0, mLength - MINMATCH);
-		} else {
-			if ((matchLongIndex > lowestIndex) && (ZSTD_read64(matchLong) == ZSTD_read64(ip))) {
-				const BYTE *matchEnd = matchLongIndex < dictLimit ? dictEnd : iend;
-				const BYTE *lowMatchPtr = matchLongIndex < dictLimit ? dictStart : lowPrefixPtr;
-				U32 offset;
-				mLength = ZSTD_count_2segments(ip + 8, matchLong + 8, iend, matchEnd, lowPrefixPtr) + 8;
-				offset = curr - matchLongIndex;
-				while (((ip > anchor) & (matchLong > lowMatchPtr)) && (ip[-1] == matchLong[-1])) {
-					ip--;
-					matchLong--;
-					mLength++;
-				} /* catch up */
-				offset_2 = offset_1;
-				offset_1 = offset;
-				ZSTD_storeSeq(seqStorePtr, ip - anchor, anchor, offset + ZSTD_REP_MOVE, mLength - MINMATCH);
-
-			} else if ((matchIndex > lowestIndex) && (ZSTD_read32(match) == ZSTD_read32(ip))) {
-				size_t const h3 = ZSTD_hashPtr(ip + 1, hBitsL, 8);
-				U32 const matchIndex3 = hashLong[h3];
-				const BYTE *const match3Base = matchIndex3 < dictLimit ? dictBase : base;
-				const BYTE *match3 = match3Base + matchIndex3;
-				U32 offset;
-				hashLong[h3] = curr + 1;
-				if ((matchIndex3 > lowestIndex) && (ZSTD_read64(match3) == ZSTD_read64(ip + 1))) {
-					const BYTE *matchEnd = matchIndex3 < dictLimit ? dictEnd : iend;
-					const BYTE *lowMatchPtr = matchIndex3 < dictLimit ? dictStart : lowPrefixPtr;
-					mLength = ZSTD_count_2segments(ip + 9, match3 + 8, iend, matchEnd, lowPrefixPtr) + 8;
-					ip++;
-					offset = curr + 1 - matchIndex3;
-					while (((ip > anchor) & (match3 > lowMatchPtr)) && (ip[-1] == match3[-1])) {
-						ip--;
-						match3--;
-						mLength++;
-					} /* catch up */
-				} else {
-					const BYTE *matchEnd = matchIndex < dictLimit ? dictEnd : iend;
-					const BYTE *lowMatchPtr = matchIndex < dictLimit ? dictStart : lowPrefixPtr;
-					mLength = ZSTD_count_2segments(ip + 4, match + 4, iend, matchEnd, lowPrefixPtr) + 4;
-					offset = curr - matchIndex;
-					while (((ip > anchor) & (match > lowMatchPtr)) && (ip[-1] == match[-1])) {
-						ip--;
-						match--;
-						mLength++;
-					} /* catch up */
-				}
-				offset_2 = offset_1;
-				offset_1 = offset;
-				ZSTD_storeSeq(seqStorePtr, ip - anchor, anchor, offset + ZSTD_REP_MOVE, mLength - MINMATCH);
-
-			} else {
-				ip += ((ip - anchor) >> g_searchStrength) + 1;
-				continue;
-			}
-		}
-
-		/* found a match : store it */
-		ip += mLength;
-		anchor = ip;
-
-		if (ip <= ilimit) {
-			/* Fill Table */
-			hashSmall[ZSTD_hashPtr(base + curr + 2, hBitsS, mls)] = curr + 2;
-			hashLong[ZSTD_hashPtr(base + curr + 2, hBitsL, 8)] = curr + 2;
-			hashSmall[ZSTD_hashPtr(ip - 2, hBitsS, mls)] = (U32)(ip - 2 - base);
-			hashLong[ZSTD_hashPtr(ip - 2, hBitsL, 8)] = (U32)(ip - 2 - base);
-			/* check immediate repcode */
-			while (ip <= ilimit) {
-				U32 const curr2 = (U32)(ip - base);
-				U32 const repIndex2 = curr2 - offset_2;
-				const BYTE *repMatch2 = repIndex2 < dictLimit ? dictBase + repIndex2 : base + repIndex2;
-				if ((((U32)((dictLimit - 1) - repIndex2) >= 3) & (repIndex2 > lowestIndex)) /* intentional overflow */
-				    && (ZSTD_read32(repMatch2) == ZSTD_read32(ip))) {
-					const BYTE *const repEnd2 = repIndex2 < dictLimit ? dictEnd : iend;
-					size_t const repLength2 =
-					    ZSTD_count_2segments(ip + EQUAL_READ32, repMatch2 + EQUAL_READ32, iend, repEnd2, lowPrefixPtr) + EQUAL_READ32;
-					U32 tmpOffset = offset_2;
-					offset_2 = offset_1;
-					offset_1 = tmpOffset; /* swap offset_2 <=> offset_1 */
-					ZSTD_storeSeq(seqStorePtr, 0, anchor, 0, repLength2 - MINMATCH);
-					hashSmall[ZSTD_hashPtr(ip, hBitsS, mls)] = curr2;
-					hashLong[ZSTD_hashPtr(ip, hBitsL, 8)] = curr2;
-					ip += repLength2;
-					anchor = ip;
-					continue;
-				}
-				break;
-			}
-		}
-	}
-
-	/* save reps for next block */
-	ctx->repToConfirm[0] = offset_1;
-	ctx->repToConfirm[1] = offset_2;
-
-	/* Last Literals */
-	{
-		size_t const lastLLSize = iend - anchor;
-		memcpy(seqStorePtr->lit, anchor, lastLLSize);
-		seqStorePtr->lit += lastLLSize;
-	}
-}
-
-static void ZSTD_compressBlock_doubleFast_extDict(ZSTD_CCtx *ctx, const void *src, size_t srcSize)
-{
-	U32 const mls = ctx->params.cParams.searchLength;
-	switch (mls) {
-	default: /* includes case 3 */
-	case 4: ZSTD_compressBlock_doubleFast_extDict_generic(ctx, src, srcSize, 4); return;
-	case 5: ZSTD_compressBlock_doubleFast_extDict_generic(ctx, src, srcSize, 5); return;
-	case 6: ZSTD_compressBlock_doubleFast_extDict_generic(ctx, src, srcSize, 6); return;
-	case 7: ZSTD_compressBlock_doubleFast_extDict_generic(ctx, src, srcSize, 7); return;
-	}
-}
-
-/*-*************************************
-*  Binary Tree search
-***************************************/
-/** ZSTD_insertBt1() : add one or multiple positions to tree.
-*   ip : assumed <= iend-8 .
-*   @return : nb of positions added */
-static U32 ZSTD_insertBt1(ZSTD_CCtx *zc, const BYTE *const ip, const U32 mls, const BYTE *const iend, U32 nbCompares, U32 extDict)
-{
-	U32 *const hashTable = zc->hashTable;
-	U32 const hashLog = zc->params.cParams.hashLog;
-	size_t const h = ZSTD_hashPtr(ip, hashLog, mls);
-	U32 *const bt = zc->chainTable;
-	U32 const btLog = zc->params.cParams.chainLog - 1;
-	U32 const btMask = (1 << btLog) - 1;
-	U32 matchIndex = hashTable[h];
-	size_t commonLengthSmaller = 0, commonLengthLarger = 0;
-	const BYTE *const base = zc->base;
-	const BYTE *const dictBase = zc->dictBase;
-	const U32 dictLimit = zc->dictLimit;
-	const BYTE *const dictEnd = dictBase + dictLimit;
-	const BYTE *const prefixStart = base + dictLimit;
-	const BYTE *match;
-	const U32 curr = (U32)(ip - base);
-	const U32 btLow = btMask >= curr ? 0 : curr - btMask;
-	U32 *smallerPtr = bt + 2 * (curr & btMask);
-	U32 *largerPtr = smallerPtr + 1;
-	U32 dummy32; /* to be nullified at the end */
-	U32 const windowLow = zc->lowLimit;
-	U32 matchEndIdx = curr + 8;
-	size_t bestLength = 8;
-
-	hashTable[h] = curr; /* Update Hash Table */
-
-	while (nbCompares-- && (matchIndex > windowLow)) {
-		U32 *const nextPtr = bt + 2 * (matchIndex & btMask);
-		size_t matchLength = MIN(commonLengthSmaller, commonLengthLarger); /* guaranteed minimum nb of common bytes */
-
-		if ((!extDict) || (matchIndex + matchLength >= dictLimit)) {
-			match = base + matchIndex;
-			if (match[matchLength] == ip[matchLength])
-				matchLength += ZSTD_count(ip + matchLength + 1, match + matchLength + 1, iend) + 1;
-		} else {
-			match = dictBase + matchIndex;
-			matchLength += ZSTD_count_2segments(ip + matchLength, match + matchLength, iend, dictEnd, prefixStart);
-			if (matchIndex + matchLength >= dictLimit)
-				match = base + matchIndex; /* to prepare for next usage of match[matchLength] */
-		}
-
-		if (matchLength > bestLength) {
-			bestLength = matchLength;
-			if (matchLength > matchEndIdx - matchIndex)
-				matchEndIdx = matchIndex + (U32)matchLength;
-		}
-
-		if (ip + matchLength == iend) /* equal : no way to know if inf or sup */
-			break;		      /* drop , to guarantee consistency ; miss a bit of compression, but other solutions can corrupt the tree */
-
-		if (match[matchLength] < ip[matchLength]) { /* necessarily within correct buffer */
-			/* match is smaller than curr */
-			*smallerPtr = matchIndex;	  /* update smaller idx */
-			commonLengthSmaller = matchLength; /* all smaller will now have at least this guaranteed common length */
-			if (matchIndex <= btLow) {
-				smallerPtr = &dummy32;
-				break;
-			}			  /* beyond tree size, stop the search */
-			smallerPtr = nextPtr + 1; /* new "smaller" => larger of match */
-			matchIndex = nextPtr[1];  /* new matchIndex larger than previous (closer to curr) */
-		} else {
-			/* match is larger than curr */
-			*largerPtr = matchIndex;
-			commonLengthLarger = matchLength;
-			if (matchIndex <= btLow) {
-				largerPtr = &dummy32;
-				break;
-			} /* beyond tree size, stop the search */
-			largerPtr = nextPtr;
-			matchIndex = nextPtr[0];
-		}
-	}
-
-	*smallerPtr = *largerPtr = 0;
-	if (bestLength > 384)
-		return MIN(192, (U32)(bestLength - 384)); /* speed optimization */
-	if (matchEndIdx > curr + 8)
-		return matchEndIdx - curr - 8;
-	return 1;
-}
-
-static size_t ZSTD_insertBtAndFindBestMatch(ZSTD_CCtx *zc, const BYTE *const ip, const BYTE *const iend, size_t *offsetPtr, U32 nbCompares, const U32 mls,
-					    U32 extDict)
-{
-	U32 *const hashTable = zc->hashTable;
-	U32 const hashLog = zc->params.cParams.hashLog;
-	size_t const h = ZSTD_hashPtr(ip, hashLog, mls);
-	U32 *const bt = zc->chainTable;
-	U32 const btLog = zc->params.cParams.chainLog - 1;
-	U32 const btMask = (1 << btLog) - 1;
-	U32 matchIndex = hashTable[h];
-	size_t commonLengthSmaller = 0, commonLengthLarger = 0;
-	const BYTE *const base = zc->base;
-	const BYTE *const dictBase = zc->dictBase;
-	const U32 dictLimit = zc->dictLimit;
-	const BYTE *const dictEnd = dictBase + dictLimit;
-	const BYTE *const prefixStart = base + dictLimit;
-	const U32 curr = (U32)(ip - base);
-	const U32 btLow = btMask >= curr ? 0 : curr - btMask;
-	const U32 windowLow = zc->lowLimit;
-	U32 *smallerPtr = bt + 2 * (curr & btMask);
-	U32 *largerPtr = bt + 2 * (curr & btMask) + 1;
-	U32 matchEndIdx = curr + 8;
-	U32 dummy32; /* to be nullified at the end */
-	size_t bestLength = 0;
-
-	hashTable[h] = curr; /* Update Hash Table */
-
-	while (nbCompares-- && (matchIndex > windowLow)) {
-		U32 *const nextPtr = bt + 2 * (matchIndex & btMask);
-		size_t matchLength = MIN(commonLengthSmaller, commonLengthLarger); /* guaranteed minimum nb of common bytes */
-		const BYTE *match;
-
-		if ((!extDict) || (matchIndex + matchLength >= dictLimit)) {
-			match = base + matchIndex;
-			if (match[matchLength] == ip[matchLength])
-				matchLength += ZSTD_count(ip + matchLength + 1, match + matchLength + 1, iend) + 1;
-		} else {
-			match = dictBase + matchIndex;
-			matchLength += ZSTD_count_2segments(ip + matchLength, match + matchLength, iend, dictEnd, prefixStart);
-			if (matchIndex + matchLength >= dictLimit)
-				match = base + matchIndex; /* to prepare for next usage of match[matchLength] */
-		}
-
-		if (matchLength > bestLength) {
-			if (matchLength > matchEndIdx - matchIndex)
-				matchEndIdx = matchIndex + (U32)matchLength;
-			if ((4 * (int)(matchLength - bestLength)) > (int)(ZSTD_highbit32(curr - matchIndex + 1) - ZSTD_highbit32((U32)offsetPtr[0] + 1)))
-				bestLength = matchLength, *offsetPtr = ZSTD_REP_MOVE + curr - matchIndex;
-			if (ip + matchLength == iend) /* equal : no way to know if inf or sup */
-				break;		      /* drop, to guarantee consistency (miss a little bit of compression) */
-		}
-
-		if (match[matchLength] < ip[matchLength]) {
-			/* match is smaller than curr */
-			*smallerPtr = matchIndex;	  /* update smaller idx */
-			commonLengthSmaller = matchLength; /* all smaller will now have at least this guaranteed common length */
-			if (matchIndex <= btLow) {
-				smallerPtr = &dummy32;
-				break;
-			}			  /* beyond tree size, stop the search */
-			smallerPtr = nextPtr + 1; /* new "smaller" => larger of match */
-			matchIndex = nextPtr[1];  /* new matchIndex larger than previous (closer to curr) */
-		} else {
-			/* match is larger than curr */
-			*largerPtr = matchIndex;
-			commonLengthLarger = matchLength;
-			if (matchIndex <= btLow) {
-				largerPtr = &dummy32;
-				break;
-			} /* beyond tree size, stop the search */
-			largerPtr = nextPtr;
-			matchIndex = nextPtr[0];
-		}
-	}
-
-	*smallerPtr = *largerPtr = 0;
-
-	zc->nextToUpdate = (matchEndIdx > curr + 8) ? matchEndIdx - 8 : curr + 1;
-	return bestLength;
-}
-
-static void ZSTD_updateTree(ZSTD_CCtx *zc, const BYTE *const ip, const BYTE *const iend, const U32 nbCompares, const U32 mls)
-{
-	const BYTE *const base = zc->base;
-	const U32 target = (U32)(ip - base);
-	U32 idx = zc->nextToUpdate;
-
-	while (idx < target)
-		idx += ZSTD_insertBt1(zc, base + idx, mls, iend, nbCompares, 0);
-}
-
-/** ZSTD_BtFindBestMatch() : Tree updater, providing best match */
-static size_t ZSTD_BtFindBestMatch(ZSTD_CCtx *zc, const BYTE *const ip, const BYTE *const iLimit, size_t *offsetPtr, const U32 maxNbAttempts, const U32 mls)
-{
-	if (ip < zc->base + zc->nextToUpdate)
-		return 0; /* skipped area */
-	ZSTD_updateTree(zc, ip, iLimit, maxNbAttempts, mls);
-	return ZSTD_insertBtAndFindBestMatch(zc, ip, iLimit, offsetPtr, maxNbAttempts, mls, 0);
-}
-
-static size_t ZSTD_BtFindBestMatch_selectMLS(ZSTD_CCtx *zc, /* Index table will be updated */
-					     const BYTE *ip, const BYTE *const iLimit, size_t *offsetPtr, const U32 maxNbAttempts, const U32 matchLengthSearch)
-{
-	switch (matchLengthSearch) {
-	default: /* includes case 3 */
-	case 4: return ZSTD_BtFindBestMatch(zc, ip, iLimit, offsetPtr, maxNbAttempts, 4);
-	case 5: return ZSTD_BtFindBestMatch(zc, ip, iLimit, offsetPtr, maxNbAttempts, 5);
-	case 7:
-	case 6: return ZSTD_BtFindBestMatch(zc, ip, iLimit, offsetPtr, maxNbAttempts, 6);
-	}
-}
-
-static void ZSTD_updateTree_extDict(ZSTD_CCtx *zc, const BYTE *const ip, const BYTE *const iend, const U32 nbCompares, const U32 mls)
-{
-	const BYTE *const base = zc->base;
-	const U32 target = (U32)(ip - base);
-	U32 idx = zc->nextToUpdate;
-
-	while (idx < target)
-		idx += ZSTD_insertBt1(zc, base + idx, mls, iend, nbCompares, 1);
-}
-
-/** Tree updater, providing best match */
-static size_t ZSTD_BtFindBestMatch_extDict(ZSTD_CCtx *zc, const BYTE *const ip, const BYTE *const iLimit, size_t *offsetPtr, const U32 maxNbAttempts,
-					   const U32 mls)
-{
-	if (ip < zc->base + zc->nextToUpdate)
-		return 0; /* skipped area */
-	ZSTD_updateTree_extDict(zc, ip, iLimit, maxNbAttempts, mls);
-	return ZSTD_insertBtAndFindBestMatch(zc, ip, iLimit, offsetPtr, maxNbAttempts, mls, 1);
-}
-
-static size_t ZSTD_BtFindBestMatch_selectMLS_extDict(ZSTD_CCtx *zc, /* Index table will be updated */
-						     const BYTE *ip, const BYTE *const iLimit, size_t *offsetPtr, const U32 maxNbAttempts,
-						     const U32 matchLengthSearch)
-{
-	switch (matchLengthSearch) {
-	default: /* includes case 3 */
-	case 4: return ZSTD_BtFindBestMatch_extDict(zc, ip, iLimit, offsetPtr, maxNbAttempts, 4);
-	case 5: return ZSTD_BtFindBestMatch_extDict(zc, ip, iLimit, offsetPtr, maxNbAttempts, 5);
-	case 7:
-	case 6: return ZSTD_BtFindBestMatch_extDict(zc, ip, iLimit, offsetPtr, maxNbAttempts, 6);
-	}
-}
-
-/* *********************************
-*  Hash Chain
-***********************************/
-#define NEXT_IN_CHAIN(d, mask) chainTable[(d)&mask]
-
-/* Update chains up to ip (excluded)
-   Assumption : always within prefix (i.e. not within extDict) */
-FORCE_INLINE
-U32 ZSTD_insertAndFindFirstIndex(ZSTD_CCtx *zc, const BYTE *ip, U32 mls)
-{
-	U32 *const hashTable = zc->hashTable;
-	const U32 hashLog = zc->params.cParams.hashLog;
-	U32 *const chainTable = zc->chainTable;
-	const U32 chainMask = (1 << zc->params.cParams.chainLog) - 1;
-	const BYTE *const base = zc->base;
-	const U32 target = (U32)(ip - base);
-	U32 idx = zc->nextToUpdate;
-
-	while (idx < target) { /* catch up */
-		size_t const h = ZSTD_hashPtr(base + idx, hashLog, mls);
-		NEXT_IN_CHAIN(idx, chainMask) = hashTable[h];
-		hashTable[h] = idx;
-		idx++;
-	}
-
-	zc->nextToUpdate = target;
-	return hashTable[ZSTD_hashPtr(ip, hashLog, mls)];
-}
-
-/* inlining is important to hardwire a hot branch (template emulation) */
-FORCE_INLINE
-size_t ZSTD_HcFindBestMatch_generic(ZSTD_CCtx *zc, /* Index table will be updated */
-				    const BYTE *const ip, const BYTE *const iLimit, size_t *offsetPtr, const U32 maxNbAttempts, const U32 mls,
-				    const U32 extDict)
-{
-	U32 *const chainTable = zc->chainTable;
-	const U32 chainSize = (1 << zc->params.cParams.chainLog);
-	const U32 chainMask = chainSize - 1;
-	const BYTE *const base = zc->base;
-	const BYTE *const dictBase = zc->dictBase;
-	const U32 dictLimit = zc->dictLimit;
-	const BYTE *const prefixStart = base + dictLimit;
-	const BYTE *const dictEnd = dictBase + dictLimit;
-	const U32 lowLimit = zc->lowLimit;
-	const U32 curr = (U32)(ip - base);
-	const U32 minChain = curr > chainSize ? curr - chainSize : 0;
-	int nbAttempts = maxNbAttempts;
-	size_t ml = EQUAL_READ32 - 1;
-
-	/* HC4 match finder */
-	U32 matchIndex = ZSTD_insertAndFindFirstIndex(zc, ip, mls);
-
-	for (; (matchIndex > lowLimit) & (nbAttempts > 0); nbAttempts--) {
-		const BYTE *match;
-		size_t currMl = 0;
-		if ((!extDict) || matchIndex >= dictLimit) {
-			match = base + matchIndex;
-			if (match[ml] == ip[ml]) /* potentially better */
-				currMl = ZSTD_count(ip, match, iLimit);
-		} else {
-			match = dictBase + matchIndex;
-			if (ZSTD_read32(match) == ZSTD_read32(ip)) /* assumption : matchIndex <= dictLimit-4 (by table construction) */
-				currMl = ZSTD_count_2segments(ip + EQUAL_READ32, match + EQUAL_READ32, iLimit, dictEnd, prefixStart) + EQUAL_READ32;
-		}
-
-		/* save best solution */
-		if (currMl > ml) {
-			ml = currMl;
-			*offsetPtr = curr - matchIndex + ZSTD_REP_MOVE;
-			if (ip + currMl == iLimit)
-				break; /* best possible, and avoid read overflow*/
-		}
-
-		if (matchIndex <= minChain)
-			break;
-		matchIndex = NEXT_IN_CHAIN(matchIndex, chainMask);
-	}
-
-	return ml;
-}
-
-FORCE_INLINE size_t ZSTD_HcFindBestMatch_selectMLS(ZSTD_CCtx *zc, const BYTE *ip, const BYTE *const iLimit, size_t *offsetPtr, const U32 maxNbAttempts,
-						   const U32 matchLengthSearch)
-{
-	switch (matchLengthSearch) {
-	default: /* includes case 3 */
-	case 4: return ZSTD_HcFindBestMatch_generic(zc, ip, iLimit, offsetPtr, maxNbAttempts, 4, 0);
-	case 5: return ZSTD_HcFindBestMatch_generic(zc, ip, iLimit, offsetPtr, maxNbAttempts, 5, 0);
-	case 7:
-	case 6: return ZSTD_HcFindBestMatch_generic(zc, ip, iLimit, offsetPtr, maxNbAttempts, 6, 0);
-	}
-}
-
-FORCE_INLINE size_t ZSTD_HcFindBestMatch_extDict_selectMLS(ZSTD_CCtx *zc, const BYTE *ip, const BYTE *const iLimit, size_t *offsetPtr, const U32 maxNbAttempts,
-							   const U32 matchLengthSearch)
-{
-	switch (matchLengthSearch) {
-	default: /* includes case 3 */
-	case 4: return ZSTD_HcFindBestMatch_generic(zc, ip, iLimit, offsetPtr, maxNbAttempts, 4, 1);
-	case 5: return ZSTD_HcFindBestMatch_generic(zc, ip, iLimit, offsetPtr, maxNbAttempts, 5, 1);
-	case 7:
-	case 6: return ZSTD_HcFindBestMatch_generic(zc, ip, iLimit, offsetPtr, maxNbAttempts, 6, 1);
-	}
-}
-
-/* *******************************
-*  Common parser - lazy strategy
-*********************************/
-FORCE_INLINE
-void ZSTD_compressBlock_lazy_generic(ZSTD_CCtx *ctx, const void *src, size_t srcSize, const U32 searchMethod, const U32 depth)
-{
-	seqStore_t *seqStorePtr = &(ctx->seqStore);
-	const BYTE *const istart = (const BYTE *)src;
-	const BYTE *ip = istart;
-	const BYTE *anchor = istart;
-	const BYTE *const iend = istart + srcSize;
-	const BYTE *const ilimit = iend - 8;
-	const BYTE *const base = ctx->base + ctx->dictLimit;
-
-	U32 const maxSearches = 1 << ctx->params.cParams.searchLog;
-	U32 const mls = ctx->params.cParams.searchLength;
-
-	typedef size_t (*searchMax_f)(ZSTD_CCtx * zc, const BYTE *ip, const BYTE *iLimit, size_t *offsetPtr, U32 maxNbAttempts, U32 matchLengthSearch);
-	searchMax_f const searchMax = searchMethod ? ZSTD_BtFindBestMatch_selectMLS : ZSTD_HcFindBestMatch_selectMLS;
-	U32 offset_1 = ctx->rep[0], offset_2 = ctx->rep[1], savedOffset = 0;
-
-	/* init */
-	ip += (ip == base);
-	ctx->nextToUpdate3 = ctx->nextToUpdate;
-	{
-		U32 const maxRep = (U32)(ip - base);
-		if (offset_2 > maxRep)
-			savedOffset = offset_2, offset_2 = 0;
-		if (offset_1 > maxRep)
-			savedOffset = offset_1, offset_1 = 0;
-	}
-
-	/* Match Loop */
-	while (ip < ilimit) {
-		size_t matchLength = 0;
-		size_t offset = 0;
-		const BYTE *start = ip + 1;
-
-		/* check repCode */
-		if ((offset_1 > 0) & (ZSTD_read32(ip + 1) == ZSTD_read32(ip + 1 - offset_1))) {
-			/* repcode : we take it */
-			matchLength = ZSTD_count(ip + 1 + EQUAL_READ32, ip + 1 + EQUAL_READ32 - offset_1, iend) + EQUAL_READ32;
-			if (depth == 0)
-				goto _storeSequence;
-		}
-
-		/* first search (depth 0) */
-		{
-			size_t offsetFound = 99999999;
-			size_t const ml2 = searchMax(ctx, ip, iend, &offsetFound, maxSearches, mls);
-			if (ml2 > matchLength)
-				matchLength = ml2, start = ip, offset = offsetFound;
-		}
-
-		if (matchLength < EQUAL_READ32) {
-			ip += ((ip - anchor) >> g_searchStrength) + 1; /* jump faster over incompressible sections */
-			continue;
-		}
-
-		/* let's try to find a better solution */
-		if (depth >= 1)
-			while (ip < ilimit) {
-				ip++;
-				if ((offset) && ((offset_1 > 0) & (ZSTD_read32(ip) == ZSTD_read32(ip - offset_1)))) {
-					size_t const mlRep = ZSTD_count(ip + EQUAL_READ32, ip + EQUAL_READ32 - offset_1, iend) + EQUAL_READ32;
-					int const gain2 = (int)(mlRep * 3);
-					int const gain1 = (int)(matchLength * 3 - ZSTD_highbit32((U32)offset + 1) + 1);
-					if ((mlRep >= EQUAL_READ32) && (gain2 > gain1))
-						matchLength = mlRep, offset = 0, start = ip;
-				}
-				{
-					size_t offset2 = 99999999;
-					size_t const ml2 = searchMax(ctx, ip, iend, &offset2, maxSearches, mls);
-					int const gain2 = (int)(ml2 * 4 - ZSTD_highbit32((U32)offset2 + 1)); /* raw approx */
-					int const gain1 = (int)(matchLength * 4 - ZSTD_highbit32((U32)offset + 1) + 4);
-					if ((ml2 >= EQUAL_READ32) && (gain2 > gain1)) {
-						matchLength = ml2, offset = offset2, start = ip;
-						continue; /* search a better one */
-					}
-				}
-
-				/* let's find an even better one */
-				if ((depth == 2) && (ip < ilimit)) {
-					ip++;
-					if ((offset) && ((offset_1 > 0) & (ZSTD_read32(ip) == ZSTD_read32(ip - offset_1)))) {
-						size_t const ml2 = ZSTD_count(ip + EQUAL_READ32, ip + EQUAL_READ32 - offset_1, iend) + EQUAL_READ32;
-						int const gain2 = (int)(ml2 * 4);
-						int const gain1 = (int)(matchLength * 4 - ZSTD_highbit32((U32)offset + 1) + 1);
-						if ((ml2 >= EQUAL_READ32) && (gain2 > gain1))
-							matchLength = ml2, offset = 0, start = ip;
-					}
-					{
-						size_t offset2 = 99999999;
-						size_t const ml2 = searchMax(ctx, ip, iend, &offset2, maxSearches, mls);
-						int const gain2 = (int)(ml2 * 4 - ZSTD_highbit32((U32)offset2 + 1)); /* raw approx */
-						int const gain1 = (int)(matchLength * 4 - ZSTD_highbit32((U32)offset + 1) + 7);
-						if ((ml2 >= EQUAL_READ32) && (gain2 > gain1)) {
-							matchLength = ml2, offset = offset2, start = ip;
-							continue;
-						}
-					}
-				}
-				break; /* nothing found : store previous solution */
-			}
-
-		/* NOTE:
-		 * start[-offset+ZSTD_REP_MOVE-1] is undefined behavior.
-		 * (-offset+ZSTD_REP_MOVE-1) is unsigned, and is added to start, which
-		 * overflows the pointer, which is undefined behavior.
-		 */
-		/* catch up */
-		if (offset) {
-			while ((start > anchor) && (start > base + offset - ZSTD_REP_MOVE) &&
-			       (start[-1] == (start-offset+ZSTD_REP_MOVE)[-1])) /* only search for offset within prefix */
-			{
-				start--;
-				matchLength++;
-			}
-			offset_2 = offset_1;
-			offset_1 = (U32)(offset - ZSTD_REP_MOVE);
-		}
-
-	/* store sequence */
-_storeSequence:
-		{
-			size_t const litLength = start - anchor;
-			ZSTD_storeSeq(seqStorePtr, litLength, anchor, (U32)offset, matchLength - MINMATCH);
-			anchor = ip = start + matchLength;
-		}
-
-		/* check immediate repcode */
-		while ((ip <= ilimit) && ((offset_2 > 0) & (ZSTD_read32(ip) == ZSTD_read32(ip - offset_2)))) {
-			/* store sequence */
-			matchLength = ZSTD_count(ip + EQUAL_READ32, ip + EQUAL_READ32 - offset_2, iend) + EQUAL_READ32;
-			offset = offset_2;
-			offset_2 = offset_1;
-			offset_1 = (U32)offset; /* swap repcodes */
-			ZSTD_storeSeq(seqStorePtr, 0, anchor, 0, matchLength - MINMATCH);
-			ip += matchLength;
-			anchor = ip;
-			continue; /* faster when present ... (?) */
-		}
-	}
-
-	/* Save reps for next block */
-	ctx->repToConfirm[0] = offset_1 ? offset_1 : savedOffset;
-	ctx->repToConfirm[1] = offset_2 ? offset_2 : savedOffset;
-
-	/* Last Literals */
-	{
-		size_t const lastLLSize = iend - anchor;
-		memcpy(seqStorePtr->lit, anchor, lastLLSize);
-		seqStorePtr->lit += lastLLSize;
-	}
-}
-
-static void ZSTD_compressBlock_btlazy2(ZSTD_CCtx *ctx, const void *src, size_t srcSize) { ZSTD_compressBlock_lazy_generic(ctx, src, srcSize, 1, 2); }
-
-static void ZSTD_compressBlock_lazy2(ZSTD_CCtx *ctx, const void *src, size_t srcSize) { ZSTD_compressBlock_lazy_generic(ctx, src, srcSize, 0, 2); }
-
-static void ZSTD_compressBlock_lazy(ZSTD_CCtx *ctx, const void *src, size_t srcSize) { ZSTD_compressBlock_lazy_generic(ctx, src, srcSize, 0, 1); }
-
-static void ZSTD_compressBlock_greedy(ZSTD_CCtx *ctx, const void *src, size_t srcSize) { ZSTD_compressBlock_lazy_generic(ctx, src, srcSize, 0, 0); }
-
-FORCE_INLINE
-void ZSTD_compressBlock_lazy_extDict_generic(ZSTD_CCtx *ctx, const void *src, size_t srcSize, const U32 searchMethod, const U32 depth)
-{
-	seqStore_t *seqStorePtr = &(ctx->seqStore);
-	const BYTE *const istart = (const BYTE *)src;
-	const BYTE *ip = istart;
-	const BYTE *anchor = istart;
-	const BYTE *const iend = istart + srcSize;
-	const BYTE *const ilimit = iend - 8;
-	const BYTE *const base = ctx->base;
-	const U32 dictLimit = ctx->dictLimit;
-	const U32 lowestIndex = ctx->lowLimit;
-	const BYTE *const prefixStart = base + dictLimit;
-	const BYTE *const dictBase = ctx->dictBase;
-	const BYTE *const dictEnd = dictBase + dictLimit;
-	const BYTE *const dictStart = dictBase + ctx->lowLimit;
-
-	const U32 maxSearches = 1 << ctx->params.cParams.searchLog;
-	const U32 mls = ctx->params.cParams.searchLength;
-
-	typedef size_t (*searchMax_f)(ZSTD_CCtx * zc, const BYTE *ip, const BYTE *iLimit, size_t *offsetPtr, U32 maxNbAttempts, U32 matchLengthSearch);
-	searchMax_f searchMax = searchMethod ? ZSTD_BtFindBestMatch_selectMLS_extDict : ZSTD_HcFindBestMatch_extDict_selectMLS;
-
-	U32 offset_1 = ctx->rep[0], offset_2 = ctx->rep[1];
-
-	/* init */
-	ctx->nextToUpdate3 = ctx->nextToUpdate;
-	ip += (ip == prefixStart);
-
-	/* Match Loop */
-	while (ip < ilimit) {
-		size_t matchLength = 0;
-		size_t offset = 0;
-		const BYTE *start = ip + 1;
-		U32 curr = (U32)(ip - base);
-
-		/* check repCode */
-		{
-			const U32 repIndex = (U32)(curr + 1 - offset_1);
-			const BYTE *const repBase = repIndex < dictLimit ? dictBase : base;
-			const BYTE *const repMatch = repBase + repIndex;
-			if (((U32)((dictLimit - 1) - repIndex) >= 3) & (repIndex > lowestIndex)) /* intentional overflow */
-				if (ZSTD_read32(ip + 1) == ZSTD_read32(repMatch)) {
-					/* repcode detected we should take it */
-					const BYTE *const repEnd = repIndex < dictLimit ? dictEnd : iend;
-					matchLength =
-					    ZSTD_count_2segments(ip + 1 + EQUAL_READ32, repMatch + EQUAL_READ32, iend, repEnd, prefixStart) + EQUAL_READ32;
-					if (depth == 0)
-						goto _storeSequence;
-				}
-		}
-
-		/* first search (depth 0) */
-		{
-			size_t offsetFound = 99999999;
-			size_t const ml2 = searchMax(ctx, ip, iend, &offsetFound, maxSearches, mls);
-			if (ml2 > matchLength)
-				matchLength = ml2, start = ip, offset = offsetFound;
-		}
-
-		if (matchLength < EQUAL_READ32) {
-			ip += ((ip - anchor) >> g_searchStrength) + 1; /* jump faster over incompressible sections */
-			continue;
-		}
-
-		/* let's try to find a better solution */
-		if (depth >= 1)
-			while (ip < ilimit) {
-				ip++;
-				curr++;
-				/* check repCode */
-				if (offset) {
-					const U32 repIndex = (U32)(curr - offset_1);
-					const BYTE *const repBase = repIndex < dictLimit ? dictBase : base;
-					const BYTE *const repMatch = repBase + repIndex;
-					if (((U32)((dictLimit - 1) - repIndex) >= 3) & (repIndex > lowestIndex)) /* intentional overflow */
-						if (ZSTD_read32(ip) == ZSTD_read32(repMatch)) {
-							/* repcode detected */
-							const BYTE *const repEnd = repIndex < dictLimit ? dictEnd : iend;
-							size_t const repLength =
-							    ZSTD_count_2segments(ip + EQUAL_READ32, repMatch + EQUAL_READ32, iend, repEnd, prefixStart) +
-							    EQUAL_READ32;
-							int const gain2 = (int)(repLength * 3);
-							int const gain1 = (int)(matchLength * 3 - ZSTD_highbit32((U32)offset + 1) + 1);
-							if ((repLength >= EQUAL_READ32) && (gain2 > gain1))
-								matchLength = repLength, offset = 0, start = ip;
-						}
-				}
-
-				/* search match, depth 1 */
-				{
-					size_t offset2 = 99999999;
-					size_t const ml2 = searchMax(ctx, ip, iend, &offset2, maxSearches, mls);
-					int const gain2 = (int)(ml2 * 4 - ZSTD_highbit32((U32)offset2 + 1)); /* raw approx */
-					int const gain1 = (int)(matchLength * 4 - ZSTD_highbit32((U32)offset + 1) + 4);
-					if ((ml2 >= EQUAL_READ32) && (gain2 > gain1)) {
-						matchLength = ml2, offset = offset2, start = ip;
-						continue; /* search a better one */
-					}
-				}
-
-				/* let's find an even better one */
-				if ((depth == 2) && (ip < ilimit)) {
-					ip++;
-					curr++;
-					/* check repCode */
-					if (offset) {
-						const U32 repIndex = (U32)(curr - offset_1);
-						const BYTE *const repBase = repIndex < dictLimit ? dictBase : base;
-						const BYTE *const repMatch = repBase + repIndex;
-						if (((U32)((dictLimit - 1) - repIndex) >= 3) & (repIndex > lowestIndex)) /* intentional overflow */
-							if (ZSTD_read32(ip) == ZSTD_read32(repMatch)) {
-								/* repcode detected */
-								const BYTE *const repEnd = repIndex < dictLimit ? dictEnd : iend;
-								size_t repLength = ZSTD_count_2segments(ip + EQUAL_READ32, repMatch + EQUAL_READ32, iend,
-													repEnd, prefixStart) +
-										   EQUAL_READ32;
-								int gain2 = (int)(repLength * 4);
-								int gain1 = (int)(matchLength * 4 - ZSTD_highbit32((U32)offset + 1) + 1);
-								if ((repLength >= EQUAL_READ32) && (gain2 > gain1))
-									matchLength = repLength, offset = 0, start = ip;
-							}
-					}
-
-					/* search match, depth 2 */
-					{
-						size_t offset2 = 99999999;
-						size_t const ml2 = searchMax(ctx, ip, iend, &offset2, maxSearches, mls);
-						int const gain2 = (int)(ml2 * 4 - ZSTD_highbit32((U32)offset2 + 1)); /* raw approx */
-						int const gain1 = (int)(matchLength * 4 - ZSTD_highbit32((U32)offset + 1) + 7);
-						if ((ml2 >= EQUAL_READ32) && (gain2 > gain1)) {
-							matchLength = ml2, offset = offset2, start = ip;
-							continue;
-						}
-					}
-				}
-				break; /* nothing found : store previous solution */
-			}
-
-		/* catch up */
-		if (offset) {
-			U32 const matchIndex = (U32)((start - base) - (offset - ZSTD_REP_MOVE));
-			const BYTE *match = (matchIndex < dictLimit) ? dictBase + matchIndex : base + matchIndex;
-			const BYTE *const mStart = (matchIndex < dictLimit) ? dictStart : prefixStart;
-			while ((start > anchor) && (match > mStart) && (start[-1] == match[-1])) {
-				start--;
-				match--;
-				matchLength++;
-			} /* catch up */
-			offset_2 = offset_1;
-			offset_1 = (U32)(offset - ZSTD_REP_MOVE);
-		}
-
-	/* store sequence */
-	_storeSequence : {
-		size_t const litLength = start - anchor;
-		ZSTD_storeSeq(seqStorePtr, litLength, anchor, (U32)offset, matchLength - MINMATCH);
-		anchor = ip = start + matchLength;
-	}
-
-		/* check immediate repcode */
-		while (ip <= ilimit) {
-			const U32 repIndex = (U32)((ip - base) - offset_2);
-			const BYTE *const repBase = repIndex < dictLimit ? dictBase : base;
-			const BYTE *const repMatch = repBase + repIndex;
-			if (((U32)((dictLimit - 1) - repIndex) >= 3) & (repIndex > lowestIndex)) /* intentional overflow */
-				if (ZSTD_read32(ip) == ZSTD_read32(repMatch)) {
-					/* repcode detected we should take it */
-					const BYTE *const repEnd = repIndex < dictLimit ? dictEnd : iend;
-					matchLength =
-					    ZSTD_count_2segments(ip + EQUAL_READ32, repMatch + EQUAL_READ32, iend, repEnd, prefixStart) + EQUAL_READ32;
-					offset = offset_2;
-					offset_2 = offset_1;
-					offset_1 = (U32)offset; /* swap offset history */
-					ZSTD_storeSeq(seqStorePtr, 0, anchor, 0, matchLength - MINMATCH);
-					ip += matchLength;
-					anchor = ip;
-					continue; /* faster when present ... (?) */
-				}
-			break;
-		}
-	}
-
-	/* Save reps for next block */
-	ctx->repToConfirm[0] = offset_1;
-	ctx->repToConfirm[1] = offset_2;
-
-	/* Last Literals */
-	{
-		size_t const lastLLSize = iend - anchor;
-		memcpy(seqStorePtr->lit, anchor, lastLLSize);
-		seqStorePtr->lit += lastLLSize;
-	}
-}
-
-void ZSTD_compressBlock_greedy_extDict(ZSTD_CCtx *ctx, const void *src, size_t srcSize) { ZSTD_compressBlock_lazy_extDict_generic(ctx, src, srcSize, 0, 0); }
-
-static void ZSTD_compressBlock_lazy_extDict(ZSTD_CCtx *ctx, const void *src, size_t srcSize)
-{
-	ZSTD_compressBlock_lazy_extDict_generic(ctx, src, srcSize, 0, 1);
-}
-
-static void ZSTD_compressBlock_lazy2_extDict(ZSTD_CCtx *ctx, const void *src, size_t srcSize)
-{
-	ZSTD_compressBlock_lazy_extDict_generic(ctx, src, srcSize, 0, 2);
-}
-
-static void ZSTD_compressBlock_btlazy2_extDict(ZSTD_CCtx *ctx, const void *src, size_t srcSize)
-{
-	ZSTD_compressBlock_lazy_extDict_generic(ctx, src, srcSize, 1, 2);
-}
-
-/* The optimal parser */
-#include "zstd_opt.h"
-
-static void ZSTD_compressBlock_btopt(ZSTD_CCtx *ctx, const void *src, size_t srcSize)
-{
-#ifdef ZSTD_OPT_H_91842398743
-	ZSTD_compressBlock_opt_generic(ctx, src, srcSize, 0);
-#else
-	(void)ctx;
-	(void)src;
-	(void)srcSize;
-	return;
-#endif
-}
-
-static void ZSTD_compressBlock_btopt2(ZSTD_CCtx *ctx, const void *src, size_t srcSize)
-{
-#ifdef ZSTD_OPT_H_91842398743
-	ZSTD_compressBlock_opt_generic(ctx, src, srcSize, 1);
-#else
-	(void)ctx;
-	(void)src;
-	(void)srcSize;
-	return;
-#endif
-}
-
-static void ZSTD_compressBlock_btopt_extDict(ZSTD_CCtx *ctx, const void *src, size_t srcSize)
-{
-#ifdef ZSTD_OPT_H_91842398743
-	ZSTD_compressBlock_opt_extDict_generic(ctx, src, srcSize, 0);
-#else
-	(void)ctx;
-	(void)src;
-	(void)srcSize;
-	return;
-#endif
-}
-
-static void ZSTD_compressBlock_btopt2_extDict(ZSTD_CCtx *ctx, const void *src, size_t srcSize)
-{
-#ifdef ZSTD_OPT_H_91842398743
-	ZSTD_compressBlock_opt_extDict_generic(ctx, src, srcSize, 1);
-#else
-	(void)ctx;
-	(void)src;
-	(void)srcSize;
-	return;
-#endif
-}
-
-typedef void (*ZSTD_blockCompressor)(ZSTD_CCtx *ctx, const void *src, size_t srcSize);
-
-static ZSTD_blockCompressor ZSTD_selectBlockCompressor(ZSTD_strategy strat, int extDict)
-{
-	static const ZSTD_blockCompressor blockCompressor[2][8] = {
-	    {ZSTD_compressBlock_fast, ZSTD_compressBlock_doubleFast, ZSTD_compressBlock_greedy, ZSTD_compressBlock_lazy, ZSTD_compressBlock_lazy2,
-	     ZSTD_compressBlock_btlazy2, ZSTD_compressBlock_btopt, ZSTD_compressBlock_btopt2},
-	    {ZSTD_compressBlock_fast_extDict, ZSTD_compressBlock_doubleFast_extDict, ZSTD_compressBlock_greedy_extDict, ZSTD_compressBlock_lazy_extDict,
-	     ZSTD_compressBlock_lazy2_extDict, ZSTD_compressBlock_btlazy2_extDict, ZSTD_compressBlock_btopt_extDict, ZSTD_compressBlock_btopt2_extDict}};
-
-	return blockCompressor[extDict][(U32)strat];
-}
-
-static size_t ZSTD_compressBlock_internal(ZSTD_CCtx *zc, void *dst, size_t dstCapacity, const void *src, size_t srcSize)
-{
-	ZSTD_blockCompressor const blockCompressor = ZSTD_selectBlockCompressor(zc->params.cParams.strategy, zc->lowLimit < zc->dictLimit);
-	const BYTE *const base = zc->base;
-	const BYTE *const istart = (const BYTE *)src;
-	const U32 curr = (U32)(istart - base);
-	if (srcSize < MIN_CBLOCK_SIZE + ZSTD_blockHeaderSize + 1)
-		return 0; /* don't even attempt compression below a certain srcSize */
-	ZSTD_resetSeqStore(&(zc->seqStore));
-	if (curr > zc->nextToUpdate + 384)
-		zc->nextToUpdate = curr - MIN(192, (U32)(curr - zc->nextToUpdate - 384)); /* update tree not updated after finding very long rep matches */
-	blockCompressor(zc, src, srcSize);
-	return ZSTD_compressSequences(zc, dst, dstCapacity, srcSize);
-}
-
-/*! ZSTD_compress_generic() :
-*   Compress a chunk of data into one or multiple blocks.
-*   All blocks will be terminated, all input will be consumed.
-*   Function will issue an error if there is not enough `dstCapacity` to hold the compressed content.
-*   Frame is supposed already started (header already produced)
-*   @return : compressed size, or an error code
-*/
-static size_t ZSTD_compress_generic(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity, const void *src, size_t srcSize, U32 lastFrameChunk)
-{
-	size_t blockSize = cctx->blockSize;
-	size_t remaining = srcSize;
-	const BYTE *ip = (const BYTE *)src;
-	BYTE *const ostart = (BYTE *)dst;
-	BYTE *op = ostart;
-	U32 const maxDist = 1 << cctx->params.cParams.windowLog;
-
-	if (cctx->params.fParams.checksumFlag && srcSize)
-		xxh64_update(&cctx->xxhState, src, srcSize);
-
-	while (remaining) {
-		U32 const lastBlock = lastFrameChunk & (blockSize >= remaining);
-		size_t cSize;
-
-		if (dstCapacity < ZSTD_blockHeaderSize + MIN_CBLOCK_SIZE)
-			return ERROR(dstSize_tooSmall); /* not enough space to store compressed block */
-		if (remaining < blockSize)
-			blockSize = remaining;
-
-		/* preemptive overflow correction */
-		if (cctx->lowLimit > (3U << 29)) {
-			U32 const cycleMask = (1 << ZSTD_cycleLog(cctx->params.cParams.hashLog, cctx->params.cParams.strategy)) - 1;
-			U32 const curr = (U32)(ip - cctx->base);
-			U32 const newCurr = (curr & cycleMask) + (1 << cctx->params.cParams.windowLog);
-			U32 const correction = curr - newCurr;
-			ZSTD_STATIC_ASSERT(ZSTD_WINDOWLOG_MAX_64 <= 30);
-			ZSTD_reduceIndex(cctx, correction);
-			cctx->base += correction;
-			cctx->dictBase += correction;
-			cctx->lowLimit -= correction;
-			cctx->dictLimit -= correction;
-			if (cctx->nextToUpdate < correction)
-				cctx->nextToUpdate = 0;
-			else
-				cctx->nextToUpdate -= correction;
-		}
-
-		if ((U32)(ip + blockSize - cctx->base) > cctx->loadedDictEnd + maxDist) {
-			/* enforce maxDist */
-			U32 const newLowLimit = (U32)(ip + blockSize - cctx->base) - maxDist;
-			if (cctx->lowLimit < newLowLimit)
-				cctx->lowLimit = newLowLimit;
-			if (cctx->dictLimit < cctx->lowLimit)
-				cctx->dictLimit = cctx->lowLimit;
-		}
-
-		cSize = ZSTD_compressBlock_internal(cctx, op + ZSTD_blockHeaderSize, dstCapacity - ZSTD_blockHeaderSize, ip, blockSize);
-		if (ZSTD_isError(cSize))
-			return cSize;
-
-		if (cSize == 0) { /* block is not compressible */
-			U32 const cBlockHeader24 = lastBlock + (((U32)bt_raw) << 1) + (U32)(blockSize << 3);
-			if (blockSize + ZSTD_blockHeaderSize > dstCapacity)
-				return ERROR(dstSize_tooSmall);
-			ZSTD_writeLE32(op, cBlockHeader24); /* no pb, 4th byte will be overwritten */
-			memcpy(op + ZSTD_blockHeaderSize, ip, blockSize);
-			cSize = ZSTD_blockHeaderSize + blockSize;
-		} else {
-			U32 const cBlockHeader24 = lastBlock + (((U32)bt_compressed) << 1) + (U32)(cSize << 3);
-			ZSTD_writeLE24(op, cBlockHeader24);
-			cSize += ZSTD_blockHeaderSize;
-		}
-
-		remaining -= blockSize;
-		dstCapacity -= cSize;
-		ip += blockSize;
-		op += cSize;
-	}
-
-	if (lastFrameChunk && (op > ostart))
-		cctx->stage = ZSTDcs_ending;
-	return op - ostart;
-}
-
-static size_t ZSTD_writeFrameHeader(void *dst, size_t dstCapacity, ZSTD_parameters params, U64 pledgedSrcSize, U32 dictID)
-{
-	BYTE *const op = (BYTE *)dst;
-	U32 const dictIDSizeCode = (dictID > 0) + (dictID >= 256) + (dictID >= 65536); /* 0-3 */
-	U32 const checksumFlag = params.fParams.checksumFlag > 0;
-	U32 const windowSize = 1U << params.cParams.windowLog;
-	U32 const singleSegment = params.fParams.contentSizeFlag && (windowSize >= pledgedSrcSize);
-	BYTE const windowLogByte = (BYTE)((params.cParams.windowLog - ZSTD_WINDOWLOG_ABSOLUTEMIN) << 3);
-	U32 const fcsCode =
-	    params.fParams.contentSizeFlag ? (pledgedSrcSize >= 256) + (pledgedSrcSize >= 65536 + 256) + (pledgedSrcSize >= 0xFFFFFFFFU) : 0; /* 0-3 */
-	BYTE const frameHeaderDecriptionByte = (BYTE)(dictIDSizeCode + (checksumFlag << 2) + (singleSegment << 5) + (fcsCode << 6));
-	size_t pos;
-
-	if (dstCapacity < ZSTD_frameHeaderSize_max)
-		return ERROR(dstSize_tooSmall);
-
-	ZSTD_writeLE32(dst, ZSTD_MAGICNUMBER);
-	op[4] = frameHeaderDecriptionByte;
-	pos = 5;
-	if (!singleSegment)
-		op[pos++] = windowLogByte;
-	switch (dictIDSizeCode) {
-	default: /* impossible */
-	case 0: break;
-	case 1:
-		op[pos] = (BYTE)(dictID);
-		pos++;
-		break;
-	case 2:
-		ZSTD_writeLE16(op + pos, (U16)dictID);
-		pos += 2;
-		break;
-	case 3:
-		ZSTD_writeLE32(op + pos, dictID);
-		pos += 4;
-		break;
-	}
-	switch (fcsCode) {
-	default: /* impossible */
-	case 0:
-		if (singleSegment)
-			op[pos++] = (BYTE)(pledgedSrcSize);
-		break;
-	case 1:
-		ZSTD_writeLE16(op + pos, (U16)(pledgedSrcSize - 256));
-		pos += 2;
-		break;
-	case 2:
-		ZSTD_writeLE32(op + pos, (U32)(pledgedSrcSize));
-		pos += 4;
-		break;
-	case 3:
-		ZSTD_writeLE64(op + pos, (U64)(pledgedSrcSize));
-		pos += 8;
-		break;
-	}
-	return pos;
-}
-
-static size_t ZSTD_compressContinue_internal(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity, const void *src, size_t srcSize, U32 frame, U32 lastFrameChunk)
-{
-	const BYTE *const ip = (const BYTE *)src;
-	size_t fhSize = 0;
-
-	if (cctx->stage == ZSTDcs_created)
-		return ERROR(stage_wrong); /* missing init (ZSTD_compressBegin) */
-
-	if (frame && (cctx->stage == ZSTDcs_init)) {
-		fhSize = ZSTD_writeFrameHeader(dst, dstCapacity, cctx->params, cctx->frameContentSize, cctx->dictID);
-		if (ZSTD_isError(fhSize))
-			return fhSize;
-		dstCapacity -= fhSize;
-		dst = (char *)dst + fhSize;
-		cctx->stage = ZSTDcs_ongoing;
-	}
-
-	/* Check if blocks follow each other */
-	if (src != cctx->nextSrc) {
-		/* not contiguous */
-		ptrdiff_t const delta = cctx->nextSrc - ip;
-		cctx->lowLimit = cctx->dictLimit;
-		cctx->dictLimit = (U32)(cctx->nextSrc - cctx->base);
-		cctx->dictBase = cctx->base;
-		cctx->base -= delta;
-		cctx->nextToUpdate = cctx->dictLimit;
-		if (cctx->dictLimit - cctx->lowLimit < HASH_READ_SIZE)
-			cctx->lowLimit = cctx->dictLimit; /* too small extDict */
-	}
-
-	/* if input and dictionary overlap : reduce dictionary (area presumed modified by input) */
-	if ((ip + srcSize > cctx->dictBase + cctx->lowLimit) & (ip < cctx->dictBase + cctx->dictLimit)) {
-		ptrdiff_t const highInputIdx = (ip + srcSize) - cctx->dictBase;
-		U32 const lowLimitMax = (highInputIdx > (ptrdiff_t)cctx->dictLimit) ? cctx->dictLimit : (U32)highInputIdx;
-		cctx->lowLimit = lowLimitMax;
-	}
-
-	cctx->nextSrc = ip + srcSize;
-
-	if (srcSize) {
-		size_t const cSize = frame ? ZSTD_compress_generic(cctx, dst, dstCapacity, src, srcSize, lastFrameChunk)
-					   : ZSTD_compressBlock_internal(cctx, dst, dstCapacity, src, srcSize);
-		if (ZSTD_isError(cSize))
-			return cSize;
-		return cSize + fhSize;
-	} else
-		return fhSize;
-}
-
-size_t ZSTD_compressContinue(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity, const void *src, size_t srcSize)
-{
-	return ZSTD_compressContinue_internal(cctx, dst, dstCapacity, src, srcSize, 1, 0);
-}
-
-size_t ZSTD_getBlockSizeMax(ZSTD_CCtx *cctx) { return MIN(ZSTD_BLOCKSIZE_ABSOLUTEMAX, 1 << cctx->params.cParams.windowLog); }
-
-size_t ZSTD_compressBlock(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity, const void *src, size_t srcSize)
-{
-	size_t const blockSizeMax = ZSTD_getBlockSizeMax(cctx);
-	if (srcSize > blockSizeMax)
-		return ERROR(srcSize_wrong);
-	return ZSTD_compressContinue_internal(cctx, dst, dstCapacity, src, srcSize, 0, 0);
-}
-
-/*! ZSTD_loadDictionaryContent() :
- *  @return : 0, or an error code
- */
-static size_t ZSTD_loadDictionaryContent(ZSTD_CCtx *zc, const void *src, size_t srcSize)
-{
-	const BYTE *const ip = (const BYTE *)src;
-	const BYTE *const iend = ip + srcSize;
-
-	/* input becomes curr prefix */
-	zc->lowLimit = zc->dictLimit;
-	zc->dictLimit = (U32)(zc->nextSrc - zc->base);
-	zc->dictBase = zc->base;
-	zc->base += ip - zc->nextSrc;
-	zc->nextToUpdate = zc->dictLimit;
-	zc->loadedDictEnd = zc->forceWindow ? 0 : (U32)(iend - zc->base);
-
-	zc->nextSrc = iend;
-	if (srcSize <= HASH_READ_SIZE)
-		return 0;
-
-	switch (zc->params.cParams.strategy) {
-	case ZSTD_fast: ZSTD_fillHashTable(zc, iend, zc->params.cParams.searchLength); break;
-
-	case ZSTD_dfast: ZSTD_fillDoubleHashTable(zc, iend, zc->params.cParams.searchLength); break;
-
-	case ZSTD_greedy:
-	case ZSTD_lazy:
-	case ZSTD_lazy2:
-		if (srcSize >= HASH_READ_SIZE)
-			ZSTD_insertAndFindFirstIndex(zc, iend - HASH_READ_SIZE, zc->params.cParams.searchLength);
-		break;
-
-	case ZSTD_btlazy2:
-	case ZSTD_btopt:
-	case ZSTD_btopt2:
-		if (srcSize >= HASH_READ_SIZE)
-			ZSTD_updateTree(zc, iend - HASH_READ_SIZE, iend, 1 << zc->params.cParams.searchLog, zc->params.cParams.searchLength);
-		break;
-
-	default:
-		return ERROR(GENERIC); /* strategy doesn't exist; impossible */
-	}
-
-	zc->nextToUpdate = (U32)(iend - zc->base);
-	return 0;
-}
-
-/* Dictionaries that assign zero probability to symbols that show up causes problems
-   when FSE encoding.  Refuse dictionaries that assign zero probability to symbols
-   that we may encounter during compression.
-   NOTE: This behavior is not standard and could be improved in the future. */
-static size_t ZSTD_checkDictNCount(short *normalizedCounter, unsigned dictMaxSymbolValue, unsigned maxSymbolValue)
-{
-	U32 s;
-	if (dictMaxSymbolValue < maxSymbolValue)
-		return ERROR(dictionary_corrupted);
-	for (s = 0; s <= maxSymbolValue; ++s) {
-		if (normalizedCounter[s] == 0)
-			return ERROR(dictionary_corrupted);
-	}
-	return 0;
-}
-
-/* Dictionary format :
- * See :
- * https://github.com/facebook/zstd/blob/master/doc/zstd_compression_format.md#dictionary-format
- */
-/*! ZSTD_loadZstdDictionary() :
- * @return : 0, or an error code
- *  assumptions : magic number supposed already checked
- *                dictSize supposed > 8
- */
-static size_t ZSTD_loadZstdDictionary(ZSTD_CCtx *cctx, const void *dict, size_t dictSize)
-{
-	const BYTE *dictPtr = (const BYTE *)dict;
-	const BYTE *const dictEnd = dictPtr + dictSize;
-	short offcodeNCount[MaxOff + 1];
-	unsigned offcodeMaxValue = MaxOff;
-
-	dictPtr += 4; /* skip magic number */
-	cctx->dictID = cctx->params.fParams.noDictIDFlag ? 0 : ZSTD_readLE32(dictPtr);
-	dictPtr += 4;
-
-	{
-		size_t const hufHeaderSize = HUF_readCTable_wksp(cctx->hufTable, 255, dictPtr, dictEnd - dictPtr, cctx->tmpCounters, sizeof(cctx->tmpCounters));
-		if (HUF_isError(hufHeaderSize))
-			return ERROR(dictionary_corrupted);
-		dictPtr += hufHeaderSize;
-	}
-
-	{
-		unsigned offcodeLog;
-		size_t const offcodeHeaderSize = FSE_readNCount(offcodeNCount, &offcodeMaxValue, &offcodeLog, dictPtr, dictEnd - dictPtr);
-		if (FSE_isError(offcodeHeaderSize))
-			return ERROR(dictionary_corrupted);
-		if (offcodeLog > OffFSELog)
-			return ERROR(dictionary_corrupted);
-		/* Defer checking offcodeMaxValue because we need to know the size of the dictionary content */
-		CHECK_E(FSE_buildCTable_wksp(cctx->offcodeCTable, offcodeNCount, offcodeMaxValue, offcodeLog, cctx->tmpCounters, sizeof(cctx->tmpCounters)),
-			dictionary_corrupted);
-		dictPtr += offcodeHeaderSize;
-	}
-
-	{
-		short matchlengthNCount[MaxML + 1];
-		unsigned matchlengthMaxValue = MaxML, matchlengthLog;
-		size_t const matchlengthHeaderSize = FSE_readNCount(matchlengthNCount, &matchlengthMaxValue, &matchlengthLog, dictPtr, dictEnd - dictPtr);
-		if (FSE_isError(matchlengthHeaderSize))
-			return ERROR(dictionary_corrupted);
-		if (matchlengthLog > MLFSELog)
-			return ERROR(dictionary_corrupted);
-		/* Every match length code must have non-zero probability */
-		CHECK_F(ZSTD_checkDictNCount(matchlengthNCount, matchlengthMaxValue, MaxML));
-		CHECK_E(
-		    FSE_buildCTable_wksp(cctx->matchlengthCTable, matchlengthNCount, matchlengthMaxValue, matchlengthLog, cctx->tmpCounters, sizeof(cctx->tmpCounters)),
-		    dictionary_corrupted);
-		dictPtr += matchlengthHeaderSize;
-	}
-
-	{
-		short litlengthNCount[MaxLL + 1];
-		unsigned litlengthMaxValue = MaxLL, litlengthLog;
-		size_t const litlengthHeaderSize = FSE_readNCount(litlengthNCount, &litlengthMaxValue, &litlengthLog, dictPtr, dictEnd - dictPtr);
-		if (FSE_isError(litlengthHeaderSize))
-			return ERROR(dictionary_corrupted);
-		if (litlengthLog > LLFSELog)
-			return ERROR(dictionary_corrupted);
-		/* Every literal length code must have non-zero probability */
-		CHECK_F(ZSTD_checkDictNCount(litlengthNCount, litlengthMaxValue, MaxLL));
-		CHECK_E(FSE_buildCTable_wksp(cctx->litlengthCTable, litlengthNCount, litlengthMaxValue, litlengthLog, cctx->tmpCounters, sizeof(cctx->tmpCounters)),
-			dictionary_corrupted);
-		dictPtr += litlengthHeaderSize;
-	}
-
-	if (dictPtr + 12 > dictEnd)
-		return ERROR(dictionary_corrupted);
-	cctx->rep[0] = ZSTD_readLE32(dictPtr + 0);
-	cctx->rep[1] = ZSTD_readLE32(dictPtr + 4);
-	cctx->rep[2] = ZSTD_readLE32(dictPtr + 8);
-	dictPtr += 12;
-
-	{
-		size_t const dictContentSize = (size_t)(dictEnd - dictPtr);
-		U32 offcodeMax = MaxOff;
-		if (dictContentSize <= ((U32)-1) - 128 KB) {
-			U32 const maxOffset = (U32)dictContentSize + 128 KB; /* The maximum offset that must be supported */
-			offcodeMax = ZSTD_highbit32(maxOffset);		     /* Calculate minimum offset code required to represent maxOffset */
-		}
-		/* All offset values <= dictContentSize + 128 KB must be representable */
-		CHECK_F(ZSTD_checkDictNCount(offcodeNCount, offcodeMaxValue, MIN(offcodeMax, MaxOff)));
-		/* All repCodes must be <= dictContentSize and != 0*/
-		{
-			U32 u;
-			for (u = 0; u < 3; u++) {
-				if (cctx->rep[u] == 0)
-					return ERROR(dictionary_corrupted);
-				if (cctx->rep[u] > dictContentSize)
-					return ERROR(dictionary_corrupted);
-			}
-		}
-
-		cctx->flagStaticTables = 1;
-		cctx->flagStaticHufTable = HUF_repeat_valid;
-		return ZSTD_loadDictionaryContent(cctx, dictPtr, dictContentSize);
-	}
-}
-
-/** ZSTD_compress_insertDictionary() :
-*   @return : 0, or an error code */
-static size_t ZSTD_compress_insertDictionary(ZSTD_CCtx *cctx, const void *dict, size_t dictSize)
-{
-	if ((dict == NULL) || (dictSize <= 8))
-		return 0;
-
-	/* dict as pure content */
-	if ((ZSTD_readLE32(dict) != ZSTD_DICT_MAGIC) || (cctx->forceRawDict))
-		return ZSTD_loadDictionaryContent(cctx, dict, dictSize);
-
-	/* dict as zstd dictionary */
-	return ZSTD_loadZstdDictionary(cctx, dict, dictSize);
-}
-
-/*! ZSTD_compressBegin_internal() :
-*   @return : 0, or an error code */
-static size_t ZSTD_compressBegin_internal(ZSTD_CCtx *cctx, const void *dict, size_t dictSize, ZSTD_parameters params, U64 pledgedSrcSize)
-{
-	ZSTD_compResetPolicy_e const crp = dictSize ? ZSTDcrp_fullReset : ZSTDcrp_continue;
-	CHECK_F(ZSTD_resetCCtx_advanced(cctx, params, pledgedSrcSize, crp));
-	return ZSTD_compress_insertDictionary(cctx, dict, dictSize);
-}
-
-/*! ZSTD_compressBegin_advanced() :
-*   @return : 0, or an error code */
-size_t ZSTD_compressBegin_advanced(ZSTD_CCtx *cctx, const void *dict, size_t dictSize, ZSTD_parameters params, unsigned long long pledgedSrcSize)
-{
-	/* compression parameters verification and optimization */
-	CHECK_F(ZSTD_checkCParams(params.cParams));
-	return ZSTD_compressBegin_internal(cctx, dict, dictSize, params, pledgedSrcSize);
-}
-
-size_t ZSTD_compressBegin_usingDict(ZSTD_CCtx *cctx, const void *dict, size_t dictSize, int compressionLevel)
-{
-	ZSTD_parameters const params = ZSTD_getParams(compressionLevel, 0, dictSize);
-	return ZSTD_compressBegin_internal(cctx, dict, dictSize, params, 0);
-}
-
-size_t ZSTD_compressBegin(ZSTD_CCtx *cctx, int compressionLevel) { return ZSTD_compressBegin_usingDict(cctx, NULL, 0, compressionLevel); }
-
-/*! ZSTD_writeEpilogue() :
-*   Ends a frame.
-*   @return : nb of bytes written into dst (or an error code) */
-static size_t ZSTD_writeEpilogue(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity)
-{
-	BYTE *const ostart = (BYTE *)dst;
-	BYTE *op = ostart;
-	size_t fhSize = 0;
-
-	if (cctx->stage == ZSTDcs_created)
-		return ERROR(stage_wrong); /* init missing */
-
-	/* special case : empty frame */
-	if (cctx->stage == ZSTDcs_init) {
-		fhSize = ZSTD_writeFrameHeader(dst, dstCapacity, cctx->params, 0, 0);
-		if (ZSTD_isError(fhSize))
-			return fhSize;
-		dstCapacity -= fhSize;
-		op += fhSize;
-		cctx->stage = ZSTDcs_ongoing;
-	}
-
-	if (cctx->stage != ZSTDcs_ending) {
-		/* write one last empty block, make it the "last" block */
-		U32 const cBlockHeader24 = 1 /* last block */ + (((U32)bt_raw) << 1) + 0;
-		if (dstCapacity < 4)
-			return ERROR(dstSize_tooSmall);
-		ZSTD_writeLE32(op, cBlockHeader24);
-		op += ZSTD_blockHeaderSize;
-		dstCapacity -= ZSTD_blockHeaderSize;
-	}
-
-	if (cctx->params.fParams.checksumFlag) {
-		U32 const checksum = (U32)xxh64_digest(&cctx->xxhState);
-		if (dstCapacity < 4)
-			return ERROR(dstSize_tooSmall);
-		ZSTD_writeLE32(op, checksum);
-		op += 4;
-	}
-
-	cctx->stage = ZSTDcs_created; /* return to "created but no init" status */
-	return op - ostart;
-}
-
-size_t ZSTD_compressEnd(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity, const void *src, size_t srcSize)
-{
-	size_t endResult;
-	size_t const cSize = ZSTD_compressContinue_internal(cctx, dst, dstCapacity, src, srcSize, 1, 1);
-	if (ZSTD_isError(cSize))
-		return cSize;
-	endResult = ZSTD_writeEpilogue(cctx, (char *)dst + cSize, dstCapacity - cSize);
-	if (ZSTD_isError(endResult))
-		return endResult;
-	return cSize + endResult;
-}
-
-static size_t ZSTD_compress_internal(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity, const void *src, size_t srcSize, const void *dict, size_t dictSize,
-				     ZSTD_parameters params)
-{
-	CHECK_F(ZSTD_compressBegin_internal(cctx, dict, dictSize, params, srcSize));
-	return ZSTD_compressEnd(cctx, dst, dstCapacity, src, srcSize);
-}
-
-size_t ZSTD_compress_usingDict(ZSTD_CCtx *ctx, void *dst, size_t dstCapacity, const void *src, size_t srcSize, const void *dict, size_t dictSize,
-			       ZSTD_parameters params)
-{
-	return ZSTD_compress_internal(ctx, dst, dstCapacity, src, srcSize, dict, dictSize, params);
-}
-
-size_t ZSTD_compressCCtx(ZSTD_CCtx *ctx, void *dst, size_t dstCapacity, const void *src, size_t srcSize, ZSTD_parameters params)
-{
-	return ZSTD_compress_internal(ctx, dst, dstCapacity, src, srcSize, NULL, 0, params);
-}
-
-/* =====  Dictionary API  ===== */
-
-struct ZSTD_CDict_s {
-	void *dictBuffer;
-	const void *dictContent;
-	size_t dictContentSize;
-	ZSTD_CCtx *refContext;
-}; /* typedef'd tp ZSTD_CDict within "zstd.h" */
-
-size_t ZSTD_CDictWorkspaceBound(ZSTD_compressionParameters cParams) { return ZSTD_CCtxWorkspaceBound(cParams) + ZSTD_ALIGN(sizeof(ZSTD_CDict)); }
-
-static ZSTD_CDict *ZSTD_createCDict_advanced(const void *dictBuffer, size_t dictSize, unsigned byReference, ZSTD_parameters params, ZSTD_customMem customMem)
-{
-	if (!customMem.customAlloc || !customMem.customFree)
-		return NULL;
-
-	{
-		ZSTD_CDict *const cdict = (ZSTD_CDict *)ZSTD_malloc(sizeof(ZSTD_CDict), customMem);
-		ZSTD_CCtx *const cctx = ZSTD_createCCtx_advanced(customMem);
-
-		if (!cdict || !cctx) {
-			ZSTD_free(cdict, customMem);
-			ZSTD_freeCCtx(cctx);
-			return NULL;
-		}
-
-		if ((byReference) || (!dictBuffer) || (!dictSize)) {
-			cdict->dictBuffer = NULL;
-			cdict->dictContent = dictBuffer;
-		} else {
-			void *const internalBuffer = ZSTD_malloc(dictSize, customMem);
-			if (!internalBuffer) {
-				ZSTD_free(cctx, customMem);
-				ZSTD_free(cdict, customMem);
-				return NULL;
-			}
-			memcpy(internalBuffer, dictBuffer, dictSize);
-			cdict->dictBuffer = internalBuffer;
-			cdict->dictContent = internalBuffer;
-		}
-
-		{
-			size_t const errorCode = ZSTD_compressBegin_advanced(cctx, cdict->dictContent, dictSize, params, 0);
-			if (ZSTD_isError(errorCode)) {
-				ZSTD_free(cdict->dictBuffer, customMem);
-				ZSTD_free(cdict, customMem);
-				ZSTD_freeCCtx(cctx);
-				return NULL;
-			}
-		}
-
-		cdict->refContext = cctx;
-		cdict->dictContentSize = dictSize;
-		return cdict;
-	}
-}
-
-ZSTD_CDict *ZSTD_initCDict(const void *dict, size_t dictSize, ZSTD_parameters params, void *workspace, size_t workspaceSize)
-{
-	ZSTD_customMem const stackMem = ZSTD_initStack(workspace, workspaceSize);
-	return ZSTD_createCDict_advanced(dict, dictSize, 1, params, stackMem);
-}
-
-size_t ZSTD_freeCDict(ZSTD_CDict *cdict)
-{
-	if (cdict == NULL)
-		return 0; /* support free on NULL */
-	{
-		ZSTD_customMem const cMem = cdict->refContext->customMem;
-		ZSTD_freeCCtx(cdict->refContext);
-		ZSTD_free(cdict->dictBuffer, cMem);
-		ZSTD_free(cdict, cMem);
-		return 0;
-	}
-}
-
-static ZSTD_parameters ZSTD_getParamsFromCDict(const ZSTD_CDict *cdict) { return ZSTD_getParamsFromCCtx(cdict->refContext); }
-
-size_t ZSTD_compressBegin_usingCDict(ZSTD_CCtx *cctx, const ZSTD_CDict *cdict, unsigned long long pledgedSrcSize)
-{
-	if (cdict->dictContentSize)
-		CHECK_F(ZSTD_copyCCtx(cctx, cdict->refContext, pledgedSrcSize))
-	else {
-		ZSTD_parameters params = cdict->refContext->params;
-		params.fParams.contentSizeFlag = (pledgedSrcSize > 0);
-		CHECK_F(ZSTD_compressBegin_advanced(cctx, NULL, 0, params, pledgedSrcSize));
-	}
-	return 0;
-}
-
-/*! ZSTD_compress_usingCDict() :
-*   Compression using a digested Dictionary.
-*   Faster startup than ZSTD_compress_usingDict(), recommended when same dictionary is used multiple times.
-*   Note that compression level is decided during dictionary creation */
-size_t ZSTD_compress_usingCDict(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity, const void *src, size_t srcSize, const ZSTD_CDict *cdict)
-{
-	CHECK_F(ZSTD_compressBegin_usingCDict(cctx, cdict, srcSize));
-
-	if (cdict->refContext->params.fParams.contentSizeFlag == 1) {
-		cctx->params.fParams.contentSizeFlag = 1;
-		cctx->frameContentSize = srcSize;
-	} else {
-		cctx->params.fParams.contentSizeFlag = 0;
-	}
-
-	return ZSTD_compressEnd(cctx, dst, dstCapacity, src, srcSize);
-}
-
-/* ******************************************************************
-*  Streaming
-********************************************************************/
-
-typedef enum { zcss_init, zcss_load, zcss_flush, zcss_final } ZSTD_cStreamStage;
-
-struct ZSTD_CStream_s {
-	ZSTD_CCtx *cctx;
-	ZSTD_CDict *cdictLocal;
-	const ZSTD_CDict *cdict;
-	char *inBuff;
-	size_t inBuffSize;
-	size_t inToCompress;
-	size_t inBuffPos;
-	size_t inBuffTarget;
-	size_t blockSize;
-	char *outBuff;
-	size_t outBuffSize;
-	size_t outBuffContentSize;
-	size_t outBuffFlushedSize;
-	ZSTD_cStreamStage stage;
-	U32 checksum;
-	U32 frameEnded;
-	U64 pledgedSrcSize;
-	U64 inputProcessed;
-	ZSTD_parameters params;
-	ZSTD_customMem customMem;
-}; /* typedef'd to ZSTD_CStream within "zstd.h" */
-
-size_t ZSTD_CStreamWorkspaceBound(ZSTD_compressionParameters cParams)
-{
-	size_t const inBuffSize = (size_t)1 << cParams.windowLog;
-	size_t const blockSize = MIN(ZSTD_BLOCKSIZE_ABSOLUTEMAX, inBuffSize);
-	size_t const outBuffSize = ZSTD_compressBound(blockSize) + 1;
-
-	return ZSTD_CCtxWorkspaceBound(cParams) + ZSTD_ALIGN(sizeof(ZSTD_CStream)) + ZSTD_ALIGN(inBuffSize) + ZSTD_ALIGN(outBuffSize);
-}
-
-ZSTD_CStream *ZSTD_createCStream_advanced(ZSTD_customMem customMem)
-{
-	ZSTD_CStream *zcs;
-
-	if (!customMem.customAlloc || !customMem.customFree)
-		return NULL;
-
-	zcs = (ZSTD_CStream *)ZSTD_malloc(sizeof(ZSTD_CStream), customMem);
-	if (zcs == NULL)
-		return NULL;
-	memset(zcs, 0, sizeof(ZSTD_CStream));
-	memcpy(&zcs->customMem, &customMem, sizeof(ZSTD_customMem));
-	zcs->cctx = ZSTD_createCCtx_advanced(customMem);
-	if (zcs->cctx == NULL) {
-		ZSTD_freeCStream(zcs);
-		return NULL;
-	}
-	return zcs;
-}
-
-size_t ZSTD_freeCStream(ZSTD_CStream *zcs)
-{
-	if (zcs == NULL)
-		return 0; /* support free on NULL */
-	{
-		ZSTD_customMem const cMem = zcs->customMem;
-		ZSTD_freeCCtx(zcs->cctx);
-		zcs->cctx = NULL;
-		ZSTD_freeCDict(zcs->cdictLocal);
-		zcs->cdictLocal = NULL;
-		ZSTD_free(zcs->inBuff, cMem);
-		zcs->inBuff = NULL;
-		ZSTD_free(zcs->outBuff, cMem);
-		zcs->outBuff = NULL;
-		ZSTD_free(zcs, cMem);
-		return 0;
-	}
-}
-
-/*======   Initialization   ======*/
-
-size_t ZSTD_CStreamInSize(void) { return ZSTD_BLOCKSIZE_ABSOLUTEMAX; }
-size_t ZSTD_CStreamOutSize(void) { return ZSTD_compressBound(ZSTD_BLOCKSIZE_ABSOLUTEMAX) + ZSTD_blockHeaderSize + 4 /* 32-bits hash */; }
-
-static size_t ZSTD_resetCStream_internal(ZSTD_CStream *zcs, unsigned long long pledgedSrcSize)
-{
-	if (zcs->inBuffSize == 0)
-		return ERROR(stage_wrong); /* zcs has not been init at least once => can't reset */
-
-	if (zcs->cdict)
-		CHECK_F(ZSTD_compressBegin_usingCDict(zcs->cctx, zcs->cdict, pledgedSrcSize))
-	else
-		CHECK_F(ZSTD_compressBegin_advanced(zcs->cctx, NULL, 0, zcs->params, pledgedSrcSize));
-
-	zcs->inToCompress = 0;
-	zcs->inBuffPos = 0;
-	zcs->inBuffTarget = zcs->blockSize;
-	zcs->outBuffContentSize = zcs->outBuffFlushedSize = 0;
-	zcs->stage = zcss_load;
-	zcs->frameEnded = 0;
-	zcs->pledgedSrcSize = pledgedSrcSize;
-	zcs->inputProcessed = 0;
-	return 0; /* ready to go */
-}
-
-size_t ZSTD_resetCStream(ZSTD_CStream *zcs, unsigned long long pledgedSrcSize)
-{
-
-	zcs->params.fParams.contentSizeFlag = (pledgedSrcSize > 0);
-
-	return ZSTD_resetCStream_internal(zcs, pledgedSrcSize);
-}
-
-static size_t ZSTD_initCStream_advanced(ZSTD_CStream *zcs, const void *dict, size_t dictSize, ZSTD_parameters params, unsigned long long pledgedSrcSize)
-{
-	/* allocate buffers */
-	{
-		size_t const neededInBuffSize = (size_t)1 << params.cParams.windowLog;
-		if (zcs->inBuffSize < neededInBuffSize) {
-			zcs->inBuffSize = neededInBuffSize;
-			ZSTD_free(zcs->inBuff, zcs->customMem);
-			zcs->inBuff = (char *)ZSTD_malloc(neededInBuffSize, zcs->customMem);
-			if (zcs->inBuff == NULL)
-				return ERROR(memory_allocation);
-		}
-		zcs->blockSize = MIN(ZSTD_BLOCKSIZE_ABSOLUTEMAX, neededInBuffSize);
-	}
-	if (zcs->outBuffSize < ZSTD_compressBound(zcs->blockSize) + 1) {
-		zcs->outBuffSize = ZSTD_compressBound(zcs->blockSize) + 1;
-		ZSTD_free(zcs->outBuff, zcs->customMem);
-		zcs->outBuff = (char *)ZSTD_malloc(zcs->outBuffSize, zcs->customMem);
-		if (zcs->outBuff == NULL)
-			return ERROR(memory_allocation);
-	}
-
-	if (dict && dictSize >= 8) {
-		ZSTD_freeCDict(zcs->cdictLocal);
-		zcs->cdictLocal = ZSTD_createCDict_advanced(dict, dictSize, 0, params, zcs->customMem);
-		if (zcs->cdictLocal == NULL)
-			return ERROR(memory_allocation);
-		zcs->cdict = zcs->cdictLocal;
-	} else
-		zcs->cdict = NULL;
-
-	zcs->checksum = params.fParams.checksumFlag > 0;
-	zcs->params = params;
-
-	return ZSTD_resetCStream_internal(zcs, pledgedSrcSize);
-}
-
-ZSTD_CStream *ZSTD_initCStream(ZSTD_parameters params, unsigned long long pledgedSrcSize, void *workspace, size_t workspaceSize)
-{
-	ZSTD_customMem const stackMem = ZSTD_initStack(workspace, workspaceSize);
-	ZSTD_CStream *const zcs = ZSTD_createCStream_advanced(stackMem);
-	if (zcs) {
-		size_t const code = ZSTD_initCStream_advanced(zcs, NULL, 0, params, pledgedSrcSize);
-		if (ZSTD_isError(code)) {
-			return NULL;
-		}
-	}
-	return zcs;
-}
-
-ZSTD_CStream *ZSTD_initCStream_usingCDict(const ZSTD_CDict *cdict, unsigned long long pledgedSrcSize, void *workspace, size_t workspaceSize)
-{
-	ZSTD_parameters const params = ZSTD_getParamsFromCDict(cdict);
-	ZSTD_CStream *const zcs = ZSTD_initCStream(params, pledgedSrcSize, workspace, workspaceSize);
-	if (zcs) {
-		zcs->cdict = cdict;
-		if (ZSTD_isError(ZSTD_resetCStream_internal(zcs, pledgedSrcSize))) {
-			return NULL;
-		}
-	}
-	return zcs;
-}
-
-/*======   Compression   ======*/
-
-typedef enum { zsf_gather, zsf_flush, zsf_end } ZSTD_flush_e;
-
-ZSTD_STATIC size_t ZSTD_limitCopy(void *dst, size_t dstCapacity, const void *src, size_t srcSize)
-{
-	size_t const length = MIN(dstCapacity, srcSize);
-	memcpy(dst, src, length);
-	return length;
-}
-
-static size_t ZSTD_compressStream_generic(ZSTD_CStream *zcs, void *dst, size_t *dstCapacityPtr, const void *src, size_t *srcSizePtr, ZSTD_flush_e const flush)
-{
-	U32 someMoreWork = 1;
-	const char *const istart = (const char *)src;
-	const char *const iend = istart + *srcSizePtr;
-	const char *ip = istart;
-	char *const ostart = (char *)dst;
-	char *const oend = ostart + *dstCapacityPtr;
-	char *op = ostart;
-
-	while (someMoreWork) {
-		switch (zcs->stage) {
-		case zcss_init:
-			return ERROR(init_missing); /* call ZBUFF_compressInit() first ! */
-
-		case zcss_load:
-			/* complete inBuffer */
-			{
-				size_t const toLoad = zcs->inBuffTarget - zcs->inBuffPos;
-				size_t const loaded = ZSTD_limitCopy(zcs->inBuff + zcs->inBuffPos, toLoad, ip, iend - ip);
-				zcs->inBuffPos += loaded;
-				ip += loaded;
-				if ((zcs->inBuffPos == zcs->inToCompress) || (!flush && (toLoad != loaded))) {
-					someMoreWork = 0;
-					break; /* not enough input to get a full block : stop there, wait for more */
-				}
-			}
-			/* compress curr block (note : this stage cannot be stopped in the middle) */
-			{
-				void *cDst;
-				size_t cSize;
-				size_t const iSize = zcs->inBuffPos - zcs->inToCompress;
-				size_t oSize = oend - op;
-				if (oSize >= ZSTD_compressBound(iSize))
-					cDst = op; /* compress directly into output buffer (avoid flush stage) */
-				else
-					cDst = zcs->outBuff, oSize = zcs->outBuffSize;
-				cSize = (flush == zsf_end) ? ZSTD_compressEnd(zcs->cctx, cDst, oSize, zcs->inBuff + zcs->inToCompress, iSize)
-							   : ZSTD_compressContinue(zcs->cctx, cDst, oSize, zcs->inBuff + zcs->inToCompress, iSize);
-				if (ZSTD_isError(cSize))
-					return cSize;
-				if (flush == zsf_end)
-					zcs->frameEnded = 1;
-				/* prepare next block */
-				zcs->inBuffTarget = zcs->inBuffPos + zcs->blockSize;
-				if (zcs->inBuffTarget > zcs->inBuffSize)
-					zcs->inBuffPos = 0, zcs->inBuffTarget = zcs->blockSize; /* note : inBuffSize >= blockSize */
-				zcs->inToCompress = zcs->inBuffPos;
-				if (cDst == op) {
-					op += cSize;
-					break;
-				} /* no need to flush */
-				zcs->outBuffContentSize = cSize;
-				zcs->outBuffFlushedSize = 0;
-				zcs->stage = zcss_flush; /* pass-through to flush stage */
-			}
-			fallthrough;
-
-		case zcss_flush: {
-			size_t const toFlush = zcs->outBuffContentSize - zcs->outBuffFlushedSize;
-			size_t const flushed = ZSTD_limitCopy(op, oend - op, zcs->outBuff + zcs->outBuffFlushedSize, toFlush);
-			op += flushed;
-			zcs->outBuffFlushedSize += flushed;
-			if (toFlush != flushed) {
-				someMoreWork = 0;
-				break;
-			} /* dst too small to store flushed data : stop there */
-			zcs->outBuffContentSize = zcs->outBuffFlushedSize = 0;
-			zcs->stage = zcss_load;
-			break;
-		}
-
-		case zcss_final:
-			someMoreWork = 0; /* do nothing */
-			break;
-
-		default:
-			return ERROR(GENERIC); /* impossible */
-		}
-	}
-
-	*srcSizePtr = ip - istart;
-	*dstCapacityPtr = op - ostart;
-	zcs->inputProcessed += *srcSizePtr;
-	if (zcs->frameEnded)
-		return 0;
-	{
-		size_t hintInSize = zcs->inBuffTarget - zcs->inBuffPos;
-		if (hintInSize == 0)
-			hintInSize = zcs->blockSize;
-		return hintInSize;
-	}
-}
-
-size_t ZSTD_compressStream(ZSTD_CStream *zcs, ZSTD_outBuffer *output, ZSTD_inBuffer *input)
-{
-	size_t sizeRead = input->size - input->pos;
-	size_t sizeWritten = output->size - output->pos;
-	size_t const result =
-	    ZSTD_compressStream_generic(zcs, (char *)(output->dst) + output->pos, &sizeWritten, (const char *)(input->src) + input->pos, &sizeRead, zsf_gather);
-	input->pos += sizeRead;
-	output->pos += sizeWritten;
-	return result;
-}
-
-/*======   Finalize   ======*/
-
-/*! ZSTD_flushStream() :
-*   @return : amount of data remaining to flush */
-size_t ZSTD_flushStream(ZSTD_CStream *zcs, ZSTD_outBuffer *output)
-{
-	size_t srcSize = 0;
-	size_t sizeWritten = output->size - output->pos;
-	size_t const result = ZSTD_compressStream_generic(zcs, (char *)(output->dst) + output->pos, &sizeWritten, &srcSize,
-							  &srcSize, /* use a valid src address instead of NULL */
-							  zsf_flush);
-	output->pos += sizeWritten;
-	if (ZSTD_isError(result))
-		return result;
-	return zcs->outBuffContentSize - zcs->outBuffFlushedSize; /* remaining to flush */
-}
-
-size_t ZSTD_endStream(ZSTD_CStream *zcs, ZSTD_outBuffer *output)
-{
-	BYTE *const ostart = (BYTE *)(output->dst) + output->pos;
-	BYTE *const oend = (BYTE *)(output->dst) + output->size;
-	BYTE *op = ostart;
-
-	if ((zcs->pledgedSrcSize) && (zcs->inputProcessed != zcs->pledgedSrcSize))
-		return ERROR(srcSize_wrong); /* pledgedSrcSize not respected */
-
-	if (zcs->stage != zcss_final) {
-		/* flush whatever remains */
-		size_t srcSize = 0;
-		size_t sizeWritten = output->size - output->pos;
-		size_t const notEnded =
-		    ZSTD_compressStream_generic(zcs, ostart, &sizeWritten, &srcSize, &srcSize, zsf_end); /* use a valid src address instead of NULL */
-		size_t const remainingToFlush = zcs->outBuffContentSize - zcs->outBuffFlushedSize;
-		op += sizeWritten;
-		if (remainingToFlush) {
-			output->pos += sizeWritten;
-			return remainingToFlush + ZSTD_BLOCKHEADERSIZE /* final empty block */ + (zcs->checksum * 4);
-		}
-		/* create epilogue */
-		zcs->stage = zcss_final;
-		zcs->outBuffContentSize = !notEnded ? 0 : ZSTD_compressEnd(zcs->cctx, zcs->outBuff, zcs->outBuffSize, NULL,
-									   0); /* write epilogue, including final empty block, into outBuff */
-	}
-
-	/* flush epilogue */
-	{
-		size_t const toFlush = zcs->outBuffContentSize - zcs->outBuffFlushedSize;
-		size_t const flushed = ZSTD_limitCopy(op, oend - op, zcs->outBuff + zcs->outBuffFlushedSize, toFlush);
-		op += flushed;
-		zcs->outBuffFlushedSize += flushed;
-		output->pos += op - ostart;
-		if (toFlush == flushed)
-			zcs->stage = zcss_init; /* end reached */
-		return toFlush - flushed;
-	}
-}
-
-/*-=====  Pre-defined compression levels  =====-*/
-
-#define ZSTD_DEFAULT_CLEVEL 1
-#define ZSTD_MAX_CLEVEL 22
-int ZSTD_maxCLevel(void) { return ZSTD_MAX_CLEVEL; }
-
-static const ZSTD_compressionParameters ZSTD_defaultCParameters[4][ZSTD_MAX_CLEVEL + 1] = {
-    {
-	/* "default" */
-	/* W,  C,  H,  S,  L, TL, strat */
-	{18, 12, 12, 1, 7, 16, ZSTD_fast},    /* level  0 - never used */
-	{19, 13, 14, 1, 7, 16, ZSTD_fast},    /* level  1 */
-	{19, 15, 16, 1, 6, 16, ZSTD_fast},    /* level  2 */
-	{20, 16, 17, 1, 5, 16, ZSTD_dfast},   /* level  3.*/
-	{20, 18, 18, 1, 5, 16, ZSTD_dfast},   /* level  4.*/
-	{20, 15, 18, 3, 5, 16, ZSTD_greedy},  /* level  5 */
-	{21, 16, 19, 2, 5, 16, ZSTD_lazy},    /* level  6 */
-	{21, 17, 20, 3, 5, 16, ZSTD_lazy},    /* level  7 */
-	{21, 18, 20, 3, 5, 16, ZSTD_lazy2},   /* level  8 */
-	{21, 20, 20, 3, 5, 16, ZSTD_lazy2},   /* level  9 */
-	{21, 19, 21, 4, 5, 16, ZSTD_lazy2},   /* level 10 */
-	{22, 20, 22, 4, 5, 16, ZSTD_lazy2},   /* level 11 */
-	{22, 20, 22, 5, 5, 16, ZSTD_lazy2},   /* level 12 */
-	{22, 21, 22, 5, 5, 16, ZSTD_lazy2},   /* level 13 */
-	{22, 21, 22, 6, 5, 16, ZSTD_lazy2},   /* level 14 */
-	{22, 21, 21, 5, 5, 16, ZSTD_btlazy2}, /* level 15 */
-	{23, 22, 22, 5, 5, 16, ZSTD_btlazy2}, /* level 16 */
-	{23, 21, 22, 4, 5, 24, ZSTD_btopt},   /* level 17 */
-	{23, 23, 22, 6, 5, 32, ZSTD_btopt},   /* level 18 */
-	{23, 23, 22, 6, 3, 48, ZSTD_btopt},   /* level 19 */
-	{25, 25, 23, 7, 3, 64, ZSTD_btopt2},  /* level 20 */
-	{26, 26, 23, 7, 3, 256, ZSTD_btopt2}, /* level 21 */
-	{27, 27, 25, 9, 3, 512, ZSTD_btopt2}, /* level 22 */
-    },
-    {
-	/* for srcSize <= 256 KB */
-	/* W,  C,  H,  S,  L,  T, strat */
-	{0, 0, 0, 0, 0, 0, ZSTD_fast},	 /* level  0 - not used */
-	{18, 13, 14, 1, 6, 8, ZSTD_fast},      /* level  1 */
-	{18, 14, 13, 1, 5, 8, ZSTD_dfast},     /* level  2 */
-	{18, 16, 15, 1, 5, 8, ZSTD_dfast},     /* level  3 */
-	{18, 15, 17, 1, 5, 8, ZSTD_greedy},    /* level  4.*/
-	{18, 16, 17, 4, 5, 8, ZSTD_greedy},    /* level  5.*/
-	{18, 16, 17, 3, 5, 8, ZSTD_lazy},      /* level  6.*/
-	{18, 17, 17, 4, 4, 8, ZSTD_lazy},      /* level  7 */
-	{18, 17, 17, 4, 4, 8, ZSTD_lazy2},     /* level  8 */
-	{18, 17, 17, 5, 4, 8, ZSTD_lazy2},     /* level  9 */
-	{18, 17, 17, 6, 4, 8, ZSTD_lazy2},     /* level 10 */
-	{18, 18, 17, 6, 4, 8, ZSTD_lazy2},     /* level 11.*/
-	{18, 18, 17, 7, 4, 8, ZSTD_lazy2},     /* level 12.*/
-	{18, 19, 17, 6, 4, 8, ZSTD_btlazy2},   /* level 13 */
-	{18, 18, 18, 4, 4, 16, ZSTD_btopt},    /* level 14.*/
-	{18, 18, 18, 4, 3, 16, ZSTD_btopt},    /* level 15.*/
-	{18, 19, 18, 6, 3, 32, ZSTD_btopt},    /* level 16.*/
-	{18, 19, 18, 8, 3, 64, ZSTD_btopt},    /* level 17.*/
-	{18, 19, 18, 9, 3, 128, ZSTD_btopt},   /* level 18.*/
-	{18, 19, 18, 10, 3, 256, ZSTD_btopt},  /* level 19.*/
-	{18, 19, 18, 11, 3, 512, ZSTD_btopt2}, /* level 20.*/
-	{18, 19, 18, 12, 3, 512, ZSTD_btopt2}, /* level 21.*/
-	{18, 19, 18, 13, 3, 512, ZSTD_btopt2}, /* level 22.*/
-    },
-    {
-	/* for srcSize <= 128 KB */
-	/* W,  C,  H,  S,  L,  T, strat */
-	{17, 12, 12, 1, 7, 8, ZSTD_fast},      /* level  0 - not used */
-	{17, 12, 13, 1, 6, 8, ZSTD_fast},      /* level  1 */
-	{17, 13, 16, 1, 5, 8, ZSTD_fast},      /* level  2 */
-	{17, 16, 16, 2, 5, 8, ZSTD_dfast},     /* level  3 */
-	{17, 13, 15, 3, 4, 8, ZSTD_greedy},    /* level  4 */
-	{17, 15, 17, 4, 4, 8, ZSTD_greedy},    /* level  5 */
-	{17, 16, 17, 3, 4, 8, ZSTD_lazy},      /* level  6 */
-	{17, 15, 17, 4, 4, 8, ZSTD_lazy2},     /* level  7 */
-	{17, 17, 17, 4, 4, 8, ZSTD_lazy2},     /* level  8 */
-	{17, 17, 17, 5, 4, 8, ZSTD_lazy2},     /* level  9 */
-	{17, 17, 17, 6, 4, 8, ZSTD_lazy2},     /* level 10 */
-	{17, 17, 17, 7, 4, 8, ZSTD_lazy2},     /* level 11 */
-	{17, 17, 17, 8, 4, 8, ZSTD_lazy2},     /* level 12 */
-	{17, 18, 17, 6, 4, 8, ZSTD_btlazy2},   /* level 13.*/
-	{17, 17, 17, 7, 3, 8, ZSTD_btopt},     /* level 14.*/
-	{17, 17, 17, 7, 3, 16, ZSTD_btopt},    /* level 15.*/
-	{17, 18, 17, 7, 3, 32, ZSTD_btopt},    /* level 16.*/
-	{17, 18, 17, 7, 3, 64, ZSTD_btopt},    /* level 17.*/
-	{17, 18, 17, 7, 3, 256, ZSTD_btopt},   /* level 18.*/
-	{17, 18, 17, 8, 3, 256, ZSTD_btopt},   /* level 19.*/
-	{17, 18, 17, 9, 3, 256, ZSTD_btopt2},  /* level 20.*/
-	{17, 18, 17, 10, 3, 256, ZSTD_btopt2}, /* level 21.*/
-	{17, 18, 17, 11, 3, 512, ZSTD_btopt2}, /* level 22.*/
-    },
-    {
-	/* for srcSize <= 16 KB */
-	/* W,  C,  H,  S,  L,  T, strat */
-	{14, 12, 12, 1, 7, 6, ZSTD_fast},      /* level  0 - not used */
-	{14, 14, 14, 1, 6, 6, ZSTD_fast},      /* level  1 */
-	{14, 14, 14, 1, 4, 6, ZSTD_fast},      /* level  2 */
-	{14, 14, 14, 1, 4, 6, ZSTD_dfast},     /* level  3.*/
-	{14, 14, 14, 4, 4, 6, ZSTD_greedy},    /* level  4.*/
-	{14, 14, 14, 3, 4, 6, ZSTD_lazy},      /* level  5.*/
-	{14, 14, 14, 4, 4, 6, ZSTD_lazy2},     /* level  6 */
-	{14, 14, 14, 5, 4, 6, ZSTD_lazy2},     /* level  7 */
-	{14, 14, 14, 6, 4, 6, ZSTD_lazy2},     /* level  8.*/
-	{14, 15, 14, 6, 4, 6, ZSTD_btlazy2},   /* level  9.*/
-	{14, 15, 14, 3, 3, 6, ZSTD_btopt},     /* level 10.*/
-	{14, 15, 14, 6, 3, 8, ZSTD_btopt},     /* level 11.*/
-	{14, 15, 14, 6, 3, 16, ZSTD_btopt},    /* level 12.*/
-	{14, 15, 14, 6, 3, 24, ZSTD_btopt},    /* level 13.*/
-	{14, 15, 15, 6, 3, 48, ZSTD_btopt},    /* level 14.*/
-	{14, 15, 15, 6, 3, 64, ZSTD_btopt},    /* level 15.*/
-	{14, 15, 15, 6, 3, 96, ZSTD_btopt},    /* level 16.*/
-	{14, 15, 15, 6, 3, 128, ZSTD_btopt},   /* level 17.*/
-	{14, 15, 15, 6, 3, 256, ZSTD_btopt},   /* level 18.*/
-	{14, 15, 15, 7, 3, 256, ZSTD_btopt},   /* level 19.*/
-	{14, 15, 15, 8, 3, 256, ZSTD_btopt2},  /* level 20.*/
-	{14, 15, 15, 9, 3, 256, ZSTD_btopt2},  /* level 21.*/
-	{14, 15, 15, 10, 3, 256, ZSTD_btopt2}, /* level 22.*/
-    },
-};
-
-/*! ZSTD_getCParams() :
-*   @return ZSTD_compressionParameters structure for a selected compression level, `srcSize` and `dictSize`.
-*   Size values are optional, provide 0 if not known or unused */
-ZSTD_compressionParameters ZSTD_getCParams(int compressionLevel, unsigned long long srcSize, size_t dictSize)
-{
-	ZSTD_compressionParameters cp;
-	size_t const addedSize = srcSize ? 0 : 500;
-	U64 const rSize = srcSize + dictSize ? srcSize + dictSize + addedSize : (U64)-1;
-	U32 const tableID = (rSize <= 256 KB) + (rSize <= 128 KB) + (rSize <= 16 KB); /* intentional underflow for srcSizeHint == 0 */
-	if (compressionLevel <= 0)
-		compressionLevel = ZSTD_DEFAULT_CLEVEL; /* 0 == default; no negative compressionLevel yet */
-	if (compressionLevel > ZSTD_MAX_CLEVEL)
-		compressionLevel = ZSTD_MAX_CLEVEL;
-	cp = ZSTD_defaultCParameters[tableID][compressionLevel];
-	if (ZSTD_32bits()) { /* auto-correction, for 32-bits mode */
-		if (cp.windowLog > ZSTD_WINDOWLOG_MAX)
-			cp.windowLog = ZSTD_WINDOWLOG_MAX;
-		if (cp.chainLog > ZSTD_CHAINLOG_MAX)
-			cp.chainLog = ZSTD_CHAINLOG_MAX;
-		if (cp.hashLog > ZSTD_HASHLOG_MAX)
-			cp.hashLog = ZSTD_HASHLOG_MAX;
-	}
-	cp = ZSTD_adjustCParams(cp, srcSize, dictSize);
-	return cp;
-}
-
-/*! ZSTD_getParams() :
-*   same as ZSTD_getCParams(), but @return a `ZSTD_parameters` object (instead of `ZSTD_compressionParameters`).
-*   All fields of `ZSTD_frameParameters` are set to default (0) */
-ZSTD_parameters ZSTD_getParams(int compressionLevel, unsigned long long srcSize, size_t dictSize)
-{
-	ZSTD_parameters params;
-	ZSTD_compressionParameters const cParams = ZSTD_getCParams(compressionLevel, srcSize, dictSize);
-	memset(&params, 0, sizeof(params));
-	params.cParams = cParams;
-	return params;
-}
-
-EXPORT_SYMBOL(ZSTD_maxCLevel);
-EXPORT_SYMBOL(ZSTD_compressBound);
-
-EXPORT_SYMBOL(ZSTD_CCtxWorkspaceBound);
-EXPORT_SYMBOL(ZSTD_initCCtx);
-EXPORT_SYMBOL(ZSTD_compressCCtx);
-EXPORT_SYMBOL(ZSTD_compress_usingDict);
-
-EXPORT_SYMBOL(ZSTD_CDictWorkspaceBound);
-EXPORT_SYMBOL(ZSTD_initCDict);
-EXPORT_SYMBOL(ZSTD_compress_usingCDict);
-
-EXPORT_SYMBOL(ZSTD_CStreamWorkspaceBound);
-EXPORT_SYMBOL(ZSTD_initCStream);
-EXPORT_SYMBOL(ZSTD_initCStream_usingCDict);
-EXPORT_SYMBOL(ZSTD_resetCStream);
-EXPORT_SYMBOL(ZSTD_compressStream);
-EXPORT_SYMBOL(ZSTD_flushStream);
-EXPORT_SYMBOL(ZSTD_endStream);
-EXPORT_SYMBOL(ZSTD_CStreamInSize);
-EXPORT_SYMBOL(ZSTD_CStreamOutSize);
-
-EXPORT_SYMBOL(ZSTD_getCParams);
-EXPORT_SYMBOL(ZSTD_getParams);
-EXPORT_SYMBOL(ZSTD_checkCParams);
-EXPORT_SYMBOL(ZSTD_adjustCParams);
-
-EXPORT_SYMBOL(ZSTD_compressBegin);
-EXPORT_SYMBOL(ZSTD_compressBegin_usingDict);
-EXPORT_SYMBOL(ZSTD_compressBegin_advanced);
-EXPORT_SYMBOL(ZSTD_copyCCtx);
-EXPORT_SYMBOL(ZSTD_compressBegin_usingCDict);
-EXPORT_SYMBOL(ZSTD_compressContinue);
-EXPORT_SYMBOL(ZSTD_compressEnd);
-
-EXPORT_SYMBOL(ZSTD_getBlockSizeMax);
-EXPORT_SYMBOL(ZSTD_compressBlock);
-
-MODULE_LICENSE("Dual BSD/GPL");
-MODULE_DESCRIPTION("Zstd Compressor");
diff --git a/lib/zstd/compress/fse_compress.c b/lib/zstd/compress/fse_compress.c
new file mode 100644
index 000000000000..436985b620e5
--- /dev/null
+++ b/lib/zstd/compress/fse_compress.c
@@ -0,0 +1,625 @@
+/* ******************************************************************
+ * FSE : Finite State Entropy encoder
+ * Copyright (c) Yann Collet, Facebook, Inc.
+ *
+ *  You can contact the author at :
+ *  - FSE source repository : https://github.com/Cyan4973/FiniteStateEntropy
+ *  - Public forum : https://groups.google.com/forum/#!forum/lz4c
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+****************************************************************** */
+
+/* **************************************************************
+*  Includes
+****************************************************************/
+#include "../common/compiler.h"
+#include "../common/mem.h"        /* U32, U16, etc. */
+#include "../common/debug.h"      /* assert, DEBUGLOG */
+#include "hist.h"       /* HIST_count_wksp */
+#include "../common/bitstream.h"
+#define FSE_STATIC_LINKING_ONLY
+#include "../common/fse.h"
+#include "../common/error_private.h"
+#define ZSTD_DEPS_NEED_MALLOC
+#define ZSTD_DEPS_NEED_MATH64
+#include "../common/zstd_deps.h"  /* ZSTD_malloc, ZSTD_free, ZSTD_memcpy, ZSTD_memset */
+
+
+/* **************************************************************
+*  Error Management
+****************************************************************/
+#define FSE_isError ERR_isError
+
+
+/* **************************************************************
+*  Templates
+****************************************************************/
+/*
+  designed to be included
+  for type-specific functions (template emulation in C)
+  Objective is to write these functions only once, for improved maintenance
+*/
+
+/* safety checks */
+#ifndef FSE_FUNCTION_EXTENSION
+#  error "FSE_FUNCTION_EXTENSION must be defined"
+#endif
+#ifndef FSE_FUNCTION_TYPE
+#  error "FSE_FUNCTION_TYPE must be defined"
+#endif
+
+/* Function names */
+#define FSE_CAT(X,Y) X##Y
+#define FSE_FUNCTION_NAME(X,Y) FSE_CAT(X,Y)
+#define FSE_TYPE_NAME(X,Y) FSE_CAT(X,Y)
+
+
+/* Function templates */
+
+/* FSE_buildCTable_wksp() :
+ * Same as FSE_buildCTable(), but using an externally allocated scratch buffer (`workSpace`).
+ * wkspSize should be sized to handle worst case situation, which is `1<<max_tableLog * sizeof(FSE_FUNCTION_TYPE)`
+ * workSpace must also be properly aligned with FSE_FUNCTION_TYPE requirements
+ */
+size_t FSE_buildCTable_wksp(FSE_CTable* ct,
+                      const short* normalizedCounter, unsigned maxSymbolValue, unsigned tableLog,
+                            void* workSpace, size_t wkspSize)
+{
+    U32 const tableSize = 1 << tableLog;
+    U32 const tableMask = tableSize - 1;
+    void* const ptr = ct;
+    U16* const tableU16 = ( (U16*) ptr) + 2;
+    void* const FSCT = ((U32*)ptr) + 1 /* header */ + (tableLog ? tableSize>>1 : 1) ;
+    FSE_symbolCompressionTransform* const symbolTT = (FSE_symbolCompressionTransform*) (FSCT);
+    U32 const step = FSE_TABLESTEP(tableSize);
+
+    U32* cumul = (U32*)workSpace;
+    FSE_FUNCTION_TYPE* tableSymbol = (FSE_FUNCTION_TYPE*)(cumul + (maxSymbolValue + 2));
+
+    U32 highThreshold = tableSize-1;
+
+    if ((size_t)workSpace & 3) return ERROR(GENERIC); /* Must be 4 byte aligned */
+    if (FSE_BUILD_CTABLE_WORKSPACE_SIZE(maxSymbolValue, tableLog) > wkspSize) return ERROR(tableLog_tooLarge);
+    /* CTable header */
+    tableU16[-2] = (U16) tableLog;
+    tableU16[-1] = (U16) maxSymbolValue;
+    assert(tableLog < 16);   /* required for threshold strategy to work */
+
+    /* For explanations on how to distribute symbol values over the table :
+     * http://fastcompression.blogspot.fr/2014/02/fse-distributing-symbol-values.html */
+
+     #ifdef __clang_analyzer__
+     ZSTD_memset(tableSymbol, 0, sizeof(*tableSymbol) * tableSize);   /* useless initialization, just to keep scan-build happy */
+     #endif
+
+    /* symbol start positions */
+    {   U32 u;
+        cumul[0] = 0;
+        for (u=1; u <= maxSymbolValue+1; u++) {
+            if (normalizedCounter[u-1]==-1) {  /* Low proba symbol */
+                cumul[u] = cumul[u-1] + 1;
+                tableSymbol[highThreshold--] = (FSE_FUNCTION_TYPE)(u-1);
+            } else {
+                cumul[u] = cumul[u-1] + normalizedCounter[u-1];
+        }   }
+        cumul[maxSymbolValue+1] = tableSize+1;
+    }
+
+    /* Spread symbols */
+    {   U32 position = 0;
+        U32 symbol;
+        for (symbol=0; symbol<=maxSymbolValue; symbol++) {
+            int nbOccurrences;
+            int const freq = normalizedCounter[symbol];
+            for (nbOccurrences=0; nbOccurrences<freq; nbOccurrences++) {
+                tableSymbol[position] = (FSE_FUNCTION_TYPE)symbol;
+                position = (position + step) & tableMask;
+                while (position > highThreshold)
+                    position = (position + step) & tableMask;   /* Low proba area */
+        }   }
+
+        assert(position==0);  /* Must have initialized all positions */
+    }
+
+    /* Build table */
+    {   U32 u; for (u=0; u<tableSize; u++) {
+        FSE_FUNCTION_TYPE s = tableSymbol[u];   /* note : static analyzer may not understand tableSymbol is properly initialized */
+        tableU16[cumul[s]++] = (U16) (tableSize+u);   /* TableU16 : sorted by symbol order; gives next state value */
+    }   }
+
+    /* Build Symbol Transformation Table */
+    {   unsigned total = 0;
+        unsigned s;
+        for (s=0; s<=maxSymbolValue; s++) {
+            switch (normalizedCounter[s])
+            {
+            case  0:
+                /* filling nonetheless, for compatibility with FSE_getMaxNbBits() */
+                symbolTT[s].deltaNbBits = ((tableLog+1) << 16) - (1<<tableLog);
+                break;
+
+            case -1:
+            case  1:
+                symbolTT[s].deltaNbBits = (tableLog << 16) - (1<<tableLog);
+                symbolTT[s].deltaFindState = total - 1;
+                total ++;
+                break;
+            default :
+                {
+                    U32 const maxBitsOut = tableLog - BIT_highbit32 (normalizedCounter[s]-1);
+                    U32 const minStatePlus = normalizedCounter[s] << maxBitsOut;
+                    symbolTT[s].deltaNbBits = (maxBitsOut << 16) - minStatePlus;
+                    symbolTT[s].deltaFindState = total - normalizedCounter[s];
+                    total +=  normalizedCounter[s];
+    }   }   }   }
+
+#if 0  /* debug : symbol costs */
+    DEBUGLOG(5, "\n --- table statistics : ");
+    {   U32 symbol;
+        for (symbol=0; symbol<=maxSymbolValue; symbol++) {
+            DEBUGLOG(5, "%3u: w=%3i,   maxBits=%u, fracBits=%.2f",
+                symbol, normalizedCounter[symbol],
+                FSE_getMaxNbBits(symbolTT, symbol),
+                (double)FSE_bitCost(symbolTT, tableLog, symbol, 8) / 256);
+        }
+    }
+#endif
+
+    return 0;
+}
+
+
+
+
+#ifndef FSE_COMMONDEFS_ONLY
+
+
+/*-**************************************************************
+*  FSE NCount encoding
+****************************************************************/
+size_t FSE_NCountWriteBound(unsigned maxSymbolValue, unsigned tableLog)
+{
+    size_t const maxHeaderSize = (((maxSymbolValue+1) * tableLog) >> 3) + 3;
+    return maxSymbolValue ? maxHeaderSize : FSE_NCOUNTBOUND;  /* maxSymbolValue==0 ? use default */
+}
+
+static size_t
+FSE_writeNCount_generic (void* header, size_t headerBufferSize,
+                   const short* normalizedCounter, unsigned maxSymbolValue, unsigned tableLog,
+                         unsigned writeIsSafe)
+{
+    BYTE* const ostart = (BYTE*) header;
+    BYTE* out = ostart;
+    BYTE* const oend = ostart + headerBufferSize;
+    int nbBits;
+    const int tableSize = 1 << tableLog;
+    int remaining;
+    int threshold;
+    U32 bitStream = 0;
+    int bitCount = 0;
+    unsigned symbol = 0;
+    unsigned const alphabetSize = maxSymbolValue + 1;
+    int previousIs0 = 0;
+
+    /* Table Size */
+    bitStream += (tableLog-FSE_MIN_TABLELOG) << bitCount;
+    bitCount  += 4;
+
+    /* Init */
+    remaining = tableSize+1;   /* +1 for extra accuracy */
+    threshold = tableSize;
+    nbBits = tableLog+1;
+
+    while ((symbol < alphabetSize) && (remaining>1)) {  /* stops at 1 */
+        if (previousIs0) {
+            unsigned start = symbol;
+            while ((symbol < alphabetSize) && !normalizedCounter[symbol]) symbol++;
+            if (symbol == alphabetSize) break;   /* incorrect distribution */
+            while (symbol >= start+24) {
+                start+=24;
+                bitStream += 0xFFFFU << bitCount;
+                if ((!writeIsSafe) && (out > oend-2))
+                    return ERROR(dstSize_tooSmall);   /* Buffer overflow */
+                out[0] = (BYTE) bitStream;
+                out[1] = (BYTE)(bitStream>>8);
+                out+=2;
+                bitStream>>=16;
+            }
+            while (symbol >= start+3) {
+                start+=3;
+                bitStream += 3 << bitCount;
+                bitCount += 2;
+            }
+            bitStream += (symbol-start) << bitCount;
+            bitCount += 2;
+            if (bitCount>16) {
+                if ((!writeIsSafe) && (out > oend - 2))
+                    return ERROR(dstSize_tooSmall);   /* Buffer overflow */
+                out[0] = (BYTE)bitStream;
+                out[1] = (BYTE)(bitStream>>8);
+                out += 2;
+                bitStream >>= 16;
+                bitCount -= 16;
+        }   }
+        {   int count = normalizedCounter[symbol++];
+            int const max = (2*threshold-1) - remaining;
+            remaining -= count < 0 ? -count : count;
+            count++;   /* +1 for extra accuracy */
+            if (count>=threshold)
+                count += max;   /* [0..max[ [max..threshold[ (...) [threshold+max 2*threshold[ */
+            bitStream += count << bitCount;
+            bitCount  += nbBits;
+            bitCount  -= (count<max);
+            previousIs0  = (count==1);
+            if (remaining<1) return ERROR(GENERIC);
+            while (remaining<threshold) { nbBits--; threshold>>=1; }
+        }
+        if (bitCount>16) {
+            if ((!writeIsSafe) && (out > oend - 2))
+                return ERROR(dstSize_tooSmall);   /* Buffer overflow */
+            out[0] = (BYTE)bitStream;
+            out[1] = (BYTE)(bitStream>>8);
+            out += 2;
+            bitStream >>= 16;
+            bitCount -= 16;
+    }   }
+
+    if (remaining != 1)
+        return ERROR(GENERIC);  /* incorrect normalized distribution */
+    assert(symbol <= alphabetSize);
+
+    /* flush remaining bitStream */
+    if ((!writeIsSafe) && (out > oend - 2))
+        return ERROR(dstSize_tooSmall);   /* Buffer overflow */
+    out[0] = (BYTE)bitStream;
+    out[1] = (BYTE)(bitStream>>8);
+    out+= (bitCount+7) /8;
+
+    return (out-ostart);
+}
+
+
+size_t FSE_writeNCount (void* buffer, size_t bufferSize,
+                  const short* normalizedCounter, unsigned maxSymbolValue, unsigned tableLog)
+{
+    if (tableLog > FSE_MAX_TABLELOG) return ERROR(tableLog_tooLarge);   /* Unsupported */
+    if (tableLog < FSE_MIN_TABLELOG) return ERROR(GENERIC);   /* Unsupported */
+
+    if (bufferSize < FSE_NCountWriteBound(maxSymbolValue, tableLog))
+        return FSE_writeNCount_generic(buffer, bufferSize, normalizedCounter, maxSymbolValue, tableLog, 0);
+
+    return FSE_writeNCount_generic(buffer, bufferSize, normalizedCounter, maxSymbolValue, tableLog, 1 /* write in buffer is safe */);
+}
+
+
+/*-**************************************************************
+*  FSE Compression Code
+****************************************************************/
+
+FSE_CTable* FSE_createCTable (unsigned maxSymbolValue, unsigned tableLog)
+{
+    size_t size;
+    if (tableLog > FSE_TABLELOG_ABSOLUTE_MAX) tableLog = FSE_TABLELOG_ABSOLUTE_MAX;
+    size = FSE_CTABLE_SIZE_U32 (tableLog, maxSymbolValue) * sizeof(U32);
+    return (FSE_CTable*)ZSTD_malloc(size);
+}
+
+void FSE_freeCTable (FSE_CTable* ct) { ZSTD_free(ct); }
+
+/* provides the minimum logSize to safely represent a distribution */
+static unsigned FSE_minTableLog(size_t srcSize, unsigned maxSymbolValue)
+{
+    U32 minBitsSrc = BIT_highbit32((U32)(srcSize)) + 1;
+    U32 minBitsSymbols = BIT_highbit32(maxSymbolValue) + 2;
+    U32 minBits = minBitsSrc < minBitsSymbols ? minBitsSrc : minBitsSymbols;
+    assert(srcSize > 1); /* Not supported, RLE should be used instead */
+    return minBits;
+}
+
+unsigned FSE_optimalTableLog_internal(unsigned maxTableLog, size_t srcSize, unsigned maxSymbolValue, unsigned minus)
+{
+    U32 maxBitsSrc = BIT_highbit32((U32)(srcSize - 1)) - minus;
+    U32 tableLog = maxTableLog;
+    U32 minBits = FSE_minTableLog(srcSize, maxSymbolValue);
+    assert(srcSize > 1); /* Not supported, RLE should be used instead */
+    if (tableLog==0) tableLog = FSE_DEFAULT_TABLELOG;
+    if (maxBitsSrc < tableLog) tableLog = maxBitsSrc;   /* Accuracy can be reduced */
+    if (minBits > tableLog) tableLog = minBits;   /* Need a minimum to safely represent all symbol values */
+    if (tableLog < FSE_MIN_TABLELOG) tableLog = FSE_MIN_TABLELOG;
+    if (tableLog > FSE_MAX_TABLELOG) tableLog = FSE_MAX_TABLELOG;
+    return tableLog;
+}
+
+unsigned FSE_optimalTableLog(unsigned maxTableLog, size_t srcSize, unsigned maxSymbolValue)
+{
+    return FSE_optimalTableLog_internal(maxTableLog, srcSize, maxSymbolValue, 2);
+}
+
+/* Secondary normalization method.
+   To be used when primary method fails. */
+
+static size_t FSE_normalizeM2(short* norm, U32 tableLog, const unsigned* count, size_t total, U32 maxSymbolValue, short lowProbCount)
+{
+    short const NOT_YET_ASSIGNED = -2;
+    U32 s;
+    U32 distributed = 0;
+    U32 ToDistribute;
+
+    /* Init */
+    U32 const lowThreshold = (U32)(total >> tableLog);
+    U32 lowOne = (U32)((total * 3) >> (tableLog + 1));
+
+    for (s=0; s<=maxSymbolValue; s++) {
+        if (count[s] == 0) {
+            norm[s]=0;
+            continue;
+        }
+        if (count[s] <= lowThreshold) {
+            norm[s] = lowProbCount;
+            distributed++;
+            total -= count[s];
+            continue;
+        }
+        if (count[s] <= lowOne) {
+            norm[s] = 1;
+            distributed++;
+            total -= count[s];
+            continue;
+        }
+
+        norm[s]=NOT_YET_ASSIGNED;
+    }
+    ToDistribute = (1 << tableLog) - distributed;
+
+    if (ToDistribute == 0)
+        return 0;
+
+    if ((total / ToDistribute) > lowOne) {
+        /* risk of rounding to zero */
+        lowOne = (U32)((total * 3) / (ToDistribute * 2));
+        for (s=0; s<=maxSymbolValue; s++) {
+            if ((norm[s] == NOT_YET_ASSIGNED) && (count[s] <= lowOne)) {
+                norm[s] = 1;
+                distributed++;
+                total -= count[s];
+                continue;
+        }   }
+        ToDistribute = (1 << tableLog) - distributed;
+    }
+
+    if (distributed == maxSymbolValue+1) {
+        /* all values are pretty poor;
+           probably incompressible data (should have already been detected);
+           find max, then give all remaining points to max */
+        U32 maxV = 0, maxC = 0;
+        for (s=0; s<=maxSymbolValue; s++)
+            if (count[s] > maxC) { maxV=s; maxC=count[s]; }
+        norm[maxV] += (short)ToDistribute;
+        return 0;
+    }
+
+    if (total == 0) {
+        /* all of the symbols were low enough for the lowOne or lowThreshold */
+        for (s=0; ToDistribute > 0; s = (s+1)%(maxSymbolValue+1))
+            if (norm[s] > 0) { ToDistribute--; norm[s]++; }
+        return 0;
+    }
+
+    {   U64 const vStepLog = 62 - tableLog;
+        U64 const mid = (1ULL << (vStepLog-1)) - 1;
+        U64 const rStep = ZSTD_div64((((U64)1<<vStepLog) * ToDistribute) + mid, (U32)total);   /* scale on remaining */
+        U64 tmpTotal = mid;
+        for (s=0; s<=maxSymbolValue; s++) {
+            if (norm[s]==NOT_YET_ASSIGNED) {
+                U64 const end = tmpTotal + (count[s] * rStep);
+                U32 const sStart = (U32)(tmpTotal >> vStepLog);
+                U32 const sEnd = (U32)(end >> vStepLog);
+                U32 const weight = sEnd - sStart;
+                if (weight < 1)
+                    return ERROR(GENERIC);
+                norm[s] = (short)weight;
+                tmpTotal = end;
+    }   }   }
+
+    return 0;
+}
+
+size_t FSE_normalizeCount (short* normalizedCounter, unsigned tableLog,
+                           const unsigned* count, size_t total,
+                           unsigned maxSymbolValue, unsigned useLowProbCount)
+{
+    /* Sanity checks */
+    if (tableLog==0) tableLog = FSE_DEFAULT_TABLELOG;
+    if (tableLog < FSE_MIN_TABLELOG) return ERROR(GENERIC);   /* Unsupported size */
+    if (tableLog > FSE_MAX_TABLELOG) return ERROR(tableLog_tooLarge);   /* Unsupported size */
+    if (tableLog < FSE_minTableLog(total, maxSymbolValue)) return ERROR(GENERIC);   /* Too small tableLog, compression potentially impossible */
+
+    {   static U32 const rtbTable[] = {     0, 473195, 504333, 520860, 550000, 700000, 750000, 830000 };
+        short const lowProbCount = useLowProbCount ? -1 : 1;
+        U64 const scale = 62 - tableLog;
+        U64 const step = ZSTD_div64((U64)1<<62, (U32)total);   /* <== here, one division ! */
+        U64 const vStep = 1ULL<<(scale-20);
+        int stillToDistribute = 1<<tableLog;
+        unsigned s;
+        unsigned largest=0;
+        short largestP=0;
+        U32 lowThreshold = (U32)(total >> tableLog);
+
+        for (s=0; s<=maxSymbolValue; s++) {
+            if (count[s] == total) return 0;   /* rle special case */
+            if (count[s] == 0) { normalizedCounter[s]=0; continue; }
+            if (count[s] <= lowThreshold) {
+                normalizedCounter[s] = lowProbCount;
+                stillToDistribute--;
+            } else {
+                short proba = (short)((count[s]*step) >> scale);
+                if (proba<8) {
+                    U64 restToBeat = vStep * rtbTable[proba];
+                    proba += (count[s]*step) - ((U64)proba<<scale) > restToBeat;
+                }
+                if (proba > largestP) { largestP=proba; largest=s; }
+                normalizedCounter[s] = proba;
+                stillToDistribute -= proba;
+        }   }
+        if (-stillToDistribute >= (normalizedCounter[largest] >> 1)) {
+            /* corner case, need another normalization method */
+            size_t const errorCode = FSE_normalizeM2(normalizedCounter, tableLog, count, total, maxSymbolValue, lowProbCount);
+            if (FSE_isError(errorCode)) return errorCode;
+        }
+        else normalizedCounter[largest] += (short)stillToDistribute;
+    }
+
+#if 0
+    {   /* Print Table (debug) */
+        U32 s;
+        U32 nTotal = 0;
+        for (s=0; s<=maxSymbolValue; s++)
+            RAWLOG(2, "%3i: %4i \n", s, normalizedCounter[s]);
+        for (s=0; s<=maxSymbolValue; s++)
+            nTotal += abs(normalizedCounter[s]);
+        if (nTotal != (1U<<tableLog))
+            RAWLOG(2, "Warning !!! Total == %u != %u !!!", nTotal, 1U<<tableLog);
+        getchar();
+    }
+#endif
+
+    return tableLog;
+}
+
+
+/* fake FSE_CTable, for raw (uncompressed) input */
+size_t FSE_buildCTable_raw (FSE_CTable* ct, unsigned nbBits)
+{
+    const unsigned tableSize = 1 << nbBits;
+    const unsigned tableMask = tableSize - 1;
+    const unsigned maxSymbolValue = tableMask;
+    void* const ptr = ct;
+    U16* const tableU16 = ( (U16*) ptr) + 2;
+    void* const FSCT = ((U32*)ptr) + 1 /* header */ + (tableSize>>1);   /* assumption : tableLog >= 1 */
+    FSE_symbolCompressionTransform* const symbolTT = (FSE_symbolCompressionTransform*) (FSCT);
+    unsigned s;
+
+    /* Sanity checks */
+    if (nbBits < 1) return ERROR(GENERIC);             /* min size */
+
+    /* header */
+    tableU16[-2] = (U16) nbBits;
+    tableU16[-1] = (U16) maxSymbolValue;
+
+    /* Build table */
+    for (s=0; s<tableSize; s++)
+        tableU16[s] = (U16)(tableSize + s);
+
+    /* Build Symbol Transformation Table */
+    {   const U32 deltaNbBits = (nbBits << 16) - (1 << nbBits);
+        for (s=0; s<=maxSymbolValue; s++) {
+            symbolTT[s].deltaNbBits = deltaNbBits;
+            symbolTT[s].deltaFindState = s-1;
+    }   }
+
+    return 0;
+}
+
+/* fake FSE_CTable, for rle input (always same symbol) */
+size_t FSE_buildCTable_rle (FSE_CTable* ct, BYTE symbolValue)
+{
+    void* ptr = ct;
+    U16* tableU16 = ( (U16*) ptr) + 2;
+    void* FSCTptr = (U32*)ptr + 2;
+    FSE_symbolCompressionTransform* symbolTT = (FSE_symbolCompressionTransform*) FSCTptr;
+
+    /* header */
+    tableU16[-2] = (U16) 0;
+    tableU16[-1] = (U16) symbolValue;
+
+    /* Build table */
+    tableU16[0] = 0;
+    tableU16[1] = 0;   /* just in case */
+
+    /* Build Symbol Transformation Table */
+    symbolTT[symbolValue].deltaNbBits = 0;
+    symbolTT[symbolValue].deltaFindState = 0;
+
+    return 0;
+}
+
+
+static size_t FSE_compress_usingCTable_generic (void* dst, size_t dstSize,
+                           const void* src, size_t srcSize,
+                           const FSE_CTable* ct, const unsigned fast)
+{
+    const BYTE* const istart = (const BYTE*) src;
+    const BYTE* const iend = istart + srcSize;
+    const BYTE* ip=iend;
+
+    BIT_CStream_t bitC;
+    FSE_CState_t CState1, CState2;
+
+    /* init */
+    if (srcSize <= 2) return 0;
+    { size_t const initError = BIT_initCStream(&bitC, dst, dstSize);
+      if (FSE_isError(initError)) return 0; /* not enough space available to write a bitstream */ }
+
+#define FSE_FLUSHBITS(s)  (fast ? BIT_flushBitsFast(s) : BIT_flushBits(s))
+
+    if (srcSize & 1) {
+        FSE_initCState2(&CState1, ct, *--ip);
+        FSE_initCState2(&CState2, ct, *--ip);
+        FSE_encodeSymbol(&bitC, &CState1, *--ip);
+        FSE_FLUSHBITS(&bitC);
+    } else {
+        FSE_initCState2(&CState2, ct, *--ip);
+        FSE_initCState2(&CState1, ct, *--ip);
+    }
+
+    /* join to mod 4 */
+    srcSize -= 2;
+    if ((sizeof(bitC.bitContainer)*8 > FSE_MAX_TABLELOG*4+7 ) && (srcSize & 2)) {  /* test bit 2 */
+        FSE_encodeSymbol(&bitC, &CState2, *--ip);
+        FSE_encodeSymbol(&bitC, &CState1, *--ip);
+        FSE_FLUSHBITS(&bitC);
+    }
+
+    /* 2 or 4 encoding per loop */
+    while ( ip>istart ) {
+
+        FSE_encodeSymbol(&bitC, &CState2, *--ip);
+
+        if (sizeof(bitC.bitContainer)*8 < FSE_MAX_TABLELOG*2+7 )   /* this test must be static */
+            FSE_FLUSHBITS(&bitC);
+
+        FSE_encodeSymbol(&bitC, &CState1, *--ip);
+
+        if (sizeof(bitC.bitContainer)*8 > FSE_MAX_TABLELOG*4+7 ) {  /* this test must be static */
+            FSE_encodeSymbol(&bitC, &CState2, *--ip);
+            FSE_encodeSymbol(&bitC, &CState1, *--ip);
+        }
+
+        FSE_FLUSHBITS(&bitC);
+    }
+
+    FSE_flushCState(&bitC, &CState2);
+    FSE_flushCState(&bitC, &CState1);
+    return BIT_closeCStream(&bitC);
+}
+
+size_t FSE_compress_usingCTable (void* dst, size_t dstSize,
+                           const void* src, size_t srcSize,
+                           const FSE_CTable* ct)
+{
+    unsigned const fast = (dstSize >= FSE_BLOCKBOUND(srcSize));
+
+    if (fast)
+        return FSE_compress_usingCTable_generic(dst, dstSize, src, srcSize, ct, 1);
+    else
+        return FSE_compress_usingCTable_generic(dst, dstSize, src, srcSize, ct, 0);
+}
+
+
+size_t FSE_compressBound(size_t size) { return FSE_COMPRESSBOUND(size); }
+
+
+#endif   /* FSE_COMMONDEFS_ONLY */
diff --git a/lib/zstd/compress/hist.c b/lib/zstd/compress/hist.c
new file mode 100644
index 000000000000..3ddc6dfb6894
--- /dev/null
+++ b/lib/zstd/compress/hist.c
@@ -0,0 +1,165 @@
+/* ******************************************************************
+ * hist : Histogram functions
+ * part of Finite State Entropy project
+ * Copyright (c) Yann Collet, Facebook, Inc.
+ *
+ *  You can contact the author at :
+ *  - FSE source repository : https://github.com/Cyan4973/FiniteStateEntropy
+ *  - Public forum : https://groups.google.com/forum/#!forum/lz4c
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+****************************************************************** */
+
+/* --- dependencies --- */
+#include "../common/mem.h"             /* U32, BYTE, etc. */
+#include "../common/debug.h"           /* assert, DEBUGLOG */
+#include "../common/error_private.h"   /* ERROR */
+#include "hist.h"
+
+
+/* --- Error management --- */
+unsigned HIST_isError(size_t code) { return ERR_isError(code); }
+
+/*-**************************************************************
+ *  Histogram functions
+ ****************************************************************/
+unsigned HIST_count_simple(unsigned* count, unsigned* maxSymbolValuePtr,
+                           const void* src, size_t srcSize)
+{
+    const BYTE* ip = (const BYTE*)src;
+    const BYTE* const end = ip + srcSize;
+    unsigned maxSymbolValue = *maxSymbolValuePtr;
+    unsigned largestCount=0;
+
+    ZSTD_memset(count, 0, (maxSymbolValue+1) * sizeof(*count));
+    if (srcSize==0) { *maxSymbolValuePtr = 0; return 0; }
+
+    while (ip<end) {
+        assert(*ip <= maxSymbolValue);
+        count[*ip++]++;
+    }
+
+    while (!count[maxSymbolValue]) maxSymbolValue--;
+    *maxSymbolValuePtr = maxSymbolValue;
+
+    {   U32 s;
+        for (s=0; s<=maxSymbolValue; s++)
+            if (count[s] > largestCount) largestCount = count[s];
+    }
+
+    return largestCount;
+}
+
+typedef enum { trustInput, checkMaxSymbolValue } HIST_checkInput_e;
+
+/* HIST_count_parallel_wksp() :
+ * store histogram into 4 intermediate tables, recombined at the end.
+ * this design makes better use of OoO cpus,
+ * and is noticeably faster when some values are heavily repeated.
+ * But it needs some additional workspace for intermediate tables.
+ * `workSpace` must be a U32 table of size >= HIST_WKSP_SIZE_U32.
+ * @return : largest histogram frequency,
+ *           or an error code (notably when histogram's alphabet is larger than *maxSymbolValuePtr) */
+static size_t HIST_count_parallel_wksp(
+                                unsigned* count, unsigned* maxSymbolValuePtr,
+                                const void* source, size_t sourceSize,
+                                HIST_checkInput_e check,
+                                U32* const workSpace)
+{
+    const BYTE* ip = (const BYTE*)source;
+    const BYTE* const iend = ip+sourceSize;
+    size_t const countSize = (*maxSymbolValuePtr + 1) * sizeof(*count);
+    unsigned max=0;
+    U32* const Counting1 = workSpace;
+    U32* const Counting2 = Counting1 + 256;
+    U32* const Counting3 = Counting2 + 256;
+    U32* const Counting4 = Counting3 + 256;
+
+    /* safety checks */
+    assert(*maxSymbolValuePtr <= 255);
+    if (!sourceSize) {
+        ZSTD_memset(count, 0, countSize);
+        *maxSymbolValuePtr = 0;
+        return 0;
+    }
+    ZSTD_memset(workSpace, 0, 4*256*sizeof(unsigned));
+
+    /* by stripes of 16 bytes */
+    {   U32 cached = MEM_read32(ip); ip += 4;
+        while (ip < iend-15) {
+            U32 c = cached; cached = MEM_read32(ip); ip += 4;
+            Counting1[(BYTE) c     ]++;
+            Counting2[(BYTE)(c>>8) ]++;
+            Counting3[(BYTE)(c>>16)]++;
+            Counting4[       c>>24 ]++;
+            c = cached; cached = MEM_read32(ip); ip += 4;
+            Counting1[(BYTE) c     ]++;
+            Counting2[(BYTE)(c>>8) ]++;
+            Counting3[(BYTE)(c>>16)]++;
+            Counting4[       c>>24 ]++;
+            c = cached; cached = MEM_read32(ip); ip += 4;
+            Counting1[(BYTE) c     ]++;
+            Counting2[(BYTE)(c>>8) ]++;
+            Counting3[(BYTE)(c>>16)]++;
+            Counting4[       c>>24 ]++;
+            c = cached; cached = MEM_read32(ip); ip += 4;
+            Counting1[(BYTE) c     ]++;
+            Counting2[(BYTE)(c>>8) ]++;
+            Counting3[(BYTE)(c>>16)]++;
+            Counting4[       c>>24 ]++;
+        }
+        ip-=4;
+    }
+
+    /* finish last symbols */
+    while (ip<iend) Counting1[*ip++]++;
+
+    {   U32 s;
+        for (s=0; s<256; s++) {
+            Counting1[s] += Counting2[s] + Counting3[s] + Counting4[s];
+            if (Counting1[s] > max) max = Counting1[s];
+    }   }
+
+    {   unsigned maxSymbolValue = 255;
+        while (!Counting1[maxSymbolValue]) maxSymbolValue--;
+        if (check && maxSymbolValue > *maxSymbolValuePtr) return ERROR(maxSymbolValue_tooSmall);
+        *maxSymbolValuePtr = maxSymbolValue;
+        ZSTD_memmove(count, Counting1, countSize);   /* in case count & Counting1 are overlapping */
+    }
+    return (size_t)max;
+}
+
+/* HIST_countFast_wksp() :
+ * Same as HIST_countFast(), but using an externally provided scratch buffer.
+ * `workSpace` is a writable buffer which must be 4-bytes aligned,
+ * `workSpaceSize` must be >= HIST_WKSP_SIZE
+ */
+size_t HIST_countFast_wksp(unsigned* count, unsigned* maxSymbolValuePtr,
+                          const void* source, size_t sourceSize,
+                          void* workSpace, size_t workSpaceSize)
+{
+    if (sourceSize < 1500) /* heuristic threshold */
+        return HIST_count_simple(count, maxSymbolValuePtr, source, sourceSize);
+    if ((size_t)workSpace & 3) return ERROR(GENERIC);  /* must be aligned on 4-bytes boundaries */
+    if (workSpaceSize < HIST_WKSP_SIZE) return ERROR(workSpace_tooSmall);
+    return HIST_count_parallel_wksp(count, maxSymbolValuePtr, source, sourceSize, trustInput, (U32*)workSpace);
+}
+
+/* HIST_count_wksp() :
+ * Same as HIST_count(), but using an externally provided scratch buffer.
+ * `workSpace` size must be table of >= HIST_WKSP_SIZE_U32 unsigned */
+size_t HIST_count_wksp(unsigned* count, unsigned* maxSymbolValuePtr,
+                       const void* source, size_t sourceSize,
+                       void* workSpace, size_t workSpaceSize)
+{
+    if ((size_t)workSpace & 3) return ERROR(GENERIC);  /* must be aligned on 4-bytes boundaries */
+    if (workSpaceSize < HIST_WKSP_SIZE) return ERROR(workSpace_tooSmall);
+    if (*maxSymbolValuePtr < 255)
+        return HIST_count_parallel_wksp(count, maxSymbolValuePtr, source, sourceSize, checkMaxSymbolValue, (U32*)workSpace);
+    *maxSymbolValuePtr = 255;
+    return HIST_countFast_wksp(count, maxSymbolValuePtr, source, sourceSize, workSpace, workSpaceSize);
+}
+
diff --git a/lib/zstd/compress/hist.h b/lib/zstd/compress/hist.h
new file mode 100644
index 000000000000..fc1830abc9c6
--- /dev/null
+++ b/lib/zstd/compress/hist.h
@@ -0,0 +1,75 @@
+/* ******************************************************************
+ * hist : Histogram functions
+ * part of Finite State Entropy project
+ * Copyright (c) Yann Collet, Facebook, Inc.
+ *
+ *  You can contact the author at :
+ *  - FSE source repository : https://github.com/Cyan4973/FiniteStateEntropy
+ *  - Public forum : https://groups.google.com/forum/#!forum/lz4c
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+****************************************************************** */
+
+/* --- dependencies --- */
+#include "../common/zstd_deps.h"   /* size_t */
+
+
+/* --- simple histogram functions --- */
+
+/*! HIST_count():
+ *  Provides the precise count of each byte within a table 'count'.
+ * 'count' is a table of unsigned int, of minimum size (*maxSymbolValuePtr+1).
+ *  Updates *maxSymbolValuePtr with actual largest symbol value detected.
+ * @return : count of the most frequent symbol (which isn't identified).
+ *           or an error code, which can be tested using HIST_isError().
+ *           note : if return == srcSize, there is only one symbol.
+ */
+size_t HIST_count(unsigned* count, unsigned* maxSymbolValuePtr,
+                  const void* src, size_t srcSize);
+
+unsigned HIST_isError(size_t code);  /*< tells if a return value is an error code */
+
+
+/* --- advanced histogram functions --- */
+
+#define HIST_WKSP_SIZE_U32 1024
+#define HIST_WKSP_SIZE    (HIST_WKSP_SIZE_U32 * sizeof(unsigned))
+/* HIST_count_wksp() :
+ *  Same as HIST_count(), but using an externally provided scratch buffer.
+ *  Benefit is this function will use very little stack space.
+ * `workSpace` is a writable buffer which must be 4-bytes aligned,
+ * `workSpaceSize` must be >= HIST_WKSP_SIZE
+ */
+size_t HIST_count_wksp(unsigned* count, unsigned* maxSymbolValuePtr,
+                       const void* src, size_t srcSize,
+                       void* workSpace, size_t workSpaceSize);
+
+/* HIST_countFast() :
+ *  same as HIST_count(), but blindly trusts that all byte values within src are <= *maxSymbolValuePtr.
+ *  This function is unsafe, and will segfault if any value within `src` is `> *maxSymbolValuePtr`
+ */
+size_t HIST_countFast(unsigned* count, unsigned* maxSymbolValuePtr,
+                      const void* src, size_t srcSize);
+
+/* HIST_countFast_wksp() :
+ *  Same as HIST_countFast(), but using an externally provided scratch buffer.
+ * `workSpace` is a writable buffer which must be 4-bytes aligned,
+ * `workSpaceSize` must be >= HIST_WKSP_SIZE
+ */
+size_t HIST_countFast_wksp(unsigned* count, unsigned* maxSymbolValuePtr,
+                           const void* src, size_t srcSize,
+                           void* workSpace, size_t workSpaceSize);
+
+/*! HIST_count_simple() :
+ *  Same as HIST_countFast(), this function is unsafe,
+ *  and will segfault if any value within `src` is `> *maxSymbolValuePtr`.
+ *  It is also a bit slower for large inputs.
+ *  However, it does not need any additional memory (not even on stack).
+ * @return : count of the most frequent symbol.
+ *  Note this function doesn't produce any error (i.e. it must succeed).
+ */
+unsigned HIST_count_simple(unsigned* count, unsigned* maxSymbolValuePtr,
+                           const void* src, size_t srcSize);
diff --git a/lib/zstd/compress/huf_compress.c b/lib/zstd/compress/huf_compress.c
new file mode 100644
index 000000000000..f76a526bfa54
--- /dev/null
+++ b/lib/zstd/compress/huf_compress.c
@@ -0,0 +1,905 @@
+/* ******************************************************************
+ * Huffman encoder, part of New Generation Entropy library
+ * Copyright (c) Yann Collet, Facebook, Inc.
+ *
+ *  You can contact the author at :
+ *  - FSE+HUF source repository : https://github.com/Cyan4973/FiniteStateEntropy
+ *  - Public forum : https://groups.google.com/forum/#!forum/lz4c
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+****************************************************************** */
+
+/* **************************************************************
+*  Compiler specifics
+****************************************************************/
+
+
+/* **************************************************************
+*  Includes
+****************************************************************/
+#include "../common/zstd_deps.h"     /* ZSTD_memcpy, ZSTD_memset */
+#include "../common/compiler.h"
+#include "../common/bitstream.h"
+#include "hist.h"
+#define FSE_STATIC_LINKING_ONLY   /* FSE_optimalTableLog_internal */
+#include "../common/fse.h"        /* header compression */
+#define HUF_STATIC_LINKING_ONLY
+#include "../common/huf.h"
+#include "../common/error_private.h"
+
+
+/* **************************************************************
+*  Error Management
+****************************************************************/
+#define HUF_isError ERR_isError
+#define HUF_STATIC_ASSERT(c) DEBUG_STATIC_ASSERT(c)   /* use only *after* variable declarations */
+
+
+/* **************************************************************
+*  Utils
+****************************************************************/
+unsigned HUF_optimalTableLog(unsigned maxTableLog, size_t srcSize, unsigned maxSymbolValue)
+{
+    return FSE_optimalTableLog_internal(maxTableLog, srcSize, maxSymbolValue, 1);
+}
+
+
+/* *******************************************************
+*  HUF : Huffman block compression
+*********************************************************/
+/* HUF_compressWeights() :
+ * Same as FSE_compress(), but dedicated to huff0's weights compression.
+ * The use case needs much less stack memory.
+ * Note : all elements within weightTable are supposed to be <= HUF_TABLELOG_MAX.
+ */
+#define MAX_FSE_TABLELOG_FOR_HUFF_HEADER 6
+
+typedef struct {
+    FSE_CTable CTable[FSE_CTABLE_SIZE_U32(MAX_FSE_TABLELOG_FOR_HUFF_HEADER, HUF_TABLELOG_MAX)];
+    U32 scratchBuffer[FSE_BUILD_CTABLE_WORKSPACE_SIZE_U32(HUF_TABLELOG_MAX, MAX_FSE_TABLELOG_FOR_HUFF_HEADER)];
+    unsigned count[HUF_TABLELOG_MAX+1];
+    S16 norm[HUF_TABLELOG_MAX+1];
+} HUF_CompressWeightsWksp;
+
+static size_t HUF_compressWeights(void* dst, size_t dstSize, const void* weightTable, size_t wtSize, void* workspace, size_t workspaceSize)
+{
+    BYTE* const ostart = (BYTE*) dst;
+    BYTE* op = ostart;
+    BYTE* const oend = ostart + dstSize;
+
+    unsigned maxSymbolValue = HUF_TABLELOG_MAX;
+    U32 tableLog = MAX_FSE_TABLELOG_FOR_HUFF_HEADER;
+    HUF_CompressWeightsWksp* wksp = (HUF_CompressWeightsWksp*)workspace;
+
+    if (workspaceSize < sizeof(HUF_CompressWeightsWksp)) return ERROR(GENERIC);
+
+    /* init conditions */
+    if (wtSize <= 1) return 0;  /* Not compressible */
+
+    /* Scan input and build symbol stats */
+    {   unsigned const maxCount = HIST_count_simple(wksp->count, &maxSymbolValue, weightTable, wtSize);   /* never fails */
+        if (maxCount == wtSize) return 1;   /* only a single symbol in src : rle */
+        if (maxCount == 1) return 0;        /* each symbol present maximum once => not compressible */
+    }
+
+    tableLog = FSE_optimalTableLog(tableLog, wtSize, maxSymbolValue);
+    CHECK_F( FSE_normalizeCount(wksp->norm, tableLog, wksp->count, wtSize, maxSymbolValue, /* useLowProbCount */ 0) );
+
+    /* Write table description header */
+    {   CHECK_V_F(hSize, FSE_writeNCount(op, (size_t)(oend-op), wksp->norm, maxSymbolValue, tableLog) );
+        op += hSize;
+    }
+
+    /* Compress */
+    CHECK_F( FSE_buildCTable_wksp(wksp->CTable, wksp->norm, maxSymbolValue, tableLog, wksp->scratchBuffer, sizeof(wksp->scratchBuffer)) );
+    {   CHECK_V_F(cSize, FSE_compress_usingCTable(op, (size_t)(oend - op), weightTable, wtSize, wksp->CTable) );
+        if (cSize == 0) return 0;   /* not enough space for compressed data */
+        op += cSize;
+    }
+
+    return (size_t)(op-ostart);
+}
+
+
+typedef struct {
+    HUF_CompressWeightsWksp wksp;
+    BYTE bitsToWeight[HUF_TABLELOG_MAX + 1];   /* precomputed conversion table */
+    BYTE huffWeight[HUF_SYMBOLVALUE_MAX];
+} HUF_WriteCTableWksp;
+
+size_t HUF_writeCTable_wksp(void* dst, size_t maxDstSize,
+                            const HUF_CElt* CTable, unsigned maxSymbolValue, unsigned huffLog,
+                            void* workspace, size_t workspaceSize)
+{
+    BYTE* op = (BYTE*)dst;
+    U32 n;
+    HUF_WriteCTableWksp* wksp = (HUF_WriteCTableWksp*)workspace;
+
+    /* check conditions */
+    if (workspaceSize < sizeof(HUF_WriteCTableWksp)) return ERROR(GENERIC);
+    if (maxSymbolValue > HUF_SYMBOLVALUE_MAX) return ERROR(maxSymbolValue_tooLarge);
+
+    /* convert to weight */
+    wksp->bitsToWeight[0] = 0;
+    for (n=1; n<huffLog+1; n++)
+        wksp->bitsToWeight[n] = (BYTE)(huffLog + 1 - n);
+    for (n=0; n<maxSymbolValue; n++)
+        wksp->huffWeight[n] = wksp->bitsToWeight[CTable[n].nbBits];
+
+    /* attempt weights compression by FSE */
+    {   CHECK_V_F(hSize, HUF_compressWeights(op+1, maxDstSize-1, wksp->huffWeight, maxSymbolValue, &wksp->wksp, sizeof(wksp->wksp)) );
+        if ((hSize>1) & (hSize < maxSymbolValue/2)) {   /* FSE compressed */
+            op[0] = (BYTE)hSize;
+            return hSize+1;
+    }   }
+
+    /* write raw values as 4-bits (max : 15) */
+    if (maxSymbolValue > (256-128)) return ERROR(GENERIC);   /* should not happen : likely means source cannot be compressed */
+    if (((maxSymbolValue+1)/2) + 1 > maxDstSize) return ERROR(dstSize_tooSmall);   /* not enough space within dst buffer */
+    op[0] = (BYTE)(128 /*special case*/ + (maxSymbolValue-1));
+    wksp->huffWeight[maxSymbolValue] = 0;   /* to be sure it doesn't cause msan issue in final combination */
+    for (n=0; n<maxSymbolValue; n+=2)
+        op[(n/2)+1] = (BYTE)((wksp->huffWeight[n] << 4) + wksp->huffWeight[n+1]);
+    return ((maxSymbolValue+1)/2) + 1;
+}
+
+/*! HUF_writeCTable() :
+    `CTable` : Huffman tree to save, using huf representation.
+    @return : size of saved CTable */
+size_t HUF_writeCTable (void* dst, size_t maxDstSize,
+                        const HUF_CElt* CTable, unsigned maxSymbolValue, unsigned huffLog)
+{
+    HUF_WriteCTableWksp wksp;
+    return HUF_writeCTable_wksp(dst, maxDstSize, CTable, maxSymbolValue, huffLog, &wksp, sizeof(wksp));
+}
+
+
+size_t HUF_readCTable (HUF_CElt* CTable, unsigned* maxSymbolValuePtr, const void* src, size_t srcSize, unsigned* hasZeroWeights)
+{
+    BYTE huffWeight[HUF_SYMBOLVALUE_MAX + 1];   /* init not required, even though some static analyzer may complain */
+    U32 rankVal[HUF_TABLELOG_ABSOLUTEMAX + 1];   /* large enough for values from 0 to 16 */
+    U32 tableLog = 0;
+    U32 nbSymbols = 0;
+
+    /* get symbol weights */
+    CHECK_V_F(readSize, HUF_readStats(huffWeight, HUF_SYMBOLVALUE_MAX+1, rankVal, &nbSymbols, &tableLog, src, srcSize));
+    *hasZeroWeights = (rankVal[0] > 0);
+
+    /* check result */
+    if (tableLog > HUF_TABLELOG_MAX) return ERROR(tableLog_tooLarge);
+    if (nbSymbols > *maxSymbolValuePtr+1) return ERROR(maxSymbolValue_tooSmall);
+
+    /* Prepare base value per rank */
+    {   U32 n, nextRankStart = 0;
+        for (n=1; n<=tableLog; n++) {
+            U32 curr = nextRankStart;
+            nextRankStart += (rankVal[n] << (n-1));
+            rankVal[n] = curr;
+    }   }
+
+    /* fill nbBits */
+    {   U32 n; for (n=0; n<nbSymbols; n++) {
+            const U32 w = huffWeight[n];
+            CTable[n].nbBits = (BYTE)(tableLog + 1 - w) & -(w != 0);
+    }   }
+
+    /* fill val */
+    {   U16 nbPerRank[HUF_TABLELOG_MAX+2]  = {0};  /* support w=0=>n=tableLog+1 */
+        U16 valPerRank[HUF_TABLELOG_MAX+2] = {0};
+        { U32 n; for (n=0; n<nbSymbols; n++) nbPerRank[CTable[n].nbBits]++; }
+        /* determine stating value per rank */
+        valPerRank[tableLog+1] = 0;   /* for w==0 */
+        {   U16 min = 0;
+            U32 n; for (n=tableLog; n>0; n--) {  /* start at n=tablelog <-> w=1 */
+                valPerRank[n] = min;     /* get starting value within each rank */
+                min += nbPerRank[n];
+                min >>= 1;
+        }   }
+        /* assign value within rank, symbol order */
+        { U32 n; for (n=0; n<nbSymbols; n++) CTable[n].val = valPerRank[CTable[n].nbBits]++; }
+    }
+
+    *maxSymbolValuePtr = nbSymbols - 1;
+    return readSize;
+}
+
+U32 HUF_getNbBits(const void* symbolTable, U32 symbolValue)
+{
+    const HUF_CElt* table = (const HUF_CElt*)symbolTable;
+    assert(symbolValue <= HUF_SYMBOLVALUE_MAX);
+    return table[symbolValue].nbBits;
+}
+
+
+typedef struct nodeElt_s {
+    U32 count;
+    U16 parent;
+    BYTE byte;
+    BYTE nbBits;
+} nodeElt;
+
+/*
+ * HUF_setMaxHeight():
+ * Enforces maxNbBits on the Huffman tree described in huffNode.
+ *
+ * It sets all nodes with nbBits > maxNbBits to be maxNbBits. Then it adjusts
+ * the tree to so that it is a valid canonical Huffman tree.
+ *
+ * @pre               The sum of the ranks of each symbol == 2^largestBits,
+ *                    where largestBits == huffNode[lastNonNull].nbBits.
+ * @post              The sum of the ranks of each symbol == 2^largestBits,
+ *                    where largestBits is the return value <= maxNbBits.
+ *
+ * @param huffNode    The Huffman tree modified in place to enforce maxNbBits.
+ * @param lastNonNull The symbol with the lowest count in the Huffman tree.
+ * @param maxNbBits   The maximum allowed number of bits, which the Huffman tree
+ *                    may not respect. After this function the Huffman tree will
+ *                    respect maxNbBits.
+ * @return            The maximum number of bits of the Huffman tree after adjustment,
+ *                    necessarily no more than maxNbBits.
+ */
+static U32 HUF_setMaxHeight(nodeElt* huffNode, U32 lastNonNull, U32 maxNbBits)
+{
+    const U32 largestBits = huffNode[lastNonNull].nbBits;
+    /* early exit : no elt > maxNbBits, so the tree is already valid. */
+    if (largestBits <= maxNbBits) return largestBits;
+
+    /* there are several too large elements (at least >= 2) */
+    {   int totalCost = 0;
+        const U32 baseCost = 1 << (largestBits - maxNbBits);
+        int n = (int)lastNonNull;
+
+        /* Adjust any ranks > maxNbBits to maxNbBits.
+         * Compute totalCost, which is how far the sum of the ranks is
+         * we are over 2^largestBits after adjust the offending ranks.
+         */
+        while (huffNode[n].nbBits > maxNbBits) {
+            totalCost += baseCost - (1 << (largestBits - huffNode[n].nbBits));
+            huffNode[n].nbBits = (BYTE)maxNbBits;
+            n--;
+        }
+        /* n stops at huffNode[n].nbBits <= maxNbBits */
+        assert(huffNode[n].nbBits <= maxNbBits);
+        /* n end at index of smallest symbol using < maxNbBits */
+        while (huffNode[n].nbBits == maxNbBits) --n;
+
+        /* renorm totalCost from 2^largestBits to 2^maxNbBits
+         * note : totalCost is necessarily a multiple of baseCost */
+        assert((totalCost & (baseCost - 1)) == 0);
+        totalCost >>= (largestBits - maxNbBits);
+        assert(totalCost > 0);
+
+        /* repay normalized cost */
+        {   U32 const noSymbol = 0xF0F0F0F0;
+            U32 rankLast[HUF_TABLELOG_MAX+2];
+
+            /* Get pos of last (smallest = lowest cum. count) symbol per rank */
+            ZSTD_memset(rankLast, 0xF0, sizeof(rankLast));
+            {   U32 currentNbBits = maxNbBits;
+                int pos;
+                for (pos=n ; pos >= 0; pos--) {
+                    if (huffNode[pos].nbBits >= currentNbBits) continue;
+                    currentNbBits = huffNode[pos].nbBits;   /* < maxNbBits */
+                    rankLast[maxNbBits-currentNbBits] = (U32)pos;
+            }   }
+
+            while (totalCost > 0) {
+                /* Try to reduce the next power of 2 above totalCost because we
+                 * gain back half the rank.
+                 */
+                U32 nBitsToDecrease = BIT_highbit32((U32)totalCost) + 1;
+                for ( ; nBitsToDecrease > 1; nBitsToDecrease--) {
+                    U32 const highPos = rankLast[nBitsToDecrease];
+                    U32 const lowPos = rankLast[nBitsToDecrease-1];
+                    if (highPos == noSymbol) continue;
+                    /* Decrease highPos if no symbols of lowPos or if it is
+                     * not cheaper to remove 2 lowPos than highPos.
+                     */
+                    if (lowPos == noSymbol) break;
+                    {   U32 const highTotal = huffNode[highPos].count;
+                        U32 const lowTotal = 2 * huffNode[lowPos].count;
+                        if (highTotal <= lowTotal) break;
+                }   }
+                /* only triggered when no more rank 1 symbol left => find closest one (note : there is necessarily at least one !) */
+                assert(rankLast[nBitsToDecrease] != noSymbol || nBitsToDecrease == 1);
+                /* HUF_MAX_TABLELOG test just to please gcc 5+; but it should not be necessary */
+                while ((nBitsToDecrease<=HUF_TABLELOG_MAX) && (rankLast[nBitsToDecrease] == noSymbol))
+                    nBitsToDecrease++;
+                assert(rankLast[nBitsToDecrease] != noSymbol);
+                /* Increase the number of bits to gain back half the rank cost. */
+                totalCost -= 1 << (nBitsToDecrease-1);
+                huffNode[rankLast[nBitsToDecrease]].nbBits++;
+
+                /* Fix up the new rank.
+                 * If the new rank was empty, this symbol is now its smallest.
+                 * Otherwise, this symbol will be the largest in the new rank so no adjustment.
+                 */
+                if (rankLast[nBitsToDecrease-1] == noSymbol)
+                    rankLast[nBitsToDecrease-1] = rankLast[nBitsToDecrease];
+                /* Fix up the old rank.
+                 * If the symbol was at position 0, meaning it was the highest weight symbol in the tree,
+                 * it must be the only symbol in its rank, so the old rank now has no symbols.
+                 * Otherwise, since the Huffman nodes are sorted by count, the previous position is now
+                 * the smallest node in the rank. If the previous position belongs to a different rank,
+                 * then the rank is now empty.
+                 */
+                if (rankLast[nBitsToDecrease] == 0)    /* special case, reached largest symbol */
+                    rankLast[nBitsToDecrease] = noSymbol;
+                else {
+                    rankLast[nBitsToDecrease]--;
+                    if (huffNode[rankLast[nBitsToDecrease]].nbBits != maxNbBits-nBitsToDecrease)
+                        rankLast[nBitsToDecrease] = noSymbol;   /* this rank is now empty */
+                }
+            }   /* while (totalCost > 0) */
+
+            /* If we've removed too much weight, then we have to add it back.
+             * To avoid overshooting again, we only adjust the smallest rank.
+             * We take the largest nodes from the lowest rank 0 and move them
+             * to rank 1. There's guaranteed to be enough rank 0 symbols because
+             * TODO.
+             */
+            while (totalCost < 0) {  /* Sometimes, cost correction overshoot */
+                /* special case : no rank 1 symbol (using maxNbBits-1);
+                 * let's create one from largest rank 0 (using maxNbBits).
+                 */
+                if (rankLast[1] == noSymbol) {
+                    while (huffNode[n].nbBits == maxNbBits) n--;
+                    huffNode[n+1].nbBits--;
+                    assert(n >= 0);
+                    rankLast[1] = (U32)(n+1);
+                    totalCost++;
+                    continue;
+                }
+                huffNode[ rankLast[1] + 1 ].nbBits--;
+                rankLast[1]++;
+                totalCost ++;
+            }
+        }   /* repay normalized cost */
+    }   /* there are several too large elements (at least >= 2) */
+
+    return maxNbBits;
+}
+
+typedef struct {
+    U32 base;
+    U32 curr;
+} rankPos;
+
+typedef nodeElt huffNodeTable[HUF_CTABLE_WORKSPACE_SIZE_U32];
+
+#define RANK_POSITION_TABLE_SIZE 32
+
+typedef struct {
+  huffNodeTable huffNodeTbl;
+  rankPos rankPosition[RANK_POSITION_TABLE_SIZE];
+} HUF_buildCTable_wksp_tables;
+
+/*
+ * HUF_sort():
+ * Sorts the symbols [0, maxSymbolValue] by count[symbol] in decreasing order.
+ *
+ * @param[out] huffNode       Sorted symbols by decreasing count. Only members `.count` and `.byte` are filled.
+ *                            Must have (maxSymbolValue + 1) entries.
+ * @param[in]  count          Histogram of the symbols.
+ * @param[in]  maxSymbolValue Maximum symbol value.
+ * @param      rankPosition   This is a scratch workspace. Must have RANK_POSITION_TABLE_SIZE entries.
+ */
+static void HUF_sort(nodeElt* huffNode, const unsigned* count, U32 maxSymbolValue, rankPos* rankPosition)
+{
+    int n;
+    int const maxSymbolValue1 = (int)maxSymbolValue + 1;
+
+    /* Compute base and set curr to base.
+     * For symbol s let lowerRank = BIT_highbit32(count[n]+1) and rank = lowerRank + 1.
+     * Then 2^lowerRank <= count[n]+1 <= 2^rank.
+     * We attribute each symbol to lowerRank's base value, because we want to know where
+     * each rank begins in the output, so for rank R we want to count ranks R+1 and above.
+     */
+    ZSTD_memset(rankPosition, 0, sizeof(*rankPosition) * RANK_POSITION_TABLE_SIZE);
+    for (n = 0; n < maxSymbolValue1; ++n) {
+        U32 lowerRank = BIT_highbit32(count[n] + 1);
+        rankPosition[lowerRank].base++;
+    }
+    assert(rankPosition[RANK_POSITION_TABLE_SIZE - 1].base == 0);
+    for (n = RANK_POSITION_TABLE_SIZE - 1; n > 0; --n) {
+        rankPosition[n-1].base += rankPosition[n].base;
+        rankPosition[n-1].curr = rankPosition[n-1].base;
+    }
+    /* Sort */
+    for (n = 0; n < maxSymbolValue1; ++n) {
+        U32 const c = count[n];
+        U32 const r = BIT_highbit32(c+1) + 1;
+        U32 pos = rankPosition[r].curr++;
+        /* Insert into the correct position in the rank.
+         * We have at most 256 symbols, so this insertion should be fine.
+         */
+        while ((pos > rankPosition[r].base) && (c > huffNode[pos-1].count)) {
+            huffNode[pos] = huffNode[pos-1];
+            pos--;
+        }
+        huffNode[pos].count = c;
+        huffNode[pos].byte  = (BYTE)n;
+    }
+}
+
+
+/* HUF_buildCTable_wksp() :
+ *  Same as HUF_buildCTable(), but using externally allocated scratch buffer.
+ *  `workSpace` must be aligned on 4-bytes boundaries, and be at least as large as sizeof(HUF_buildCTable_wksp_tables).
+ */
+#define STARTNODE (HUF_SYMBOLVALUE_MAX+1)
+
+/* HUF_buildTree():
+ * Takes the huffNode array sorted by HUF_sort() and builds an unlimited-depth Huffman tree.
+ *
+ * @param huffNode        The array sorted by HUF_sort(). Builds the Huffman tree in this array.
+ * @param maxSymbolValue  The maximum symbol value.
+ * @return                The smallest node in the Huffman tree (by count).
+ */
+static int HUF_buildTree(nodeElt* huffNode, U32 maxSymbolValue)
+{
+    nodeElt* const huffNode0 = huffNode - 1;
+    int nonNullRank;
+    int lowS, lowN;
+    int nodeNb = STARTNODE;
+    int n, nodeRoot;
+    /* init for parents */
+    nonNullRank = (int)maxSymbolValue;
+    while(huffNode[nonNullRank].count == 0) nonNullRank--;
+    lowS = nonNullRank; nodeRoot = nodeNb + lowS - 1; lowN = nodeNb;
+    huffNode[nodeNb].count = huffNode[lowS].count + huffNode[lowS-1].count;
+    huffNode[lowS].parent = huffNode[lowS-1].parent = (U16)nodeNb;
+    nodeNb++; lowS-=2;
+    for (n=nodeNb; n<=nodeRoot; n++) huffNode[n].count = (U32)(1U<<30);
+    huffNode0[0].count = (U32)(1U<<31);  /* fake entry, strong barrier */
+
+    /* create parents */
+    while (nodeNb <= nodeRoot) {
+        int const n1 = (huffNode[lowS].count < huffNode[lowN].count) ? lowS-- : lowN++;
+        int const n2 = (huffNode[lowS].count < huffNode[lowN].count) ? lowS-- : lowN++;
+        huffNode[nodeNb].count = huffNode[n1].count + huffNode[n2].count;
+        huffNode[n1].parent = huffNode[n2].parent = (U16)nodeNb;
+        nodeNb++;
+    }
+
+    /* distribute weights (unlimited tree height) */
+    huffNode[nodeRoot].nbBits = 0;
+    for (n=nodeRoot-1; n>=STARTNODE; n--)
+        huffNode[n].nbBits = huffNode[ huffNode[n].parent ].nbBits + 1;
+    for (n=0; n<=nonNullRank; n++)
+        huffNode[n].nbBits = huffNode[ huffNode[n].parent ].nbBits + 1;
+
+    return nonNullRank;
+}
+
+/*
+ * HUF_buildCTableFromTree():
+ * Build the CTable given the Huffman tree in huffNode.
+ *
+ * @param[out] CTable         The output Huffman CTable.
+ * @param      huffNode       The Huffman tree.
+ * @param      nonNullRank    The last and smallest node in the Huffman tree.
+ * @param      maxSymbolValue The maximum symbol value.
+ * @param      maxNbBits      The exact maximum number of bits used in the Huffman tree.
+ */
+static void HUF_buildCTableFromTree(HUF_CElt* CTable, nodeElt const* huffNode, int nonNullRank, U32 maxSymbolValue, U32 maxNbBits)
+{
+    /* fill result into ctable (val, nbBits) */
+    int n;
+    U16 nbPerRank[HUF_TABLELOG_MAX+1] = {0};
+    U16 valPerRank[HUF_TABLELOG_MAX+1] = {0};
+    int const alphabetSize = (int)(maxSymbolValue + 1);
+    for (n=0; n<=nonNullRank; n++)
+        nbPerRank[huffNode[n].nbBits]++;
+    /* determine starting value per rank */
+    {   U16 min = 0;
+        for (n=(int)maxNbBits; n>0; n--) {
+            valPerRank[n] = min;      /* get starting value within each rank */
+            min += nbPerRank[n];
+            min >>= 1;
+    }   }
+    for (n=0; n<alphabetSize; n++)
+        CTable[huffNode[n].byte].nbBits = huffNode[n].nbBits;   /* push nbBits per symbol, symbol order */
+    for (n=0; n<alphabetSize; n++)
+        CTable[n].val = valPerRank[CTable[n].nbBits]++;   /* assign value within rank, symbol order */
+}
+
+size_t HUF_buildCTable_wksp (HUF_CElt* tree, const unsigned* count, U32 maxSymbolValue, U32 maxNbBits, void* workSpace, size_t wkspSize)
+{
+    HUF_buildCTable_wksp_tables* const wksp_tables = (HUF_buildCTable_wksp_tables*)workSpace;
+    nodeElt* const huffNode0 = wksp_tables->huffNodeTbl;
+    nodeElt* const huffNode = huffNode0+1;
+    int nonNullRank;
+
+    /* safety checks */
+    if (((size_t)workSpace & 3) != 0) return ERROR(GENERIC);  /* must be aligned on 4-bytes boundaries */
+    if (wkspSize < sizeof(HUF_buildCTable_wksp_tables))
+      return ERROR(workSpace_tooSmall);
+    if (maxNbBits == 0) maxNbBits = HUF_TABLELOG_DEFAULT;
+    if (maxSymbolValue > HUF_SYMBOLVALUE_MAX)
+      return ERROR(maxSymbolValue_tooLarge);
+    ZSTD_memset(huffNode0, 0, sizeof(huffNodeTable));
+
+    /* sort, decreasing order */
+    HUF_sort(huffNode, count, maxSymbolValue, wksp_tables->rankPosition);
+
+    /* build tree */
+    nonNullRank = HUF_buildTree(huffNode, maxSymbolValue);
+
+    /* enforce maxTableLog */
+    maxNbBits = HUF_setMaxHeight(huffNode, (U32)nonNullRank, maxNbBits);
+    if (maxNbBits > HUF_TABLELOG_MAX) return ERROR(GENERIC);   /* check fit into table */
+
+    HUF_buildCTableFromTree(tree, huffNode, nonNullRank, maxSymbolValue, maxNbBits);
+
+    return maxNbBits;
+}
+
+size_t HUF_estimateCompressedSize(const HUF_CElt* CTable, const unsigned* count, unsigned maxSymbolValue)
+{
+    size_t nbBits = 0;
+    int s;
+    for (s = 0; s <= (int)maxSymbolValue; ++s) {
+        nbBits += CTable[s].nbBits * count[s];
+    }
+    return nbBits >> 3;
+}
+
+int HUF_validateCTable(const HUF_CElt* CTable, const unsigned* count, unsigned maxSymbolValue) {
+  int bad = 0;
+  int s;
+  for (s = 0; s <= (int)maxSymbolValue; ++s) {
+    bad |= (count[s] != 0) & (CTable[s].nbBits == 0);
+  }
+  return !bad;
+}
+
+size_t HUF_compressBound(size_t size) { return HUF_COMPRESSBOUND(size); }
+
+FORCE_INLINE_TEMPLATE void
+HUF_encodeSymbol(BIT_CStream_t* bitCPtr, U32 symbol, const HUF_CElt* CTable)
+{
+    BIT_addBitsFast(bitCPtr, CTable[symbol].val, CTable[symbol].nbBits);
+}
+
+#define HUF_FLUSHBITS(s)  BIT_flushBits(s)
+
+#define HUF_FLUSHBITS_1(stream) \
+    if (sizeof((stream)->bitContainer)*8 < HUF_TABLELOG_MAX*2+7) HUF_FLUSHBITS(stream)
+
+#define HUF_FLUSHBITS_2(stream) \
+    if (sizeof((stream)->bitContainer)*8 < HUF_TABLELOG_MAX*4+7) HUF_FLUSHBITS(stream)
+
+FORCE_INLINE_TEMPLATE size_t
+HUF_compress1X_usingCTable_internal_body(void* dst, size_t dstSize,
+                                   const void* src, size_t srcSize,
+                                   const HUF_CElt* CTable)
+{
+    const BYTE* ip = (const BYTE*) src;
+    BYTE* const ostart = (BYTE*)dst;
+    BYTE* const oend = ostart + dstSize;
+    BYTE* op = ostart;
+    size_t n;
+    BIT_CStream_t bitC;
+
+    /* init */
+    if (dstSize < 8) return 0;   /* not enough space to compress */
+    { size_t const initErr = BIT_initCStream(&bitC, op, (size_t)(oend-op));
+      if (HUF_isError(initErr)) return 0; }
+
+    n = srcSize & ~3;  /* join to mod 4 */
+    switch (srcSize & 3)
+    {
+        case 3:
+            HUF_encodeSymbol(&bitC, ip[n+ 2], CTable);
+            HUF_FLUSHBITS_2(&bitC);
+            ZSTD_FALLTHROUGH;
+        case 2:
+            HUF_encodeSymbol(&bitC, ip[n+ 1], CTable);
+            HUF_FLUSHBITS_1(&bitC);
+            ZSTD_FALLTHROUGH;
+        case 1:
+            HUF_encodeSymbol(&bitC, ip[n+ 0], CTable);
+            HUF_FLUSHBITS(&bitC);
+            ZSTD_FALLTHROUGH;
+        case 0: ZSTD_FALLTHROUGH;
+        default: break;
+    }
+
+    for (; n>0; n-=4) {  /* note : n&3==0 at this stage */
+        HUF_encodeSymbol(&bitC, ip[n- 1], CTable);
+        HUF_FLUSHBITS_1(&bitC);
+        HUF_encodeSymbol(&bitC, ip[n- 2], CTable);
+        HUF_FLUSHBITS_2(&bitC);
+        HUF_encodeSymbol(&bitC, ip[n- 3], CTable);
+        HUF_FLUSHBITS_1(&bitC);
+        HUF_encodeSymbol(&bitC, ip[n- 4], CTable);
+        HUF_FLUSHBITS(&bitC);
+    }
+
+    return BIT_closeCStream(&bitC);
+}
+
+#if DYNAMIC_BMI2
+
+static TARGET_ATTRIBUTE("bmi2") size_t
+HUF_compress1X_usingCTable_internal_bmi2(void* dst, size_t dstSize,
+                                   const void* src, size_t srcSize,
+                                   const HUF_CElt* CTable)
+{
+    return HUF_compress1X_usingCTable_internal_body(dst, dstSize, src, srcSize, CTable);
+}
+
+static size_t
+HUF_compress1X_usingCTable_internal_default(void* dst, size_t dstSize,
+                                      const void* src, size_t srcSize,
+                                      const HUF_CElt* CTable)
+{
+    return HUF_compress1X_usingCTable_internal_body(dst, dstSize, src, srcSize, CTable);
+}
+
+static size_t
+HUF_compress1X_usingCTable_internal(void* dst, size_t dstSize,
+                              const void* src, size_t srcSize,
+                              const HUF_CElt* CTable, const int bmi2)
+{
+    if (bmi2) {
+        return HUF_compress1X_usingCTable_internal_bmi2(dst, dstSize, src, srcSize, CTable);
+    }
+    return HUF_compress1X_usingCTable_internal_default(dst, dstSize, src, srcSize, CTable);
+}
+
+#else
+
+static size_t
+HUF_compress1X_usingCTable_internal(void* dst, size_t dstSize,
+                              const void* src, size_t srcSize,
+                              const HUF_CElt* CTable, const int bmi2)
+{
+    (void)bmi2;
+    return HUF_compress1X_usingCTable_internal_body(dst, dstSize, src, srcSize, CTable);
+}
+
+#endif
+
+size_t HUF_compress1X_usingCTable(void* dst, size_t dstSize, const void* src, size_t srcSize, const HUF_CElt* CTable)
+{
+    return HUF_compress1X_usingCTable_internal(dst, dstSize, src, srcSize, CTable, /* bmi2 */ 0);
+}
+
+
+static size_t
+HUF_compress4X_usingCTable_internal(void* dst, size_t dstSize,
+                              const void* src, size_t srcSize,
+                              const HUF_CElt* CTable, int bmi2)
+{
+    size_t const segmentSize = (srcSize+3)/4;   /* first 3 segments */
+    const BYTE* ip = (const BYTE*) src;
+    const BYTE* const iend = ip + srcSize;
+    BYTE* const ostart = (BYTE*) dst;
+    BYTE* const oend = ostart + dstSize;
+    BYTE* op = ostart;
+
+    if (dstSize < 6 + 1 + 1 + 1 + 8) return 0;   /* minimum space to compress successfully */
+    if (srcSize < 12) return 0;   /* no saving possible : too small input */
+    op += 6;   /* jumpTable */
+
+    assert(op <= oend);
+    {   CHECK_V_F(cSize, HUF_compress1X_usingCTable_internal(op, (size_t)(oend-op), ip, segmentSize, CTable, bmi2) );
+        if (cSize==0) return 0;
+        assert(cSize <= 65535);
+        MEM_writeLE16(ostart, (U16)cSize);
+        op += cSize;
+    }
+
+    ip += segmentSize;
+    assert(op <= oend);
+    {   CHECK_V_F(cSize, HUF_compress1X_usingCTable_internal(op, (size_t)(oend-op), ip, segmentSize, CTable, bmi2) );
+        if (cSize==0) return 0;
+        assert(cSize <= 65535);
+        MEM_writeLE16(ostart+2, (U16)cSize);
+        op += cSize;
+    }
+
+    ip += segmentSize;
+    assert(op <= oend);
+    {   CHECK_V_F(cSize, HUF_compress1X_usingCTable_internal(op, (size_t)(oend-op), ip, segmentSize, CTable, bmi2) );
+        if (cSize==0) return 0;
+        assert(cSize <= 65535);
+        MEM_writeLE16(ostart+4, (U16)cSize);
+        op += cSize;
+    }
+
+    ip += segmentSize;
+    assert(op <= oend);
+    assert(ip <= iend);
+    {   CHECK_V_F(cSize, HUF_compress1X_usingCTable_internal(op, (size_t)(oend-op), ip, (size_t)(iend-ip), CTable, bmi2) );
+        if (cSize==0) return 0;
+        op += cSize;
+    }
+
+    return (size_t)(op-ostart);
+}
+
+size_t HUF_compress4X_usingCTable(void* dst, size_t dstSize, const void* src, size_t srcSize, const HUF_CElt* CTable)
+{
+    return HUF_compress4X_usingCTable_internal(dst, dstSize, src, srcSize, CTable, /* bmi2 */ 0);
+}
+
+typedef enum { HUF_singleStream, HUF_fourStreams } HUF_nbStreams_e;
+
+static size_t HUF_compressCTable_internal(
+                BYTE* const ostart, BYTE* op, BYTE* const oend,
+                const void* src, size_t srcSize,
+                HUF_nbStreams_e nbStreams, const HUF_CElt* CTable, const int bmi2)
+{
+    size_t const cSize = (nbStreams==HUF_singleStream) ?
+                         HUF_compress1X_usingCTable_internal(op, (size_t)(oend - op), src, srcSize, CTable, bmi2) :
+                         HUF_compress4X_usingCTable_internal(op, (size_t)(oend - op), src, srcSize, CTable, bmi2);
+    if (HUF_isError(cSize)) { return cSize; }
+    if (cSize==0) { return 0; }   /* uncompressible */
+    op += cSize;
+    /* check compressibility */
+    assert(op >= ostart);
+    if ((size_t)(op-ostart) >= srcSize-1) { return 0; }
+    return (size_t)(op-ostart);
+}
+
+typedef struct {
+    unsigned count[HUF_SYMBOLVALUE_MAX + 1];
+    HUF_CElt CTable[HUF_SYMBOLVALUE_MAX + 1];
+    union {
+        HUF_buildCTable_wksp_tables buildCTable_wksp;
+        HUF_WriteCTableWksp writeCTable_wksp;
+    } wksps;
+} HUF_compress_tables_t;
+
+/* HUF_compress_internal() :
+ * `workSpace_align4` must be aligned on 4-bytes boundaries,
+ * and occupies the same space as a table of HUF_WORKSPACE_SIZE_U32 unsigned */
+static size_t
+HUF_compress_internal (void* dst, size_t dstSize,
+                 const void* src, size_t srcSize,
+                       unsigned maxSymbolValue, unsigned huffLog,
+                       HUF_nbStreams_e nbStreams,
+                       void* workSpace_align4, size_t wkspSize,
+                       HUF_CElt* oldHufTable, HUF_repeat* repeat, int preferRepeat,
+                 const int bmi2)
+{
+    HUF_compress_tables_t* const table = (HUF_compress_tables_t*)workSpace_align4;
+    BYTE* const ostart = (BYTE*)dst;
+    BYTE* const oend = ostart + dstSize;
+    BYTE* op = ostart;
+
+    HUF_STATIC_ASSERT(sizeof(*table) <= HUF_WORKSPACE_SIZE);
+    assert(((size_t)workSpace_align4 & 3) == 0);   /* must be aligned on 4-bytes boundaries */
+
+    /* checks & inits */
+    if (wkspSize < HUF_WORKSPACE_SIZE) return ERROR(workSpace_tooSmall);
+    if (!srcSize) return 0;  /* Uncompressed */
+    if (!dstSize) return 0;  /* cannot fit anything within dst budget */
+    if (srcSize > HUF_BLOCKSIZE_MAX) return ERROR(srcSize_wrong);   /* current block size limit */
+    if (huffLog > HUF_TABLELOG_MAX) return ERROR(tableLog_tooLarge);
+    if (maxSymbolValue > HUF_SYMBOLVALUE_MAX) return ERROR(maxSymbolValue_tooLarge);
+    if (!maxSymbolValue) maxSymbolValue = HUF_SYMBOLVALUE_MAX;
+    if (!huffLog) huffLog = HUF_TABLELOG_DEFAULT;
+
+    /* Heuristic : If old table is valid, use it for small inputs */
+    if (preferRepeat && repeat && *repeat == HUF_repeat_valid) {
+        return HUF_compressCTable_internal(ostart, op, oend,
+                                           src, srcSize,
+                                           nbStreams, oldHufTable, bmi2);
+    }
+
+    /* Scan input and build symbol stats */
+    {   CHECK_V_F(largest, HIST_count_wksp (table->count, &maxSymbolValue, (const BYTE*)src, srcSize, workSpace_align4, wkspSize) );
+        if (largest == srcSize) { *ostart = ((const BYTE*)src)[0]; return 1; }   /* single symbol, rle */
+        if (largest <= (srcSize >> 7)+4) return 0;   /* heuristic : probably not compressible enough */
+    }
+
+    /* Check validity of previous table */
+    if ( repeat
+      && *repeat == HUF_repeat_check
+      && !HUF_validateCTable(oldHufTable, table->count, maxSymbolValue)) {
+        *repeat = HUF_repeat_none;
+    }
+    /* Heuristic : use existing table for small inputs */
+    if (preferRepeat && repeat && *repeat != HUF_repeat_none) {
+        return HUF_compressCTable_internal(ostart, op, oend,
+                                           src, srcSize,
+                                           nbStreams, oldHufTable, bmi2);
+    }
+
+    /* Build Huffman Tree */
+    huffLog = HUF_optimalTableLog(huffLog, srcSize, maxSymbolValue);
+    {   size_t const maxBits = HUF_buildCTable_wksp(table->CTable, table->count,
+                                            maxSymbolValue, huffLog,
+                                            &table->wksps.buildCTable_wksp, sizeof(table->wksps.buildCTable_wksp));
+        CHECK_F(maxBits);
+        huffLog = (U32)maxBits;
+        /* Zero unused symbols in CTable, so we can check it for validity */
+        ZSTD_memset(table->CTable + (maxSymbolValue + 1), 0,
+               sizeof(table->CTable) - ((maxSymbolValue + 1) * sizeof(HUF_CElt)));
+    }
+
+    /* Write table description header */
+    {   CHECK_V_F(hSize, HUF_writeCTable_wksp(op, dstSize, table->CTable, maxSymbolValue, huffLog,
+                                              &table->wksps.writeCTable_wksp, sizeof(table->wksps.writeCTable_wksp)) );
+        /* Check if using previous huffman table is beneficial */
+        if (repeat && *repeat != HUF_repeat_none) {
+            size_t const oldSize = HUF_estimateCompressedSize(oldHufTable, table->count, maxSymbolValue);
+            size_t const newSize = HUF_estimateCompressedSize(table->CTable, table->count, maxSymbolValue);
+            if (oldSize <= hSize + newSize || hSize + 12 >= srcSize) {
+                return HUF_compressCTable_internal(ostart, op, oend,
+                                                   src, srcSize,
+                                                   nbStreams, oldHufTable, bmi2);
+        }   }
+
+        /* Use the new huffman table */
+        if (hSize + 12ul >= srcSize) { return 0; }
+        op += hSize;
+        if (repeat) { *repeat = HUF_repeat_none; }
+        if (oldHufTable)
+            ZSTD_memcpy(oldHufTable, table->CTable, sizeof(table->CTable));  /* Save new table */
+    }
+    return HUF_compressCTable_internal(ostart, op, oend,
+                                       src, srcSize,
+                                       nbStreams, table->CTable, bmi2);
+}
+
+
+size_t HUF_compress1X_wksp (void* dst, size_t dstSize,
+                      const void* src, size_t srcSize,
+                      unsigned maxSymbolValue, unsigned huffLog,
+                      void* workSpace, size_t wkspSize)
+{
+    return HUF_compress_internal(dst, dstSize, src, srcSize,
+                                 maxSymbolValue, huffLog, HUF_singleStream,
+                                 workSpace, wkspSize,
+                                 NULL, NULL, 0, 0 /*bmi2*/);
+}
+
+size_t HUF_compress1X_repeat (void* dst, size_t dstSize,
+                      const void* src, size_t srcSize,
+                      unsigned maxSymbolValue, unsigned huffLog,
+                      void* workSpace, size_t wkspSize,
+                      HUF_CElt* hufTable, HUF_repeat* repeat, int preferRepeat, int bmi2)
+{
+    return HUF_compress_internal(dst, dstSize, src, srcSize,
+                                 maxSymbolValue, huffLog, HUF_singleStream,
+                                 workSpace, wkspSize, hufTable,
+                                 repeat, preferRepeat, bmi2);
+}
+
+/* HUF_compress4X_repeat():
+ * compress input using 4 streams.
+ * provide workspace to generate compression tables */
+size_t HUF_compress4X_wksp (void* dst, size_t dstSize,
+                      const void* src, size_t srcSize,
+                      unsigned maxSymbolValue, unsigned huffLog,
+                      void* workSpace, size_t wkspSize)
+{
+    return HUF_compress_internal(dst, dstSize, src, srcSize,
+                                 maxSymbolValue, huffLog, HUF_fourStreams,
+                                 workSpace, wkspSize,
+                                 NULL, NULL, 0, 0 /*bmi2*/);
+}
+
+/* HUF_compress4X_repeat():
+ * compress input using 4 streams.
+ * re-use an existing huffman compression table */
+size_t HUF_compress4X_repeat (void* dst, size_t dstSize,
+                      const void* src, size_t srcSize,
+                      unsigned maxSymbolValue, unsigned huffLog,
+                      void* workSpace, size_t wkspSize,
+                      HUF_CElt* hufTable, HUF_repeat* repeat, int preferRepeat, int bmi2)
+{
+    return HUF_compress_internal(dst, dstSize, src, srcSize,
+                                 maxSymbolValue, huffLog, HUF_fourStreams,
+                                 workSpace, wkspSize,
+                                 hufTable, repeat, preferRepeat, bmi2);
+}
+
diff --git a/lib/zstd/compress/zstd_compress.c b/lib/zstd/compress/zstd_compress.c
new file mode 100644
index 000000000000..a4e916008b3a
--- /dev/null
+++ b/lib/zstd/compress/zstd_compress.c
@@ -0,0 +1,5109 @@
+/*
+ * Copyright (c) Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+/*-*************************************
+*  Dependencies
+***************************************/
+#include "../common/zstd_deps.h"  /* INT_MAX, ZSTD_memset, ZSTD_memcpy */
+#include "../common/cpu.h"
+#include "../common/mem.h"
+#include "hist.h"           /* HIST_countFast_wksp */
+#define FSE_STATIC_LINKING_ONLY   /* FSE_encodeSymbol */
+#include "../common/fse.h"
+#define HUF_STATIC_LINKING_ONLY
+#include "../common/huf.h"
+#include "zstd_compress_internal.h"
+#include "zstd_compress_sequences.h"
+#include "zstd_compress_literals.h"
+#include "zstd_fast.h"
+#include "zstd_double_fast.h"
+#include "zstd_lazy.h"
+#include "zstd_opt.h"
+#include "zstd_ldm.h"
+#include "zstd_compress_superblock.h"
+
+/* ***************************************************************
+*  Tuning parameters
+*****************************************************************/
+/*!
+ * COMPRESS_HEAPMODE :
+ * Select how default decompression function ZSTD_compress() allocates its context,
+ * on stack (0, default), or into heap (1).
+ * Note that functions with explicit context such as ZSTD_compressCCtx() are unaffected.
+ */
+
+
+/*-*************************************
+*  Helper functions
+***************************************/
+/* ZSTD_compressBound()
+ * Note that the result from this function is only compatible with the "normal"
+ * full-block strategy.
+ * When there are a lot of small blocks due to frequent flush in streaming mode
+ * the overhead of headers can make the compressed data to be larger than the
+ * return value of ZSTD_compressBound().
+ */
+size_t ZSTD_compressBound(size_t srcSize) {
+    return ZSTD_COMPRESSBOUND(srcSize);
+}
+
+
+/*-*************************************
+*  Context memory management
+***************************************/
+struct ZSTD_CDict_s {
+    const void* dictContent;
+    size_t dictContentSize;
+    ZSTD_dictContentType_e dictContentType; /* The dictContentType the CDict was created with */
+    U32* entropyWorkspace; /* entropy workspace of HUF_WORKSPACE_SIZE bytes */
+    ZSTD_cwksp workspace;
+    ZSTD_matchState_t matchState;
+    ZSTD_compressedBlockState_t cBlockState;
+    ZSTD_customMem customMem;
+    U32 dictID;
+    int compressionLevel; /* 0 indicates that advanced API was used to select CDict params */
+};  /* typedef'd to ZSTD_CDict within "zstd.h" */
+
+ZSTD_CCtx* ZSTD_createCCtx(void)
+{
+    return ZSTD_createCCtx_advanced(ZSTD_defaultCMem);
+}
+
+static void ZSTD_initCCtx(ZSTD_CCtx* cctx, ZSTD_customMem memManager)
+{
+    assert(cctx != NULL);
+    ZSTD_memset(cctx, 0, sizeof(*cctx));
+    cctx->customMem = memManager;
+    cctx->bmi2 = ZSTD_cpuid_bmi2(ZSTD_cpuid());
+    {   size_t const err = ZSTD_CCtx_reset(cctx, ZSTD_reset_parameters);
+        assert(!ZSTD_isError(err));
+        (void)err;
+    }
+}
+
+ZSTD_CCtx* ZSTD_createCCtx_advanced(ZSTD_customMem customMem)
+{
+    ZSTD_STATIC_ASSERT(zcss_init==0);
+    ZSTD_STATIC_ASSERT(ZSTD_CONTENTSIZE_UNKNOWN==(0ULL - 1));
+    if ((!customMem.customAlloc) ^ (!customMem.customFree)) return NULL;
+    {   ZSTD_CCtx* const cctx = (ZSTD_CCtx*)ZSTD_customMalloc(sizeof(ZSTD_CCtx), customMem);
+        if (!cctx) return NULL;
+        ZSTD_initCCtx(cctx, customMem);
+        return cctx;
+    }
+}
+
+ZSTD_CCtx* ZSTD_initStaticCCtx(void* workspace, size_t workspaceSize)
+{
+    ZSTD_cwksp ws;
+    ZSTD_CCtx* cctx;
+    if (workspaceSize <= sizeof(ZSTD_CCtx)) return NULL;  /* minimum size */
+    if ((size_t)workspace & 7) return NULL;  /* must be 8-aligned */
+    ZSTD_cwksp_init(&ws, workspace, workspaceSize, ZSTD_cwksp_static_alloc);
+
+    cctx = (ZSTD_CCtx*)ZSTD_cwksp_reserve_object(&ws, sizeof(ZSTD_CCtx));
+    if (cctx == NULL) return NULL;
+
+    ZSTD_memset(cctx, 0, sizeof(ZSTD_CCtx));
+    ZSTD_cwksp_move(&cctx->workspace, &ws);
+    cctx->staticSize = workspaceSize;
+
+    /* statically sized space. entropyWorkspace never moves (but prev/next block swap places) */
+    if (!ZSTD_cwksp_check_available(&cctx->workspace, ENTROPY_WORKSPACE_SIZE + 2 * sizeof(ZSTD_compressedBlockState_t))) return NULL;
+    cctx->blockState.prevCBlock = (ZSTD_compressedBlockState_t*)ZSTD_cwksp_reserve_object(&cctx->workspace, sizeof(ZSTD_compressedBlockState_t));
+    cctx->blockState.nextCBlock = (ZSTD_compressedBlockState_t*)ZSTD_cwksp_reserve_object(&cctx->workspace, sizeof(ZSTD_compressedBlockState_t));
+    cctx->entropyWorkspace = (U32*)ZSTD_cwksp_reserve_object(&cctx->workspace, ENTROPY_WORKSPACE_SIZE);
+    cctx->bmi2 = ZSTD_cpuid_bmi2(ZSTD_cpuid());
+    return cctx;
+}
+
+/*
+ * Clears and frees all of the dictionaries in the CCtx.
+ */
+static void ZSTD_clearAllDicts(ZSTD_CCtx* cctx)
+{
+    ZSTD_customFree(cctx->localDict.dictBuffer, cctx->customMem);
+    ZSTD_freeCDict(cctx->localDict.cdict);
+    ZSTD_memset(&cctx->localDict, 0, sizeof(cctx->localDict));
+    ZSTD_memset(&cctx->prefixDict, 0, sizeof(cctx->prefixDict));
+    cctx->cdict = NULL;
+}
+
+static size_t ZSTD_sizeof_localDict(ZSTD_localDict dict)
+{
+    size_t const bufferSize = dict.dictBuffer != NULL ? dict.dictSize : 0;
+    size_t const cdictSize = ZSTD_sizeof_CDict(dict.cdict);
+    return bufferSize + cdictSize;
+}
+
+static void ZSTD_freeCCtxContent(ZSTD_CCtx* cctx)
+{
+    assert(cctx != NULL);
+    assert(cctx->staticSize == 0);
+    ZSTD_clearAllDicts(cctx);
+    ZSTD_cwksp_free(&cctx->workspace, cctx->customMem);
+}
+
+size_t ZSTD_freeCCtx(ZSTD_CCtx* cctx)
+{
+    if (cctx==NULL) return 0;   /* support free on NULL */
+    RETURN_ERROR_IF(cctx->staticSize, memory_allocation,
+                    "not compatible with static CCtx");
+    {
+        int cctxInWorkspace = ZSTD_cwksp_owns_buffer(&cctx->workspace, cctx);
+        ZSTD_freeCCtxContent(cctx);
+        if (!cctxInWorkspace) {
+            ZSTD_customFree(cctx, cctx->customMem);
+        }
+    }
+    return 0;
+}
+
+
+static size_t ZSTD_sizeof_mtctx(const ZSTD_CCtx* cctx)
+{
+    (void)cctx;
+    return 0;
+}
+
+
+size_t ZSTD_sizeof_CCtx(const ZSTD_CCtx* cctx)
+{
+    if (cctx==NULL) return 0;   /* support sizeof on NULL */
+    /* cctx may be in the workspace */
+    return (cctx->workspace.workspace == cctx ? 0 : sizeof(*cctx))
+           + ZSTD_cwksp_sizeof(&cctx->workspace)
+           + ZSTD_sizeof_localDict(cctx->localDict)
+           + ZSTD_sizeof_mtctx(cctx);
+}
+
+size_t ZSTD_sizeof_CStream(const ZSTD_CStream* zcs)
+{
+    return ZSTD_sizeof_CCtx(zcs);  /* same object */
+}
+
+/* private API call, for dictBuilder only */
+const seqStore_t* ZSTD_getSeqStore(const ZSTD_CCtx* ctx) { return &(ctx->seqStore); }
+
+/* Returns 1 if compression parameters are such that we should
+ * enable long distance matching (wlog >= 27, strategy >= btopt).
+ * Returns 0 otherwise.
+ */
+static U32 ZSTD_CParams_shouldEnableLdm(const ZSTD_compressionParameters* const cParams) {
+    return cParams->strategy >= ZSTD_btopt && cParams->windowLog >= 27;
+}
+
+static ZSTD_CCtx_params ZSTD_makeCCtxParamsFromCParams(
+        ZSTD_compressionParameters cParams)
+{
+    ZSTD_CCtx_params cctxParams;
+    /* should not matter, as all cParams are presumed properly defined */
+    ZSTD_CCtxParams_init(&cctxParams, ZSTD_CLEVEL_DEFAULT);
+    cctxParams.cParams = cParams;
+
+    if (ZSTD_CParams_shouldEnableLdm(&cParams)) {
+        DEBUGLOG(4, "ZSTD_makeCCtxParamsFromCParams(): Including LDM into cctx params");
+        cctxParams.ldmParams.enableLdm = 1;
+        /* LDM is enabled by default for optimal parser and window size >= 128MB */
+        ZSTD_ldm_adjustParameters(&cctxParams.ldmParams, &cParams);
+        assert(cctxParams.ldmParams.hashLog >= cctxParams.ldmParams.bucketSizeLog);
+        assert(cctxParams.ldmParams.hashRateLog < 32);
+    }
+
+    assert(!ZSTD_checkCParams(cParams));
+    return cctxParams;
+}
+
+static ZSTD_CCtx_params* ZSTD_createCCtxParams_advanced(
+        ZSTD_customMem customMem)
+{
+    ZSTD_CCtx_params* params;
+    if ((!customMem.customAlloc) ^ (!customMem.customFree)) return NULL;
+    params = (ZSTD_CCtx_params*)ZSTD_customCalloc(
+            sizeof(ZSTD_CCtx_params), customMem);
+    if (!params) { return NULL; }
+    ZSTD_CCtxParams_init(params, ZSTD_CLEVEL_DEFAULT);
+    params->customMem = customMem;
+    return params;
+}
+
+ZSTD_CCtx_params* ZSTD_createCCtxParams(void)
+{
+    return ZSTD_createCCtxParams_advanced(ZSTD_defaultCMem);
+}
+
+size_t ZSTD_freeCCtxParams(ZSTD_CCtx_params* params)
+{
+    if (params == NULL) { return 0; }
+    ZSTD_customFree(params, params->customMem);
+    return 0;
+}
+
+size_t ZSTD_CCtxParams_reset(ZSTD_CCtx_params* params)
+{
+    return ZSTD_CCtxParams_init(params, ZSTD_CLEVEL_DEFAULT);
+}
+
+size_t ZSTD_CCtxParams_init(ZSTD_CCtx_params* cctxParams, int compressionLevel) {
+    RETURN_ERROR_IF(!cctxParams, GENERIC, "NULL pointer!");
+    ZSTD_memset(cctxParams, 0, sizeof(*cctxParams));
+    cctxParams->compressionLevel = compressionLevel;
+    cctxParams->fParams.contentSizeFlag = 1;
+    return 0;
+}
+
+#define ZSTD_NO_CLEVEL 0
+
+/*
+ * Initializes the cctxParams from params and compressionLevel.
+ * @param compressionLevel If params are derived from a compression level then that compression level, otherwise ZSTD_NO_CLEVEL.
+ */
+static void ZSTD_CCtxParams_init_internal(ZSTD_CCtx_params* cctxParams, ZSTD_parameters const* params, int compressionLevel)
+{
+    assert(!ZSTD_checkCParams(params->cParams));
+    ZSTD_memset(cctxParams, 0, sizeof(*cctxParams));
+    cctxParams->cParams = params->cParams;
+    cctxParams->fParams = params->fParams;
+    /* Should not matter, as all cParams are presumed properly defined.
+     * But, set it for tracing anyway.
+     */
+    cctxParams->compressionLevel = compressionLevel;
+}
+
+size_t ZSTD_CCtxParams_init_advanced(ZSTD_CCtx_params* cctxParams, ZSTD_parameters params)
+{
+    RETURN_ERROR_IF(!cctxParams, GENERIC, "NULL pointer!");
+    FORWARD_IF_ERROR( ZSTD_checkCParams(params.cParams) , "");
+    ZSTD_CCtxParams_init_internal(cctxParams, &params, ZSTD_NO_CLEVEL);
+    return 0;
+}
+
+/*
+ * Sets cctxParams' cParams and fParams from params, but otherwise leaves them alone.
+ * @param param Validated zstd parameters.
+ */
+static void ZSTD_CCtxParams_setZstdParams(
+        ZSTD_CCtx_params* cctxParams, const ZSTD_parameters* params)
+{
+    assert(!ZSTD_checkCParams(params->cParams));
+    cctxParams->cParams = params->cParams;
+    cctxParams->fParams = params->fParams;
+    /* Should not matter, as all cParams are presumed properly defined.
+     * But, set it for tracing anyway.
+     */
+    cctxParams->compressionLevel = ZSTD_NO_CLEVEL;
+}
+
+ZSTD_bounds ZSTD_cParam_getBounds(ZSTD_cParameter param)
+{
+    ZSTD_bounds bounds = { 0, 0, 0 };
+
+    switch(param)
+    {
+    case ZSTD_c_compressionLevel:
+        bounds.lowerBound = ZSTD_minCLevel();
+        bounds.upperBound = ZSTD_maxCLevel();
+        return bounds;
+
+    case ZSTD_c_windowLog:
+        bounds.lowerBound = ZSTD_WINDOWLOG_MIN;
+        bounds.upperBound = ZSTD_WINDOWLOG_MAX;
+        return bounds;
+
+    case ZSTD_c_hashLog:
+        bounds.lowerBound = ZSTD_HASHLOG_MIN;
+        bounds.upperBound = ZSTD_HASHLOG_MAX;
+        return bounds;
+
+    case ZSTD_c_chainLog:
+        bounds.lowerBound = ZSTD_CHAINLOG_MIN;
+        bounds.upperBound = ZSTD_CHAINLOG_MAX;
+        return bounds;
+
+    case ZSTD_c_searchLog:
+        bounds.lowerBound = ZSTD_SEARCHLOG_MIN;
+        bounds.upperBound = ZSTD_SEARCHLOG_MAX;
+        return bounds;
+
+    case ZSTD_c_minMatch:
+        bounds.lowerBound = ZSTD_MINMATCH_MIN;
+        bounds.upperBound = ZSTD_MINMATCH_MAX;
+        return bounds;
+
+    case ZSTD_c_targetLength:
+        bounds.lowerBound = ZSTD_TARGETLENGTH_MIN;
+        bounds.upperBound = ZSTD_TARGETLENGTH_MAX;
+        return bounds;
+
+    case ZSTD_c_strategy:
+        bounds.lowerBound = ZSTD_STRATEGY_MIN;
+        bounds.upperBound = ZSTD_STRATEGY_MAX;
+        return bounds;
+
+    case ZSTD_c_contentSizeFlag:
+        bounds.lowerBound = 0;
+        bounds.upperBound = 1;
+        return bounds;
+
+    case ZSTD_c_checksumFlag:
+        bounds.lowerBound = 0;
+        bounds.upperBound = 1;
+        return bounds;
+
+    case ZSTD_c_dictIDFlag:
+        bounds.lowerBound = 0;
+        bounds.upperBound = 1;
+        return bounds;
+
+    case ZSTD_c_nbWorkers:
+        bounds.lowerBound = 0;
+        bounds.upperBound = 0;
+        return bounds;
+
+    case ZSTD_c_jobSize:
+        bounds.lowerBound = 0;
+        bounds.upperBound = 0;
+        return bounds;
+
+    case ZSTD_c_overlapLog:
+        bounds.lowerBound = 0;
+        bounds.upperBound = 0;
+        return bounds;
+
+    case ZSTD_c_enableDedicatedDictSearch:
+        bounds.lowerBound = 0;
+        bounds.upperBound = 1;
+        return bounds;
+
+    case ZSTD_c_enableLongDistanceMatching:
+        bounds.lowerBound = 0;
+        bounds.upperBound = 1;
+        return bounds;
+
+    case ZSTD_c_ldmHashLog:
+        bounds.lowerBound = ZSTD_LDM_HASHLOG_MIN;
+        bounds.upperBound = ZSTD_LDM_HASHLOG_MAX;
+        return bounds;
+
+    case ZSTD_c_ldmMinMatch:
+        bounds.lowerBound = ZSTD_LDM_MINMATCH_MIN;
+        bounds.upperBound = ZSTD_LDM_MINMATCH_MAX;
+        return bounds;
+
+    case ZSTD_c_ldmBucketSizeLog:
+        bounds.lowerBound = ZSTD_LDM_BUCKETSIZELOG_MIN;
+        bounds.upperBound = ZSTD_LDM_BUCKETSIZELOG_MAX;
+        return bounds;
+
+    case ZSTD_c_ldmHashRateLog:
+        bounds.lowerBound = ZSTD_LDM_HASHRATELOG_MIN;
+        bounds.upperBound = ZSTD_LDM_HASHRATELOG_MAX;
+        return bounds;
+
+    /* experimental parameters */
+    case ZSTD_c_rsyncable:
+        bounds.lowerBound = 0;
+        bounds.upperBound = 1;
+        return bounds;
+
+    case ZSTD_c_forceMaxWindow :
+        bounds.lowerBound = 0;
+        bounds.upperBound = 1;
+        return bounds;
+
+    case ZSTD_c_format:
+        ZSTD_STATIC_ASSERT(ZSTD_f_zstd1 < ZSTD_f_zstd1_magicless);
+        bounds.lowerBound = ZSTD_f_zstd1;
+        bounds.upperBound = ZSTD_f_zstd1_magicless;   /* note : how to ensure at compile time that this is the highest value enum ? */
+        return bounds;
+
+    case ZSTD_c_forceAttachDict:
+        ZSTD_STATIC_ASSERT(ZSTD_dictDefaultAttach < ZSTD_dictForceLoad);
+        bounds.lowerBound = ZSTD_dictDefaultAttach;
+        bounds.upperBound = ZSTD_dictForceLoad;       /* note : how to ensure at compile time that this is the highest value enum ? */
+        return bounds;
+
+    case ZSTD_c_literalCompressionMode:
+        ZSTD_STATIC_ASSERT(ZSTD_lcm_auto < ZSTD_lcm_huffman && ZSTD_lcm_huffman < ZSTD_lcm_uncompressed);
+        bounds.lowerBound = ZSTD_lcm_auto;
+        bounds.upperBound = ZSTD_lcm_uncompressed;
+        return bounds;
+
+    case ZSTD_c_targetCBlockSize:
+        bounds.lowerBound = ZSTD_TARGETCBLOCKSIZE_MIN;
+        bounds.upperBound = ZSTD_TARGETCBLOCKSIZE_MAX;
+        return bounds;
+
+    case ZSTD_c_srcSizeHint:
+        bounds.lowerBound = ZSTD_SRCSIZEHINT_MIN;
+        bounds.upperBound = ZSTD_SRCSIZEHINT_MAX;
+        return bounds;
+
+    case ZSTD_c_stableInBuffer:
+    case ZSTD_c_stableOutBuffer:
+        bounds.lowerBound = (int)ZSTD_bm_buffered;
+        bounds.upperBound = (int)ZSTD_bm_stable;
+        return bounds;
+
+    case ZSTD_c_blockDelimiters:
+        bounds.lowerBound = (int)ZSTD_sf_noBlockDelimiters;
+        bounds.upperBound = (int)ZSTD_sf_explicitBlockDelimiters;
+        return bounds;
+
+    case ZSTD_c_validateSequences:
+        bounds.lowerBound = 0;
+        bounds.upperBound = 1;
+        return bounds;
+
+    default:
+        bounds.error = ERROR(parameter_unsupported);
+        return bounds;
+    }
+}
+
+/* ZSTD_cParam_clampBounds:
+ * Clamps the value into the bounded range.
+ */
+static size_t ZSTD_cParam_clampBounds(ZSTD_cParameter cParam, int* value)
+{
+    ZSTD_bounds const bounds = ZSTD_cParam_getBounds(cParam);
+    if (ZSTD_isError(bounds.error)) return bounds.error;
+    if (*value < bounds.lowerBound) *value = bounds.lowerBound;
+    if (*value > bounds.upperBound) *value = bounds.upperBound;
+    return 0;
+}
+
+#define BOUNDCHECK(cParam, val) { \
+    RETURN_ERROR_IF(!ZSTD_cParam_withinBounds(cParam,val), \
+                    parameter_outOfBound, "Param out of bounds"); \
+}
+
+
+static int ZSTD_isUpdateAuthorized(ZSTD_cParameter param)
+{
+    switch(param)
+    {
+    case ZSTD_c_compressionLevel:
+    case ZSTD_c_hashLog:
+    case ZSTD_c_chainLog:
+    case ZSTD_c_searchLog:
+    case ZSTD_c_minMatch:
+    case ZSTD_c_targetLength:
+    case ZSTD_c_strategy:
+        return 1;
+
+    case ZSTD_c_format:
+    case ZSTD_c_windowLog:
+    case ZSTD_c_contentSizeFlag:
+    case ZSTD_c_checksumFlag:
+    case ZSTD_c_dictIDFlag:
+    case ZSTD_c_forceMaxWindow :
+    case ZSTD_c_nbWorkers:
+    case ZSTD_c_jobSize:
+    case ZSTD_c_overlapLog:
+    case ZSTD_c_rsyncable:
+    case ZSTD_c_enableDedicatedDictSearch:
+    case ZSTD_c_enableLongDistanceMatching:
+    case ZSTD_c_ldmHashLog:
+    case ZSTD_c_ldmMinMatch:
+    case ZSTD_c_ldmBucketSizeLog:
+    case ZSTD_c_ldmHashRateLog:
+    case ZSTD_c_forceAttachDict:
+    case ZSTD_c_literalCompressionMode:
+    case ZSTD_c_targetCBlockSize:
+    case ZSTD_c_srcSizeHint:
+    case ZSTD_c_stableInBuffer:
+    case ZSTD_c_stableOutBuffer:
+    case ZSTD_c_blockDelimiters:
+    case ZSTD_c_validateSequences:
+    default:
+        return 0;
+    }
+}
+
+size_t ZSTD_CCtx_setParameter(ZSTD_CCtx* cctx, ZSTD_cParameter param, int value)
+{
+    DEBUGLOG(4, "ZSTD_CCtx_setParameter (%i, %i)", (int)param, value);
+    if (cctx->streamStage != zcss_init) {
+        if (ZSTD_isUpdateAuthorized(param)) {
+            cctx->cParamsChanged = 1;
+        } else {
+            RETURN_ERROR(stage_wrong, "can only set params in ctx init stage");
+    }   }
+
+    switch(param)
+    {
+    case ZSTD_c_nbWorkers:
+        RETURN_ERROR_IF((value!=0) && cctx->staticSize, parameter_unsupported,
+                        "MT not compatible with static alloc");
+        break;
+
+    case ZSTD_c_compressionLevel:
+    case ZSTD_c_windowLog:
+    case ZSTD_c_hashLog:
+    case ZSTD_c_chainLog:
+    case ZSTD_c_searchLog:
+    case ZSTD_c_minMatch:
+    case ZSTD_c_targetLength:
+    case ZSTD_c_strategy:
+    case ZSTD_c_ldmHashRateLog:
+    case ZSTD_c_format:
+    case ZSTD_c_contentSizeFlag:
+    case ZSTD_c_checksumFlag:
+    case ZSTD_c_dictIDFlag:
+    case ZSTD_c_forceMaxWindow:
+    case ZSTD_c_forceAttachDict:
+    case ZSTD_c_literalCompressionMode:
+    case ZSTD_c_jobSize:
+    case ZSTD_c_overlapLog:
+    case ZSTD_c_rsyncable:
+    case ZSTD_c_enableDedicatedDictSearch:
+    case ZSTD_c_enableLongDistanceMatching:
+    case ZSTD_c_ldmHashLog:
+    case ZSTD_c_ldmMinMatch:
+    case ZSTD_c_ldmBucketSizeLog:
+    case ZSTD_c_targetCBlockSize:
+    case ZSTD_c_srcSizeHint:
+    case ZSTD_c_stableInBuffer:
+    case ZSTD_c_stableOutBuffer:
+    case ZSTD_c_blockDelimiters:
+    case ZSTD_c_validateSequences:
+        break;
+
+    default: RETURN_ERROR(parameter_unsupported, "unknown parameter");
+    }
+    return ZSTD_CCtxParams_setParameter(&cctx->requestedParams, param, value);
+}
+
+size_t ZSTD_CCtxParams_setParameter(ZSTD_CCtx_params* CCtxParams,
+                                    ZSTD_cParameter param, int value)
+{
+    DEBUGLOG(4, "ZSTD_CCtxParams_setParameter (%i, %i)", (int)param, value);
+    switch(param)
+    {
+    case ZSTD_c_format :
+        BOUNDCHECK(ZSTD_c_format, value);
+        CCtxParams->format = (ZSTD_format_e)value;
+        return (size_t)CCtxParams->format;
+
+    case ZSTD_c_compressionLevel : {
+        FORWARD_IF_ERROR(ZSTD_cParam_clampBounds(param, &value), "");
+        if (value == 0)
+            CCtxParams->compressionLevel = ZSTD_CLEVEL_DEFAULT; /* 0 == default */
+        else
+            CCtxParams->compressionLevel = value;
+        if (CCtxParams->compressionLevel >= 0) return (size_t)CCtxParams->compressionLevel;
+        return 0;  /* return type (size_t) cannot represent negative values */
+    }
+
+    case ZSTD_c_windowLog :
+        if (value!=0)   /* 0 => use default */
+            BOUNDCHECK(ZSTD_c_windowLog, value);
+        CCtxParams->cParams.windowLog = (U32)value;
+        return CCtxParams->cParams.windowLog;
+
+    case ZSTD_c_hashLog :
+        if (value!=0)   /* 0 => use default */
+            BOUNDCHECK(ZSTD_c_hashLog, value);
+        CCtxParams->cParams.hashLog = (U32)value;
+        return CCtxParams->cParams.hashLog;
+
+    case ZSTD_c_chainLog :
+        if (value!=0)   /* 0 => use default */
+            BOUNDCHECK(ZSTD_c_chainLog, value);
+        CCtxParams->cParams.chainLog = (U32)value;
+        return CCtxParams->cParams.chainLog;
+
+    case ZSTD_c_searchLog :
+        if (value!=0)   /* 0 => use default */
+            BOUNDCHECK(ZSTD_c_searchLog, value);
+        CCtxParams->cParams.searchLog = (U32)value;
+        return (size_t)value;
+
+    case ZSTD_c_minMatch :
+        if (value!=0)   /* 0 => use default */
+            BOUNDCHECK(ZSTD_c_minMatch, value);
+        CCtxParams->cParams.minMatch = value;
+        return CCtxParams->cParams.minMatch;
+
+    case ZSTD_c_targetLength :
+        BOUNDCHECK(ZSTD_c_targetLength, value);
+        CCtxParams->cParams.targetLength = value;
+        return CCtxParams->cParams.targetLength;
+
+    case ZSTD_c_strategy :
+        if (value!=0)   /* 0 => use default */
+            BOUNDCHECK(ZSTD_c_strategy, value);
+        CCtxParams->cParams.strategy = (ZSTD_strategy)value;
+        return (size_t)CCtxParams->cParams.strategy;
+
+    case ZSTD_c_contentSizeFlag :
+        /* Content size written in frame header _when known_ (default:1) */
+        DEBUGLOG(4, "set content size flag = %u", (value!=0));
+        CCtxParams->fParams.contentSizeFlag = value != 0;
+        return CCtxParams->fParams.contentSizeFlag;
+
+    case ZSTD_c_checksumFlag :
+        /* A 32-bits content checksum will be calculated and written at end of frame (default:0) */
+        CCtxParams->fParams.checksumFlag = value != 0;
+        return CCtxParams->fParams.checksumFlag;
+
+    case ZSTD_c_dictIDFlag : /* When applicable, dictionary's dictID is provided in frame header (default:1) */
+        DEBUGLOG(4, "set dictIDFlag = %u", (value!=0));
+        CCtxParams->fParams.noDictIDFlag = !value;
+        return !CCtxParams->fParams.noDictIDFlag;
+
+    case ZSTD_c_forceMaxWindow :
+        CCtxParams->forceWindow = (value != 0);
+        return CCtxParams->forceWindow;
+
+    case ZSTD_c_forceAttachDict : {
+        const ZSTD_dictAttachPref_e pref = (ZSTD_dictAttachPref_e)value;
+        BOUNDCHECK(ZSTD_c_forceAttachDict, pref);
+        CCtxParams->attachDictPref = pref;
+        return CCtxParams->attachDictPref;
+    }
+
+    case ZSTD_c_literalCompressionMode : {
+        const ZSTD_literalCompressionMode_e lcm = (ZSTD_literalCompressionMode_e)value;
+        BOUNDCHECK(ZSTD_c_literalCompressionMode, lcm);
+        CCtxParams->literalCompressionMode = lcm;
+        return CCtxParams->literalCompressionMode;
+    }
+
+    case ZSTD_c_nbWorkers :
+        RETURN_ERROR_IF(value!=0, parameter_unsupported, "not compiled with multithreading");
+        return 0;
+
+    case ZSTD_c_jobSize :
+        RETURN_ERROR_IF(value!=0, parameter_unsupported, "not compiled with multithreading");
+        return 0;
+
+    case ZSTD_c_overlapLog :
+        RETURN_ERROR_IF(value!=0, parameter_unsupported, "not compiled with multithreading");
+        return 0;
+
+    case ZSTD_c_rsyncable :
+        RETURN_ERROR_IF(value!=0, parameter_unsupported, "not compiled with multithreading");
+        return 0;
+
+    case ZSTD_c_enableDedicatedDictSearch :
+        CCtxParams->enableDedicatedDictSearch = (value!=0);
+        return CCtxParams->enableDedicatedDictSearch;
+
+    case ZSTD_c_enableLongDistanceMatching :
+        CCtxParams->ldmParams.enableLdm = (value!=0);
+        return CCtxParams->ldmParams.enableLdm;
+
+    case ZSTD_c_ldmHashLog :
+        if (value!=0)   /* 0 ==> auto */
+            BOUNDCHECK(ZSTD_c_ldmHashLog, value);
+        CCtxParams->ldmParams.hashLog = value;
+        return CCtxParams->ldmParams.hashLog;
+
+    case ZSTD_c_ldmMinMatch :
+        if (value!=0)   /* 0 ==> default */
+            BOUNDCHECK(ZSTD_c_ldmMinMatch, value);
+        CCtxParams->ldmParams.minMatchLength = value;
+        return CCtxParams->ldmParams.minMatchLength;
+
+    case ZSTD_c_ldmBucketSizeLog :
+        if (value!=0)   /* 0 ==> default */
+            BOUNDCHECK(ZSTD_c_ldmBucketSizeLog, value);
+        CCtxParams->ldmParams.bucketSizeLog = value;
+        return CCtxParams->ldmParams.bucketSizeLog;
+
+    case ZSTD_c_ldmHashRateLog :
+        if (value!=0)   /* 0 ==> default */
+            BOUNDCHECK(ZSTD_c_ldmHashRateLog, value);
+        CCtxParams->ldmParams.hashRateLog = value;
+        return CCtxParams->ldmParams.hashRateLog;
+
+    case ZSTD_c_targetCBlockSize :
+        if (value!=0)   /* 0 ==> default */
+            BOUNDCHECK(ZSTD_c_targetCBlockSize, value);
+        CCtxParams->targetCBlockSize = value;
+        return CCtxParams->targetCBlockSize;
+
+    case ZSTD_c_srcSizeHint :
+        if (value!=0)    /* 0 ==> default */
+            BOUNDCHECK(ZSTD_c_srcSizeHint, value);
+        CCtxParams->srcSizeHint = value;
+        return CCtxParams->srcSizeHint;
+
+    case ZSTD_c_stableInBuffer:
+        BOUNDCHECK(ZSTD_c_stableInBuffer, value);
+        CCtxParams->inBufferMode = (ZSTD_bufferMode_e)value;
+        return CCtxParams->inBufferMode;
+
+    case ZSTD_c_stableOutBuffer:
+        BOUNDCHECK(ZSTD_c_stableOutBuffer, value);
+        CCtxParams->outBufferMode = (ZSTD_bufferMode_e)value;
+        return CCtxParams->outBufferMode;
+
+    case ZSTD_c_blockDelimiters:
+        BOUNDCHECK(ZSTD_c_blockDelimiters, value);
+        CCtxParams->blockDelimiters = (ZSTD_sequenceFormat_e)value;
+        return CCtxParams->blockDelimiters;
+
+    case ZSTD_c_validateSequences:
+        BOUNDCHECK(ZSTD_c_validateSequences, value);
+        CCtxParams->validateSequences = value;
+        return CCtxParams->validateSequences;
+
+    default: RETURN_ERROR(parameter_unsupported, "unknown parameter");
+    }
+}
+
+size_t ZSTD_CCtx_getParameter(ZSTD_CCtx const* cctx, ZSTD_cParameter param, int* value)
+{
+    return ZSTD_CCtxParams_getParameter(&cctx->requestedParams, param, value);
+}
+
+size_t ZSTD_CCtxParams_getParameter(
+        ZSTD_CCtx_params const* CCtxParams, ZSTD_cParameter param, int* value)
+{
+    switch(param)
+    {
+    case ZSTD_c_format :
+        *value = CCtxParams->format;
+        break;
+    case ZSTD_c_compressionLevel :
+        *value = CCtxParams->compressionLevel;
+        break;
+    case ZSTD_c_windowLog :
+        *value = (int)CCtxParams->cParams.windowLog;
+        break;
+    case ZSTD_c_hashLog :
+        *value = (int)CCtxParams->cParams.hashLog;
+        break;
+    case ZSTD_c_chainLog :
+        *value = (int)CCtxParams->cParams.chainLog;
+        break;
+    case ZSTD_c_searchLog :
+        *value = CCtxParams->cParams.searchLog;
+        break;
+    case ZSTD_c_minMatch :
+        *value = CCtxParams->cParams.minMatch;
+        break;
+    case ZSTD_c_targetLength :
+        *value = CCtxParams->cParams.targetLength;
+        break;
+    case ZSTD_c_strategy :
+        *value = (unsigned)CCtxParams->cParams.strategy;
+        break;
+    case ZSTD_c_contentSizeFlag :
+        *value = CCtxParams->fParams.contentSizeFlag;
+        break;
+    case ZSTD_c_checksumFlag :
+        *value = CCtxParams->fParams.checksumFlag;
+        break;
+    case ZSTD_c_dictIDFlag :
+        *value = !CCtxParams->fParams.noDictIDFlag;
+        break;
+    case ZSTD_c_forceMaxWindow :
+        *value = CCtxParams->forceWindow;
+        break;
+    case ZSTD_c_forceAttachDict :
+        *value = CCtxParams->attachDictPref;
+        break;
+    case ZSTD_c_literalCompressionMode :
+        *value = CCtxParams->literalCompressionMode;
+        break;
+    case ZSTD_c_nbWorkers :
+        assert(CCtxParams->nbWorkers == 0);
+        *value = CCtxParams->nbWorkers;
+        break;
+    case ZSTD_c_jobSize :
+        RETURN_ERROR(parameter_unsupported, "not compiled with multithreading");
+    case ZSTD_c_overlapLog :
+        RETURN_ERROR(parameter_unsupported, "not compiled with multithreading");
+    case ZSTD_c_rsyncable :
+        RETURN_ERROR(parameter_unsupported, "not compiled with multithreading");
+    case ZSTD_c_enableDedicatedDictSearch :
+        *value = CCtxParams->enableDedicatedDictSearch;
+        break;
+    case ZSTD_c_enableLongDistanceMatching :
+        *value = CCtxParams->ldmParams.enableLdm;
+        break;
+    case ZSTD_c_ldmHashLog :
+        *value = CCtxParams->ldmParams.hashLog;
+        break;
+    case ZSTD_c_ldmMinMatch :
+        *value = CCtxParams->ldmParams.minMatchLength;
+        break;
+    case ZSTD_c_ldmBucketSizeLog :
+        *value = CCtxParams->ldmParams.bucketSizeLog;
+        break;
+    case ZSTD_c_ldmHashRateLog :
+        *value = CCtxParams->ldmParams.hashRateLog;
+        break;
+    case ZSTD_c_targetCBlockSize :
+        *value = (int)CCtxParams->targetCBlockSize;
+        break;
+    case ZSTD_c_srcSizeHint :
+        *value = (int)CCtxParams->srcSizeHint;
+        break;
+    case ZSTD_c_stableInBuffer :
+        *value = (int)CCtxParams->inBufferMode;
+        break;
+    case ZSTD_c_stableOutBuffer :
+        *value = (int)CCtxParams->outBufferMode;
+        break;
+    case ZSTD_c_blockDelimiters :
+        *value = (int)CCtxParams->blockDelimiters;
+        break;
+    case ZSTD_c_validateSequences :
+        *value = (int)CCtxParams->validateSequences;
+        break;
+    default: RETURN_ERROR(parameter_unsupported, "unknown parameter");
+    }
+    return 0;
+}
+
+/* ZSTD_CCtx_setParametersUsingCCtxParams() :
+ *  just applies `params` into `cctx`
+ *  no action is performed, parameters are merely stored.
+ *  If ZSTDMT is enabled, parameters are pushed to cctx->mtctx.
+ *    This is possible even if a compression is ongoing.
+ *    In which case, new parameters will be applied on the fly, starting with next compression job.
+ */
+size_t ZSTD_CCtx_setParametersUsingCCtxParams(
+        ZSTD_CCtx* cctx, const ZSTD_CCtx_params* params)
+{
+    DEBUGLOG(4, "ZSTD_CCtx_setParametersUsingCCtxParams");
+    RETURN_ERROR_IF(cctx->streamStage != zcss_init, stage_wrong,
+                    "The context is in the wrong stage!");
+    RETURN_ERROR_IF(cctx->cdict, stage_wrong,
+                    "Can't override parameters with cdict attached (some must "
+                    "be inherited from the cdict).");
+
+    cctx->requestedParams = *params;
+    return 0;
+}
+
+ZSTDLIB_API size_t ZSTD_CCtx_setPledgedSrcSize(ZSTD_CCtx* cctx, unsigned long long pledgedSrcSize)
+{
+    DEBUGLOG(4, "ZSTD_CCtx_setPledgedSrcSize to %u bytes", (U32)pledgedSrcSize);
+    RETURN_ERROR_IF(cctx->streamStage != zcss_init, stage_wrong,
+                    "Can't set pledgedSrcSize when not in init stage.");
+    cctx->pledgedSrcSizePlusOne = pledgedSrcSize+1;
+    return 0;
+}
+
+static ZSTD_compressionParameters ZSTD_dedicatedDictSearch_getCParams(
+        int const compressionLevel,
+        size_t const dictSize);
+static int ZSTD_dedicatedDictSearch_isSupported(
+        const ZSTD_compressionParameters* cParams);
+static void ZSTD_dedicatedDictSearch_revertCParams(
+        ZSTD_compressionParameters* cParams);
+
+/*
+ * Initializes the local dict using the requested parameters.
+ * NOTE: This does not use the pledged src size, because it may be used for more
+ * than one compression.
+ */
+static size_t ZSTD_initLocalDict(ZSTD_CCtx* cctx)
+{
+    ZSTD_localDict* const dl = &cctx->localDict;
+    if (dl->dict == NULL) {
+        /* No local dictionary. */
+        assert(dl->dictBuffer == NULL);
+        assert(dl->cdict == NULL);
+        assert(dl->dictSize == 0);
+        return 0;
+    }
+    if (dl->cdict != NULL) {
+        assert(cctx->cdict == dl->cdict);
+        /* Local dictionary already initialized. */
+        return 0;
+    }
+    assert(dl->dictSize > 0);
+    assert(cctx->cdict == NULL);
+    assert(cctx->prefixDict.dict == NULL);
+
+    dl->cdict = ZSTD_createCDict_advanced2(
+            dl->dict,
+            dl->dictSize,
+            ZSTD_dlm_byRef,
+            dl->dictContentType,
+            &cctx->requestedParams,
+            cctx->customMem);
+    RETURN_ERROR_IF(!dl->cdict, memory_allocation, "ZSTD_createCDict_advanced failed");
+    cctx->cdict = dl->cdict;
+    return 0;
+}
+
+size_t ZSTD_CCtx_loadDictionary_advanced(
+        ZSTD_CCtx* cctx, const void* dict, size_t dictSize,
+        ZSTD_dictLoadMethod_e dictLoadMethod, ZSTD_dictContentType_e dictContentType)
+{
+    RETURN_ERROR_IF(cctx->streamStage != zcss_init, stage_wrong,
+                    "Can't load a dictionary when ctx is not in init stage.");
+    DEBUGLOG(4, "ZSTD_CCtx_loadDictionary_advanced (size: %u)", (U32)dictSize);
+    ZSTD_clearAllDicts(cctx);  /* in case one already exists */
+    if (dict == NULL || dictSize == 0)  /* no dictionary mode */
+        return 0;
+    if (dictLoadMethod == ZSTD_dlm_byRef) {
+        cctx->localDict.dict = dict;
+    } else {
+        void* dictBuffer;
+        RETURN_ERROR_IF(cctx->staticSize, memory_allocation,
+                        "no malloc for static CCtx");
+        dictBuffer = ZSTD_customMalloc(dictSize, cctx->customMem);
+        RETURN_ERROR_IF(!dictBuffer, memory_allocation, "NULL pointer!");
+        ZSTD_memcpy(dictBuffer, dict, dictSize);
+        cctx->localDict.dictBuffer = dictBuffer;
+        cctx->localDict.dict = dictBuffer;
+    }
+    cctx->localDict.dictSize = dictSize;
+    cctx->localDict.dictContentType = dictContentType;
+    return 0;
+}
+
+ZSTDLIB_API size_t ZSTD_CCtx_loadDictionary_byReference(
+      ZSTD_CCtx* cctx, const void* dict, size_t dictSize)
+{
+    return ZSTD_CCtx_loadDictionary_advanced(
+            cctx, dict, dictSize, ZSTD_dlm_byRef, ZSTD_dct_auto);
+}
+
+ZSTDLIB_API size_t ZSTD_CCtx_loadDictionary(ZSTD_CCtx* cctx, const void* dict, size_t dictSize)
+{
+    return ZSTD_CCtx_loadDictionary_advanced(
+            cctx, dict, dictSize, ZSTD_dlm_byCopy, ZSTD_dct_auto);
+}
+
+
+size_t ZSTD_CCtx_refCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict)
+{
+    RETURN_ERROR_IF(cctx->streamStage != zcss_init, stage_wrong,
+                    "Can't ref a dict when ctx not in init stage.");
+    /* Free the existing local cdict (if any) to save memory. */
+    ZSTD_clearAllDicts(cctx);
+    cctx->cdict = cdict;
+    return 0;
+}
+
+size_t ZSTD_CCtx_refThreadPool(ZSTD_CCtx* cctx, ZSTD_threadPool* pool)
+{
+    RETURN_ERROR_IF(cctx->streamStage != zcss_init, stage_wrong,
+                    "Can't ref a pool when ctx not in init stage.");
+    cctx->pool = pool;
+    return 0;
+}
+
+size_t ZSTD_CCtx_refPrefix(ZSTD_CCtx* cctx, const void* prefix, size_t prefixSize)
+{
+    return ZSTD_CCtx_refPrefix_advanced(cctx, prefix, prefixSize, ZSTD_dct_rawContent);
+}
+
+size_t ZSTD_CCtx_refPrefix_advanced(
+        ZSTD_CCtx* cctx, const void* prefix, size_t prefixSize, ZSTD_dictContentType_e dictContentType)
+{
+    RETURN_ERROR_IF(cctx->streamStage != zcss_init, stage_wrong,
+                    "Can't ref a prefix when ctx not in init stage.");
+    ZSTD_clearAllDicts(cctx);
+    if (prefix != NULL && prefixSize > 0) {
+        cctx->prefixDict.dict = prefix;
+        cctx->prefixDict.dictSize = prefixSize;
+        cctx->prefixDict.dictContentType = dictContentType;
+    }
+    return 0;
+}
+
+/*! ZSTD_CCtx_reset() :
+ *  Also dumps dictionary */
+size_t ZSTD_CCtx_reset(ZSTD_CCtx* cctx, ZSTD_ResetDirective reset)
+{
+    if ( (reset == ZSTD_reset_session_only)
+      || (reset == ZSTD_reset_session_and_parameters) ) {
+        cctx->streamStage = zcss_init;
+        cctx->pledgedSrcSizePlusOne = 0;
+    }
+    if ( (reset == ZSTD_reset_parameters)
+      || (reset == ZSTD_reset_session_and_parameters) ) {
+        RETURN_ERROR_IF(cctx->streamStage != zcss_init, stage_wrong,
+                        "Can't reset parameters only when not in init stage.");
+        ZSTD_clearAllDicts(cctx);
+        return ZSTD_CCtxParams_reset(&cctx->requestedParams);
+    }
+    return 0;
+}
+
+
+/* ZSTD_checkCParams() :
+    control CParam values remain within authorized range.
+    @return : 0, or an error code if one value is beyond authorized range */
+size_t ZSTD_checkCParams(ZSTD_compressionParameters cParams)
+{
+    BOUNDCHECK(ZSTD_c_windowLog, (int)cParams.windowLog);
+    BOUNDCHECK(ZSTD_c_chainLog,  (int)cParams.chainLog);
+    BOUNDCHECK(ZSTD_c_hashLog,   (int)cParams.hashLog);
+    BOUNDCHECK(ZSTD_c_searchLog, (int)cParams.searchLog);
+    BOUNDCHECK(ZSTD_c_minMatch,  (int)cParams.minMatch);
+    BOUNDCHECK(ZSTD_c_targetLength,(int)cParams.targetLength);
+    BOUNDCHECK(ZSTD_c_strategy,  cParams.strategy);
+    return 0;
+}
+
+/* ZSTD_clampCParams() :
+ *  make CParam values within valid range.
+ *  @return : valid CParams */
+static ZSTD_compressionParameters
+ZSTD_clampCParams(ZSTD_compressionParameters cParams)
+{
+#   define CLAMP_TYPE(cParam, val, type) {                                \
+        ZSTD_bounds const bounds = ZSTD_cParam_getBounds(cParam);         \
+        if ((int)val<bounds.lowerBound) val=(type)bounds.lowerBound;      \
+        else if ((int)val>bounds.upperBound) val=(type)bounds.upperBound; \
+    }
+#   define CLAMP(cParam, val) CLAMP_TYPE(cParam, val, unsigned)
+    CLAMP(ZSTD_c_windowLog, cParams.windowLog);
+    CLAMP(ZSTD_c_chainLog,  cParams.chainLog);
+    CLAMP(ZSTD_c_hashLog,   cParams.hashLog);
+    CLAMP(ZSTD_c_searchLog, cParams.searchLog);
+    CLAMP(ZSTD_c_minMatch,  cParams.minMatch);
+    CLAMP(ZSTD_c_targetLength,cParams.targetLength);
+    CLAMP_TYPE(ZSTD_c_strategy,cParams.strategy, ZSTD_strategy);
+    return cParams;
+}
+
+/* ZSTD_cycleLog() :
+ *  condition for correct operation : hashLog > 1 */
+U32 ZSTD_cycleLog(U32 hashLog, ZSTD_strategy strat)
+{
+    U32 const btScale = ((U32)strat >= (U32)ZSTD_btlazy2);
+    return hashLog - btScale;
+}
+
+/* ZSTD_dictAndWindowLog() :
+ * Returns an adjusted window log that is large enough to fit the source and the dictionary.
+ * The zstd format says that the entire dictionary is valid if one byte of the dictionary
+ * is within the window. So the hashLog and chainLog should be large enough to reference both
+ * the dictionary and the window. So we must use this adjusted dictAndWindowLog when downsizing
+ * the hashLog and windowLog.
+ * NOTE: srcSize must not be ZSTD_CONTENTSIZE_UNKNOWN.
+ */
+static U32 ZSTD_dictAndWindowLog(U32 windowLog, U64 srcSize, U64 dictSize)
+{
+    const U64 maxWindowSize = 1ULL << ZSTD_WINDOWLOG_MAX;
+    /* No dictionary ==> No change */
+    if (dictSize == 0) {
+        return windowLog;
+    }
+    assert(windowLog <= ZSTD_WINDOWLOG_MAX);
+    assert(srcSize != ZSTD_CONTENTSIZE_UNKNOWN); /* Handled in ZSTD_adjustCParams_internal() */
+    {
+        U64 const windowSize = 1ULL << windowLog;
+        U64 const dictAndWindowSize = dictSize + windowSize;
+        /* If the window size is already large enough to fit both the source and the dictionary
+         * then just use the window size. Otherwise adjust so that it fits the dictionary and
+         * the window.
+         */
+        if (windowSize >= dictSize + srcSize) {
+            return windowLog; /* Window size large enough already */
+        } else if (dictAndWindowSize >= maxWindowSize) {
+            return ZSTD_WINDOWLOG_MAX; /* Larger than max window log */
+        } else  {
+            return ZSTD_highbit32((U32)dictAndWindowSize - 1) + 1;
+        }
+    }
+}
+
+/* ZSTD_adjustCParams_internal() :
+ *  optimize `cPar` for a specified input (`srcSize` and `dictSize`).
+ *  mostly downsize to reduce memory consumption and initialization latency.
+ * `srcSize` can be ZSTD_CONTENTSIZE_UNKNOWN when not known.
+ * `mode` is the mode for parameter adjustment. See docs for `ZSTD_cParamMode_e`.
+ *  note : `srcSize==0` means 0!
+ *  condition : cPar is presumed validated (can be checked using ZSTD_checkCParams()). */
+static ZSTD_compressionParameters
+ZSTD_adjustCParams_internal(ZSTD_compressionParameters cPar,
+                            unsigned long long srcSize,
+                            size_t dictSize,
+                            ZSTD_cParamMode_e mode)
+{
+    const U64 minSrcSize = 513; /* (1<<9) + 1 */
+    const U64 maxWindowResize = 1ULL << (ZSTD_WINDOWLOG_MAX-1);
+    assert(ZSTD_checkCParams(cPar)==0);
+
+    switch (mode) {
+    case ZSTD_cpm_unknown:
+    case ZSTD_cpm_noAttachDict:
+        /* If we don't know the source size, don't make any
+         * assumptions about it. We will already have selected
+         * smaller parameters if a dictionary is in use.
+         */
+        break;
+    case ZSTD_cpm_createCDict:
+        /* Assume a small source size when creating a dictionary
+         * with an unkown source size.
+         */
+        if (dictSize && srcSize == ZSTD_CONTENTSIZE_UNKNOWN)
+            srcSize = minSrcSize;
+        break;
+    case ZSTD_cpm_attachDict:
+        /* Dictionary has its own dedicated parameters which have
+         * already been selected. We are selecting parameters
+         * for only the source.
+         */
+        dictSize = 0;
+        break;
+    default:
+        assert(0);
+        break;
+    }
+
+    /* resize windowLog if input is small enough, to use less memory */
+    if ( (srcSize < maxWindowResize)
+      && (dictSize < maxWindowResize) )  {
+        U32 const tSize = (U32)(srcSize + dictSize);
+        static U32 const hashSizeMin = 1 << ZSTD_HASHLOG_MIN;
+        U32 const srcLog = (tSize < hashSizeMin) ? ZSTD_HASHLOG_MIN :
+                            ZSTD_highbit32(tSize-1) + 1;
+        if (cPar.windowLog > srcLog) cPar.windowLog = srcLog;
+    }
+    if (srcSize != ZSTD_CONTENTSIZE_UNKNOWN) {
+        U32 const dictAndWindowLog = ZSTD_dictAndWindowLog(cPar.windowLog, (U64)srcSize, (U64)dictSize);
+        U32 const cycleLog = ZSTD_cycleLog(cPar.chainLog, cPar.strategy);
+        if (cPar.hashLog > dictAndWindowLog+1) cPar.hashLog = dictAndWindowLog+1;
+        if (cycleLog > dictAndWindowLog)
+            cPar.chainLog -= (cycleLog - dictAndWindowLog);
+    }
+
+    if (cPar.windowLog < ZSTD_WINDOWLOG_ABSOLUTEMIN)
+        cPar.windowLog = ZSTD_WINDOWLOG_ABSOLUTEMIN;  /* minimum wlog required for valid frame header */
+
+    return cPar;
+}
+
+ZSTD_compressionParameters
+ZSTD_adjustCParams(ZSTD_compressionParameters cPar,
+                   unsigned long long srcSize,
+                   size_t dictSize)
+{
+    cPar = ZSTD_clampCParams(cPar);   /* resulting cPar is necessarily valid (all parameters within range) */
+    if (srcSize == 0) srcSize = ZSTD_CONTENTSIZE_UNKNOWN;
+    return ZSTD_adjustCParams_internal(cPar, srcSize, dictSize, ZSTD_cpm_unknown);
+}
+
+static ZSTD_compressionParameters ZSTD_getCParams_internal(int compressionLevel, unsigned long long srcSizeHint, size_t dictSize, ZSTD_cParamMode_e mode);
+static ZSTD_parameters ZSTD_getParams_internal(int compressionLevel, unsigned long long srcSizeHint, size_t dictSize, ZSTD_cParamMode_e mode);
+
+static void ZSTD_overrideCParams(
+              ZSTD_compressionParameters* cParams,
+        const ZSTD_compressionParameters* overrides)
+{
+    if (overrides->windowLog)    cParams->windowLog    = overrides->windowLog;
+    if (overrides->hashLog)      cParams->hashLog      = overrides->hashLog;
+    if (overrides->chainLog)     cParams->chainLog     = overrides->chainLog;
+    if (overrides->searchLog)    cParams->searchLog    = overrides->searchLog;
+    if (overrides->minMatch)     cParams->minMatch     = overrides->minMatch;
+    if (overrides->targetLength) cParams->targetLength = overrides->targetLength;
+    if (overrides->strategy)     cParams->strategy     = overrides->strategy;
+}
+
+ZSTD_compressionParameters ZSTD_getCParamsFromCCtxParams(
+        const ZSTD_CCtx_params* CCtxParams, U64 srcSizeHint, size_t dictSize, ZSTD_cParamMode_e mode)
+{
+    ZSTD_compressionParameters cParams;
+    if (srcSizeHint == ZSTD_CONTENTSIZE_UNKNOWN && CCtxParams->srcSizeHint > 0) {
+      srcSizeHint = CCtxParams->srcSizeHint;
+    }
+    cParams = ZSTD_getCParams_internal(CCtxParams->compressionLevel, srcSizeHint, dictSize, mode);
+    if (CCtxParams->ldmParams.enableLdm) cParams.windowLog = ZSTD_LDM_DEFAULT_WINDOW_LOG;
+    ZSTD_overrideCParams(&cParams, &CCtxParams->cParams);
+    assert(!ZSTD_checkCParams(cParams));
+    /* srcSizeHint == 0 means 0 */
+    return ZSTD_adjustCParams_internal(cParams, srcSizeHint, dictSize, mode);
+}
+
+static size_t
+ZSTD_sizeof_matchState(const ZSTD_compressionParameters* const cParams,
+                       const U32 forCCtx)
+{
+    size_t const chainSize = (cParams->strategy == ZSTD_fast) ? 0 : ((size_t)1 << cParams->chainLog);
+    size_t const hSize = ((size_t)1) << cParams->hashLog;
+    U32    const hashLog3 = (forCCtx && cParams->minMatch==3) ? MIN(ZSTD_HASHLOG3_MAX, cParams->windowLog) : 0;
+    size_t const h3Size = hashLog3 ? ((size_t)1) << hashLog3 : 0;
+    /* We don't use ZSTD_cwksp_alloc_size() here because the tables aren't
+     * surrounded by redzones in ASAN. */
+    size_t const tableSpace = chainSize * sizeof(U32)
+                            + hSize * sizeof(U32)
+                            + h3Size * sizeof(U32);
+    size_t const optPotentialSpace =
+        ZSTD_cwksp_alloc_size((MaxML+1) * sizeof(U32))
+      + ZSTD_cwksp_alloc_size((MaxLL+1) * sizeof(U32))
+      + ZSTD_cwksp_alloc_size((MaxOff+1) * sizeof(U32))
+      + ZSTD_cwksp_alloc_size((1<<Litbits) * sizeof(U32))
+      + ZSTD_cwksp_alloc_size((ZSTD_OPT_NUM+1) * sizeof(ZSTD_match_t))
+      + ZSTD_cwksp_alloc_size((ZSTD_OPT_NUM+1) * sizeof(ZSTD_optimal_t));
+    size_t const optSpace = (forCCtx && (cParams->strategy >= ZSTD_btopt))
+                                ? optPotentialSpace
+                                : 0;
+    DEBUGLOG(4, "chainSize: %u - hSize: %u - h3Size: %u",
+                (U32)chainSize, (U32)hSize, (U32)h3Size);
+    return tableSpace + optSpace;
+}
+
+static size_t ZSTD_estimateCCtxSize_usingCCtxParams_internal(
+        const ZSTD_compressionParameters* cParams,
+        const ldmParams_t* ldmParams,
+        const int isStatic,
+        const size_t buffInSize,
+        const size_t buffOutSize,
+        const U64 pledgedSrcSize)
+{
+    size_t const windowSize = MAX(1, (size_t)MIN(((U64)1 << cParams->windowLog), pledgedSrcSize));
+    size_t const blockSize = MIN(ZSTD_BLOCKSIZE_MAX, windowSize);
+    U32    const divider = (cParams->minMatch==3) ? 3 : 4;
+    size_t const maxNbSeq = blockSize / divider;
+    size_t const tokenSpace = ZSTD_cwksp_alloc_size(WILDCOPY_OVERLENGTH + blockSize)
+                            + ZSTD_cwksp_alloc_size(maxNbSeq * sizeof(seqDef))
+                            + 3 * ZSTD_cwksp_alloc_size(maxNbSeq * sizeof(BYTE));
+    size_t const entropySpace = ZSTD_cwksp_alloc_size(ENTROPY_WORKSPACE_SIZE);
+    size_t const blockStateSpace = 2 * ZSTD_cwksp_alloc_size(sizeof(ZSTD_compressedBlockState_t));
+    size_t const matchStateSize = ZSTD_sizeof_matchState(cParams, /* forCCtx */ 1);
+
+    size_t const ldmSpace = ZSTD_ldm_getTableSize(*ldmParams);
+    size_t const maxNbLdmSeq = ZSTD_ldm_getMaxNbSeq(*ldmParams, blockSize);
+    size_t const ldmSeqSpace = ldmParams->enableLdm ?
+        ZSTD_cwksp_alloc_size(maxNbLdmSeq * sizeof(rawSeq)) : 0;
+
+
+    size_t const bufferSpace = ZSTD_cwksp_alloc_size(buffInSize)
+                             + ZSTD_cwksp_alloc_size(buffOutSize);
+
+    size_t const cctxSpace = isStatic ? ZSTD_cwksp_alloc_size(sizeof(ZSTD_CCtx)) : 0;
+
+    size_t const neededSpace =
+        cctxSpace +
+        entropySpace +
+        blockStateSpace +
+        ldmSpace +
+        ldmSeqSpace +
+        matchStateSize +
+        tokenSpace +
+        bufferSpace;
+
+    DEBUGLOG(5, "estimate workspace : %u", (U32)neededSpace);
+    return neededSpace;
+}
+
+size_t ZSTD_estimateCCtxSize_usingCCtxParams(const ZSTD_CCtx_params* params)
+{
+    ZSTD_compressionParameters const cParams =
+                ZSTD_getCParamsFromCCtxParams(params, ZSTD_CONTENTSIZE_UNKNOWN, 0, ZSTD_cpm_noAttachDict);
+
+    RETURN_ERROR_IF(params->nbWorkers > 0, GENERIC, "Estimate CCtx size is supported for single-threaded compression only.");
+    /* estimateCCtxSize is for one-shot compression. So no buffers should
+     * be needed. However, we still allocate two 0-sized buffers, which can
+     * take space under ASAN. */
+    return ZSTD_estimateCCtxSize_usingCCtxParams_internal(
+        &cParams, &params->ldmParams, 1, 0, 0, ZSTD_CONTENTSIZE_UNKNOWN);
+}
+
+size_t ZSTD_estimateCCtxSize_usingCParams(ZSTD_compressionParameters cParams)
+{
+    ZSTD_CCtx_params const params = ZSTD_makeCCtxParamsFromCParams(cParams);
+    return ZSTD_estimateCCtxSize_usingCCtxParams(&params);
+}
+
+static size_t ZSTD_estimateCCtxSize_internal(int compressionLevel)
+{
+    int tier = 0;
+    size_t largestSize = 0;
+    static const unsigned long long srcSizeTiers[4] = {16 KB, 128 KB, 256 KB, ZSTD_CONTENTSIZE_UNKNOWN};
+    for (; tier < 4; ++tier) {
+        /* Choose the set of cParams for a given level across all srcSizes that give the largest cctxSize */
+        ZSTD_compressionParameters const cParams = ZSTD_getCParams_internal(compressionLevel, srcSizeTiers[tier], 0, ZSTD_cpm_noAttachDict);
+        largestSize = MAX(ZSTD_estimateCCtxSize_usingCParams(cParams), largestSize);
+    }
+    return largestSize;
+}
+
+size_t ZSTD_estimateCCtxSize(int compressionLevel)
+{
+    int level;
+    size_t memBudget = 0;
+    for (level=MIN(compressionLevel, 1); level<=compressionLevel; level++) {
+        /* Ensure monotonically increasing memory usage as compression level increases */
+        size_t const newMB = ZSTD_estimateCCtxSize_internal(level);
+        if (newMB > memBudget) memBudget = newMB;
+    }
+    return memBudget;
+}
+
+size_t ZSTD_estimateCStreamSize_usingCCtxParams(const ZSTD_CCtx_params* params)
+{
+    RETURN_ERROR_IF(params->nbWorkers > 0, GENERIC, "Estimate CCtx size is supported for single-threaded compression only.");
+    {   ZSTD_compressionParameters const cParams =
+                ZSTD_getCParamsFromCCtxParams(params, ZSTD_CONTENTSIZE_UNKNOWN, 0, ZSTD_cpm_noAttachDict);
+        size_t const blockSize = MIN(ZSTD_BLOCKSIZE_MAX, (size_t)1 << cParams.windowLog);
+        size_t const inBuffSize = (params->inBufferMode == ZSTD_bm_buffered)
+                ? ((size_t)1 << cParams.windowLog) + blockSize
+                : 0;
+        size_t const outBuffSize = (params->outBufferMode == ZSTD_bm_buffered)
+                ? ZSTD_compressBound(blockSize) + 1
+                : 0;
+
+        return ZSTD_estimateCCtxSize_usingCCtxParams_internal(
+            &cParams, &params->ldmParams, 1, inBuffSize, outBuffSize,
+            ZSTD_CONTENTSIZE_UNKNOWN);
+    }
+}
+
+size_t ZSTD_estimateCStreamSize_usingCParams(ZSTD_compressionParameters cParams)
+{
+    ZSTD_CCtx_params const params = ZSTD_makeCCtxParamsFromCParams(cParams);
+    return ZSTD_estimateCStreamSize_usingCCtxParams(&params);
+}
+
+static size_t ZSTD_estimateCStreamSize_internal(int compressionLevel)
+{
+    ZSTD_compressionParameters const cParams = ZSTD_getCParams_internal(compressionLevel, ZSTD_CONTENTSIZE_UNKNOWN, 0, ZSTD_cpm_noAttachDict);
+    return ZSTD_estimateCStreamSize_usingCParams(cParams);
+}
+
+size_t ZSTD_estimateCStreamSize(int compressionLevel)
+{
+    int level;
+    size_t memBudget = 0;
+    for (level=MIN(compressionLevel, 1); level<=compressionLevel; level++) {
+        size_t const newMB = ZSTD_estimateCStreamSize_internal(level);
+        if (newMB > memBudget) memBudget = newMB;
+    }
+    return memBudget;
+}
+
+/* ZSTD_getFrameProgression():
+ * tells how much data has been consumed (input) and produced (output) for current frame.
+ * able to count progression inside worker threads (non-blocking mode).
+ */
+ZSTD_frameProgression ZSTD_getFrameProgression(const ZSTD_CCtx* cctx)
+{
+    {   ZSTD_frameProgression fp;
+        size_t const buffered = (cctx->inBuff == NULL) ? 0 :
+                                cctx->inBuffPos - cctx->inToCompress;
+        if (buffered) assert(cctx->inBuffPos >= cctx->inToCompress);
+        assert(buffered <= ZSTD_BLOCKSIZE_MAX);
+        fp.ingested = cctx->consumedSrcSize + buffered;
+        fp.consumed = cctx->consumedSrcSize;
+        fp.produced = cctx->producedCSize;
+        fp.flushed  = cctx->producedCSize;   /* simplified; some data might still be left within streaming output buffer */
+        fp.currentJobID = 0;
+        fp.nbActiveWorkers = 0;
+        return fp;
+}   }
+
+/*! ZSTD_toFlushNow()
+ *  Only useful for multithreading scenarios currently (nbWorkers >= 1).
+ */
+size_t ZSTD_toFlushNow(ZSTD_CCtx* cctx)
+{
+    (void)cctx;
+    return 0;   /* over-simplification; could also check if context is currently running in streaming mode, and in which case, report how many bytes are left to be flushed within output buffer */
+}
+
+static void ZSTD_assertEqualCParams(ZSTD_compressionParameters cParams1,
+                                    ZSTD_compressionParameters cParams2)
+{
+    (void)cParams1;
+    (void)cParams2;
+    assert(cParams1.windowLog    == cParams2.windowLog);
+    assert(cParams1.chainLog     == cParams2.chainLog);
+    assert(cParams1.hashLog      == cParams2.hashLog);
+    assert(cParams1.searchLog    == cParams2.searchLog);
+    assert(cParams1.minMatch     == cParams2.minMatch);
+    assert(cParams1.targetLength == cParams2.targetLength);
+    assert(cParams1.strategy     == cParams2.strategy);
+}
+
+void ZSTD_reset_compressedBlockState(ZSTD_compressedBlockState_t* bs)
+{
+    int i;
+    for (i = 0; i < ZSTD_REP_NUM; ++i)
+        bs->rep[i] = repStartValue[i];
+    bs->entropy.huf.repeatMode = HUF_repeat_none;
+    bs->entropy.fse.offcode_repeatMode = FSE_repeat_none;
+    bs->entropy.fse.matchlength_repeatMode = FSE_repeat_none;
+    bs->entropy.fse.litlength_repeatMode = FSE_repeat_none;
+}
+
+/*! ZSTD_invalidateMatchState()
+ *  Invalidate all the matches in the match finder tables.
+ *  Requires nextSrc and base to be set (can be NULL).
+ */
+static void ZSTD_invalidateMatchState(ZSTD_matchState_t* ms)
+{
+    ZSTD_window_clear(&ms->window);
+
+    ms->nextToUpdate = ms->window.dictLimit;
+    ms->loadedDictEnd = 0;
+    ms->opt.litLengthSum = 0;  /* force reset of btopt stats */
+    ms->dictMatchState = NULL;
+}
+
+/*
+ * Controls, for this matchState reset, whether the tables need to be cleared /
+ * prepared for the coming compression (ZSTDcrp_makeClean), or whether the
+ * tables can be left unclean (ZSTDcrp_leaveDirty), because we know that a
+ * subsequent operation will overwrite the table space anyways (e.g., copying
+ * the matchState contents in from a CDict).
+ */
+typedef enum {
+    ZSTDcrp_makeClean,
+    ZSTDcrp_leaveDirty
+} ZSTD_compResetPolicy_e;
+
+/*
+ * Controls, for this matchState reset, whether indexing can continue where it
+ * left off (ZSTDirp_continue), or whether it needs to be restarted from zero
+ * (ZSTDirp_reset).
+ */
+typedef enum {
+    ZSTDirp_continue,
+    ZSTDirp_reset
+} ZSTD_indexResetPolicy_e;
+
+typedef enum {
+    ZSTD_resetTarget_CDict,
+    ZSTD_resetTarget_CCtx
+} ZSTD_resetTarget_e;
+
+static size_t
+ZSTD_reset_matchState(ZSTD_matchState_t* ms,
+                      ZSTD_cwksp* ws,
+                const ZSTD_compressionParameters* cParams,
+                const ZSTD_compResetPolicy_e crp,
+                const ZSTD_indexResetPolicy_e forceResetIndex,
+                const ZSTD_resetTarget_e forWho)
+{
+    size_t const chainSize = (cParams->strategy == ZSTD_fast) ? 0 : ((size_t)1 << cParams->chainLog);
+    size_t const hSize = ((size_t)1) << cParams->hashLog;
+    U32    const hashLog3 = ((forWho == ZSTD_resetTarget_CCtx) && cParams->minMatch==3) ? MIN(ZSTD_HASHLOG3_MAX, cParams->windowLog) : 0;
+    size_t const h3Size = hashLog3 ? ((size_t)1) << hashLog3 : 0;
+
+    DEBUGLOG(4, "reset indices : %u", forceResetIndex == ZSTDirp_reset);
+    if (forceResetIndex == ZSTDirp_reset) {
+        ZSTD_window_init(&ms->window);
+        ZSTD_cwksp_mark_tables_dirty(ws);
+    }
+
+    ms->hashLog3 = hashLog3;
+
+    ZSTD_invalidateMatchState(ms);
+
+    assert(!ZSTD_cwksp_reserve_failed(ws)); /* check that allocation hasn't already failed */
+
+    ZSTD_cwksp_clear_tables(ws);
+
+    DEBUGLOG(5, "reserving table space");
+    /* table Space */
+    ms->hashTable = (U32*)ZSTD_cwksp_reserve_table(ws, hSize * sizeof(U32));
+    ms->chainTable = (U32*)ZSTD_cwksp_reserve_table(ws, chainSize * sizeof(U32));
+    ms->hashTable3 = (U32*)ZSTD_cwksp_reserve_table(ws, h3Size * sizeof(U32));
+    RETURN_ERROR_IF(ZSTD_cwksp_reserve_failed(ws), memory_allocation,
+                    "failed a workspace allocation in ZSTD_reset_matchState");
+
+    DEBUGLOG(4, "reset table : %u", crp!=ZSTDcrp_leaveDirty);
+    if (crp!=ZSTDcrp_leaveDirty) {
+        /* reset tables only */
+        ZSTD_cwksp_clean_tables(ws);
+    }
+
+    /* opt parser space */
+    if ((forWho == ZSTD_resetTarget_CCtx) && (cParams->strategy >= ZSTD_btopt)) {
+        DEBUGLOG(4, "reserving optimal parser space");
+        ms->opt.litFreq = (unsigned*)ZSTD_cwksp_reserve_aligned(ws, (1<<Litbits) * sizeof(unsigned));
+        ms->opt.litLengthFreq = (unsigned*)ZSTD_cwksp_reserve_aligned(ws, (MaxLL+1) * sizeof(unsigned));
+        ms->opt.matchLengthFreq = (unsigned*)ZSTD_cwksp_reserve_aligned(ws, (MaxML+1) * sizeof(unsigned));
+        ms->opt.offCodeFreq = (unsigned*)ZSTD_cwksp_reserve_aligned(ws, (MaxOff+1) * sizeof(unsigned));
+        ms->opt.matchTable = (ZSTD_match_t*)ZSTD_cwksp_reserve_aligned(ws, (ZSTD_OPT_NUM+1) * sizeof(ZSTD_match_t));
+        ms->opt.priceTable = (ZSTD_optimal_t*)ZSTD_cwksp_reserve_aligned(ws, (ZSTD_OPT_NUM+1) * sizeof(ZSTD_optimal_t));
+    }
+
+    ms->cParams = *cParams;
+
+    RETURN_ERROR_IF(ZSTD_cwksp_reserve_failed(ws), memory_allocation,
+                    "failed a workspace allocation in ZSTD_reset_matchState");
+
+    return 0;
+}
+
+/* ZSTD_indexTooCloseToMax() :
+ * minor optimization : prefer memset() rather than reduceIndex()
+ * which is measurably slow in some circumstances (reported for Visual Studio).
+ * Works when re-using a context for a lot of smallish inputs :
+ * if all inputs are smaller than ZSTD_INDEXOVERFLOW_MARGIN,
+ * memset() will be triggered before reduceIndex().
+ */
+#define ZSTD_INDEXOVERFLOW_MARGIN (16 MB)
+static int ZSTD_indexTooCloseToMax(ZSTD_window_t w)
+{
+    return (size_t)(w.nextSrc - w.base) > (ZSTD_CURRENT_MAX - ZSTD_INDEXOVERFLOW_MARGIN);
+}
+
+/*! ZSTD_resetCCtx_internal() :
+    note : `params` are assumed fully validated at this stage */
+static size_t ZSTD_resetCCtx_internal(ZSTD_CCtx* zc,
+                                      ZSTD_CCtx_params params,
+                                      U64 const pledgedSrcSize,
+                                      ZSTD_compResetPolicy_e const crp,
+                                      ZSTD_buffered_policy_e const zbuff)
+{
+    ZSTD_cwksp* const ws = &zc->workspace;
+    DEBUGLOG(4, "ZSTD_resetCCtx_internal: pledgedSrcSize=%u, wlog=%u",
+                (U32)pledgedSrcSize, params.cParams.windowLog);
+    assert(!ZSTD_isError(ZSTD_checkCParams(params.cParams)));
+
+    zc->isFirstBlock = 1;
+
+    if (params.ldmParams.enableLdm) {
+        /* Adjust long distance matching parameters */
+        ZSTD_ldm_adjustParameters(&params.ldmParams, &params.cParams);
+        assert(params.ldmParams.hashLog >= params.ldmParams.bucketSizeLog);
+        assert(params.ldmParams.hashRateLog < 32);
+    }
+
+    {   size_t const windowSize = MAX(1, (size_t)MIN(((U64)1 << params.cParams.windowLog), pledgedSrcSize));
+        size_t const blockSize = MIN(ZSTD_BLOCKSIZE_MAX, windowSize);
+        U32    const divider = (params.cParams.minMatch==3) ? 3 : 4;
+        size_t const maxNbSeq = blockSize / divider;
+        size_t const buffOutSize = (zbuff == ZSTDb_buffered && params.outBufferMode == ZSTD_bm_buffered)
+                ? ZSTD_compressBound(blockSize) + 1
+                : 0;
+        size_t const buffInSize = (zbuff == ZSTDb_buffered && params.inBufferMode == ZSTD_bm_buffered)
+                ? windowSize + blockSize
+                : 0;
+        size_t const maxNbLdmSeq = ZSTD_ldm_getMaxNbSeq(params.ldmParams, blockSize);
+
+        int const indexTooClose = ZSTD_indexTooCloseToMax(zc->blockState.matchState.window);
+        ZSTD_indexResetPolicy_e needsIndexReset =
+            (!indexTooClose && zc->initialized) ? ZSTDirp_continue : ZSTDirp_reset;
+
+        size_t const neededSpace =
+            ZSTD_estimateCCtxSize_usingCCtxParams_internal(
+                &params.cParams, &params.ldmParams, zc->staticSize != 0,
+                buffInSize, buffOutSize, pledgedSrcSize);
+        FORWARD_IF_ERROR(neededSpace, "cctx size estimate failed!");
+
+        if (!zc->staticSize) ZSTD_cwksp_bump_oversized_duration(ws, 0);
+
+        /* Check if workspace is large enough, alloc a new one if needed */
+        {
+            int const workspaceTooSmall = ZSTD_cwksp_sizeof(ws) < neededSpace;
+            int const workspaceWasteful = ZSTD_cwksp_check_wasteful(ws, neededSpace);
+
+            DEBUGLOG(4, "Need %zu B workspace", neededSpace);
+            DEBUGLOG(4, "windowSize: %zu - blockSize: %zu", windowSize, blockSize);
+
+            if (workspaceTooSmall || workspaceWasteful) {
+                DEBUGLOG(4, "Resize workspaceSize from %zuKB to %zuKB",
+                            ZSTD_cwksp_sizeof(ws) >> 10,
+                            neededSpace >> 10);
+
+                RETURN_ERROR_IF(zc->staticSize, memory_allocation, "static cctx : no resize");
+
+                needsIndexReset = ZSTDirp_reset;
+
+                ZSTD_cwksp_free(ws, zc->customMem);
+                FORWARD_IF_ERROR(ZSTD_cwksp_create(ws, neededSpace, zc->customMem), "");
+
+                DEBUGLOG(5, "reserving object space");
+                /* Statically sized space.
+                 * entropyWorkspace never moves,
+                 * though prev/next block swap places */
+                assert(ZSTD_cwksp_check_available(ws, 2 * sizeof(ZSTD_compressedBlockState_t)));
+                zc->blockState.prevCBlock = (ZSTD_compressedBlockState_t*) ZSTD_cwksp_reserve_object(ws, sizeof(ZSTD_compressedBlockState_t));
+                RETURN_ERROR_IF(zc->blockState.prevCBlock == NULL, memory_allocation, "couldn't allocate prevCBlock");
+                zc->blockState.nextCBlock = (ZSTD_compressedBlockState_t*) ZSTD_cwksp_reserve_object(ws, sizeof(ZSTD_compressedBlockState_t));
+                RETURN_ERROR_IF(zc->blockState.nextCBlock == NULL, memory_allocation, "couldn't allocate nextCBlock");
+                zc->entropyWorkspace = (U32*) ZSTD_cwksp_reserve_object(ws, ENTROPY_WORKSPACE_SIZE);
+                RETURN_ERROR_IF(zc->blockState.nextCBlock == NULL, memory_allocation, "couldn't allocate entropyWorkspace");
+        }   }
+
+        ZSTD_cwksp_clear(ws);
+
+        /* init params */
+        zc->appliedParams = params;
+        zc->blockState.matchState.cParams = params.cParams;
+        zc->pledgedSrcSizePlusOne = pledgedSrcSize+1;
+        zc->consumedSrcSize = 0;
+        zc->producedCSize = 0;
+        if (pledgedSrcSize == ZSTD_CONTENTSIZE_UNKNOWN)
+            zc->appliedParams.fParams.contentSizeFlag = 0;
+        DEBUGLOG(4, "pledged content size : %u ; flag : %u",
+            (unsigned)pledgedSrcSize, zc->appliedParams.fParams.contentSizeFlag);
+        zc->blockSize = blockSize;
+
+        xxh64_reset(&zc->xxhState, 0);
+        zc->stage = ZSTDcs_init;
+        zc->dictID = 0;
+        zc->dictContentSize = 0;
+
+        ZSTD_reset_compressedBlockState(zc->blockState.prevCBlock);
+
+        /* ZSTD_wildcopy() is used to copy into the literals buffer,
+         * so we have to oversize the buffer by WILDCOPY_OVERLENGTH bytes.
+         */
+        zc->seqStore.litStart = ZSTD_cwksp_reserve_buffer(ws, blockSize + WILDCOPY_OVERLENGTH);
+        zc->seqStore.maxNbLit = blockSize;
+
+        /* buffers */
+        zc->bufferedPolicy = zbuff;
+        zc->inBuffSize = buffInSize;
+        zc->inBuff = (char*)ZSTD_cwksp_reserve_buffer(ws, buffInSize);
+        zc->outBuffSize = buffOutSize;
+        zc->outBuff = (char*)ZSTD_cwksp_reserve_buffer(ws, buffOutSize);
+
+        /* ldm bucketOffsets table */
+        if (params.ldmParams.enableLdm) {
+            /* TODO: avoid memset? */
+            size_t const numBuckets =
+                  ((size_t)1) << (params.ldmParams.hashLog -
+                                  params.ldmParams.bucketSizeLog);
+            zc->ldmState.bucketOffsets = ZSTD_cwksp_reserve_buffer(ws, numBuckets);
+            ZSTD_memset(zc->ldmState.bucketOffsets, 0, numBuckets);
+        }
+
+        /* sequences storage */
+        ZSTD_referenceExternalSequences(zc, NULL, 0);
+        zc->seqStore.maxNbSeq = maxNbSeq;
+        zc->seqStore.llCode = ZSTD_cwksp_reserve_buffer(ws, maxNbSeq * sizeof(BYTE));
+        zc->seqStore.mlCode = ZSTD_cwksp_reserve_buffer(ws, maxNbSeq * sizeof(BYTE));
+        zc->seqStore.ofCode = ZSTD_cwksp_reserve_buffer(ws, maxNbSeq * sizeof(BYTE));
+        zc->seqStore.sequencesStart = (seqDef*)ZSTD_cwksp_reserve_aligned(ws, maxNbSeq * sizeof(seqDef));
+
+        FORWARD_IF_ERROR(ZSTD_reset_matchState(
+            &zc->blockState.matchState,
+            ws,
+            &params.cParams,
+            crp,
+            needsIndexReset,
+            ZSTD_resetTarget_CCtx), "");
+
+        /* ldm hash table */
+        if (params.ldmParams.enableLdm) {
+            /* TODO: avoid memset? */
+            size_t const ldmHSize = ((size_t)1) << params.ldmParams.hashLog;
+            zc->ldmState.hashTable = (ldmEntry_t*)ZSTD_cwksp_reserve_aligned(ws, ldmHSize * sizeof(ldmEntry_t));
+            ZSTD_memset(zc->ldmState.hashTable, 0, ldmHSize * sizeof(ldmEntry_t));
+            zc->ldmSequences = (rawSeq*)ZSTD_cwksp_reserve_aligned(ws, maxNbLdmSeq * sizeof(rawSeq));
+            zc->maxNbLdmSequences = maxNbLdmSeq;
+
+            ZSTD_window_init(&zc->ldmState.window);
+            ZSTD_window_clear(&zc->ldmState.window);
+            zc->ldmState.loadedDictEnd = 0;
+        }
+
+        /* Due to alignment, when reusing a workspace, we can actually consume
+         * up to 3 extra bytes for alignment. See the comments in zstd_cwksp.h
+         */
+        assert(ZSTD_cwksp_used(ws) >= neededSpace &&
+               ZSTD_cwksp_used(ws) <= neededSpace + 3);
+
+        DEBUGLOG(3, "wksp: finished allocating, %zd bytes remain available", ZSTD_cwksp_available_space(ws));
+        zc->initialized = 1;
+
+        return 0;
+    }
+}
+
+/* ZSTD_invalidateRepCodes() :
+ * ensures next compression will not use repcodes from previous block.
+ * Note : only works with regular variant;
+ *        do not use with extDict variant ! */
+void ZSTD_invalidateRepCodes(ZSTD_CCtx* cctx) {
+    int i;
+    for (i=0; i<ZSTD_REP_NUM; i++) cctx->blockState.prevCBlock->rep[i] = 0;
+    assert(!ZSTD_window_hasExtDict(cctx->blockState.matchState.window));
+}
+
+/* These are the approximate sizes for each strategy past which copying the
+ * dictionary tables into the working context is faster than using them
+ * in-place.
+ */
+static const size_t attachDictSizeCutoffs[ZSTD_STRATEGY_MAX+1] = {
+    8 KB,  /* unused */
+    8 KB,  /* ZSTD_fast */
+    16 KB, /* ZSTD_dfast */
+    32 KB, /* ZSTD_greedy */
+    32 KB, /* ZSTD_lazy */
+    32 KB, /* ZSTD_lazy2 */
+    32 KB, /* ZSTD_btlazy2 */
+    32 KB, /* ZSTD_btopt */
+    8 KB,  /* ZSTD_btultra */
+    8 KB   /* ZSTD_btultra2 */
+};
+
+static int ZSTD_shouldAttachDict(const ZSTD_CDict* cdict,
+                                 const ZSTD_CCtx_params* params,
+                                 U64 pledgedSrcSize)
+{
+    size_t cutoff = attachDictSizeCutoffs[cdict->matchState.cParams.strategy];
+    int const dedicatedDictSearch = cdict->matchState.dedicatedDictSearch;
+    return dedicatedDictSearch
+        || ( ( pledgedSrcSize <= cutoff
+            || pledgedSrcSize == ZSTD_CONTENTSIZE_UNKNOWN
+            || params->attachDictPref == ZSTD_dictForceAttach )
+          && params->attachDictPref != ZSTD_dictForceCopy
+          && !params->forceWindow ); /* dictMatchState isn't correctly
+                                      * handled in _enforceMaxDist */
+}
+
+static size_t
+ZSTD_resetCCtx_byAttachingCDict(ZSTD_CCtx* cctx,
+                        const ZSTD_CDict* cdict,
+                        ZSTD_CCtx_params params,
+                        U64 pledgedSrcSize,
+                        ZSTD_buffered_policy_e zbuff)
+{
+    {
+        ZSTD_compressionParameters adjusted_cdict_cParams = cdict->matchState.cParams;
+        unsigned const windowLog = params.cParams.windowLog;
+        assert(windowLog != 0);
+        /* Resize working context table params for input only, since the dict
+         * has its own tables. */
+        /* pledgedSrcSize == 0 means 0! */
+
+        if (cdict->matchState.dedicatedDictSearch) {
+            ZSTD_dedicatedDictSearch_revertCParams(&adjusted_cdict_cParams);
+        }
+
+        params.cParams = ZSTD_adjustCParams_internal(adjusted_cdict_cParams, pledgedSrcSize,
+                                                     cdict->dictContentSize, ZSTD_cpm_attachDict);
+        params.cParams.windowLog = windowLog;
+        FORWARD_IF_ERROR(ZSTD_resetCCtx_internal(cctx, params, pledgedSrcSize,
+                                                 ZSTDcrp_makeClean, zbuff), "");
+        assert(cctx->appliedParams.cParams.strategy == adjusted_cdict_cParams.strategy);
+    }
+
+    {   const U32 cdictEnd = (U32)( cdict->matchState.window.nextSrc
+                                  - cdict->matchState.window.base);
+        const U32 cdictLen = cdictEnd - cdict->matchState.window.dictLimit;
+        if (cdictLen == 0) {
+            /* don't even attach dictionaries with no contents */
+            DEBUGLOG(4, "skipping attaching empty dictionary");
+        } else {
+            DEBUGLOG(4, "attaching dictionary into context");
+            cctx->blockState.matchState.dictMatchState = &cdict->matchState;
+
+            /* prep working match state so dict matches never have negative indices
+             * when they are translated to the working context's index space. */
+            if (cctx->blockState.matchState.window.dictLimit < cdictEnd) {
+                cctx->blockState.matchState.window.nextSrc =
+                    cctx->blockState.matchState.window.base + cdictEnd;
+                ZSTD_window_clear(&cctx->blockState.matchState.window);
+            }
+            /* loadedDictEnd is expressed within the referential of the active context */
+            cctx->blockState.matchState.loadedDictEnd = cctx->blockState.matchState.window.dictLimit;
+    }   }
+
+    cctx->dictID = cdict->dictID;
+    cctx->dictContentSize = cdict->dictContentSize;
+
+    /* copy block state */
+    ZSTD_memcpy(cctx->blockState.prevCBlock, &cdict->cBlockState, sizeof(cdict->cBlockState));
+
+    return 0;
+}
+
+static size_t ZSTD_resetCCtx_byCopyingCDict(ZSTD_CCtx* cctx,
+                            const ZSTD_CDict* cdict,
+                            ZSTD_CCtx_params params,
+                            U64 pledgedSrcSize,
+                            ZSTD_buffered_policy_e zbuff)
+{
+    const ZSTD_compressionParameters *cdict_cParams = &cdict->matchState.cParams;
+
+    assert(!cdict->matchState.dedicatedDictSearch);
+
+    DEBUGLOG(4, "copying dictionary into context");
+
+    {   unsigned const windowLog = params.cParams.windowLog;
+        assert(windowLog != 0);
+        /* Copy only compression parameters related to tables. */
+        params.cParams = *cdict_cParams;
+        params.cParams.windowLog = windowLog;
+        FORWARD_IF_ERROR(ZSTD_resetCCtx_internal(cctx, params, pledgedSrcSize,
+                                                 ZSTDcrp_leaveDirty, zbuff), "");
+        assert(cctx->appliedParams.cParams.strategy == cdict_cParams->strategy);
+        assert(cctx->appliedParams.cParams.hashLog == cdict_cParams->hashLog);
+        assert(cctx->appliedParams.cParams.chainLog == cdict_cParams->chainLog);
+    }
+
+    ZSTD_cwksp_mark_tables_dirty(&cctx->workspace);
+
+    /* copy tables */
+    {   size_t const chainSize = (cdict_cParams->strategy == ZSTD_fast) ? 0 : ((size_t)1 << cdict_cParams->chainLog);
+        size_t const hSize =  (size_t)1 << cdict_cParams->hashLog;
+
+        ZSTD_memcpy(cctx->blockState.matchState.hashTable,
+               cdict->matchState.hashTable,
+               hSize * sizeof(U32));
+        ZSTD_memcpy(cctx->blockState.matchState.chainTable,
+               cdict->matchState.chainTable,
+               chainSize * sizeof(U32));
+    }
+
+    /* Zero the hashTable3, since the cdict never fills it */
+    {   int const h3log = cctx->blockState.matchState.hashLog3;
+        size_t const h3Size = h3log ? ((size_t)1 << h3log) : 0;
+        assert(cdict->matchState.hashLog3 == 0);
+        ZSTD_memset(cctx->blockState.matchState.hashTable3, 0, h3Size * sizeof(U32));
+    }
+
+    ZSTD_cwksp_mark_tables_clean(&cctx->workspace);
+
+    /* copy dictionary offsets */
+    {   ZSTD_matchState_t const* srcMatchState = &cdict->matchState;
+        ZSTD_matchState_t* dstMatchState = &cctx->blockState.matchState;
+        dstMatchState->window       = srcMatchState->window;
+        dstMatchState->nextToUpdate = srcMatchState->nextToUpdate;
+        dstMatchState->loadedDictEnd= srcMatchState->loadedDictEnd;
+    }
+
+    cctx->dictID = cdict->dictID;
+    cctx->dictContentSize = cdict->dictContentSize;
+
+    /* copy block state */
+    ZSTD_memcpy(cctx->blockState.prevCBlock, &cdict->cBlockState, sizeof(cdict->cBlockState));
+
+    return 0;
+}
+
+/* We have a choice between copying the dictionary context into the working
+ * context, or referencing the dictionary context from the working context
+ * in-place. We decide here which strategy to use. */
+static size_t ZSTD_resetCCtx_usingCDict(ZSTD_CCtx* cctx,
+                            const ZSTD_CDict* cdict,
+                            const ZSTD_CCtx_params* params,
+                            U64 pledgedSrcSize,
+                            ZSTD_buffered_policy_e zbuff)
+{
+
+    DEBUGLOG(4, "ZSTD_resetCCtx_usingCDict (pledgedSrcSize=%u)",
+                (unsigned)pledgedSrcSize);
+
+    if (ZSTD_shouldAttachDict(cdict, params, pledgedSrcSize)) {
+        return ZSTD_resetCCtx_byAttachingCDict(
+            cctx, cdict, *params, pledgedSrcSize, zbuff);
+    } else {
+        return ZSTD_resetCCtx_byCopyingCDict(
+            cctx, cdict, *params, pledgedSrcSize, zbuff);
+    }
+}
+
+/*! ZSTD_copyCCtx_internal() :
+ *  Duplicate an existing context `srcCCtx` into another one `dstCCtx`.
+ *  Only works during stage ZSTDcs_init (i.e. after creation, but before first call to ZSTD_compressContinue()).
+ *  The "context", in this case, refers to the hash and chain tables,
+ *  entropy tables, and dictionary references.
+ * `windowLog` value is enforced if != 0, otherwise value is copied from srcCCtx.
+ * @return : 0, or an error code */
+static size_t ZSTD_copyCCtx_internal(ZSTD_CCtx* dstCCtx,
+                            const ZSTD_CCtx* srcCCtx,
+                            ZSTD_frameParameters fParams,
+                            U64 pledgedSrcSize,
+                            ZSTD_buffered_policy_e zbuff)
+{
+    DEBUGLOG(5, "ZSTD_copyCCtx_internal");
+    RETURN_ERROR_IF(srcCCtx->stage!=ZSTDcs_init, stage_wrong,
+                    "Can't copy a ctx that's not in init stage.");
+
+    ZSTD_memcpy(&dstCCtx->customMem, &srcCCtx->customMem, sizeof(ZSTD_customMem));
+    {   ZSTD_CCtx_params params = dstCCtx->requestedParams;
+        /* Copy only compression parameters related to tables. */
+        params.cParams = srcCCtx->appliedParams.cParams;
+        params.fParams = fParams;
+        ZSTD_resetCCtx_internal(dstCCtx, params, pledgedSrcSize,
+                                ZSTDcrp_leaveDirty, zbuff);
+        assert(dstCCtx->appliedParams.cParams.windowLog == srcCCtx->appliedParams.cParams.windowLog);
+        assert(dstCCtx->appliedParams.cParams.strategy == srcCCtx->appliedParams.cParams.strategy);
+        assert(dstCCtx->appliedParams.cParams.hashLog == srcCCtx->appliedParams.cParams.hashLog);
+        assert(dstCCtx->appliedParams.cParams.chainLog == srcCCtx->appliedParams.cParams.chainLog);
+        assert(dstCCtx->blockState.matchState.hashLog3 == srcCCtx->blockState.matchState.hashLog3);
+    }
+
+    ZSTD_cwksp_mark_tables_dirty(&dstCCtx->workspace);
+
+    /* copy tables */
+    {   size_t const chainSize = (srcCCtx->appliedParams.cParams.strategy == ZSTD_fast) ? 0 : ((size_t)1 << srcCCtx->appliedParams.cParams.chainLog);
+        size_t const hSize =  (size_t)1 << srcCCtx->appliedParams.cParams.hashLog;
+        int const h3log = srcCCtx->blockState.matchState.hashLog3;
+        size_t const h3Size = h3log ? ((size_t)1 << h3log) : 0;
+
+        ZSTD_memcpy(dstCCtx->blockState.matchState.hashTable,
+               srcCCtx->blockState.matchState.hashTable,
+               hSize * sizeof(U32));
+        ZSTD_memcpy(dstCCtx->blockState.matchState.chainTable,
+               srcCCtx->blockState.matchState.chainTable,
+               chainSize * sizeof(U32));
+        ZSTD_memcpy(dstCCtx->blockState.matchState.hashTable3,
+               srcCCtx->blockState.matchState.hashTable3,
+               h3Size * sizeof(U32));
+    }
+
+    ZSTD_cwksp_mark_tables_clean(&dstCCtx->workspace);
+
+    /* copy dictionary offsets */
+    {
+        const ZSTD_matchState_t* srcMatchState = &srcCCtx->blockState.matchState;
+        ZSTD_matchState_t* dstMatchState = &dstCCtx->blockState.matchState;
+        dstMatchState->window       = srcMatchState->window;
+        dstMatchState->nextToUpdate = srcMatchState->nextToUpdate;
+        dstMatchState->loadedDictEnd= srcMatchState->loadedDictEnd;
+    }
+    dstCCtx->dictID = srcCCtx->dictID;
+    dstCCtx->dictContentSize = srcCCtx->dictContentSize;
+
+    /* copy block state */
+    ZSTD_memcpy(dstCCtx->blockState.prevCBlock, srcCCtx->blockState.prevCBlock, sizeof(*srcCCtx->blockState.prevCBlock));
+
+    return 0;
+}
+
+/*! ZSTD_copyCCtx() :
+ *  Duplicate an existing context `srcCCtx` into another one `dstCCtx`.
+ *  Only works during stage ZSTDcs_init (i.e. after creation, but before first call to ZSTD_compressContinue()).
+ *  pledgedSrcSize==0 means "unknown".
+*   @return : 0, or an error code */
+size_t ZSTD_copyCCtx(ZSTD_CCtx* dstCCtx, const ZSTD_CCtx* srcCCtx, unsigned long long pledgedSrcSize)
+{
+    ZSTD_frameParameters fParams = { 1 /*content*/, 0 /*checksum*/, 0 /*noDictID*/ };
+    ZSTD_buffered_policy_e const zbuff = srcCCtx->bufferedPolicy;
+    ZSTD_STATIC_ASSERT((U32)ZSTDb_buffered==1);
+    if (pledgedSrcSize==0) pledgedSrcSize = ZSTD_CONTENTSIZE_UNKNOWN;
+    fParams.contentSizeFlag = (pledgedSrcSize != ZSTD_CONTENTSIZE_UNKNOWN);
+
+    return ZSTD_copyCCtx_internal(dstCCtx, srcCCtx,
+                                fParams, pledgedSrcSize,
+                                zbuff);
+}
+
+
+#define ZSTD_ROWSIZE 16
+/*! ZSTD_reduceTable() :
+ *  reduce table indexes by `reducerValue`, or squash to zero.
+ *  PreserveMark preserves "unsorted mark" for btlazy2 strategy.
+ *  It must be set to a clear 0/1 value, to remove branch during inlining.
+ *  Presume table size is a multiple of ZSTD_ROWSIZE
+ *  to help auto-vectorization */
+FORCE_INLINE_TEMPLATE void
+ZSTD_reduceTable_internal (U32* const table, U32 const size, U32 const reducerValue, int const preserveMark)
+{
+    int const nbRows = (int)size / ZSTD_ROWSIZE;
+    int cellNb = 0;
+    int rowNb;
+    assert((size & (ZSTD_ROWSIZE-1)) == 0);  /* multiple of ZSTD_ROWSIZE */
+    assert(size < (1U<<31));   /* can be casted to int */
+
+
+    for (rowNb=0 ; rowNb < nbRows ; rowNb++) {
+        int column;
+        for (column=0; column<ZSTD_ROWSIZE; column++) {
+            if (preserveMark) {
+                U32 const adder = (table[cellNb] == ZSTD_DUBT_UNSORTED_MARK) ? reducerValue : 0;
+                table[cellNb] += adder;
+            }
+            if (table[cellNb] < reducerValue) table[cellNb] = 0;
+            else table[cellNb] -= reducerValue;
+            cellNb++;
+    }   }
+}
+
+static void ZSTD_reduceTable(U32* const table, U32 const size, U32 const reducerValue)
+{
+    ZSTD_reduceTable_internal(table, size, reducerValue, 0);
+}
+
+static void ZSTD_reduceTable_btlazy2(U32* const table, U32 const size, U32 const reducerValue)
+{
+    ZSTD_reduceTable_internal(table, size, reducerValue, 1);
+}
+
+/*! ZSTD_reduceIndex() :
+*   rescale all indexes to avoid future overflow (indexes are U32) */
+static void ZSTD_reduceIndex (ZSTD_matchState_t* ms, ZSTD_CCtx_params const* params, const U32 reducerValue)
+{
+    {   U32 const hSize = (U32)1 << params->cParams.hashLog;
+        ZSTD_reduceTable(ms->hashTable, hSize, reducerValue);
+    }
+
+    if (params->cParams.strategy != ZSTD_fast) {
+        U32 const chainSize = (U32)1 << params->cParams.chainLog;
+        if (params->cParams.strategy == ZSTD_btlazy2)
+            ZSTD_reduceTable_btlazy2(ms->chainTable, chainSize, reducerValue);
+        else
+            ZSTD_reduceTable(ms->chainTable, chainSize, reducerValue);
+    }
+
+    if (ms->hashLog3) {
+        U32 const h3Size = (U32)1 << ms->hashLog3;
+        ZSTD_reduceTable(ms->hashTable3, h3Size, reducerValue);
+    }
+}
+
+
+/*-*******************************************************
+*  Block entropic compression
+*********************************************************/
+
+/* See doc/zstd_compression_format.md for detailed format description */
+
+void ZSTD_seqToCodes(const seqStore_t* seqStorePtr)
+{
+    const seqDef* const sequences = seqStorePtr->sequencesStart;
+    BYTE* const llCodeTable = seqStorePtr->llCode;
+    BYTE* const ofCodeTable = seqStorePtr->ofCode;
+    BYTE* const mlCodeTable = seqStorePtr->mlCode;
+    U32 const nbSeq = (U32)(seqStorePtr->sequences - seqStorePtr->sequencesStart);
+    U32 u;
+    assert(nbSeq <= seqStorePtr->maxNbSeq);
+    for (u=0; u<nbSeq; u++) {
+        U32 const llv = sequences[u].litLength;
+        U32 const mlv = sequences[u].matchLength;
+        llCodeTable[u] = (BYTE)ZSTD_LLcode(llv);
+        ofCodeTable[u] = (BYTE)ZSTD_highbit32(sequences[u].offset);
+        mlCodeTable[u] = (BYTE)ZSTD_MLcode(mlv);
+    }
+    if (seqStorePtr->longLengthID==1)
+        llCodeTable[seqStorePtr->longLengthPos] = MaxLL;
+    if (seqStorePtr->longLengthID==2)
+        mlCodeTable[seqStorePtr->longLengthPos] = MaxML;
+}
+
+/* ZSTD_useTargetCBlockSize():
+ * Returns if target compressed block size param is being used.
+ * If used, compression will do best effort to make a compressed block size to be around targetCBlockSize.
+ * Returns 1 if true, 0 otherwise. */
+static int ZSTD_useTargetCBlockSize(const ZSTD_CCtx_params* cctxParams)
+{
+    DEBUGLOG(5, "ZSTD_useTargetCBlockSize (targetCBlockSize=%zu)", cctxParams->targetCBlockSize);
+    return (cctxParams->targetCBlockSize != 0);
+}
+
+/* ZSTD_entropyCompressSequences_internal():
+ * actually compresses both literals and sequences */
+MEM_STATIC size_t
+ZSTD_entropyCompressSequences_internal(seqStore_t* seqStorePtr,
+                          const ZSTD_entropyCTables_t* prevEntropy,
+                                ZSTD_entropyCTables_t* nextEntropy,
+                          const ZSTD_CCtx_params* cctxParams,
+                                void* dst, size_t dstCapacity,
+                                void* entropyWorkspace, size_t entropyWkspSize,
+                          const int bmi2)
+{
+    const int longOffsets = cctxParams->cParams.windowLog > STREAM_ACCUMULATOR_MIN;
+    ZSTD_strategy const strategy = cctxParams->cParams.strategy;
+    unsigned* count = (unsigned*)entropyWorkspace;
+    FSE_CTable* CTable_LitLength = nextEntropy->fse.litlengthCTable;
+    FSE_CTable* CTable_OffsetBits = nextEntropy->fse.offcodeCTable;
+    FSE_CTable* CTable_MatchLength = nextEntropy->fse.matchlengthCTable;
+    U32 LLtype, Offtype, MLtype;   /* compressed, raw or rle */
+    const seqDef* const sequences = seqStorePtr->sequencesStart;
+    const BYTE* const ofCodeTable = seqStorePtr->ofCode;
+    const BYTE* const llCodeTable = seqStorePtr->llCode;
+    const BYTE* const mlCodeTable = seqStorePtr->mlCode;
+    BYTE* const ostart = (BYTE*)dst;
+    BYTE* const oend = ostart + dstCapacity;
+    BYTE* op = ostart;
+    size_t const nbSeq = (size_t)(seqStorePtr->sequences - seqStorePtr->sequencesStart);
+    BYTE* seqHead;
+    BYTE* lastNCount = NULL;
+
+    entropyWorkspace = count + (MaxSeq + 1);
+    entropyWkspSize -= (MaxSeq + 1) * sizeof(*count);
+
+    DEBUGLOG(4, "ZSTD_entropyCompressSequences_internal (nbSeq=%zu)", nbSeq);
+    ZSTD_STATIC_ASSERT(HUF_WORKSPACE_SIZE >= (1<<MAX(MLFSELog,LLFSELog)));
+    assert(entropyWkspSize >= HUF_WORKSPACE_SIZE);
+
+    /* Compress literals */
+    {   const BYTE* const literals = seqStorePtr->litStart;
+        size_t const litSize = (size_t)(seqStorePtr->lit - literals);
+        size_t const cSize = ZSTD_compressLiterals(
+                                    &prevEntropy->huf, &nextEntropy->huf,
+                                    cctxParams->cParams.strategy,
+                                    ZSTD_disableLiteralsCompression(cctxParams),
+                                    op, dstCapacity,
+                                    literals, litSize,
+                                    entropyWorkspace, entropyWkspSize,
+                                    bmi2);
+        FORWARD_IF_ERROR(cSize, "ZSTD_compressLiterals failed");
+        assert(cSize <= dstCapacity);
+        op += cSize;
+    }
+
+    /* Sequences Header */
+    RETURN_ERROR_IF((oend-op) < 3 /*max nbSeq Size*/ + 1 /*seqHead*/,
+                    dstSize_tooSmall, "Can't fit seq hdr in output buf!");
+    if (nbSeq < 128) {
+        *op++ = (BYTE)nbSeq;
+    } else if (nbSeq < LONGNBSEQ) {
+        op[0] = (BYTE)((nbSeq>>8) + 0x80);
+        op[1] = (BYTE)nbSeq;
+        op+=2;
+    } else {
+        op[0]=0xFF;
+        MEM_writeLE16(op+1, (U16)(nbSeq - LONGNBSEQ));
+        op+=3;
+    }
+    assert(op <= oend);
+    if (nbSeq==0) {
+        /* Copy the old tables over as if we repeated them */
+        ZSTD_memcpy(&nextEntropy->fse, &prevEntropy->fse, sizeof(prevEntropy->fse));
+        return (size_t)(op - ostart);
+    }
+
+    /* seqHead : flags for FSE encoding type */
+    seqHead = op++;
+    assert(op <= oend);
+
+    /* convert length/distances into codes */
+    ZSTD_seqToCodes(seqStorePtr);
+    /* build CTable for Literal Lengths */
+    {   unsigned max = MaxLL;
+        size_t const mostFrequent = HIST_countFast_wksp(count, &max, llCodeTable, nbSeq, entropyWorkspace, entropyWkspSize);   /* can't fail */
+        DEBUGLOG(5, "Building LL table");
+        nextEntropy->fse.litlength_repeatMode = prevEntropy->fse.litlength_repeatMode;
+        LLtype = ZSTD_selectEncodingType(&nextEntropy->fse.litlength_repeatMode,
+                                        count, max, mostFrequent, nbSeq,
+                                        LLFSELog, prevEntropy->fse.litlengthCTable,
+                                        LL_defaultNorm, LL_defaultNormLog,
+                                        ZSTD_defaultAllowed, strategy);
+        assert(set_basic < set_compressed && set_rle < set_compressed);
+        assert(!(LLtype < set_compressed && nextEntropy->fse.litlength_repeatMode != FSE_repeat_none)); /* We don't copy tables */
+        {   size_t const countSize = ZSTD_buildCTable(
+                op, (size_t)(oend - op),
+                CTable_LitLength, LLFSELog, (symbolEncodingType_e)LLtype,
+                count, max, llCodeTable, nbSeq,
+                LL_defaultNorm, LL_defaultNormLog, MaxLL,
+                prevEntropy->fse.litlengthCTable,
+                sizeof(prevEntropy->fse.litlengthCTable),
+                entropyWorkspace, entropyWkspSize);
+            FORWARD_IF_ERROR(countSize, "ZSTD_buildCTable for LitLens failed");
+            if (LLtype == set_compressed)
+                lastNCount = op;
+            op += countSize;
+            assert(op <= oend);
+    }   }
+    /* build CTable for Offsets */
+    {   unsigned max = MaxOff;
+        size_t const mostFrequent = HIST_countFast_wksp(
+            count, &max, ofCodeTable, nbSeq, entropyWorkspace, entropyWkspSize);  /* can't fail */
+        /* We can only use the basic table if max <= DefaultMaxOff, otherwise the offsets are too large */
+        ZSTD_defaultPolicy_e const defaultPolicy = (max <= DefaultMaxOff) ? ZSTD_defaultAllowed : ZSTD_defaultDisallowed;
+        DEBUGLOG(5, "Building OF table");
+        nextEntropy->fse.offcode_repeatMode = prevEntropy->fse.offcode_repeatMode;
+        Offtype = ZSTD_selectEncodingType(&nextEntropy->fse.offcode_repeatMode,
+                                        count, max, mostFrequent, nbSeq,
+                                        OffFSELog, prevEntropy->fse.offcodeCTable,
+                                        OF_defaultNorm, OF_defaultNormLog,
+                                        defaultPolicy, strategy);
+        assert(!(Offtype < set_compressed && nextEntropy->fse.offcode_repeatMode != FSE_repeat_none)); /* We don't copy tables */
+        {   size_t const countSize = ZSTD_buildCTable(
+                op, (size_t)(oend - op),
+                CTable_OffsetBits, OffFSELog, (symbolEncodingType_e)Offtype,
+                count, max, ofCodeTable, nbSeq,
+                OF_defaultNorm, OF_defaultNormLog, DefaultMaxOff,
+                prevEntropy->fse.offcodeCTable,
+                sizeof(prevEntropy->fse.offcodeCTable),
+                entropyWorkspace, entropyWkspSize);
+            FORWARD_IF_ERROR(countSize, "ZSTD_buildCTable for Offsets failed");
+            if (Offtype == set_compressed)
+                lastNCount = op;
+            op += countSize;
+            assert(op <= oend);
+    }   }
+    /* build CTable for MatchLengths */
+    {   unsigned max = MaxML;
+        size_t const mostFrequent = HIST_countFast_wksp(
+            count, &max, mlCodeTable, nbSeq, entropyWorkspace, entropyWkspSize);   /* can't fail */
+        DEBUGLOG(5, "Building ML table (remaining space : %i)", (int)(oend-op));
+        nextEntropy->fse.matchlength_repeatMode = prevEntropy->fse.matchlength_repeatMode;
+        MLtype = ZSTD_selectEncodingType(&nextEntropy->fse.matchlength_repeatMode,
+                                        count, max, mostFrequent, nbSeq,
+                                        MLFSELog, prevEntropy->fse.matchlengthCTable,
+                                        ML_defaultNorm, ML_defaultNormLog,
+                                        ZSTD_defaultAllowed, strategy);
+        assert(!(MLtype < set_compressed && nextEntropy->fse.matchlength_repeatMode != FSE_repeat_none)); /* We don't copy tables */
+        {   size_t const countSize = ZSTD_buildCTable(
+                op, (size_t)(oend - op),
+                CTable_MatchLength, MLFSELog, (symbolEncodingType_e)MLtype,
+                count, max, mlCodeTable, nbSeq,
+                ML_defaultNorm, ML_defaultNormLog, MaxML,
+                prevEntropy->fse.matchlengthCTable,
+                sizeof(prevEntropy->fse.matchlengthCTable),
+                entropyWorkspace, entropyWkspSize);
+            FORWARD_IF_ERROR(countSize, "ZSTD_buildCTable for MatchLengths failed");
+            if (MLtype == set_compressed)
+                lastNCount = op;
+            op += countSize;
+            assert(op <= oend);
+    }   }
+
+    *seqHead = (BYTE)((LLtype<<6) + (Offtype<<4) + (MLtype<<2));
+
+    {   size_t const bitstreamSize = ZSTD_encodeSequences(
+                                        op, (size_t)(oend - op),
+                                        CTable_MatchLength, mlCodeTable,
+                                        CTable_OffsetBits, ofCodeTable,
+                                        CTable_LitLength, llCodeTable,
+                                        sequences, nbSeq,
+                                        longOffsets, bmi2);
+        FORWARD_IF_ERROR(bitstreamSize, "ZSTD_encodeSequences failed");
+        op += bitstreamSize;
+        assert(op <= oend);
+        /* zstd versions <= 1.3.4 mistakenly report corruption when
+         * FSE_readNCount() receives a buffer < 4 bytes.
+         * Fixed by https://github.com/facebook/zstd/pull/1146.
+         * This can happen when the last set_compressed table present is 2
+         * bytes and the bitstream is only one byte.
+         * In this exceedingly rare case, we will simply emit an uncompressed
+         * block, since it isn't worth optimizing.
+         */
+        if (lastNCount && (op - lastNCount) < 4) {
+            /* NCountSize >= 2 && bitstreamSize > 0 ==> lastCountSize == 3 */
+            assert(op - lastNCount == 3);
+            DEBUGLOG(5, "Avoiding bug in zstd decoder in versions <= 1.3.4 by "
+                        "emitting an uncompressed block.");
+            return 0;
+        }
+    }
+
+    DEBUGLOG(5, "compressed block size : %u", (unsigned)(op - ostart));
+    return (size_t)(op - ostart);
+}
+
+MEM_STATIC size_t
+ZSTD_entropyCompressSequences(seqStore_t* seqStorePtr,
+                       const ZSTD_entropyCTables_t* prevEntropy,
+                             ZSTD_entropyCTables_t* nextEntropy,
+                       const ZSTD_CCtx_params* cctxParams,
+                             void* dst, size_t dstCapacity,
+                             size_t srcSize,
+                             void* entropyWorkspace, size_t entropyWkspSize,
+                             int bmi2)
+{
+    size_t const cSize = ZSTD_entropyCompressSequences_internal(
+                            seqStorePtr, prevEntropy, nextEntropy, cctxParams,
+                            dst, dstCapacity,
+                            entropyWorkspace, entropyWkspSize, bmi2);
+    if (cSize == 0) return 0;
+    /* When srcSize <= dstCapacity, there is enough space to write a raw uncompressed block.
+     * Since we ran out of space, block must be not compressible, so fall back to raw uncompressed block.
+     */
+    if ((cSize == ERROR(dstSize_tooSmall)) & (srcSize <= dstCapacity))
+        return 0;  /* block not compressed */
+    FORWARD_IF_ERROR(cSize, "ZSTD_entropyCompressSequences_internal failed");
+
+    /* Check compressibility */
+    {   size_t const maxCSize = srcSize - ZSTD_minGain(srcSize, cctxParams->cParams.strategy);
+        if (cSize >= maxCSize) return 0;  /* block not compressed */
+    }
+    DEBUGLOG(4, "ZSTD_entropyCompressSequences() cSize: %zu\n", cSize);
+    return cSize;
+}
+
+/* ZSTD_selectBlockCompressor() :
+ * Not static, but internal use only (used by long distance matcher)
+ * assumption : strat is a valid strategy */
+ZSTD_blockCompressor ZSTD_selectBlockCompressor(ZSTD_strategy strat, ZSTD_dictMode_e dictMode)
+{
+    static const ZSTD_blockCompressor blockCompressor[4][ZSTD_STRATEGY_MAX+1] = {
+        { ZSTD_compressBlock_fast  /* default for 0 */,
+          ZSTD_compressBlock_fast,
+          ZSTD_compressBlock_doubleFast,
+          ZSTD_compressBlock_greedy,
+          ZSTD_compressBlock_lazy,
+          ZSTD_compressBlock_lazy2,
+          ZSTD_compressBlock_btlazy2,
+          ZSTD_compressBlock_btopt,
+          ZSTD_compressBlock_btultra,
+          ZSTD_compressBlock_btultra2 },
+        { ZSTD_compressBlock_fast_extDict  /* default for 0 */,
+          ZSTD_compressBlock_fast_extDict,
+          ZSTD_compressBlock_doubleFast_extDict,
+          ZSTD_compressBlock_greedy_extDict,
+          ZSTD_compressBlock_lazy_extDict,
+          ZSTD_compressBlock_lazy2_extDict,
+          ZSTD_compressBlock_btlazy2_extDict,
+          ZSTD_compressBlock_btopt_extDict,
+          ZSTD_compressBlock_btultra_extDict,
+          ZSTD_compressBlock_btultra_extDict },
+        { ZSTD_compressBlock_fast_dictMatchState  /* default for 0 */,
+          ZSTD_compressBlock_fast_dictMatchState,
+          ZSTD_compressBlock_doubleFast_dictMatchState,
+          ZSTD_compressBlock_greedy_dictMatchState,
+          ZSTD_compressBlock_lazy_dictMatchState,
+          ZSTD_compressBlock_lazy2_dictMatchState,
+          ZSTD_compressBlock_btlazy2_dictMatchState,
+          ZSTD_compressBlock_btopt_dictMatchState,
+          ZSTD_compressBlock_btultra_dictMatchState,
+          ZSTD_compressBlock_btultra_dictMatchState },
+        { NULL  /* default for 0 */,
+          NULL,
+          NULL,
+          ZSTD_compressBlock_greedy_dedicatedDictSearch,
+          ZSTD_compressBlock_lazy_dedicatedDictSearch,
+          ZSTD_compressBlock_lazy2_dedicatedDictSearch,
+          NULL,
+          NULL,
+          NULL,
+          NULL }
+    };
+    ZSTD_blockCompressor selectedCompressor;
+    ZSTD_STATIC_ASSERT((unsigned)ZSTD_fast == 1);
+
+    assert(ZSTD_cParam_withinBounds(ZSTD_c_strategy, strat));
+    selectedCompressor = blockCompressor[(int)dictMode][(int)strat];
+    assert(selectedCompressor != NULL);
+    return selectedCompressor;
+}
+
+static void ZSTD_storeLastLiterals(seqStore_t* seqStorePtr,
+                                   const BYTE* anchor, size_t lastLLSize)
+{
+    ZSTD_memcpy(seqStorePtr->lit, anchor, lastLLSize);
+    seqStorePtr->lit += lastLLSize;
+}
+
+void ZSTD_resetSeqStore(seqStore_t* ssPtr)
+{
+    ssPtr->lit = ssPtr->litStart;
+    ssPtr->sequences = ssPtr->sequencesStart;
+    ssPtr->longLengthID = 0;
+}
+
+typedef enum { ZSTDbss_compress, ZSTDbss_noCompress } ZSTD_buildSeqStore_e;
+
+static size_t ZSTD_buildSeqStore(ZSTD_CCtx* zc, const void* src, size_t srcSize)
+{
+    ZSTD_matchState_t* const ms = &zc->blockState.matchState;
+    DEBUGLOG(5, "ZSTD_buildSeqStore (srcSize=%zu)", srcSize);
+    assert(srcSize <= ZSTD_BLOCKSIZE_MAX);
+    /* Assert that we have correctly flushed the ctx params into the ms's copy */
+    ZSTD_assertEqualCParams(zc->appliedParams.cParams, ms->cParams);
+    if (srcSize < MIN_CBLOCK_SIZE+ZSTD_blockHeaderSize+1) {
+        if (zc->appliedParams.cParams.strategy >= ZSTD_btopt) {
+            ZSTD_ldm_skipRawSeqStoreBytes(&zc->externSeqStore, srcSize);
+        } else {
+            ZSTD_ldm_skipSequences(&zc->externSeqStore, srcSize, zc->appliedParams.cParams.minMatch);
+        }
+        return ZSTDbss_noCompress; /* don't even attempt compression below a certain srcSize */
+    }
+    ZSTD_resetSeqStore(&(zc->seqStore));
+    /* required for optimal parser to read stats from dictionary */
+    ms->opt.symbolCosts = &zc->blockState.prevCBlock->entropy;
+    /* tell the optimal parser how we expect to compress literals */
+    ms->opt.literalCompressionMode = zc->appliedParams.literalCompressionMode;
+    /* a gap between an attached dict and the current window is not safe,
+     * they must remain adjacent,
+     * and when that stops being the case, the dict must be unset */
+    assert(ms->dictMatchState == NULL || ms->loadedDictEnd == ms->window.dictLimit);
+
+    /* limited update after a very long match */
+    {   const BYTE* const base = ms->window.base;
+        const BYTE* const istart = (const BYTE*)src;
+        const U32 curr = (U32)(istart-base);
+        if (sizeof(ptrdiff_t)==8) assert(istart - base < (ptrdiff_t)(U32)(-1));   /* ensure no overflow */
+        if (curr > ms->nextToUpdate + 384)
+            ms->nextToUpdate = curr - MIN(192, (U32)(curr - ms->nextToUpdate - 384));
+    }
+
+    /* select and store sequences */
+    {   ZSTD_dictMode_e const dictMode = ZSTD_matchState_dictMode(ms);
+        size_t lastLLSize;
+        {   int i;
+            for (i = 0; i < ZSTD_REP_NUM; ++i)
+                zc->blockState.nextCBlock->rep[i] = zc->blockState.prevCBlock->rep[i];
+        }
+        if (zc->externSeqStore.pos < zc->externSeqStore.size) {
+            assert(!zc->appliedParams.ldmParams.enableLdm);
+            /* Updates ldmSeqStore.pos */
+            lastLLSize =
+                ZSTD_ldm_blockCompress(&zc->externSeqStore,
+                                       ms, &zc->seqStore,
+                                       zc->blockState.nextCBlock->rep,
+                                       src, srcSize);
+            assert(zc->externSeqStore.pos <= zc->externSeqStore.size);
+        } else if (zc->appliedParams.ldmParams.enableLdm) {
+            rawSeqStore_t ldmSeqStore = kNullRawSeqStore;
+
+            ldmSeqStore.seq = zc->ldmSequences;
+            ldmSeqStore.capacity = zc->maxNbLdmSequences;
+            /* Updates ldmSeqStore.size */
+            FORWARD_IF_ERROR(ZSTD_ldm_generateSequences(&zc->ldmState, &ldmSeqStore,
+                                               &zc->appliedParams.ldmParams,
+                                               src, srcSize), "");
+            /* Updates ldmSeqStore.pos */
+            lastLLSize =
+                ZSTD_ldm_blockCompress(&ldmSeqStore,
+                                       ms, &zc->seqStore,
+                                       zc->blockState.nextCBlock->rep,
+                                       src, srcSize);
+            assert(ldmSeqStore.pos == ldmSeqStore.size);
+        } else {   /* not long range mode */
+            ZSTD_blockCompressor const blockCompressor = ZSTD_selectBlockCompressor(zc->appliedParams.cParams.strategy, dictMode);
+            ms->ldmSeqStore = NULL;
+            lastLLSize = blockCompressor(ms, &zc->seqStore, zc->blockState.nextCBlock->rep, src, srcSize);
+        }
+        {   const BYTE* const lastLiterals = (const BYTE*)src + srcSize - lastLLSize;
+            ZSTD_storeLastLiterals(&zc->seqStore, lastLiterals, lastLLSize);
+    }   }
+    return ZSTDbss_compress;
+}
+
+static void ZSTD_copyBlockSequences(ZSTD_CCtx* zc)
+{
+    const seqStore_t* seqStore = ZSTD_getSeqStore(zc);
+    const seqDef* seqStoreSeqs = seqStore->sequencesStart;
+    size_t seqStoreSeqSize = seqStore->sequences - seqStoreSeqs;
+    size_t seqStoreLiteralsSize = (size_t)(seqStore->lit - seqStore->litStart);
+    size_t literalsRead = 0;
+    size_t lastLLSize;
+
+    ZSTD_Sequence* outSeqs = &zc->seqCollector.seqStart[zc->seqCollector.seqIndex];
+    size_t i;
+    repcodes_t updatedRepcodes;
+
+    assert(zc->seqCollector.seqIndex + 1 < zc->seqCollector.maxSequences);
+    /* Ensure we have enough space for last literals "sequence" */
+    assert(zc->seqCollector.maxSequences >= seqStoreSeqSize + 1);
+    ZSTD_memcpy(updatedRepcodes.rep, zc->blockState.prevCBlock->rep, sizeof(repcodes_t));
+    for (i = 0; i < seqStoreSeqSize; ++i) {
+        U32 rawOffset = seqStoreSeqs[i].offset - ZSTD_REP_NUM;
+        outSeqs[i].litLength = seqStoreSeqs[i].litLength;
+        outSeqs[i].matchLength = seqStoreSeqs[i].matchLength + MINMATCH;
+        outSeqs[i].rep = 0;
+
+        if (i == seqStore->longLengthPos) {
+            if (seqStore->longLengthID == 1) {
+                outSeqs[i].litLength += 0x10000;
+            } else if (seqStore->longLengthID == 2) {
+                outSeqs[i].matchLength += 0x10000;
+            }
+        }
+
+        if (seqStoreSeqs[i].offset <= ZSTD_REP_NUM) {
+            /* Derive the correct offset corresponding to a repcode */
+            outSeqs[i].rep = seqStoreSeqs[i].offset;
+            if (outSeqs[i].litLength != 0) {
+                rawOffset = updatedRepcodes.rep[outSeqs[i].rep - 1];
+            } else {
+                if (outSeqs[i].rep == 3) {
+                    rawOffset = updatedRepcodes.rep[0] - 1;
+                } else {
+                    rawOffset = updatedRepcodes.rep[outSeqs[i].rep];
+                }
+            }
+        }
+        outSeqs[i].offset = rawOffset;
+        /* seqStoreSeqs[i].offset == offCode+1, and ZSTD_updateRep() expects offCode
+           so we provide seqStoreSeqs[i].offset - 1 */
+        updatedRepcodes = ZSTD_updateRep(updatedRepcodes.rep,
+                                         seqStoreSeqs[i].offset - 1,
+                                         seqStoreSeqs[i].litLength == 0);
+        literalsRead += outSeqs[i].litLength;
+    }
+    /* Insert last literals (if any exist) in the block as a sequence with ml == off == 0.
+     * If there are no last literals, then we'll emit (of: 0, ml: 0, ll: 0), which is a marker
+     * for the block boundary, according to the API.
+     */
+    assert(seqStoreLiteralsSize >= literalsRead);
+    lastLLSize = seqStoreLiteralsSize - literalsRead;
+    outSeqs[i].litLength = (U32)lastLLSize;
+    outSeqs[i].matchLength = outSeqs[i].offset = outSeqs[i].rep = 0;
+    seqStoreSeqSize++;
+    zc->seqCollector.seqIndex += seqStoreSeqSize;
+}
+
+size_t ZSTD_generateSequences(ZSTD_CCtx* zc, ZSTD_Sequence* outSeqs,
+                              size_t outSeqsSize, const void* src, size_t srcSize)
+{
+    const size_t dstCapacity = ZSTD_compressBound(srcSize);
+    void* dst = ZSTD_customMalloc(dstCapacity, ZSTD_defaultCMem);
+    SeqCollector seqCollector;
+
+    RETURN_ERROR_IF(dst == NULL, memory_allocation, "NULL pointer!");
+
+    seqCollector.collectSequences = 1;
+    seqCollector.seqStart = outSeqs;
+    seqCollector.seqIndex = 0;
+    seqCollector.maxSequences = outSeqsSize;
+    zc->seqCollector = seqCollector;
+
+    ZSTD_compress2(zc, dst, dstCapacity, src, srcSize);
+    ZSTD_customFree(dst, ZSTD_defaultCMem);
+    return zc->seqCollector.seqIndex;
+}
+
+size_t ZSTD_mergeBlockDelimiters(ZSTD_Sequence* sequences, size_t seqsSize) {
+    size_t in = 0;
+    size_t out = 0;
+    for (; in < seqsSize; ++in) {
+        if (sequences[in].offset == 0 && sequences[in].matchLength == 0) {
+            if (in != seqsSize - 1) {
+                sequences[in+1].litLength += sequences[in].litLength;
+            }
+        } else {
+            sequences[out] = sequences[in];
+            ++out;
+        }
+    }
+    return out;
+}
+
+/* Unrolled loop to read four size_ts of input at a time. Returns 1 if is RLE, 0 if not. */
+static int ZSTD_isRLE(const BYTE* src, size_t length) {
+    const BYTE* ip = src;
+    const BYTE value = ip[0];
+    const size_t valueST = (size_t)((U64)value * 0x0101010101010101ULL);
+    const size_t unrollSize = sizeof(size_t) * 4;
+    const size_t unrollMask = unrollSize - 1;
+    const size_t prefixLength = length & unrollMask;
+    size_t i;
+    size_t u;
+    if (length == 1) return 1;
+    /* Check if prefix is RLE first before using unrolled loop */
+    if (prefixLength && ZSTD_count(ip+1, ip, ip+prefixLength) != prefixLength-1) {
+        return 0;
+    }
+    for (i = prefixLength; i != length; i += unrollSize) {
+        for (u = 0; u < unrollSize; u += sizeof(size_t)) {
+            if (MEM_readST(ip + i + u) != valueST) {
+                return 0;
+            }
+        }
+    }
+    return 1;
+}
+
+/* Returns true if the given block may be RLE.
+ * This is just a heuristic based on the compressibility.
+ * It may return both false positives and false negatives.
+ */
+static int ZSTD_maybeRLE(seqStore_t const* seqStore)
+{
+    size_t const nbSeqs = (size_t)(seqStore->sequences - seqStore->sequencesStart);
+    size_t const nbLits = (size_t)(seqStore->lit - seqStore->litStart);
+
+    return nbSeqs < 4 && nbLits < 10;
+}
+
+static void ZSTD_confirmRepcodesAndEntropyTables(ZSTD_CCtx* zc)
+{
+    ZSTD_compressedBlockState_t* const tmp = zc->blockState.prevCBlock;
+    zc->blockState.prevCBlock = zc->blockState.nextCBlock;
+    zc->blockState.nextCBlock = tmp;
+}
+
+static size_t ZSTD_compressBlock_internal(ZSTD_CCtx* zc,
+                                        void* dst, size_t dstCapacity,
+                                        const void* src, size_t srcSize, U32 frame)
+{
+    /* This the upper bound for the length of an rle block.
+     * This isn't the actual upper bound. Finding the real threshold
+     * needs further investigation.
+     */
+    const U32 rleMaxLength = 25;
+    size_t cSize;
+    const BYTE* ip = (const BYTE*)src;
+    BYTE* op = (BYTE*)dst;
+    DEBUGLOG(5, "ZSTD_compressBlock_internal (dstCapacity=%u, dictLimit=%u, nextToUpdate=%u)",
+                (unsigned)dstCapacity, (unsigned)zc->blockState.matchState.window.dictLimit,
+                (unsigned)zc->blockState.matchState.nextToUpdate);
+
+    {   const size_t bss = ZSTD_buildSeqStore(zc, src, srcSize);
+        FORWARD_IF_ERROR(bss, "ZSTD_buildSeqStore failed");
+        if (bss == ZSTDbss_noCompress) { cSize = 0; goto out; }
+    }
+
+    if (zc->seqCollector.collectSequences) {
+        ZSTD_copyBlockSequences(zc);
+        ZSTD_confirmRepcodesAndEntropyTables(zc);
+        return 0;
+    }
+
+    /* encode sequences and literals */
+    cSize = ZSTD_entropyCompressSequences(&zc->seqStore,
+            &zc->blockState.prevCBlock->entropy, &zc->blockState.nextCBlock->entropy,
+            &zc->appliedParams,
+            dst, dstCapacity,
+            srcSize,
+            zc->entropyWorkspace, ENTROPY_WORKSPACE_SIZE /* statically allocated in resetCCtx */,
+            zc->bmi2);
+
+    if (zc->seqCollector.collectSequences) {
+        ZSTD_copyBlockSequences(zc);
+        return 0;
+    }
+
+
+    if (frame &&
+        /* We don't want to emit our first block as a RLE even if it qualifies because
+         * doing so will cause the decoder (cli only) to throw a "should consume all input error."
+         * This is only an issue for zstd <= v1.4.3
+         */
+        !zc->isFirstBlock &&
+        cSize < rleMaxLength &&
+        ZSTD_isRLE(ip, srcSize))
+    {
+        cSize = 1;
+        op[0] = ip[0];
+    }
+
+out:
+    if (!ZSTD_isError(cSize) && cSize > 1) {
+        ZSTD_confirmRepcodesAndEntropyTables(zc);
+    }
+    /* We check that dictionaries have offset codes available for the first
+     * block. After the first block, the offcode table might not have large
+     * enough codes to represent the offsets in the data.
+     */
+    if (zc->blockState.prevCBlock->entropy.fse.offcode_repeatMode == FSE_repeat_valid)
+        zc->blockState.prevCBlock->entropy.fse.offcode_repeatMode = FSE_repeat_check;
+
+    return cSize;
+}
+
+static size_t ZSTD_compressBlock_targetCBlockSize_body(ZSTD_CCtx* zc,
+                               void* dst, size_t dstCapacity,
+                               const void* src, size_t srcSize,
+                               const size_t bss, U32 lastBlock)
+{
+    DEBUGLOG(6, "Attempting ZSTD_compressSuperBlock()");
+    if (bss == ZSTDbss_compress) {
+        if (/* We don't want to emit our first block as a RLE even if it qualifies because
+            * doing so will cause the decoder (cli only) to throw a "should consume all input error."
+            * This is only an issue for zstd <= v1.4.3
+            */
+            !zc->isFirstBlock &&
+            ZSTD_maybeRLE(&zc->seqStore) &&
+            ZSTD_isRLE((BYTE const*)src, srcSize))
+        {
+            return ZSTD_rleCompressBlock(dst, dstCapacity, *(BYTE const*)src, srcSize, lastBlock);
+        }
+        /* Attempt superblock compression.
+         *
+         * Note that compressed size of ZSTD_compressSuperBlock() is not bound by the
+         * standard ZSTD_compressBound(). This is a problem, because even if we have
+         * space now, taking an extra byte now could cause us to run out of space later
+         * and violate ZSTD_compressBound().
+         *
+         * Define blockBound(blockSize) = blockSize + ZSTD_blockHeaderSize.
+         *
+         * In order to respect ZSTD_compressBound() we must attempt to emit a raw
+         * uncompressed block in these cases:
+         *   * cSize == 0: Return code for an uncompressed block.
+         *   * cSize == dstSize_tooSmall: We may have expanded beyond blockBound(srcSize).
+         *     ZSTD_noCompressBlock() will return dstSize_tooSmall if we are really out of
+         *     output space.
+         *   * cSize >= blockBound(srcSize): We have expanded the block too much so
+         *     emit an uncompressed block.
+         */
+        {
+            size_t const cSize = ZSTD_compressSuperBlock(zc, dst, dstCapacity, src, srcSize, lastBlock);
+            if (cSize != ERROR(dstSize_tooSmall)) {
+                size_t const maxCSize = srcSize - ZSTD_minGain(srcSize, zc->appliedParams.cParams.strategy);
+                FORWARD_IF_ERROR(cSize, "ZSTD_compressSuperBlock failed");
+                if (cSize != 0 && cSize < maxCSize + ZSTD_blockHeaderSize) {
+                    ZSTD_confirmRepcodesAndEntropyTables(zc);
+                    return cSize;
+                }
+            }
+        }
+    }
+
+    DEBUGLOG(6, "Resorting to ZSTD_noCompressBlock()");
+    /* Superblock compression failed, attempt to emit a single no compress block.
+     * The decoder will be able to stream this block since it is uncompressed.
+     */
+    return ZSTD_noCompressBlock(dst, dstCapacity, src, srcSize, lastBlock);
+}
+
+static size_t ZSTD_compressBlock_targetCBlockSize(ZSTD_CCtx* zc,
+                               void* dst, size_t dstCapacity,
+                               const void* src, size_t srcSize,
+                               U32 lastBlock)
+{
+    size_t cSize = 0;
+    const size_t bss = ZSTD_buildSeqStore(zc, src, srcSize);
+    DEBUGLOG(5, "ZSTD_compressBlock_targetCBlockSize (dstCapacity=%u, dictLimit=%u, nextToUpdate=%u, srcSize=%zu)",
+                (unsigned)dstCapacity, (unsigned)zc->blockState.matchState.window.dictLimit, (unsigned)zc->blockState.matchState.nextToUpdate, srcSize);
+    FORWARD_IF_ERROR(bss, "ZSTD_buildSeqStore failed");
+
+    cSize = ZSTD_compressBlock_targetCBlockSize_body(zc, dst, dstCapacity, src, srcSize, bss, lastBlock);
+    FORWARD_IF_ERROR(cSize, "ZSTD_compressBlock_targetCBlockSize_body failed");
+
+    if (zc->blockState.prevCBlock->entropy.fse.offcode_repeatMode == FSE_repeat_valid)
+        zc->blockState.prevCBlock->entropy.fse.offcode_repeatMode = FSE_repeat_check;
+
+    return cSize;
+}
+
+static void ZSTD_overflowCorrectIfNeeded(ZSTD_matchState_t* ms,
+                                         ZSTD_cwksp* ws,
+                                         ZSTD_CCtx_params const* params,
+                                         void const* ip,
+                                         void const* iend)
+{
+    if (ZSTD_window_needOverflowCorrection(ms->window, iend)) {
+        U32 const maxDist = (U32)1 << params->cParams.windowLog;
+        U32 const cycleLog = ZSTD_cycleLog(params->cParams.chainLog, params->cParams.strategy);
+        U32 const correction = ZSTD_window_correctOverflow(&ms->window, cycleLog, maxDist, ip);
+        ZSTD_STATIC_ASSERT(ZSTD_CHAINLOG_MAX <= 30);
+        ZSTD_STATIC_ASSERT(ZSTD_WINDOWLOG_MAX_32 <= 30);
+        ZSTD_STATIC_ASSERT(ZSTD_WINDOWLOG_MAX <= 31);
+        ZSTD_cwksp_mark_tables_dirty(ws);
+        ZSTD_reduceIndex(ms, params, correction);
+        ZSTD_cwksp_mark_tables_clean(ws);
+        if (ms->nextToUpdate < correction) ms->nextToUpdate = 0;
+        else ms->nextToUpdate -= correction;
+        /* invalidate dictionaries on overflow correction */
+        ms->loadedDictEnd = 0;
+        ms->dictMatchState = NULL;
+    }
+}
+
+/*! ZSTD_compress_frameChunk() :
+*   Compress a chunk of data into one or multiple blocks.
+*   All blocks will be terminated, all input will be consumed.
+*   Function will issue an error if there is not enough `dstCapacity` to hold the compressed content.
+*   Frame is supposed already started (header already produced)
+*   @return : compressed size, or an error code
+*/
+static size_t ZSTD_compress_frameChunk (ZSTD_CCtx* cctx,
+                                     void* dst, size_t dstCapacity,
+                               const void* src, size_t srcSize,
+                                     U32 lastFrameChunk)
+{
+    size_t blockSize = cctx->blockSize;
+    size_t remaining = srcSize;
+    const BYTE* ip = (const BYTE*)src;
+    BYTE* const ostart = (BYTE*)dst;
+    BYTE* op = ostart;
+    U32 const maxDist = (U32)1 << cctx->appliedParams.cParams.windowLog;
+
+    assert(cctx->appliedParams.cParams.windowLog <= ZSTD_WINDOWLOG_MAX);
+
+    DEBUGLOG(4, "ZSTD_compress_frameChunk (blockSize=%u)", (unsigned)blockSize);
+    if (cctx->appliedParams.fParams.checksumFlag && srcSize)
+        xxh64_update(&cctx->xxhState, src, srcSize);
+
+    while (remaining) {
+        ZSTD_matchState_t* const ms = &cctx->blockState.matchState;
+        U32 const lastBlock = lastFrameChunk & (blockSize >= remaining);
+
+        RETURN_ERROR_IF(dstCapacity < ZSTD_blockHeaderSize + MIN_CBLOCK_SIZE,
+                        dstSize_tooSmall,
+                        "not enough space to store compressed block");
+        if (remaining < blockSize) blockSize = remaining;
+
+        ZSTD_overflowCorrectIfNeeded(
+            ms, &cctx->workspace, &cctx->appliedParams, ip, ip + blockSize);
+        ZSTD_checkDictValidity(&ms->window, ip + blockSize, maxDist, &ms->loadedDictEnd, &ms->dictMatchState);
+
+        /* Ensure hash/chain table insertion resumes no sooner than lowlimit */
+        if (ms->nextToUpdate < ms->window.lowLimit) ms->nextToUpdate = ms->window.lowLimit;
+
+        {   size_t cSize;
+            if (ZSTD_useTargetCBlockSize(&cctx->appliedParams)) {
+                cSize = ZSTD_compressBlock_targetCBlockSize(cctx, op, dstCapacity, ip, blockSize, lastBlock);
+                FORWARD_IF_ERROR(cSize, "ZSTD_compressBlock_targetCBlockSize failed");
+                assert(cSize > 0);
+                assert(cSize <= blockSize + ZSTD_blockHeaderSize);
+            } else {
+                cSize = ZSTD_compressBlock_internal(cctx,
+                                        op+ZSTD_blockHeaderSize, dstCapacity-ZSTD_blockHeaderSize,
+                                        ip, blockSize, 1 /* frame */);
+                FORWARD_IF_ERROR(cSize, "ZSTD_compressBlock_internal failed");
+
+                if (cSize == 0) {  /* block is not compressible */
+                    cSize = ZSTD_noCompressBlock(op, dstCapacity, ip, blockSize, lastBlock);
+                    FORWARD_IF_ERROR(cSize, "ZSTD_noCompressBlock failed");
+                } else {
+                    U32 const cBlockHeader = cSize == 1 ?
+                        lastBlock + (((U32)bt_rle)<<1) + (U32)(blockSize << 3) :
+                        lastBlock + (((U32)bt_compressed)<<1) + (U32)(cSize << 3);
+                    MEM_writeLE24(op, cBlockHeader);
+                    cSize += ZSTD_blockHeaderSize;
+                }
+            }
+
+
+            ip += blockSize;
+            assert(remaining >= blockSize);
+            remaining -= blockSize;
+            op += cSize;
+            assert(dstCapacity >= cSize);
+            dstCapacity -= cSize;
+            cctx->isFirstBlock = 0;
+            DEBUGLOG(5, "ZSTD_compress_frameChunk: adding a block of size %u",
+                        (unsigned)cSize);
+    }   }
+
+    if (lastFrameChunk && (op>ostart)) cctx->stage = ZSTDcs_ending;
+    return (size_t)(op-ostart);
+}
+
+
+static size_t ZSTD_writeFrameHeader(void* dst, size_t dstCapacity,
+                                    const ZSTD_CCtx_params* params, U64 pledgedSrcSize, U32 dictID)
+{   BYTE* const op = (BYTE*)dst;
+    U32   const dictIDSizeCodeLength = (dictID>0) + (dictID>=256) + (dictID>=65536);   /* 0-3 */
+    U32   const dictIDSizeCode = params->fParams.noDictIDFlag ? 0 : dictIDSizeCodeLength;   /* 0-3 */
+    U32   const checksumFlag = params->fParams.checksumFlag>0;
+    U32   const windowSize = (U32)1 << params->cParams.windowLog;
+    U32   const singleSegment = params->fParams.contentSizeFlag && (windowSize >= pledgedSrcSize);
+    BYTE  const windowLogByte = (BYTE)((params->cParams.windowLog - ZSTD_WINDOWLOG_ABSOLUTEMIN) << 3);
+    U32   const fcsCode = params->fParams.contentSizeFlag ?
+                     (pledgedSrcSize>=256) + (pledgedSrcSize>=65536+256) + (pledgedSrcSize>=0xFFFFFFFFU) : 0;  /* 0-3 */
+    BYTE  const frameHeaderDescriptionByte = (BYTE)(dictIDSizeCode + (checksumFlag<<2) + (singleSegment<<5) + (fcsCode<<6) );
+    size_t pos=0;
+
+    assert(!(params->fParams.contentSizeFlag && pledgedSrcSize == ZSTD_CONTENTSIZE_UNKNOWN));
+    RETURN_ERROR_IF(dstCapacity < ZSTD_FRAMEHEADERSIZE_MAX, dstSize_tooSmall,
+                    "dst buf is too small to fit worst-case frame header size.");
+    DEBUGLOG(4, "ZSTD_writeFrameHeader : dictIDFlag : %u ; dictID : %u ; dictIDSizeCode : %u",
+                !params->fParams.noDictIDFlag, (unsigned)dictID, (unsigned)dictIDSizeCode);
+    if (params->format == ZSTD_f_zstd1) {
+        MEM_writeLE32(dst, ZSTD_MAGICNUMBER);
+        pos = 4;
+    }
+    op[pos++] = frameHeaderDescriptionByte;
+    if (!singleSegment) op[pos++] = windowLogByte;
+    switch(dictIDSizeCode)
+    {
+        default:
+            assert(0); /* impossible */
+            ZSTD_FALLTHROUGH;
+        case 0 : break;
+        case 1 : op[pos] = (BYTE)(dictID); pos++; break;
+        case 2 : MEM_writeLE16(op+pos, (U16)dictID); pos+=2; break;
+        case 3 : MEM_writeLE32(op+pos, dictID); pos+=4; break;
+    }
+    switch(fcsCode)
+    {
+        default:
+            assert(0); /* impossible */
+            ZSTD_FALLTHROUGH;
+        case 0 : if (singleSegment) op[pos++] = (BYTE)(pledgedSrcSize); break;
+        case 1 : MEM_writeLE16(op+pos, (U16)(pledgedSrcSize-256)); pos+=2; break;
+        case 2 : MEM_writeLE32(op+pos, (U32)(pledgedSrcSize)); pos+=4; break;
+        case 3 : MEM_writeLE64(op+pos, (U64)(pledgedSrcSize)); pos+=8; break;
+    }
+    return pos;
+}
+
+/* ZSTD_writeSkippableFrame_advanced() :
+ * Writes out a skippable frame with the specified magic number variant (16 are supported),
+ * from ZSTD_MAGIC_SKIPPABLE_START to ZSTD_MAGIC_SKIPPABLE_START+15, and the desired source data.
+ *
+ * Returns the total number of bytes written, or a ZSTD error code.
+ */
+size_t ZSTD_writeSkippableFrame(void* dst, size_t dstCapacity,
+                                const void* src, size_t srcSize, unsigned magicVariant) {
+    BYTE* op = (BYTE*)dst;
+    RETURN_ERROR_IF(dstCapacity < srcSize + ZSTD_SKIPPABLEHEADERSIZE /* Skippable frame overhead */,
+                    dstSize_tooSmall, "Not enough room for skippable frame");
+    RETURN_ERROR_IF(srcSize > (unsigned)0xFFFFFFFF, srcSize_wrong, "Src size too large for skippable frame");
+    RETURN_ERROR_IF(magicVariant > 15, parameter_outOfBound, "Skippable frame magic number variant not supported");
+
+    MEM_writeLE32(op, (U32)(ZSTD_MAGIC_SKIPPABLE_START + magicVariant));
+    MEM_writeLE32(op+4, (U32)srcSize);
+    ZSTD_memcpy(op+8, src, srcSize);
+    return srcSize + ZSTD_SKIPPABLEHEADERSIZE;
+}
+
+/* ZSTD_writeLastEmptyBlock() :
+ * output an empty Block with end-of-frame mark to complete a frame
+ * @return : size of data written into `dst` (== ZSTD_blockHeaderSize (defined in zstd_internal.h))
+ *           or an error code if `dstCapacity` is too small (<ZSTD_blockHeaderSize)
+ */
+size_t ZSTD_writeLastEmptyBlock(void* dst, size_t dstCapacity)
+{
+    RETURN_ERROR_IF(dstCapacity < ZSTD_blockHeaderSize, dstSize_tooSmall,
+                    "dst buf is too small to write frame trailer empty block.");
+    {   U32 const cBlockHeader24 = 1 /*lastBlock*/ + (((U32)bt_raw)<<1);  /* 0 size */
+        MEM_writeLE24(dst, cBlockHeader24);
+        return ZSTD_blockHeaderSize;
+    }
+}
+
+size_t ZSTD_referenceExternalSequences(ZSTD_CCtx* cctx, rawSeq* seq, size_t nbSeq)
+{
+    RETURN_ERROR_IF(cctx->stage != ZSTDcs_init, stage_wrong,
+                    "wrong cctx stage");
+    RETURN_ERROR_IF(cctx->appliedParams.ldmParams.enableLdm,
+                    parameter_unsupported,
+                    "incompatible with ldm");
+    cctx->externSeqStore.seq = seq;
+    cctx->externSeqStore.size = nbSeq;
+    cctx->externSeqStore.capacity = nbSeq;
+    cctx->externSeqStore.pos = 0;
+    cctx->externSeqStore.posInSequence = 0;
+    return 0;
+}
+
+
+static size_t ZSTD_compressContinue_internal (ZSTD_CCtx* cctx,
+                              void* dst, size_t dstCapacity,
+                        const void* src, size_t srcSize,
+                               U32 frame, U32 lastFrameChunk)
+{
+    ZSTD_matchState_t* const ms = &cctx->blockState.matchState;
+    size_t fhSize = 0;
+
+    DEBUGLOG(5, "ZSTD_compressContinue_internal, stage: %u, srcSize: %u",
+                cctx->stage, (unsigned)srcSize);
+    RETURN_ERROR_IF(cctx->stage==ZSTDcs_created, stage_wrong,
+                    "missing init (ZSTD_compressBegin)");
+
+    if (frame && (cctx->stage==ZSTDcs_init)) {
+        fhSize = ZSTD_writeFrameHeader(dst, dstCapacity, &cctx->appliedParams,
+                                       cctx->pledgedSrcSizePlusOne-1, cctx->dictID);
+        FORWARD_IF_ERROR(fhSize, "ZSTD_writeFrameHeader failed");
+        assert(fhSize <= dstCapacity);
+        dstCapacity -= fhSize;
+        dst = (char*)dst + fhSize;
+        cctx->stage = ZSTDcs_ongoing;
+    }
+
+    if (!srcSize) return fhSize;  /* do not generate an empty block if no input */
+
+    if (!ZSTD_window_update(&ms->window, src, srcSize)) {
+        ms->nextToUpdate = ms->window.dictLimit;
+    }
+    if (cctx->appliedParams.ldmParams.enableLdm) {
+        ZSTD_window_update(&cctx->ldmState.window, src, srcSize);
+    }
+
+    if (!frame) {
+        /* overflow check and correction for block mode */
+        ZSTD_overflowCorrectIfNeeded(
+            ms, &cctx->workspace, &cctx->appliedParams,
+            src, (BYTE const*)src + srcSize);
+    }
+
+    DEBUGLOG(5, "ZSTD_compressContinue_internal (blockSize=%u)", (unsigned)cctx->blockSize);
+    {   size_t const cSize = frame ?
+                             ZSTD_compress_frameChunk (cctx, dst, dstCapacity, src, srcSize, lastFrameChunk) :
+                             ZSTD_compressBlock_internal (cctx, dst, dstCapacity, src, srcSize, 0 /* frame */);
+        FORWARD_IF_ERROR(cSize, "%s", frame ? "ZSTD_compress_frameChunk failed" : "ZSTD_compressBlock_internal failed");
+        cctx->consumedSrcSize += srcSize;
+        cctx->producedCSize += (cSize + fhSize);
+        assert(!(cctx->appliedParams.fParams.contentSizeFlag && cctx->pledgedSrcSizePlusOne == 0));
+        if (cctx->pledgedSrcSizePlusOne != 0) {  /* control src size */
+            ZSTD_STATIC_ASSERT(ZSTD_CONTENTSIZE_UNKNOWN == (unsigned long long)-1);
+            RETURN_ERROR_IF(
+                cctx->consumedSrcSize+1 > cctx->pledgedSrcSizePlusOne,
+                srcSize_wrong,
+                "error : pledgedSrcSize = %u, while realSrcSize >= %u",
+                (unsigned)cctx->pledgedSrcSizePlusOne-1,
+                (unsigned)cctx->consumedSrcSize);
+        }
+        return cSize + fhSize;
+    }
+}
+
+size_t ZSTD_compressContinue (ZSTD_CCtx* cctx,
+                              void* dst, size_t dstCapacity,
+                        const void* src, size_t srcSize)
+{
+    DEBUGLOG(5, "ZSTD_compressContinue (srcSize=%u)", (unsigned)srcSize);
+    return ZSTD_compressContinue_internal(cctx, dst, dstCapacity, src, srcSize, 1 /* frame mode */, 0 /* last chunk */);
+}
+
+
+size_t ZSTD_getBlockSize(const ZSTD_CCtx* cctx)
+{
+    ZSTD_compressionParameters const cParams = cctx->appliedParams.cParams;
+    assert(!ZSTD_checkCParams(cParams));
+    return MIN (ZSTD_BLOCKSIZE_MAX, (U32)1 << cParams.windowLog);
+}
+
+size_t ZSTD_compressBlock(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize)
+{
+    DEBUGLOG(5, "ZSTD_compressBlock: srcSize = %u", (unsigned)srcSize);
+    { size_t const blockSizeMax = ZSTD_getBlockSize(cctx);
+      RETURN_ERROR_IF(srcSize > blockSizeMax, srcSize_wrong, "input is larger than a block"); }
+
+    return ZSTD_compressContinue_internal(cctx, dst, dstCapacity, src, srcSize, 0 /* frame mode */, 0 /* last chunk */);
+}
+
+/*! ZSTD_loadDictionaryContent() :
+ *  @return : 0, or an error code
+ */
+static size_t ZSTD_loadDictionaryContent(ZSTD_matchState_t* ms,
+                                         ldmState_t* ls,
+                                         ZSTD_cwksp* ws,
+                                         ZSTD_CCtx_params const* params,
+                                         const void* src, size_t srcSize,
+                                         ZSTD_dictTableLoadMethod_e dtlm)
+{
+    const BYTE* ip = (const BYTE*) src;
+    const BYTE* const iend = ip + srcSize;
+
+    ZSTD_window_update(&ms->window, src, srcSize);
+    ms->loadedDictEnd = params->forceWindow ? 0 : (U32)(iend - ms->window.base);
+
+    if (params->ldmParams.enableLdm && ls != NULL) {
+        ZSTD_window_update(&ls->window, src, srcSize);
+        ls->loadedDictEnd = params->forceWindow ? 0 : (U32)(iend - ls->window.base);
+    }
+
+    /* Assert that we the ms params match the params we're being given */
+    ZSTD_assertEqualCParams(params->cParams, ms->cParams);
+
+    if (srcSize <= HASH_READ_SIZE) return 0;
+
+    while (iend - ip > HASH_READ_SIZE) {
+        size_t const remaining = (size_t)(iend - ip);
+        size_t const chunk = MIN(remaining, ZSTD_CHUNKSIZE_MAX);
+        const BYTE* const ichunk = ip + chunk;
+
+        ZSTD_overflowCorrectIfNeeded(ms, ws, params, ip, ichunk);
+
+        if (params->ldmParams.enableLdm && ls != NULL)
+            ZSTD_ldm_fillHashTable(ls, (const BYTE*)src, (const BYTE*)src + srcSize, &params->ldmParams);
+
+        switch(params->cParams.strategy)
+        {
+        case ZSTD_fast:
+            ZSTD_fillHashTable(ms, ichunk, dtlm);
+            break;
+        case ZSTD_dfast:
+            ZSTD_fillDoubleHashTable(ms, ichunk, dtlm);
+            break;
+
+        case ZSTD_greedy:
+        case ZSTD_lazy:
+        case ZSTD_lazy2:
+            if (chunk >= HASH_READ_SIZE && ms->dedicatedDictSearch) {
+                assert(chunk == remaining); /* must load everything in one go */
+                ZSTD_dedicatedDictSearch_lazy_loadDictionary(ms, ichunk-HASH_READ_SIZE);
+            } else if (chunk >= HASH_READ_SIZE) {
+                ZSTD_insertAndFindFirstIndex(ms, ichunk-HASH_READ_SIZE);
+            }
+            break;
+
+        case ZSTD_btlazy2:   /* we want the dictionary table fully sorted */
+        case ZSTD_btopt:
+        case ZSTD_btultra:
+        case ZSTD_btultra2:
+            if (chunk >= HASH_READ_SIZE)
+                ZSTD_updateTree(ms, ichunk-HASH_READ_SIZE, ichunk);
+            break;
+
+        default:
+            assert(0);  /* not possible : not a valid strategy id */
+        }
+
+        ip = ichunk;
+    }
+
+    ms->nextToUpdate = (U32)(iend - ms->window.base);
+    return 0;
+}
+
+
+/* Dictionaries that assign zero probability to symbols that show up causes problems
+ * when FSE encoding. Mark dictionaries with zero probability symbols as FSE_repeat_check
+ * and only dictionaries with 100% valid symbols can be assumed valid.
+ */
+static FSE_repeat ZSTD_dictNCountRepeat(short* normalizedCounter, unsigned dictMaxSymbolValue, unsigned maxSymbolValue)
+{
+    U32 s;
+    if (dictMaxSymbolValue < maxSymbolValue) {
+        return FSE_repeat_check;
+    }
+    for (s = 0; s <= maxSymbolValue; ++s) {
+        if (normalizedCounter[s] == 0) {
+            return FSE_repeat_check;
+        }
+    }
+    return FSE_repeat_valid;
+}
+
+size_t ZSTD_loadCEntropy(ZSTD_compressedBlockState_t* bs, void* workspace,
+                         const void* const dict, size_t dictSize)
+{
+    short offcodeNCount[MaxOff+1];
+    unsigned offcodeMaxValue = MaxOff;
+    const BYTE* dictPtr = (const BYTE*)dict;    /* skip magic num and dict ID */
+    const BYTE* const dictEnd = dictPtr + dictSize;
+    dictPtr += 8;
+    bs->entropy.huf.repeatMode = HUF_repeat_check;
+
+    {   unsigned maxSymbolValue = 255;
+        unsigned hasZeroWeights = 1;
+        size_t const hufHeaderSize = HUF_readCTable((HUF_CElt*)bs->entropy.huf.CTable, &maxSymbolValue, dictPtr,
+            dictEnd-dictPtr, &hasZeroWeights);
+
+        /* We only set the loaded table as valid if it contains all non-zero
+         * weights. Otherwise, we set it to check */
+        if (!hasZeroWeights)
+            bs->entropy.huf.repeatMode = HUF_repeat_valid;
+
+        RETURN_ERROR_IF(HUF_isError(hufHeaderSize), dictionary_corrupted, "");
+        RETURN_ERROR_IF(maxSymbolValue < 255, dictionary_corrupted, "");
+        dictPtr += hufHeaderSize;
+    }
+
+    {   unsigned offcodeLog;
+        size_t const offcodeHeaderSize = FSE_readNCount(offcodeNCount, &offcodeMaxValue, &offcodeLog, dictPtr, dictEnd-dictPtr);
+        RETURN_ERROR_IF(FSE_isError(offcodeHeaderSize), dictionary_corrupted, "");
+        RETURN_ERROR_IF(offcodeLog > OffFSELog, dictionary_corrupted, "");
+        /* fill all offset symbols to avoid garbage at end of table */
+        RETURN_ERROR_IF(FSE_isError(FSE_buildCTable_wksp(
+                bs->entropy.fse.offcodeCTable,
+                offcodeNCount, MaxOff, offcodeLog,
+                workspace, HUF_WORKSPACE_SIZE)),
+            dictionary_corrupted, "");
+        /* Defer checking offcodeMaxValue because we need to know the size of the dictionary content */
+        dictPtr += offcodeHeaderSize;
+    }
+
+    {   short matchlengthNCount[MaxML+1];
+        unsigned matchlengthMaxValue = MaxML, matchlengthLog;
+        size_t const matchlengthHeaderSize = FSE_readNCount(matchlengthNCount, &matchlengthMaxValue, &matchlengthLog, dictPtr, dictEnd-dictPtr);
+        RETURN_ERROR_IF(FSE_isError(matchlengthHeaderSize), dictionary_corrupted, "");
+        RETURN_ERROR_IF(matchlengthLog > MLFSELog, dictionary_corrupted, "");
+        RETURN_ERROR_IF(FSE_isError(FSE_buildCTable_wksp(
+                bs->entropy.fse.matchlengthCTable,
+                matchlengthNCount, matchlengthMaxValue, matchlengthLog,
+                workspace, HUF_WORKSPACE_SIZE)),
+            dictionary_corrupted, "");
+        bs->entropy.fse.matchlength_repeatMode = ZSTD_dictNCountRepeat(matchlengthNCount, matchlengthMaxValue, MaxML);
+        dictPtr += matchlengthHeaderSize;
+    }
+
+    {   short litlengthNCount[MaxLL+1];
+        unsigned litlengthMaxValue = MaxLL, litlengthLog;
+        size_t const litlengthHeaderSize = FSE_readNCount(litlengthNCount, &litlengthMaxValue, &litlengthLog, dictPtr, dictEnd-dictPtr);
+        RETURN_ERROR_IF(FSE_isError(litlengthHeaderSize), dictionary_corrupted, "");
+        RETURN_ERROR_IF(litlengthLog > LLFSELog, dictionary_corrupted, "");
+        RETURN_ERROR_IF(FSE_isError(FSE_buildCTable_wksp(
+                bs->entropy.fse.litlengthCTable,
+                litlengthNCount, litlengthMaxValue, litlengthLog,
+                workspace, HUF_WORKSPACE_SIZE)),
+            dictionary_corrupted, "");
+        bs->entropy.fse.litlength_repeatMode = ZSTD_dictNCountRepeat(litlengthNCount, litlengthMaxValue, MaxLL);
+        dictPtr += litlengthHeaderSize;
+    }
+
+    RETURN_ERROR_IF(dictPtr+12 > dictEnd, dictionary_corrupted, "");
+    bs->rep[0] = MEM_readLE32(dictPtr+0);
+    bs->rep[1] = MEM_readLE32(dictPtr+4);
+    bs->rep[2] = MEM_readLE32(dictPtr+8);
+    dictPtr += 12;
+
+    {   size_t const dictContentSize = (size_t)(dictEnd - dictPtr);
+        U32 offcodeMax = MaxOff;
+        if (dictContentSize <= ((U32)-1) - 128 KB) {
+            U32 const maxOffset = (U32)dictContentSize + 128 KB; /* The maximum offset that must be supported */
+            offcodeMax = ZSTD_highbit32(maxOffset); /* Calculate minimum offset code required to represent maxOffset */
+        }
+        /* All offset values <= dictContentSize + 128 KB must be representable for a valid table */
+        bs->entropy.fse.offcode_repeatMode = ZSTD_dictNCountRepeat(offcodeNCount, offcodeMaxValue, MIN(offcodeMax, MaxOff));
+
+        /* All repCodes must be <= dictContentSize and != 0 */
+        {   U32 u;
+            for (u=0; u<3; u++) {
+                RETURN_ERROR_IF(bs->rep[u] == 0, dictionary_corrupted, "");
+                RETURN_ERROR_IF(bs->rep[u] > dictContentSize, dictionary_corrupted, "");
+    }   }   }
+
+    return dictPtr - (const BYTE*)dict;
+}
+
+/* Dictionary format :
+ * See :
+ * https://github.com/facebook/zstd/blob/release/doc/zstd_compression_format.md#dictionary-format
+ */
+/*! ZSTD_loadZstdDictionary() :
+ * @return : dictID, or an error code
+ *  assumptions : magic number supposed already checked
+ *                dictSize supposed >= 8
+ */
+static size_t ZSTD_loadZstdDictionary(ZSTD_compressedBlockState_t* bs,
+                                      ZSTD_matchState_t* ms,
+                                      ZSTD_cwksp* ws,
+                                      ZSTD_CCtx_params const* params,
+                                      const void* dict, size_t dictSize,
+                                      ZSTD_dictTableLoadMethod_e dtlm,
+                                      void* workspace)
+{
+    const BYTE* dictPtr = (const BYTE*)dict;
+    const BYTE* const dictEnd = dictPtr + dictSize;
+    size_t dictID;
+    size_t eSize;
+
+    ZSTD_STATIC_ASSERT(HUF_WORKSPACE_SIZE >= (1<<MAX(MLFSELog,LLFSELog)));
+    assert(dictSize >= 8);
+    assert(MEM_readLE32(dictPtr) == ZSTD_MAGIC_DICTIONARY);
+
+    dictID = params->fParams.noDictIDFlag ? 0 :  MEM_readLE32(dictPtr + 4 /* skip magic number */ );
+    eSize = ZSTD_loadCEntropy(bs, workspace, dict, dictSize);
+    FORWARD_IF_ERROR(eSize, "ZSTD_loadCEntropy failed");
+    dictPtr += eSize;
+
+    {
+        size_t const dictContentSize = (size_t)(dictEnd - dictPtr);
+        FORWARD_IF_ERROR(ZSTD_loadDictionaryContent(
+            ms, NULL, ws, params, dictPtr, dictContentSize, dtlm), "");
+    }
+    return dictID;
+}
+
+/* ZSTD_compress_insertDictionary() :
+*   @return : dictID, or an error code */
+static size_t
+ZSTD_compress_insertDictionary(ZSTD_compressedBlockState_t* bs,
+                               ZSTD_matchState_t* ms,
+                               ldmState_t* ls,
+                               ZSTD_cwksp* ws,
+                         const ZSTD_CCtx_params* params,
+                         const void* dict, size_t dictSize,
+                               ZSTD_dictContentType_e dictContentType,
+                               ZSTD_dictTableLoadMethod_e dtlm,
+                               void* workspace)
+{
+    DEBUGLOG(4, "ZSTD_compress_insertDictionary (dictSize=%u)", (U32)dictSize);
+    if ((dict==NULL) || (dictSize<8)) {
+        RETURN_ERROR_IF(dictContentType == ZSTD_dct_fullDict, dictionary_wrong, "");
+        return 0;
+    }
+
+    ZSTD_reset_compressedBlockState(bs);
+
+    /* dict restricted modes */
+    if (dictContentType == ZSTD_dct_rawContent)
+        return ZSTD_loadDictionaryContent(ms, ls, ws, params, dict, dictSize, dtlm);
+
+    if (MEM_readLE32(dict) != ZSTD_MAGIC_DICTIONARY) {
+        if (dictContentType == ZSTD_dct_auto) {
+            DEBUGLOG(4, "raw content dictionary detected");
+            return ZSTD_loadDictionaryContent(
+                ms, ls, ws, params, dict, dictSize, dtlm);
+        }
+        RETURN_ERROR_IF(dictContentType == ZSTD_dct_fullDict, dictionary_wrong, "");
+        assert(0);   /* impossible */
+    }
+
+    /* dict as full zstd dictionary */
+    return ZSTD_loadZstdDictionary(
+        bs, ms, ws, params, dict, dictSize, dtlm, workspace);
+}
+
+#define ZSTD_USE_CDICT_PARAMS_SRCSIZE_CUTOFF (128 KB)
+#define ZSTD_USE_CDICT_PARAMS_DICTSIZE_MULTIPLIER (6ULL)
+
+/*! ZSTD_compressBegin_internal() :
+ * @return : 0, or an error code */
+static size_t ZSTD_compressBegin_internal(ZSTD_CCtx* cctx,
+                                    const void* dict, size_t dictSize,
+                                    ZSTD_dictContentType_e dictContentType,
+                                    ZSTD_dictTableLoadMethod_e dtlm,
+                                    const ZSTD_CDict* cdict,
+                                    const ZSTD_CCtx_params* params, U64 pledgedSrcSize,
+                                    ZSTD_buffered_policy_e zbuff)
+{
+    DEBUGLOG(4, "ZSTD_compressBegin_internal: wlog=%u", params->cParams.windowLog);
+    /* params are supposed to be fully validated at this point */
+    assert(!ZSTD_isError(ZSTD_checkCParams(params->cParams)));
+    assert(!((dict) && (cdict)));  /* either dict or cdict, not both */
+    if ( (cdict)
+      && (cdict->dictContentSize > 0)
+      && ( pledgedSrcSize < ZSTD_USE_CDICT_PARAMS_SRCSIZE_CUTOFF
+        || pledgedSrcSize < cdict->dictContentSize * ZSTD_USE_CDICT_PARAMS_DICTSIZE_MULTIPLIER
+        || pledgedSrcSize == ZSTD_CONTENTSIZE_UNKNOWN
+        || cdict->compressionLevel == 0)
+      && (params->attachDictPref != ZSTD_dictForceLoad) ) {
+        return ZSTD_resetCCtx_usingCDict(cctx, cdict, params, pledgedSrcSize, zbuff);
+    }
+
+    FORWARD_IF_ERROR( ZSTD_resetCCtx_internal(cctx, *params, pledgedSrcSize,
+                                     ZSTDcrp_makeClean, zbuff) , "");
+    {   size_t const dictID = cdict ?
+                ZSTD_compress_insertDictionary(
+                        cctx->blockState.prevCBlock, &cctx->blockState.matchState,
+                        &cctx->ldmState, &cctx->workspace, &cctx->appliedParams, cdict->dictContent,
+                        cdict->dictContentSize, cdict->dictContentType, dtlm,
+                        cctx->entropyWorkspace)
+              : ZSTD_compress_insertDictionary(
+                        cctx->blockState.prevCBlock, &cctx->blockState.matchState,
+                        &cctx->ldmState, &cctx->workspace, &cctx->appliedParams, dict, dictSize,
+                        dictContentType, dtlm, cctx->entropyWorkspace);
+        FORWARD_IF_ERROR(dictID, "ZSTD_compress_insertDictionary failed");
+        assert(dictID <= UINT_MAX);
+        cctx->dictID = (U32)dictID;
+        cctx->dictContentSize = cdict ? cdict->dictContentSize : dictSize;
+    }
+    return 0;
+}
+
+size_t ZSTD_compressBegin_advanced_internal(ZSTD_CCtx* cctx,
+                                    const void* dict, size_t dictSize,
+                                    ZSTD_dictContentType_e dictContentType,
+                                    ZSTD_dictTableLoadMethod_e dtlm,
+                                    const ZSTD_CDict* cdict,
+                                    const ZSTD_CCtx_params* params,
+                                    unsigned long long pledgedSrcSize)
+{
+    DEBUGLOG(4, "ZSTD_compressBegin_advanced_internal: wlog=%u", params->cParams.windowLog);
+    /* compression parameters verification and optimization */
+    FORWARD_IF_ERROR( ZSTD_checkCParams(params->cParams) , "");
+    return ZSTD_compressBegin_internal(cctx,
+                                       dict, dictSize, dictContentType, dtlm,
+                                       cdict,
+                                       params, pledgedSrcSize,
+                                       ZSTDb_not_buffered);
+}
+
+/*! ZSTD_compressBegin_advanced() :
+*   @return : 0, or an error code */
+size_t ZSTD_compressBegin_advanced(ZSTD_CCtx* cctx,
+                             const void* dict, size_t dictSize,
+                                   ZSTD_parameters params, unsigned long long pledgedSrcSize)
+{
+    ZSTD_CCtx_params cctxParams;
+    ZSTD_CCtxParams_init_internal(&cctxParams, &params, ZSTD_NO_CLEVEL);
+    return ZSTD_compressBegin_advanced_internal(cctx,
+                                            dict, dictSize, ZSTD_dct_auto, ZSTD_dtlm_fast,
+                                            NULL /*cdict*/,
+                                            &cctxParams, pledgedSrcSize);
+}
+
+size_t ZSTD_compressBegin_usingDict(ZSTD_CCtx* cctx, const void* dict, size_t dictSize, int compressionLevel)
+{
+    ZSTD_CCtx_params cctxParams;
+    {
+        ZSTD_parameters const params = ZSTD_getParams_internal(compressionLevel, ZSTD_CONTENTSIZE_UNKNOWN, dictSize, ZSTD_cpm_noAttachDict);
+        ZSTD_CCtxParams_init_internal(&cctxParams, &params, (compressionLevel == 0) ? ZSTD_CLEVEL_DEFAULT : compressionLevel);
+    }
+    DEBUGLOG(4, "ZSTD_compressBegin_usingDict (dictSize=%u)", (unsigned)dictSize);
+    return ZSTD_compressBegin_internal(cctx, dict, dictSize, ZSTD_dct_auto, ZSTD_dtlm_fast, NULL,
+                                       &cctxParams, ZSTD_CONTENTSIZE_UNKNOWN, ZSTDb_not_buffered);
+}
+
+size_t ZSTD_compressBegin(ZSTD_CCtx* cctx, int compressionLevel)
+{
+    return ZSTD_compressBegin_usingDict(cctx, NULL, 0, compressionLevel);
+}
+
+
+/*! ZSTD_writeEpilogue() :
+*   Ends a frame.
+*   @return : nb of bytes written into dst (or an error code) */
+static size_t ZSTD_writeEpilogue(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity)
+{
+    BYTE* const ostart = (BYTE*)dst;
+    BYTE* op = ostart;
+    size_t fhSize = 0;
+
+    DEBUGLOG(4, "ZSTD_writeEpilogue");
+    RETURN_ERROR_IF(cctx->stage == ZSTDcs_created, stage_wrong, "init missing");
+
+    /* special case : empty frame */
+    if (cctx->stage == ZSTDcs_init) {
+        fhSize = ZSTD_writeFrameHeader(dst, dstCapacity, &cctx->appliedParams, 0, 0);
+        FORWARD_IF_ERROR(fhSize, "ZSTD_writeFrameHeader failed");
+        dstCapacity -= fhSize;
+        op += fhSize;
+        cctx->stage = ZSTDcs_ongoing;
+    }
+
+    if (cctx->stage != ZSTDcs_ending) {
+        /* write one last empty block, make it the "last" block */
+        U32 const cBlockHeader24 = 1 /* last block */ + (((U32)bt_raw)<<1) + 0;
+        RETURN_ERROR_IF(dstCapacity<4, dstSize_tooSmall, "no room for epilogue");
+        MEM_writeLE32(op, cBlockHeader24);
+        op += ZSTD_blockHeaderSize;
+        dstCapacity -= ZSTD_blockHeaderSize;
+    }
+
+    if (cctx->appliedParams.fParams.checksumFlag) {
+        U32 const checksum = (U32) xxh64_digest(&cctx->xxhState);
+        RETURN_ERROR_IF(dstCapacity<4, dstSize_tooSmall, "no room for checksum");
+        DEBUGLOG(4, "ZSTD_writeEpilogue: write checksum : %08X", (unsigned)checksum);
+        MEM_writeLE32(op, checksum);
+        op += 4;
+    }
+
+    cctx->stage = ZSTDcs_created;  /* return to "created but no init" status */
+    return op-ostart;
+}
+
+void ZSTD_CCtx_trace(ZSTD_CCtx* cctx, size_t extraCSize)
+{
+    (void)cctx;
+    (void)extraCSize;
+}
+
+size_t ZSTD_compressEnd (ZSTD_CCtx* cctx,
+                         void* dst, size_t dstCapacity,
+                   const void* src, size_t srcSize)
+{
+    size_t endResult;
+    size_t const cSize = ZSTD_compressContinue_internal(cctx,
+                                dst, dstCapacity, src, srcSize,
+                                1 /* frame mode */, 1 /* last chunk */);
+    FORWARD_IF_ERROR(cSize, "ZSTD_compressContinue_internal failed");
+    endResult = ZSTD_writeEpilogue(cctx, (char*)dst + cSize, dstCapacity-cSize);
+    FORWARD_IF_ERROR(endResult, "ZSTD_writeEpilogue failed");
+    assert(!(cctx->appliedParams.fParams.contentSizeFlag && cctx->pledgedSrcSizePlusOne == 0));
+    if (cctx->pledgedSrcSizePlusOne != 0) {  /* control src size */
+        ZSTD_STATIC_ASSERT(ZSTD_CONTENTSIZE_UNKNOWN == (unsigned long long)-1);
+        DEBUGLOG(4, "end of frame : controlling src size");
+        RETURN_ERROR_IF(
+            cctx->pledgedSrcSizePlusOne != cctx->consumedSrcSize+1,
+            srcSize_wrong,
+             "error : pledgedSrcSize = %u, while realSrcSize = %u",
+            (unsigned)cctx->pledgedSrcSizePlusOne-1,
+            (unsigned)cctx->consumedSrcSize);
+    }
+    ZSTD_CCtx_trace(cctx, endResult);
+    return cSize + endResult;
+}
+
+size_t ZSTD_compress_advanced (ZSTD_CCtx* cctx,
+                               void* dst, size_t dstCapacity,
+                         const void* src, size_t srcSize,
+                         const void* dict,size_t dictSize,
+                               ZSTD_parameters params)
+{
+    ZSTD_CCtx_params cctxParams;
+    DEBUGLOG(4, "ZSTD_compress_advanced");
+    FORWARD_IF_ERROR(ZSTD_checkCParams(params.cParams), "");
+    ZSTD_CCtxParams_init_internal(&cctxParams, &params, ZSTD_NO_CLEVEL);
+    return ZSTD_compress_advanced_internal(cctx,
+                                           dst, dstCapacity,
+                                           src, srcSize,
+                                           dict, dictSize,
+                                           &cctxParams);
+}
+
+/* Internal */
+size_t ZSTD_compress_advanced_internal(
+        ZSTD_CCtx* cctx,
+        void* dst, size_t dstCapacity,
+        const void* src, size_t srcSize,
+        const void* dict,size_t dictSize,
+        const ZSTD_CCtx_params* params)
+{
+    DEBUGLOG(4, "ZSTD_compress_advanced_internal (srcSize:%u)", (unsigned)srcSize);
+    FORWARD_IF_ERROR( ZSTD_compressBegin_internal(cctx,
+                         dict, dictSize, ZSTD_dct_auto, ZSTD_dtlm_fast, NULL,
+                         params, srcSize, ZSTDb_not_buffered) , "");
+    return ZSTD_compressEnd(cctx, dst, dstCapacity, src, srcSize);
+}
+
+size_t ZSTD_compress_usingDict(ZSTD_CCtx* cctx,
+                               void* dst, size_t dstCapacity,
+                         const void* src, size_t srcSize,
+                         const void* dict, size_t dictSize,
+                               int compressionLevel)
+{
+    ZSTD_CCtx_params cctxParams;
+    {
+        ZSTD_parameters const params = ZSTD_getParams_internal(compressionLevel, srcSize, dict ? dictSize : 0, ZSTD_cpm_noAttachDict);
+        assert(params.fParams.contentSizeFlag == 1);
+        ZSTD_CCtxParams_init_internal(&cctxParams, &params, (compressionLevel == 0) ? ZSTD_CLEVEL_DEFAULT: compressionLevel);
+    }
+    DEBUGLOG(4, "ZSTD_compress_usingDict (srcSize=%u)", (unsigned)srcSize);
+    return ZSTD_compress_advanced_internal(cctx, dst, dstCapacity, src, srcSize, dict, dictSize, &cctxParams);
+}
+
+size_t ZSTD_compressCCtx(ZSTD_CCtx* cctx,
+                         void* dst, size_t dstCapacity,
+                   const void* src, size_t srcSize,
+                         int compressionLevel)
+{
+    DEBUGLOG(4, "ZSTD_compressCCtx (srcSize=%u)", (unsigned)srcSize);
+    assert(cctx != NULL);
+    return ZSTD_compress_usingDict(cctx, dst, dstCapacity, src, srcSize, NULL, 0, compressionLevel);
+}
+
+size_t ZSTD_compress(void* dst, size_t dstCapacity,
+               const void* src, size_t srcSize,
+                     int compressionLevel)
+{
+    size_t result;
+    ZSTD_CCtx* cctx = ZSTD_createCCtx();
+    RETURN_ERROR_IF(!cctx, memory_allocation, "ZSTD_createCCtx failed");
+    result = ZSTD_compressCCtx(cctx, dst, dstCapacity, src, srcSize, compressionLevel);
+    ZSTD_freeCCtx(cctx);
+    return result;
+}
+
+
+/* =====  Dictionary API  ===== */
+
+/*! ZSTD_estimateCDictSize_advanced() :
+ *  Estimate amount of memory that will be needed to create a dictionary with following arguments */
+size_t ZSTD_estimateCDictSize_advanced(
+        size_t dictSize, ZSTD_compressionParameters cParams,
+        ZSTD_dictLoadMethod_e dictLoadMethod)
+{
+    DEBUGLOG(5, "sizeof(ZSTD_CDict) : %u", (unsigned)sizeof(ZSTD_CDict));
+    return ZSTD_cwksp_alloc_size(sizeof(ZSTD_CDict))
+         + ZSTD_cwksp_alloc_size(HUF_WORKSPACE_SIZE)
+         + ZSTD_sizeof_matchState(&cParams, /* forCCtx */ 0)
+         + (dictLoadMethod == ZSTD_dlm_byRef ? 0
+            : ZSTD_cwksp_alloc_size(ZSTD_cwksp_align(dictSize, sizeof(void *))));
+}
+
+size_t ZSTD_estimateCDictSize(size_t dictSize, int compressionLevel)
+{
+    ZSTD_compressionParameters const cParams = ZSTD_getCParams_internal(compressionLevel, ZSTD_CONTENTSIZE_UNKNOWN, dictSize, ZSTD_cpm_createCDict);
+    return ZSTD_estimateCDictSize_advanced(dictSize, cParams, ZSTD_dlm_byCopy);
+}
+
+size_t ZSTD_sizeof_CDict(const ZSTD_CDict* cdict)
+{
+    if (cdict==NULL) return 0;   /* support sizeof on NULL */
+    DEBUGLOG(5, "sizeof(*cdict) : %u", (unsigned)sizeof(*cdict));
+    /* cdict may be in the workspace */
+    return (cdict->workspace.workspace == cdict ? 0 : sizeof(*cdict))
+        + ZSTD_cwksp_sizeof(&cdict->workspace);
+}
+
+static size_t ZSTD_initCDict_internal(
+                    ZSTD_CDict* cdict,
+              const void* dictBuffer, size_t dictSize,
+                    ZSTD_dictLoadMethod_e dictLoadMethod,
+                    ZSTD_dictContentType_e dictContentType,
+                    ZSTD_CCtx_params params)
+{
+    DEBUGLOG(3, "ZSTD_initCDict_internal (dictContentType:%u)", (unsigned)dictContentType);
+    assert(!ZSTD_checkCParams(params.cParams));
+    cdict->matchState.cParams = params.cParams;
+    cdict->matchState.dedicatedDictSearch = params.enableDedicatedDictSearch;
+    if (cdict->matchState.dedicatedDictSearch && dictSize > ZSTD_CHUNKSIZE_MAX) {
+        cdict->matchState.dedicatedDictSearch = 0;
+    }
+    if ((dictLoadMethod == ZSTD_dlm_byRef) || (!dictBuffer) || (!dictSize)) {
+        cdict->dictContent = dictBuffer;
+    } else {
+         void *internalBuffer = ZSTD_cwksp_reserve_object(&cdict->workspace, ZSTD_cwksp_align(dictSize, sizeof(void*)));
+        RETURN_ERROR_IF(!internalBuffer, memory_allocation, "NULL pointer!");
+        cdict->dictContent = internalBuffer;
+        ZSTD_memcpy(internalBuffer, dictBuffer, dictSize);
+    }
+    cdict->dictContentSize = dictSize;
+    cdict->dictContentType = dictContentType;
+
+    cdict->entropyWorkspace = (U32*)ZSTD_cwksp_reserve_object(&cdict->workspace, HUF_WORKSPACE_SIZE);
+
+
+    /* Reset the state to no dictionary */
+    ZSTD_reset_compressedBlockState(&cdict->cBlockState);
+    FORWARD_IF_ERROR(ZSTD_reset_matchState(
+        &cdict->matchState,
+        &cdict->workspace,
+        &params.cParams,
+        ZSTDcrp_makeClean,
+        ZSTDirp_reset,
+        ZSTD_resetTarget_CDict), "");
+    /* (Maybe) load the dictionary
+     * Skips loading the dictionary if it is < 8 bytes.
+     */
+    {   params.compressionLevel = ZSTD_CLEVEL_DEFAULT;
+        params.fParams.contentSizeFlag = 1;
+        {   size_t const dictID = ZSTD_compress_insertDictionary(
+                    &cdict->cBlockState, &cdict->matchState, NULL, &cdict->workspace,
+                    &params, cdict->dictContent, cdict->dictContentSize,
+                    dictContentType, ZSTD_dtlm_full, cdict->entropyWorkspace);
+            FORWARD_IF_ERROR(dictID, "ZSTD_compress_insertDictionary failed");
+            assert(dictID <= (size_t)(U32)-1);
+            cdict->dictID = (U32)dictID;
+        }
+    }
+
+    return 0;
+}
+
+static ZSTD_CDict* ZSTD_createCDict_advanced_internal(size_t dictSize,
+                                      ZSTD_dictLoadMethod_e dictLoadMethod,
+                                      ZSTD_compressionParameters cParams, ZSTD_customMem customMem)
+{
+    if ((!customMem.customAlloc) ^ (!customMem.customFree)) return NULL;
+
+    {   size_t const workspaceSize =
+            ZSTD_cwksp_alloc_size(sizeof(ZSTD_CDict)) +
+            ZSTD_cwksp_alloc_size(HUF_WORKSPACE_SIZE) +
+            ZSTD_sizeof_matchState(&cParams, /* forCCtx */ 0) +
+            (dictLoadMethod == ZSTD_dlm_byRef ? 0
+             : ZSTD_cwksp_alloc_size(ZSTD_cwksp_align(dictSize, sizeof(void*))));
+        void* const workspace = ZSTD_customMalloc(workspaceSize, customMem);
+        ZSTD_cwksp ws;
+        ZSTD_CDict* cdict;
+
+        if (!workspace) {
+            ZSTD_customFree(workspace, customMem);
+            return NULL;
+        }
+
+        ZSTD_cwksp_init(&ws, workspace, workspaceSize, ZSTD_cwksp_dynamic_alloc);
+
+        cdict = (ZSTD_CDict*)ZSTD_cwksp_reserve_object(&ws, sizeof(ZSTD_CDict));
+        assert(cdict != NULL);
+        ZSTD_cwksp_move(&cdict->workspace, &ws);
+        cdict->customMem = customMem;
+        cdict->compressionLevel = ZSTD_NO_CLEVEL; /* signals advanced API usage */
+
+        return cdict;
+    }
+}
+
+ZSTD_CDict* ZSTD_createCDict_advanced(const void* dictBuffer, size_t dictSize,
+                                      ZSTD_dictLoadMethod_e dictLoadMethod,
+                                      ZSTD_dictContentType_e dictContentType,
+                                      ZSTD_compressionParameters cParams,
+                                      ZSTD_customMem customMem)
+{
+    ZSTD_CCtx_params cctxParams;
+    ZSTD_memset(&cctxParams, 0, sizeof(cctxParams));
+    ZSTD_CCtxParams_init(&cctxParams, 0);
+    cctxParams.cParams = cParams;
+    cctxParams.customMem = customMem;
+    return ZSTD_createCDict_advanced2(
+        dictBuffer, dictSize,
+        dictLoadMethod, dictContentType,
+        &cctxParams, customMem);
+}
+
+ZSTDLIB_API ZSTD_CDict* ZSTD_createCDict_advanced2(
+        const void* dict, size_t dictSize,
+        ZSTD_dictLoadMethod_e dictLoadMethod,
+        ZSTD_dictContentType_e dictContentType,
+        const ZSTD_CCtx_params* originalCctxParams,
+        ZSTD_customMem customMem)
+{
+    ZSTD_CCtx_params cctxParams = *originalCctxParams;
+    ZSTD_compressionParameters cParams;
+    ZSTD_CDict* cdict;
+
+    DEBUGLOG(3, "ZSTD_createCDict_advanced2, mode %u", (unsigned)dictContentType);
+    if (!customMem.customAlloc ^ !customMem.customFree) return NULL;
+
+    if (cctxParams.enableDedicatedDictSearch) {
+        cParams = ZSTD_dedicatedDictSearch_getCParams(
+            cctxParams.compressionLevel, dictSize);
+        ZSTD_overrideCParams(&cParams, &cctxParams.cParams);
+    } else {
+        cParams = ZSTD_getCParamsFromCCtxParams(
+            &cctxParams, ZSTD_CONTENTSIZE_UNKNOWN, dictSize, ZSTD_cpm_createCDict);
+    }
+
+    if (!ZSTD_dedicatedDictSearch_isSupported(&cParams)) {
+        /* Fall back to non-DDSS params */
+        cctxParams.enableDedicatedDictSearch = 0;
+        cParams = ZSTD_getCParamsFromCCtxParams(
+            &cctxParams, ZSTD_CONTENTSIZE_UNKNOWN, dictSize, ZSTD_cpm_createCDict);
+    }
+
+    cctxParams.cParams = cParams;
+
+    cdict = ZSTD_createCDict_advanced_internal(dictSize,
+                        dictLoadMethod, cctxParams.cParams,
+                        customMem);
+
+    if (ZSTD_isError( ZSTD_initCDict_internal(cdict,
+                                    dict, dictSize,
+                                    dictLoadMethod, dictContentType,
+                                    cctxParams) )) {
+        ZSTD_freeCDict(cdict);
+        return NULL;
+    }
+
+    return cdict;
+}
+
+ZSTD_CDict* ZSTD_createCDict(const void* dict, size_t dictSize, int compressionLevel)
+{
+    ZSTD_compressionParameters cParams = ZSTD_getCParams_internal(compressionLevel, ZSTD_CONTENTSIZE_UNKNOWN, dictSize, ZSTD_cpm_createCDict);
+    ZSTD_CDict* const cdict = ZSTD_createCDict_advanced(dict, dictSize,
+                                                  ZSTD_dlm_byCopy, ZSTD_dct_auto,
+                                                  cParams, ZSTD_defaultCMem);
+    if (cdict)
+        cdict->compressionLevel = (compressionLevel == 0) ? ZSTD_CLEVEL_DEFAULT : compressionLevel;
+    return cdict;
+}
+
+ZSTD_CDict* ZSTD_createCDict_byReference(const void* dict, size_t dictSize, int compressionLevel)
+{
+    ZSTD_compressionParameters cParams = ZSTD_getCParams_internal(compressionLevel, ZSTD_CONTENTSIZE_UNKNOWN, dictSize, ZSTD_cpm_createCDict);
+    ZSTD_CDict* const cdict = ZSTD_createCDict_advanced(dict, dictSize,
+                                     ZSTD_dlm_byRef, ZSTD_dct_auto,
+                                     cParams, ZSTD_defaultCMem);
+    if (cdict)
+        cdict->compressionLevel = (compressionLevel == 0) ? ZSTD_CLEVEL_DEFAULT : compressionLevel;
+    return cdict;
+}
+
+size_t ZSTD_freeCDict(ZSTD_CDict* cdict)
+{
+    if (cdict==NULL) return 0;   /* support free on NULL */
+    {   ZSTD_customMem const cMem = cdict->customMem;
+        int cdictInWorkspace = ZSTD_cwksp_owns_buffer(&cdict->workspace, cdict);
+        ZSTD_cwksp_free(&cdict->workspace, cMem);
+        if (!cdictInWorkspace) {
+            ZSTD_customFree(cdict, cMem);
+        }
+        return 0;
+    }
+}
+
+/*! ZSTD_initStaticCDict_advanced() :
+ *  Generate a digested dictionary in provided memory area.
+ *  workspace: The memory area to emplace the dictionary into.
+ *             Provided pointer must 8-bytes aligned.
+ *             It must outlive dictionary usage.
+ *  workspaceSize: Use ZSTD_estimateCDictSize()
+ *                 to determine how large workspace must be.
+ *  cParams : use ZSTD_getCParams() to transform a compression level
+ *            into its relevants cParams.
+ * @return : pointer to ZSTD_CDict*, or NULL if error (size too small)
+ *  Note : there is no corresponding "free" function.
+ *         Since workspace was allocated externally, it must be freed externally.
+ */
+const ZSTD_CDict* ZSTD_initStaticCDict(
+                                 void* workspace, size_t workspaceSize,
+                           const void* dict, size_t dictSize,
+                                 ZSTD_dictLoadMethod_e dictLoadMethod,
+                                 ZSTD_dictContentType_e dictContentType,
+                                 ZSTD_compressionParameters cParams)
+{
+    size_t const matchStateSize = ZSTD_sizeof_matchState(&cParams, /* forCCtx */ 0);
+    size_t const neededSize = ZSTD_cwksp_alloc_size(sizeof(ZSTD_CDict))
+                            + (dictLoadMethod == ZSTD_dlm_byRef ? 0
+                               : ZSTD_cwksp_alloc_size(ZSTD_cwksp_align(dictSize, sizeof(void*))))
+                            + ZSTD_cwksp_alloc_size(HUF_WORKSPACE_SIZE)
+                            + matchStateSize;
+    ZSTD_CDict* cdict;
+    ZSTD_CCtx_params params;
+
+    if ((size_t)workspace & 7) return NULL;  /* 8-aligned */
+
+    {
+        ZSTD_cwksp ws;
+        ZSTD_cwksp_init(&ws, workspace, workspaceSize, ZSTD_cwksp_static_alloc);
+        cdict = (ZSTD_CDict*)ZSTD_cwksp_reserve_object(&ws, sizeof(ZSTD_CDict));
+        if (cdict == NULL) return NULL;
+        ZSTD_cwksp_move(&cdict->workspace, &ws);
+    }
+
+    DEBUGLOG(4, "(workspaceSize < neededSize) : (%u < %u) => %u",
+        (unsigned)workspaceSize, (unsigned)neededSize, (unsigned)(workspaceSize < neededSize));
+    if (workspaceSize < neededSize) return NULL;
+
+    ZSTD_CCtxParams_init(&params, 0);
+    params.cParams = cParams;
+
+    if (ZSTD_isError( ZSTD_initCDict_internal(cdict,
+                                              dict, dictSize,
+                                              dictLoadMethod, dictContentType,
+                                              params) ))
+        return NULL;
+
+    return cdict;
+}
+
+ZSTD_compressionParameters ZSTD_getCParamsFromCDict(const ZSTD_CDict* cdict)
+{
+    assert(cdict != NULL);
+    return cdict->matchState.cParams;
+}
+
+/*! ZSTD_getDictID_fromCDict() :
+ *  Provides the dictID of the dictionary loaded into `cdict`.
+ *  If @return == 0, the dictionary is not conformant to Zstandard specification, or empty.
+ *  Non-conformant dictionaries can still be loaded, but as content-only dictionaries. */
+unsigned ZSTD_getDictID_fromCDict(const ZSTD_CDict* cdict)
+{
+    if (cdict==NULL) return 0;
+    return cdict->dictID;
+}
+
+
+/* ZSTD_compressBegin_usingCDict_advanced() :
+ * cdict must be != NULL */
+size_t ZSTD_compressBegin_usingCDict_advanced(
+    ZSTD_CCtx* const cctx, const ZSTD_CDict* const cdict,
+    ZSTD_frameParameters const fParams, unsigned long long const pledgedSrcSize)
+{
+    ZSTD_CCtx_params cctxParams;
+    DEBUGLOG(4, "ZSTD_compressBegin_usingCDict_advanced");
+    RETURN_ERROR_IF(cdict==NULL, dictionary_wrong, "NULL pointer!");
+    /* Initialize the cctxParams from the cdict */
+    {
+        ZSTD_parameters params;
+        params.fParams = fParams;
+        params.cParams = ( pledgedSrcSize < ZSTD_USE_CDICT_PARAMS_SRCSIZE_CUTOFF
+                        || pledgedSrcSize < cdict->dictContentSize * ZSTD_USE_CDICT_PARAMS_DICTSIZE_MULTIPLIER
+                        || pledgedSrcSize == ZSTD_CONTENTSIZE_UNKNOWN
+                        || cdict->compressionLevel == 0 ) ?
+                ZSTD_getCParamsFromCDict(cdict)
+              : ZSTD_getCParams(cdict->compressionLevel,
+                                pledgedSrcSize,
+                                cdict->dictContentSize);
+        ZSTD_CCtxParams_init_internal(&cctxParams, &params, cdict->compressionLevel);
+    }
+    /* Increase window log to fit the entire dictionary and source if the
+     * source size is known. Limit the increase to 19, which is the
+     * window log for compression level 1 with the largest source size.
+     */
+    if (pledgedSrcSize != ZSTD_CONTENTSIZE_UNKNOWN) {
+        U32 const limitedSrcSize = (U32)MIN(pledgedSrcSize, 1U << 19);
+        U32 const limitedSrcLog = limitedSrcSize > 1 ? ZSTD_highbit32(limitedSrcSize - 1) + 1 : 1;
+        cctxParams.cParams.windowLog = MAX(cctxParams.cParams.windowLog, limitedSrcLog);
+    }
+    return ZSTD_compressBegin_internal(cctx,
+                                        NULL, 0, ZSTD_dct_auto, ZSTD_dtlm_fast,
+                                        cdict,
+                                        &cctxParams, pledgedSrcSize,
+                                        ZSTDb_not_buffered);
+}
+
+/* ZSTD_compressBegin_usingCDict() :
+ * pledgedSrcSize=0 means "unknown"
+ * if pledgedSrcSize>0, it will enable contentSizeFlag */
+size_t ZSTD_compressBegin_usingCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict)
+{
+    ZSTD_frameParameters const fParams = { 0 /*content*/, 0 /*checksum*/, 0 /*noDictID*/ };
+    DEBUGLOG(4, "ZSTD_compressBegin_usingCDict : dictIDFlag == %u", !fParams.noDictIDFlag);
+    return ZSTD_compressBegin_usingCDict_advanced(cctx, cdict, fParams, ZSTD_CONTENTSIZE_UNKNOWN);
+}
+
+size_t ZSTD_compress_usingCDict_advanced(ZSTD_CCtx* cctx,
+                                void* dst, size_t dstCapacity,
+                                const void* src, size_t srcSize,
+                                const ZSTD_CDict* cdict, ZSTD_frameParameters fParams)
+{
+    FORWARD_IF_ERROR(ZSTD_compressBegin_usingCDict_advanced(cctx, cdict, fParams, srcSize), "");   /* will check if cdict != NULL */
+    return ZSTD_compressEnd(cctx, dst, dstCapacity, src, srcSize);
+}
+
+/*! ZSTD_compress_usingCDict() :
+ *  Compression using a digested Dictionary.
+ *  Faster startup than ZSTD_compress_usingDict(), recommended when same dictionary is used multiple times.
+ *  Note that compression parameters are decided at CDict creation time
+ *  while frame parameters are hardcoded */
+size_t ZSTD_compress_usingCDict(ZSTD_CCtx* cctx,
+                                void* dst, size_t dstCapacity,
+                                const void* src, size_t srcSize,
+                                const ZSTD_CDict* cdict)
+{
+    ZSTD_frameParameters const fParams = { 1 /*content*/, 0 /*checksum*/, 0 /*noDictID*/ };
+    return ZSTD_compress_usingCDict_advanced(cctx, dst, dstCapacity, src, srcSize, cdict, fParams);
+}
+
+
+
+/* ******************************************************************
+*  Streaming
+********************************************************************/
+
+ZSTD_CStream* ZSTD_createCStream(void)
+{
+    DEBUGLOG(3, "ZSTD_createCStream");
+    return ZSTD_createCStream_advanced(ZSTD_defaultCMem);
+}
+
+ZSTD_CStream* ZSTD_initStaticCStream(void *workspace, size_t workspaceSize)
+{
+    return ZSTD_initStaticCCtx(workspace, workspaceSize);
+}
+
+ZSTD_CStream* ZSTD_createCStream_advanced(ZSTD_customMem customMem)
+{   /* CStream and CCtx are now same object */
+    return ZSTD_createCCtx_advanced(customMem);
+}
+
+size_t ZSTD_freeCStream(ZSTD_CStream* zcs)
+{
+    return ZSTD_freeCCtx(zcs);   /* same object */
+}
+
+
+
+/*======   Initialization   ======*/
+
+size_t ZSTD_CStreamInSize(void)  { return ZSTD_BLOCKSIZE_MAX; }
+
+size_t ZSTD_CStreamOutSize(void)
+{
+    return ZSTD_compressBound(ZSTD_BLOCKSIZE_MAX) + ZSTD_blockHeaderSize + 4 /* 32-bits hash */ ;
+}
+
+static ZSTD_cParamMode_e ZSTD_getCParamMode(ZSTD_CDict const* cdict, ZSTD_CCtx_params const* params, U64 pledgedSrcSize)
+{
+    if (cdict != NULL && ZSTD_shouldAttachDict(cdict, params, pledgedSrcSize))
+        return ZSTD_cpm_attachDict;
+    else
+        return ZSTD_cpm_noAttachDict;
+}
+
+/* ZSTD_resetCStream():
+ * pledgedSrcSize == 0 means "unknown" */
+size_t ZSTD_resetCStream(ZSTD_CStream* zcs, unsigned long long pss)
+{
+    /* temporary : 0 interpreted as "unknown" during transition period.
+     * Users willing to specify "unknown" **must** use ZSTD_CONTENTSIZE_UNKNOWN.
+     * 0 will be interpreted as "empty" in the future.
+     */
+    U64 const pledgedSrcSize = (pss==0) ? ZSTD_CONTENTSIZE_UNKNOWN : pss;
+    DEBUGLOG(4, "ZSTD_resetCStream: pledgedSrcSize = %u", (unsigned)pledgedSrcSize);
+    FORWARD_IF_ERROR( ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only) , "");
+    FORWARD_IF_ERROR( ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize) , "");
+    return 0;
+}
+
+/*! ZSTD_initCStream_internal() :
+ *  Note : for lib/compress only. Used by zstdmt_compress.c.
+ *  Assumption 1 : params are valid
+ *  Assumption 2 : either dict, or cdict, is defined, not both */
+size_t ZSTD_initCStream_internal(ZSTD_CStream* zcs,
+                    const void* dict, size_t dictSize, const ZSTD_CDict* cdict,
+                    const ZSTD_CCtx_params* params,
+                    unsigned long long pledgedSrcSize)
+{
+    DEBUGLOG(4, "ZSTD_initCStream_internal");
+    FORWARD_IF_ERROR( ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only) , "");
+    FORWARD_IF_ERROR( ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize) , "");
+    assert(!ZSTD_isError(ZSTD_checkCParams(params->cParams)));
+    zcs->requestedParams = *params;
+    assert(!((dict) && (cdict)));  /* either dict or cdict, not both */
+    if (dict) {
+        FORWARD_IF_ERROR( ZSTD_CCtx_loadDictionary(zcs, dict, dictSize) , "");
+    } else {
+        /* Dictionary is cleared if !cdict */
+        FORWARD_IF_ERROR( ZSTD_CCtx_refCDict(zcs, cdict) , "");
+    }
+    return 0;
+}
+
+/* ZSTD_initCStream_usingCDict_advanced() :
+ * same as ZSTD_initCStream_usingCDict(), with control over frame parameters */
+size_t ZSTD_initCStream_usingCDict_advanced(ZSTD_CStream* zcs,
+                                            const ZSTD_CDict* cdict,
+                                            ZSTD_frameParameters fParams,
+                                            unsigned long long pledgedSrcSize)
+{
+    DEBUGLOG(4, "ZSTD_initCStream_usingCDict_advanced");
+    FORWARD_IF_ERROR( ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only) , "");
+    FORWARD_IF_ERROR( ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize) , "");
+    zcs->requestedParams.fParams = fParams;
+    FORWARD_IF_ERROR( ZSTD_CCtx_refCDict(zcs, cdict) , "");
+    return 0;
+}
+
+/* note : cdict must outlive compression session */
+size_t ZSTD_initCStream_usingCDict(ZSTD_CStream* zcs, const ZSTD_CDict* cdict)
+{
+    DEBUGLOG(4, "ZSTD_initCStream_usingCDict");
+    FORWARD_IF_ERROR( ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only) , "");
+    FORWARD_IF_ERROR( ZSTD_CCtx_refCDict(zcs, cdict) , "");
+    return 0;
+}
+
+
+/* ZSTD_initCStream_advanced() :
+ * pledgedSrcSize must be exact.
+ * if srcSize is not known at init time, use value ZSTD_CONTENTSIZE_UNKNOWN.
+ * dict is loaded with default parameters ZSTD_dct_auto and ZSTD_dlm_byCopy. */
+size_t ZSTD_initCStream_advanced(ZSTD_CStream* zcs,
+                                 const void* dict, size_t dictSize,
+                                 ZSTD_parameters params, unsigned long long pss)
+{
+    /* for compatibility with older programs relying on this behavior.
+     * Users should now specify ZSTD_CONTENTSIZE_UNKNOWN.
+     * This line will be removed in the future.
+     */
+    U64 const pledgedSrcSize = (pss==0 && params.fParams.contentSizeFlag==0) ? ZSTD_CONTENTSIZE_UNKNOWN : pss;
+    DEBUGLOG(4, "ZSTD_initCStream_advanced");
+    FORWARD_IF_ERROR( ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only) , "");
+    FORWARD_IF_ERROR( ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize) , "");
+    FORWARD_IF_ERROR( ZSTD_checkCParams(params.cParams) , "");
+    ZSTD_CCtxParams_setZstdParams(&zcs->requestedParams, &params);
+    FORWARD_IF_ERROR( ZSTD_CCtx_loadDictionary(zcs, dict, dictSize) , "");
+    return 0;
+}
+
+size_t ZSTD_initCStream_usingDict(ZSTD_CStream* zcs, const void* dict, size_t dictSize, int compressionLevel)
+{
+    DEBUGLOG(4, "ZSTD_initCStream_usingDict");
+    FORWARD_IF_ERROR( ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only) , "");
+    FORWARD_IF_ERROR( ZSTD_CCtx_setParameter(zcs, ZSTD_c_compressionLevel, compressionLevel) , "");
+    FORWARD_IF_ERROR( ZSTD_CCtx_loadDictionary(zcs, dict, dictSize) , "");
+    return 0;
+}
+
+size_t ZSTD_initCStream_srcSize(ZSTD_CStream* zcs, int compressionLevel, unsigned long long pss)
+{
+    /* temporary : 0 interpreted as "unknown" during transition period.
+     * Users willing to specify "unknown" **must** use ZSTD_CONTENTSIZE_UNKNOWN.
+     * 0 will be interpreted as "empty" in the future.
+     */
+    U64 const pledgedSrcSize = (pss==0) ? ZSTD_CONTENTSIZE_UNKNOWN : pss;
+    DEBUGLOG(4, "ZSTD_initCStream_srcSize");
+    FORWARD_IF_ERROR( ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only) , "");
+    FORWARD_IF_ERROR( ZSTD_CCtx_refCDict(zcs, NULL) , "");
+    FORWARD_IF_ERROR( ZSTD_CCtx_setParameter(zcs, ZSTD_c_compressionLevel, compressionLevel) , "");
+    FORWARD_IF_ERROR( ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize) , "");
+    return 0;
+}
+
+size_t ZSTD_initCStream(ZSTD_CStream* zcs, int compressionLevel)
+{
+    DEBUGLOG(4, "ZSTD_initCStream");
+    FORWARD_IF_ERROR( ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only) , "");
+    FORWARD_IF_ERROR( ZSTD_CCtx_refCDict(zcs, NULL) , "");
+    FORWARD_IF_ERROR( ZSTD_CCtx_setParameter(zcs, ZSTD_c_compressionLevel, compressionLevel) , "");
+    return 0;
+}
+
+/*======   Compression   ======*/
+
+static size_t ZSTD_nextInputSizeHint(const ZSTD_CCtx* cctx)
+{
+    size_t hintInSize = cctx->inBuffTarget - cctx->inBuffPos;
+    if (hintInSize==0) hintInSize = cctx->blockSize;
+    return hintInSize;
+}
+
+/* ZSTD_compressStream_generic():
+ *  internal function for all *compressStream*() variants
+ *  non-static, because can be called from zstdmt_compress.c
+ * @return : hint size for next input */
+static size_t ZSTD_compressStream_generic(ZSTD_CStream* zcs,
+                                          ZSTD_outBuffer* output,
+                                          ZSTD_inBuffer* input,
+                                          ZSTD_EndDirective const flushMode)
+{
+    const char* const istart = (const char*)input->src;
+    const char* const iend = input->size != 0 ? istart + input->size : istart;
+    const char* ip = input->pos != 0 ? istart + input->pos : istart;
+    char* const ostart = (char*)output->dst;
+    char* const oend = output->size != 0 ? ostart + output->size : ostart;
+    char* op = output->pos != 0 ? ostart + output->pos : ostart;
+    U32 someMoreWork = 1;
+
+    /* check expectations */
+    DEBUGLOG(5, "ZSTD_compressStream_generic, flush=%u", (unsigned)flushMode);
+    if (zcs->appliedParams.inBufferMode == ZSTD_bm_buffered) {
+        assert(zcs->inBuff != NULL);
+        assert(zcs->inBuffSize > 0);
+    }
+    if (zcs->appliedParams.outBufferMode == ZSTD_bm_buffered) {
+        assert(zcs->outBuff !=  NULL);
+        assert(zcs->outBuffSize > 0);
+    }
+    assert(output->pos <= output->size);
+    assert(input->pos <= input->size);
+    assert((U32)flushMode <= (U32)ZSTD_e_end);
+
+    while (someMoreWork) {
+        switch(zcs->streamStage)
+        {
+        case zcss_init:
+            RETURN_ERROR(init_missing, "call ZSTD_initCStream() first!");
+
+        case zcss_load:
+            if ( (flushMode == ZSTD_e_end)
+              && ( (size_t)(oend-op) >= ZSTD_compressBound(iend-ip)     /* Enough output space */
+                || zcs->appliedParams.outBufferMode == ZSTD_bm_stable)  /* OR we are allowed to return dstSizeTooSmall */
+              && (zcs->inBuffPos == 0) ) {
+                /* shortcut to compression pass directly into output buffer */
+                size_t const cSize = ZSTD_compressEnd(zcs,
+                                                op, oend-op, ip, iend-ip);
+                DEBUGLOG(4, "ZSTD_compressEnd : cSize=%u", (unsigned)cSize);
+                FORWARD_IF_ERROR(cSize, "ZSTD_compressEnd failed");
+                ip = iend;
+                op += cSize;
+                zcs->frameEnded = 1;
+                ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only);
+                someMoreWork = 0; break;
+            }
+            /* complete loading into inBuffer in buffered mode */
+            if (zcs->appliedParams.inBufferMode == ZSTD_bm_buffered) {
+                size_t const toLoad = zcs->inBuffTarget - zcs->inBuffPos;
+                size_t const loaded = ZSTD_limitCopy(
+                                        zcs->inBuff + zcs->inBuffPos, toLoad,
+                                        ip, iend-ip);
+                zcs->inBuffPos += loaded;
+                if (loaded != 0)
+                    ip += loaded;
+                if ( (flushMode == ZSTD_e_continue)
+                  && (zcs->inBuffPos < zcs->inBuffTarget) ) {
+                    /* not enough input to fill full block : stop here */
+                    someMoreWork = 0; break;
+                }
+                if ( (flushMode == ZSTD_e_flush)
+                  && (zcs->inBuffPos == zcs->inToCompress) ) {
+                    /* empty */
+                    someMoreWork = 0; break;
+                }
+            }
+            /* compress current block (note : this stage cannot be stopped in the middle) */
+            DEBUGLOG(5, "stream compression stage (flushMode==%u)", flushMode);
+            {   int const inputBuffered = (zcs->appliedParams.inBufferMode == ZSTD_bm_buffered);
+                void* cDst;
+                size_t cSize;
+                size_t oSize = oend-op;
+                size_t const iSize = inputBuffered
+                    ? zcs->inBuffPos - zcs->inToCompress
+                    : MIN((size_t)(iend - ip), zcs->blockSize);
+                if (oSize >= ZSTD_compressBound(iSize) || zcs->appliedParams.outBufferMode == ZSTD_bm_stable)
+                    cDst = op;   /* compress into output buffer, to skip flush stage */
+                else
+                    cDst = zcs->outBuff, oSize = zcs->outBuffSize;
+                if (inputBuffered) {
+                    unsigned const lastBlock = (flushMode == ZSTD_e_end) && (ip==iend);
+                    cSize = lastBlock ?
+                            ZSTD_compressEnd(zcs, cDst, oSize,
+                                        zcs->inBuff + zcs->inToCompress, iSize) :
+                            ZSTD_compressContinue(zcs, cDst, oSize,
+                                        zcs->inBuff + zcs->inToCompress, iSize);
+                    FORWARD_IF_ERROR(cSize, "%s", lastBlock ? "ZSTD_compressEnd failed" : "ZSTD_compressContinue failed");
+                    zcs->frameEnded = lastBlock;
+                    /* prepare next block */
+                    zcs->inBuffTarget = zcs->inBuffPos + zcs->blockSize;
+                    if (zcs->inBuffTarget > zcs->inBuffSize)
+                        zcs->inBuffPos = 0, zcs->inBuffTarget = zcs->blockSize;
+                    DEBUGLOG(5, "inBuffTarget:%u / inBuffSize:%u",
+                            (unsigned)zcs->inBuffTarget, (unsigned)zcs->inBuffSize);
+                    if (!lastBlock)
+                        assert(zcs->inBuffTarget <= zcs->inBuffSize);
+                    zcs->inToCompress = zcs->inBuffPos;
+                } else {
+                    unsigned const lastBlock = (ip + iSize == iend);
+                    assert(flushMode == ZSTD_e_end /* Already validated */);
+                    cSize = lastBlock ?
+                            ZSTD_compressEnd(zcs, cDst, oSize, ip, iSize) :
+                            ZSTD_compressContinue(zcs, cDst, oSize, ip, iSize);
+                    /* Consume the input prior to error checking to mirror buffered mode. */
+                    if (iSize > 0)
+                        ip += iSize;
+                    FORWARD_IF_ERROR(cSize, "%s", lastBlock ? "ZSTD_compressEnd failed" : "ZSTD_compressContinue failed");
+                    zcs->frameEnded = lastBlock;
+                    if (lastBlock)
+                        assert(ip == iend);
+                }
+                if (cDst == op) {  /* no need to flush */
+                    op += cSize;
+                    if (zcs->frameEnded) {
+                        DEBUGLOG(5, "Frame completed directly in outBuffer");
+                        someMoreWork = 0;
+                        ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only);
+                    }
+                    break;
+                }
+                zcs->outBuffContentSize = cSize;
+                zcs->outBuffFlushedSize = 0;
+                zcs->streamStage = zcss_flush; /* pass-through to flush stage */
+            }
+	    ZSTD_FALLTHROUGH;
+        case zcss_flush:
+            DEBUGLOG(5, "flush stage");
+            assert(zcs->appliedParams.outBufferMode == ZSTD_bm_buffered);
+            {   size_t const toFlush = zcs->outBuffContentSize - zcs->outBuffFlushedSize;
+                size_t const flushed = ZSTD_limitCopy(op, (size_t)(oend-op),
+                            zcs->outBuff + zcs->outBuffFlushedSize, toFlush);
+                DEBUGLOG(5, "toFlush: %u into %u ==> flushed: %u",
+                            (unsigned)toFlush, (unsigned)(oend-op), (unsigned)flushed);
+                if (flushed)
+                    op += flushed;
+                zcs->outBuffFlushedSize += flushed;
+                if (toFlush!=flushed) {
+                    /* flush not fully completed, presumably because dst is too small */
+                    assert(op==oend);
+                    someMoreWork = 0;
+                    break;
+                }
+                zcs->outBuffContentSize = zcs->outBuffFlushedSize = 0;
+                if (zcs->frameEnded) {
+                    DEBUGLOG(5, "Frame completed on flush");
+                    someMoreWork = 0;
+                    ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only);
+                    break;
+                }
+                zcs->streamStage = zcss_load;
+                break;
+            }
+
+        default: /* impossible */
+            assert(0);
+        }
+    }
+
+    input->pos = ip - istart;
+    output->pos = op - ostart;
+    if (zcs->frameEnded) return 0;
+    return ZSTD_nextInputSizeHint(zcs);
+}
+
+static size_t ZSTD_nextInputSizeHint_MTorST(const ZSTD_CCtx* cctx)
+{
+    return ZSTD_nextInputSizeHint(cctx);
+
+}
+
+size_t ZSTD_compressStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output, ZSTD_inBuffer* input)
+{
+    FORWARD_IF_ERROR( ZSTD_compressStream2(zcs, output, input, ZSTD_e_continue) , "");
+    return ZSTD_nextInputSizeHint_MTorST(zcs);
+}
+
+/* After a compression call set the expected input/output buffer.
+ * This is validated at the start of the next compression call.
+ */
+static void ZSTD_setBufferExpectations(ZSTD_CCtx* cctx, ZSTD_outBuffer const* output, ZSTD_inBuffer const* input)
+{
+    if (cctx->appliedParams.inBufferMode == ZSTD_bm_stable) {
+        cctx->expectedInBuffer = *input;
+    }
+    if (cctx->appliedParams.outBufferMode == ZSTD_bm_stable) {
+        cctx->expectedOutBufferSize = output->size - output->pos;
+    }
+}
+
+/* Validate that the input/output buffers match the expectations set by
+ * ZSTD_setBufferExpectations.
+ */
+static size_t ZSTD_checkBufferStability(ZSTD_CCtx const* cctx,
+                                        ZSTD_outBuffer const* output,
+                                        ZSTD_inBuffer const* input,
+                                        ZSTD_EndDirective endOp)
+{
+    if (cctx->appliedParams.inBufferMode == ZSTD_bm_stable) {
+        ZSTD_inBuffer const expect = cctx->expectedInBuffer;
+        if (expect.src != input->src || expect.pos != input->pos || expect.size != input->size)
+            RETURN_ERROR(srcBuffer_wrong, "ZSTD_c_stableInBuffer enabled but input differs!");
+        if (endOp != ZSTD_e_end)
+            RETURN_ERROR(srcBuffer_wrong, "ZSTD_c_stableInBuffer can only be used with ZSTD_e_end!");
+    }
+    if (cctx->appliedParams.outBufferMode == ZSTD_bm_stable) {
+        size_t const outBufferSize = output->size - output->pos;
+        if (cctx->expectedOutBufferSize != outBufferSize)
+            RETURN_ERROR(dstBuffer_wrong, "ZSTD_c_stableOutBuffer enabled but output size differs!");
+    }
+    return 0;
+}
+
+static size_t ZSTD_CCtx_init_compressStream2(ZSTD_CCtx* cctx,
+                                             ZSTD_EndDirective endOp,
+                                             size_t inSize) {
+    ZSTD_CCtx_params params = cctx->requestedParams;
+    ZSTD_prefixDict const prefixDict = cctx->prefixDict;
+    FORWARD_IF_ERROR( ZSTD_initLocalDict(cctx) , ""); /* Init the local dict if present. */
+    ZSTD_memset(&cctx->prefixDict, 0, sizeof(cctx->prefixDict));   /* single usage */
+    assert(prefixDict.dict==NULL || cctx->cdict==NULL);    /* only one can be set */
+    if (cctx->cdict)
+        params.compressionLevel = cctx->cdict->compressionLevel; /* let cdict take priority in terms of compression level */
+    DEBUGLOG(4, "ZSTD_compressStream2 : transparent init stage");
+    if (endOp == ZSTD_e_end) cctx->pledgedSrcSizePlusOne = inSize + 1;  /* auto-fix pledgedSrcSize */
+    {
+        size_t const dictSize = prefixDict.dict
+                ? prefixDict.dictSize
+                : (cctx->cdict ? cctx->cdict->dictContentSize : 0);
+        ZSTD_cParamMode_e const mode = ZSTD_getCParamMode(cctx->cdict, &params, cctx->pledgedSrcSizePlusOne - 1);
+        params.cParams = ZSTD_getCParamsFromCCtxParams(
+                &params, cctx->pledgedSrcSizePlusOne-1,
+                dictSize, mode);
+    }
+
+    if (ZSTD_CParams_shouldEnableLdm(&params.cParams)) {
+        /* Enable LDM by default for optimal parser and window size >= 128MB */
+        DEBUGLOG(4, "LDM enabled by default (window size >= 128MB, strategy >= btopt)");
+        params.ldmParams.enableLdm = 1;
+    }
+
+    {   U64 const pledgedSrcSize = cctx->pledgedSrcSizePlusOne - 1;
+        assert(!ZSTD_isError(ZSTD_checkCParams(params.cParams)));
+        FORWARD_IF_ERROR( ZSTD_compressBegin_internal(cctx,
+                prefixDict.dict, prefixDict.dictSize, prefixDict.dictContentType, ZSTD_dtlm_fast,
+                cctx->cdict,
+                &params, pledgedSrcSize,
+                ZSTDb_buffered) , "");
+        assert(cctx->appliedParams.nbWorkers == 0);
+        cctx->inToCompress = 0;
+        cctx->inBuffPos = 0;
+        if (cctx->appliedParams.inBufferMode == ZSTD_bm_buffered) {
+            /* for small input: avoid automatic flush on reaching end of block, since
+            * it would require to add a 3-bytes null block to end frame
+            */
+            cctx->inBuffTarget = cctx->blockSize + (cctx->blockSize == pledgedSrcSize);
+        } else {
+            cctx->inBuffTarget = 0;
+        }
+        cctx->outBuffContentSize = cctx->outBuffFlushedSize = 0;
+        cctx->streamStage = zcss_load;
+        cctx->frameEnded = 0;
+    }
+    return 0;
+}
+
+size_t ZSTD_compressStream2( ZSTD_CCtx* cctx,
+                             ZSTD_outBuffer* output,
+                             ZSTD_inBuffer* input,
+                             ZSTD_EndDirective endOp)
+{
+    DEBUGLOG(5, "ZSTD_compressStream2, endOp=%u ", (unsigned)endOp);
+    /* check conditions */
+    RETURN_ERROR_IF(output->pos > output->size, dstSize_tooSmall, "invalid output buffer");
+    RETURN_ERROR_IF(input->pos  > input->size, srcSize_wrong, "invalid input buffer");
+    RETURN_ERROR_IF((U32)endOp > (U32)ZSTD_e_end, parameter_outOfBound, "invalid endDirective");
+    assert(cctx != NULL);
+
+    /* transparent initialization stage */
+    if (cctx->streamStage == zcss_init) {
+        FORWARD_IF_ERROR(ZSTD_CCtx_init_compressStream2(cctx, endOp, input->size), "CompressStream2 initialization failed");
+        ZSTD_setBufferExpectations(cctx, output, input);    /* Set initial buffer expectations now that we've initialized */
+    }
+    /* end of transparent initialization stage */
+
+    FORWARD_IF_ERROR(ZSTD_checkBufferStability(cctx, output, input, endOp), "invalid buffers");
+    /* compression stage */
+    FORWARD_IF_ERROR( ZSTD_compressStream_generic(cctx, output, input, endOp) , "");
+    DEBUGLOG(5, "completed ZSTD_compressStream2");
+    ZSTD_setBufferExpectations(cctx, output, input);
+    return cctx->outBuffContentSize - cctx->outBuffFlushedSize; /* remaining to flush */
+}
+
+size_t ZSTD_compressStream2_simpleArgs (
+                            ZSTD_CCtx* cctx,
+                            void* dst, size_t dstCapacity, size_t* dstPos,
+                      const void* src, size_t srcSize, size_t* srcPos,
+                            ZSTD_EndDirective endOp)
+{
+    ZSTD_outBuffer output = { dst, dstCapacity, *dstPos };
+    ZSTD_inBuffer  input  = { src, srcSize, *srcPos };
+    /* ZSTD_compressStream2() will check validity of dstPos and srcPos */
+    size_t const cErr = ZSTD_compressStream2(cctx, &output, &input, endOp);
+    *dstPos = output.pos;
+    *srcPos = input.pos;
+    return cErr;
+}
+
+size_t ZSTD_compress2(ZSTD_CCtx* cctx,
+                      void* dst, size_t dstCapacity,
+                      const void* src, size_t srcSize)
+{
+    ZSTD_bufferMode_e const originalInBufferMode = cctx->requestedParams.inBufferMode;
+    ZSTD_bufferMode_e const originalOutBufferMode = cctx->requestedParams.outBufferMode;
+    DEBUGLOG(4, "ZSTD_compress2 (srcSize=%u)", (unsigned)srcSize);
+    ZSTD_CCtx_reset(cctx, ZSTD_reset_session_only);
+    /* Enable stable input/output buffers. */
+    cctx->requestedParams.inBufferMode = ZSTD_bm_stable;
+    cctx->requestedParams.outBufferMode = ZSTD_bm_stable;
+    {   size_t oPos = 0;
+        size_t iPos = 0;
+        size_t const result = ZSTD_compressStream2_simpleArgs(cctx,
+                                        dst, dstCapacity, &oPos,
+                                        src, srcSize, &iPos,
+                                        ZSTD_e_end);
+        /* Reset to the original values. */
+        cctx->requestedParams.inBufferMode = originalInBufferMode;
+        cctx->requestedParams.outBufferMode = originalOutBufferMode;
+        FORWARD_IF_ERROR(result, "ZSTD_compressStream2_simpleArgs failed");
+        if (result != 0) {  /* compression not completed, due to lack of output space */
+            assert(oPos == dstCapacity);
+            RETURN_ERROR(dstSize_tooSmall, "");
+        }
+        assert(iPos == srcSize);   /* all input is expected consumed */
+        return oPos;
+    }
+}
+
+typedef struct {
+    U32 idx;             /* Index in array of ZSTD_Sequence */
+    U32 posInSequence;   /* Position within sequence at idx */
+    size_t posInSrc;        /* Number of bytes given by sequences provided so far */
+} ZSTD_sequencePosition;
+
+/* Returns a ZSTD error code if sequence is not valid */
+static size_t ZSTD_validateSequence(U32 offCode, U32 matchLength,
+                                    size_t posInSrc, U32 windowLog, size_t dictSize, U32 minMatch) {
+    size_t offsetBound;
+    U32 windowSize = 1 << windowLog;
+    /* posInSrc represents the amount of data the the decoder would decode up to this point.
+     * As long as the amount of data decoded is less than or equal to window size, offsets may be
+     * larger than the total length of output decoded in order to reference the dict, even larger than
+     * window size. After output surpasses windowSize, we're limited to windowSize offsets again.
+     */
+    offsetBound = posInSrc > windowSize ? (size_t)windowSize : posInSrc + (size_t)dictSize;
+    RETURN_ERROR_IF(offCode > offsetBound + ZSTD_REP_MOVE, corruption_detected, "Offset too large!");
+    RETURN_ERROR_IF(matchLength < minMatch, corruption_detected, "Matchlength too small");
+    return 0;
+}
+
+/* Returns an offset code, given a sequence's raw offset, the ongoing repcode array, and whether litLength == 0 */
+static U32 ZSTD_finalizeOffCode(U32 rawOffset, const U32 rep[ZSTD_REP_NUM], U32 ll0) {
+    U32 offCode = rawOffset + ZSTD_REP_MOVE;
+    U32 repCode = 0;
+
+    if (!ll0 && rawOffset == rep[0]) {
+        repCode = 1;
+    } else if (rawOffset == rep[1]) {
+        repCode = 2 - ll0;
+    } else if (rawOffset == rep[2]) {
+        repCode = 3 - ll0;
+    } else if (ll0 && rawOffset == rep[0] - 1) {
+        repCode = 3;
+    }
+    if (repCode) {
+        /* ZSTD_storeSeq expects a number in the range [0, 2] to represent a repcode */
+        offCode = repCode - 1;
+    }
+    return offCode;
+}
+
+/* Returns 0 on success, and a ZSTD_error otherwise. This function scans through an array of
+ * ZSTD_Sequence, storing the sequences it finds, until it reaches a block delimiter.
+ */
+static size_t ZSTD_copySequencesToSeqStoreExplicitBlockDelim(ZSTD_CCtx* cctx, ZSTD_sequencePosition* seqPos,
+                                                             const ZSTD_Sequence* const inSeqs, size_t inSeqsSize,
+                                                             const void* src, size_t blockSize) {
+    U32 idx = seqPos->idx;
+    BYTE const* ip = (BYTE const*)(src);
+    const BYTE* const iend = ip + blockSize;
+    repcodes_t updatedRepcodes;
+    U32 dictSize;
+    U32 litLength;
+    U32 matchLength;
+    U32 ll0;
+    U32 offCode;
+
+    if (cctx->cdict) {
+        dictSize = (U32)cctx->cdict->dictContentSize;
+    } else if (cctx->prefixDict.dict) {
+        dictSize = (U32)cctx->prefixDict.dictSize;
+    } else {
+        dictSize = 0;
+    }
+    ZSTD_memcpy(updatedRepcodes.rep, cctx->blockState.prevCBlock->rep, sizeof(repcodes_t));
+    for (; (inSeqs[idx].matchLength != 0 || inSeqs[idx].offset != 0) && idx < inSeqsSize; ++idx) {
+        litLength = inSeqs[idx].litLength;
+        matchLength = inSeqs[idx].matchLength;
+        ll0 = litLength == 0;
+        offCode = ZSTD_finalizeOffCode(inSeqs[idx].offset, updatedRepcodes.rep, ll0);
+        updatedRepcodes = ZSTD_updateRep(updatedRepcodes.rep, offCode, ll0);
+
+        DEBUGLOG(6, "Storing sequence: (of: %u, ml: %u, ll: %u)", offCode, matchLength, litLength);
+        if (cctx->appliedParams.validateSequences) {
+            seqPos->posInSrc += litLength + matchLength;
+            FORWARD_IF_ERROR(ZSTD_validateSequence(offCode, matchLength, seqPos->posInSrc,
+                                                cctx->appliedParams.cParams.windowLog, dictSize,
+                                                cctx->appliedParams.cParams.minMatch),
+                                                "Sequence validation failed");
+        }
+        RETURN_ERROR_IF(idx - seqPos->idx > cctx->seqStore.maxNbSeq, memory_allocation,
+                        "Not enough memory allocated. Try adjusting ZSTD_c_minMatch.");
+        ZSTD_storeSeq(&cctx->seqStore, litLength, ip, iend, offCode, matchLength - MINMATCH);
+        ip += matchLength + litLength;
+    }
+    ZSTD_memcpy(cctx->blockState.nextCBlock->rep, updatedRepcodes.rep, sizeof(repcodes_t));
+
+    if (inSeqs[idx].litLength) {
+        DEBUGLOG(6, "Storing last literals of size: %u", inSeqs[idx].litLength);
+        ZSTD_storeLastLiterals(&cctx->seqStore, ip, inSeqs[idx].litLength);
+        ip += inSeqs[idx].litLength;
+        seqPos->posInSrc += inSeqs[idx].litLength;
+    }
+    RETURN_ERROR_IF(ip != iend, corruption_detected, "Blocksize doesn't agree with block delimiter!");
+    seqPos->idx = idx+1;
+    return 0;
+}
+
+/* Returns the number of bytes to move the current read position back by. Only non-zero
+ * if we ended up splitting a sequence. Otherwise, it may return a ZSTD error if something
+ * went wrong.
+ *
+ * This function will attempt to scan through blockSize bytes represented by the sequences
+ * in inSeqs, storing any (partial) sequences.
+ *
+ * Occasionally, we may want to change the actual number of bytes we consumed from inSeqs to
+ * avoid splitting a match, or to avoid splitting a match such that it would produce a match
+ * smaller than MINMATCH. In this case, we return the number of bytes that we didn't read from this block.
+ */
+static size_t ZSTD_copySequencesToSeqStoreNoBlockDelim(ZSTD_CCtx* cctx, ZSTD_sequencePosition* seqPos,
+                                                       const ZSTD_Sequence* const inSeqs, size_t inSeqsSize,
+                                                       const void* src, size_t blockSize) {
+    U32 idx = seqPos->idx;
+    U32 startPosInSequence = seqPos->posInSequence;
+    U32 endPosInSequence = seqPos->posInSequence + (U32)blockSize;
+    size_t dictSize;
+    BYTE const* ip = (BYTE const*)(src);
+    BYTE const* iend = ip + blockSize;  /* May be adjusted if we decide to process fewer than blockSize bytes */
+    repcodes_t updatedRepcodes;
+    U32 bytesAdjustment = 0;
+    U32 finalMatchSplit = 0;
+    U32 litLength;
+    U32 matchLength;
+    U32 rawOffset;
+    U32 offCode;
+
+    if (cctx->cdict) {
+        dictSize = cctx->cdict->dictContentSize;
+    } else if (cctx->prefixDict.dict) {
+        dictSize = cctx->prefixDict.dictSize;
+    } else {
+        dictSize = 0;
+    }
+    DEBUGLOG(5, "ZSTD_copySequencesToSeqStore: idx: %u PIS: %u blockSize: %zu", idx, startPosInSequence, blockSize);
+    DEBUGLOG(5, "Start seq: idx: %u (of: %u ml: %u ll: %u)", idx, inSeqs[idx].offset, inSeqs[idx].matchLength, inSeqs[idx].litLength);
+    ZSTD_memcpy(updatedRepcodes.rep, cctx->blockState.prevCBlock->rep, sizeof(repcodes_t));
+    while (endPosInSequence && idx < inSeqsSize && !finalMatchSplit) {
+        const ZSTD_Sequence currSeq = inSeqs[idx];
+        litLength = currSeq.litLength;
+        matchLength = currSeq.matchLength;
+        rawOffset = currSeq.offset;
+
+        /* Modify the sequence depending on where endPosInSequence lies */
+        if (endPosInSequence >= currSeq.litLength + currSeq.matchLength) {
+            if (startPosInSequence >= litLength) {
+                startPosInSequence -= litLength;
+                litLength = 0;
+                matchLength -= startPosInSequence;
+            } else {
+                litLength -= startPosInSequence;
+            }
+            /* Move to the next sequence */
+            endPosInSequence -= currSeq.litLength + currSeq.matchLength;
+            startPosInSequence = 0;
+            idx++;
+        } else {
+            /* This is the final (partial) sequence we're adding from inSeqs, and endPosInSequence
+               does not reach the end of the match. So, we have to split the sequence */
+            DEBUGLOG(6, "Require a split: diff: %u, idx: %u PIS: %u",
+                     currSeq.litLength + currSeq.matchLength - endPosInSequence, idx, endPosInSequence);
+            if (endPosInSequence > litLength) {
+                U32 firstHalfMatchLength;
+                litLength = startPosInSequence >= litLength ? 0 : litLength - startPosInSequence;
+                firstHalfMatchLength = endPosInSequence - startPosInSequence - litLength;
+                if (matchLength > blockSize && firstHalfMatchLength >= cctx->appliedParams.cParams.minMatch) {
+                    /* Only ever split the match if it is larger than the block size */
+                    U32 secondHalfMatchLength = currSeq.matchLength + currSeq.litLength - endPosInSequence;
+                    if (secondHalfMatchLength < cctx->appliedParams.cParams.minMatch) {
+                        /* Move the endPosInSequence backward so that it creates match of minMatch length */
+                        endPosInSequence -= cctx->appliedParams.cParams.minMatch - secondHalfMatchLength;
+                        bytesAdjustment = cctx->appliedParams.cParams.minMatch - secondHalfMatchLength;
+                        firstHalfMatchLength -= bytesAdjustment;
+                    }
+                    matchLength = firstHalfMatchLength;
+                    /* Flag that we split the last match - after storing the sequence, exit the loop,
+                       but keep the value of endPosInSequence */
+                    finalMatchSplit = 1;
+                } else {
+                    /* Move the position in sequence backwards so that we don't split match, and break to store
+                     * the last literals. We use the original currSeq.litLength as a marker for where endPosInSequence
+                     * should go. We prefer to do this whenever it is not necessary to split the match, or if doing so
+                     * would cause the first half of the match to be too small
+                     */
+                    bytesAdjustment = endPosInSequence - currSeq.litLength;
+                    endPosInSequence = currSeq.litLength;
+                    break;
+                }
+            } else {
+                /* This sequence ends inside the literals, break to store the last literals */
+                break;
+            }
+        }
+        /* Check if this offset can be represented with a repcode */
+        {   U32 ll0 = (litLength == 0);
+            offCode = ZSTD_finalizeOffCode(rawOffset, updatedRepcodes.rep, ll0);
+            updatedRepcodes = ZSTD_updateRep(updatedRepcodes.rep, offCode, ll0);
+        }
+
+        if (cctx->appliedParams.validateSequences) {
+            seqPos->posInSrc += litLength + matchLength;
+            FORWARD_IF_ERROR(ZSTD_validateSequence(offCode, matchLength, seqPos->posInSrc,
+                                                   cctx->appliedParams.cParams.windowLog, dictSize,
+                                                   cctx->appliedParams.cParams.minMatch),
+                                                   "Sequence validation failed");
+        }
+        DEBUGLOG(6, "Storing sequence: (of: %u, ml: %u, ll: %u)", offCode, matchLength, litLength);
+        RETURN_ERROR_IF(idx - seqPos->idx > cctx->seqStore.maxNbSeq, memory_allocation,
+                        "Not enough memory allocated. Try adjusting ZSTD_c_minMatch.");
+        ZSTD_storeSeq(&cctx->seqStore, litLength, ip, iend, offCode, matchLength - MINMATCH);
+        ip += matchLength + litLength;
+    }
+    DEBUGLOG(5, "Ending seq: idx: %u (of: %u ml: %u ll: %u)", idx, inSeqs[idx].offset, inSeqs[idx].matchLength, inSeqs[idx].litLength);
+    assert(idx == inSeqsSize || endPosInSequence <= inSeqs[idx].litLength + inSeqs[idx].matchLength);
+    seqPos->idx = idx;
+    seqPos->posInSequence = endPosInSequence;
+    ZSTD_memcpy(cctx->blockState.nextCBlock->rep, updatedRepcodes.rep, sizeof(repcodes_t));
+
+    iend -= bytesAdjustment;
+    if (ip != iend) {
+        /* Store any last literals */
+        U32 lastLLSize = (U32)(iend - ip);
+        assert(ip <= iend);
+        DEBUGLOG(6, "Storing last literals of size: %u", lastLLSize);
+        ZSTD_storeLastLiterals(&cctx->seqStore, ip, lastLLSize);
+        seqPos->posInSrc += lastLLSize;
+    }
+
+    return bytesAdjustment;
+}
+
+typedef size_t (*ZSTD_sequenceCopier) (ZSTD_CCtx* cctx, ZSTD_sequencePosition* seqPos,
+                                       const ZSTD_Sequence* const inSeqs, size_t inSeqsSize,
+                                       const void* src, size_t blockSize);
+static ZSTD_sequenceCopier ZSTD_selectSequenceCopier(ZSTD_sequenceFormat_e mode) {
+    ZSTD_sequenceCopier sequenceCopier = NULL;
+    assert(ZSTD_cParam_withinBounds(ZSTD_c_blockDelimiters, mode));
+    if (mode == ZSTD_sf_explicitBlockDelimiters) {
+        return ZSTD_copySequencesToSeqStoreExplicitBlockDelim;
+    } else if (mode == ZSTD_sf_noBlockDelimiters) {
+        return ZSTD_copySequencesToSeqStoreNoBlockDelim;
+    }
+    assert(sequenceCopier != NULL);
+    return sequenceCopier;
+}
+
+/* Compress, block-by-block, all of the sequences given.
+ *
+ * Returns the cumulative size of all compressed blocks (including their headers), otherwise a ZSTD error.
+ */
+static size_t ZSTD_compressSequences_internal(ZSTD_CCtx* cctx,
+                                              void* dst, size_t dstCapacity,
+                                              const ZSTD_Sequence* inSeqs, size_t inSeqsSize,
+                                              const void* src, size_t srcSize) {
+    size_t cSize = 0;
+    U32 lastBlock;
+    size_t blockSize;
+    size_t compressedSeqsSize;
+    size_t remaining = srcSize;
+    ZSTD_sequencePosition seqPos = {0, 0, 0};
+
+    BYTE const* ip = (BYTE const*)src;
+    BYTE* op = (BYTE*)dst;
+    ZSTD_sequenceCopier sequenceCopier = ZSTD_selectSequenceCopier(cctx->appliedParams.blockDelimiters);
+
+    DEBUGLOG(4, "ZSTD_compressSequences_internal srcSize: %zu, inSeqsSize: %zu", srcSize, inSeqsSize);
+    /* Special case: empty frame */
+    if (remaining == 0) {
+        U32 const cBlockHeader24 = 1 /* last block */ + (((U32)bt_raw)<<1);
+        RETURN_ERROR_IF(dstCapacity<4, dstSize_tooSmall, "No room for empty frame block header");
+        MEM_writeLE32(op, cBlockHeader24);
+        op += ZSTD_blockHeaderSize;
+        dstCapacity -= ZSTD_blockHeaderSize;
+        cSize += ZSTD_blockHeaderSize;
+    }
+
+    while (remaining) {
+        size_t cBlockSize;
+        size_t additionalByteAdjustment;
+        lastBlock = remaining <= cctx->blockSize;
+        blockSize = lastBlock ? (U32)remaining : (U32)cctx->blockSize;
+        ZSTD_resetSeqStore(&cctx->seqStore);
+        DEBUGLOG(4, "Working on new block. Blocksize: %zu", blockSize);
+
+        additionalByteAdjustment = sequenceCopier(cctx, &seqPos, inSeqs, inSeqsSize, ip, blockSize);
+        FORWARD_IF_ERROR(additionalByteAdjustment, "Bad sequence copy");
+        blockSize -= additionalByteAdjustment;
+
+        /* If blocks are too small, emit as a nocompress block */
+        if (blockSize < MIN_CBLOCK_SIZE+ZSTD_blockHeaderSize+1) {
+            cBlockSize = ZSTD_noCompressBlock(op, dstCapacity, ip, blockSize, lastBlock);
+            FORWARD_IF_ERROR(cBlockSize, "Nocompress block failed");
+            DEBUGLOG(4, "Block too small, writing out nocompress block: cSize: %zu", cBlockSize);
+            cSize += cBlockSize;
+            ip += blockSize;
+            op += cBlockSize;
+            remaining -= blockSize;
+            dstCapacity -= cBlockSize;
+            continue;
+        }
+
+        compressedSeqsSize = ZSTD_entropyCompressSequences(&cctx->seqStore,
+                                &cctx->blockState.prevCBlock->entropy, &cctx->blockState.nextCBlock->entropy,
+                                &cctx->appliedParams,
+                                op + ZSTD_blockHeaderSize /* Leave space for block header */, dstCapacity - ZSTD_blockHeaderSize,
+                                blockSize,
+                                cctx->entropyWorkspace, ENTROPY_WORKSPACE_SIZE /* statically allocated in resetCCtx */,
+                                cctx->bmi2);
+        FORWARD_IF_ERROR(compressedSeqsSize, "Compressing sequences of block failed");
+        DEBUGLOG(4, "Compressed sequences size: %zu", compressedSeqsSize);
+
+        if (!cctx->isFirstBlock &&
+            ZSTD_maybeRLE(&cctx->seqStore) &&
+            ZSTD_isRLE((BYTE const*)src, srcSize)) {
+            /* We don't want to emit our first block as a RLE even if it qualifies because
+            * doing so will cause the decoder (cli only) to throw a "should consume all input error."
+            * This is only an issue for zstd <= v1.4.3
+            */
+            compressedSeqsSize = 1;
+        }
+
+        if (compressedSeqsSize == 0) {
+            /* ZSTD_noCompressBlock writes the block header as well */
+            cBlockSize = ZSTD_noCompressBlock(op, dstCapacity, ip, blockSize, lastBlock);
+            FORWARD_IF_ERROR(cBlockSize, "Nocompress block failed");
+            DEBUGLOG(4, "Writing out nocompress block, size: %zu", cBlockSize);
+        } else if (compressedSeqsSize == 1) {
+            cBlockSize = ZSTD_rleCompressBlock(op, dstCapacity, *ip, blockSize, lastBlock);
+            FORWARD_IF_ERROR(cBlockSize, "RLE compress block failed");
+            DEBUGLOG(4, "Writing out RLE block, size: %zu", cBlockSize);
+        } else {
+            U32 cBlockHeader;
+            /* Error checking and repcodes update */
+            ZSTD_confirmRepcodesAndEntropyTables(cctx);
+            if (cctx->blockState.prevCBlock->entropy.fse.offcode_repeatMode == FSE_repeat_valid)
+                cctx->blockState.prevCBlock->entropy.fse.offcode_repeatMode = FSE_repeat_check;
+
+            /* Write block header into beginning of block*/
+            cBlockHeader = lastBlock + (((U32)bt_compressed)<<1) + (U32)(compressedSeqsSize << 3);
+            MEM_writeLE24(op, cBlockHeader);
+            cBlockSize = ZSTD_blockHeaderSize + compressedSeqsSize;
+            DEBUGLOG(4, "Writing out compressed block, size: %zu", cBlockSize);
+        }
+
+        cSize += cBlockSize;
+        DEBUGLOG(4, "cSize running total: %zu", cSize);
+
+        if (lastBlock) {
+            break;
+        } else {
+            ip += blockSize;
+            op += cBlockSize;
+            remaining -= blockSize;
+            dstCapacity -= cBlockSize;
+            cctx->isFirstBlock = 0;
+        }
+    }
+
+    return cSize;
+}
+
+size_t ZSTD_compressSequences(ZSTD_CCtx* const cctx, void* dst, size_t dstCapacity,
+                              const ZSTD_Sequence* inSeqs, size_t inSeqsSize,
+                              const void* src, size_t srcSize) {
+    BYTE* op = (BYTE*)dst;
+    size_t cSize = 0;
+    size_t compressedBlocksSize = 0;
+    size_t frameHeaderSize = 0;
+
+    /* Transparent initialization stage, same as compressStream2() */
+    DEBUGLOG(3, "ZSTD_compressSequences()");
+    assert(cctx != NULL);
+    FORWARD_IF_ERROR(ZSTD_CCtx_init_compressStream2(cctx, ZSTD_e_end, srcSize), "CCtx initialization failed");
+    /* Begin writing output, starting with frame header */
+    frameHeaderSize = ZSTD_writeFrameHeader(op, dstCapacity, &cctx->appliedParams, srcSize, cctx->dictID);
+    op += frameHeaderSize;
+    dstCapacity -= frameHeaderSize;
+    cSize += frameHeaderSize;
+    if (cctx->appliedParams.fParams.checksumFlag && srcSize) {
+        xxh64_update(&cctx->xxhState, src, srcSize);
+    }
+    /* cSize includes block header size and compressed sequences size */
+    compressedBlocksSize = ZSTD_compressSequences_internal(cctx,
+                                                           op, dstCapacity,
+                                                           inSeqs, inSeqsSize,
+                                                           src, srcSize);
+    FORWARD_IF_ERROR(compressedBlocksSize, "Compressing blocks failed!");
+    cSize += compressedBlocksSize;
+    dstCapacity -= compressedBlocksSize;
+
+    if (cctx->appliedParams.fParams.checksumFlag) {
+        U32 const checksum = (U32) xxh64_digest(&cctx->xxhState);
+        RETURN_ERROR_IF(dstCapacity<4, dstSize_tooSmall, "no room for checksum");
+        DEBUGLOG(4, "Write checksum : %08X", (unsigned)checksum);
+        MEM_writeLE32((char*)dst + cSize, checksum);
+        cSize += 4;
+    }
+
+    DEBUGLOG(3, "Final compressed size: %zu", cSize);
+    return cSize;
+}
+
+/*======   Finalize   ======*/
+
+/*! ZSTD_flushStream() :
+ * @return : amount of data remaining to flush */
+size_t ZSTD_flushStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output)
+{
+    ZSTD_inBuffer input = { NULL, 0, 0 };
+    return ZSTD_compressStream2(zcs, output, &input, ZSTD_e_flush);
+}
+
+
+size_t ZSTD_endStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output)
+{
+    ZSTD_inBuffer input = { NULL, 0, 0 };
+    size_t const remainingToFlush = ZSTD_compressStream2(zcs, output, &input, ZSTD_e_end);
+    FORWARD_IF_ERROR( remainingToFlush , "ZSTD_compressStream2 failed");
+    if (zcs->appliedParams.nbWorkers > 0) return remainingToFlush;   /* minimal estimation */
+    /* single thread mode : attempt to calculate remaining to flush more precisely */
+    {   size_t const lastBlockSize = zcs->frameEnded ? 0 : ZSTD_BLOCKHEADERSIZE;
+        size_t const checksumSize = (size_t)(zcs->frameEnded ? 0 : zcs->appliedParams.fParams.checksumFlag * 4);
+        size_t const toFlush = remainingToFlush + lastBlockSize + checksumSize;
+        DEBUGLOG(4, "ZSTD_endStream : remaining to flush : %u", (unsigned)toFlush);
+        return toFlush;
+    }
+}
+
+
+/*-=====  Pre-defined compression levels  =====-*/
+
+#define ZSTD_MAX_CLEVEL     22
+int ZSTD_maxCLevel(void) { return ZSTD_MAX_CLEVEL; }
+int ZSTD_minCLevel(void) { return (int)-ZSTD_TARGETLENGTH_MAX; }
+
+static const ZSTD_compressionParameters ZSTD_defaultCParameters[4][ZSTD_MAX_CLEVEL+1] = {
+{   /* "default" - for any srcSize > 256 KB */
+    /* W,  C,  H,  S,  L, TL, strat */
+    { 19, 12, 13,  1,  6,  1, ZSTD_fast    },  /* base for negative levels */
+    { 19, 13, 14,  1,  7,  0, ZSTD_fast    },  /* level  1 */
+    { 20, 15, 16,  1,  6,  0, ZSTD_fast    },  /* level  2 */
+    { 21, 16, 17,  1,  5,  0, ZSTD_dfast   },  /* level  3 */
+    { 21, 18, 18,  1,  5,  0, ZSTD_dfast   },  /* level  4 */
+    { 21, 18, 19,  2,  5,  2, ZSTD_greedy  },  /* level  5 */
+    { 21, 19, 19,  3,  5,  4, ZSTD_greedy  },  /* level  6 */
+    { 21, 19, 19,  3,  5,  8, ZSTD_lazy    },  /* level  7 */
+    { 21, 19, 19,  3,  5, 16, ZSTD_lazy2   },  /* level  8 */
+    { 21, 19, 20,  4,  5, 16, ZSTD_lazy2   },  /* level  9 */
+    { 22, 20, 21,  4,  5, 16, ZSTD_lazy2   },  /* level 10 */
+    { 22, 21, 22,  4,  5, 16, ZSTD_lazy2   },  /* level 11 */
+    { 22, 21, 22,  5,  5, 16, ZSTD_lazy2   },  /* level 12 */
+    { 22, 21, 22,  5,  5, 32, ZSTD_btlazy2 },  /* level 13 */
+    { 22, 22, 23,  5,  5, 32, ZSTD_btlazy2 },  /* level 14 */
+    { 22, 23, 23,  6,  5, 32, ZSTD_btlazy2 },  /* level 15 */
+    { 22, 22, 22,  5,  5, 48, ZSTD_btopt   },  /* level 16 */
+    { 23, 23, 22,  5,  4, 64, ZSTD_btopt   },  /* level 17 */
+    { 23, 23, 22,  6,  3, 64, ZSTD_btultra },  /* level 18 */
+    { 23, 24, 22,  7,  3,256, ZSTD_btultra2},  /* level 19 */
+    { 25, 25, 23,  7,  3,256, ZSTD_btultra2},  /* level 20 */
+    { 26, 26, 24,  7,  3,512, ZSTD_btultra2},  /* level 21 */
+    { 27, 27, 25,  9,  3,999, ZSTD_btultra2},  /* level 22 */
+},
+{   /* for srcSize <= 256 KB */
+    /* W,  C,  H,  S,  L,  T, strat */
+    { 18, 12, 13,  1,  5,  1, ZSTD_fast    },  /* base for negative levels */
+    { 18, 13, 14,  1,  6,  0, ZSTD_fast    },  /* level  1 */
+    { 18, 14, 14,  1,  5,  0, ZSTD_dfast   },  /* level  2 */
+    { 18, 16, 16,  1,  4,  0, ZSTD_dfast   },  /* level  3 */
+    { 18, 16, 17,  2,  5,  2, ZSTD_greedy  },  /* level  4.*/
+    { 18, 18, 18,  3,  5,  2, ZSTD_greedy  },  /* level  5.*/
+    { 18, 18, 19,  3,  5,  4, ZSTD_lazy    },  /* level  6.*/
+    { 18, 18, 19,  4,  4,  4, ZSTD_lazy    },  /* level  7 */
+    { 18, 18, 19,  4,  4,  8, ZSTD_lazy2   },  /* level  8 */
+    { 18, 18, 19,  5,  4,  8, ZSTD_lazy2   },  /* level  9 */
+    { 18, 18, 19,  6,  4,  8, ZSTD_lazy2   },  /* level 10 */
+    { 18, 18, 19,  5,  4, 12, ZSTD_btlazy2 },  /* level 11.*/
+    { 18, 19, 19,  7,  4, 12, ZSTD_btlazy2 },  /* level 12.*/
+    { 18, 18, 19,  4,  4, 16, ZSTD_btopt   },  /* level 13 */
+    { 18, 18, 19,  4,  3, 32, ZSTD_btopt   },  /* level 14.*/
+    { 18, 18, 19,  6,  3,128, ZSTD_btopt   },  /* level 15.*/
+    { 18, 19, 19,  6,  3,128, ZSTD_btultra },  /* level 16.*/
+    { 18, 19, 19,  8,  3,256, ZSTD_btultra },  /* level 17.*/
+    { 18, 19, 19,  6,  3,128, ZSTD_btultra2},  /* level 18.*/
+    { 18, 19, 19,  8,  3,256, ZSTD_btultra2},  /* level 19.*/
+    { 18, 19, 19, 10,  3,512, ZSTD_btultra2},  /* level 20.*/
+    { 18, 19, 19, 12,  3,512, ZSTD_btultra2},  /* level 21.*/
+    { 18, 19, 19, 13,  3,999, ZSTD_btultra2},  /* level 22.*/
+},
+{   /* for srcSize <= 128 KB */
+    /* W,  C,  H,  S,  L,  T, strat */
+    { 17, 12, 12,  1,  5,  1, ZSTD_fast    },  /* base for negative levels */
+    { 17, 12, 13,  1,  6,  0, ZSTD_fast    },  /* level  1 */
+    { 17, 13, 15,  1,  5,  0, ZSTD_fast    },  /* level  2 */
+    { 17, 15, 16,  2,  5,  0, ZSTD_dfast   },  /* level  3 */
+    { 17, 17, 17,  2,  4,  0, ZSTD_dfast   },  /* level  4 */
+    { 17, 16, 17,  3,  4,  2, ZSTD_greedy  },  /* level  5 */
+    { 17, 17, 17,  3,  4,  4, ZSTD_lazy    },  /* level  6 */
+    { 17, 17, 17,  3,  4,  8, ZSTD_lazy2   },  /* level  7 */
+    { 17, 17, 17,  4,  4,  8, ZSTD_lazy2   },  /* level  8 */
+    { 17, 17, 17,  5,  4,  8, ZSTD_lazy2   },  /* level  9 */
+    { 17, 17, 17,  6,  4,  8, ZSTD_lazy2   },  /* level 10 */
+    { 17, 17, 17,  5,  4,  8, ZSTD_btlazy2 },  /* level 11 */
+    { 17, 18, 17,  7,  4, 12, ZSTD_btlazy2 },  /* level 12 */
+    { 17, 18, 17,  3,  4, 12, ZSTD_btopt   },  /* level 13.*/
+    { 17, 18, 17,  4,  3, 32, ZSTD_btopt   },  /* level 14.*/
+    { 17, 18, 17,  6,  3,256, ZSTD_btopt   },  /* level 15.*/
+    { 17, 18, 17,  6,  3,128, ZSTD_btultra },  /* level 16.*/
+    { 17, 18, 17,  8,  3,256, ZSTD_btultra },  /* level 17.*/
+    { 17, 18, 17, 10,  3,512, ZSTD_btultra },  /* level 18.*/
+    { 17, 18, 17,  5,  3,256, ZSTD_btultra2},  /* level 19.*/
+    { 17, 18, 17,  7,  3,512, ZSTD_btultra2},  /* level 20.*/
+    { 17, 18, 17,  9,  3,512, ZSTD_btultra2},  /* level 21.*/
+    { 17, 18, 17, 11,  3,999, ZSTD_btultra2},  /* level 22.*/
+},
+{   /* for srcSize <= 16 KB */
+    /* W,  C,  H,  S,  L,  T, strat */
+    { 14, 12, 13,  1,  5,  1, ZSTD_fast    },  /* base for negative levels */
+    { 14, 14, 15,  1,  5,  0, ZSTD_fast    },  /* level  1 */
+    { 14, 14, 15,  1,  4,  0, ZSTD_fast    },  /* level  2 */
+    { 14, 14, 15,  2,  4,  0, ZSTD_dfast   },  /* level  3 */
+    { 14, 14, 14,  4,  4,  2, ZSTD_greedy  },  /* level  4 */
+    { 14, 14, 14,  3,  4,  4, ZSTD_lazy    },  /* level  5.*/
+    { 14, 14, 14,  4,  4,  8, ZSTD_lazy2   },  /* level  6 */
+    { 14, 14, 14,  6,  4,  8, ZSTD_lazy2   },  /* level  7 */
+    { 14, 14, 14,  8,  4,  8, ZSTD_lazy2   },  /* level  8.*/
+    { 14, 15, 14,  5,  4,  8, ZSTD_btlazy2 },  /* level  9.*/
+    { 14, 15, 14,  9,  4,  8, ZSTD_btlazy2 },  /* level 10.*/
+    { 14, 15, 14,  3,  4, 12, ZSTD_btopt   },  /* level 11.*/
+    { 14, 15, 14,  4,  3, 24, ZSTD_btopt   },  /* level 12.*/
+    { 14, 15, 14,  5,  3, 32, ZSTD_btultra },  /* level 13.*/
+    { 14, 15, 15,  6,  3, 64, ZSTD_btultra },  /* level 14.*/
+    { 14, 15, 15,  7,  3,256, ZSTD_btultra },  /* level 15.*/
+    { 14, 15, 15,  5,  3, 48, ZSTD_btultra2},  /* level 16.*/
+    { 14, 15, 15,  6,  3,128, ZSTD_btultra2},  /* level 17.*/
+    { 14, 15, 15,  7,  3,256, ZSTD_btultra2},  /* level 18.*/
+    { 14, 15, 15,  8,  3,256, ZSTD_btultra2},  /* level 19.*/
+    { 14, 15, 15,  8,  3,512, ZSTD_btultra2},  /* level 20.*/
+    { 14, 15, 15,  9,  3,512, ZSTD_btultra2},  /* level 21.*/
+    { 14, 15, 15, 10,  3,999, ZSTD_btultra2},  /* level 22.*/
+},
+};
+
+static ZSTD_compressionParameters ZSTD_dedicatedDictSearch_getCParams(int const compressionLevel, size_t const dictSize)
+{
+    ZSTD_compressionParameters cParams = ZSTD_getCParams_internal(compressionLevel, 0, dictSize, ZSTD_cpm_createCDict);
+    switch (cParams.strategy) {
+        case ZSTD_fast:
+        case ZSTD_dfast:
+            break;
+        case ZSTD_greedy:
+        case ZSTD_lazy:
+        case ZSTD_lazy2:
+            cParams.hashLog += ZSTD_LAZY_DDSS_BUCKET_LOG;
+            break;
+        case ZSTD_btlazy2:
+        case ZSTD_btopt:
+        case ZSTD_btultra:
+        case ZSTD_btultra2:
+            break;
+    }
+    return cParams;
+}
+
+static int ZSTD_dedicatedDictSearch_isSupported(
+        ZSTD_compressionParameters const* cParams)
+{
+    return (cParams->strategy >= ZSTD_greedy)
+        && (cParams->strategy <= ZSTD_lazy2)
+        && (cParams->hashLog >= cParams->chainLog)
+        && (cParams->chainLog <= 24);
+}
+
+/*
+ * Reverses the adjustment applied to cparams when enabling dedicated dict
+ * search. This is used to recover the params set to be used in the working
+ * context. (Otherwise, those tables would also grow.)
+ */
+static void ZSTD_dedicatedDictSearch_revertCParams(
+        ZSTD_compressionParameters* cParams) {
+    switch (cParams->strategy) {
+        case ZSTD_fast:
+        case ZSTD_dfast:
+            break;
+        case ZSTD_greedy:
+        case ZSTD_lazy:
+        case ZSTD_lazy2:
+            cParams->hashLog -= ZSTD_LAZY_DDSS_BUCKET_LOG;
+            break;
+        case ZSTD_btlazy2:
+        case ZSTD_btopt:
+        case ZSTD_btultra:
+        case ZSTD_btultra2:
+            break;
+    }
+}
+
+static U64 ZSTD_getCParamRowSize(U64 srcSizeHint, size_t dictSize, ZSTD_cParamMode_e mode)
+{
+    switch (mode) {
+    case ZSTD_cpm_unknown:
+    case ZSTD_cpm_noAttachDict:
+    case ZSTD_cpm_createCDict:
+        break;
+    case ZSTD_cpm_attachDict:
+        dictSize = 0;
+        break;
+    default:
+        assert(0);
+        break;
+    }
+    {   int const unknown = srcSizeHint == ZSTD_CONTENTSIZE_UNKNOWN;
+        size_t const addedSize = unknown && dictSize > 0 ? 500 : 0;
+        return unknown && dictSize == 0 ? ZSTD_CONTENTSIZE_UNKNOWN : srcSizeHint+dictSize+addedSize;
+    }
+}
+
+/*! ZSTD_getCParams_internal() :
+ * @return ZSTD_compressionParameters structure for a selected compression level, srcSize and dictSize.
+ *  Note: srcSizeHint 0 means 0, use ZSTD_CONTENTSIZE_UNKNOWN for unknown.
+ *        Use dictSize == 0 for unknown or unused.
+ *  Note: `mode` controls how we treat the `dictSize`. See docs for `ZSTD_cParamMode_e`. */
+static ZSTD_compressionParameters ZSTD_getCParams_internal(int compressionLevel, unsigned long long srcSizeHint, size_t dictSize, ZSTD_cParamMode_e mode)
+{
+    U64 const rSize = ZSTD_getCParamRowSize(srcSizeHint, dictSize, mode);
+    U32 const tableID = (rSize <= 256 KB) + (rSize <= 128 KB) + (rSize <= 16 KB);
+    int row;
+    DEBUGLOG(5, "ZSTD_getCParams_internal (cLevel=%i)", compressionLevel);
+
+    /* row */
+    if (compressionLevel == 0) row = ZSTD_CLEVEL_DEFAULT;   /* 0 == default */
+    else if (compressionLevel < 0) row = 0;   /* entry 0 is baseline for fast mode */
+    else if (compressionLevel > ZSTD_MAX_CLEVEL) row = ZSTD_MAX_CLEVEL;
+    else row = compressionLevel;
+
+    {   ZSTD_compressionParameters cp = ZSTD_defaultCParameters[tableID][row];
+        /* acceleration factor */
+        if (compressionLevel < 0) {
+            int const clampedCompressionLevel = MAX(ZSTD_minCLevel(), compressionLevel);
+            cp.targetLength = (unsigned)(-clampedCompressionLevel);
+        }
+        /* refine parameters based on srcSize & dictSize */
+        return ZSTD_adjustCParams_internal(cp, srcSizeHint, dictSize, mode);
+    }
+}
+
+/*! ZSTD_getCParams() :
+ * @return ZSTD_compressionParameters structure for a selected compression level, srcSize and dictSize.
+ *  Size values are optional, provide 0 if not known or unused */
+ZSTD_compressionParameters ZSTD_getCParams(int compressionLevel, unsigned long long srcSizeHint, size_t dictSize)
+{
+    if (srcSizeHint == 0) srcSizeHint = ZSTD_CONTENTSIZE_UNKNOWN;
+    return ZSTD_getCParams_internal(compressionLevel, srcSizeHint, dictSize, ZSTD_cpm_unknown);
+}
+
+/*! ZSTD_getParams() :
+ *  same idea as ZSTD_getCParams()
+ * @return a `ZSTD_parameters` structure (instead of `ZSTD_compressionParameters`).
+ *  Fields of `ZSTD_frameParameters` are set to default values */
+static ZSTD_parameters ZSTD_getParams_internal(int compressionLevel, unsigned long long srcSizeHint, size_t dictSize, ZSTD_cParamMode_e mode) {
+    ZSTD_parameters params;
+    ZSTD_compressionParameters const cParams = ZSTD_getCParams_internal(compressionLevel, srcSizeHint, dictSize, mode);
+    DEBUGLOG(5, "ZSTD_getParams (cLevel=%i)", compressionLevel);
+    ZSTD_memset(&params, 0, sizeof(params));
+    params.cParams = cParams;
+    params.fParams.contentSizeFlag = 1;
+    return params;
+}
+
+/*! ZSTD_getParams() :
+ *  same idea as ZSTD_getCParams()
+ * @return a `ZSTD_parameters` structure (instead of `ZSTD_compressionParameters`).
+ *  Fields of `ZSTD_frameParameters` are set to default values */
+ZSTD_parameters ZSTD_getParams(int compressionLevel, unsigned long long srcSizeHint, size_t dictSize) {
+    if (srcSizeHint == 0) srcSizeHint = ZSTD_CONTENTSIZE_UNKNOWN;
+    return ZSTD_getParams_internal(compressionLevel, srcSizeHint, dictSize, ZSTD_cpm_unknown);
+}
diff --git a/lib/zstd/compress/zstd_compress_internal.h b/lib/zstd/compress/zstd_compress_internal.h
new file mode 100644
index 000000000000..685d2f996cc2
--- /dev/null
+++ b/lib/zstd/compress/zstd_compress_internal.h
@@ -0,0 +1,1188 @@
+/*
+ * Copyright (c) Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+/* This header contains definitions
+ * that shall **only** be used by modules within lib/compress.
+ */
+
+#ifndef ZSTD_COMPRESS_H
+#define ZSTD_COMPRESS_H
+
+/*-*************************************
+*  Dependencies
+***************************************/
+#include "../common/zstd_internal.h"
+#include "zstd_cwksp.h"
+
+
+/*-*************************************
+*  Constants
+***************************************/
+#define kSearchStrength      8
+#define HASH_READ_SIZE       8
+#define ZSTD_DUBT_UNSORTED_MARK 1   /* For btlazy2 strategy, index ZSTD_DUBT_UNSORTED_MARK==1 means "unsorted".
+                                       It could be confused for a real successor at index "1", if sorted as larger than its predecessor.
+                                       It's not a big deal though : candidate will just be sorted again.
+                                       Additionally, candidate position 1 will be lost.
+                                       But candidate 1 cannot hide a large tree of candidates, so it's a minimal loss.
+                                       The benefit is that ZSTD_DUBT_UNSORTED_MARK cannot be mishandled after table re-use with a different strategy.
+                                       This constant is required by ZSTD_compressBlock_btlazy2() and ZSTD_reduceTable_internal() */
+
+
+/*-*************************************
+*  Context memory management
+***************************************/
+typedef enum { ZSTDcs_created=0, ZSTDcs_init, ZSTDcs_ongoing, ZSTDcs_ending } ZSTD_compressionStage_e;
+typedef enum { zcss_init=0, zcss_load, zcss_flush } ZSTD_cStreamStage;
+
+typedef struct ZSTD_prefixDict_s {
+    const void* dict;
+    size_t dictSize;
+    ZSTD_dictContentType_e dictContentType;
+} ZSTD_prefixDict;
+
+typedef struct {
+    void* dictBuffer;
+    void const* dict;
+    size_t dictSize;
+    ZSTD_dictContentType_e dictContentType;
+    ZSTD_CDict* cdict;
+} ZSTD_localDict;
+
+typedef struct {
+    HUF_CElt CTable[HUF_CTABLE_SIZE_U32(255)];
+    HUF_repeat repeatMode;
+} ZSTD_hufCTables_t;
+
+typedef struct {
+    FSE_CTable offcodeCTable[FSE_CTABLE_SIZE_U32(OffFSELog, MaxOff)];
+    FSE_CTable matchlengthCTable[FSE_CTABLE_SIZE_U32(MLFSELog, MaxML)];
+    FSE_CTable litlengthCTable[FSE_CTABLE_SIZE_U32(LLFSELog, MaxLL)];
+    FSE_repeat offcode_repeatMode;
+    FSE_repeat matchlength_repeatMode;
+    FSE_repeat litlength_repeatMode;
+} ZSTD_fseCTables_t;
+
+typedef struct {
+    ZSTD_hufCTables_t huf;
+    ZSTD_fseCTables_t fse;
+} ZSTD_entropyCTables_t;
+
+typedef struct {
+    U32 off;            /* Offset code (offset + ZSTD_REP_MOVE) for the match */
+    U32 len;            /* Raw length of match */
+} ZSTD_match_t;
+
+typedef struct {
+    U32 offset;         /* Offset of sequence */
+    U32 litLength;      /* Length of literals prior to match */
+    U32 matchLength;    /* Raw length of match */
+} rawSeq;
+
+typedef struct {
+  rawSeq* seq;          /* The start of the sequences */
+  size_t pos;           /* The index in seq where reading stopped. pos <= size. */
+  size_t posInSequence; /* The position within the sequence at seq[pos] where reading
+                           stopped. posInSequence <= seq[pos].litLength + seq[pos].matchLength */
+  size_t size;          /* The number of sequences. <= capacity. */
+  size_t capacity;      /* The capacity starting from `seq` pointer */
+} rawSeqStore_t;
+
+UNUSED_ATTR static const rawSeqStore_t kNullRawSeqStore = {NULL, 0, 0, 0, 0};
+
+typedef struct {
+    int price;
+    U32 off;
+    U32 mlen;
+    U32 litlen;
+    U32 rep[ZSTD_REP_NUM];
+} ZSTD_optimal_t;
+
+typedef enum { zop_dynamic=0, zop_predef } ZSTD_OptPrice_e;
+
+typedef struct {
+    /* All tables are allocated inside cctx->workspace by ZSTD_resetCCtx_internal() */
+    unsigned* litFreq;           /* table of literals statistics, of size 256 */
+    unsigned* litLengthFreq;     /* table of litLength statistics, of size (MaxLL+1) */
+    unsigned* matchLengthFreq;   /* table of matchLength statistics, of size (MaxML+1) */
+    unsigned* offCodeFreq;       /* table of offCode statistics, of size (MaxOff+1) */
+    ZSTD_match_t* matchTable;    /* list of found matches, of size ZSTD_OPT_NUM+1 */
+    ZSTD_optimal_t* priceTable;  /* All positions tracked by optimal parser, of size ZSTD_OPT_NUM+1 */
+
+    U32  litSum;                 /* nb of literals */
+    U32  litLengthSum;           /* nb of litLength codes */
+    U32  matchLengthSum;         /* nb of matchLength codes */
+    U32  offCodeSum;             /* nb of offset codes */
+    U32  litSumBasePrice;        /* to compare to log2(litfreq) */
+    U32  litLengthSumBasePrice;  /* to compare to log2(llfreq)  */
+    U32  matchLengthSumBasePrice;/* to compare to log2(mlfreq)  */
+    U32  offCodeSumBasePrice;    /* to compare to log2(offreq)  */
+    ZSTD_OptPrice_e priceType;   /* prices can be determined dynamically, or follow a pre-defined cost structure */
+    const ZSTD_entropyCTables_t* symbolCosts;  /* pre-calculated dictionary statistics */
+    ZSTD_literalCompressionMode_e literalCompressionMode;
+} optState_t;
+
+typedef struct {
+  ZSTD_entropyCTables_t entropy;
+  U32 rep[ZSTD_REP_NUM];
+} ZSTD_compressedBlockState_t;
+
+typedef struct {
+    BYTE const* nextSrc;    /* next block here to continue on current prefix */
+    BYTE const* base;       /* All regular indexes relative to this position */
+    BYTE const* dictBase;   /* extDict indexes relative to this position */
+    U32 dictLimit;          /* below that point, need extDict */
+    U32 lowLimit;           /* below that point, no more valid data */
+} ZSTD_window_t;
+
+typedef struct ZSTD_matchState_t ZSTD_matchState_t;
+struct ZSTD_matchState_t {
+    ZSTD_window_t window;   /* State for window round buffer management */
+    U32 loadedDictEnd;      /* index of end of dictionary, within context's referential.
+                             * When loadedDictEnd != 0, a dictionary is in use, and still valid.
+                             * This relies on a mechanism to set loadedDictEnd=0 when dictionary is no longer within distance.
+                             * Such mechanism is provided within ZSTD_window_enforceMaxDist() and ZSTD_checkDictValidity().
+                             * When dict referential is copied into active context (i.e. not attached),
+                             * loadedDictEnd == dictSize, since referential starts from zero.
+                             */
+    U32 nextToUpdate;       /* index from which to continue table update */
+    U32 hashLog3;           /* dispatch table for matches of len==3 : larger == faster, more memory */
+    U32* hashTable;
+    U32* hashTable3;
+    U32* chainTable;
+    int dedicatedDictSearch;  /* Indicates whether this matchState is using the
+                               * dedicated dictionary search structure.
+                               */
+    optState_t opt;         /* optimal parser state */
+    const ZSTD_matchState_t* dictMatchState;
+    ZSTD_compressionParameters cParams;
+    const rawSeqStore_t* ldmSeqStore;
+};
+
+typedef struct {
+    ZSTD_compressedBlockState_t* prevCBlock;
+    ZSTD_compressedBlockState_t* nextCBlock;
+    ZSTD_matchState_t matchState;
+} ZSTD_blockState_t;
+
+typedef struct {
+    U32 offset;
+    U32 checksum;
+} ldmEntry_t;
+
+typedef struct {
+    BYTE const* split;
+    U32 hash;
+    U32 checksum;
+    ldmEntry_t* bucket;
+} ldmMatchCandidate_t;
+
+#define LDM_BATCH_SIZE 64
+
+typedef struct {
+    ZSTD_window_t window;   /* State for the window round buffer management */
+    ldmEntry_t* hashTable;
+    U32 loadedDictEnd;
+    BYTE* bucketOffsets;    /* Next position in bucket to insert entry */
+    size_t splitIndices[LDM_BATCH_SIZE];
+    ldmMatchCandidate_t matchCandidates[LDM_BATCH_SIZE];
+} ldmState_t;
+
+typedef struct {
+    U32 enableLdm;          /* 1 if enable long distance matching */
+    U32 hashLog;            /* Log size of hashTable */
+    U32 bucketSizeLog;      /* Log bucket size for collision resolution, at most 8 */
+    U32 minMatchLength;     /* Minimum match length */
+    U32 hashRateLog;       /* Log number of entries to skip */
+    U32 windowLog;          /* Window log for the LDM */
+} ldmParams_t;
+
+typedef struct {
+    int collectSequences;
+    ZSTD_Sequence* seqStart;
+    size_t seqIndex;
+    size_t maxSequences;
+} SeqCollector;
+
+struct ZSTD_CCtx_params_s {
+    ZSTD_format_e format;
+    ZSTD_compressionParameters cParams;
+    ZSTD_frameParameters fParams;
+
+    int compressionLevel;
+    int forceWindow;           /* force back-references to respect limit of
+                                * 1<<wLog, even for dictionary */
+    size_t targetCBlockSize;   /* Tries to fit compressed block size to be around targetCBlockSize.
+                                * No target when targetCBlockSize == 0.
+                                * There is no guarantee on compressed block size */
+    int srcSizeHint;           /* User's best guess of source size.
+                                * Hint is not valid when srcSizeHint == 0.
+                                * There is no guarantee that hint is close to actual source size */
+
+    ZSTD_dictAttachPref_e attachDictPref;
+    ZSTD_literalCompressionMode_e literalCompressionMode;
+
+    /* Multithreading: used to pass parameters to mtctx */
+    int nbWorkers;
+    size_t jobSize;
+    int overlapLog;
+    int rsyncable;
+
+    /* Long distance matching parameters */
+    ldmParams_t ldmParams;
+
+    /* Dedicated dict search algorithm trigger */
+    int enableDedicatedDictSearch;
+
+    /* Input/output buffer modes */
+    ZSTD_bufferMode_e inBufferMode;
+    ZSTD_bufferMode_e outBufferMode;
+
+    /* Sequence compression API */
+    ZSTD_sequenceFormat_e blockDelimiters;
+    int validateSequences;
+
+    /* Internal use, for createCCtxParams() and freeCCtxParams() only */
+    ZSTD_customMem customMem;
+};  /* typedef'd to ZSTD_CCtx_params within "zstd.h" */
+
+#define COMPRESS_SEQUENCES_WORKSPACE_SIZE (sizeof(unsigned) * (MaxSeq + 2))
+#define ENTROPY_WORKSPACE_SIZE (HUF_WORKSPACE_SIZE + COMPRESS_SEQUENCES_WORKSPACE_SIZE)
+
+/*
+ * Indicates whether this compression proceeds directly from user-provided
+ * source buffer to user-provided destination buffer (ZSTDb_not_buffered), or
+ * whether the context needs to buffer the input/output (ZSTDb_buffered).
+ */
+typedef enum {
+    ZSTDb_not_buffered,
+    ZSTDb_buffered
+} ZSTD_buffered_policy_e;
+
+struct ZSTD_CCtx_s {
+    ZSTD_compressionStage_e stage;
+    int cParamsChanged;                  /* == 1 if cParams(except wlog) or compression level are changed in requestedParams. Triggers transmission of new params to ZSTDMT (if available) then reset to 0. */
+    int bmi2;                            /* == 1 if the CPU supports BMI2 and 0 otherwise. CPU support is determined dynamically once per context lifetime. */
+    ZSTD_CCtx_params requestedParams;
+    ZSTD_CCtx_params appliedParams;
+    U32   dictID;
+    size_t dictContentSize;
+
+    ZSTD_cwksp workspace; /* manages buffer for dynamic allocations */
+    size_t blockSize;
+    unsigned long long pledgedSrcSizePlusOne;  /* this way, 0 (default) == unknown */
+    unsigned long long consumedSrcSize;
+    unsigned long long producedCSize;
+    struct xxh64_state xxhState;
+    ZSTD_customMem customMem;
+    ZSTD_threadPool* pool;
+    size_t staticSize;
+    SeqCollector seqCollector;
+    int isFirstBlock;
+    int initialized;
+
+    seqStore_t seqStore;      /* sequences storage ptrs */
+    ldmState_t ldmState;      /* long distance matching state */
+    rawSeq* ldmSequences;     /* Storage for the ldm output sequences */
+    size_t maxNbLdmSequences;
+    rawSeqStore_t externSeqStore; /* Mutable reference to external sequences */
+    ZSTD_blockState_t blockState;
+    U32* entropyWorkspace;  /* entropy workspace of ENTROPY_WORKSPACE_SIZE bytes */
+
+    /* Wether we are streaming or not */
+    ZSTD_buffered_policy_e bufferedPolicy;
+
+    /* streaming */
+    char*  inBuff;
+    size_t inBuffSize;
+    size_t inToCompress;
+    size_t inBuffPos;
+    size_t inBuffTarget;
+    char*  outBuff;
+    size_t outBuffSize;
+    size_t outBuffContentSize;
+    size_t outBuffFlushedSize;
+    ZSTD_cStreamStage streamStage;
+    U32    frameEnded;
+
+    /* Stable in/out buffer verification */
+    ZSTD_inBuffer expectedInBuffer;
+    size_t expectedOutBufferSize;
+
+    /* Dictionary */
+    ZSTD_localDict localDict;
+    const ZSTD_CDict* cdict;
+    ZSTD_prefixDict prefixDict;   /* single-usage dictionary */
+
+    /* Multi-threading */
+
+    /* Tracing */
+};
+
+typedef enum { ZSTD_dtlm_fast, ZSTD_dtlm_full } ZSTD_dictTableLoadMethod_e;
+
+typedef enum {
+    ZSTD_noDict = 0,
+    ZSTD_extDict = 1,
+    ZSTD_dictMatchState = 2,
+    ZSTD_dedicatedDictSearch = 3
+} ZSTD_dictMode_e;
+
+typedef enum {
+    ZSTD_cpm_noAttachDict = 0,  /* Compression with ZSTD_noDict or ZSTD_extDict.
+                                 * In this mode we use both the srcSize and the dictSize
+                                 * when selecting and adjusting parameters.
+                                 */
+    ZSTD_cpm_attachDict = 1,    /* Compression with ZSTD_dictMatchState or ZSTD_dedicatedDictSearch.
+                                 * In this mode we only take the srcSize into account when selecting
+                                 * and adjusting parameters.
+                                 */
+    ZSTD_cpm_createCDict = 2,   /* Creating a CDict.
+                                 * In this mode we take both the source size and the dictionary size
+                                 * into account when selecting and adjusting the parameters.
+                                 */
+    ZSTD_cpm_unknown = 3,       /* ZSTD_getCParams, ZSTD_getParams, ZSTD_adjustParams.
+                                 * We don't know what these parameters are for. We default to the legacy
+                                 * behavior of taking both the source size and the dict size into account
+                                 * when selecting and adjusting parameters.
+                                 */
+} ZSTD_cParamMode_e;
+
+typedef size_t (*ZSTD_blockCompressor) (
+        ZSTD_matchState_t* bs, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize);
+ZSTD_blockCompressor ZSTD_selectBlockCompressor(ZSTD_strategy strat, ZSTD_dictMode_e dictMode);
+
+
+MEM_STATIC U32 ZSTD_LLcode(U32 litLength)
+{
+    static const BYTE LL_Code[64] = {  0,  1,  2,  3,  4,  5,  6,  7,
+                                       8,  9, 10, 11, 12, 13, 14, 15,
+                                      16, 16, 17, 17, 18, 18, 19, 19,
+                                      20, 20, 20, 20, 21, 21, 21, 21,
+                                      22, 22, 22, 22, 22, 22, 22, 22,
+                                      23, 23, 23, 23, 23, 23, 23, 23,
+                                      24, 24, 24, 24, 24, 24, 24, 24,
+                                      24, 24, 24, 24, 24, 24, 24, 24 };
+    static const U32 LL_deltaCode = 19;
+    return (litLength > 63) ? ZSTD_highbit32(litLength) + LL_deltaCode : LL_Code[litLength];
+}
+
+/* ZSTD_MLcode() :
+ * note : mlBase = matchLength - MINMATCH;
+ *        because it's the format it's stored in seqStore->sequences */
+MEM_STATIC U32 ZSTD_MLcode(U32 mlBase)
+{
+    static const BYTE ML_Code[128] = { 0,  1,  2,  3,  4,  5,  6,  7,  8,  9, 10, 11, 12, 13, 14, 15,
+                                      16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31,
+                                      32, 32, 33, 33, 34, 34, 35, 35, 36, 36, 36, 36, 37, 37, 37, 37,
+                                      38, 38, 38, 38, 38, 38, 38, 38, 39, 39, 39, 39, 39, 39, 39, 39,
+                                      40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40,
+                                      41, 41, 41, 41, 41, 41, 41, 41, 41, 41, 41, 41, 41, 41, 41, 41,
+                                      42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42,
+                                      42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42 };
+    static const U32 ML_deltaCode = 36;
+    return (mlBase > 127) ? ZSTD_highbit32(mlBase) + ML_deltaCode : ML_Code[mlBase];
+}
+
+typedef struct repcodes_s {
+    U32 rep[3];
+} repcodes_t;
+
+MEM_STATIC repcodes_t ZSTD_updateRep(U32 const rep[3], U32 const offset, U32 const ll0)
+{
+    repcodes_t newReps;
+    if (offset >= ZSTD_REP_NUM) {  /* full offset */
+        newReps.rep[2] = rep[1];
+        newReps.rep[1] = rep[0];
+        newReps.rep[0] = offset - ZSTD_REP_MOVE;
+    } else {   /* repcode */
+        U32 const repCode = offset + ll0;
+        if (repCode > 0) {  /* note : if repCode==0, no change */
+            U32 const currentOffset = (repCode==ZSTD_REP_NUM) ? (rep[0] - 1) : rep[repCode];
+            newReps.rep[2] = (repCode >= 2) ? rep[1] : rep[2];
+            newReps.rep[1] = rep[0];
+            newReps.rep[0] = currentOffset;
+        } else {   /* repCode == 0 */
+            ZSTD_memcpy(&newReps, rep, sizeof(newReps));
+        }
+    }
+    return newReps;
+}
+
+/* ZSTD_cParam_withinBounds:
+ * @return 1 if value is within cParam bounds,
+ * 0 otherwise */
+MEM_STATIC int ZSTD_cParam_withinBounds(ZSTD_cParameter cParam, int value)
+{
+    ZSTD_bounds const bounds = ZSTD_cParam_getBounds(cParam);
+    if (ZSTD_isError(bounds.error)) return 0;
+    if (value < bounds.lowerBound) return 0;
+    if (value > bounds.upperBound) return 0;
+    return 1;
+}
+
+/* ZSTD_noCompressBlock() :
+ * Writes uncompressed block to dst buffer from given src.
+ * Returns the size of the block */
+MEM_STATIC size_t ZSTD_noCompressBlock (void* dst, size_t dstCapacity, const void* src, size_t srcSize, U32 lastBlock)
+{
+    U32 const cBlockHeader24 = lastBlock + (((U32)bt_raw)<<1) + (U32)(srcSize << 3);
+    RETURN_ERROR_IF(srcSize + ZSTD_blockHeaderSize > dstCapacity,
+                    dstSize_tooSmall, "dst buf too small for uncompressed block");
+    MEM_writeLE24(dst, cBlockHeader24);
+    ZSTD_memcpy((BYTE*)dst + ZSTD_blockHeaderSize, src, srcSize);
+    return ZSTD_blockHeaderSize + srcSize;
+}
+
+MEM_STATIC size_t ZSTD_rleCompressBlock (void* dst, size_t dstCapacity, BYTE src, size_t srcSize, U32 lastBlock)
+{
+    BYTE* const op = (BYTE*)dst;
+    U32 const cBlockHeader = lastBlock + (((U32)bt_rle)<<1) + (U32)(srcSize << 3);
+    RETURN_ERROR_IF(dstCapacity < 4, dstSize_tooSmall, "");
+    MEM_writeLE24(op, cBlockHeader);
+    op[3] = src;
+    return 4;
+}
+
+
+/* ZSTD_minGain() :
+ * minimum compression required
+ * to generate a compress block or a compressed literals section.
+ * note : use same formula for both situations */
+MEM_STATIC size_t ZSTD_minGain(size_t srcSize, ZSTD_strategy strat)
+{
+    U32 const minlog = (strat>=ZSTD_btultra) ? (U32)(strat) - 1 : 6;
+    ZSTD_STATIC_ASSERT(ZSTD_btultra == 8);
+    assert(ZSTD_cParam_withinBounds(ZSTD_c_strategy, strat));
+    return (srcSize >> minlog) + 2;
+}
+
+MEM_STATIC int ZSTD_disableLiteralsCompression(const ZSTD_CCtx_params* cctxParams)
+{
+    switch (cctxParams->literalCompressionMode) {
+    case ZSTD_lcm_huffman:
+        return 0;
+    case ZSTD_lcm_uncompressed:
+        return 1;
+    default:
+        assert(0 /* impossible: pre-validated */);
+        ZSTD_FALLTHROUGH;
+    case ZSTD_lcm_auto:
+        return (cctxParams->cParams.strategy == ZSTD_fast) && (cctxParams->cParams.targetLength > 0);
+    }
+}
+
+/*! ZSTD_safecopyLiterals() :
+ *  memcpy() function that won't read beyond more than WILDCOPY_OVERLENGTH bytes past ilimit_w.
+ *  Only called when the sequence ends past ilimit_w, so it only needs to be optimized for single
+ *  large copies.
+ */
+static void ZSTD_safecopyLiterals(BYTE* op, BYTE const* ip, BYTE const* const iend, BYTE const* ilimit_w) {
+    assert(iend > ilimit_w);
+    if (ip <= ilimit_w) {
+        ZSTD_wildcopy(op, ip, ilimit_w - ip, ZSTD_no_overlap);
+        op += ilimit_w - ip;
+        ip = ilimit_w;
+    }
+    while (ip < iend) *op++ = *ip++;
+}
+
+/*! ZSTD_storeSeq() :
+ *  Store a sequence (litlen, litPtr, offCode and mlBase) into seqStore_t.
+ *  `offCode` : distance to match + ZSTD_REP_MOVE (values <= ZSTD_REP_MOVE are repCodes).
+ *  `mlBase` : matchLength - MINMATCH
+ *  Allowed to overread literals up to litLimit.
+*/
+HINT_INLINE UNUSED_ATTR
+void ZSTD_storeSeq(seqStore_t* seqStorePtr, size_t litLength, const BYTE* literals, const BYTE* litLimit, U32 offCode, size_t mlBase)
+{
+    BYTE const* const litLimit_w = litLimit - WILDCOPY_OVERLENGTH;
+    BYTE const* const litEnd = literals + litLength;
+#if defined(DEBUGLEVEL) && (DEBUGLEVEL >= 6)
+    static const BYTE* g_start = NULL;
+    if (g_start==NULL) g_start = (const BYTE*)literals;  /* note : index only works for compression within a single segment */
+    {   U32 const pos = (U32)((const BYTE*)literals - g_start);
+        DEBUGLOG(6, "Cpos%7u :%3u literals, match%4u bytes at offCode%7u",
+               pos, (U32)litLength, (U32)mlBase+MINMATCH, (U32)offCode);
+    }
+#endif
+    assert((size_t)(seqStorePtr->sequences - seqStorePtr->sequencesStart) < seqStorePtr->maxNbSeq);
+    /* copy Literals */
+    assert(seqStorePtr->maxNbLit <= 128 KB);
+    assert(seqStorePtr->lit + litLength <= seqStorePtr->litStart + seqStorePtr->maxNbLit);
+    assert(literals + litLength <= litLimit);
+    if (litEnd <= litLimit_w) {
+        /* Common case we can use wildcopy.
+	 * First copy 16 bytes, because literals are likely short.
+	 */
+        assert(WILDCOPY_OVERLENGTH >= 16);
+        ZSTD_copy16(seqStorePtr->lit, literals);
+        if (litLength > 16) {
+            ZSTD_wildcopy(seqStorePtr->lit+16, literals+16, (ptrdiff_t)litLength-16, ZSTD_no_overlap);
+        }
+    } else {
+        ZSTD_safecopyLiterals(seqStorePtr->lit, literals, litEnd, litLimit_w);
+    }
+    seqStorePtr->lit += litLength;
+
+    /* literal Length */
+    if (litLength>0xFFFF) {
+        assert(seqStorePtr->longLengthID == 0); /* there can only be a single long length */
+        seqStorePtr->longLengthID = 1;
+        seqStorePtr->longLengthPos = (U32)(seqStorePtr->sequences - seqStorePtr->sequencesStart);
+    }
+    seqStorePtr->sequences[0].litLength = (U16)litLength;
+
+    /* match offset */
+    seqStorePtr->sequences[0].offset = offCode + 1;
+
+    /* match Length */
+    if (mlBase>0xFFFF) {
+        assert(seqStorePtr->longLengthID == 0); /* there can only be a single long length */
+        seqStorePtr->longLengthID = 2;
+        seqStorePtr->longLengthPos = (U32)(seqStorePtr->sequences - seqStorePtr->sequencesStart);
+    }
+    seqStorePtr->sequences[0].matchLength = (U16)mlBase;
+
+    seqStorePtr->sequences++;
+}
+
+
+/*-*************************************
+*  Match length counter
+***************************************/
+static unsigned ZSTD_NbCommonBytes (size_t val)
+{
+    if (MEM_isLittleEndian()) {
+        if (MEM_64bits()) {
+#       if (__GNUC__ >= 4)
+            return (__builtin_ctzll((U64)val) >> 3);
+#       else
+            static const int DeBruijnBytePos[64] = { 0, 0, 0, 0, 0, 1, 1, 2,
+                                                     0, 3, 1, 3, 1, 4, 2, 7,
+                                                     0, 2, 3, 6, 1, 5, 3, 5,
+                                                     1, 3, 4, 4, 2, 5, 6, 7,
+                                                     7, 0, 1, 2, 3, 3, 4, 6,
+                                                     2, 6, 5, 5, 3, 4, 5, 6,
+                                                     7, 1, 2, 4, 6, 4, 4, 5,
+                                                     7, 2, 6, 5, 7, 6, 7, 7 };
+            return DeBruijnBytePos[((U64)((val & -(long long)val) * 0x0218A392CDABBD3FULL)) >> 58];
+#       endif
+        } else { /* 32 bits */
+#       if (__GNUC__ >= 3)
+            return (__builtin_ctz((U32)val) >> 3);
+#       else
+            static const int DeBruijnBytePos[32] = { 0, 0, 3, 0, 3, 1, 3, 0,
+                                                     3, 2, 2, 1, 3, 2, 0, 1,
+                                                     3, 3, 1, 2, 2, 2, 2, 0,
+                                                     3, 1, 2, 0, 1, 0, 1, 1 };
+            return DeBruijnBytePos[((U32)((val & -(S32)val) * 0x077CB531U)) >> 27];
+#       endif
+        }
+    } else {  /* Big Endian CPU */
+        if (MEM_64bits()) {
+#       if (__GNUC__ >= 4)
+            return (__builtin_clzll(val) >> 3);
+#       else
+            unsigned r;
+            const unsigned n32 = sizeof(size_t)*4;   /* calculate this way due to compiler complaining in 32-bits mode */
+            if (!(val>>n32)) { r=4; } else { r=0; val>>=n32; }
+            if (!(val>>16)) { r+=2; val>>=8; } else { val>>=24; }
+            r += (!val);
+            return r;
+#       endif
+        } else { /* 32 bits */
+#       if (__GNUC__ >= 3)
+            return (__builtin_clz((U32)val) >> 3);
+#       else
+            unsigned r;
+            if (!(val>>16)) { r=2; val>>=8; } else { r=0; val>>=24; }
+            r += (!val);
+            return r;
+#       endif
+    }   }
+}
+
+
+MEM_STATIC size_t ZSTD_count(const BYTE* pIn, const BYTE* pMatch, const BYTE* const pInLimit)
+{
+    const BYTE* const pStart = pIn;
+    const BYTE* const pInLoopLimit = pInLimit - (sizeof(size_t)-1);
+
+    if (pIn < pInLoopLimit) {
+        { size_t const diff = MEM_readST(pMatch) ^ MEM_readST(pIn);
+          if (diff) return ZSTD_NbCommonBytes(diff); }
+        pIn+=sizeof(size_t); pMatch+=sizeof(size_t);
+        while (pIn < pInLoopLimit) {
+            size_t const diff = MEM_readST(pMatch) ^ MEM_readST(pIn);
+            if (!diff) { pIn+=sizeof(size_t); pMatch+=sizeof(size_t); continue; }
+            pIn += ZSTD_NbCommonBytes(diff);
+            return (size_t)(pIn - pStart);
+    }   }
+    if (MEM_64bits() && (pIn<(pInLimit-3)) && (MEM_read32(pMatch) == MEM_read32(pIn))) { pIn+=4; pMatch+=4; }
+    if ((pIn<(pInLimit-1)) && (MEM_read16(pMatch) == MEM_read16(pIn))) { pIn+=2; pMatch+=2; }
+    if ((pIn<pInLimit) && (*pMatch == *pIn)) pIn++;
+    return (size_t)(pIn - pStart);
+}
+
+/* ZSTD_count_2segments() :
+ *  can count match length with `ip` & `match` in 2 different segments.
+ *  convention : on reaching mEnd, match count continue starting from iStart
+ */
+MEM_STATIC size_t
+ZSTD_count_2segments(const BYTE* ip, const BYTE* match,
+                     const BYTE* iEnd, const BYTE* mEnd, const BYTE* iStart)
+{
+    const BYTE* const vEnd = MIN( ip + (mEnd - match), iEnd);
+    size_t const matchLength = ZSTD_count(ip, match, vEnd);
+    if (match + matchLength != mEnd) return matchLength;
+    DEBUGLOG(7, "ZSTD_count_2segments: found a 2-parts match (current length==%zu)", matchLength);
+    DEBUGLOG(7, "distance from match beginning to end dictionary = %zi", mEnd - match);
+    DEBUGLOG(7, "distance from current pos to end buffer = %zi", iEnd - ip);
+    DEBUGLOG(7, "next byte : ip==%02X, istart==%02X", ip[matchLength], *iStart);
+    DEBUGLOG(7, "final match length = %zu", matchLength + ZSTD_count(ip+matchLength, iStart, iEnd));
+    return matchLength + ZSTD_count(ip+matchLength, iStart, iEnd);
+}
+
+
+/*-*************************************
+ *  Hashes
+ ***************************************/
+static const U32 prime3bytes = 506832829U;
+static U32    ZSTD_hash3(U32 u, U32 h) { return ((u << (32-24)) * prime3bytes)  >> (32-h) ; }
+MEM_STATIC size_t ZSTD_hash3Ptr(const void* ptr, U32 h) { return ZSTD_hash3(MEM_readLE32(ptr), h); } /* only in zstd_opt.h */
+
+static const U32 prime4bytes = 2654435761U;
+static U32    ZSTD_hash4(U32 u, U32 h) { return (u * prime4bytes) >> (32-h) ; }
+static size_t ZSTD_hash4Ptr(const void* ptr, U32 h) { return ZSTD_hash4(MEM_read32(ptr), h); }
+
+static const U64 prime5bytes = 889523592379ULL;
+static size_t ZSTD_hash5(U64 u, U32 h) { return (size_t)(((u  << (64-40)) * prime5bytes) >> (64-h)) ; }
+static size_t ZSTD_hash5Ptr(const void* p, U32 h) { return ZSTD_hash5(MEM_readLE64(p), h); }
+
+static const U64 prime6bytes = 227718039650203ULL;
+static size_t ZSTD_hash6(U64 u, U32 h) { return (size_t)(((u  << (64-48)) * prime6bytes) >> (64-h)) ; }
+static size_t ZSTD_hash6Ptr(const void* p, U32 h) { return ZSTD_hash6(MEM_readLE64(p), h); }
+
+static const U64 prime7bytes = 58295818150454627ULL;
+static size_t ZSTD_hash7(U64 u, U32 h) { return (size_t)(((u  << (64-56)) * prime7bytes) >> (64-h)) ; }
+static size_t ZSTD_hash7Ptr(const void* p, U32 h) { return ZSTD_hash7(MEM_readLE64(p), h); }
+
+static const U64 prime8bytes = 0xCF1BBCDCB7A56463ULL;
+static size_t ZSTD_hash8(U64 u, U32 h) { return (size_t)(((u) * prime8bytes) >> (64-h)) ; }
+static size_t ZSTD_hash8Ptr(const void* p, U32 h) { return ZSTD_hash8(MEM_readLE64(p), h); }
+
+MEM_STATIC FORCE_INLINE_ATTR
+size_t ZSTD_hashPtr(const void* p, U32 hBits, U32 mls)
+{
+    switch(mls)
+    {
+    default:
+    case 4: return ZSTD_hash4Ptr(p, hBits);
+    case 5: return ZSTD_hash5Ptr(p, hBits);
+    case 6: return ZSTD_hash6Ptr(p, hBits);
+    case 7: return ZSTD_hash7Ptr(p, hBits);
+    case 8: return ZSTD_hash8Ptr(p, hBits);
+    }
+}
+
+/* ZSTD_ipow() :
+ * Return base^exponent.
+ */
+static U64 ZSTD_ipow(U64 base, U64 exponent)
+{
+    U64 power = 1;
+    while (exponent) {
+      if (exponent & 1) power *= base;
+      exponent >>= 1;
+      base *= base;
+    }
+    return power;
+}
+
+#define ZSTD_ROLL_HASH_CHAR_OFFSET 10
+
+/* ZSTD_rollingHash_append() :
+ * Add the buffer to the hash value.
+ */
+static U64 ZSTD_rollingHash_append(U64 hash, void const* buf, size_t size)
+{
+    BYTE const* istart = (BYTE const*)buf;
+    size_t pos;
+    for (pos = 0; pos < size; ++pos) {
+        hash *= prime8bytes;
+        hash += istart[pos] + ZSTD_ROLL_HASH_CHAR_OFFSET;
+    }
+    return hash;
+}
+
+/* ZSTD_rollingHash_compute() :
+ * Compute the rolling hash value of the buffer.
+ */
+MEM_STATIC U64 ZSTD_rollingHash_compute(void const* buf, size_t size)
+{
+    return ZSTD_rollingHash_append(0, buf, size);
+}
+
+/* ZSTD_rollingHash_primePower() :
+ * Compute the primePower to be passed to ZSTD_rollingHash_rotate() for a hash
+ * over a window of length bytes.
+ */
+MEM_STATIC U64 ZSTD_rollingHash_primePower(U32 length)
+{
+    return ZSTD_ipow(prime8bytes, length - 1);
+}
+
+/* ZSTD_rollingHash_rotate() :
+ * Rotate the rolling hash by one byte.
+ */
+MEM_STATIC U64 ZSTD_rollingHash_rotate(U64 hash, BYTE toRemove, BYTE toAdd, U64 primePower)
+{
+    hash -= (toRemove + ZSTD_ROLL_HASH_CHAR_OFFSET) * primePower;
+    hash *= prime8bytes;
+    hash += toAdd + ZSTD_ROLL_HASH_CHAR_OFFSET;
+    return hash;
+}
+
+/*-*************************************
+*  Round buffer management
+***************************************/
+#if (ZSTD_WINDOWLOG_MAX_64 > 31)
+# error "ZSTD_WINDOWLOG_MAX is too large : would overflow ZSTD_CURRENT_MAX"
+#endif
+/* Max current allowed */
+#define ZSTD_CURRENT_MAX ((3U << 29) + (1U << ZSTD_WINDOWLOG_MAX))
+/* Maximum chunk size before overflow correction needs to be called again */
+#define ZSTD_CHUNKSIZE_MAX                                                     \
+    ( ((U32)-1)                  /* Maximum ending current index */            \
+    - ZSTD_CURRENT_MAX)          /* Maximum beginning lowLimit */
+
+/*
+ * ZSTD_window_clear():
+ * Clears the window containing the history by simply setting it to empty.
+ */
+MEM_STATIC void ZSTD_window_clear(ZSTD_window_t* window)
+{
+    size_t const endT = (size_t)(window->nextSrc - window->base);
+    U32 const end = (U32)endT;
+
+    window->lowLimit = end;
+    window->dictLimit = end;
+}
+
+/*
+ * ZSTD_window_hasExtDict():
+ * Returns non-zero if the window has a non-empty extDict.
+ */
+MEM_STATIC U32 ZSTD_window_hasExtDict(ZSTD_window_t const window)
+{
+    return window.lowLimit < window.dictLimit;
+}
+
+/*
+ * ZSTD_matchState_dictMode():
+ * Inspects the provided matchState and figures out what dictMode should be
+ * passed to the compressor.
+ */
+MEM_STATIC ZSTD_dictMode_e ZSTD_matchState_dictMode(const ZSTD_matchState_t *ms)
+{
+    return ZSTD_window_hasExtDict(ms->window) ?
+        ZSTD_extDict :
+        ms->dictMatchState != NULL ?
+            (ms->dictMatchState->dedicatedDictSearch ? ZSTD_dedicatedDictSearch : ZSTD_dictMatchState) :
+            ZSTD_noDict;
+}
+
+/*
+ * ZSTD_window_needOverflowCorrection():
+ * Returns non-zero if the indices are getting too large and need overflow
+ * protection.
+ */
+MEM_STATIC U32 ZSTD_window_needOverflowCorrection(ZSTD_window_t const window,
+                                                  void const* srcEnd)
+{
+    U32 const curr = (U32)((BYTE const*)srcEnd - window.base);
+    return curr > ZSTD_CURRENT_MAX;
+}
+
+/*
+ * ZSTD_window_correctOverflow():
+ * Reduces the indices to protect from index overflow.
+ * Returns the correction made to the indices, which must be applied to every
+ * stored index.
+ *
+ * The least significant cycleLog bits of the indices must remain the same,
+ * which may be 0. Every index up to maxDist in the past must be valid.
+ * NOTE: (maxDist & cycleMask) must be zero.
+ */
+MEM_STATIC U32 ZSTD_window_correctOverflow(ZSTD_window_t* window, U32 cycleLog,
+                                           U32 maxDist, void const* src)
+{
+    /* preemptive overflow correction:
+     * 1. correction is large enough:
+     *    lowLimit > (3<<29) ==> current > 3<<29 + 1<<windowLog
+     *    1<<windowLog <= newCurrent < 1<<chainLog + 1<<windowLog
+     *
+     *    current - newCurrent
+     *    > (3<<29 + 1<<windowLog) - (1<<windowLog + 1<<chainLog)
+     *    > (3<<29) - (1<<chainLog)
+     *    > (3<<29) - (1<<30)             (NOTE: chainLog <= 30)
+     *    > 1<<29
+     *
+     * 2. (ip+ZSTD_CHUNKSIZE_MAX - cctx->base) doesn't overflow:
+     *    After correction, current is less than (1<<chainLog + 1<<windowLog).
+     *    In 64-bit mode we are safe, because we have 64-bit ptrdiff_t.
+     *    In 32-bit mode we are safe, because (chainLog <= 29), so
+     *    ip+ZSTD_CHUNKSIZE_MAX - cctx->base < 1<<32.
+     * 3. (cctx->lowLimit + 1<<windowLog) < 1<<32:
+     *    windowLog <= 31 ==> 3<<29 + 1<<windowLog < 7<<29 < 1<<32.
+     */
+    U32 const cycleMask = (1U << cycleLog) - 1;
+    U32 const curr = (U32)((BYTE const*)src - window->base);
+    U32 const currentCycle0 = curr & cycleMask;
+    /* Exclude zero so that newCurrent - maxDist >= 1. */
+    U32 const currentCycle1 = currentCycle0 == 0 ? (1U << cycleLog) : currentCycle0;
+    U32 const newCurrent = currentCycle1 + maxDist;
+    U32 const correction = curr - newCurrent;
+    assert((maxDist & cycleMask) == 0);
+    assert(curr > newCurrent);
+    /* Loose bound, should be around 1<<29 (see above) */
+    assert(correction > 1<<28);
+
+    window->base += correction;
+    window->dictBase += correction;
+    if (window->lowLimit <= correction) window->lowLimit = 1;
+    else window->lowLimit -= correction;
+    if (window->dictLimit <= correction) window->dictLimit = 1;
+    else window->dictLimit -= correction;
+
+    /* Ensure we can still reference the full window. */
+    assert(newCurrent >= maxDist);
+    assert(newCurrent - maxDist >= 1);
+    /* Ensure that lowLimit and dictLimit didn't underflow. */
+    assert(window->lowLimit <= newCurrent);
+    assert(window->dictLimit <= newCurrent);
+
+    DEBUGLOG(4, "Correction of 0x%x bytes to lowLimit=0x%x", correction,
+             window->lowLimit);
+    return correction;
+}
+
+/*
+ * ZSTD_window_enforceMaxDist():
+ * Updates lowLimit so that:
+ *    (srcEnd - base) - lowLimit == maxDist + loadedDictEnd
+ *
+ * It ensures index is valid as long as index >= lowLimit.
+ * This must be called before a block compression call.
+ *
+ * loadedDictEnd is only defined if a dictionary is in use for current compression.
+ * As the name implies, loadedDictEnd represents the index at end of dictionary.
+ * The value lies within context's referential, it can be directly compared to blockEndIdx.
+ *
+ * If loadedDictEndPtr is NULL, no dictionary is in use, and we use loadedDictEnd == 0.
+ * If loadedDictEndPtr is not NULL, we set it to zero after updating lowLimit.
+ * This is because dictionaries are allowed to be referenced fully
+ * as long as the last byte of the dictionary is in the window.
+ * Once input has progressed beyond window size, dictionary cannot be referenced anymore.
+ *
+ * In normal dict mode, the dictionary lies between lowLimit and dictLimit.
+ * In dictMatchState mode, lowLimit and dictLimit are the same,
+ * and the dictionary is below them.
+ * forceWindow and dictMatchState are therefore incompatible.
+ */
+MEM_STATIC void
+ZSTD_window_enforceMaxDist(ZSTD_window_t* window,
+                     const void* blockEnd,
+                           U32   maxDist,
+                           U32*  loadedDictEndPtr,
+                     const ZSTD_matchState_t** dictMatchStatePtr)
+{
+    U32 const blockEndIdx = (U32)((BYTE const*)blockEnd - window->base);
+    U32 const loadedDictEnd = (loadedDictEndPtr != NULL) ? *loadedDictEndPtr : 0;
+    DEBUGLOG(5, "ZSTD_window_enforceMaxDist: blockEndIdx=%u, maxDist=%u, loadedDictEnd=%u",
+                (unsigned)blockEndIdx, (unsigned)maxDist, (unsigned)loadedDictEnd);
+
+    /* - When there is no dictionary : loadedDictEnd == 0.
+         In which case, the test (blockEndIdx > maxDist) is merely to avoid
+         overflowing next operation `newLowLimit = blockEndIdx - maxDist`.
+       - When there is a standard dictionary :
+         Index referential is copied from the dictionary,
+         which means it starts from 0.
+         In which case, loadedDictEnd == dictSize,
+         and it makes sense to compare `blockEndIdx > maxDist + dictSize`
+         since `blockEndIdx` also starts from zero.
+       - When there is an attached dictionary :
+         loadedDictEnd is expressed within the referential of the context,
+         so it can be directly compared against blockEndIdx.
+    */
+    if (blockEndIdx > maxDist + loadedDictEnd) {
+        U32 const newLowLimit = blockEndIdx - maxDist;
+        if (window->lowLimit < newLowLimit) window->lowLimit = newLowLimit;
+        if (window->dictLimit < window->lowLimit) {
+            DEBUGLOG(5, "Update dictLimit to match lowLimit, from %u to %u",
+                        (unsigned)window->dictLimit, (unsigned)window->lowLimit);
+            window->dictLimit = window->lowLimit;
+        }
+        /* On reaching window size, dictionaries are invalidated */
+        if (loadedDictEndPtr) *loadedDictEndPtr = 0;
+        if (dictMatchStatePtr) *dictMatchStatePtr = NULL;
+    }
+}
+
+/* Similar to ZSTD_window_enforceMaxDist(),
+ * but only invalidates dictionary
+ * when input progresses beyond window size.
+ * assumption : loadedDictEndPtr and dictMatchStatePtr are valid (non NULL)
+ *              loadedDictEnd uses same referential as window->base
+ *              maxDist is the window size */
+MEM_STATIC void
+ZSTD_checkDictValidity(const ZSTD_window_t* window,
+                       const void* blockEnd,
+                             U32   maxDist,
+                             U32*  loadedDictEndPtr,
+                       const ZSTD_matchState_t** dictMatchStatePtr)
+{
+    assert(loadedDictEndPtr != NULL);
+    assert(dictMatchStatePtr != NULL);
+    {   U32 const blockEndIdx = (U32)((BYTE const*)blockEnd - window->base);
+        U32 const loadedDictEnd = *loadedDictEndPtr;
+        DEBUGLOG(5, "ZSTD_checkDictValidity: blockEndIdx=%u, maxDist=%u, loadedDictEnd=%u",
+                    (unsigned)blockEndIdx, (unsigned)maxDist, (unsigned)loadedDictEnd);
+        assert(blockEndIdx >= loadedDictEnd);
+
+        if (blockEndIdx > loadedDictEnd + maxDist) {
+            /* On reaching window size, dictionaries are invalidated.
+             * For simplification, if window size is reached anywhere within next block,
+             * the dictionary is invalidated for the full block.
+             */
+            DEBUGLOG(6, "invalidating dictionary for current block (distance > windowSize)");
+            *loadedDictEndPtr = 0;
+            *dictMatchStatePtr = NULL;
+        } else {
+            if (*loadedDictEndPtr != 0) {
+                DEBUGLOG(6, "dictionary considered valid for current block");
+    }   }   }
+}
+
+MEM_STATIC void ZSTD_window_init(ZSTD_window_t* window) {
+    ZSTD_memset(window, 0, sizeof(*window));
+    window->base = (BYTE const*)"";
+    window->dictBase = (BYTE const*)"";
+    window->dictLimit = 1;    /* start from 1, so that 1st position is valid */
+    window->lowLimit = 1;     /* it ensures first and later CCtx usages compress the same */
+    window->nextSrc = window->base + 1;   /* see issue #1241 */
+}
+
+/*
+ * ZSTD_window_update():
+ * Updates the window by appending [src, src + srcSize) to the window.
+ * If it is not contiguous, the current prefix becomes the extDict, and we
+ * forget about the extDict. Handles overlap of the prefix and extDict.
+ * Returns non-zero if the segment is contiguous.
+ */
+MEM_STATIC U32 ZSTD_window_update(ZSTD_window_t* window,
+                                  void const* src, size_t srcSize)
+{
+    BYTE const* const ip = (BYTE const*)src;
+    U32 contiguous = 1;
+    DEBUGLOG(5, "ZSTD_window_update");
+    if (srcSize == 0)
+        return contiguous;
+    assert(window->base != NULL);
+    assert(window->dictBase != NULL);
+    /* Check if blocks follow each other */
+    if (src != window->nextSrc) {
+        /* not contiguous */
+        size_t const distanceFromBase = (size_t)(window->nextSrc - window->base);
+        DEBUGLOG(5, "Non contiguous blocks, new segment starts at %u", window->dictLimit);
+        window->lowLimit = window->dictLimit;
+        assert(distanceFromBase == (size_t)(U32)distanceFromBase);  /* should never overflow */
+        window->dictLimit = (U32)distanceFromBase;
+        window->dictBase = window->base;
+        window->base = ip - distanceFromBase;
+        /* ms->nextToUpdate = window->dictLimit; */
+        if (window->dictLimit - window->lowLimit < HASH_READ_SIZE) window->lowLimit = window->dictLimit;   /* too small extDict */
+        contiguous = 0;
+    }
+    window->nextSrc = ip + srcSize;
+    /* if input and dictionary overlap : reduce dictionary (area presumed modified by input) */
+    if ( (ip+srcSize > window->dictBase + window->lowLimit)
+       & (ip < window->dictBase + window->dictLimit)) {
+        ptrdiff_t const highInputIdx = (ip + srcSize) - window->dictBase;
+        U32 const lowLimitMax = (highInputIdx > (ptrdiff_t)window->dictLimit) ? window->dictLimit : (U32)highInputIdx;
+        window->lowLimit = lowLimitMax;
+        DEBUGLOG(5, "Overlapping extDict and input : new lowLimit = %u", window->lowLimit);
+    }
+    return contiguous;
+}
+
+/*
+ * Returns the lowest allowed match index. It may either be in the ext-dict or the prefix.
+ */
+MEM_STATIC U32 ZSTD_getLowestMatchIndex(const ZSTD_matchState_t* ms, U32 curr, unsigned windowLog)
+{
+    U32    const maxDistance = 1U << windowLog;
+    U32    const lowestValid = ms->window.lowLimit;
+    U32    const withinWindow = (curr - lowestValid > maxDistance) ? curr - maxDistance : lowestValid;
+    U32    const isDictionary = (ms->loadedDictEnd != 0);
+    /* When using a dictionary the entire dictionary is valid if a single byte of the dictionary
+     * is within the window. We invalidate the dictionary (and set loadedDictEnd to 0) when it isn't
+     * valid for the entire block. So this check is sufficient to find the lowest valid match index.
+     */
+    U32    const matchLowest = isDictionary ? lowestValid : withinWindow;
+    return matchLowest;
+}
+
+/*
+ * Returns the lowest allowed match index in the prefix.
+ */
+MEM_STATIC U32 ZSTD_getLowestPrefixIndex(const ZSTD_matchState_t* ms, U32 curr, unsigned windowLog)
+{
+    U32    const maxDistance = 1U << windowLog;
+    U32    const lowestValid = ms->window.dictLimit;
+    U32    const withinWindow = (curr - lowestValid > maxDistance) ? curr - maxDistance : lowestValid;
+    U32    const isDictionary = (ms->loadedDictEnd != 0);
+    /* When computing the lowest prefix index we need to take the dictionary into account to handle
+     * the edge case where the dictionary and the source are contiguous in memory.
+     */
+    U32    const matchLowest = isDictionary ? lowestValid : withinWindow;
+    return matchLowest;
+}
+
+
+
+/* debug functions */
+#if (DEBUGLEVEL>=2)
+
+MEM_STATIC double ZSTD_fWeight(U32 rawStat)
+{
+    U32 const fp_accuracy = 8;
+    U32 const fp_multiplier = (1 << fp_accuracy);
+    U32 const newStat = rawStat + 1;
+    U32 const hb = ZSTD_highbit32(newStat);
+    U32 const BWeight = hb * fp_multiplier;
+    U32 const FWeight = (newStat << fp_accuracy) >> hb;
+    U32 const weight = BWeight + FWeight;
+    assert(hb + fp_accuracy < 31);
+    return (double)weight / fp_multiplier;
+}
+
+/* display a table content,
+ * listing each element, its frequency, and its predicted bit cost */
+MEM_STATIC void ZSTD_debugTable(const U32* table, U32 max)
+{
+    unsigned u, sum;
+    for (u=0, sum=0; u<=max; u++) sum += table[u];
+    DEBUGLOG(2, "total nb elts: %u", sum);
+    for (u=0; u<=max; u++) {
+        DEBUGLOG(2, "%2u: %5u  (%.2f)",
+                u, table[u], ZSTD_fWeight(sum) - ZSTD_fWeight(table[u]) );
+    }
+}
+
+#endif
+
+
+
+/* ===============================================================
+ * Shared internal declarations
+ * These prototypes may be called from sources not in lib/compress
+ * =============================================================== */
+
+/* ZSTD_loadCEntropy() :
+ * dict : must point at beginning of a valid zstd dictionary.
+ * return : size of dictionary header (size of magic number + dict ID + entropy tables)
+ * assumptions : magic number supposed already checked
+ *               and dictSize >= 8 */
+size_t ZSTD_loadCEntropy(ZSTD_compressedBlockState_t* bs, void* workspace,
+                         const void* const dict, size_t dictSize);
+
+void ZSTD_reset_compressedBlockState(ZSTD_compressedBlockState_t* bs);
+
+/* ==============================================================
+ * Private declarations
+ * These prototypes shall only be called from within lib/compress
+ * ============================================================== */
+
+/* ZSTD_getCParamsFromCCtxParams() :
+ * cParams are built depending on compressionLevel, src size hints,
+ * LDM and manually set compression parameters.
+ * Note: srcSizeHint == 0 means 0!
+ */
+ZSTD_compressionParameters ZSTD_getCParamsFromCCtxParams(
+        const ZSTD_CCtx_params* CCtxParams, U64 srcSizeHint, size_t dictSize, ZSTD_cParamMode_e mode);
+
+/*! ZSTD_initCStream_internal() :
+ *  Private use only. Init streaming operation.
+ *  expects params to be valid.
+ *  must receive dict, or cdict, or none, but not both.
+ *  @return : 0, or an error code */
+size_t ZSTD_initCStream_internal(ZSTD_CStream* zcs,
+                     const void* dict, size_t dictSize,
+                     const ZSTD_CDict* cdict,
+                     const ZSTD_CCtx_params* params, unsigned long long pledgedSrcSize);
+
+void ZSTD_resetSeqStore(seqStore_t* ssPtr);
+
+/*! ZSTD_getCParamsFromCDict() :
+ *  as the name implies */
+ZSTD_compressionParameters ZSTD_getCParamsFromCDict(const ZSTD_CDict* cdict);
+
+/* ZSTD_compressBegin_advanced_internal() :
+ * Private use only. To be called from zstdmt_compress.c. */
+size_t ZSTD_compressBegin_advanced_internal(ZSTD_CCtx* cctx,
+                                    const void* dict, size_t dictSize,
+                                    ZSTD_dictContentType_e dictContentType,
+                                    ZSTD_dictTableLoadMethod_e dtlm,
+                                    const ZSTD_CDict* cdict,
+                                    const ZSTD_CCtx_params* params,
+                                    unsigned long long pledgedSrcSize);
+
+/* ZSTD_compress_advanced_internal() :
+ * Private use only. To be called from zstdmt_compress.c. */
+size_t ZSTD_compress_advanced_internal(ZSTD_CCtx* cctx,
+                                       void* dst, size_t dstCapacity,
+                                 const void* src, size_t srcSize,
+                                 const void* dict,size_t dictSize,
+                                 const ZSTD_CCtx_params* params);
+
+
+/* ZSTD_writeLastEmptyBlock() :
+ * output an empty Block with end-of-frame mark to complete a frame
+ * @return : size of data written into `dst` (== ZSTD_blockHeaderSize (defined in zstd_internal.h))
+ *           or an error code if `dstCapacity` is too small (<ZSTD_blockHeaderSize)
+ */
+size_t ZSTD_writeLastEmptyBlock(void* dst, size_t dstCapacity);
+
+
+/* ZSTD_referenceExternalSequences() :
+ * Must be called before starting a compression operation.
+ * seqs must parse a prefix of the source.
+ * This cannot be used when long range matching is enabled.
+ * Zstd will use these sequences, and pass the literals to a secondary block
+ * compressor.
+ * @return : An error code on failure.
+ * NOTE: seqs are not verified! Invalid sequences can cause out-of-bounds memory
+ * access and data corruption.
+ */
+size_t ZSTD_referenceExternalSequences(ZSTD_CCtx* cctx, rawSeq* seq, size_t nbSeq);
+
+/* ZSTD_cycleLog() :
+ *  condition for correct operation : hashLog > 1 */
+U32 ZSTD_cycleLog(U32 hashLog, ZSTD_strategy strat);
+
+/* ZSTD_CCtx_trace() :
+ *  Trace the end of a compression call.
+ */
+void ZSTD_CCtx_trace(ZSTD_CCtx* cctx, size_t extraCSize);
+
+#endif /* ZSTD_COMPRESS_H */
diff --git a/lib/zstd/compress/zstd_compress_literals.c b/lib/zstd/compress/zstd_compress_literals.c
new file mode 100644
index 000000000000..655bcda4d1f1
--- /dev/null
+++ b/lib/zstd/compress/zstd_compress_literals.c
@@ -0,0 +1,158 @@
+/*
+ * Copyright (c) Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+ /*-*************************************
+ *  Dependencies
+ ***************************************/
+#include "zstd_compress_literals.h"
+
+size_t ZSTD_noCompressLiterals (void* dst, size_t dstCapacity, const void* src, size_t srcSize)
+{
+    BYTE* const ostart = (BYTE*)dst;
+    U32   const flSize = 1 + (srcSize>31) + (srcSize>4095);
+
+    RETURN_ERROR_IF(srcSize + flSize > dstCapacity, dstSize_tooSmall, "");
+
+    switch(flSize)
+    {
+        case 1: /* 2 - 1 - 5 */
+            ostart[0] = (BYTE)((U32)set_basic + (srcSize<<3));
+            break;
+        case 2: /* 2 - 2 - 12 */
+            MEM_writeLE16(ostart, (U16)((U32)set_basic + (1<<2) + (srcSize<<4)));
+            break;
+        case 3: /* 2 - 2 - 20 */
+            MEM_writeLE32(ostart, (U32)((U32)set_basic + (3<<2) + (srcSize<<4)));
+            break;
+        default:   /* not necessary : flSize is {1,2,3} */
+            assert(0);
+    }
+
+    ZSTD_memcpy(ostart + flSize, src, srcSize);
+    DEBUGLOG(5, "Raw literals: %u -> %u", (U32)srcSize, (U32)(srcSize + flSize));
+    return srcSize + flSize;
+}
+
+size_t ZSTD_compressRleLiteralsBlock (void* dst, size_t dstCapacity, const void* src, size_t srcSize)
+{
+    BYTE* const ostart = (BYTE*)dst;
+    U32   const flSize = 1 + (srcSize>31) + (srcSize>4095);
+
+    (void)dstCapacity;  /* dstCapacity already guaranteed to be >=4, hence large enough */
+
+    switch(flSize)
+    {
+        case 1: /* 2 - 1 - 5 */
+            ostart[0] = (BYTE)((U32)set_rle + (srcSize<<3));
+            break;
+        case 2: /* 2 - 2 - 12 */
+            MEM_writeLE16(ostart, (U16)((U32)set_rle + (1<<2) + (srcSize<<4)));
+            break;
+        case 3: /* 2 - 2 - 20 */
+            MEM_writeLE32(ostart, (U32)((U32)set_rle + (3<<2) + (srcSize<<4)));
+            break;
+        default:   /* not necessary : flSize is {1,2,3} */
+            assert(0);
+    }
+
+    ostart[flSize] = *(const BYTE*)src;
+    DEBUGLOG(5, "RLE literals: %u -> %u", (U32)srcSize, (U32)flSize + 1);
+    return flSize+1;
+}
+
+size_t ZSTD_compressLiterals (ZSTD_hufCTables_t const* prevHuf,
+                              ZSTD_hufCTables_t* nextHuf,
+                              ZSTD_strategy strategy, int disableLiteralCompression,
+                              void* dst, size_t dstCapacity,
+                        const void* src, size_t srcSize,
+                              void* entropyWorkspace, size_t entropyWorkspaceSize,
+                        const int bmi2)
+{
+    size_t const minGain = ZSTD_minGain(srcSize, strategy);
+    size_t const lhSize = 3 + (srcSize >= 1 KB) + (srcSize >= 16 KB);
+    BYTE*  const ostart = (BYTE*)dst;
+    U32 singleStream = srcSize < 256;
+    symbolEncodingType_e hType = set_compressed;
+    size_t cLitSize;
+
+    DEBUGLOG(5,"ZSTD_compressLiterals (disableLiteralCompression=%i srcSize=%u)",
+                disableLiteralCompression, (U32)srcSize);
+
+    /* Prepare nextEntropy assuming reusing the existing table */
+    ZSTD_memcpy(nextHuf, prevHuf, sizeof(*prevHuf));
+
+    if (disableLiteralCompression)
+        return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize);
+
+    /* small ? don't even attempt compression (speed opt) */
+#   define COMPRESS_LITERALS_SIZE_MIN 63
+    {   size_t const minLitSize = (prevHuf->repeatMode == HUF_repeat_valid) ? 6 : COMPRESS_LITERALS_SIZE_MIN;
+        if (srcSize <= minLitSize) return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize);
+    }
+
+    RETURN_ERROR_IF(dstCapacity < lhSize+1, dstSize_tooSmall, "not enough space for compression");
+    {   HUF_repeat repeat = prevHuf->repeatMode;
+        int const preferRepeat = strategy < ZSTD_lazy ? srcSize <= 1024 : 0;
+        if (repeat == HUF_repeat_valid && lhSize == 3) singleStream = 1;
+        cLitSize = singleStream ?
+            HUF_compress1X_repeat(
+                ostart+lhSize, dstCapacity-lhSize, src, srcSize,
+                HUF_SYMBOLVALUE_MAX, HUF_TABLELOG_DEFAULT, entropyWorkspace, entropyWorkspaceSize,
+                (HUF_CElt*)nextHuf->CTable, &repeat, preferRepeat, bmi2) :
+            HUF_compress4X_repeat(
+                ostart+lhSize, dstCapacity-lhSize, src, srcSize,
+                HUF_SYMBOLVALUE_MAX, HUF_TABLELOG_DEFAULT, entropyWorkspace, entropyWorkspaceSize,
+                (HUF_CElt*)nextHuf->CTable, &repeat, preferRepeat, bmi2);
+        if (repeat != HUF_repeat_none) {
+            /* reused the existing table */
+            DEBUGLOG(5, "Reusing previous huffman table");
+            hType = set_repeat;
+        }
+    }
+
+    if ((cLitSize==0) | (cLitSize >= srcSize - minGain) | ERR_isError(cLitSize)) {
+        ZSTD_memcpy(nextHuf, prevHuf, sizeof(*prevHuf));
+        return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize);
+    }
+    if (cLitSize==1) {
+        ZSTD_memcpy(nextHuf, prevHuf, sizeof(*prevHuf));
+        return ZSTD_compressRleLiteralsBlock(dst, dstCapacity, src, srcSize);
+    }
+
+    if (hType == set_compressed) {
+        /* using a newly constructed table */
+        nextHuf->repeatMode = HUF_repeat_check;
+    }
+
+    /* Build header */
+    switch(lhSize)
+    {
+    case 3: /* 2 - 2 - 10 - 10 */
+        {   U32 const lhc = hType + ((!singleStream) << 2) + ((U32)srcSize<<4) + ((U32)cLitSize<<14);
+            MEM_writeLE24(ostart, lhc);
+            break;
+        }
+    case 4: /* 2 - 2 - 14 - 14 */
+        {   U32 const lhc = hType + (2 << 2) + ((U32)srcSize<<4) + ((U32)cLitSize<<18);
+            MEM_writeLE32(ostart, lhc);
+            break;
+        }
+    case 5: /* 2 - 2 - 18 - 18 */
+        {   U32 const lhc = hType + (3 << 2) + ((U32)srcSize<<4) + ((U32)cLitSize<<22);
+            MEM_writeLE32(ostart, lhc);
+            ostart[4] = (BYTE)(cLitSize >> 10);
+            break;
+        }
+    default:  /* not possible : lhSize is {3,4,5} */
+        assert(0);
+    }
+    DEBUGLOG(5, "Compressed literals: %u -> %u", (U32)srcSize, (U32)(lhSize+cLitSize));
+    return lhSize+cLitSize;
+}
diff --git a/lib/zstd/compress/zstd_compress_literals.h b/lib/zstd/compress/zstd_compress_literals.h
new file mode 100644
index 000000000000..9904c0cd30a0
--- /dev/null
+++ b/lib/zstd/compress/zstd_compress_literals.h
@@ -0,0 +1,29 @@
+/*
+ * Copyright (c) Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+#ifndef ZSTD_COMPRESS_LITERALS_H
+#define ZSTD_COMPRESS_LITERALS_H
+
+#include "zstd_compress_internal.h" /* ZSTD_hufCTables_t, ZSTD_minGain() */
+
+
+size_t ZSTD_noCompressLiterals (void* dst, size_t dstCapacity, const void* src, size_t srcSize);
+
+size_t ZSTD_compressRleLiteralsBlock (void* dst, size_t dstCapacity, const void* src, size_t srcSize);
+
+size_t ZSTD_compressLiterals (ZSTD_hufCTables_t const* prevHuf,
+                              ZSTD_hufCTables_t* nextHuf,
+                              ZSTD_strategy strategy, int disableLiteralCompression,
+                              void* dst, size_t dstCapacity,
+                        const void* src, size_t srcSize,
+                              void* entropyWorkspace, size_t entropyWorkspaceSize,
+                        const int bmi2);
+
+#endif /* ZSTD_COMPRESS_LITERALS_H */
diff --git a/lib/zstd/compress/zstd_compress_sequences.c b/lib/zstd/compress/zstd_compress_sequences.c
new file mode 100644
index 000000000000..dcfcdc9cc5e8
--- /dev/null
+++ b/lib/zstd/compress/zstd_compress_sequences.c
@@ -0,0 +1,439 @@
+/*
+ * Copyright (c) Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+ /*-*************************************
+ *  Dependencies
+ ***************************************/
+#include "zstd_compress_sequences.h"
+
+/*
+ * -log2(x / 256) lookup table for x in [0, 256).
+ * If x == 0: Return 0
+ * Else: Return floor(-log2(x / 256) * 256)
+ */
+static unsigned const kInverseProbabilityLog256[256] = {
+    0,    2048, 1792, 1642, 1536, 1453, 1386, 1329, 1280, 1236, 1197, 1162,
+    1130, 1100, 1073, 1047, 1024, 1001, 980,  960,  941,  923,  906,  889,
+    874,  859,  844,  830,  817,  804,  791,  779,  768,  756,  745,  734,
+    724,  714,  704,  694,  685,  676,  667,  658,  650,  642,  633,  626,
+    618,  610,  603,  595,  588,  581,  574,  567,  561,  554,  548,  542,
+    535,  529,  523,  517,  512,  506,  500,  495,  489,  484,  478,  473,
+    468,  463,  458,  453,  448,  443,  438,  434,  429,  424,  420,  415,
+    411,  407,  402,  398,  394,  390,  386,  382,  377,  373,  370,  366,
+    362,  358,  354,  350,  347,  343,  339,  336,  332,  329,  325,  322,
+    318,  315,  311,  308,  305,  302,  298,  295,  292,  289,  286,  282,
+    279,  276,  273,  270,  267,  264,  261,  258,  256,  253,  250,  247,
+    244,  241,  239,  236,  233,  230,  228,  225,  222,  220,  217,  215,
+    212,  209,  207,  204,  202,  199,  197,  194,  192,  190,  187,  185,
+    182,  180,  178,  175,  173,  171,  168,  166,  164,  162,  159,  157,
+    155,  153,  151,  149,  146,  144,  142,  140,  138,  136,  134,  132,
+    130,  128,  126,  123,  121,  119,  117,  115,  114,  112,  110,  108,
+    106,  104,  102,  100,  98,   96,   94,   93,   91,   89,   87,   85,
+    83,   82,   80,   78,   76,   74,   73,   71,   69,   67,   66,   64,
+    62,   61,   59,   57,   55,   54,   52,   50,   49,   47,   46,   44,
+    42,   41,   39,   37,   36,   34,   33,   31,   30,   28,   26,   25,
+    23,   22,   20,   19,   17,   16,   14,   13,   11,   10,   8,    7,
+    5,    4,    2,    1,
+};
+
+static unsigned ZSTD_getFSEMaxSymbolValue(FSE_CTable const* ctable) {
+  void const* ptr = ctable;
+  U16 const* u16ptr = (U16 const*)ptr;
+  U32 const maxSymbolValue = MEM_read16(u16ptr + 1);
+  return maxSymbolValue;
+}
+
+/*
+ * Returns true if we should use ncount=-1 else we should
+ * use ncount=1 for low probability symbols instead.
+ */
+static unsigned ZSTD_useLowProbCount(size_t const nbSeq)
+{
+    /* Heuristic: This should cover most blocks <= 16K and
+     * start to fade out after 16K to about 32K depending on
+     * comprssibility.
+     */
+    return nbSeq >= 2048;
+}
+
+/*
+ * Returns the cost in bytes of encoding the normalized count header.
+ * Returns an error if any of the helper functions return an error.
+ */
+static size_t ZSTD_NCountCost(unsigned const* count, unsigned const max,
+                              size_t const nbSeq, unsigned const FSELog)
+{
+    BYTE wksp[FSE_NCOUNTBOUND];
+    S16 norm[MaxSeq + 1];
+    const U32 tableLog = FSE_optimalTableLog(FSELog, nbSeq, max);
+    FORWARD_IF_ERROR(FSE_normalizeCount(norm, tableLog, count, nbSeq, max, ZSTD_useLowProbCount(nbSeq)), "");
+    return FSE_writeNCount(wksp, sizeof(wksp), norm, max, tableLog);
+}
+
+/*
+ * Returns the cost in bits of encoding the distribution described by count
+ * using the entropy bound.
+ */
+static size_t ZSTD_entropyCost(unsigned const* count, unsigned const max, size_t const total)
+{
+    unsigned cost = 0;
+    unsigned s;
+    for (s = 0; s <= max; ++s) {
+        unsigned norm = (unsigned)((256 * count[s]) / total);
+        if (count[s] != 0 && norm == 0)
+            norm = 1;
+        assert(count[s] < total);
+        cost += count[s] * kInverseProbabilityLog256[norm];
+    }
+    return cost >> 8;
+}
+
+/*
+ * Returns the cost in bits of encoding the distribution in count using ctable.
+ * Returns an error if ctable cannot represent all the symbols in count.
+ */
+size_t ZSTD_fseBitCost(
+    FSE_CTable const* ctable,
+    unsigned const* count,
+    unsigned const max)
+{
+    unsigned const kAccuracyLog = 8;
+    size_t cost = 0;
+    unsigned s;
+    FSE_CState_t cstate;
+    FSE_initCState(&cstate, ctable);
+    if (ZSTD_getFSEMaxSymbolValue(ctable) < max) {
+        DEBUGLOG(5, "Repeat FSE_CTable has maxSymbolValue %u < %u",
+                    ZSTD_getFSEMaxSymbolValue(ctable), max);
+        return ERROR(GENERIC);
+    }
+    for (s = 0; s <= max; ++s) {
+        unsigned const tableLog = cstate.stateLog;
+        unsigned const badCost = (tableLog + 1) << kAccuracyLog;
+        unsigned const bitCost = FSE_bitCost(cstate.symbolTT, tableLog, s, kAccuracyLog);
+        if (count[s] == 0)
+            continue;
+        if (bitCost >= badCost) {
+            DEBUGLOG(5, "Repeat FSE_CTable has Prob[%u] == 0", s);
+            return ERROR(GENERIC);
+        }
+        cost += (size_t)count[s] * bitCost;
+    }
+    return cost >> kAccuracyLog;
+}
+
+/*
+ * Returns the cost in bits of encoding the distribution in count using the
+ * table described by norm. The max symbol support by norm is assumed >= max.
+ * norm must be valid for every symbol with non-zero probability in count.
+ */
+size_t ZSTD_crossEntropyCost(short const* norm, unsigned accuracyLog,
+                             unsigned const* count, unsigned const max)
+{
+    unsigned const shift = 8 - accuracyLog;
+    size_t cost = 0;
+    unsigned s;
+    assert(accuracyLog <= 8);
+    for (s = 0; s <= max; ++s) {
+        unsigned const normAcc = (norm[s] != -1) ? (unsigned)norm[s] : 1;
+        unsigned const norm256 = normAcc << shift;
+        assert(norm256 > 0);
+        assert(norm256 < 256);
+        cost += count[s] * kInverseProbabilityLog256[norm256];
+    }
+    return cost >> 8;
+}
+
+symbolEncodingType_e
+ZSTD_selectEncodingType(
+        FSE_repeat* repeatMode, unsigned const* count, unsigned const max,
+        size_t const mostFrequent, size_t nbSeq, unsigned const FSELog,
+        FSE_CTable const* prevCTable,
+        short const* defaultNorm, U32 defaultNormLog,
+        ZSTD_defaultPolicy_e const isDefaultAllowed,
+        ZSTD_strategy const strategy)
+{
+    ZSTD_STATIC_ASSERT(ZSTD_defaultDisallowed == 0 && ZSTD_defaultAllowed != 0);
+    if (mostFrequent == nbSeq) {
+        *repeatMode = FSE_repeat_none;
+        if (isDefaultAllowed && nbSeq <= 2) {
+            /* Prefer set_basic over set_rle when there are 2 or less symbols,
+             * since RLE uses 1 byte, but set_basic uses 5-6 bits per symbol.
+             * If basic encoding isn't possible, always choose RLE.
+             */
+            DEBUGLOG(5, "Selected set_basic");
+            return set_basic;
+        }
+        DEBUGLOG(5, "Selected set_rle");
+        return set_rle;
+    }
+    if (strategy < ZSTD_lazy) {
+        if (isDefaultAllowed) {
+            size_t const staticFse_nbSeq_max = 1000;
+            size_t const mult = 10 - strategy;
+            size_t const baseLog = 3;
+            size_t const dynamicFse_nbSeq_min = (((size_t)1 << defaultNormLog) * mult) >> baseLog;  /* 28-36 for offset, 56-72 for lengths */
+            assert(defaultNormLog >= 5 && defaultNormLog <= 6);  /* xx_DEFAULTNORMLOG */
+            assert(mult <= 9 && mult >= 7);
+            if ( (*repeatMode == FSE_repeat_valid)
+              && (nbSeq < staticFse_nbSeq_max) ) {
+                DEBUGLOG(5, "Selected set_repeat");
+                return set_repeat;
+            }
+            if ( (nbSeq < dynamicFse_nbSeq_min)
+              || (mostFrequent < (nbSeq >> (defaultNormLog-1))) ) {
+                DEBUGLOG(5, "Selected set_basic");
+                /* The format allows default tables to be repeated, but it isn't useful.
+                 * When using simple heuristics to select encoding type, we don't want
+                 * to confuse these tables with dictionaries. When running more careful
+                 * analysis, we don't need to waste time checking both repeating tables
+                 * and default tables.
+                 */
+                *repeatMode = FSE_repeat_none;
+                return set_basic;
+            }
+        }
+    } else {
+        size_t const basicCost = isDefaultAllowed ? ZSTD_crossEntropyCost(defaultNorm, defaultNormLog, count, max) : ERROR(GENERIC);
+        size_t const repeatCost = *repeatMode != FSE_repeat_none ? ZSTD_fseBitCost(prevCTable, count, max) : ERROR(GENERIC);
+        size_t const NCountCost = ZSTD_NCountCost(count, max, nbSeq, FSELog);
+        size_t const compressedCost = (NCountCost << 3) + ZSTD_entropyCost(count, max, nbSeq);
+
+        if (isDefaultAllowed) {
+            assert(!ZSTD_isError(basicCost));
+            assert(!(*repeatMode == FSE_repeat_valid && ZSTD_isError(repeatCost)));
+        }
+        assert(!ZSTD_isError(NCountCost));
+        assert(compressedCost < ERROR(maxCode));
+        DEBUGLOG(5, "Estimated bit costs: basic=%u\trepeat=%u\tcompressed=%u",
+                    (unsigned)basicCost, (unsigned)repeatCost, (unsigned)compressedCost);
+        if (basicCost <= repeatCost && basicCost <= compressedCost) {
+            DEBUGLOG(5, "Selected set_basic");
+            assert(isDefaultAllowed);
+            *repeatMode = FSE_repeat_none;
+            return set_basic;
+        }
+        if (repeatCost <= compressedCost) {
+            DEBUGLOG(5, "Selected set_repeat");
+            assert(!ZSTD_isError(repeatCost));
+            return set_repeat;
+        }
+        assert(compressedCost < basicCost && compressedCost < repeatCost);
+    }
+    DEBUGLOG(5, "Selected set_compressed");
+    *repeatMode = FSE_repeat_check;
+    return set_compressed;
+}
+
+typedef struct {
+    S16 norm[MaxSeq + 1];
+    U32 wksp[FSE_BUILD_CTABLE_WORKSPACE_SIZE_U32(MaxSeq, MaxFSELog)];
+} ZSTD_BuildCTableWksp;
+
+size_t
+ZSTD_buildCTable(void* dst, size_t dstCapacity,
+                FSE_CTable* nextCTable, U32 FSELog, symbolEncodingType_e type,
+                unsigned* count, U32 max,
+                const BYTE* codeTable, size_t nbSeq,
+                const S16* defaultNorm, U32 defaultNormLog, U32 defaultMax,
+                const FSE_CTable* prevCTable, size_t prevCTableSize,
+                void* entropyWorkspace, size_t entropyWorkspaceSize)
+{
+    BYTE* op = (BYTE*)dst;
+    const BYTE* const oend = op + dstCapacity;
+    DEBUGLOG(6, "ZSTD_buildCTable (dstCapacity=%u)", (unsigned)dstCapacity);
+
+    switch (type) {
+    case set_rle:
+        FORWARD_IF_ERROR(FSE_buildCTable_rle(nextCTable, (BYTE)max), "");
+        RETURN_ERROR_IF(dstCapacity==0, dstSize_tooSmall, "not enough space");
+        *op = codeTable[0];
+        return 1;
+    case set_repeat:
+        ZSTD_memcpy(nextCTable, prevCTable, prevCTableSize);
+        return 0;
+    case set_basic:
+        FORWARD_IF_ERROR(FSE_buildCTable_wksp(nextCTable, defaultNorm, defaultMax, defaultNormLog, entropyWorkspace, entropyWorkspaceSize), "");  /* note : could be pre-calculated */
+        return 0;
+    case set_compressed: {
+        ZSTD_BuildCTableWksp* wksp = (ZSTD_BuildCTableWksp*)entropyWorkspace;
+        size_t nbSeq_1 = nbSeq;
+        const U32 tableLog = FSE_optimalTableLog(FSELog, nbSeq, max);
+        if (count[codeTable[nbSeq-1]] > 1) {
+            count[codeTable[nbSeq-1]]--;
+            nbSeq_1--;
+        }
+        assert(nbSeq_1 > 1);
+        assert(entropyWorkspaceSize >= sizeof(ZSTD_BuildCTableWksp));
+        (void)entropyWorkspaceSize;
+        FORWARD_IF_ERROR(FSE_normalizeCount(wksp->norm, tableLog, count, nbSeq_1, max, ZSTD_useLowProbCount(nbSeq_1)), "");
+        {   size_t const NCountSize = FSE_writeNCount(op, oend - op, wksp->norm, max, tableLog);   /* overflow protected */
+            FORWARD_IF_ERROR(NCountSize, "FSE_writeNCount failed");
+            FORWARD_IF_ERROR(FSE_buildCTable_wksp(nextCTable, wksp->norm, max, tableLog, wksp->wksp, sizeof(wksp->wksp)), "");
+            return NCountSize;
+        }
+    }
+    default: assert(0); RETURN_ERROR(GENERIC, "impossible to reach");
+    }
+}
+
+FORCE_INLINE_TEMPLATE size_t
+ZSTD_encodeSequences_body(
+            void* dst, size_t dstCapacity,
+            FSE_CTable const* CTable_MatchLength, BYTE const* mlCodeTable,
+            FSE_CTable const* CTable_OffsetBits, BYTE const* ofCodeTable,
+            FSE_CTable const* CTable_LitLength, BYTE const* llCodeTable,
+            seqDef const* sequences, size_t nbSeq, int longOffsets)
+{
+    BIT_CStream_t blockStream;
+    FSE_CState_t  stateMatchLength;
+    FSE_CState_t  stateOffsetBits;
+    FSE_CState_t  stateLitLength;
+
+    RETURN_ERROR_IF(
+        ERR_isError(BIT_initCStream(&blockStream, dst, dstCapacity)),
+        dstSize_tooSmall, "not enough space remaining");
+    DEBUGLOG(6, "available space for bitstream : %i  (dstCapacity=%u)",
+                (int)(blockStream.endPtr - blockStream.startPtr),
+                (unsigned)dstCapacity);
+
+    /* first symbols */
+    FSE_initCState2(&stateMatchLength, CTable_MatchLength, mlCodeTable[nbSeq-1]);
+    FSE_initCState2(&stateOffsetBits,  CTable_OffsetBits,  ofCodeTable[nbSeq-1]);
+    FSE_initCState2(&stateLitLength,   CTable_LitLength,   llCodeTable[nbSeq-1]);
+    BIT_addBits(&blockStream, sequences[nbSeq-1].litLength, LL_bits[llCodeTable[nbSeq-1]]);
+    if (MEM_32bits()) BIT_flushBits(&blockStream);
+    BIT_addBits(&blockStream, sequences[nbSeq-1].matchLength, ML_bits[mlCodeTable[nbSeq-1]]);
+    if (MEM_32bits()) BIT_flushBits(&blockStream);
+    if (longOffsets) {
+        U32 const ofBits = ofCodeTable[nbSeq-1];
+        unsigned const extraBits = ofBits - MIN(ofBits, STREAM_ACCUMULATOR_MIN-1);
+        if (extraBits) {
+            BIT_addBits(&blockStream, sequences[nbSeq-1].offset, extraBits);
+            BIT_flushBits(&blockStream);
+        }
+        BIT_addBits(&blockStream, sequences[nbSeq-1].offset >> extraBits,
+                    ofBits - extraBits);
+    } else {
+        BIT_addBits(&blockStream, sequences[nbSeq-1].offset, ofCodeTable[nbSeq-1]);
+    }
+    BIT_flushBits(&blockStream);
+
+    {   size_t n;
+        for (n=nbSeq-2 ; n<nbSeq ; n--) {      /* intentional underflow */
+            BYTE const llCode = llCodeTable[n];
+            BYTE const ofCode = ofCodeTable[n];
+            BYTE const mlCode = mlCodeTable[n];
+            U32  const llBits = LL_bits[llCode];
+            U32  const ofBits = ofCode;
+            U32  const mlBits = ML_bits[mlCode];
+            DEBUGLOG(6, "encoding: litlen:%2u - matchlen:%2u - offCode:%7u",
+                        (unsigned)sequences[n].litLength,
+                        (unsigned)sequences[n].matchLength + MINMATCH,
+                        (unsigned)sequences[n].offset);
+                                                                            /* 32b*/  /* 64b*/
+                                                                            /* (7)*/  /* (7)*/
+            FSE_encodeSymbol(&blockStream, &stateOffsetBits, ofCode);       /* 15 */  /* 15 */
+            FSE_encodeSymbol(&blockStream, &stateMatchLength, mlCode);      /* 24 */  /* 24 */
+            if (MEM_32bits()) BIT_flushBits(&blockStream);                  /* (7)*/
+            FSE_encodeSymbol(&blockStream, &stateLitLength, llCode);        /* 16 */  /* 33 */
+            if (MEM_32bits() || (ofBits+mlBits+llBits >= 64-7-(LLFSELog+MLFSELog+OffFSELog)))
+                BIT_flushBits(&blockStream);                                /* (7)*/
+            BIT_addBits(&blockStream, sequences[n].litLength, llBits);
+            if (MEM_32bits() && ((llBits+mlBits)>24)) BIT_flushBits(&blockStream);
+            BIT_addBits(&blockStream, sequences[n].matchLength, mlBits);
+            if (MEM_32bits() || (ofBits+mlBits+llBits > 56)) BIT_flushBits(&blockStream);
+            if (longOffsets) {
+                unsigned const extraBits = ofBits - MIN(ofBits, STREAM_ACCUMULATOR_MIN-1);
+                if (extraBits) {
+                    BIT_addBits(&blockStream, sequences[n].offset, extraBits);
+                    BIT_flushBits(&blockStream);                            /* (7)*/
+                }
+                BIT_addBits(&blockStream, sequences[n].offset >> extraBits,
+                            ofBits - extraBits);                            /* 31 */
+            } else {
+                BIT_addBits(&blockStream, sequences[n].offset, ofBits);     /* 31 */
+            }
+            BIT_flushBits(&blockStream);                                    /* (7)*/
+            DEBUGLOG(7, "remaining space : %i", (int)(blockStream.endPtr - blockStream.ptr));
+    }   }
+
+    DEBUGLOG(6, "ZSTD_encodeSequences: flushing ML state with %u bits", stateMatchLength.stateLog);
+    FSE_flushCState(&blockStream, &stateMatchLength);
+    DEBUGLOG(6, "ZSTD_encodeSequences: flushing Off state with %u bits", stateOffsetBits.stateLog);
+    FSE_flushCState(&blockStream, &stateOffsetBits);
+    DEBUGLOG(6, "ZSTD_encodeSequences: flushing LL state with %u bits", stateLitLength.stateLog);
+    FSE_flushCState(&blockStream, &stateLitLength);
+
+    {   size_t const streamSize = BIT_closeCStream(&blockStream);
+        RETURN_ERROR_IF(streamSize==0, dstSize_tooSmall, "not enough space");
+        return streamSize;
+    }
+}
+
+static size_t
+ZSTD_encodeSequences_default(
+            void* dst, size_t dstCapacity,
+            FSE_CTable const* CTable_MatchLength, BYTE const* mlCodeTable,
+            FSE_CTable const* CTable_OffsetBits, BYTE const* ofCodeTable,
+            FSE_CTable const* CTable_LitLength, BYTE const* llCodeTable,
+            seqDef const* sequences, size_t nbSeq, int longOffsets)
+{
+    return ZSTD_encodeSequences_body(dst, dstCapacity,
+                                    CTable_MatchLength, mlCodeTable,
+                                    CTable_OffsetBits, ofCodeTable,
+                                    CTable_LitLength, llCodeTable,
+                                    sequences, nbSeq, longOffsets);
+}
+
+
+#if DYNAMIC_BMI2
+
+static TARGET_ATTRIBUTE("bmi2") size_t
+ZSTD_encodeSequences_bmi2(
+            void* dst, size_t dstCapacity,
+            FSE_CTable const* CTable_MatchLength, BYTE const* mlCodeTable,
+            FSE_CTable const* CTable_OffsetBits, BYTE const* ofCodeTable,
+            FSE_CTable const* CTable_LitLength, BYTE const* llCodeTable,
+            seqDef const* sequences, size_t nbSeq, int longOffsets)
+{
+    return ZSTD_encodeSequences_body(dst, dstCapacity,
+                                    CTable_MatchLength, mlCodeTable,
+                                    CTable_OffsetBits, ofCodeTable,
+                                    CTable_LitLength, llCodeTable,
+                                    sequences, nbSeq, longOffsets);
+}
+
+#endif
+
+size_t ZSTD_encodeSequences(
+            void* dst, size_t dstCapacity,
+            FSE_CTable const* CTable_MatchLength, BYTE const* mlCodeTable,
+            FSE_CTable const* CTable_OffsetBits, BYTE const* ofCodeTable,
+            FSE_CTable const* CTable_LitLength, BYTE const* llCodeTable,
+            seqDef const* sequences, size_t nbSeq, int longOffsets, int bmi2)
+{
+    DEBUGLOG(5, "ZSTD_encodeSequences: dstCapacity = %u", (unsigned)dstCapacity);
+#if DYNAMIC_BMI2
+    if (bmi2) {
+        return ZSTD_encodeSequences_bmi2(dst, dstCapacity,
+                                         CTable_MatchLength, mlCodeTable,
+                                         CTable_OffsetBits, ofCodeTable,
+                                         CTable_LitLength, llCodeTable,
+                                         sequences, nbSeq, longOffsets);
+    }
+#endif
+    (void)bmi2;
+    return ZSTD_encodeSequences_default(dst, dstCapacity,
+                                        CTable_MatchLength, mlCodeTable,
+                                        CTable_OffsetBits, ofCodeTable,
+                                        CTable_LitLength, llCodeTable,
+                                        sequences, nbSeq, longOffsets);
+}
diff --git a/lib/zstd/compress/zstd_compress_sequences.h b/lib/zstd/compress/zstd_compress_sequences.h
new file mode 100644
index 000000000000..7991364c2f71
--- /dev/null
+++ b/lib/zstd/compress/zstd_compress_sequences.h
@@ -0,0 +1,54 @@
+/*
+ * Copyright (c) Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+#ifndef ZSTD_COMPRESS_SEQUENCES_H
+#define ZSTD_COMPRESS_SEQUENCES_H
+
+#include "../common/fse.h" /* FSE_repeat, FSE_CTable */
+#include "../common/zstd_internal.h" /* symbolEncodingType_e, ZSTD_strategy */
+
+typedef enum {
+    ZSTD_defaultDisallowed = 0,
+    ZSTD_defaultAllowed = 1
+} ZSTD_defaultPolicy_e;
+
+symbolEncodingType_e
+ZSTD_selectEncodingType(
+        FSE_repeat* repeatMode, unsigned const* count, unsigned const max,
+        size_t const mostFrequent, size_t nbSeq, unsigned const FSELog,
+        FSE_CTable const* prevCTable,
+        short const* defaultNorm, U32 defaultNormLog,
+        ZSTD_defaultPolicy_e const isDefaultAllowed,
+        ZSTD_strategy const strategy);
+
+size_t
+ZSTD_buildCTable(void* dst, size_t dstCapacity,
+                FSE_CTable* nextCTable, U32 FSELog, symbolEncodingType_e type,
+                unsigned* count, U32 max,
+                const BYTE* codeTable, size_t nbSeq,
+                const S16* defaultNorm, U32 defaultNormLog, U32 defaultMax,
+                const FSE_CTable* prevCTable, size_t prevCTableSize,
+                void* entropyWorkspace, size_t entropyWorkspaceSize);
+
+size_t ZSTD_encodeSequences(
+            void* dst, size_t dstCapacity,
+            FSE_CTable const* CTable_MatchLength, BYTE const* mlCodeTable,
+            FSE_CTable const* CTable_OffsetBits, BYTE const* ofCodeTable,
+            FSE_CTable const* CTable_LitLength, BYTE const* llCodeTable,
+            seqDef const* sequences, size_t nbSeq, int longOffsets, int bmi2);
+
+size_t ZSTD_fseBitCost(
+    FSE_CTable const* ctable,
+    unsigned const* count,
+    unsigned const max);
+
+size_t ZSTD_crossEntropyCost(short const* norm, unsigned accuracyLog,
+                             unsigned const* count, unsigned const max);
+#endif /* ZSTD_COMPRESS_SEQUENCES_H */
diff --git a/lib/zstd/compress/zstd_compress_superblock.c b/lib/zstd/compress/zstd_compress_superblock.c
new file mode 100644
index 000000000000..b0610b255653
--- /dev/null
+++ b/lib/zstd/compress/zstd_compress_superblock.c
@@ -0,0 +1,852 @@
+/*
+ * Copyright (c) Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+ /*-*************************************
+ *  Dependencies
+ ***************************************/
+#include "zstd_compress_superblock.h"
+
+#include "../common/zstd_internal.h"  /* ZSTD_getSequenceLength */
+#include "hist.h"                     /* HIST_countFast_wksp */
+#include "zstd_compress_internal.h"
+#include "zstd_compress_sequences.h"
+#include "zstd_compress_literals.h"
+
+/*-*************************************
+*  Superblock entropy buffer structs
+***************************************/
+/* ZSTD_hufCTablesMetadata_t :
+ *  Stores Literals Block Type for a super-block in hType, and
+ *  huffman tree description in hufDesBuffer.
+ *  hufDesSize refers to the size of huffman tree description in bytes.
+ *  This metadata is populated in ZSTD_buildSuperBlockEntropy_literal() */
+typedef struct {
+    symbolEncodingType_e hType;
+    BYTE hufDesBuffer[ZSTD_MAX_HUF_HEADER_SIZE];
+    size_t hufDesSize;
+} ZSTD_hufCTablesMetadata_t;
+
+/* ZSTD_fseCTablesMetadata_t :
+ *  Stores symbol compression modes for a super-block in {ll, ol, ml}Type, and
+ *  fse tables in fseTablesBuffer.
+ *  fseTablesSize refers to the size of fse tables in bytes.
+ *  This metadata is populated in ZSTD_buildSuperBlockEntropy_sequences() */
+typedef struct {
+    symbolEncodingType_e llType;
+    symbolEncodingType_e ofType;
+    symbolEncodingType_e mlType;
+    BYTE fseTablesBuffer[ZSTD_MAX_FSE_HEADERS_SIZE];
+    size_t fseTablesSize;
+    size_t lastCountSize; /* This is to account for bug in 1.3.4. More detail in ZSTD_compressSubBlock_sequences() */
+} ZSTD_fseCTablesMetadata_t;
+
+typedef struct {
+    ZSTD_hufCTablesMetadata_t hufMetadata;
+    ZSTD_fseCTablesMetadata_t fseMetadata;
+} ZSTD_entropyCTablesMetadata_t;
+
+
+/* ZSTD_buildSuperBlockEntropy_literal() :
+ *  Builds entropy for the super-block literals.
+ *  Stores literals block type (raw, rle, compressed, repeat) and
+ *  huffman description table to hufMetadata.
+ *  @return : size of huffman description table or error code */
+static size_t ZSTD_buildSuperBlockEntropy_literal(void* const src, size_t srcSize,
+                                            const ZSTD_hufCTables_t* prevHuf,
+                                                  ZSTD_hufCTables_t* nextHuf,
+                                                  ZSTD_hufCTablesMetadata_t* hufMetadata,
+                                                  const int disableLiteralsCompression,
+                                                  void* workspace, size_t wkspSize)
+{
+    BYTE* const wkspStart = (BYTE*)workspace;
+    BYTE* const wkspEnd = wkspStart + wkspSize;
+    BYTE* const countWkspStart = wkspStart;
+    unsigned* const countWksp = (unsigned*)workspace;
+    const size_t countWkspSize = (HUF_SYMBOLVALUE_MAX + 1) * sizeof(unsigned);
+    BYTE* const nodeWksp = countWkspStart + countWkspSize;
+    const size_t nodeWkspSize = wkspEnd-nodeWksp;
+    unsigned maxSymbolValue = 255;
+    unsigned huffLog = HUF_TABLELOG_DEFAULT;
+    HUF_repeat repeat = prevHuf->repeatMode;
+
+    DEBUGLOG(5, "ZSTD_buildSuperBlockEntropy_literal (srcSize=%zu)", srcSize);
+
+    /* Prepare nextEntropy assuming reusing the existing table */
+    ZSTD_memcpy(nextHuf, prevHuf, sizeof(*prevHuf));
+
+    if (disableLiteralsCompression) {
+        DEBUGLOG(5, "set_basic - disabled");
+        hufMetadata->hType = set_basic;
+        return 0;
+    }
+
+    /* small ? don't even attempt compression (speed opt) */
+#   define COMPRESS_LITERALS_SIZE_MIN 63
+    {   size_t const minLitSize = (prevHuf->repeatMode == HUF_repeat_valid) ? 6 : COMPRESS_LITERALS_SIZE_MIN;
+        if (srcSize <= minLitSize) {
+            DEBUGLOG(5, "set_basic - too small");
+            hufMetadata->hType = set_basic;
+            return 0;
+        }
+    }
+
+    /* Scan input and build symbol stats */
+    {   size_t const largest = HIST_count_wksp (countWksp, &maxSymbolValue, (const BYTE*)src, srcSize, workspace, wkspSize);
+        FORWARD_IF_ERROR(largest, "HIST_count_wksp failed");
+        if (largest == srcSize) {
+            DEBUGLOG(5, "set_rle");
+            hufMetadata->hType = set_rle;
+            return 0;
+        }
+        if (largest <= (srcSize >> 7)+4) {
+            DEBUGLOG(5, "set_basic - no gain");
+            hufMetadata->hType = set_basic;
+            return 0;
+        }
+    }
+
+    /* Validate the previous Huffman table */
+    if (repeat == HUF_repeat_check && !HUF_validateCTable((HUF_CElt const*)prevHuf->CTable, countWksp, maxSymbolValue)) {
+        repeat = HUF_repeat_none;
+    }
+
+    /* Build Huffman Tree */
+    ZSTD_memset(nextHuf->CTable, 0, sizeof(nextHuf->CTable));
+    huffLog = HUF_optimalTableLog(huffLog, srcSize, maxSymbolValue);
+    {   size_t const maxBits = HUF_buildCTable_wksp((HUF_CElt*)nextHuf->CTable, countWksp,
+                                                    maxSymbolValue, huffLog,
+                                                    nodeWksp, nodeWkspSize);
+        FORWARD_IF_ERROR(maxBits, "HUF_buildCTable_wksp");
+        huffLog = (U32)maxBits;
+        {   /* Build and write the CTable */
+            size_t const newCSize = HUF_estimateCompressedSize(
+                    (HUF_CElt*)nextHuf->CTable, countWksp, maxSymbolValue);
+            size_t const hSize = HUF_writeCTable_wksp(
+                    hufMetadata->hufDesBuffer, sizeof(hufMetadata->hufDesBuffer),
+                    (HUF_CElt*)nextHuf->CTable, maxSymbolValue, huffLog,
+                    nodeWksp, nodeWkspSize);
+            /* Check against repeating the previous CTable */
+            if (repeat != HUF_repeat_none) {
+                size_t const oldCSize = HUF_estimateCompressedSize(
+                        (HUF_CElt const*)prevHuf->CTable, countWksp, maxSymbolValue);
+                if (oldCSize < srcSize && (oldCSize <= hSize + newCSize || hSize + 12 >= srcSize)) {
+                    DEBUGLOG(5, "set_repeat - smaller");
+                    ZSTD_memcpy(nextHuf, prevHuf, sizeof(*prevHuf));
+                    hufMetadata->hType = set_repeat;
+                    return 0;
+                }
+            }
+            if (newCSize + hSize >= srcSize) {
+                DEBUGLOG(5, "set_basic - no gains");
+                ZSTD_memcpy(nextHuf, prevHuf, sizeof(*prevHuf));
+                hufMetadata->hType = set_basic;
+                return 0;
+            }
+            DEBUGLOG(5, "set_compressed (hSize=%u)", (U32)hSize);
+            hufMetadata->hType = set_compressed;
+            nextHuf->repeatMode = HUF_repeat_check;
+            return hSize;
+        }
+    }
+}
+
+/* ZSTD_buildSuperBlockEntropy_sequences() :
+ *  Builds entropy for the super-block sequences.
+ *  Stores symbol compression modes and fse table to fseMetadata.
+ *  @return : size of fse tables or error code */
+static size_t ZSTD_buildSuperBlockEntropy_sequences(seqStore_t* seqStorePtr,
+                                              const ZSTD_fseCTables_t* prevEntropy,
+                                                    ZSTD_fseCTables_t* nextEntropy,
+                                              const ZSTD_CCtx_params* cctxParams,
+                                                    ZSTD_fseCTablesMetadata_t* fseMetadata,
+                                                    void* workspace, size_t wkspSize)
+{
+    BYTE* const wkspStart = (BYTE*)workspace;
+    BYTE* const wkspEnd = wkspStart + wkspSize;
+    BYTE* const countWkspStart = wkspStart;
+    unsigned* const countWksp = (unsigned*)workspace;
+    const size_t countWkspSize = (MaxSeq + 1) * sizeof(unsigned);
+    BYTE* const cTableWksp = countWkspStart + countWkspSize;
+    const size_t cTableWkspSize = wkspEnd-cTableWksp;
+    ZSTD_strategy const strategy = cctxParams->cParams.strategy;
+    FSE_CTable* CTable_LitLength = nextEntropy->litlengthCTable;
+    FSE_CTable* CTable_OffsetBits = nextEntropy->offcodeCTable;
+    FSE_CTable* CTable_MatchLength = nextEntropy->matchlengthCTable;
+    const BYTE* const ofCodeTable = seqStorePtr->ofCode;
+    const BYTE* const llCodeTable = seqStorePtr->llCode;
+    const BYTE* const mlCodeTable = seqStorePtr->mlCode;
+    size_t const nbSeq = seqStorePtr->sequences - seqStorePtr->sequencesStart;
+    BYTE* const ostart = fseMetadata->fseTablesBuffer;
+    BYTE* const oend = ostart + sizeof(fseMetadata->fseTablesBuffer);
+    BYTE* op = ostart;
+
+    assert(cTableWkspSize >= (1 << MaxFSELog) * sizeof(FSE_FUNCTION_TYPE));
+    DEBUGLOG(5, "ZSTD_buildSuperBlockEntropy_sequences (nbSeq=%zu)", nbSeq);
+    ZSTD_memset(workspace, 0, wkspSize);
+
+    fseMetadata->lastCountSize = 0;
+    /* convert length/distances into codes */
+    ZSTD_seqToCodes(seqStorePtr);
+    /* build CTable for Literal Lengths */
+    {   U32 LLtype;
+        unsigned max = MaxLL;
+        size_t const mostFrequent = HIST_countFast_wksp(countWksp, &max, llCodeTable, nbSeq, workspace, wkspSize);  /* can't fail */
+        DEBUGLOG(5, "Building LL table");
+        nextEntropy->litlength_repeatMode = prevEntropy->litlength_repeatMode;
+        LLtype = ZSTD_selectEncodingType(&nextEntropy->litlength_repeatMode,
+                                        countWksp, max, mostFrequent, nbSeq,
+                                        LLFSELog, prevEntropy->litlengthCTable,
+                                        LL_defaultNorm, LL_defaultNormLog,
+                                        ZSTD_defaultAllowed, strategy);
+        assert(set_basic < set_compressed && set_rle < set_compressed);
+        assert(!(LLtype < set_compressed && nextEntropy->litlength_repeatMode != FSE_repeat_none)); /* We don't copy tables */
+        {   size_t const countSize = ZSTD_buildCTable(op, oend - op, CTable_LitLength, LLFSELog, (symbolEncodingType_e)LLtype,
+                                                    countWksp, max, llCodeTable, nbSeq, LL_defaultNorm, LL_defaultNormLog, MaxLL,
+                                                    prevEntropy->litlengthCTable, sizeof(prevEntropy->litlengthCTable),
+                                                    cTableWksp, cTableWkspSize);
+            FORWARD_IF_ERROR(countSize, "ZSTD_buildCTable for LitLens failed");
+            if (LLtype == set_compressed)
+                fseMetadata->lastCountSize = countSize;
+            op += countSize;
+            fseMetadata->llType = (symbolEncodingType_e) LLtype;
+    }   }
+    /* build CTable for Offsets */
+    {   U32 Offtype;
+        unsigned max = MaxOff;
+        size_t const mostFrequent = HIST_countFast_wksp(countWksp, &max, ofCodeTable, nbSeq, workspace, wkspSize);  /* can't fail */
+        /* We can only use the basic table if max <= DefaultMaxOff, otherwise the offsets are too large */
+        ZSTD_defaultPolicy_e const defaultPolicy = (max <= DefaultMaxOff) ? ZSTD_defaultAllowed : ZSTD_defaultDisallowed;
+        DEBUGLOG(5, "Building OF table");
+        nextEntropy->offcode_repeatMode = prevEntropy->offcode_repeatMode;
+        Offtype = ZSTD_selectEncodingType(&nextEntropy->offcode_repeatMode,
+                                        countWksp, max, mostFrequent, nbSeq,
+                                        OffFSELog, prevEntropy->offcodeCTable,
+                                        OF_defaultNorm, OF_defaultNormLog,
+                                        defaultPolicy, strategy);
+        assert(!(Offtype < set_compressed && nextEntropy->offcode_repeatMode != FSE_repeat_none)); /* We don't copy tables */
+        {   size_t const countSize = ZSTD_buildCTable(op, oend - op, CTable_OffsetBits, OffFSELog, (symbolEncodingType_e)Offtype,
+                                                    countWksp, max, ofCodeTable, nbSeq, OF_defaultNorm, OF_defaultNormLog, DefaultMaxOff,
+                                                    prevEntropy->offcodeCTable, sizeof(prevEntropy->offcodeCTable),
+                                                    cTableWksp, cTableWkspSize);
+            FORWARD_IF_ERROR(countSize, "ZSTD_buildCTable for Offsets failed");
+            if (Offtype == set_compressed)
+                fseMetadata->lastCountSize = countSize;
+            op += countSize;
+            fseMetadata->ofType = (symbolEncodingType_e) Offtype;
+    }   }
+    /* build CTable for MatchLengths */
+    {   U32 MLtype;
+        unsigned max = MaxML;
+        size_t const mostFrequent = HIST_countFast_wksp(countWksp, &max, mlCodeTable, nbSeq, workspace, wkspSize);   /* can't fail */
+        DEBUGLOG(5, "Building ML table (remaining space : %i)", (int)(oend-op));
+        nextEntropy->matchlength_repeatMode = prevEntropy->matchlength_repeatMode;
+        MLtype = ZSTD_selectEncodingType(&nextEntropy->matchlength_repeatMode,
+                                        countWksp, max, mostFrequent, nbSeq,
+                                        MLFSELog, prevEntropy->matchlengthCTable,
+                                        ML_defaultNorm, ML_defaultNormLog,
+                                        ZSTD_defaultAllowed, strategy);
+        assert(!(MLtype < set_compressed && nextEntropy->matchlength_repeatMode != FSE_repeat_none)); /* We don't copy tables */
+        {   size_t const countSize = ZSTD_buildCTable(op, oend - op, CTable_MatchLength, MLFSELog, (symbolEncodingType_e)MLtype,
+                                                    countWksp, max, mlCodeTable, nbSeq, ML_defaultNorm, ML_defaultNormLog, MaxML,
+                                                    prevEntropy->matchlengthCTable, sizeof(prevEntropy->matchlengthCTable),
+                                                    cTableWksp, cTableWkspSize);
+            FORWARD_IF_ERROR(countSize, "ZSTD_buildCTable for MatchLengths failed");
+            if (MLtype == set_compressed)
+                fseMetadata->lastCountSize = countSize;
+            op += countSize;
+            fseMetadata->mlType = (symbolEncodingType_e) MLtype;
+    }   }
+    assert((size_t) (op-ostart) <= sizeof(fseMetadata->fseTablesBuffer));
+    return op-ostart;
+}
+
+
+/* ZSTD_buildSuperBlockEntropy() :
+ *  Builds entropy for the super-block.
+ *  @return : 0 on success or error code */
+static size_t
+ZSTD_buildSuperBlockEntropy(seqStore_t* seqStorePtr,
+                      const ZSTD_entropyCTables_t* prevEntropy,
+                            ZSTD_entropyCTables_t* nextEntropy,
+                      const ZSTD_CCtx_params* cctxParams,
+                            ZSTD_entropyCTablesMetadata_t* entropyMetadata,
+                            void* workspace, size_t wkspSize)
+{
+    size_t const litSize = seqStorePtr->lit - seqStorePtr->litStart;
+    DEBUGLOG(5, "ZSTD_buildSuperBlockEntropy");
+    entropyMetadata->hufMetadata.hufDesSize =
+        ZSTD_buildSuperBlockEntropy_literal(seqStorePtr->litStart, litSize,
+                                            &prevEntropy->huf, &nextEntropy->huf,
+                                            &entropyMetadata->hufMetadata,
+                                            ZSTD_disableLiteralsCompression(cctxParams),
+                                            workspace, wkspSize);
+    FORWARD_IF_ERROR(entropyMetadata->hufMetadata.hufDesSize, "ZSTD_buildSuperBlockEntropy_literal failed");
+    entropyMetadata->fseMetadata.fseTablesSize =
+        ZSTD_buildSuperBlockEntropy_sequences(seqStorePtr,
+                                              &prevEntropy->fse, &nextEntropy->fse,
+                                              cctxParams,
+                                              &entropyMetadata->fseMetadata,
+                                              workspace, wkspSize);
+    FORWARD_IF_ERROR(entropyMetadata->fseMetadata.fseTablesSize, "ZSTD_buildSuperBlockEntropy_sequences failed");
+    return 0;
+}
+
+/* ZSTD_compressSubBlock_literal() :
+ *  Compresses literals section for a sub-block.
+ *  When we have to write the Huffman table we will sometimes choose a header
+ *  size larger than necessary. This is because we have to pick the header size
+ *  before we know the table size + compressed size, so we have a bound on the
+ *  table size. If we guessed incorrectly, we fall back to uncompressed literals.
+ *
+ *  We write the header when writeEntropy=1 and set entropyWritten=1 when we succeeded
+ *  in writing the header, otherwise it is set to 0.
+ *
+ *  hufMetadata->hType has literals block type info.
+ *      If it is set_basic, all sub-blocks literals section will be Raw_Literals_Block.
+ *      If it is set_rle, all sub-blocks literals section will be RLE_Literals_Block.
+ *      If it is set_compressed, first sub-block's literals section will be Compressed_Literals_Block
+ *      If it is set_compressed, first sub-block's literals section will be Treeless_Literals_Block
+ *      and the following sub-blocks' literals sections will be Treeless_Literals_Block.
+ *  @return : compressed size of literals section of a sub-block
+ *            Or 0 if it unable to compress.
+ *            Or error code */
+static size_t ZSTD_compressSubBlock_literal(const HUF_CElt* hufTable,
+                                    const ZSTD_hufCTablesMetadata_t* hufMetadata,
+                                    const BYTE* literals, size_t litSize,
+                                    void* dst, size_t dstSize,
+                                    const int bmi2, int writeEntropy, int* entropyWritten)
+{
+    size_t const header = writeEntropy ? 200 : 0;
+    size_t const lhSize = 3 + (litSize >= (1 KB - header)) + (litSize >= (16 KB - header));
+    BYTE* const ostart = (BYTE*)dst;
+    BYTE* const oend = ostart + dstSize;
+    BYTE* op = ostart + lhSize;
+    U32 const singleStream = lhSize == 3;
+    symbolEncodingType_e hType = writeEntropy ? hufMetadata->hType : set_repeat;
+    size_t cLitSize = 0;
+
+    (void)bmi2; /* TODO bmi2... */
+
+    DEBUGLOG(5, "ZSTD_compressSubBlock_literal (litSize=%zu, lhSize=%zu, writeEntropy=%d)", litSize, lhSize, writeEntropy);
+
+    *entropyWritten = 0;
+    if (litSize == 0 || hufMetadata->hType == set_basic) {
+      DEBUGLOG(5, "ZSTD_compressSubBlock_literal using raw literal");
+      return ZSTD_noCompressLiterals(dst, dstSize, literals, litSize);
+    } else if (hufMetadata->hType == set_rle) {
+      DEBUGLOG(5, "ZSTD_compressSubBlock_literal using rle literal");
+      return ZSTD_compressRleLiteralsBlock(dst, dstSize, literals, litSize);
+    }
+
+    assert(litSize > 0);
+    assert(hufMetadata->hType == set_compressed || hufMetadata->hType == set_repeat);
+
+    if (writeEntropy && hufMetadata->hType == set_compressed) {
+        ZSTD_memcpy(op, hufMetadata->hufDesBuffer, hufMetadata->hufDesSize);
+        op += hufMetadata->hufDesSize;
+        cLitSize += hufMetadata->hufDesSize;
+        DEBUGLOG(5, "ZSTD_compressSubBlock_literal (hSize=%zu)", hufMetadata->hufDesSize);
+    }
+
+    /* TODO bmi2 */
+    {   const size_t cSize = singleStream ? HUF_compress1X_usingCTable(op, oend-op, literals, litSize, hufTable)
+                                          : HUF_compress4X_usingCTable(op, oend-op, literals, litSize, hufTable);
+        op += cSize;
+        cLitSize += cSize;
+        if (cSize == 0 || ERR_isError(cSize)) {
+            DEBUGLOG(5, "Failed to write entropy tables %s", ZSTD_getErrorName(cSize));
+            return 0;
+        }
+        /* If we expand and we aren't writing a header then emit uncompressed */
+        if (!writeEntropy && cLitSize >= litSize) {
+            DEBUGLOG(5, "ZSTD_compressSubBlock_literal using raw literal because uncompressible");
+            return ZSTD_noCompressLiterals(dst, dstSize, literals, litSize);
+        }
+        /* If we are writing headers then allow expansion that doesn't change our header size. */
+        if (lhSize < (size_t)(3 + (cLitSize >= 1 KB) + (cLitSize >= 16 KB))) {
+            assert(cLitSize > litSize);
+            DEBUGLOG(5, "Literals expanded beyond allowed header size");
+            return ZSTD_noCompressLiterals(dst, dstSize, literals, litSize);
+        }
+        DEBUGLOG(5, "ZSTD_compressSubBlock_literal (cSize=%zu)", cSize);
+    }
+
+    /* Build header */
+    switch(lhSize)
+    {
+    case 3: /* 2 - 2 - 10 - 10 */
+        {   U32 const lhc = hType + ((!singleStream) << 2) + ((U32)litSize<<4) + ((U32)cLitSize<<14);
+            MEM_writeLE24(ostart, lhc);
+            break;
+        }
+    case 4: /* 2 - 2 - 14 - 14 */
+        {   U32 const lhc = hType + (2 << 2) + ((U32)litSize<<4) + ((U32)cLitSize<<18);
+            MEM_writeLE32(ostart, lhc);
+            break;
+        }
+    case 5: /* 2 - 2 - 18 - 18 */
+        {   U32 const lhc = hType + (3 << 2) + ((U32)litSize<<4) + ((U32)cLitSize<<22);
+            MEM_writeLE32(ostart, lhc);
+            ostart[4] = (BYTE)(cLitSize >> 10);
+            break;
+        }
+    default:  /* not possible : lhSize is {3,4,5} */
+        assert(0);
+    }
+    *entropyWritten = 1;
+    DEBUGLOG(5, "Compressed literals: %u -> %u", (U32)litSize, (U32)(op-ostart));
+    return op-ostart;
+}
+
+static size_t ZSTD_seqDecompressedSize(seqStore_t const* seqStore, const seqDef* sequences, size_t nbSeq, size_t litSize, int lastSequence) {
+    const seqDef* const sstart = sequences;
+    const seqDef* const send = sequences + nbSeq;
+    const seqDef* sp = sstart;
+    size_t matchLengthSum = 0;
+    size_t litLengthSum = 0;
+    /* Only used by assert(), suppress unused variable warnings in production. */
+    (void)litLengthSum;
+    while (send-sp > 0) {
+        ZSTD_sequenceLength const seqLen = ZSTD_getSequenceLength(seqStore, sp);
+        litLengthSum += seqLen.litLength;
+        matchLengthSum += seqLen.matchLength;
+        sp++;
+    }
+    assert(litLengthSum <= litSize);
+    if (!lastSequence) {
+        assert(litLengthSum == litSize);
+    }
+    return matchLengthSum + litSize;
+}
+
+/* ZSTD_compressSubBlock_sequences() :
+ *  Compresses sequences section for a sub-block.
+ *  fseMetadata->llType, fseMetadata->ofType, and fseMetadata->mlType have
+ *  symbol compression modes for the super-block.
+ *  The first successfully compressed block will have these in its header.
+ *  We set entropyWritten=1 when we succeed in compressing the sequences.
+ *  The following sub-blocks will always have repeat mode.
+ *  @return : compressed size of sequences section of a sub-block
+ *            Or 0 if it is unable to compress
+ *            Or error code. */
+static size_t ZSTD_compressSubBlock_sequences(const ZSTD_fseCTables_t* fseTables,
+                                              const ZSTD_fseCTablesMetadata_t* fseMetadata,
+                                              const seqDef* sequences, size_t nbSeq,
+                                              const BYTE* llCode, const BYTE* mlCode, const BYTE* ofCode,
+                                              const ZSTD_CCtx_params* cctxParams,
+                                              void* dst, size_t dstCapacity,
+                                              const int bmi2, int writeEntropy, int* entropyWritten)
+{
+    const int longOffsets = cctxParams->cParams.windowLog > STREAM_ACCUMULATOR_MIN;
+    BYTE* const ostart = (BYTE*)dst;
+    BYTE* const oend = ostart + dstCapacity;
+    BYTE* op = ostart;
+    BYTE* seqHead;
+
+    DEBUGLOG(5, "ZSTD_compressSubBlock_sequences (nbSeq=%zu, writeEntropy=%d, longOffsets=%d)", nbSeq, writeEntropy, longOffsets);
+
+    *entropyWritten = 0;
+    /* Sequences Header */
+    RETURN_ERROR_IF((oend-op) < 3 /*max nbSeq Size*/ + 1 /*seqHead*/,
+                    dstSize_tooSmall, "");
+    if (nbSeq < 0x7F)
+        *op++ = (BYTE)nbSeq;
+    else if (nbSeq < LONGNBSEQ)
+        op[0] = (BYTE)((nbSeq>>8) + 0x80), op[1] = (BYTE)nbSeq, op+=2;
+    else
+        op[0]=0xFF, MEM_writeLE16(op+1, (U16)(nbSeq - LONGNBSEQ)), op+=3;
+    if (nbSeq==0) {
+        return op - ostart;
+    }
+
+    /* seqHead : flags for FSE encoding type */
+    seqHead = op++;
+
+    DEBUGLOG(5, "ZSTD_compressSubBlock_sequences (seqHeadSize=%u)", (unsigned)(op-ostart));
+
+    if (writeEntropy) {
+        const U32 LLtype = fseMetadata->llType;
+        const U32 Offtype = fseMetadata->ofType;
+        const U32 MLtype = fseMetadata->mlType;
+        DEBUGLOG(5, "ZSTD_compressSubBlock_sequences (fseTablesSize=%zu)", fseMetadata->fseTablesSize);
+        *seqHead = (BYTE)((LLtype<<6) + (Offtype<<4) + (MLtype<<2));
+        ZSTD_memcpy(op, fseMetadata->fseTablesBuffer, fseMetadata->fseTablesSize);
+        op += fseMetadata->fseTablesSize;
+    } else {
+        const U32 repeat = set_repeat;
+        *seqHead = (BYTE)((repeat<<6) + (repeat<<4) + (repeat<<2));
+    }
+
+    {   size_t const bitstreamSize = ZSTD_encodeSequences(
+                                        op, oend - op,
+                                        fseTables->matchlengthCTable, mlCode,
+                                        fseTables->offcodeCTable, ofCode,
+                                        fseTables->litlengthCTable, llCode,
+                                        sequences, nbSeq,
+                                        longOffsets, bmi2);
+        FORWARD_IF_ERROR(bitstreamSize, "ZSTD_encodeSequences failed");
+        op += bitstreamSize;
+        /* zstd versions <= 1.3.4 mistakenly report corruption when
+         * FSE_readNCount() receives a buffer < 4 bytes.
+         * Fixed by https://github.com/facebook/zstd/pull/1146.
+         * This can happen when the last set_compressed table present is 2
+         * bytes and the bitstream is only one byte.
+         * In this exceedingly rare case, we will simply emit an uncompressed
+         * block, since it isn't worth optimizing.
+         */
+#ifndef FUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION
+        if (writeEntropy && fseMetadata->lastCountSize && fseMetadata->lastCountSize + bitstreamSize < 4) {
+            /* NCountSize >= 2 && bitstreamSize > 0 ==> lastCountSize == 3 */
+            assert(fseMetadata->lastCountSize + bitstreamSize == 3);
+            DEBUGLOG(5, "Avoiding bug in zstd decoder in versions <= 1.3.4 by "
+                        "emitting an uncompressed block.");
+            return 0;
+        }
+#endif
+        DEBUGLOG(5, "ZSTD_compressSubBlock_sequences (bitstreamSize=%zu)", bitstreamSize);
+    }
+
+    /* zstd versions <= 1.4.0 mistakenly report error when
+     * sequences section body size is less than 3 bytes.
+     * Fixed by https://github.com/facebook/zstd/pull/1664.
+     * This can happen when the previous sequences section block is compressed
+     * with rle mode and the current block's sequences section is compressed
+     * with repeat mode where sequences section body size can be 1 byte.
+     */
+#ifndef FUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION
+    if (op-seqHead < 4) {
+        DEBUGLOG(5, "Avoiding bug in zstd decoder in versions <= 1.4.0 by emitting "
+                    "an uncompressed block when sequences are < 4 bytes");
+        return 0;
+    }
+#endif
+
+    *entropyWritten = 1;
+    return op - ostart;
+}
+
+/* ZSTD_compressSubBlock() :
+ *  Compresses a single sub-block.
+ *  @return : compressed size of the sub-block
+ *            Or 0 if it failed to compress. */
+static size_t ZSTD_compressSubBlock(const ZSTD_entropyCTables_t* entropy,
+                                    const ZSTD_entropyCTablesMetadata_t* entropyMetadata,
+                                    const seqDef* sequences, size_t nbSeq,
+                                    const BYTE* literals, size_t litSize,
+                                    const BYTE* llCode, const BYTE* mlCode, const BYTE* ofCode,
+                                    const ZSTD_CCtx_params* cctxParams,
+                                    void* dst, size_t dstCapacity,
+                                    const int bmi2,
+                                    int writeLitEntropy, int writeSeqEntropy,
+                                    int* litEntropyWritten, int* seqEntropyWritten,
+                                    U32 lastBlock)
+{
+    BYTE* const ostart = (BYTE*)dst;
+    BYTE* const oend = ostart + dstCapacity;
+    BYTE* op = ostart + ZSTD_blockHeaderSize;
+    DEBUGLOG(5, "ZSTD_compressSubBlock (litSize=%zu, nbSeq=%zu, writeLitEntropy=%d, writeSeqEntropy=%d, lastBlock=%d)",
+                litSize, nbSeq, writeLitEntropy, writeSeqEntropy, lastBlock);
+    {   size_t cLitSize = ZSTD_compressSubBlock_literal((const HUF_CElt*)entropy->huf.CTable,
+                                                        &entropyMetadata->hufMetadata, literals, litSize,
+                                                        op, oend-op, bmi2, writeLitEntropy, litEntropyWritten);
+        FORWARD_IF_ERROR(cLitSize, "ZSTD_compressSubBlock_literal failed");
+        if (cLitSize == 0) return 0;
+        op += cLitSize;
+    }
+    {   size_t cSeqSize = ZSTD_compressSubBlock_sequences(&entropy->fse,
+                                                  &entropyMetadata->fseMetadata,
+                                                  sequences, nbSeq,
+                                                  llCode, mlCode, ofCode,
+                                                  cctxParams,
+                                                  op, oend-op,
+                                                  bmi2, writeSeqEntropy, seqEntropyWritten);
+        FORWARD_IF_ERROR(cSeqSize, "ZSTD_compressSubBlock_sequences failed");
+        if (cSeqSize == 0) return 0;
+        op += cSeqSize;
+    }
+    /* Write block header */
+    {   size_t cSize = (op-ostart)-ZSTD_blockHeaderSize;
+        U32 const cBlockHeader24 = lastBlock + (((U32)bt_compressed)<<1) + (U32)(cSize << 3);
+        MEM_writeLE24(ostart, cBlockHeader24);
+    }
+    return op-ostart;
+}
+
+static size_t ZSTD_estimateSubBlockSize_literal(const BYTE* literals, size_t litSize,
+                                                const ZSTD_hufCTables_t* huf,
+                                                const ZSTD_hufCTablesMetadata_t* hufMetadata,
+                                                void* workspace, size_t wkspSize,
+                                                int writeEntropy)
+{
+    unsigned* const countWksp = (unsigned*)workspace;
+    unsigned maxSymbolValue = 255;
+    size_t literalSectionHeaderSize = 3; /* Use hard coded size of 3 bytes */
+
+    if (hufMetadata->hType == set_basic) return litSize;
+    else if (hufMetadata->hType == set_rle) return 1;
+    else if (hufMetadata->hType == set_compressed || hufMetadata->hType == set_repeat) {
+        size_t const largest = HIST_count_wksp (countWksp, &maxSymbolValue, (const BYTE*)literals, litSize, workspace, wkspSize);
+        if (ZSTD_isError(largest)) return litSize;
+        {   size_t cLitSizeEstimate = HUF_estimateCompressedSize((const HUF_CElt*)huf->CTable, countWksp, maxSymbolValue);
+            if (writeEntropy) cLitSizeEstimate += hufMetadata->hufDesSize;
+            return cLitSizeEstimate + literalSectionHeaderSize;
+    }   }
+    assert(0); /* impossible */
+    return 0;
+}
+
+static size_t ZSTD_estimateSubBlockSize_symbolType(symbolEncodingType_e type,
+                        const BYTE* codeTable, unsigned maxCode,
+                        size_t nbSeq, const FSE_CTable* fseCTable,
+                        const U32* additionalBits,
+                        short const* defaultNorm, U32 defaultNormLog, U32 defaultMax,
+                        void* workspace, size_t wkspSize)
+{
+    unsigned* const countWksp = (unsigned*)workspace;
+    const BYTE* ctp = codeTable;
+    const BYTE* const ctStart = ctp;
+    const BYTE* const ctEnd = ctStart + nbSeq;
+    size_t cSymbolTypeSizeEstimateInBits = 0;
+    unsigned max = maxCode;
+
+    HIST_countFast_wksp(countWksp, &max, codeTable, nbSeq, workspace, wkspSize);  /* can't fail */
+    if (type == set_basic) {
+        /* We selected this encoding type, so it must be valid. */
+        assert(max <= defaultMax);
+        cSymbolTypeSizeEstimateInBits = max <= defaultMax
+                ? ZSTD_crossEntropyCost(defaultNorm, defaultNormLog, countWksp, max)
+                : ERROR(GENERIC);
+    } else if (type == set_rle) {
+        cSymbolTypeSizeEstimateInBits = 0;
+    } else if (type == set_compressed || type == set_repeat) {
+        cSymbolTypeSizeEstimateInBits = ZSTD_fseBitCost(fseCTable, countWksp, max);
+    }
+    if (ZSTD_isError(cSymbolTypeSizeEstimateInBits)) return nbSeq * 10;
+    while (ctp < ctEnd) {
+        if (additionalBits) cSymbolTypeSizeEstimateInBits += additionalBits[*ctp];
+        else cSymbolTypeSizeEstimateInBits += *ctp; /* for offset, offset code is also the number of additional bits */
+        ctp++;
+    }
+    return cSymbolTypeSizeEstimateInBits / 8;
+}
+
+static size_t ZSTD_estimateSubBlockSize_sequences(const BYTE* ofCodeTable,
+                                                  const BYTE* llCodeTable,
+                                                  const BYTE* mlCodeTable,
+                                                  size_t nbSeq,
+                                                  const ZSTD_fseCTables_t* fseTables,
+                                                  const ZSTD_fseCTablesMetadata_t* fseMetadata,
+                                                  void* workspace, size_t wkspSize,
+                                                  int writeEntropy)
+{
+    size_t sequencesSectionHeaderSize = 3; /* Use hard coded size of 3 bytes */
+    size_t cSeqSizeEstimate = 0;
+    cSeqSizeEstimate += ZSTD_estimateSubBlockSize_symbolType(fseMetadata->ofType, ofCodeTable, MaxOff,
+                                         nbSeq, fseTables->offcodeCTable, NULL,
+                                         OF_defaultNorm, OF_defaultNormLog, DefaultMaxOff,
+                                         workspace, wkspSize);
+    cSeqSizeEstimate += ZSTD_estimateSubBlockSize_symbolType(fseMetadata->llType, llCodeTable, MaxLL,
+                                         nbSeq, fseTables->litlengthCTable, LL_bits,
+                                         LL_defaultNorm, LL_defaultNormLog, MaxLL,
+                                         workspace, wkspSize);
+    cSeqSizeEstimate += ZSTD_estimateSubBlockSize_symbolType(fseMetadata->mlType, mlCodeTable, MaxML,
+                                         nbSeq, fseTables->matchlengthCTable, ML_bits,
+                                         ML_defaultNorm, ML_defaultNormLog, MaxML,
+                                         workspace, wkspSize);
+    if (writeEntropy) cSeqSizeEstimate += fseMetadata->fseTablesSize;
+    return cSeqSizeEstimate + sequencesSectionHeaderSize;
+}
+
+static size_t ZSTD_estimateSubBlockSize(const BYTE* literals, size_t litSize,
+                                        const BYTE* ofCodeTable,
+                                        const BYTE* llCodeTable,
+                                        const BYTE* mlCodeTable,
+                                        size_t nbSeq,
+                                        const ZSTD_entropyCTables_t* entropy,
+                                        const ZSTD_entropyCTablesMetadata_t* entropyMetadata,
+                                        void* workspace, size_t wkspSize,
+                                        int writeLitEntropy, int writeSeqEntropy) {
+    size_t cSizeEstimate = 0;
+    cSizeEstimate += ZSTD_estimateSubBlockSize_literal(literals, litSize,
+                                                         &entropy->huf, &entropyMetadata->hufMetadata,
+                                                         workspace, wkspSize, writeLitEntropy);
+    cSizeEstimate += ZSTD_estimateSubBlockSize_sequences(ofCodeTable, llCodeTable, mlCodeTable,
+                                                         nbSeq, &entropy->fse, &entropyMetadata->fseMetadata,
+                                                         workspace, wkspSize, writeSeqEntropy);
+    return cSizeEstimate + ZSTD_blockHeaderSize;
+}
+
+static int ZSTD_needSequenceEntropyTables(ZSTD_fseCTablesMetadata_t const* fseMetadata)
+{
+    if (fseMetadata->llType == set_compressed || fseMetadata->llType == set_rle)
+        return 1;
+    if (fseMetadata->mlType == set_compressed || fseMetadata->mlType == set_rle)
+        return 1;
+    if (fseMetadata->ofType == set_compressed || fseMetadata->ofType == set_rle)
+        return 1;
+    return 0;
+}
+
+/* ZSTD_compressSubBlock_multi() :
+ *  Breaks super-block into multiple sub-blocks and compresses them.
+ *  Entropy will be written to the first block.
+ *  The following blocks will use repeat mode to compress.
+ *  All sub-blocks are compressed blocks (no raw or rle blocks).
+ *  @return : compressed size of the super block (which is multiple ZSTD blocks)
+ *            Or 0 if it failed to compress. */
+static size_t ZSTD_compressSubBlock_multi(const seqStore_t* seqStorePtr,
+                            const ZSTD_compressedBlockState_t* prevCBlock,
+                            ZSTD_compressedBlockState_t* nextCBlock,
+                            const ZSTD_entropyCTablesMetadata_t* entropyMetadata,
+                            const ZSTD_CCtx_params* cctxParams,
+                                  void* dst, size_t dstCapacity,
+                            const void* src, size_t srcSize,
+                            const int bmi2, U32 lastBlock,
+                            void* workspace, size_t wkspSize)
+{
+    const seqDef* const sstart = seqStorePtr->sequencesStart;
+    const seqDef* const send = seqStorePtr->sequences;
+    const seqDef* sp = sstart;
+    const BYTE* const lstart = seqStorePtr->litStart;
+    const BYTE* const lend = seqStorePtr->lit;
+    const BYTE* lp = lstart;
+    BYTE const* ip = (BYTE const*)src;
+    BYTE const* const iend = ip + srcSize;
+    BYTE* const ostart = (BYTE*)dst;
+    BYTE* const oend = ostart + dstCapacity;
+    BYTE* op = ostart;
+    const BYTE* llCodePtr = seqStorePtr->llCode;
+    const BYTE* mlCodePtr = seqStorePtr->mlCode;
+    const BYTE* ofCodePtr = seqStorePtr->ofCode;
+    size_t targetCBlockSize = cctxParams->targetCBlockSize;
+    size_t litSize, seqCount;
+    int writeLitEntropy = entropyMetadata->hufMetadata.hType == set_compressed;
+    int writeSeqEntropy = 1;
+    int lastSequence = 0;
+
+    DEBUGLOG(5, "ZSTD_compressSubBlock_multi (litSize=%u, nbSeq=%u)",
+                (unsigned)(lend-lp), (unsigned)(send-sstart));
+
+    litSize = 0;
+    seqCount = 0;
+    do {
+        size_t cBlockSizeEstimate = 0;
+        if (sstart == send) {
+            lastSequence = 1;
+        } else {
+            const seqDef* const sequence = sp + seqCount;
+            lastSequence = sequence == send - 1;
+            litSize += ZSTD_getSequenceLength(seqStorePtr, sequence).litLength;
+            seqCount++;
+        }
+        if (lastSequence) {
+            assert(lp <= lend);
+            assert(litSize <= (size_t)(lend - lp));
+            litSize = (size_t)(lend - lp);
+        }
+        /* I think there is an optimization opportunity here.
+         * Calling ZSTD_estimateSubBlockSize for every sequence can be wasteful
+         * since it recalculates estimate from scratch.
+         * For example, it would recount literal distribution and symbol codes everytime.
+         */
+        cBlockSizeEstimate = ZSTD_estimateSubBlockSize(lp, litSize, ofCodePtr, llCodePtr, mlCodePtr, seqCount,
+                                                       &nextCBlock->entropy, entropyMetadata,
+                                                       workspace, wkspSize, writeLitEntropy, writeSeqEntropy);
+        if (cBlockSizeEstimate > targetCBlockSize || lastSequence) {
+            int litEntropyWritten = 0;
+            int seqEntropyWritten = 0;
+            const size_t decompressedSize = ZSTD_seqDecompressedSize(seqStorePtr, sp, seqCount, litSize, lastSequence);
+            const size_t cSize = ZSTD_compressSubBlock(&nextCBlock->entropy, entropyMetadata,
+                                                       sp, seqCount,
+                                                       lp, litSize,
+                                                       llCodePtr, mlCodePtr, ofCodePtr,
+                                                       cctxParams,
+                                                       op, oend-op,
+                                                       bmi2, writeLitEntropy, writeSeqEntropy,
+                                                       &litEntropyWritten, &seqEntropyWritten,
+                                                       lastBlock && lastSequence);
+            FORWARD_IF_ERROR(cSize, "ZSTD_compressSubBlock failed");
+            if (cSize > 0 && cSize < decompressedSize) {
+                DEBUGLOG(5, "Committed the sub-block");
+                assert(ip + decompressedSize <= iend);
+                ip += decompressedSize;
+                sp += seqCount;
+                lp += litSize;
+                op += cSize;
+                llCodePtr += seqCount;
+                mlCodePtr += seqCount;
+                ofCodePtr += seqCount;
+                litSize = 0;
+                seqCount = 0;
+                /* Entropy only needs to be written once */
+                if (litEntropyWritten) {
+                    writeLitEntropy = 0;
+                }
+                if (seqEntropyWritten) {
+                    writeSeqEntropy = 0;
+                }
+            }
+        }
+    } while (!lastSequence);
+    if (writeLitEntropy) {
+        DEBUGLOG(5, "ZSTD_compressSubBlock_multi has literal entropy tables unwritten");
+        ZSTD_memcpy(&nextCBlock->entropy.huf, &prevCBlock->entropy.huf, sizeof(prevCBlock->entropy.huf));
+    }
+    if (writeSeqEntropy && ZSTD_needSequenceEntropyTables(&entropyMetadata->fseMetadata)) {
+        /* If we haven't written our entropy tables, then we've violated our contract and
+         * must emit an uncompressed block.
+         */
+        DEBUGLOG(5, "ZSTD_compressSubBlock_multi has sequence entropy tables unwritten");
+        return 0;
+    }
+    if (ip < iend) {
+        size_t const cSize = ZSTD_noCompressBlock(op, oend - op, ip, iend - ip, lastBlock);
+        DEBUGLOG(5, "ZSTD_compressSubBlock_multi last sub-block uncompressed, %zu bytes", (size_t)(iend - ip));
+        FORWARD_IF_ERROR(cSize, "ZSTD_noCompressBlock failed");
+        assert(cSize != 0);
+        op += cSize;
+        /* We have to regenerate the repcodes because we've skipped some sequences */
+        if (sp < send) {
+            seqDef const* seq;
+            repcodes_t rep;
+            ZSTD_memcpy(&rep, prevCBlock->rep, sizeof(rep));
+            for (seq = sstart; seq < sp; ++seq) {
+                rep = ZSTD_updateRep(rep.rep, seq->offset - 1, ZSTD_getSequenceLength(seqStorePtr, seq).litLength == 0);
+            }
+            ZSTD_memcpy(nextCBlock->rep, &rep, sizeof(rep));
+        }
+    }
+    DEBUGLOG(5, "ZSTD_compressSubBlock_multi compressed");
+    return op-ostart;
+}
+
+size_t ZSTD_compressSuperBlock(ZSTD_CCtx* zc,
+                               void* dst, size_t dstCapacity,
+                               void const* src, size_t srcSize,
+                               unsigned lastBlock) {
+    ZSTD_entropyCTablesMetadata_t entropyMetadata;
+
+    FORWARD_IF_ERROR(ZSTD_buildSuperBlockEntropy(&zc->seqStore,
+          &zc->blockState.prevCBlock->entropy,
+          &zc->blockState.nextCBlock->entropy,
+          &zc->appliedParams,
+          &entropyMetadata,
+          zc->entropyWorkspace, ENTROPY_WORKSPACE_SIZE /* statically allocated in resetCCtx */), "");
+
+    return ZSTD_compressSubBlock_multi(&zc->seqStore,
+            zc->blockState.prevCBlock,
+            zc->blockState.nextCBlock,
+            &entropyMetadata,
+            &zc->appliedParams,
+            dst, dstCapacity,
+            src, srcSize,
+            zc->bmi2, lastBlock,
+            zc->entropyWorkspace, ENTROPY_WORKSPACE_SIZE /* statically allocated in resetCCtx */);
+}
diff --git a/lib/zstd/compress/zstd_compress_superblock.h b/lib/zstd/compress/zstd_compress_superblock.h
new file mode 100644
index 000000000000..224ece79546e
--- /dev/null
+++ b/lib/zstd/compress/zstd_compress_superblock.h
@@ -0,0 +1,32 @@
+/*
+ * Copyright (c) Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+#ifndef ZSTD_COMPRESS_ADVANCED_H
+#define ZSTD_COMPRESS_ADVANCED_H
+
+/*-*************************************
+*  Dependencies
+***************************************/
+
+#include <linux/zstd.h> /* ZSTD_CCtx */
+
+/*-*************************************
+*  Target Compressed Block Size
+***************************************/
+
+/* ZSTD_compressSuperBlock() :
+ * Used to compress a super block when targetCBlockSize is being used.
+ * The given block will be compressed into multiple sub blocks that are around targetCBlockSize. */
+size_t ZSTD_compressSuperBlock(ZSTD_CCtx* zc,
+                               void* dst, size_t dstCapacity,
+                               void const* src, size_t srcSize,
+                               unsigned lastBlock);
+
+#endif /* ZSTD_COMPRESS_ADVANCED_H */
diff --git a/lib/zstd/compress/zstd_cwksp.h b/lib/zstd/compress/zstd_cwksp.h
new file mode 100644
index 000000000000..98e359adf5d4
--- /dev/null
+++ b/lib/zstd/compress/zstd_cwksp.h
@@ -0,0 +1,482 @@
+/*
+ * Copyright (c) Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+#ifndef ZSTD_CWKSP_H
+#define ZSTD_CWKSP_H
+
+/*-*************************************
+*  Dependencies
+***************************************/
+#include "../common/zstd_internal.h"
+
+
+/*-*************************************
+*  Constants
+***************************************/
+
+/* Since the workspace is effectively its own little malloc implementation /
+ * arena, when we run under ASAN, we should similarly insert redzones between
+ * each internal element of the workspace, so ASAN will catch overruns that
+ * reach outside an object but that stay inside the workspace.
+ *
+ * This defines the size of that redzone.
+ */
+#ifndef ZSTD_CWKSP_ASAN_REDZONE_SIZE
+#define ZSTD_CWKSP_ASAN_REDZONE_SIZE 128
+#endif
+
+/*-*************************************
+*  Structures
+***************************************/
+typedef enum {
+    ZSTD_cwksp_alloc_objects,
+    ZSTD_cwksp_alloc_buffers,
+    ZSTD_cwksp_alloc_aligned
+} ZSTD_cwksp_alloc_phase_e;
+
+/*
+ * Used to describe whether the workspace is statically allocated (and will not
+ * necessarily ever be freed), or if it's dynamically allocated and we can
+ * expect a well-formed caller to free this.
+ */
+typedef enum {
+    ZSTD_cwksp_dynamic_alloc,
+    ZSTD_cwksp_static_alloc
+} ZSTD_cwksp_static_alloc_e;
+
+/*
+ * Zstd fits all its internal datastructures into a single continuous buffer,
+ * so that it only needs to perform a single OS allocation (or so that a buffer
+ * can be provided to it and it can perform no allocations at all). This buffer
+ * is called the workspace.
+ *
+ * Several optimizations complicate that process of allocating memory ranges
+ * from this workspace for each internal datastructure:
+ *
+ * - These different internal datastructures have different setup requirements:
+ *
+ *   - The static objects need to be cleared once and can then be trivially
+ *     reused for each compression.
+ *
+ *   - Various buffers don't need to be initialized at all--they are always
+ *     written into before they're read.
+ *
+ *   - The matchstate tables have a unique requirement that they don't need
+ *     their memory to be totally cleared, but they do need the memory to have
+ *     some bound, i.e., a guarantee that all values in the memory they've been
+ *     allocated is less than some maximum value (which is the starting value
+ *     for the indices that they will then use for compression). When this
+ *     guarantee is provided to them, they can use the memory without any setup
+ *     work. When it can't, they have to clear the area.
+ *
+ * - These buffers also have different alignment requirements.
+ *
+ * - We would like to reuse the objects in the workspace for multiple
+ *   compressions without having to perform any expensive reallocation or
+ *   reinitialization work.
+ *
+ * - We would like to be able to efficiently reuse the workspace across
+ *   multiple compressions **even when the compression parameters change** and
+ *   we need to resize some of the objects (where possible).
+ *
+ * To attempt to manage this buffer, given these constraints, the ZSTD_cwksp
+ * abstraction was created. It works as follows:
+ *
+ * Workspace Layout:
+ *
+ * [                        ... workspace ...                         ]
+ * [objects][tables ... ->] free space [<- ... aligned][<- ... buffers]
+ *
+ * The various objects that live in the workspace are divided into the
+ * following categories, and are allocated separately:
+ *
+ * - Static objects: this is optionally the enclosing ZSTD_CCtx or ZSTD_CDict,
+ *   so that literally everything fits in a single buffer. Note: if present,
+ *   this must be the first object in the workspace, since ZSTD_customFree{CCtx,
+ *   CDict}() rely on a pointer comparison to see whether one or two frees are
+ *   required.
+ *
+ * - Fixed size objects: these are fixed-size, fixed-count objects that are
+ *   nonetheless "dynamically" allocated in the workspace so that we can
+ *   control how they're initialized separately from the broader ZSTD_CCtx.
+ *   Examples:
+ *   - Entropy Workspace
+ *   - 2 x ZSTD_compressedBlockState_t
+ *   - CDict dictionary contents
+ *
+ * - Tables: these are any of several different datastructures (hash tables,
+ *   chain tables, binary trees) that all respect a common format: they are
+ *   uint32_t arrays, all of whose values are between 0 and (nextSrc - base).
+ *   Their sizes depend on the cparams.
+ *
+ * - Aligned: these buffers are used for various purposes that require 4 byte
+ *   alignment, but don't require any initialization before they're used.
+ *
+ * - Buffers: these buffers are used for various purposes that don't require
+ *   any alignment or initialization before they're used. This means they can
+ *   be moved around at no cost for a new compression.
+ *
+ * Allocating Memory:
+ *
+ * The various types of objects must be allocated in order, so they can be
+ * correctly packed into the workspace buffer. That order is:
+ *
+ * 1. Objects
+ * 2. Buffers
+ * 3. Aligned
+ * 4. Tables
+ *
+ * Attempts to reserve objects of different types out of order will fail.
+ */
+typedef struct {
+    void* workspace;
+    void* workspaceEnd;
+
+    void* objectEnd;
+    void* tableEnd;
+    void* tableValidEnd;
+    void* allocStart;
+
+    BYTE allocFailed;
+    int workspaceOversizedDuration;
+    ZSTD_cwksp_alloc_phase_e phase;
+    ZSTD_cwksp_static_alloc_e isStatic;
+} ZSTD_cwksp;
+
+/*-*************************************
+*  Functions
+***************************************/
+
+MEM_STATIC size_t ZSTD_cwksp_available_space(ZSTD_cwksp* ws);
+
+MEM_STATIC void ZSTD_cwksp_assert_internal_consistency(ZSTD_cwksp* ws) {
+    (void)ws;
+    assert(ws->workspace <= ws->objectEnd);
+    assert(ws->objectEnd <= ws->tableEnd);
+    assert(ws->objectEnd <= ws->tableValidEnd);
+    assert(ws->tableEnd <= ws->allocStart);
+    assert(ws->tableValidEnd <= ws->allocStart);
+    assert(ws->allocStart <= ws->workspaceEnd);
+}
+
+/*
+ * Align must be a power of 2.
+ */
+MEM_STATIC size_t ZSTD_cwksp_align(size_t size, size_t const align) {
+    size_t const mask = align - 1;
+    assert((align & mask) == 0);
+    return (size + mask) & ~mask;
+}
+
+/*
+ * Use this to determine how much space in the workspace we will consume to
+ * allocate this object. (Normally it should be exactly the size of the object,
+ * but under special conditions, like ASAN, where we pad each object, it might
+ * be larger.)
+ *
+ * Since tables aren't currently redzoned, you don't need to call through this
+ * to figure out how much space you need for the matchState tables. Everything
+ * else is though.
+ */
+MEM_STATIC size_t ZSTD_cwksp_alloc_size(size_t size) {
+    if (size == 0)
+        return 0;
+    return size;
+}
+
+MEM_STATIC void ZSTD_cwksp_internal_advance_phase(
+        ZSTD_cwksp* ws, ZSTD_cwksp_alloc_phase_e phase) {
+    assert(phase >= ws->phase);
+    if (phase > ws->phase) {
+        if (ws->phase < ZSTD_cwksp_alloc_buffers &&
+                phase >= ZSTD_cwksp_alloc_buffers) {
+            ws->tableValidEnd = ws->objectEnd;
+        }
+        if (ws->phase < ZSTD_cwksp_alloc_aligned &&
+                phase >= ZSTD_cwksp_alloc_aligned) {
+            /* If unaligned allocations down from a too-large top have left us
+             * unaligned, we need to realign our alloc ptr. Technically, this
+             * can consume space that is unaccounted for in the neededSpace
+             * calculation. However, I believe this can only happen when the
+             * workspace is too large, and specifically when it is too large
+             * by a larger margin than the space that will be consumed. */
+            /* TODO: cleaner, compiler warning friendly way to do this??? */
+            ws->allocStart = (BYTE*)ws->allocStart - ((size_t)ws->allocStart & (sizeof(U32)-1));
+            if (ws->allocStart < ws->tableValidEnd) {
+                ws->tableValidEnd = ws->allocStart;
+            }
+        }
+        ws->phase = phase;
+    }
+}
+
+/*
+ * Returns whether this object/buffer/etc was allocated in this workspace.
+ */
+MEM_STATIC int ZSTD_cwksp_owns_buffer(const ZSTD_cwksp* ws, const void* ptr) {
+    return (ptr != NULL) && (ws->workspace <= ptr) && (ptr <= ws->workspaceEnd);
+}
+
+/*
+ * Internal function. Do not use directly.
+ */
+MEM_STATIC void* ZSTD_cwksp_reserve_internal(
+        ZSTD_cwksp* ws, size_t bytes, ZSTD_cwksp_alloc_phase_e phase) {
+    void* alloc;
+    void* bottom = ws->tableEnd;
+    ZSTD_cwksp_internal_advance_phase(ws, phase);
+    alloc = (BYTE *)ws->allocStart - bytes;
+
+    if (bytes == 0)
+        return NULL;
+
+
+    DEBUGLOG(5, "cwksp: reserving %p %zd bytes, %zd bytes remaining",
+        alloc, bytes, ZSTD_cwksp_available_space(ws) - bytes);
+    ZSTD_cwksp_assert_internal_consistency(ws);
+    assert(alloc >= bottom);
+    if (alloc < bottom) {
+        DEBUGLOG(4, "cwksp: alloc failed!");
+        ws->allocFailed = 1;
+        return NULL;
+    }
+    if (alloc < ws->tableValidEnd) {
+        ws->tableValidEnd = alloc;
+    }
+    ws->allocStart = alloc;
+
+
+    return alloc;
+}
+
+/*
+ * Reserves and returns unaligned memory.
+ */
+MEM_STATIC BYTE* ZSTD_cwksp_reserve_buffer(ZSTD_cwksp* ws, size_t bytes) {
+    return (BYTE*)ZSTD_cwksp_reserve_internal(ws, bytes, ZSTD_cwksp_alloc_buffers);
+}
+
+/*
+ * Reserves and returns memory sized on and aligned on sizeof(unsigned).
+ */
+MEM_STATIC void* ZSTD_cwksp_reserve_aligned(ZSTD_cwksp* ws, size_t bytes) {
+    assert((bytes & (sizeof(U32)-1)) == 0);
+    return ZSTD_cwksp_reserve_internal(ws, ZSTD_cwksp_align(bytes, sizeof(U32)), ZSTD_cwksp_alloc_aligned);
+}
+
+/*
+ * Aligned on sizeof(unsigned). These buffers have the special property that
+ * their values remain constrained, allowing us to re-use them without
+ * memset()-ing them.
+ */
+MEM_STATIC void* ZSTD_cwksp_reserve_table(ZSTD_cwksp* ws, size_t bytes) {
+    const ZSTD_cwksp_alloc_phase_e phase = ZSTD_cwksp_alloc_aligned;
+    void* alloc = ws->tableEnd;
+    void* end = (BYTE *)alloc + bytes;
+    void* top = ws->allocStart;
+
+    DEBUGLOG(5, "cwksp: reserving %p table %zd bytes, %zd bytes remaining",
+        alloc, bytes, ZSTD_cwksp_available_space(ws) - bytes);
+    assert((bytes & (sizeof(U32)-1)) == 0);
+    ZSTD_cwksp_internal_advance_phase(ws, phase);
+    ZSTD_cwksp_assert_internal_consistency(ws);
+    assert(end <= top);
+    if (end > top) {
+        DEBUGLOG(4, "cwksp: table alloc failed!");
+        ws->allocFailed = 1;
+        return NULL;
+    }
+    ws->tableEnd = end;
+
+
+    return alloc;
+}
+
+/*
+ * Aligned on sizeof(void*).
+ */
+MEM_STATIC void* ZSTD_cwksp_reserve_object(ZSTD_cwksp* ws, size_t bytes) {
+    size_t roundedBytes = ZSTD_cwksp_align(bytes, sizeof(void*));
+    void* alloc = ws->objectEnd;
+    void* end = (BYTE*)alloc + roundedBytes;
+
+
+    DEBUGLOG(5,
+        "cwksp: reserving %p object %zd bytes (rounded to %zd), %zd bytes remaining",
+        alloc, bytes, roundedBytes, ZSTD_cwksp_available_space(ws) - roundedBytes);
+    assert(((size_t)alloc & (sizeof(void*)-1)) == 0);
+    assert((bytes & (sizeof(void*)-1)) == 0);
+    ZSTD_cwksp_assert_internal_consistency(ws);
+    /* we must be in the first phase, no advance is possible */
+    if (ws->phase != ZSTD_cwksp_alloc_objects || end > ws->workspaceEnd) {
+        DEBUGLOG(4, "cwksp: object alloc failed!");
+        ws->allocFailed = 1;
+        return NULL;
+    }
+    ws->objectEnd = end;
+    ws->tableEnd = end;
+    ws->tableValidEnd = end;
+
+
+    return alloc;
+}
+
+MEM_STATIC void ZSTD_cwksp_mark_tables_dirty(ZSTD_cwksp* ws) {
+    DEBUGLOG(4, "cwksp: ZSTD_cwksp_mark_tables_dirty");
+
+
+    assert(ws->tableValidEnd >= ws->objectEnd);
+    assert(ws->tableValidEnd <= ws->allocStart);
+    ws->tableValidEnd = ws->objectEnd;
+    ZSTD_cwksp_assert_internal_consistency(ws);
+}
+
+MEM_STATIC void ZSTD_cwksp_mark_tables_clean(ZSTD_cwksp* ws) {
+    DEBUGLOG(4, "cwksp: ZSTD_cwksp_mark_tables_clean");
+    assert(ws->tableValidEnd >= ws->objectEnd);
+    assert(ws->tableValidEnd <= ws->allocStart);
+    if (ws->tableValidEnd < ws->tableEnd) {
+        ws->tableValidEnd = ws->tableEnd;
+    }
+    ZSTD_cwksp_assert_internal_consistency(ws);
+}
+
+/*
+ * Zero the part of the allocated tables not already marked clean.
+ */
+MEM_STATIC void ZSTD_cwksp_clean_tables(ZSTD_cwksp* ws) {
+    DEBUGLOG(4, "cwksp: ZSTD_cwksp_clean_tables");
+    assert(ws->tableValidEnd >= ws->objectEnd);
+    assert(ws->tableValidEnd <= ws->allocStart);
+    if (ws->tableValidEnd < ws->tableEnd) {
+        ZSTD_memset(ws->tableValidEnd, 0, (BYTE*)ws->tableEnd - (BYTE*)ws->tableValidEnd);
+    }
+    ZSTD_cwksp_mark_tables_clean(ws);
+}
+
+/*
+ * Invalidates table allocations.
+ * All other allocations remain valid.
+ */
+MEM_STATIC void ZSTD_cwksp_clear_tables(ZSTD_cwksp* ws) {
+    DEBUGLOG(4, "cwksp: clearing tables!");
+
+
+    ws->tableEnd = ws->objectEnd;
+    ZSTD_cwksp_assert_internal_consistency(ws);
+}
+
+/*
+ * Invalidates all buffer, aligned, and table allocations.
+ * Object allocations remain valid.
+ */
+MEM_STATIC void ZSTD_cwksp_clear(ZSTD_cwksp* ws) {
+    DEBUGLOG(4, "cwksp: clearing!");
+
+
+
+    ws->tableEnd = ws->objectEnd;
+    ws->allocStart = ws->workspaceEnd;
+    ws->allocFailed = 0;
+    if (ws->phase > ZSTD_cwksp_alloc_buffers) {
+        ws->phase = ZSTD_cwksp_alloc_buffers;
+    }
+    ZSTD_cwksp_assert_internal_consistency(ws);
+}
+
+/*
+ * The provided workspace takes ownership of the buffer [start, start+size).
+ * Any existing values in the workspace are ignored (the previously managed
+ * buffer, if present, must be separately freed).
+ */
+MEM_STATIC void ZSTD_cwksp_init(ZSTD_cwksp* ws, void* start, size_t size, ZSTD_cwksp_static_alloc_e isStatic) {
+    DEBUGLOG(4, "cwksp: init'ing workspace with %zd bytes", size);
+    assert(((size_t)start & (sizeof(void*)-1)) == 0); /* ensure correct alignment */
+    ws->workspace = start;
+    ws->workspaceEnd = (BYTE*)start + size;
+    ws->objectEnd = ws->workspace;
+    ws->tableValidEnd = ws->objectEnd;
+    ws->phase = ZSTD_cwksp_alloc_objects;
+    ws->isStatic = isStatic;
+    ZSTD_cwksp_clear(ws);
+    ws->workspaceOversizedDuration = 0;
+    ZSTD_cwksp_assert_internal_consistency(ws);
+}
+
+MEM_STATIC size_t ZSTD_cwksp_create(ZSTD_cwksp* ws, size_t size, ZSTD_customMem customMem) {
+    void* workspace = ZSTD_customMalloc(size, customMem);
+    DEBUGLOG(4, "cwksp: creating new workspace with %zd bytes", size);
+    RETURN_ERROR_IF(workspace == NULL, memory_allocation, "NULL pointer!");
+    ZSTD_cwksp_init(ws, workspace, size, ZSTD_cwksp_dynamic_alloc);
+    return 0;
+}
+
+MEM_STATIC void ZSTD_cwksp_free(ZSTD_cwksp* ws, ZSTD_customMem customMem) {
+    void *ptr = ws->workspace;
+    DEBUGLOG(4, "cwksp: freeing workspace");
+    ZSTD_memset(ws, 0, sizeof(ZSTD_cwksp));
+    ZSTD_customFree(ptr, customMem);
+}
+
+/*
+ * Moves the management of a workspace from one cwksp to another. The src cwksp
+ * is left in an invalid state (src must be re-init()'ed before it's used again).
+ */
+MEM_STATIC void ZSTD_cwksp_move(ZSTD_cwksp* dst, ZSTD_cwksp* src) {
+    *dst = *src;
+    ZSTD_memset(src, 0, sizeof(ZSTD_cwksp));
+}
+
+MEM_STATIC size_t ZSTD_cwksp_sizeof(const ZSTD_cwksp* ws) {
+    return (size_t)((BYTE*)ws->workspaceEnd - (BYTE*)ws->workspace);
+}
+
+MEM_STATIC size_t ZSTD_cwksp_used(const ZSTD_cwksp* ws) {
+    return (size_t)((BYTE*)ws->tableEnd - (BYTE*)ws->workspace)
+         + (size_t)((BYTE*)ws->workspaceEnd - (BYTE*)ws->allocStart);
+}
+
+MEM_STATIC int ZSTD_cwksp_reserve_failed(const ZSTD_cwksp* ws) {
+    return ws->allocFailed;
+}
+
+/*-*************************************
+*  Functions Checking Free Space
+***************************************/
+
+MEM_STATIC size_t ZSTD_cwksp_available_space(ZSTD_cwksp* ws) {
+    return (size_t)((BYTE*)ws->allocStart - (BYTE*)ws->tableEnd);
+}
+
+MEM_STATIC int ZSTD_cwksp_check_available(ZSTD_cwksp* ws, size_t additionalNeededSpace) {
+    return ZSTD_cwksp_available_space(ws) >= additionalNeededSpace;
+}
+
+MEM_STATIC int ZSTD_cwksp_check_too_large(ZSTD_cwksp* ws, size_t additionalNeededSpace) {
+    return ZSTD_cwksp_check_available(
+        ws, additionalNeededSpace * ZSTD_WORKSPACETOOLARGE_FACTOR);
+}
+
+MEM_STATIC int ZSTD_cwksp_check_wasteful(ZSTD_cwksp* ws, size_t additionalNeededSpace) {
+    return ZSTD_cwksp_check_too_large(ws, additionalNeededSpace)
+        && ws->workspaceOversizedDuration > ZSTD_WORKSPACETOOLARGE_MAXDURATION;
+}
+
+MEM_STATIC void ZSTD_cwksp_bump_oversized_duration(
+        ZSTD_cwksp* ws, size_t additionalNeededSpace) {
+    if (ZSTD_cwksp_check_too_large(ws, additionalNeededSpace)) {
+        ws->workspaceOversizedDuration++;
+    } else {
+        ws->workspaceOversizedDuration = 0;
+    }
+}
+
+
+#endif /* ZSTD_CWKSP_H */
diff --git a/lib/zstd/compress/zstd_double_fast.c b/lib/zstd/compress/zstd_double_fast.c
new file mode 100644
index 000000000000..b0424d23ac57
--- /dev/null
+++ b/lib/zstd/compress/zstd_double_fast.c
@@ -0,0 +1,519 @@
+/*
+ * Copyright (c) Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+#include "zstd_compress_internal.h"
+#include "zstd_double_fast.h"
+
+
+void ZSTD_fillDoubleHashTable(ZSTD_matchState_t* ms,
+                              void const* end, ZSTD_dictTableLoadMethod_e dtlm)
+{
+    const ZSTD_compressionParameters* const cParams = &ms->cParams;
+    U32* const hashLarge = ms->hashTable;
+    U32  const hBitsL = cParams->hashLog;
+    U32  const mls = cParams->minMatch;
+    U32* const hashSmall = ms->chainTable;
+    U32  const hBitsS = cParams->chainLog;
+    const BYTE* const base = ms->window.base;
+    const BYTE* ip = base + ms->nextToUpdate;
+    const BYTE* const iend = ((const BYTE*)end) - HASH_READ_SIZE;
+    const U32 fastHashFillStep = 3;
+
+    /* Always insert every fastHashFillStep position into the hash tables.
+     * Insert the other positions into the large hash table if their entry
+     * is empty.
+     */
+    for (; ip + fastHashFillStep - 1 <= iend; ip += fastHashFillStep) {
+        U32 const curr = (U32)(ip - base);
+        U32 i;
+        for (i = 0; i < fastHashFillStep; ++i) {
+            size_t const smHash = ZSTD_hashPtr(ip + i, hBitsS, mls);
+            size_t const lgHash = ZSTD_hashPtr(ip + i, hBitsL, 8);
+            if (i == 0)
+                hashSmall[smHash] = curr + i;
+            if (i == 0 || hashLarge[lgHash] == 0)
+                hashLarge[lgHash] = curr + i;
+            /* Only load extra positions for ZSTD_dtlm_full */
+            if (dtlm == ZSTD_dtlm_fast)
+                break;
+    }   }
+}
+
+
+FORCE_INLINE_TEMPLATE
+size_t ZSTD_compressBlock_doubleFast_generic(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize,
+        U32 const mls /* template */, ZSTD_dictMode_e const dictMode)
+{
+    ZSTD_compressionParameters const* cParams = &ms->cParams;
+    U32* const hashLong = ms->hashTable;
+    const U32 hBitsL = cParams->hashLog;
+    U32* const hashSmall = ms->chainTable;
+    const U32 hBitsS = cParams->chainLog;
+    const BYTE* const base = ms->window.base;
+    const BYTE* const istart = (const BYTE*)src;
+    const BYTE* ip = istart;
+    const BYTE* anchor = istart;
+    const U32 endIndex = (U32)((size_t)(istart - base) + srcSize);
+    /* presumes that, if there is a dictionary, it must be using Attach mode */
+    const U32 prefixLowestIndex = ZSTD_getLowestPrefixIndex(ms, endIndex, cParams->windowLog);
+    const BYTE* const prefixLowest = base + prefixLowestIndex;
+    const BYTE* const iend = istart + srcSize;
+    const BYTE* const ilimit = iend - HASH_READ_SIZE;
+    U32 offset_1=rep[0], offset_2=rep[1];
+    U32 offsetSaved = 0;
+
+    const ZSTD_matchState_t* const dms = ms->dictMatchState;
+    const ZSTD_compressionParameters* const dictCParams =
+                                     dictMode == ZSTD_dictMatchState ?
+                                     &dms->cParams : NULL;
+    const U32* const dictHashLong  = dictMode == ZSTD_dictMatchState ?
+                                     dms->hashTable : NULL;
+    const U32* const dictHashSmall = dictMode == ZSTD_dictMatchState ?
+                                     dms->chainTable : NULL;
+    const U32 dictStartIndex       = dictMode == ZSTD_dictMatchState ?
+                                     dms->window.dictLimit : 0;
+    const BYTE* const dictBase     = dictMode == ZSTD_dictMatchState ?
+                                     dms->window.base : NULL;
+    const BYTE* const dictStart    = dictMode == ZSTD_dictMatchState ?
+                                     dictBase + dictStartIndex : NULL;
+    const BYTE* const dictEnd      = dictMode == ZSTD_dictMatchState ?
+                                     dms->window.nextSrc : NULL;
+    const U32 dictIndexDelta       = dictMode == ZSTD_dictMatchState ?
+                                     prefixLowestIndex - (U32)(dictEnd - dictBase) :
+                                     0;
+    const U32 dictHBitsL           = dictMode == ZSTD_dictMatchState ?
+                                     dictCParams->hashLog : hBitsL;
+    const U32 dictHBitsS           = dictMode == ZSTD_dictMatchState ?
+                                     dictCParams->chainLog : hBitsS;
+    const U32 dictAndPrefixLength  = (U32)((ip - prefixLowest) + (dictEnd - dictStart));
+
+    DEBUGLOG(5, "ZSTD_compressBlock_doubleFast_generic");
+
+    assert(dictMode == ZSTD_noDict || dictMode == ZSTD_dictMatchState);
+
+    /* if a dictionary is attached, it must be within window range */
+    if (dictMode == ZSTD_dictMatchState) {
+        assert(ms->window.dictLimit + (1U << cParams->windowLog) >= endIndex);
+    }
+
+    /* init */
+    ip += (dictAndPrefixLength == 0);
+    if (dictMode == ZSTD_noDict) {
+        U32 const curr = (U32)(ip - base);
+        U32 const windowLow = ZSTD_getLowestPrefixIndex(ms, curr, cParams->windowLog);
+        U32 const maxRep = curr - windowLow;
+        if (offset_2 > maxRep) offsetSaved = offset_2, offset_2 = 0;
+        if (offset_1 > maxRep) offsetSaved = offset_1, offset_1 = 0;
+    }
+    if (dictMode == ZSTD_dictMatchState) {
+        /* dictMatchState repCode checks don't currently handle repCode == 0
+         * disabling. */
+        assert(offset_1 <= dictAndPrefixLength);
+        assert(offset_2 <= dictAndPrefixLength);
+    }
+
+    /* Main Search Loop */
+    while (ip < ilimit) {   /* < instead of <=, because repcode check at (ip+1) */
+        size_t mLength;
+        U32 offset;
+        size_t const h2 = ZSTD_hashPtr(ip, hBitsL, 8);
+        size_t const h = ZSTD_hashPtr(ip, hBitsS, mls);
+        size_t const dictHL = ZSTD_hashPtr(ip, dictHBitsL, 8);
+        size_t const dictHS = ZSTD_hashPtr(ip, dictHBitsS, mls);
+        U32 const curr = (U32)(ip-base);
+        U32 const matchIndexL = hashLong[h2];
+        U32 matchIndexS = hashSmall[h];
+        const BYTE* matchLong = base + matchIndexL;
+        const BYTE* match = base + matchIndexS;
+        const U32 repIndex = curr + 1 - offset_1;
+        const BYTE* repMatch = (dictMode == ZSTD_dictMatchState
+                            && repIndex < prefixLowestIndex) ?
+                               dictBase + (repIndex - dictIndexDelta) :
+                               base + repIndex;
+        hashLong[h2] = hashSmall[h] = curr;   /* update hash tables */
+
+        /* check dictMatchState repcode */
+        if (dictMode == ZSTD_dictMatchState
+            && ((U32)((prefixLowestIndex-1) - repIndex) >= 3 /* intentional underflow */)
+            && (MEM_read32(repMatch) == MEM_read32(ip+1)) ) {
+            const BYTE* repMatchEnd = repIndex < prefixLowestIndex ? dictEnd : iend;
+            mLength = ZSTD_count_2segments(ip+1+4, repMatch+4, iend, repMatchEnd, prefixLowest) + 4;
+            ip++;
+            ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, iend, 0, mLength-MINMATCH);
+            goto _match_stored;
+        }
+
+        /* check noDict repcode */
+        if ( dictMode == ZSTD_noDict
+          && ((offset_1 > 0) & (MEM_read32(ip+1-offset_1) == MEM_read32(ip+1)))) {
+            mLength = ZSTD_count(ip+1+4, ip+1+4-offset_1, iend) + 4;
+            ip++;
+            ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, iend, 0, mLength-MINMATCH);
+            goto _match_stored;
+        }
+
+        if (matchIndexL > prefixLowestIndex) {
+            /* check prefix long match */
+            if (MEM_read64(matchLong) == MEM_read64(ip)) {
+                mLength = ZSTD_count(ip+8, matchLong+8, iend) + 8;
+                offset = (U32)(ip-matchLong);
+                while (((ip>anchor) & (matchLong>prefixLowest)) && (ip[-1] == matchLong[-1])) { ip--; matchLong--; mLength++; } /* catch up */
+                goto _match_found;
+            }
+        } else if (dictMode == ZSTD_dictMatchState) {
+            /* check dictMatchState long match */
+            U32 const dictMatchIndexL = dictHashLong[dictHL];
+            const BYTE* dictMatchL = dictBase + dictMatchIndexL;
+            assert(dictMatchL < dictEnd);
+
+            if (dictMatchL > dictStart && MEM_read64(dictMatchL) == MEM_read64(ip)) {
+                mLength = ZSTD_count_2segments(ip+8, dictMatchL+8, iend, dictEnd, prefixLowest) + 8;
+                offset = (U32)(curr - dictMatchIndexL - dictIndexDelta);
+                while (((ip>anchor) & (dictMatchL>dictStart)) && (ip[-1] == dictMatchL[-1])) { ip--; dictMatchL--; mLength++; } /* catch up */
+                goto _match_found;
+        }   }
+
+        if (matchIndexS > prefixLowestIndex) {
+            /* check prefix short match */
+            if (MEM_read32(match) == MEM_read32(ip)) {
+                goto _search_next_long;
+            }
+        } else if (dictMode == ZSTD_dictMatchState) {
+            /* check dictMatchState short match */
+            U32 const dictMatchIndexS = dictHashSmall[dictHS];
+            match = dictBase + dictMatchIndexS;
+            matchIndexS = dictMatchIndexS + dictIndexDelta;
+
+            if (match > dictStart && MEM_read32(match) == MEM_read32(ip)) {
+                goto _search_next_long;
+        }   }
+
+        ip += ((ip-anchor) >> kSearchStrength) + 1;
+#if defined(__aarch64__)
+        PREFETCH_L1(ip+256);
+#endif
+        continue;
+
+_search_next_long:
+
+        {   size_t const hl3 = ZSTD_hashPtr(ip+1, hBitsL, 8);
+            size_t const dictHLNext = ZSTD_hashPtr(ip+1, dictHBitsL, 8);
+            U32 const matchIndexL3 = hashLong[hl3];
+            const BYTE* matchL3 = base + matchIndexL3;
+            hashLong[hl3] = curr + 1;
+
+            /* check prefix long +1 match */
+            if (matchIndexL3 > prefixLowestIndex) {
+                if (MEM_read64(matchL3) == MEM_read64(ip+1)) {
+                    mLength = ZSTD_count(ip+9, matchL3+8, iend) + 8;
+                    ip++;
+                    offset = (U32)(ip-matchL3);
+                    while (((ip>anchor) & (matchL3>prefixLowest)) && (ip[-1] == matchL3[-1])) { ip--; matchL3--; mLength++; } /* catch up */
+                    goto _match_found;
+                }
+            } else if (dictMode == ZSTD_dictMatchState) {
+                /* check dict long +1 match */
+                U32 const dictMatchIndexL3 = dictHashLong[dictHLNext];
+                const BYTE* dictMatchL3 = dictBase + dictMatchIndexL3;
+                assert(dictMatchL3 < dictEnd);
+                if (dictMatchL3 > dictStart && MEM_read64(dictMatchL3) == MEM_read64(ip+1)) {
+                    mLength = ZSTD_count_2segments(ip+1+8, dictMatchL3+8, iend, dictEnd, prefixLowest) + 8;
+                    ip++;
+                    offset = (U32)(curr + 1 - dictMatchIndexL3 - dictIndexDelta);
+                    while (((ip>anchor) & (dictMatchL3>dictStart)) && (ip[-1] == dictMatchL3[-1])) { ip--; dictMatchL3--; mLength++; } /* catch up */
+                    goto _match_found;
+        }   }   }
+
+        /* if no long +1 match, explore the short match we found */
+        if (dictMode == ZSTD_dictMatchState && matchIndexS < prefixLowestIndex) {
+            mLength = ZSTD_count_2segments(ip+4, match+4, iend, dictEnd, prefixLowest) + 4;
+            offset = (U32)(curr - matchIndexS);
+            while (((ip>anchor) & (match>dictStart)) && (ip[-1] == match[-1])) { ip--; match--; mLength++; } /* catch up */
+        } else {
+            mLength = ZSTD_count(ip+4, match+4, iend) + 4;
+            offset = (U32)(ip - match);
+            while (((ip>anchor) & (match>prefixLowest)) && (ip[-1] == match[-1])) { ip--; match--; mLength++; } /* catch up */
+        }
+
+_match_found:
+        offset_2 = offset_1;
+        offset_1 = offset;
+
+        ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, iend, offset + ZSTD_REP_MOVE, mLength-MINMATCH);
+
+_match_stored:
+        /* match found */
+        ip += mLength;
+        anchor = ip;
+
+        if (ip <= ilimit) {
+            /* Complementary insertion */
+            /* done after iLimit test, as candidates could be > iend-8 */
+            {   U32 const indexToInsert = curr+2;
+                hashLong[ZSTD_hashPtr(base+indexToInsert, hBitsL, 8)] = indexToInsert;
+                hashLong[ZSTD_hashPtr(ip-2, hBitsL, 8)] = (U32)(ip-2-base);
+                hashSmall[ZSTD_hashPtr(base+indexToInsert, hBitsS, mls)] = indexToInsert;
+                hashSmall[ZSTD_hashPtr(ip-1, hBitsS, mls)] = (U32)(ip-1-base);
+            }
+
+            /* check immediate repcode */
+            if (dictMode == ZSTD_dictMatchState) {
+                while (ip <= ilimit) {
+                    U32 const current2 = (U32)(ip-base);
+                    U32 const repIndex2 = current2 - offset_2;
+                    const BYTE* repMatch2 = dictMode == ZSTD_dictMatchState
+                        && repIndex2 < prefixLowestIndex ?
+                            dictBase + repIndex2 - dictIndexDelta :
+                            base + repIndex2;
+                    if ( ((U32)((prefixLowestIndex-1) - (U32)repIndex2) >= 3 /* intentional overflow */)
+                       && (MEM_read32(repMatch2) == MEM_read32(ip)) ) {
+                        const BYTE* const repEnd2 = repIndex2 < prefixLowestIndex ? dictEnd : iend;
+                        size_t const repLength2 = ZSTD_count_2segments(ip+4, repMatch2+4, iend, repEnd2, prefixLowest) + 4;
+                        U32 tmpOffset = offset_2; offset_2 = offset_1; offset_1 = tmpOffset;   /* swap offset_2 <=> offset_1 */
+                        ZSTD_storeSeq(seqStore, 0, anchor, iend, 0, repLength2-MINMATCH);
+                        hashSmall[ZSTD_hashPtr(ip, hBitsS, mls)] = current2;
+                        hashLong[ZSTD_hashPtr(ip, hBitsL, 8)] = current2;
+                        ip += repLength2;
+                        anchor = ip;
+                        continue;
+                    }
+                    break;
+            }   }
+
+            if (dictMode == ZSTD_noDict) {
+                while ( (ip <= ilimit)
+                     && ( (offset_2>0)
+                        & (MEM_read32(ip) == MEM_read32(ip - offset_2)) )) {
+                    /* store sequence */
+                    size_t const rLength = ZSTD_count(ip+4, ip+4-offset_2, iend) + 4;
+                    U32 const tmpOff = offset_2; offset_2 = offset_1; offset_1 = tmpOff;  /* swap offset_2 <=> offset_1 */
+                    hashSmall[ZSTD_hashPtr(ip, hBitsS, mls)] = (U32)(ip-base);
+                    hashLong[ZSTD_hashPtr(ip, hBitsL, 8)] = (U32)(ip-base);
+                    ZSTD_storeSeq(seqStore, 0, anchor, iend, 0, rLength-MINMATCH);
+                    ip += rLength;
+                    anchor = ip;
+                    continue;   /* faster when present ... (?) */
+        }   }   }
+    }   /* while (ip < ilimit) */
+
+    /* save reps for next block */
+    rep[0] = offset_1 ? offset_1 : offsetSaved;
+    rep[1] = offset_2 ? offset_2 : offsetSaved;
+
+    /* Return the last literals size */
+    return (size_t)(iend - anchor);
+}
+
+
+size_t ZSTD_compressBlock_doubleFast(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize)
+{
+    const U32 mls = ms->cParams.minMatch;
+    switch(mls)
+    {
+    default: /* includes case 3 */
+    case 4 :
+        return ZSTD_compressBlock_doubleFast_generic(ms, seqStore, rep, src, srcSize, 4, ZSTD_noDict);
+    case 5 :
+        return ZSTD_compressBlock_doubleFast_generic(ms, seqStore, rep, src, srcSize, 5, ZSTD_noDict);
+    case 6 :
+        return ZSTD_compressBlock_doubleFast_generic(ms, seqStore, rep, src, srcSize, 6, ZSTD_noDict);
+    case 7 :
+        return ZSTD_compressBlock_doubleFast_generic(ms, seqStore, rep, src, srcSize, 7, ZSTD_noDict);
+    }
+}
+
+
+size_t ZSTD_compressBlock_doubleFast_dictMatchState(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize)
+{
+    const U32 mls = ms->cParams.minMatch;
+    switch(mls)
+    {
+    default: /* includes case 3 */
+    case 4 :
+        return ZSTD_compressBlock_doubleFast_generic(ms, seqStore, rep, src, srcSize, 4, ZSTD_dictMatchState);
+    case 5 :
+        return ZSTD_compressBlock_doubleFast_generic(ms, seqStore, rep, src, srcSize, 5, ZSTD_dictMatchState);
+    case 6 :
+        return ZSTD_compressBlock_doubleFast_generic(ms, seqStore, rep, src, srcSize, 6, ZSTD_dictMatchState);
+    case 7 :
+        return ZSTD_compressBlock_doubleFast_generic(ms, seqStore, rep, src, srcSize, 7, ZSTD_dictMatchState);
+    }
+}
+
+
+static size_t ZSTD_compressBlock_doubleFast_extDict_generic(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize,
+        U32 const mls /* template */)
+{
+    ZSTD_compressionParameters const* cParams = &ms->cParams;
+    U32* const hashLong = ms->hashTable;
+    U32  const hBitsL = cParams->hashLog;
+    U32* const hashSmall = ms->chainTable;
+    U32  const hBitsS = cParams->chainLog;
+    const BYTE* const istart = (const BYTE*)src;
+    const BYTE* ip = istart;
+    const BYTE* anchor = istart;
+    const BYTE* const iend = istart + srcSize;
+    const BYTE* const ilimit = iend - 8;
+    const BYTE* const base = ms->window.base;
+    const U32   endIndex = (U32)((size_t)(istart - base) + srcSize);
+    const U32   lowLimit = ZSTD_getLowestMatchIndex(ms, endIndex, cParams->windowLog);
+    const U32   dictStartIndex = lowLimit;
+    const U32   dictLimit = ms->window.dictLimit;
+    const U32   prefixStartIndex = (dictLimit > lowLimit) ? dictLimit : lowLimit;
+    const BYTE* const prefixStart = base + prefixStartIndex;
+    const BYTE* const dictBase = ms->window.dictBase;
+    const BYTE* const dictStart = dictBase + dictStartIndex;
+    const BYTE* const dictEnd = dictBase + prefixStartIndex;
+    U32 offset_1=rep[0], offset_2=rep[1];
+
+    DEBUGLOG(5, "ZSTD_compressBlock_doubleFast_extDict_generic (srcSize=%zu)", srcSize);
+
+    /* if extDict is invalidated due to maxDistance, switch to "regular" variant */
+    if (prefixStartIndex == dictStartIndex)
+        return ZSTD_compressBlock_doubleFast_generic(ms, seqStore, rep, src, srcSize, mls, ZSTD_noDict);
+
+    /* Search Loop */
+    while (ip < ilimit) {  /* < instead of <=, because (ip+1) */
+        const size_t hSmall = ZSTD_hashPtr(ip, hBitsS, mls);
+        const U32 matchIndex = hashSmall[hSmall];
+        const BYTE* const matchBase = matchIndex < prefixStartIndex ? dictBase : base;
+        const BYTE* match = matchBase + matchIndex;
+
+        const size_t hLong = ZSTD_hashPtr(ip, hBitsL, 8);
+        const U32 matchLongIndex = hashLong[hLong];
+        const BYTE* const matchLongBase = matchLongIndex < prefixStartIndex ? dictBase : base;
+        const BYTE* matchLong = matchLongBase + matchLongIndex;
+
+        const U32 curr = (U32)(ip-base);
+        const U32 repIndex = curr + 1 - offset_1;   /* offset_1 expected <= curr +1 */
+        const BYTE* const repBase = repIndex < prefixStartIndex ? dictBase : base;
+        const BYTE* const repMatch = repBase + repIndex;
+        size_t mLength;
+        hashSmall[hSmall] = hashLong[hLong] = curr;   /* update hash table */
+
+        if ((((U32)((prefixStartIndex-1) - repIndex) >= 3) /* intentional underflow : ensure repIndex doesn't overlap dict + prefix */
+            & (repIndex > dictStartIndex))
+          && (MEM_read32(repMatch) == MEM_read32(ip+1)) ) {
+            const BYTE* repMatchEnd = repIndex < prefixStartIndex ? dictEnd : iend;
+            mLength = ZSTD_count_2segments(ip+1+4, repMatch+4, iend, repMatchEnd, prefixStart) + 4;
+            ip++;
+            ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, iend, 0, mLength-MINMATCH);
+        } else {
+            if ((matchLongIndex > dictStartIndex) && (MEM_read64(matchLong) == MEM_read64(ip))) {
+                const BYTE* const matchEnd = matchLongIndex < prefixStartIndex ? dictEnd : iend;
+                const BYTE* const lowMatchPtr = matchLongIndex < prefixStartIndex ? dictStart : prefixStart;
+                U32 offset;
+                mLength = ZSTD_count_2segments(ip+8, matchLong+8, iend, matchEnd, prefixStart) + 8;
+                offset = curr - matchLongIndex;
+                while (((ip>anchor) & (matchLong>lowMatchPtr)) && (ip[-1] == matchLong[-1])) { ip--; matchLong--; mLength++; }   /* catch up */
+                offset_2 = offset_1;
+                offset_1 = offset;
+                ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, iend, offset + ZSTD_REP_MOVE, mLength-MINMATCH);
+
+            } else if ((matchIndex > dictStartIndex) && (MEM_read32(match) == MEM_read32(ip))) {
+                size_t const h3 = ZSTD_hashPtr(ip+1, hBitsL, 8);
+                U32 const matchIndex3 = hashLong[h3];
+                const BYTE* const match3Base = matchIndex3 < prefixStartIndex ? dictBase : base;
+                const BYTE* match3 = match3Base + matchIndex3;
+                U32 offset;
+                hashLong[h3] = curr + 1;
+                if ( (matchIndex3 > dictStartIndex) && (MEM_read64(match3) == MEM_read64(ip+1)) ) {
+                    const BYTE* const matchEnd = matchIndex3 < prefixStartIndex ? dictEnd : iend;
+                    const BYTE* const lowMatchPtr = matchIndex3 < prefixStartIndex ? dictStart : prefixStart;
+                    mLength = ZSTD_count_2segments(ip+9, match3+8, iend, matchEnd, prefixStart) + 8;
+                    ip++;
+                    offset = curr+1 - matchIndex3;
+                    while (((ip>anchor) & (match3>lowMatchPtr)) && (ip[-1] == match3[-1])) { ip--; match3--; mLength++; } /* catch up */
+                } else {
+                    const BYTE* const matchEnd = matchIndex < prefixStartIndex ? dictEnd : iend;
+                    const BYTE* const lowMatchPtr = matchIndex < prefixStartIndex ? dictStart : prefixStart;
+                    mLength = ZSTD_count_2segments(ip+4, match+4, iend, matchEnd, prefixStart) + 4;
+                    offset = curr - matchIndex;
+                    while (((ip>anchor) & (match>lowMatchPtr)) && (ip[-1] == match[-1])) { ip--; match--; mLength++; }   /* catch up */
+                }
+                offset_2 = offset_1;
+                offset_1 = offset;
+                ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, iend, offset + ZSTD_REP_MOVE, mLength-MINMATCH);
+
+            } else {
+                ip += ((ip-anchor) >> kSearchStrength) + 1;
+                continue;
+        }   }
+
+        /* move to next sequence start */
+        ip += mLength;
+        anchor = ip;
+
+        if (ip <= ilimit) {
+            /* Complementary insertion */
+            /* done after iLimit test, as candidates could be > iend-8 */
+            {   U32 const indexToInsert = curr+2;
+                hashLong[ZSTD_hashPtr(base+indexToInsert, hBitsL, 8)] = indexToInsert;
+                hashLong[ZSTD_hashPtr(ip-2, hBitsL, 8)] = (U32)(ip-2-base);
+                hashSmall[ZSTD_hashPtr(base+indexToInsert, hBitsS, mls)] = indexToInsert;
+                hashSmall[ZSTD_hashPtr(ip-1, hBitsS, mls)] = (U32)(ip-1-base);
+            }
+
+            /* check immediate repcode */
+            while (ip <= ilimit) {
+                U32 const current2 = (U32)(ip-base);
+                U32 const repIndex2 = current2 - offset_2;
+                const BYTE* repMatch2 = repIndex2 < prefixStartIndex ? dictBase + repIndex2 : base + repIndex2;
+                if ( (((U32)((prefixStartIndex-1) - repIndex2) >= 3)   /* intentional overflow : ensure repIndex2 doesn't overlap dict + prefix */
+                    & (repIndex2 > dictStartIndex))
+                  && (MEM_read32(repMatch2) == MEM_read32(ip)) ) {
+                    const BYTE* const repEnd2 = repIndex2 < prefixStartIndex ? dictEnd : iend;
+                    size_t const repLength2 = ZSTD_count_2segments(ip+4, repMatch2+4, iend, repEnd2, prefixStart) + 4;
+                    U32 const tmpOffset = offset_2; offset_2 = offset_1; offset_1 = tmpOffset;   /* swap offset_2 <=> offset_1 */
+                    ZSTD_storeSeq(seqStore, 0, anchor, iend, 0, repLength2-MINMATCH);
+                    hashSmall[ZSTD_hashPtr(ip, hBitsS, mls)] = current2;
+                    hashLong[ZSTD_hashPtr(ip, hBitsL, 8)] = current2;
+                    ip += repLength2;
+                    anchor = ip;
+                    continue;
+                }
+                break;
+    }   }   }
+
+    /* save reps for next block */
+    rep[0] = offset_1;
+    rep[1] = offset_2;
+
+    /* Return the last literals size */
+    return (size_t)(iend - anchor);
+}
+
+
+size_t ZSTD_compressBlock_doubleFast_extDict(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize)
+{
+    U32 const mls = ms->cParams.minMatch;
+    switch(mls)
+    {
+    default: /* includes case 3 */
+    case 4 :
+        return ZSTD_compressBlock_doubleFast_extDict_generic(ms, seqStore, rep, src, srcSize, 4);
+    case 5 :
+        return ZSTD_compressBlock_doubleFast_extDict_generic(ms, seqStore, rep, src, srcSize, 5);
+    case 6 :
+        return ZSTD_compressBlock_doubleFast_extDict_generic(ms, seqStore, rep, src, srcSize, 6);
+    case 7 :
+        return ZSTD_compressBlock_doubleFast_extDict_generic(ms, seqStore, rep, src, srcSize, 7);
+    }
+}
diff --git a/lib/zstd/compress/zstd_double_fast.h b/lib/zstd/compress/zstd_double_fast.h
new file mode 100644
index 000000000000..6822bde65a1d
--- /dev/null
+++ b/lib/zstd/compress/zstd_double_fast.h
@@ -0,0 +1,32 @@
+/*
+ * Copyright (c) Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+#ifndef ZSTD_DOUBLE_FAST_H
+#define ZSTD_DOUBLE_FAST_H
+
+
+#include "../common/mem.h"      /* U32 */
+#include "zstd_compress_internal.h"     /* ZSTD_CCtx, size_t */
+
+void ZSTD_fillDoubleHashTable(ZSTD_matchState_t* ms,
+                              void const* end, ZSTD_dictTableLoadMethod_e dtlm);
+size_t ZSTD_compressBlock_doubleFast(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize);
+size_t ZSTD_compressBlock_doubleFast_dictMatchState(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize);
+size_t ZSTD_compressBlock_doubleFast_extDict(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize);
+
+
+
+#endif /* ZSTD_DOUBLE_FAST_H */
diff --git a/lib/zstd/compress/zstd_fast.c b/lib/zstd/compress/zstd_fast.c
new file mode 100644
index 000000000000..96b7d48e2868
--- /dev/null
+++ b/lib/zstd/compress/zstd_fast.c
@@ -0,0 +1,496 @@
+/*
+ * Copyright (c) Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+#include "zstd_compress_internal.h"  /* ZSTD_hashPtr, ZSTD_count, ZSTD_storeSeq */
+#include "zstd_fast.h"
+
+
+void ZSTD_fillHashTable(ZSTD_matchState_t* ms,
+                        const void* const end,
+                        ZSTD_dictTableLoadMethod_e dtlm)
+{
+    const ZSTD_compressionParameters* const cParams = &ms->cParams;
+    U32* const hashTable = ms->hashTable;
+    U32  const hBits = cParams->hashLog;
+    U32  const mls = cParams->minMatch;
+    const BYTE* const base = ms->window.base;
+    const BYTE* ip = base + ms->nextToUpdate;
+    const BYTE* const iend = ((const BYTE*)end) - HASH_READ_SIZE;
+    const U32 fastHashFillStep = 3;
+
+    /* Always insert every fastHashFillStep position into the hash table.
+     * Insert the other positions if their hash entry is empty.
+     */
+    for ( ; ip + fastHashFillStep < iend + 2; ip += fastHashFillStep) {
+        U32 const curr = (U32)(ip - base);
+        size_t const hash0 = ZSTD_hashPtr(ip, hBits, mls);
+        hashTable[hash0] = curr;
+        if (dtlm == ZSTD_dtlm_fast) continue;
+        /* Only load extra positions for ZSTD_dtlm_full */
+        {   U32 p;
+            for (p = 1; p < fastHashFillStep; ++p) {
+                size_t const hash = ZSTD_hashPtr(ip + p, hBits, mls);
+                if (hashTable[hash] == 0) {  /* not yet filled */
+                    hashTable[hash] = curr + p;
+    }   }   }   }
+}
+
+
+FORCE_INLINE_TEMPLATE size_t
+ZSTD_compressBlock_fast_generic(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize,
+        U32 const mls)
+{
+    const ZSTD_compressionParameters* const cParams = &ms->cParams;
+    U32* const hashTable = ms->hashTable;
+    U32 const hlog = cParams->hashLog;
+    /* support stepSize of 0 */
+    size_t const stepSize = cParams->targetLength + !(cParams->targetLength) + 1;
+    const BYTE* const base = ms->window.base;
+    const BYTE* const istart = (const BYTE*)src;
+    /* We check ip0 (ip + 0) and ip1 (ip + 1) each loop */
+    const BYTE* ip0 = istart;
+    const BYTE* ip1;
+    const BYTE* anchor = istart;
+    const U32   endIndex = (U32)((size_t)(istart - base) + srcSize);
+    const U32   prefixStartIndex = ZSTD_getLowestPrefixIndex(ms, endIndex, cParams->windowLog);
+    const BYTE* const prefixStart = base + prefixStartIndex;
+    const BYTE* const iend = istart + srcSize;
+    const BYTE* const ilimit = iend - HASH_READ_SIZE;
+    U32 offset_1=rep[0], offset_2=rep[1];
+    U32 offsetSaved = 0;
+
+    /* init */
+    DEBUGLOG(5, "ZSTD_compressBlock_fast_generic");
+    ip0 += (ip0 == prefixStart);
+    ip1 = ip0 + 1;
+    {   U32 const curr = (U32)(ip0 - base);
+        U32 const windowLow = ZSTD_getLowestPrefixIndex(ms, curr, cParams->windowLog);
+        U32 const maxRep = curr - windowLow;
+        if (offset_2 > maxRep) offsetSaved = offset_2, offset_2 = 0;
+        if (offset_1 > maxRep) offsetSaved = offset_1, offset_1 = 0;
+    }
+
+    /* Main Search Loop */
+#ifdef __INTEL_COMPILER
+    /* From intel 'The vector pragma indicates that the loop should be
+     * vectorized if it is legal to do so'. Can be used together with
+     * #pragma ivdep (but have opted to exclude that because intel
+     * warns against using it).*/
+    #pragma vector always
+#endif
+    while (ip1 < ilimit) {   /* < instead of <=, because check at ip0+2 */
+        size_t mLength;
+        BYTE const* ip2 = ip0 + 2;
+        size_t const h0 = ZSTD_hashPtr(ip0, hlog, mls);
+        U32 const val0 = MEM_read32(ip0);
+        size_t const h1 = ZSTD_hashPtr(ip1, hlog, mls);
+        U32 const val1 = MEM_read32(ip1);
+        U32 const current0 = (U32)(ip0-base);
+        U32 const current1 = (U32)(ip1-base);
+        U32 const matchIndex0 = hashTable[h0];
+        U32 const matchIndex1 = hashTable[h1];
+        BYTE const* repMatch = ip2 - offset_1;
+        const BYTE* match0 = base + matchIndex0;
+        const BYTE* match1 = base + matchIndex1;
+        U32 offcode;
+
+#if defined(__aarch64__)
+        PREFETCH_L1(ip0+256);
+#endif
+
+        hashTable[h0] = current0;   /* update hash table */
+        hashTable[h1] = current1;   /* update hash table */
+
+        assert(ip0 + 1 == ip1);
+
+        if ((offset_1 > 0) & (MEM_read32(repMatch) == MEM_read32(ip2))) {
+            mLength = (ip2[-1] == repMatch[-1]) ? 1 : 0;
+            ip0 = ip2 - mLength;
+            match0 = repMatch - mLength;
+            mLength += 4;
+            offcode = 0;
+            goto _match;
+        }
+        if ((matchIndex0 > prefixStartIndex) && MEM_read32(match0) == val0) {
+            /* found a regular match */
+            goto _offset;
+        }
+        if ((matchIndex1 > prefixStartIndex) && MEM_read32(match1) == val1) {
+            /* found a regular match after one literal */
+            ip0 = ip1;
+            match0 = match1;
+            goto _offset;
+        }
+        {   size_t const step = ((size_t)(ip0-anchor) >> (kSearchStrength - 1)) + stepSize;
+            assert(step >= 2);
+            ip0 += step;
+            ip1 += step;
+            continue;
+        }
+_offset: /* Requires: ip0, match0 */
+        /* Compute the offset code */
+        offset_2 = offset_1;
+        offset_1 = (U32)(ip0-match0);
+        offcode = offset_1 + ZSTD_REP_MOVE;
+        mLength = 4;
+        /* Count the backwards match length */
+        while (((ip0>anchor) & (match0>prefixStart))
+             && (ip0[-1] == match0[-1])) { ip0--; match0--; mLength++; } /* catch up */
+
+_match: /* Requires: ip0, match0, offcode */
+        /* Count the forward length */
+        mLength += ZSTD_count(ip0+mLength, match0+mLength, iend);
+        ZSTD_storeSeq(seqStore, (size_t)(ip0-anchor), anchor, iend, offcode, mLength-MINMATCH);
+        /* match found */
+        ip0 += mLength;
+        anchor = ip0;
+
+        if (ip0 <= ilimit) {
+            /* Fill Table */
+            assert(base+current0+2 > istart);  /* check base overflow */
+            hashTable[ZSTD_hashPtr(base+current0+2, hlog, mls)] = current0+2;  /* here because current+2 could be > iend-8 */
+            hashTable[ZSTD_hashPtr(ip0-2, hlog, mls)] = (U32)(ip0-2-base);
+
+            if (offset_2 > 0) { /* offset_2==0 means offset_2 is invalidated */
+                while ( (ip0 <= ilimit) && (MEM_read32(ip0) == MEM_read32(ip0 - offset_2)) ) {
+                    /* store sequence */
+                    size_t const rLength = ZSTD_count(ip0+4, ip0+4-offset_2, iend) + 4;
+                    { U32 const tmpOff = offset_2; offset_2 = offset_1; offset_1 = tmpOff; } /* swap offset_2 <=> offset_1 */
+                    hashTable[ZSTD_hashPtr(ip0, hlog, mls)] = (U32)(ip0-base);
+                    ip0 += rLength;
+                    ZSTD_storeSeq(seqStore, 0 /*litLen*/, anchor, iend, 0 /*offCode*/, rLength-MINMATCH);
+                    anchor = ip0;
+                    continue;   /* faster when present (confirmed on gcc-8) ... (?) */
+        }   }   }
+        ip1 = ip0 + 1;
+    }
+
+    /* save reps for next block */
+    rep[0] = offset_1 ? offset_1 : offsetSaved;
+    rep[1] = offset_2 ? offset_2 : offsetSaved;
+
+    /* Return the last literals size */
+    return (size_t)(iend - anchor);
+}
+
+
+size_t ZSTD_compressBlock_fast(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize)
+{
+    U32 const mls = ms->cParams.minMatch;
+    assert(ms->dictMatchState == NULL);
+    switch(mls)
+    {
+    default: /* includes case 3 */
+    case 4 :
+        return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 4);
+    case 5 :
+        return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 5);
+    case 6 :
+        return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 6);
+    case 7 :
+        return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 7);
+    }
+}
+
+FORCE_INLINE_TEMPLATE
+size_t ZSTD_compressBlock_fast_dictMatchState_generic(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize, U32 const mls)
+{
+    const ZSTD_compressionParameters* const cParams = &ms->cParams;
+    U32* const hashTable = ms->hashTable;
+    U32 const hlog = cParams->hashLog;
+    /* support stepSize of 0 */
+    U32 const stepSize = cParams->targetLength + !(cParams->targetLength);
+    const BYTE* const base = ms->window.base;
+    const BYTE* const istart = (const BYTE*)src;
+    const BYTE* ip = istart;
+    const BYTE* anchor = istart;
+    const U32   prefixStartIndex = ms->window.dictLimit;
+    const BYTE* const prefixStart = base + prefixStartIndex;
+    const BYTE* const iend = istart + srcSize;
+    const BYTE* const ilimit = iend - HASH_READ_SIZE;
+    U32 offset_1=rep[0], offset_2=rep[1];
+    U32 offsetSaved = 0;
+
+    const ZSTD_matchState_t* const dms = ms->dictMatchState;
+    const ZSTD_compressionParameters* const dictCParams = &dms->cParams ;
+    const U32* const dictHashTable = dms->hashTable;
+    const U32 dictStartIndex       = dms->window.dictLimit;
+    const BYTE* const dictBase     = dms->window.base;
+    const BYTE* const dictStart    = dictBase + dictStartIndex;
+    const BYTE* const dictEnd      = dms->window.nextSrc;
+    const U32 dictIndexDelta       = prefixStartIndex - (U32)(dictEnd - dictBase);
+    const U32 dictAndPrefixLength  = (U32)(ip - prefixStart + dictEnd - dictStart);
+    const U32 dictHLog             = dictCParams->hashLog;
+
+    /* if a dictionary is still attached, it necessarily means that
+     * it is within window size. So we just check it. */
+    const U32 maxDistance = 1U << cParams->windowLog;
+    const U32 endIndex = (U32)((size_t)(ip - base) + srcSize);
+    assert(endIndex - prefixStartIndex <= maxDistance);
+    (void)maxDistance; (void)endIndex;   /* these variables are not used when assert() is disabled */
+
+    /* ensure there will be no underflow
+     * when translating a dict index into a local index */
+    assert(prefixStartIndex >= (U32)(dictEnd - dictBase));
+
+    /* init */
+    DEBUGLOG(5, "ZSTD_compressBlock_fast_dictMatchState_generic");
+    ip += (dictAndPrefixLength == 0);
+    /* dictMatchState repCode checks don't currently handle repCode == 0
+     * disabling. */
+    assert(offset_1 <= dictAndPrefixLength);
+    assert(offset_2 <= dictAndPrefixLength);
+
+    /* Main Search Loop */
+    while (ip < ilimit) {   /* < instead of <=, because repcode check at (ip+1) */
+        size_t mLength;
+        size_t const h = ZSTD_hashPtr(ip, hlog, mls);
+        U32 const curr = (U32)(ip-base);
+        U32 const matchIndex = hashTable[h];
+        const BYTE* match = base + matchIndex;
+        const U32 repIndex = curr + 1 - offset_1;
+        const BYTE* repMatch = (repIndex < prefixStartIndex) ?
+                               dictBase + (repIndex - dictIndexDelta) :
+                               base + repIndex;
+        hashTable[h] = curr;   /* update hash table */
+
+        if ( ((U32)((prefixStartIndex-1) - repIndex) >= 3) /* intentional underflow : ensure repIndex isn't overlapping dict + prefix */
+          && (MEM_read32(repMatch) == MEM_read32(ip+1)) ) {
+            const BYTE* const repMatchEnd = repIndex < prefixStartIndex ? dictEnd : iend;
+            mLength = ZSTD_count_2segments(ip+1+4, repMatch+4, iend, repMatchEnd, prefixStart) + 4;
+            ip++;
+            ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, iend, 0, mLength-MINMATCH);
+        } else if ( (matchIndex <= prefixStartIndex) ) {
+            size_t const dictHash = ZSTD_hashPtr(ip, dictHLog, mls);
+            U32 const dictMatchIndex = dictHashTable[dictHash];
+            const BYTE* dictMatch = dictBase + dictMatchIndex;
+            if (dictMatchIndex <= dictStartIndex ||
+                MEM_read32(dictMatch) != MEM_read32(ip)) {
+                assert(stepSize >= 1);
+                ip += ((ip-anchor) >> kSearchStrength) + stepSize;
+                continue;
+            } else {
+                /* found a dict match */
+                U32 const offset = (U32)(curr-dictMatchIndex-dictIndexDelta);
+                mLength = ZSTD_count_2segments(ip+4, dictMatch+4, iend, dictEnd, prefixStart) + 4;
+                while (((ip>anchor) & (dictMatch>dictStart))
+                     && (ip[-1] == dictMatch[-1])) {
+                    ip--; dictMatch--; mLength++;
+                } /* catch up */
+                offset_2 = offset_1;
+                offset_1 = offset;
+                ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, iend, offset + ZSTD_REP_MOVE, mLength-MINMATCH);
+            }
+        } else if (MEM_read32(match) != MEM_read32(ip)) {
+            /* it's not a match, and we're not going to check the dictionary */
+            assert(stepSize >= 1);
+            ip += ((ip-anchor) >> kSearchStrength) + stepSize;
+            continue;
+        } else {
+            /* found a regular match */
+            U32 const offset = (U32)(ip-match);
+            mLength = ZSTD_count(ip+4, match+4, iend) + 4;
+            while (((ip>anchor) & (match>prefixStart))
+                 && (ip[-1] == match[-1])) { ip--; match--; mLength++; } /* catch up */
+            offset_2 = offset_1;
+            offset_1 = offset;
+            ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, iend, offset + ZSTD_REP_MOVE, mLength-MINMATCH);
+        }
+
+        /* match found */
+        ip += mLength;
+        anchor = ip;
+
+        if (ip <= ilimit) {
+            /* Fill Table */
+            assert(base+curr+2 > istart);  /* check base overflow */
+            hashTable[ZSTD_hashPtr(base+curr+2, hlog, mls)] = curr+2;  /* here because curr+2 could be > iend-8 */
+            hashTable[ZSTD_hashPtr(ip-2, hlog, mls)] = (U32)(ip-2-base);
+
+            /* check immediate repcode */
+            while (ip <= ilimit) {
+                U32 const current2 = (U32)(ip-base);
+                U32 const repIndex2 = current2 - offset_2;
+                const BYTE* repMatch2 = repIndex2 < prefixStartIndex ?
+                        dictBase - dictIndexDelta + repIndex2 :
+                        base + repIndex2;
+                if ( ((U32)((prefixStartIndex-1) - (U32)repIndex2) >= 3 /* intentional overflow */)
+                   && (MEM_read32(repMatch2) == MEM_read32(ip)) ) {
+                    const BYTE* const repEnd2 = repIndex2 < prefixStartIndex ? dictEnd : iend;
+                    size_t const repLength2 = ZSTD_count_2segments(ip+4, repMatch2+4, iend, repEnd2, prefixStart) + 4;
+                    U32 tmpOffset = offset_2; offset_2 = offset_1; offset_1 = tmpOffset;   /* swap offset_2 <=> offset_1 */
+                    ZSTD_storeSeq(seqStore, 0, anchor, iend, 0, repLength2-MINMATCH);
+                    hashTable[ZSTD_hashPtr(ip, hlog, mls)] = current2;
+                    ip += repLength2;
+                    anchor = ip;
+                    continue;
+                }
+                break;
+            }
+        }
+    }
+
+    /* save reps for next block */
+    rep[0] = offset_1 ? offset_1 : offsetSaved;
+    rep[1] = offset_2 ? offset_2 : offsetSaved;
+
+    /* Return the last literals size */
+    return (size_t)(iend - anchor);
+}
+
+size_t ZSTD_compressBlock_fast_dictMatchState(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize)
+{
+    U32 const mls = ms->cParams.minMatch;
+    assert(ms->dictMatchState != NULL);
+    switch(mls)
+    {
+    default: /* includes case 3 */
+    case 4 :
+        return ZSTD_compressBlock_fast_dictMatchState_generic(ms, seqStore, rep, src, srcSize, 4);
+    case 5 :
+        return ZSTD_compressBlock_fast_dictMatchState_generic(ms, seqStore, rep, src, srcSize, 5);
+    case 6 :
+        return ZSTD_compressBlock_fast_dictMatchState_generic(ms, seqStore, rep, src, srcSize, 6);
+    case 7 :
+        return ZSTD_compressBlock_fast_dictMatchState_generic(ms, seqStore, rep, src, srcSize, 7);
+    }
+}
+
+
+static size_t ZSTD_compressBlock_fast_extDict_generic(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize, U32 const mls)
+{
+    const ZSTD_compressionParameters* const cParams = &ms->cParams;
+    U32* const hashTable = ms->hashTable;
+    U32 const hlog = cParams->hashLog;
+    /* support stepSize of 0 */
+    U32 const stepSize = cParams->targetLength + !(cParams->targetLength);
+    const BYTE* const base = ms->window.base;
+    const BYTE* const dictBase = ms->window.dictBase;
+    const BYTE* const istart = (const BYTE*)src;
+    const BYTE* ip = istart;
+    const BYTE* anchor = istart;
+    const U32   endIndex = (U32)((size_t)(istart - base) + srcSize);
+    const U32   lowLimit = ZSTD_getLowestMatchIndex(ms, endIndex, cParams->windowLog);
+    const U32   dictStartIndex = lowLimit;
+    const BYTE* const dictStart = dictBase + dictStartIndex;
+    const U32   dictLimit = ms->window.dictLimit;
+    const U32   prefixStartIndex = dictLimit < lowLimit ? lowLimit : dictLimit;
+    const BYTE* const prefixStart = base + prefixStartIndex;
+    const BYTE* const dictEnd = dictBase + prefixStartIndex;
+    const BYTE* const iend = istart + srcSize;
+    const BYTE* const ilimit = iend - 8;
+    U32 offset_1=rep[0], offset_2=rep[1];
+
+    DEBUGLOG(5, "ZSTD_compressBlock_fast_extDict_generic (offset_1=%u)", offset_1);
+
+    /* switch to "regular" variant if extDict is invalidated due to maxDistance */
+    if (prefixStartIndex == dictStartIndex)
+        return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, mls);
+
+    /* Search Loop */
+    while (ip < ilimit) {  /* < instead of <=, because (ip+1) */
+        const size_t h = ZSTD_hashPtr(ip, hlog, mls);
+        const U32    matchIndex = hashTable[h];
+        const BYTE* const matchBase = matchIndex < prefixStartIndex ? dictBase : base;
+        const BYTE*  match = matchBase + matchIndex;
+        const U32    curr = (U32)(ip-base);
+        const U32    repIndex = curr + 1 - offset_1;
+        const BYTE* const repBase = repIndex < prefixStartIndex ? dictBase : base;
+        const BYTE* const repMatch = repBase + repIndex;
+        hashTable[h] = curr;   /* update hash table */
+        DEBUGLOG(7, "offset_1 = %u , curr = %u", offset_1, curr);
+        assert(offset_1 <= curr +1);   /* check repIndex */
+
+        if ( (((U32)((prefixStartIndex-1) - repIndex) >= 3) /* intentional underflow */ & (repIndex > dictStartIndex))
+           && (MEM_read32(repMatch) == MEM_read32(ip+1)) ) {
+            const BYTE* const repMatchEnd = repIndex < prefixStartIndex ? dictEnd : iend;
+            size_t const rLength = ZSTD_count_2segments(ip+1 +4, repMatch +4, iend, repMatchEnd, prefixStart) + 4;
+            ip++;
+            ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, iend, 0, rLength-MINMATCH);
+            ip += rLength;
+            anchor = ip;
+        } else {
+            if ( (matchIndex < dictStartIndex) ||
+                 (MEM_read32(match) != MEM_read32(ip)) ) {
+                assert(stepSize >= 1);
+                ip += ((ip-anchor) >> kSearchStrength) + stepSize;
+                continue;
+            }
+            {   const BYTE* const matchEnd = matchIndex < prefixStartIndex ? dictEnd : iend;
+                const BYTE* const lowMatchPtr = matchIndex < prefixStartIndex ? dictStart : prefixStart;
+                U32 const offset = curr - matchIndex;
+                size_t mLength = ZSTD_count_2segments(ip+4, match+4, iend, matchEnd, prefixStart) + 4;
+                while (((ip>anchor) & (match>lowMatchPtr)) && (ip[-1] == match[-1])) { ip--; match--; mLength++; }   /* catch up */
+                offset_2 = offset_1; offset_1 = offset;  /* update offset history */
+                ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, iend, offset + ZSTD_REP_MOVE, mLength-MINMATCH);
+                ip += mLength;
+                anchor = ip;
+        }   }
+
+        if (ip <= ilimit) {
+            /* Fill Table */
+            hashTable[ZSTD_hashPtr(base+curr+2, hlog, mls)] = curr+2;
+            hashTable[ZSTD_hashPtr(ip-2, hlog, mls)] = (U32)(ip-2-base);
+            /* check immediate repcode */
+            while (ip <= ilimit) {
+                U32 const current2 = (U32)(ip-base);
+                U32 const repIndex2 = current2 - offset_2;
+                const BYTE* const repMatch2 = repIndex2 < prefixStartIndex ? dictBase + repIndex2 : base + repIndex2;
+                if ( (((U32)((prefixStartIndex-1) - repIndex2) >= 3) & (repIndex2 > dictStartIndex))  /* intentional overflow */
+                   && (MEM_read32(repMatch2) == MEM_read32(ip)) ) {
+                    const BYTE* const repEnd2 = repIndex2 < prefixStartIndex ? dictEnd : iend;
+                    size_t const repLength2 = ZSTD_count_2segments(ip+4, repMatch2+4, iend, repEnd2, prefixStart) + 4;
+                    { U32 const tmpOffset = offset_2; offset_2 = offset_1; offset_1 = tmpOffset; }  /* swap offset_2 <=> offset_1 */
+                    ZSTD_storeSeq(seqStore, 0 /*litlen*/, anchor, iend, 0 /*offcode*/, repLength2-MINMATCH);
+                    hashTable[ZSTD_hashPtr(ip, hlog, mls)] = current2;
+                    ip += repLength2;
+                    anchor = ip;
+                    continue;
+                }
+                break;
+    }   }   }
+
+    /* save reps for next block */
+    rep[0] = offset_1;
+    rep[1] = offset_2;
+
+    /* Return the last literals size */
+    return (size_t)(iend - anchor);
+}
+
+
+size_t ZSTD_compressBlock_fast_extDict(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize)
+{
+    U32 const mls = ms->cParams.minMatch;
+    switch(mls)
+    {
+    default: /* includes case 3 */
+    case 4 :
+        return ZSTD_compressBlock_fast_extDict_generic(ms, seqStore, rep, src, srcSize, 4);
+    case 5 :
+        return ZSTD_compressBlock_fast_extDict_generic(ms, seqStore, rep, src, srcSize, 5);
+    case 6 :
+        return ZSTD_compressBlock_fast_extDict_generic(ms, seqStore, rep, src, srcSize, 6);
+    case 7 :
+        return ZSTD_compressBlock_fast_extDict_generic(ms, seqStore, rep, src, srcSize, 7);
+    }
+}
diff --git a/lib/zstd/compress/zstd_fast.h b/lib/zstd/compress/zstd_fast.h
new file mode 100644
index 000000000000..fddc2f532d21
--- /dev/null
+++ b/lib/zstd/compress/zstd_fast.h
@@ -0,0 +1,31 @@
+/*
+ * Copyright (c) Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+#ifndef ZSTD_FAST_H
+#define ZSTD_FAST_H
+
+
+#include "../common/mem.h"      /* U32 */
+#include "zstd_compress_internal.h"
+
+void ZSTD_fillHashTable(ZSTD_matchState_t* ms,
+                        void const* end, ZSTD_dictTableLoadMethod_e dtlm);
+size_t ZSTD_compressBlock_fast(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize);
+size_t ZSTD_compressBlock_fast_dictMatchState(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize);
+size_t ZSTD_compressBlock_fast_extDict(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize);
+
+
+#endif /* ZSTD_FAST_H */
diff --git a/lib/zstd/compress/zstd_lazy.c b/lib/zstd/compress/zstd_lazy.c
new file mode 100644
index 000000000000..fb54d4e28a2b
--- /dev/null
+++ b/lib/zstd/compress/zstd_lazy.c
@@ -0,0 +1,1414 @@
+/*
+ * Copyright (c) Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+#include "zstd_compress_internal.h"
+#include "zstd_lazy.h"
+
+
+/*-*************************************
+*  Binary Tree search
+***************************************/
+
+static void
+ZSTD_updateDUBT(ZSTD_matchState_t* ms,
+                const BYTE* ip, const BYTE* iend,
+                U32 mls)
+{
+    const ZSTD_compressionParameters* const cParams = &ms->cParams;
+    U32* const hashTable = ms->hashTable;
+    U32  const hashLog = cParams->hashLog;
+
+    U32* const bt = ms->chainTable;
+    U32  const btLog  = cParams->chainLog - 1;
+    U32  const btMask = (1 << btLog) - 1;
+
+    const BYTE* const base = ms->window.base;
+    U32 const target = (U32)(ip - base);
+    U32 idx = ms->nextToUpdate;
+
+    if (idx != target)
+        DEBUGLOG(7, "ZSTD_updateDUBT, from %u to %u (dictLimit:%u)",
+                    idx, target, ms->window.dictLimit);
+    assert(ip + 8 <= iend);   /* condition for ZSTD_hashPtr */
+    (void)iend;
+
+    assert(idx >= ms->window.dictLimit);   /* condition for valid base+idx */
+    for ( ; idx < target ; idx++) {
+        size_t const h  = ZSTD_hashPtr(base + idx, hashLog, mls);   /* assumption : ip + 8 <= iend */
+        U32    const matchIndex = hashTable[h];
+
+        U32*   const nextCandidatePtr = bt + 2*(idx&btMask);
+        U32*   const sortMarkPtr  = nextCandidatePtr + 1;
+
+        DEBUGLOG(8, "ZSTD_updateDUBT: insert %u", idx);
+        hashTable[h] = idx;   /* Update Hash Table */
+        *nextCandidatePtr = matchIndex;   /* update BT like a chain */
+        *sortMarkPtr = ZSTD_DUBT_UNSORTED_MARK;
+    }
+    ms->nextToUpdate = target;
+}
+
+
+/* ZSTD_insertDUBT1() :
+ *  sort one already inserted but unsorted position
+ *  assumption : curr >= btlow == (curr - btmask)
+ *  doesn't fail */
+static void
+ZSTD_insertDUBT1(ZSTD_matchState_t* ms,
+                 U32 curr, const BYTE* inputEnd,
+                 U32 nbCompares, U32 btLow,
+                 const ZSTD_dictMode_e dictMode)
+{
+    const ZSTD_compressionParameters* const cParams = &ms->cParams;
+    U32* const bt = ms->chainTable;
+    U32  const btLog  = cParams->chainLog - 1;
+    U32  const btMask = (1 << btLog) - 1;
+    size_t commonLengthSmaller=0, commonLengthLarger=0;
+    const BYTE* const base = ms->window.base;
+    const BYTE* const dictBase = ms->window.dictBase;
+    const U32 dictLimit = ms->window.dictLimit;
+    const BYTE* const ip = (curr>=dictLimit) ? base + curr : dictBase + curr;
+    const BYTE* const iend = (curr>=dictLimit) ? inputEnd : dictBase + dictLimit;
+    const BYTE* const dictEnd = dictBase + dictLimit;
+    const BYTE* const prefixStart = base + dictLimit;
+    const BYTE* match;
+    U32* smallerPtr = bt + 2*(curr&btMask);
+    U32* largerPtr  = smallerPtr + 1;
+    U32 matchIndex = *smallerPtr;   /* this candidate is unsorted : next sorted candidate is reached through *smallerPtr, while *largerPtr contains previous unsorted candidate (which is already saved and can be overwritten) */
+    U32 dummy32;   /* to be nullified at the end */
+    U32 const windowValid = ms->window.lowLimit;
+    U32 const maxDistance = 1U << cParams->windowLog;
+    U32 const windowLow = (curr - windowValid > maxDistance) ? curr - maxDistance : windowValid;
+
+
+    DEBUGLOG(8, "ZSTD_insertDUBT1(%u) (dictLimit=%u, lowLimit=%u)",
+                curr, dictLimit, windowLow);
+    assert(curr >= btLow);
+    assert(ip < iend);   /* condition for ZSTD_count */
+
+    for (; nbCompares && (matchIndex > windowLow); --nbCompares) {
+        U32* const nextPtr = bt + 2*(matchIndex & btMask);
+        size_t matchLength = MIN(commonLengthSmaller, commonLengthLarger);   /* guaranteed minimum nb of common bytes */
+        assert(matchIndex < curr);
+        /* note : all candidates are now supposed sorted,
+         * but it's still possible to have nextPtr[1] == ZSTD_DUBT_UNSORTED_MARK
+         * when a real index has the same value as ZSTD_DUBT_UNSORTED_MARK */
+
+        if ( (dictMode != ZSTD_extDict)
+          || (matchIndex+matchLength >= dictLimit)  /* both in current segment*/
+          || (curr < dictLimit) /* both in extDict */) {
+            const BYTE* const mBase = ( (dictMode != ZSTD_extDict)
+                                     || (matchIndex+matchLength >= dictLimit)) ?
+                                        base : dictBase;
+            assert( (matchIndex+matchLength >= dictLimit)   /* might be wrong if extDict is incorrectly set to 0 */
+                 || (curr < dictLimit) );
+            match = mBase + matchIndex;
+            matchLength += ZSTD_count(ip+matchLength, match+matchLength, iend);
+        } else {
+            match = dictBase + matchIndex;
+            matchLength += ZSTD_count_2segments(ip+matchLength, match+matchLength, iend, dictEnd, prefixStart);
+            if (matchIndex+matchLength >= dictLimit)
+                match = base + matchIndex;   /* preparation for next read of match[matchLength] */
+        }
+
+        DEBUGLOG(8, "ZSTD_insertDUBT1: comparing %u with %u : found %u common bytes ",
+                    curr, matchIndex, (U32)matchLength);
+
+        if (ip+matchLength == iend) {   /* equal : no way to know if inf or sup */
+            break;   /* drop , to guarantee consistency ; miss a bit of compression, but other solutions can corrupt tree */
+        }
+
+        if (match[matchLength] < ip[matchLength]) {  /* necessarily within buffer */
+            /* match is smaller than current */
+            *smallerPtr = matchIndex;             /* update smaller idx */
+            commonLengthSmaller = matchLength;    /* all smaller will now have at least this guaranteed common length */
+            if (matchIndex <= btLow) { smallerPtr=&dummy32; break; }   /* beyond tree size, stop searching */
+            DEBUGLOG(8, "ZSTD_insertDUBT1: %u (>btLow=%u) is smaller : next => %u",
+                        matchIndex, btLow, nextPtr[1]);
+            smallerPtr = nextPtr+1;               /* new "candidate" => larger than match, which was smaller than target */
+            matchIndex = nextPtr[1];              /* new matchIndex, larger than previous and closer to current */
+        } else {
+            /* match is larger than current */
+            *largerPtr = matchIndex;
+            commonLengthLarger = matchLength;
+            if (matchIndex <= btLow) { largerPtr=&dummy32; break; }   /* beyond tree size, stop searching */
+            DEBUGLOG(8, "ZSTD_insertDUBT1: %u (>btLow=%u) is larger => %u",
+                        matchIndex, btLow, nextPtr[0]);
+            largerPtr = nextPtr;
+            matchIndex = nextPtr[0];
+    }   }
+
+    *smallerPtr = *largerPtr = 0;
+}
+
+
+static size_t
+ZSTD_DUBT_findBetterDictMatch (
+        ZSTD_matchState_t* ms,
+        const BYTE* const ip, const BYTE* const iend,
+        size_t* offsetPtr,
+        size_t bestLength,
+        U32 nbCompares,
+        U32 const mls,
+        const ZSTD_dictMode_e dictMode)
+{
+    const ZSTD_matchState_t * const dms = ms->dictMatchState;
+    const ZSTD_compressionParameters* const dmsCParams = &dms->cParams;
+    const U32 * const dictHashTable = dms->hashTable;
+    U32         const hashLog = dmsCParams->hashLog;
+    size_t      const h  = ZSTD_hashPtr(ip, hashLog, mls);
+    U32               dictMatchIndex = dictHashTable[h];
+
+    const BYTE* const base = ms->window.base;
+    const BYTE* const prefixStart = base + ms->window.dictLimit;
+    U32         const curr = (U32)(ip-base);
+    const BYTE* const dictBase = dms->window.base;
+    const BYTE* const dictEnd = dms->window.nextSrc;
+    U32         const dictHighLimit = (U32)(dms->window.nextSrc - dms->window.base);
+    U32         const dictLowLimit = dms->window.lowLimit;
+    U32         const dictIndexDelta = ms->window.lowLimit - dictHighLimit;
+
+    U32*        const dictBt = dms->chainTable;
+    U32         const btLog  = dmsCParams->chainLog - 1;
+    U32         const btMask = (1 << btLog) - 1;
+    U32         const btLow = (btMask >= dictHighLimit - dictLowLimit) ? dictLowLimit : dictHighLimit - btMask;
+
+    size_t commonLengthSmaller=0, commonLengthLarger=0;
+
+    (void)dictMode;
+    assert(dictMode == ZSTD_dictMatchState);
+
+    for (; nbCompares && (dictMatchIndex > dictLowLimit); --nbCompares) {
+        U32* const nextPtr = dictBt + 2*(dictMatchIndex & btMask);
+        size_t matchLength = MIN(commonLengthSmaller, commonLengthLarger);   /* guaranteed minimum nb of common bytes */
+        const BYTE* match = dictBase + dictMatchIndex;
+        matchLength += ZSTD_count_2segments(ip+matchLength, match+matchLength, iend, dictEnd, prefixStart);
+        if (dictMatchIndex+matchLength >= dictHighLimit)
+            match = base + dictMatchIndex + dictIndexDelta;   /* to prepare for next usage of match[matchLength] */
+
+        if (matchLength > bestLength) {
+            U32 matchIndex = dictMatchIndex + dictIndexDelta;
+            if ( (4*(int)(matchLength-bestLength)) > (int)(ZSTD_highbit32(curr-matchIndex+1) - ZSTD_highbit32((U32)offsetPtr[0]+1)) ) {
+                DEBUGLOG(9, "ZSTD_DUBT_findBetterDictMatch(%u) : found better match length %u -> %u and offsetCode %u -> %u (dictMatchIndex %u, matchIndex %u)",
+                    curr, (U32)bestLength, (U32)matchLength, (U32)*offsetPtr, ZSTD_REP_MOVE + curr - matchIndex, dictMatchIndex, matchIndex);
+                bestLength = matchLength, *offsetPtr = ZSTD_REP_MOVE + curr - matchIndex;
+            }
+            if (ip+matchLength == iend) {   /* reached end of input : ip[matchLength] is not valid, no way to know if it's larger or smaller than match */
+                break;   /* drop, to guarantee consistency (miss a little bit of compression) */
+            }
+        }
+
+        if (match[matchLength] < ip[matchLength]) {
+            if (dictMatchIndex <= btLow) { break; }   /* beyond tree size, stop the search */
+            commonLengthSmaller = matchLength;    /* all smaller will now have at least this guaranteed common length */
+            dictMatchIndex = nextPtr[1];              /* new matchIndex larger than previous (closer to current) */
+        } else {
+            /* match is larger than current */
+            if (dictMatchIndex <= btLow) { break; }   /* beyond tree size, stop the search */
+            commonLengthLarger = matchLength;
+            dictMatchIndex = nextPtr[0];
+        }
+    }
+
+    if (bestLength >= MINMATCH) {
+        U32 const mIndex = curr - ((U32)*offsetPtr - ZSTD_REP_MOVE); (void)mIndex;
+        DEBUGLOG(8, "ZSTD_DUBT_findBetterDictMatch(%u) : found match of length %u and offsetCode %u (pos %u)",
+                    curr, (U32)bestLength, (U32)*offsetPtr, mIndex);
+    }
+    return bestLength;
+
+}
+
+
+static size_t
+ZSTD_DUBT_findBestMatch(ZSTD_matchState_t* ms,
+                        const BYTE* const ip, const BYTE* const iend,
+                        size_t* offsetPtr,
+                        U32 const mls,
+                        const ZSTD_dictMode_e dictMode)
+{
+    const ZSTD_compressionParameters* const cParams = &ms->cParams;
+    U32*   const hashTable = ms->hashTable;
+    U32    const hashLog = cParams->hashLog;
+    size_t const h  = ZSTD_hashPtr(ip, hashLog, mls);
+    U32          matchIndex  = hashTable[h];
+
+    const BYTE* const base = ms->window.base;
+    U32    const curr = (U32)(ip-base);
+    U32    const windowLow = ZSTD_getLowestMatchIndex(ms, curr, cParams->windowLog);
+
+    U32*   const bt = ms->chainTable;
+    U32    const btLog  = cParams->chainLog - 1;
+    U32    const btMask = (1 << btLog) - 1;
+    U32    const btLow = (btMask >= curr) ? 0 : curr - btMask;
+    U32    const unsortLimit = MAX(btLow, windowLow);
+
+    U32*         nextCandidate = bt + 2*(matchIndex&btMask);
+    U32*         unsortedMark = bt + 2*(matchIndex&btMask) + 1;
+    U32          nbCompares = 1U << cParams->searchLog;
+    U32          nbCandidates = nbCompares;
+    U32          previousCandidate = 0;
+
+    DEBUGLOG(7, "ZSTD_DUBT_findBestMatch (%u) ", curr);
+    assert(ip <= iend-8);   /* required for h calculation */
+    assert(dictMode != ZSTD_dedicatedDictSearch);
+
+    /* reach end of unsorted candidates list */
+    while ( (matchIndex > unsortLimit)
+         && (*unsortedMark == ZSTD_DUBT_UNSORTED_MARK)
+         && (nbCandidates > 1) ) {
+        DEBUGLOG(8, "ZSTD_DUBT_findBestMatch: candidate %u is unsorted",
+                    matchIndex);
+        *unsortedMark = previousCandidate;  /* the unsortedMark becomes a reversed chain, to move up back to original position */
+        previousCandidate = matchIndex;
+        matchIndex = *nextCandidate;
+        nextCandidate = bt + 2*(matchIndex&btMask);
+        unsortedMark = bt + 2*(matchIndex&btMask) + 1;
+        nbCandidates --;
+    }
+
+    /* nullify last candidate if it's still unsorted
+     * simplification, detrimental to compression ratio, beneficial for speed */
+    if ( (matchIndex > unsortLimit)
+      && (*unsortedMark==ZSTD_DUBT_UNSORTED_MARK) ) {
+        DEBUGLOG(7, "ZSTD_DUBT_findBestMatch: nullify last unsorted candidate %u",
+                    matchIndex);
+        *nextCandidate = *unsortedMark = 0;
+    }
+
+    /* batch sort stacked candidates */
+    matchIndex = previousCandidate;
+    while (matchIndex) {  /* will end on matchIndex == 0 */
+        U32* const nextCandidateIdxPtr = bt + 2*(matchIndex&btMask) + 1;
+        U32 const nextCandidateIdx = *nextCandidateIdxPtr;
+        ZSTD_insertDUBT1(ms, matchIndex, iend,
+                         nbCandidates, unsortLimit, dictMode);
+        matchIndex = nextCandidateIdx;
+        nbCandidates++;
+    }
+
+    /* find longest match */
+    {   size_t commonLengthSmaller = 0, commonLengthLarger = 0;
+        const BYTE* const dictBase = ms->window.dictBase;
+        const U32 dictLimit = ms->window.dictLimit;
+        const BYTE* const dictEnd = dictBase + dictLimit;
+        const BYTE* const prefixStart = base + dictLimit;
+        U32* smallerPtr = bt + 2*(curr&btMask);
+        U32* largerPtr  = bt + 2*(curr&btMask) + 1;
+        U32 matchEndIdx = curr + 8 + 1;
+        U32 dummy32;   /* to be nullified at the end */
+        size_t bestLength = 0;
+
+        matchIndex  = hashTable[h];
+        hashTable[h] = curr;   /* Update Hash Table */
+
+        for (; nbCompares && (matchIndex > windowLow); --nbCompares) {
+            U32* const nextPtr = bt + 2*(matchIndex & btMask);
+            size_t matchLength = MIN(commonLengthSmaller, commonLengthLarger);   /* guaranteed minimum nb of common bytes */
+            const BYTE* match;
+
+            if ((dictMode != ZSTD_extDict) || (matchIndex+matchLength >= dictLimit)) {
+                match = base + matchIndex;
+                matchLength += ZSTD_count(ip+matchLength, match+matchLength, iend);
+            } else {
+                match = dictBase + matchIndex;
+                matchLength += ZSTD_count_2segments(ip+matchLength, match+matchLength, iend, dictEnd, prefixStart);
+                if (matchIndex+matchLength >= dictLimit)
+                    match = base + matchIndex;   /* to prepare for next usage of match[matchLength] */
+            }
+
+            if (matchLength > bestLength) {
+                if (matchLength > matchEndIdx - matchIndex)
+                    matchEndIdx = matchIndex + (U32)matchLength;
+                if ( (4*(int)(matchLength-bestLength)) > (int)(ZSTD_highbit32(curr-matchIndex+1) - ZSTD_highbit32((U32)offsetPtr[0]+1)) )
+                    bestLength = matchLength, *offsetPtr = ZSTD_REP_MOVE + curr - matchIndex;
+                if (ip+matchLength == iend) {   /* equal : no way to know if inf or sup */
+                    if (dictMode == ZSTD_dictMatchState) {
+                        nbCompares = 0; /* in addition to avoiding checking any
+                                         * further in this loop, make sure we
+                                         * skip checking in the dictionary. */
+                    }
+                    break;   /* drop, to guarantee consistency (miss a little bit of compression) */
+                }
+            }
+
+            if (match[matchLength] < ip[matchLength]) {
+                /* match is smaller than current */
+                *smallerPtr = matchIndex;             /* update smaller idx */
+                commonLengthSmaller = matchLength;    /* all smaller will now have at least this guaranteed common length */
+                if (matchIndex <= btLow) { smallerPtr=&dummy32; break; }   /* beyond tree size, stop the search */
+                smallerPtr = nextPtr+1;               /* new "smaller" => larger of match */
+                matchIndex = nextPtr[1];              /* new matchIndex larger than previous (closer to current) */
+            } else {
+                /* match is larger than current */
+                *largerPtr = matchIndex;
+                commonLengthLarger = matchLength;
+                if (matchIndex <= btLow) { largerPtr=&dummy32; break; }   /* beyond tree size, stop the search */
+                largerPtr = nextPtr;
+                matchIndex = nextPtr[0];
+        }   }
+
+        *smallerPtr = *largerPtr = 0;
+
+        assert(nbCompares <= (1U << ZSTD_SEARCHLOG_MAX)); /* Check we haven't underflowed. */
+        if (dictMode == ZSTD_dictMatchState && nbCompares) {
+            bestLength = ZSTD_DUBT_findBetterDictMatch(
+                    ms, ip, iend,
+                    offsetPtr, bestLength, nbCompares,
+                    mls, dictMode);
+        }
+
+        assert(matchEndIdx > curr+8); /* ensure nextToUpdate is increased */
+        ms->nextToUpdate = matchEndIdx - 8;   /* skip repetitive patterns */
+        if (bestLength >= MINMATCH) {
+            U32 const mIndex = curr - ((U32)*offsetPtr - ZSTD_REP_MOVE); (void)mIndex;
+            DEBUGLOG(8, "ZSTD_DUBT_findBestMatch(%u) : found match of length %u and offsetCode %u (pos %u)",
+                        curr, (U32)bestLength, (U32)*offsetPtr, mIndex);
+        }
+        return bestLength;
+    }
+}
+
+
+/* ZSTD_BtFindBestMatch() : Tree updater, providing best match */
+FORCE_INLINE_TEMPLATE size_t
+ZSTD_BtFindBestMatch( ZSTD_matchState_t* ms,
+                const BYTE* const ip, const BYTE* const iLimit,
+                      size_t* offsetPtr,
+                const U32 mls /* template */,
+                const ZSTD_dictMode_e dictMode)
+{
+    DEBUGLOG(7, "ZSTD_BtFindBestMatch");
+    if (ip < ms->window.base + ms->nextToUpdate) return 0;   /* skipped area */
+    ZSTD_updateDUBT(ms, ip, iLimit, mls);
+    return ZSTD_DUBT_findBestMatch(ms, ip, iLimit, offsetPtr, mls, dictMode);
+}
+
+
+static size_t
+ZSTD_BtFindBestMatch_selectMLS (  ZSTD_matchState_t* ms,
+                            const BYTE* ip, const BYTE* const iLimit,
+                                  size_t* offsetPtr)
+{
+    switch(ms->cParams.minMatch)
+    {
+    default : /* includes case 3 */
+    case 4 : return ZSTD_BtFindBestMatch(ms, ip, iLimit, offsetPtr, 4, ZSTD_noDict);
+    case 5 : return ZSTD_BtFindBestMatch(ms, ip, iLimit, offsetPtr, 5, ZSTD_noDict);
+    case 7 :
+    case 6 : return ZSTD_BtFindBestMatch(ms, ip, iLimit, offsetPtr, 6, ZSTD_noDict);
+    }
+}
+
+
+static size_t ZSTD_BtFindBestMatch_dictMatchState_selectMLS (
+                        ZSTD_matchState_t* ms,
+                        const BYTE* ip, const BYTE* const iLimit,
+                        size_t* offsetPtr)
+{
+    switch(ms->cParams.minMatch)
+    {
+    default : /* includes case 3 */
+    case 4 : return ZSTD_BtFindBestMatch(ms, ip, iLimit, offsetPtr, 4, ZSTD_dictMatchState);
+    case 5 : return ZSTD_BtFindBestMatch(ms, ip, iLimit, offsetPtr, 5, ZSTD_dictMatchState);
+    case 7 :
+    case 6 : return ZSTD_BtFindBestMatch(ms, ip, iLimit, offsetPtr, 6, ZSTD_dictMatchState);
+    }
+}
+
+
+static size_t ZSTD_BtFindBestMatch_extDict_selectMLS (
+                        ZSTD_matchState_t* ms,
+                        const BYTE* ip, const BYTE* const iLimit,
+                        size_t* offsetPtr)
+{
+    switch(ms->cParams.minMatch)
+    {
+    default : /* includes case 3 */
+    case 4 : return ZSTD_BtFindBestMatch(ms, ip, iLimit, offsetPtr, 4, ZSTD_extDict);
+    case 5 : return ZSTD_BtFindBestMatch(ms, ip, iLimit, offsetPtr, 5, ZSTD_extDict);
+    case 7 :
+    case 6 : return ZSTD_BtFindBestMatch(ms, ip, iLimit, offsetPtr, 6, ZSTD_extDict);
+    }
+}
+
+
+
+/* *********************************
+*  Hash Chain
+***********************************/
+#define NEXT_IN_CHAIN(d, mask)   chainTable[(d) & (mask)]
+
+/* Update chains up to ip (excluded)
+   Assumption : always within prefix (i.e. not within extDict) */
+FORCE_INLINE_TEMPLATE U32 ZSTD_insertAndFindFirstIndex_internal(
+                        ZSTD_matchState_t* ms,
+                        const ZSTD_compressionParameters* const cParams,
+                        const BYTE* ip, U32 const mls)
+{
+    U32* const hashTable  = ms->hashTable;
+    const U32 hashLog = cParams->hashLog;
+    U32* const chainTable = ms->chainTable;
+    const U32 chainMask = (1 << cParams->chainLog) - 1;
+    const BYTE* const base = ms->window.base;
+    const U32 target = (U32)(ip - base);
+    U32 idx = ms->nextToUpdate;
+
+    while(idx < target) { /* catch up */
+        size_t const h = ZSTD_hashPtr(base+idx, hashLog, mls);
+        NEXT_IN_CHAIN(idx, chainMask) = hashTable[h];
+        hashTable[h] = idx;
+        idx++;
+    }
+
+    ms->nextToUpdate = target;
+    return hashTable[ZSTD_hashPtr(ip, hashLog, mls)];
+}
+
+U32 ZSTD_insertAndFindFirstIndex(ZSTD_matchState_t* ms, const BYTE* ip) {
+    const ZSTD_compressionParameters* const cParams = &ms->cParams;
+    return ZSTD_insertAndFindFirstIndex_internal(ms, cParams, ip, ms->cParams.minMatch);
+}
+
+void ZSTD_dedicatedDictSearch_lazy_loadDictionary(ZSTD_matchState_t* ms, const BYTE* const ip)
+{
+    const BYTE* const base = ms->window.base;
+    U32 const target = (U32)(ip - base);
+    U32* const hashTable = ms->hashTable;
+    U32* const chainTable = ms->chainTable;
+    U32 const chainSize = 1 << ms->cParams.chainLog;
+    U32 idx = ms->nextToUpdate;
+    U32 const minChain = chainSize < target ? target - chainSize : idx;
+    U32 const bucketSize = 1 << ZSTD_LAZY_DDSS_BUCKET_LOG;
+    U32 const cacheSize = bucketSize - 1;
+    U32 const chainAttempts = (1 << ms->cParams.searchLog) - cacheSize;
+    U32 const chainLimit = chainAttempts > 255 ? 255 : chainAttempts;
+
+    /* We know the hashtable is oversized by a factor of `bucketSize`.
+     * We are going to temporarily pretend `bucketSize == 1`, keeping only a
+     * single entry. We will use the rest of the space to construct a temporary
+     * chaintable.
+     */
+    U32 const hashLog = ms->cParams.hashLog - ZSTD_LAZY_DDSS_BUCKET_LOG;
+    U32* const tmpHashTable = hashTable;
+    U32* const tmpChainTable = hashTable + ((size_t)1 << hashLog);
+    U32 const tmpChainSize = ((1 << ZSTD_LAZY_DDSS_BUCKET_LOG) - 1) << hashLog;
+    U32 const tmpMinChain = tmpChainSize < target ? target - tmpChainSize : idx;
+
+    U32 hashIdx;
+
+    assert(ms->cParams.chainLog <= 24);
+    assert(ms->cParams.hashLog >= ms->cParams.chainLog);
+    assert(idx != 0);
+    assert(tmpMinChain <= minChain);
+
+    /* fill conventional hash table and conventional chain table */
+    for ( ; idx < target; idx++) {
+        U32 const h = (U32)ZSTD_hashPtr(base + idx, hashLog, ms->cParams.minMatch);
+        if (idx >= tmpMinChain) {
+            tmpChainTable[idx - tmpMinChain] = hashTable[h];
+        }
+        tmpHashTable[h] = idx;
+    }
+
+    /* sort chains into ddss chain table */
+    {
+        U32 chainPos = 0;
+        for (hashIdx = 0; hashIdx < (1U << hashLog); hashIdx++) {
+            U32 count;
+            U32 countBeyondMinChain = 0;
+            U32 i = tmpHashTable[hashIdx];
+            for (count = 0; i >= tmpMinChain && count < cacheSize; count++) {
+                /* skip through the chain to the first position that won't be
+                 * in the hash cache bucket */
+                if (i < minChain) {
+                    countBeyondMinChain++;
+                }
+                i = tmpChainTable[i - tmpMinChain];
+            }
+            if (count == cacheSize) {
+                for (count = 0; count < chainLimit;) {
+                    if (i < minChain) {
+                        if (!i || countBeyondMinChain++ > cacheSize) {
+                            /* only allow pulling `cacheSize` number of entries
+                             * into the cache or chainTable beyond `minChain`,
+                             * to replace the entries pulled out of the
+                             * chainTable into the cache. This lets us reach
+                             * back further without increasing the total number
+                             * of entries in the chainTable, guaranteeing the
+                             * DDSS chain table will fit into the space
+                             * allocated for the regular one. */
+                            break;
+                        }
+                    }
+                    chainTable[chainPos++] = i;
+                    count++;
+                    if (i < tmpMinChain) {
+                        break;
+                    }
+                    i = tmpChainTable[i - tmpMinChain];
+                }
+            } else {
+                count = 0;
+            }
+            if (count) {
+                tmpHashTable[hashIdx] = ((chainPos - count) << 8) + count;
+            } else {
+                tmpHashTable[hashIdx] = 0;
+            }
+        }
+        assert(chainPos <= chainSize); /* I believe this is guaranteed... */
+    }
+
+    /* move chain pointers into the last entry of each hash bucket */
+    for (hashIdx = (1 << hashLog); hashIdx; ) {
+        U32 const bucketIdx = --hashIdx << ZSTD_LAZY_DDSS_BUCKET_LOG;
+        U32 const chainPackedPointer = tmpHashTable[hashIdx];
+        U32 i;
+        for (i = 0; i < cacheSize; i++) {
+            hashTable[bucketIdx + i] = 0;
+        }
+        hashTable[bucketIdx + bucketSize - 1] = chainPackedPointer;
+    }
+
+    /* fill the buckets of the hash table */
+    for (idx = ms->nextToUpdate; idx < target; idx++) {
+        U32 const h = (U32)ZSTD_hashPtr(base + idx, hashLog, ms->cParams.minMatch)
+                   << ZSTD_LAZY_DDSS_BUCKET_LOG;
+        U32 i;
+        /* Shift hash cache down 1. */
+        for (i = cacheSize - 1; i; i--)
+            hashTable[h + i] = hashTable[h + i - 1];
+        hashTable[h] = idx;
+    }
+
+    ms->nextToUpdate = target;
+}
+
+
+/* inlining is important to hardwire a hot branch (template emulation) */
+FORCE_INLINE_TEMPLATE
+size_t ZSTD_HcFindBestMatch_generic (
+                        ZSTD_matchState_t* ms,
+                        const BYTE* const ip, const BYTE* const iLimit,
+                        size_t* offsetPtr,
+                        const U32 mls, const ZSTD_dictMode_e dictMode)
+{
+    const ZSTD_compressionParameters* const cParams = &ms->cParams;
+    U32* const chainTable = ms->chainTable;
+    const U32 chainSize = (1 << cParams->chainLog);
+    const U32 chainMask = chainSize-1;
+    const BYTE* const base = ms->window.base;
+    const BYTE* const dictBase = ms->window.dictBase;
+    const U32 dictLimit = ms->window.dictLimit;
+    const BYTE* const prefixStart = base + dictLimit;
+    const BYTE* const dictEnd = dictBase + dictLimit;
+    const U32 curr = (U32)(ip-base);
+    const U32 maxDistance = 1U << cParams->windowLog;
+    const U32 lowestValid = ms->window.lowLimit;
+    const U32 withinMaxDistance = (curr - lowestValid > maxDistance) ? curr - maxDistance : lowestValid;
+    const U32 isDictionary = (ms->loadedDictEnd != 0);
+    const U32 lowLimit = isDictionary ? lowestValid : withinMaxDistance;
+    const U32 minChain = curr > chainSize ? curr - chainSize : 0;
+    U32 nbAttempts = 1U << cParams->searchLog;
+    size_t ml=4-1;
+
+    const ZSTD_matchState_t* const dms = ms->dictMatchState;
+    const U32 ddsHashLog = dictMode == ZSTD_dedicatedDictSearch
+                         ? dms->cParams.hashLog - ZSTD_LAZY_DDSS_BUCKET_LOG : 0;
+    const size_t ddsIdx = dictMode == ZSTD_dedicatedDictSearch
+                        ? ZSTD_hashPtr(ip, ddsHashLog, mls) << ZSTD_LAZY_DDSS_BUCKET_LOG : 0;
+
+    U32 matchIndex;
+
+    if (dictMode == ZSTD_dedicatedDictSearch) {
+        const U32* entry = &dms->hashTable[ddsIdx];
+        PREFETCH_L1(entry);
+    }
+
+    /* HC4 match finder */
+    matchIndex = ZSTD_insertAndFindFirstIndex_internal(ms, cParams, ip, mls);
+
+    for ( ; (matchIndex>=lowLimit) & (nbAttempts>0) ; nbAttempts--) {
+        size_t currentMl=0;
+        if ((dictMode != ZSTD_extDict) || matchIndex >= dictLimit) {
+            const BYTE* const match = base + matchIndex;
+            assert(matchIndex >= dictLimit);   /* ensures this is true if dictMode != ZSTD_extDict */
+            if (match[ml] == ip[ml])   /* potentially better */
+                currentMl = ZSTD_count(ip, match, iLimit);
+        } else {
+            const BYTE* const match = dictBase + matchIndex;
+            assert(match+4 <= dictEnd);
+            if (MEM_read32(match) == MEM_read32(ip))   /* assumption : matchIndex <= dictLimit-4 (by table construction) */
+                currentMl = ZSTD_count_2segments(ip+4, match+4, iLimit, dictEnd, prefixStart) + 4;
+        }
+
+        /* save best solution */
+        if (currentMl > ml) {
+            ml = currentMl;
+            *offsetPtr = curr - matchIndex + ZSTD_REP_MOVE;
+            if (ip+currentMl == iLimit) break; /* best possible, avoids read overflow on next attempt */
+        }
+
+        if (matchIndex <= minChain) break;
+        matchIndex = NEXT_IN_CHAIN(matchIndex, chainMask);
+    }
+
+    assert(nbAttempts <= (1U << ZSTD_SEARCHLOG_MAX)); /* Check we haven't underflowed. */
+    if (dictMode == ZSTD_dedicatedDictSearch) {
+        const U32 ddsLowestIndex  = dms->window.dictLimit;
+        const BYTE* const ddsBase = dms->window.base;
+        const BYTE* const ddsEnd  = dms->window.nextSrc;
+        const U32 ddsSize         = (U32)(ddsEnd - ddsBase);
+        const U32 ddsIndexDelta   = dictLimit - ddsSize;
+        const U32 bucketSize      = (1 << ZSTD_LAZY_DDSS_BUCKET_LOG);
+        const U32 bucketLimit     = nbAttempts < bucketSize - 1 ? nbAttempts : bucketSize - 1;
+        U32 ddsAttempt;
+
+        for (ddsAttempt = 0; ddsAttempt < bucketSize - 1; ddsAttempt++) {
+            PREFETCH_L1(ddsBase + dms->hashTable[ddsIdx + ddsAttempt]);
+        }
+
+        {
+            U32 const chainPackedPointer = dms->hashTable[ddsIdx + bucketSize - 1];
+            U32 const chainIndex = chainPackedPointer >> 8;
+
+            PREFETCH_L1(&dms->chainTable[chainIndex]);
+        }
+
+        for (ddsAttempt = 0; ddsAttempt < bucketLimit; ddsAttempt++) {
+            size_t currentMl=0;
+            const BYTE* match;
+            matchIndex = dms->hashTable[ddsIdx + ddsAttempt];
+            match = ddsBase + matchIndex;
+
+            if (!matchIndex) {
+                return ml;
+            }
+
+            /* guaranteed by table construction */
+            (void)ddsLowestIndex;
+            assert(matchIndex >= ddsLowestIndex);
+            assert(match+4 <= ddsEnd);
+            if (MEM_read32(match) == MEM_read32(ip)) {
+                /* assumption : matchIndex <= dictLimit-4 (by table construction) */
+                currentMl = ZSTD_count_2segments(ip+4, match+4, iLimit, ddsEnd, prefixStart) + 4;
+            }
+
+            /* save best solution */
+            if (currentMl > ml) {
+                ml = currentMl;
+                *offsetPtr = curr - (matchIndex + ddsIndexDelta) + ZSTD_REP_MOVE;
+                if (ip+currentMl == iLimit) {
+                    /* best possible, avoids read overflow on next attempt */
+                    return ml;
+                }
+            }
+        }
+
+        {
+            U32 const chainPackedPointer = dms->hashTable[ddsIdx + bucketSize - 1];
+            U32 chainIndex = chainPackedPointer >> 8;
+            U32 const chainLength = chainPackedPointer & 0xFF;
+            U32 const chainAttempts = nbAttempts - ddsAttempt;
+            U32 const chainLimit = chainAttempts > chainLength ? chainLength : chainAttempts;
+            U32 chainAttempt;
+
+            for (chainAttempt = 0 ; chainAttempt < chainLimit; chainAttempt++) {
+                PREFETCH_L1(ddsBase + dms->chainTable[chainIndex + chainAttempt]);
+            }
+
+            for (chainAttempt = 0 ; chainAttempt < chainLimit; chainAttempt++, chainIndex++) {
+                size_t currentMl=0;
+                const BYTE* match;
+                matchIndex = dms->chainTable[chainIndex];
+                match = ddsBase + matchIndex;
+
+                /* guaranteed by table construction */
+                assert(matchIndex >= ddsLowestIndex);
+                assert(match+4 <= ddsEnd);
+                if (MEM_read32(match) == MEM_read32(ip)) {
+                    /* assumption : matchIndex <= dictLimit-4 (by table construction) */
+                    currentMl = ZSTD_count_2segments(ip+4, match+4, iLimit, ddsEnd, prefixStart) + 4;
+                }
+
+                /* save best solution */
+                if (currentMl > ml) {
+                    ml = currentMl;
+                    *offsetPtr = curr - (matchIndex + ddsIndexDelta) + ZSTD_REP_MOVE;
+                    if (ip+currentMl == iLimit) break; /* best possible, avoids read overflow on next attempt */
+                }
+            }
+        }
+    } else if (dictMode == ZSTD_dictMatchState) {
+        const U32* const dmsChainTable = dms->chainTable;
+        const U32 dmsChainSize         = (1 << dms->cParams.chainLog);
+        const U32 dmsChainMask         = dmsChainSize - 1;
+        const U32 dmsLowestIndex       = dms->window.dictLimit;
+        const BYTE* const dmsBase      = dms->window.base;
+        const BYTE* const dmsEnd       = dms->window.nextSrc;
+        const U32 dmsSize              = (U32)(dmsEnd - dmsBase);
+        const U32 dmsIndexDelta        = dictLimit - dmsSize;
+        const U32 dmsMinChain = dmsSize > dmsChainSize ? dmsSize - dmsChainSize : 0;
+
+        matchIndex = dms->hashTable[ZSTD_hashPtr(ip, dms->cParams.hashLog, mls)];
+
+        for ( ; (matchIndex>=dmsLowestIndex) & (nbAttempts>0) ; nbAttempts--) {
+            size_t currentMl=0;
+            const BYTE* const match = dmsBase + matchIndex;
+            assert(match+4 <= dmsEnd);
+            if (MEM_read32(match) == MEM_read32(ip))   /* assumption : matchIndex <= dictLimit-4 (by table construction) */
+                currentMl = ZSTD_count_2segments(ip+4, match+4, iLimit, dmsEnd, prefixStart) + 4;
+
+            /* save best solution */
+            if (currentMl > ml) {
+                ml = currentMl;
+                *offsetPtr = curr - (matchIndex + dmsIndexDelta) + ZSTD_REP_MOVE;
+                if (ip+currentMl == iLimit) break; /* best possible, avoids read overflow on next attempt */
+            }
+
+            if (matchIndex <= dmsMinChain) break;
+
+            matchIndex = dmsChainTable[matchIndex & dmsChainMask];
+        }
+    }
+
+    return ml;
+}
+
+
+FORCE_INLINE_TEMPLATE size_t ZSTD_HcFindBestMatch_selectMLS (
+                        ZSTD_matchState_t* ms,
+                        const BYTE* ip, const BYTE* const iLimit,
+                        size_t* offsetPtr)
+{
+    switch(ms->cParams.minMatch)
+    {
+    default : /* includes case 3 */
+    case 4 : return ZSTD_HcFindBestMatch_generic(ms, ip, iLimit, offsetPtr, 4, ZSTD_noDict);
+    case 5 : return ZSTD_HcFindBestMatch_generic(ms, ip, iLimit, offsetPtr, 5, ZSTD_noDict);
+    case 7 :
+    case 6 : return ZSTD_HcFindBestMatch_generic(ms, ip, iLimit, offsetPtr, 6, ZSTD_noDict);
+    }
+}
+
+
+static size_t ZSTD_HcFindBestMatch_dictMatchState_selectMLS (
+                        ZSTD_matchState_t* ms,
+                        const BYTE* ip, const BYTE* const iLimit,
+                        size_t* offsetPtr)
+{
+    switch(ms->cParams.minMatch)
+    {
+    default : /* includes case 3 */
+    case 4 : return ZSTD_HcFindBestMatch_generic(ms, ip, iLimit, offsetPtr, 4, ZSTD_dictMatchState);
+    case 5 : return ZSTD_HcFindBestMatch_generic(ms, ip, iLimit, offsetPtr, 5, ZSTD_dictMatchState);
+    case 7 :
+    case 6 : return ZSTD_HcFindBestMatch_generic(ms, ip, iLimit, offsetPtr, 6, ZSTD_dictMatchState);
+    }
+}
+
+
+static size_t ZSTD_HcFindBestMatch_dedicatedDictSearch_selectMLS (
+                        ZSTD_matchState_t* ms,
+                        const BYTE* ip, const BYTE* const iLimit,
+                        size_t* offsetPtr)
+{
+    switch(ms->cParams.minMatch)
+    {
+    default : /* includes case 3 */
+    case 4 : return ZSTD_HcFindBestMatch_generic(ms, ip, iLimit, offsetPtr, 4, ZSTD_dedicatedDictSearch);
+    case 5 : return ZSTD_HcFindBestMatch_generic(ms, ip, iLimit, offsetPtr, 5, ZSTD_dedicatedDictSearch);
+    case 7 :
+    case 6 : return ZSTD_HcFindBestMatch_generic(ms, ip, iLimit, offsetPtr, 6, ZSTD_dedicatedDictSearch);
+    }
+}
+
+
+FORCE_INLINE_TEMPLATE size_t ZSTD_HcFindBestMatch_extDict_selectMLS (
+                        ZSTD_matchState_t* ms,
+                        const BYTE* ip, const BYTE* const iLimit,
+                        size_t* offsetPtr)
+{
+    switch(ms->cParams.minMatch)
+    {
+    default : /* includes case 3 */
+    case 4 : return ZSTD_HcFindBestMatch_generic(ms, ip, iLimit, offsetPtr, 4, ZSTD_extDict);
+    case 5 : return ZSTD_HcFindBestMatch_generic(ms, ip, iLimit, offsetPtr, 5, ZSTD_extDict);
+    case 7 :
+    case 6 : return ZSTD_HcFindBestMatch_generic(ms, ip, iLimit, offsetPtr, 6, ZSTD_extDict);
+    }
+}
+
+
+/* *******************************
+*  Common parser - lazy strategy
+*********************************/
+typedef enum { search_hashChain, search_binaryTree } searchMethod_e;
+
+FORCE_INLINE_TEMPLATE size_t
+ZSTD_compressBlock_lazy_generic(
+                        ZSTD_matchState_t* ms, seqStore_t* seqStore,
+                        U32 rep[ZSTD_REP_NUM],
+                        const void* src, size_t srcSize,
+                        const searchMethod_e searchMethod, const U32 depth,
+                        ZSTD_dictMode_e const dictMode)
+{
+    const BYTE* const istart = (const BYTE*)src;
+    const BYTE* ip = istart;
+    const BYTE* anchor = istart;
+    const BYTE* const iend = istart + srcSize;
+    const BYTE* const ilimit = iend - 8;
+    const BYTE* const base = ms->window.base;
+    const U32 prefixLowestIndex = ms->window.dictLimit;
+    const BYTE* const prefixLowest = base + prefixLowestIndex;
+
+    typedef size_t (*searchMax_f)(
+                        ZSTD_matchState_t* ms,
+                        const BYTE* ip, const BYTE* iLimit, size_t* offsetPtr);
+
+    /*
+     * This table is indexed first by the four ZSTD_dictMode_e values, and then
+     * by the two searchMethod_e values. NULLs are placed for configurations
+     * that should never occur (extDict modes go to the other implementation
+     * below and there is no DDSS for binary tree search yet).
+     */
+    const searchMax_f searchFuncs[4][2] = {
+        {
+            ZSTD_HcFindBestMatch_selectMLS,
+            ZSTD_BtFindBestMatch_selectMLS
+        },
+        {
+            NULL,
+            NULL
+        },
+        {
+            ZSTD_HcFindBestMatch_dictMatchState_selectMLS,
+            ZSTD_BtFindBestMatch_dictMatchState_selectMLS
+        },
+        {
+            ZSTD_HcFindBestMatch_dedicatedDictSearch_selectMLS,
+            NULL
+        }
+    };
+
+    searchMax_f const searchMax = searchFuncs[dictMode][searchMethod == search_binaryTree];
+    U32 offset_1 = rep[0], offset_2 = rep[1], savedOffset=0;
+
+    const int isDMS = dictMode == ZSTD_dictMatchState;
+    const int isDDS = dictMode == ZSTD_dedicatedDictSearch;
+    const int isDxS = isDMS || isDDS;
+    const ZSTD_matchState_t* const dms = ms->dictMatchState;
+    const U32 dictLowestIndex      = isDxS ? dms->window.dictLimit : 0;
+    const BYTE* const dictBase     = isDxS ? dms->window.base : NULL;
+    const BYTE* const dictLowest   = isDxS ? dictBase + dictLowestIndex : NULL;
+    const BYTE* const dictEnd      = isDxS ? dms->window.nextSrc : NULL;
+    const U32 dictIndexDelta       = isDxS ?
+                                     prefixLowestIndex - (U32)(dictEnd - dictBase) :
+                                     0;
+    const U32 dictAndPrefixLength = (U32)((ip - prefixLowest) + (dictEnd - dictLowest));
+
+    assert(searchMax != NULL);
+
+    DEBUGLOG(5, "ZSTD_compressBlock_lazy_generic (dictMode=%u)", (U32)dictMode);
+
+    /* init */
+    ip += (dictAndPrefixLength == 0);
+    if (dictMode == ZSTD_noDict) {
+        U32 const curr = (U32)(ip - base);
+        U32 const windowLow = ZSTD_getLowestPrefixIndex(ms, curr, ms->cParams.windowLog);
+        U32 const maxRep = curr - windowLow;
+        if (offset_2 > maxRep) savedOffset = offset_2, offset_2 = 0;
+        if (offset_1 > maxRep) savedOffset = offset_1, offset_1 = 0;
+    }
+    if (isDxS) {
+        /* dictMatchState repCode checks don't currently handle repCode == 0
+         * disabling. */
+        assert(offset_1 <= dictAndPrefixLength);
+        assert(offset_2 <= dictAndPrefixLength);
+    }
+
+    /* Match Loop */
+#if defined(__x86_64__)
+    /* I've measured random a 5% speed loss on levels 5 & 6 (greedy) when the
+     * code alignment is perturbed. To fix the instability align the loop on 32-bytes.
+     */
+    __asm__(".p2align 5");
+#endif
+    while (ip < ilimit) {
+        size_t matchLength=0;
+        size_t offset=0;
+        const BYTE* start=ip+1;
+
+        /* check repCode */
+        if (isDxS) {
+            const U32 repIndex = (U32)(ip - base) + 1 - offset_1;
+            const BYTE* repMatch = ((dictMode == ZSTD_dictMatchState || dictMode == ZSTD_dedicatedDictSearch)
+                                && repIndex < prefixLowestIndex) ?
+                                   dictBase + (repIndex - dictIndexDelta) :
+                                   base + repIndex;
+            if (((U32)((prefixLowestIndex-1) - repIndex) >= 3 /* intentional underflow */)
+                && (MEM_read32(repMatch) == MEM_read32(ip+1)) ) {
+                const BYTE* repMatchEnd = repIndex < prefixLowestIndex ? dictEnd : iend;
+                matchLength = ZSTD_count_2segments(ip+1+4, repMatch+4, iend, repMatchEnd, prefixLowest) + 4;
+                if (depth==0) goto _storeSequence;
+            }
+        }
+        if ( dictMode == ZSTD_noDict
+          && ((offset_1 > 0) & (MEM_read32(ip+1-offset_1) == MEM_read32(ip+1)))) {
+            matchLength = ZSTD_count(ip+1+4, ip+1+4-offset_1, iend) + 4;
+            if (depth==0) goto _storeSequence;
+        }
+
+        /* first search (depth 0) */
+        {   size_t offsetFound = 999999999;
+            size_t const ml2 = searchMax(ms, ip, iend, &offsetFound);
+            if (ml2 > matchLength)
+                matchLength = ml2, start = ip, offset=offsetFound;
+        }
+
+        if (matchLength < 4) {
+            ip += ((ip-anchor) >> kSearchStrength) + 1;   /* jump faster over incompressible sections */
+            continue;
+        }
+
+        /* let's try to find a better solution */
+        if (depth>=1)
+        while (ip<ilimit) {
+            ip ++;
+            if ( (dictMode == ZSTD_noDict)
+              && (offset) && ((offset_1>0) & (MEM_read32(ip) == MEM_read32(ip - offset_1)))) {
+                size_t const mlRep = ZSTD_count(ip+4, ip+4-offset_1, iend) + 4;
+                int const gain2 = (int)(mlRep * 3);
+                int const gain1 = (int)(matchLength*3 - ZSTD_highbit32((U32)offset+1) + 1);
+                if ((mlRep >= 4) && (gain2 > gain1))
+                    matchLength = mlRep, offset = 0, start = ip;
+            }
+            if (isDxS) {
+                const U32 repIndex = (U32)(ip - base) - offset_1;
+                const BYTE* repMatch = repIndex < prefixLowestIndex ?
+                               dictBase + (repIndex - dictIndexDelta) :
+                               base + repIndex;
+                if (((U32)((prefixLowestIndex-1) - repIndex) >= 3 /* intentional underflow */)
+                    && (MEM_read32(repMatch) == MEM_read32(ip)) ) {
+                    const BYTE* repMatchEnd = repIndex < prefixLowestIndex ? dictEnd : iend;
+                    size_t const mlRep = ZSTD_count_2segments(ip+4, repMatch+4, iend, repMatchEnd, prefixLowest) + 4;
+                    int const gain2 = (int)(mlRep * 3);
+                    int const gain1 = (int)(matchLength*3 - ZSTD_highbit32((U32)offset+1) + 1);
+                    if ((mlRep >= 4) && (gain2 > gain1))
+                        matchLength = mlRep, offset = 0, start = ip;
+                }
+            }
+            {   size_t offset2=999999999;
+                size_t const ml2 = searchMax(ms, ip, iend, &offset2);
+                int const gain2 = (int)(ml2*4 - ZSTD_highbit32((U32)offset2+1));   /* raw approx */
+                int const gain1 = (int)(matchLength*4 - ZSTD_highbit32((U32)offset+1) + 4);
+                if ((ml2 >= 4) && (gain2 > gain1)) {
+                    matchLength = ml2, offset = offset2, start = ip;
+                    continue;   /* search a better one */
+            }   }
+
+            /* let's find an even better one */
+            if ((depth==2) && (ip<ilimit)) {
+                ip ++;
+                if ( (dictMode == ZSTD_noDict)
+                  && (offset) && ((offset_1>0) & (MEM_read32(ip) == MEM_read32(ip - offset_1)))) {
+                    size_t const mlRep = ZSTD_count(ip+4, ip+4-offset_1, iend) + 4;
+                    int const gain2 = (int)(mlRep * 4);
+                    int const gain1 = (int)(matchLength*4 - ZSTD_highbit32((U32)offset+1) + 1);
+                    if ((mlRep >= 4) && (gain2 > gain1))
+                        matchLength = mlRep, offset = 0, start = ip;
+                }
+                if (isDxS) {
+                    const U32 repIndex = (U32)(ip - base) - offset_1;
+                    const BYTE* repMatch = repIndex < prefixLowestIndex ?
+                                   dictBase + (repIndex - dictIndexDelta) :
+                                   base + repIndex;
+                    if (((U32)((prefixLowestIndex-1) - repIndex) >= 3 /* intentional underflow */)
+                        && (MEM_read32(repMatch) == MEM_read32(ip)) ) {
+                        const BYTE* repMatchEnd = repIndex < prefixLowestIndex ? dictEnd : iend;
+                        size_t const mlRep = ZSTD_count_2segments(ip+4, repMatch+4, iend, repMatchEnd, prefixLowest) + 4;
+                        int const gain2 = (int)(mlRep * 4);
+                        int const gain1 = (int)(matchLength*4 - ZSTD_highbit32((U32)offset+1) + 1);
+                        if ((mlRep >= 4) && (gain2 > gain1))
+                            matchLength = mlRep, offset = 0, start = ip;
+                    }
+                }
+                {   size_t offset2=999999999;
+                    size_t const ml2 = searchMax(ms, ip, iend, &offset2);
+                    int const gain2 = (int)(ml2*4 - ZSTD_highbit32((U32)offset2+1));   /* raw approx */
+                    int const gain1 = (int)(matchLength*4 - ZSTD_highbit32((U32)offset+1) + 7);
+                    if ((ml2 >= 4) && (gain2 > gain1)) {
+                        matchLength = ml2, offset = offset2, start = ip;
+                        continue;
+            }   }   }
+            break;  /* nothing found : store previous solution */
+        }
+
+        /* NOTE:
+         * start[-offset+ZSTD_REP_MOVE-1] is undefined behavior.
+         * (-offset+ZSTD_REP_MOVE-1) is unsigned, and is added to start, which
+         * overflows the pointer, which is undefined behavior.
+         */
+        /* catch up */
+        if (offset) {
+            if (dictMode == ZSTD_noDict) {
+                while ( ((start > anchor) & (start - (offset-ZSTD_REP_MOVE) > prefixLowest))
+                     && (start[-1] == (start-(offset-ZSTD_REP_MOVE))[-1]) )  /* only search for offset within prefix */
+                    { start--; matchLength++; }
+            }
+            if (isDxS) {
+                U32 const matchIndex = (U32)((start-base) - (offset - ZSTD_REP_MOVE));
+                const BYTE* match = (matchIndex < prefixLowestIndex) ? dictBase + matchIndex - dictIndexDelta : base + matchIndex;
+                const BYTE* const mStart = (matchIndex < prefixLowestIndex) ? dictLowest : prefixLowest;
+                while ((start>anchor) && (match>mStart) && (start[-1] == match[-1])) { start--; match--; matchLength++; }  /* catch up */
+            }
+            offset_2 = offset_1; offset_1 = (U32)(offset - ZSTD_REP_MOVE);
+        }
+        /* store sequence */
+_storeSequence:
+        {   size_t const litLength = start - anchor;
+            ZSTD_storeSeq(seqStore, litLength, anchor, iend, (U32)offset, matchLength-MINMATCH);
+            anchor = ip = start + matchLength;
+        }
+
+        /* check immediate repcode */
+        if (isDxS) {
+            while (ip <= ilimit) {
+                U32 const current2 = (U32)(ip-base);
+                U32 const repIndex = current2 - offset_2;
+                const BYTE* repMatch = repIndex < prefixLowestIndex ?
+                        dictBase - dictIndexDelta + repIndex :
+                        base + repIndex;
+                if ( ((U32)((prefixLowestIndex-1) - (U32)repIndex) >= 3 /* intentional overflow */)
+                   && (MEM_read32(repMatch) == MEM_read32(ip)) ) {
+                    const BYTE* const repEnd2 = repIndex < prefixLowestIndex ? dictEnd : iend;
+                    matchLength = ZSTD_count_2segments(ip+4, repMatch+4, iend, repEnd2, prefixLowest) + 4;
+                    offset = offset_2; offset_2 = offset_1; offset_1 = (U32)offset;   /* swap offset_2 <=> offset_1 */
+                    ZSTD_storeSeq(seqStore, 0, anchor, iend, 0, matchLength-MINMATCH);
+                    ip += matchLength;
+                    anchor = ip;
+                    continue;
+                }
+                break;
+            }
+        }
+
+        if (dictMode == ZSTD_noDict) {
+            while ( ((ip <= ilimit) & (offset_2>0))
+                 && (MEM_read32(ip) == MEM_read32(ip - offset_2)) ) {
+                /* store sequence */
+                matchLength = ZSTD_count(ip+4, ip+4-offset_2, iend) + 4;
+                offset = offset_2; offset_2 = offset_1; offset_1 = (U32)offset; /* swap repcodes */
+                ZSTD_storeSeq(seqStore, 0, anchor, iend, 0, matchLength-MINMATCH);
+                ip += matchLength;
+                anchor = ip;
+                continue;   /* faster when present ... (?) */
+    }   }   }
+
+    /* Save reps for next block */
+    rep[0] = offset_1 ? offset_1 : savedOffset;
+    rep[1] = offset_2 ? offset_2 : savedOffset;
+
+    /* Return the last literals size */
+    return (size_t)(iend - anchor);
+}
+
+
+size_t ZSTD_compressBlock_btlazy2(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize)
+{
+    return ZSTD_compressBlock_lazy_generic(ms, seqStore, rep, src, srcSize, search_binaryTree, 2, ZSTD_noDict);
+}
+
+size_t ZSTD_compressBlock_lazy2(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize)
+{
+    return ZSTD_compressBlock_lazy_generic(ms, seqStore, rep, src, srcSize, search_hashChain, 2, ZSTD_noDict);
+}
+
+size_t ZSTD_compressBlock_lazy(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize)
+{
+    return ZSTD_compressBlock_lazy_generic(ms, seqStore, rep, src, srcSize, search_hashChain, 1, ZSTD_noDict);
+}
+
+size_t ZSTD_compressBlock_greedy(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize)
+{
+    return ZSTD_compressBlock_lazy_generic(ms, seqStore, rep, src, srcSize, search_hashChain, 0, ZSTD_noDict);
+}
+
+size_t ZSTD_compressBlock_btlazy2_dictMatchState(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize)
+{
+    return ZSTD_compressBlock_lazy_generic(ms, seqStore, rep, src, srcSize, search_binaryTree, 2, ZSTD_dictMatchState);
+}
+
+size_t ZSTD_compressBlock_lazy2_dictMatchState(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize)
+{
+    return ZSTD_compressBlock_lazy_generic(ms, seqStore, rep, src, srcSize, search_hashChain, 2, ZSTD_dictMatchState);
+}
+
+size_t ZSTD_compressBlock_lazy_dictMatchState(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize)
+{
+    return ZSTD_compressBlock_lazy_generic(ms, seqStore, rep, src, srcSize, search_hashChain, 1, ZSTD_dictMatchState);
+}
+
+size_t ZSTD_compressBlock_greedy_dictMatchState(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize)
+{
+    return ZSTD_compressBlock_lazy_generic(ms, seqStore, rep, src, srcSize, search_hashChain, 0, ZSTD_dictMatchState);
+}
+
+
+size_t ZSTD_compressBlock_lazy2_dedicatedDictSearch(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize)
+{
+    return ZSTD_compressBlock_lazy_generic(ms, seqStore, rep, src, srcSize, search_hashChain, 2, ZSTD_dedicatedDictSearch);
+}
+
+size_t ZSTD_compressBlock_lazy_dedicatedDictSearch(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize)
+{
+    return ZSTD_compressBlock_lazy_generic(ms, seqStore, rep, src, srcSize, search_hashChain, 1, ZSTD_dedicatedDictSearch);
+}
+
+size_t ZSTD_compressBlock_greedy_dedicatedDictSearch(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize)
+{
+    return ZSTD_compressBlock_lazy_generic(ms, seqStore, rep, src, srcSize, search_hashChain, 0, ZSTD_dedicatedDictSearch);
+}
+
+
+FORCE_INLINE_TEMPLATE
+size_t ZSTD_compressBlock_lazy_extDict_generic(
+                        ZSTD_matchState_t* ms, seqStore_t* seqStore,
+                        U32 rep[ZSTD_REP_NUM],
+                        const void* src, size_t srcSize,
+                        const searchMethod_e searchMethod, const U32 depth)
+{
+    const BYTE* const istart = (const BYTE*)src;
+    const BYTE* ip = istart;
+    const BYTE* anchor = istart;
+    const BYTE* const iend = istart + srcSize;
+    const BYTE* const ilimit = iend - 8;
+    const BYTE* const base = ms->window.base;
+    const U32 dictLimit = ms->window.dictLimit;
+    const BYTE* const prefixStart = base + dictLimit;
+    const BYTE* const dictBase = ms->window.dictBase;
+    const BYTE* const dictEnd  = dictBase + dictLimit;
+    const BYTE* const dictStart  = dictBase + ms->window.lowLimit;
+    const U32 windowLog = ms->cParams.windowLog;
+
+    typedef size_t (*searchMax_f)(
+                        ZSTD_matchState_t* ms,
+                        const BYTE* ip, const BYTE* iLimit, size_t* offsetPtr);
+    searchMax_f searchMax = searchMethod==search_binaryTree ? ZSTD_BtFindBestMatch_extDict_selectMLS : ZSTD_HcFindBestMatch_extDict_selectMLS;
+
+    U32 offset_1 = rep[0], offset_2 = rep[1];
+
+    DEBUGLOG(5, "ZSTD_compressBlock_lazy_extDict_generic");
+
+    /* init */
+    ip += (ip == prefixStart);
+
+    /* Match Loop */
+#if defined(__x86_64__)
+    /* I've measured random a 5% speed loss on levels 5 & 6 (greedy) when the
+     * code alignment is perturbed. To fix the instability align the loop on 32-bytes.
+     */
+    __asm__(".p2align 5");
+#endif
+    while (ip < ilimit) {
+        size_t matchLength=0;
+        size_t offset=0;
+        const BYTE* start=ip+1;
+        U32 curr = (U32)(ip-base);
+
+        /* check repCode */
+        {   const U32 windowLow = ZSTD_getLowestMatchIndex(ms, curr+1, windowLog);
+            const U32 repIndex = (U32)(curr+1 - offset_1);
+            const BYTE* const repBase = repIndex < dictLimit ? dictBase : base;
+            const BYTE* const repMatch = repBase + repIndex;
+            if (((U32)((dictLimit-1) - repIndex) >= 3) & (repIndex > windowLow))   /* intentional overflow */
+            if (MEM_read32(ip+1) == MEM_read32(repMatch)) {
+                /* repcode detected we should take it */
+                const BYTE* const repEnd = repIndex < dictLimit ? dictEnd : iend;
+                matchLength = ZSTD_count_2segments(ip+1+4, repMatch+4, iend, repEnd, prefixStart) + 4;
+                if (depth==0) goto _storeSequence;
+        }   }
+
+        /* first search (depth 0) */
+        {   size_t offsetFound = 999999999;
+            size_t const ml2 = searchMax(ms, ip, iend, &offsetFound);
+            if (ml2 > matchLength)
+                matchLength = ml2, start = ip, offset=offsetFound;
+        }
+
+        if (matchLength < 4) {
+            ip += ((ip-anchor) >> kSearchStrength) + 1;   /* jump faster over incompressible sections */
+            continue;
+        }
+
+        /* let's try to find a better solution */
+        if (depth>=1)
+        while (ip<ilimit) {
+            ip ++;
+            curr++;
+            /* check repCode */
+            if (offset) {
+                const U32 windowLow = ZSTD_getLowestMatchIndex(ms, curr, windowLog);
+                const U32 repIndex = (U32)(curr - offset_1);
+                const BYTE* const repBase = repIndex < dictLimit ? dictBase : base;
+                const BYTE* const repMatch = repBase + repIndex;
+                if (((U32)((dictLimit-1) - repIndex) >= 3) & (repIndex > windowLow))  /* intentional overflow */
+                if (MEM_read32(ip) == MEM_read32(repMatch)) {
+                    /* repcode detected */
+                    const BYTE* const repEnd = repIndex < dictLimit ? dictEnd : iend;
+                    size_t const repLength = ZSTD_count_2segments(ip+4, repMatch+4, iend, repEnd, prefixStart) + 4;
+                    int const gain2 = (int)(repLength * 3);
+                    int const gain1 = (int)(matchLength*3 - ZSTD_highbit32((U32)offset+1) + 1);
+                    if ((repLength >= 4) && (gain2 > gain1))
+                        matchLength = repLength, offset = 0, start = ip;
+            }   }
+
+            /* search match, depth 1 */
+            {   size_t offset2=999999999;
+                size_t const ml2 = searchMax(ms, ip, iend, &offset2);
+                int const gain2 = (int)(ml2*4 - ZSTD_highbit32((U32)offset2+1));   /* raw approx */
+                int const gain1 = (int)(matchLength*4 - ZSTD_highbit32((U32)offset+1) + 4);
+                if ((ml2 >= 4) && (gain2 > gain1)) {
+                    matchLength = ml2, offset = offset2, start = ip;
+                    continue;   /* search a better one */
+            }   }
+
+            /* let's find an even better one */
+            if ((depth==2) && (ip<ilimit)) {
+                ip ++;
+                curr++;
+                /* check repCode */
+                if (offset) {
+                    const U32 windowLow = ZSTD_getLowestMatchIndex(ms, curr, windowLog);
+                    const U32 repIndex = (U32)(curr - offset_1);
+                    const BYTE* const repBase = repIndex < dictLimit ? dictBase : base;
+                    const BYTE* const repMatch = repBase + repIndex;
+                    if (((U32)((dictLimit-1) - repIndex) >= 3) & (repIndex > windowLow))  /* intentional overflow */
+                    if (MEM_read32(ip) == MEM_read32(repMatch)) {
+                        /* repcode detected */
+                        const BYTE* const repEnd = repIndex < dictLimit ? dictEnd : iend;
+                        size_t const repLength = ZSTD_count_2segments(ip+4, repMatch+4, iend, repEnd, prefixStart) + 4;
+                        int const gain2 = (int)(repLength * 4);
+                        int const gain1 = (int)(matchLength*4 - ZSTD_highbit32((U32)offset+1) + 1);
+                        if ((repLength >= 4) && (gain2 > gain1))
+                            matchLength = repLength, offset = 0, start = ip;
+                }   }
+
+                /* search match, depth 2 */
+                {   size_t offset2=999999999;
+                    size_t const ml2 = searchMax(ms, ip, iend, &offset2);
+                    int const gain2 = (int)(ml2*4 - ZSTD_highbit32((U32)offset2+1));   /* raw approx */
+                    int const gain1 = (int)(matchLength*4 - ZSTD_highbit32((U32)offset+1) + 7);
+                    if ((ml2 >= 4) && (gain2 > gain1)) {
+                        matchLength = ml2, offset = offset2, start = ip;
+                        continue;
+            }   }   }
+            break;  /* nothing found : store previous solution */
+        }
+
+        /* catch up */
+        if (offset) {
+            U32 const matchIndex = (U32)((start-base) - (offset - ZSTD_REP_MOVE));
+            const BYTE* match = (matchIndex < dictLimit) ? dictBase + matchIndex : base + matchIndex;
+            const BYTE* const mStart = (matchIndex < dictLimit) ? dictStart : prefixStart;
+            while ((start>anchor) && (match>mStart) && (start[-1] == match[-1])) { start--; match--; matchLength++; }  /* catch up */
+            offset_2 = offset_1; offset_1 = (U32)(offset - ZSTD_REP_MOVE);
+        }
+
+        /* store sequence */
+_storeSequence:
+        {   size_t const litLength = start - anchor;
+            ZSTD_storeSeq(seqStore, litLength, anchor, iend, (U32)offset, matchLength-MINMATCH);
+            anchor = ip = start + matchLength;
+        }
+
+        /* check immediate repcode */
+        while (ip <= ilimit) {
+            const U32 repCurrent = (U32)(ip-base);
+            const U32 windowLow = ZSTD_getLowestMatchIndex(ms, repCurrent, windowLog);
+            const U32 repIndex = repCurrent - offset_2;
+            const BYTE* const repBase = repIndex < dictLimit ? dictBase : base;
+            const BYTE* const repMatch = repBase + repIndex;
+            if (((U32)((dictLimit-1) - repIndex) >= 3) & (repIndex > windowLow))  /* intentional overflow */
+            if (MEM_read32(ip) == MEM_read32(repMatch)) {
+                /* repcode detected we should take it */
+                const BYTE* const repEnd = repIndex < dictLimit ? dictEnd : iend;
+                matchLength = ZSTD_count_2segments(ip+4, repMatch+4, iend, repEnd, prefixStart) + 4;
+                offset = offset_2; offset_2 = offset_1; offset_1 = (U32)offset;   /* swap offset history */
+                ZSTD_storeSeq(seqStore, 0, anchor, iend, 0, matchLength-MINMATCH);
+                ip += matchLength;
+                anchor = ip;
+                continue;   /* faster when present ... (?) */
+            }
+            break;
+    }   }
+
+    /* Save reps for next block */
+    rep[0] = offset_1;
+    rep[1] = offset_2;
+
+    /* Return the last literals size */
+    return (size_t)(iend - anchor);
+}
+
+
+size_t ZSTD_compressBlock_greedy_extDict(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize)
+{
+    return ZSTD_compressBlock_lazy_extDict_generic(ms, seqStore, rep, src, srcSize, search_hashChain, 0);
+}
+
+size_t ZSTD_compressBlock_lazy_extDict(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize)
+
+{
+    return ZSTD_compressBlock_lazy_extDict_generic(ms, seqStore, rep, src, srcSize, search_hashChain, 1);
+}
+
+size_t ZSTD_compressBlock_lazy2_extDict(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize)
+
+{
+    return ZSTD_compressBlock_lazy_extDict_generic(ms, seqStore, rep, src, srcSize, search_hashChain, 2);
+}
+
+size_t ZSTD_compressBlock_btlazy2_extDict(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize)
+
+{
+    return ZSTD_compressBlock_lazy_extDict_generic(ms, seqStore, rep, src, srcSize, search_binaryTree, 2);
+}
diff --git a/lib/zstd/compress/zstd_lazy.h b/lib/zstd/compress/zstd_lazy.h
new file mode 100644
index 000000000000..2fc5a6182134
--- /dev/null
+++ b/lib/zstd/compress/zstd_lazy.h
@@ -0,0 +1,81 @@
+/*
+ * Copyright (c) Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+#ifndef ZSTD_LAZY_H
+#define ZSTD_LAZY_H
+
+
+#include "zstd_compress_internal.h"
+
+/*
+ * Dedicated Dictionary Search Structure bucket log. In the
+ * ZSTD_dedicatedDictSearch mode, the hashTable has
+ * 2 ** ZSTD_LAZY_DDSS_BUCKET_LOG entries in each bucket, rather than just
+ * one.
+ */
+#define ZSTD_LAZY_DDSS_BUCKET_LOG 2
+
+U32 ZSTD_insertAndFindFirstIndex(ZSTD_matchState_t* ms, const BYTE* ip);
+
+void ZSTD_dedicatedDictSearch_lazy_loadDictionary(ZSTD_matchState_t* ms, const BYTE* const ip);
+
+void ZSTD_preserveUnsortedMark (U32* const table, U32 const size, U32 const reducerValue);  /*! used in ZSTD_reduceIndex(). preemptively increase value of ZSTD_DUBT_UNSORTED_MARK */
+
+size_t ZSTD_compressBlock_btlazy2(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize);
+size_t ZSTD_compressBlock_lazy2(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize);
+size_t ZSTD_compressBlock_lazy(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize);
+size_t ZSTD_compressBlock_greedy(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize);
+
+size_t ZSTD_compressBlock_btlazy2_dictMatchState(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize);
+size_t ZSTD_compressBlock_lazy2_dictMatchState(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize);
+size_t ZSTD_compressBlock_lazy_dictMatchState(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize);
+size_t ZSTD_compressBlock_greedy_dictMatchState(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize);
+
+size_t ZSTD_compressBlock_lazy2_dedicatedDictSearch(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize);
+size_t ZSTD_compressBlock_lazy_dedicatedDictSearch(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize);
+size_t ZSTD_compressBlock_greedy_dedicatedDictSearch(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize);
+
+size_t ZSTD_compressBlock_greedy_extDict(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize);
+size_t ZSTD_compressBlock_lazy_extDict(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize);
+size_t ZSTD_compressBlock_lazy2_extDict(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize);
+size_t ZSTD_compressBlock_btlazy2_extDict(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize);
+
+
+#endif /* ZSTD_LAZY_H */
diff --git a/lib/zstd/compress/zstd_ldm.c b/lib/zstd/compress/zstd_ldm.c
new file mode 100644
index 000000000000..8ef7e88a5add
--- /dev/null
+++ b/lib/zstd/compress/zstd_ldm.c
@@ -0,0 +1,686 @@
+/*
+ * Copyright (c) Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+#include "zstd_ldm.h"
+
+#include "../common/debug.h"
+#include <linux/xxhash.h>
+#include "zstd_fast.h"          /* ZSTD_fillHashTable() */
+#include "zstd_double_fast.h"   /* ZSTD_fillDoubleHashTable() */
+#include "zstd_ldm_geartab.h"
+
+#define LDM_BUCKET_SIZE_LOG 3
+#define LDM_MIN_MATCH_LENGTH 64
+#define LDM_HASH_RLOG 7
+
+typedef struct {
+    U64 rolling;
+    U64 stopMask;
+} ldmRollingHashState_t;
+
+/* ZSTD_ldm_gear_init():
+ *
+ * Initializes the rolling hash state such that it will honor the
+ * settings in params. */
+static void ZSTD_ldm_gear_init(ldmRollingHashState_t* state, ldmParams_t const* params)
+{
+    unsigned maxBitsInMask = MIN(params->minMatchLength, 64);
+    unsigned hashRateLog = params->hashRateLog;
+
+    state->rolling = ~(U32)0;
+
+    /* The choice of the splitting criterion is subject to two conditions:
+     *   1. it has to trigger on average every 2^(hashRateLog) bytes;
+     *   2. ideally, it has to depend on a window of minMatchLength bytes.
+     *
+     * In the gear hash algorithm, bit n depends on the last n bytes;
+     * so in order to obtain a good quality splitting criterion it is
+     * preferable to use bits with high weight.
+     *
+     * To match condition 1 we use a mask with hashRateLog bits set
+     * and, because of the previous remark, we make sure these bits
+     * have the highest possible weight while still respecting
+     * condition 2.
+     */
+    if (hashRateLog > 0 && hashRateLog <= maxBitsInMask) {
+        state->stopMask = (((U64)1 << hashRateLog) - 1) << (maxBitsInMask - hashRateLog);
+    } else {
+        /* In this degenerate case we simply honor the hash rate. */
+        state->stopMask = ((U64)1 << hashRateLog) - 1;
+    }
+}
+
+/* ZSTD_ldm_gear_feed():
+ *
+ * Registers in the splits array all the split points found in the first
+ * size bytes following the data pointer. This function terminates when
+ * either all the data has been processed or LDM_BATCH_SIZE splits are
+ * present in the splits array.
+ *
+ * Precondition: The splits array must not be full.
+ * Returns: The number of bytes processed. */
+static size_t ZSTD_ldm_gear_feed(ldmRollingHashState_t* state,
+                                 BYTE const* data, size_t size,
+                                 size_t* splits, unsigned* numSplits)
+{
+    size_t n;
+    U64 hash, mask;
+
+    hash = state->rolling;
+    mask = state->stopMask;
+    n = 0;
+
+#define GEAR_ITER_ONCE() do { \
+        hash = (hash << 1) + ZSTD_ldm_gearTab[data[n] & 0xff]; \
+        n += 1; \
+        if (UNLIKELY((hash & mask) == 0)) { \
+            splits[*numSplits] = n; \
+            *numSplits += 1; \
+            if (*numSplits == LDM_BATCH_SIZE) \
+                goto done; \
+        } \
+    } while (0)
+
+    while (n + 3 < size) {
+        GEAR_ITER_ONCE();
+        GEAR_ITER_ONCE();
+        GEAR_ITER_ONCE();
+        GEAR_ITER_ONCE();
+    }
+    while (n < size) {
+        GEAR_ITER_ONCE();
+    }
+
+#undef GEAR_ITER_ONCE
+
+done:
+    state->rolling = hash;
+    return n;
+}
+
+void ZSTD_ldm_adjustParameters(ldmParams_t* params,
+                               ZSTD_compressionParameters const* cParams)
+{
+    params->windowLog = cParams->windowLog;
+    ZSTD_STATIC_ASSERT(LDM_BUCKET_SIZE_LOG <= ZSTD_LDM_BUCKETSIZELOG_MAX);
+    DEBUGLOG(4, "ZSTD_ldm_adjustParameters");
+    if (!params->bucketSizeLog) params->bucketSizeLog = LDM_BUCKET_SIZE_LOG;
+    if (!params->minMatchLength) params->minMatchLength = LDM_MIN_MATCH_LENGTH;
+    if (params->hashLog == 0) {
+        params->hashLog = MAX(ZSTD_HASHLOG_MIN, params->windowLog - LDM_HASH_RLOG);
+        assert(params->hashLog <= ZSTD_HASHLOG_MAX);
+    }
+    if (params->hashRateLog == 0) {
+        params->hashRateLog = params->windowLog < params->hashLog
+                                   ? 0
+                                   : params->windowLog - params->hashLog;
+    }
+    params->bucketSizeLog = MIN(params->bucketSizeLog, params->hashLog);
+}
+
+size_t ZSTD_ldm_getTableSize(ldmParams_t params)
+{
+    size_t const ldmHSize = ((size_t)1) << params.hashLog;
+    size_t const ldmBucketSizeLog = MIN(params.bucketSizeLog, params.hashLog);
+    size_t const ldmBucketSize = ((size_t)1) << (params.hashLog - ldmBucketSizeLog);
+    size_t const totalSize = ZSTD_cwksp_alloc_size(ldmBucketSize)
+                           + ZSTD_cwksp_alloc_size(ldmHSize * sizeof(ldmEntry_t));
+    return params.enableLdm ? totalSize : 0;
+}
+
+size_t ZSTD_ldm_getMaxNbSeq(ldmParams_t params, size_t maxChunkSize)
+{
+    return params.enableLdm ? (maxChunkSize / params.minMatchLength) : 0;
+}
+
+/* ZSTD_ldm_getBucket() :
+ *  Returns a pointer to the start of the bucket associated with hash. */
+static ldmEntry_t* ZSTD_ldm_getBucket(
+        ldmState_t* ldmState, size_t hash, ldmParams_t const ldmParams)
+{
+    return ldmState->hashTable + (hash << ldmParams.bucketSizeLog);
+}
+
+/* ZSTD_ldm_insertEntry() :
+ *  Insert the entry with corresponding hash into the hash table */
+static void ZSTD_ldm_insertEntry(ldmState_t* ldmState,
+                                 size_t const hash, const ldmEntry_t entry,
+                                 ldmParams_t const ldmParams)
+{
+    BYTE* const pOffset = ldmState->bucketOffsets + hash;
+    unsigned const offset = *pOffset;
+
+    *(ZSTD_ldm_getBucket(ldmState, hash, ldmParams) + offset) = entry;
+    *pOffset = (BYTE)((offset + 1) & ((1u << ldmParams.bucketSizeLog) - 1));
+
+}
+
+/* ZSTD_ldm_countBackwardsMatch() :
+ *  Returns the number of bytes that match backwards before pIn and pMatch.
+ *
+ *  We count only bytes where pMatch >= pBase and pIn >= pAnchor. */
+static size_t ZSTD_ldm_countBackwardsMatch(
+            const BYTE* pIn, const BYTE* pAnchor,
+            const BYTE* pMatch, const BYTE* pMatchBase)
+{
+    size_t matchLength = 0;
+    while (pIn > pAnchor && pMatch > pMatchBase && pIn[-1] == pMatch[-1]) {
+        pIn--;
+        pMatch--;
+        matchLength++;
+    }
+    return matchLength;
+}
+
+/* ZSTD_ldm_countBackwardsMatch_2segments() :
+ *  Returns the number of bytes that match backwards from pMatch,
+ *  even with the backwards match spanning 2 different segments.
+ *
+ *  On reaching `pMatchBase`, start counting from mEnd */
+static size_t ZSTD_ldm_countBackwardsMatch_2segments(
+                    const BYTE* pIn, const BYTE* pAnchor,
+                    const BYTE* pMatch, const BYTE* pMatchBase,
+                    const BYTE* pExtDictStart, const BYTE* pExtDictEnd)
+{
+    size_t matchLength = ZSTD_ldm_countBackwardsMatch(pIn, pAnchor, pMatch, pMatchBase);
+    if (pMatch - matchLength != pMatchBase || pMatchBase == pExtDictStart) {
+        /* If backwards match is entirely in the extDict or prefix, immediately return */
+        return matchLength;
+    }
+    DEBUGLOG(7, "ZSTD_ldm_countBackwardsMatch_2segments: found 2-parts backwards match (length in prefix==%zu)", matchLength);
+    matchLength += ZSTD_ldm_countBackwardsMatch(pIn - matchLength, pAnchor, pExtDictEnd, pExtDictStart);
+    DEBUGLOG(7, "final backwards match length = %zu", matchLength);
+    return matchLength;
+}
+
+/* ZSTD_ldm_fillFastTables() :
+ *
+ *  Fills the relevant tables for the ZSTD_fast and ZSTD_dfast strategies.
+ *  This is similar to ZSTD_loadDictionaryContent.
+ *
+ *  The tables for the other strategies are filled within their
+ *  block compressors. */
+static size_t ZSTD_ldm_fillFastTables(ZSTD_matchState_t* ms,
+                                      void const* end)
+{
+    const BYTE* const iend = (const BYTE*)end;
+
+    switch(ms->cParams.strategy)
+    {
+    case ZSTD_fast:
+        ZSTD_fillHashTable(ms, iend, ZSTD_dtlm_fast);
+        break;
+
+    case ZSTD_dfast:
+        ZSTD_fillDoubleHashTable(ms, iend, ZSTD_dtlm_fast);
+        break;
+
+    case ZSTD_greedy:
+    case ZSTD_lazy:
+    case ZSTD_lazy2:
+    case ZSTD_btlazy2:
+    case ZSTD_btopt:
+    case ZSTD_btultra:
+    case ZSTD_btultra2:
+        break;
+    default:
+        assert(0);  /* not possible : not a valid strategy id */
+    }
+
+    return 0;
+}
+
+void ZSTD_ldm_fillHashTable(
+            ldmState_t* ldmState, const BYTE* ip,
+            const BYTE* iend, ldmParams_t const* params)
+{
+    U32 const minMatchLength = params->minMatchLength;
+    U32 const hBits = params->hashLog - params->bucketSizeLog;
+    BYTE const* const base = ldmState->window.base;
+    BYTE const* const istart = ip;
+    ldmRollingHashState_t hashState;
+    size_t* const splits = ldmState->splitIndices;
+    unsigned numSplits;
+
+    DEBUGLOG(5, "ZSTD_ldm_fillHashTable");
+
+    ZSTD_ldm_gear_init(&hashState, params);
+    while (ip < iend) {
+        size_t hashed;
+        unsigned n;
+        
+        numSplits = 0;
+        hashed = ZSTD_ldm_gear_feed(&hashState, ip, iend - ip, splits, &numSplits);
+
+        for (n = 0; n < numSplits; n++) {
+            if (ip + splits[n] >= istart + minMatchLength) {
+                BYTE const* const split = ip + splits[n] - minMatchLength;
+                U64 const xxhash = xxh64(split, minMatchLength, 0);
+                U32 const hash = (U32)(xxhash & (((U32)1 << hBits) - 1));
+                ldmEntry_t entry;
+
+                entry.offset = (U32)(split - base);
+                entry.checksum = (U32)(xxhash >> 32);
+                ZSTD_ldm_insertEntry(ldmState, hash, entry, *params);
+            }
+        }
+
+        ip += hashed;
+    }
+}
+
+
+/* ZSTD_ldm_limitTableUpdate() :
+ *
+ *  Sets cctx->nextToUpdate to a position corresponding closer to anchor
+ *  if it is far way
+ *  (after a long match, only update tables a limited amount). */
+static void ZSTD_ldm_limitTableUpdate(ZSTD_matchState_t* ms, const BYTE* anchor)
+{
+    U32 const curr = (U32)(anchor - ms->window.base);
+    if (curr > ms->nextToUpdate + 1024) {
+        ms->nextToUpdate =
+            curr - MIN(512, curr - ms->nextToUpdate - 1024);
+    }
+}
+
+static size_t ZSTD_ldm_generateSequences_internal(
+        ldmState_t* ldmState, rawSeqStore_t* rawSeqStore,
+        ldmParams_t const* params, void const* src, size_t srcSize)
+{
+    /* LDM parameters */
+    int const extDict = ZSTD_window_hasExtDict(ldmState->window);
+    U32 const minMatchLength = params->minMatchLength;
+    U32 const entsPerBucket = 1U << params->bucketSizeLog;
+    U32 const hBits = params->hashLog - params->bucketSizeLog;
+    /* Prefix and extDict parameters */
+    U32 const dictLimit = ldmState->window.dictLimit;
+    U32 const lowestIndex = extDict ? ldmState->window.lowLimit : dictLimit;
+    BYTE const* const base = ldmState->window.base;
+    BYTE const* const dictBase = extDict ? ldmState->window.dictBase : NULL;
+    BYTE const* const dictStart = extDict ? dictBase + lowestIndex : NULL;
+    BYTE const* const dictEnd = extDict ? dictBase + dictLimit : NULL;
+    BYTE const* const lowPrefixPtr = base + dictLimit;
+    /* Input bounds */
+    BYTE const* const istart = (BYTE const*)src;
+    BYTE const* const iend = istart + srcSize;
+    BYTE const* const ilimit = iend - HASH_READ_SIZE;
+    /* Input positions */
+    BYTE const* anchor = istart;
+    BYTE const* ip = istart;
+    /* Rolling hash state */
+    ldmRollingHashState_t hashState;
+    /* Arrays for staged-processing */
+    size_t* const splits = ldmState->splitIndices;
+    ldmMatchCandidate_t* const candidates = ldmState->matchCandidates;
+    unsigned numSplits;
+
+    if (srcSize < minMatchLength)
+        return iend - anchor;
+
+    /* Initialize the rolling hash state with the first minMatchLength bytes */
+    ZSTD_ldm_gear_init(&hashState, params);
+    {
+        size_t n = 0;
+
+        while (n < minMatchLength) {
+            numSplits = 0;
+            n += ZSTD_ldm_gear_feed(&hashState, ip + n, minMatchLength - n,
+                                    splits, &numSplits);
+        }
+        ip += minMatchLength;
+    }
+
+    while (ip < ilimit) {
+        size_t hashed;
+        unsigned n;
+
+        numSplits = 0;
+        hashed = ZSTD_ldm_gear_feed(&hashState, ip, ilimit - ip,
+                                    splits, &numSplits);
+
+        for (n = 0; n < numSplits; n++) {
+            BYTE const* const split = ip + splits[n] - minMatchLength;
+            U64 const xxhash = xxh64(split, minMatchLength, 0);
+            U32 const hash = (U32)(xxhash & (((U32)1 << hBits) - 1));
+
+            candidates[n].split = split;
+            candidates[n].hash = hash;
+            candidates[n].checksum = (U32)(xxhash >> 32);
+            candidates[n].bucket = ZSTD_ldm_getBucket(ldmState, hash, *params);
+            PREFETCH_L1(candidates[n].bucket);
+        }
+
+        for (n = 0; n < numSplits; n++) {
+            size_t forwardMatchLength = 0, backwardMatchLength = 0,
+                   bestMatchLength = 0, mLength;
+            BYTE const* const split = candidates[n].split;
+            U32 const checksum = candidates[n].checksum;
+            U32 const hash = candidates[n].hash;
+            ldmEntry_t* const bucket = candidates[n].bucket;
+            ldmEntry_t const* cur;
+            ldmEntry_t const* bestEntry = NULL;
+            ldmEntry_t newEntry;
+
+            newEntry.offset = (U32)(split - base);
+            newEntry.checksum = checksum;
+
+            /* If a split point would generate a sequence overlapping with
+             * the previous one, we merely register it in the hash table and
+             * move on */
+            if (split < anchor) {
+                ZSTD_ldm_insertEntry(ldmState, hash, newEntry, *params);
+                continue;
+            }
+
+            for (cur = bucket; cur < bucket + entsPerBucket; cur++) {
+                size_t curForwardMatchLength, curBackwardMatchLength,
+                       curTotalMatchLength;
+                if (cur->checksum != checksum || cur->offset <= lowestIndex) {
+                    continue;
+                }
+                if (extDict) {
+                    BYTE const* const curMatchBase =
+                        cur->offset < dictLimit ? dictBase : base;
+                    BYTE const* const pMatch = curMatchBase + cur->offset;
+                    BYTE const* const matchEnd =
+                        cur->offset < dictLimit ? dictEnd : iend;
+                    BYTE const* const lowMatchPtr =
+                        cur->offset < dictLimit ? dictStart : lowPrefixPtr;
+                    curForwardMatchLength =
+                        ZSTD_count_2segments(split, pMatch, iend, matchEnd, lowPrefixPtr);
+                    if (curForwardMatchLength < minMatchLength) {
+                        continue;
+                    }
+                    curBackwardMatchLength = ZSTD_ldm_countBackwardsMatch_2segments(
+                            split, anchor, pMatch, lowMatchPtr, dictStart, dictEnd);
+                } else { /* !extDict */
+                    BYTE const* const pMatch = base + cur->offset;
+                    curForwardMatchLength = ZSTD_count(split, pMatch, iend);
+                    if (curForwardMatchLength < minMatchLength) {
+                        continue;
+                    }
+                    curBackwardMatchLength =
+                        ZSTD_ldm_countBackwardsMatch(split, anchor, pMatch, lowPrefixPtr);
+                }
+                curTotalMatchLength = curForwardMatchLength + curBackwardMatchLength;
+
+                if (curTotalMatchLength > bestMatchLength) {
+                    bestMatchLength = curTotalMatchLength;
+                    forwardMatchLength = curForwardMatchLength;
+                    backwardMatchLength = curBackwardMatchLength;
+                    bestEntry = cur;
+                }
+            }
+
+            /* No match found -- insert an entry into the hash table
+             * and process the next candidate match */
+            if (bestEntry == NULL) {
+                ZSTD_ldm_insertEntry(ldmState, hash, newEntry, *params);
+                continue;
+            }
+
+            /* Match found */
+            mLength = forwardMatchLength + backwardMatchLength;
+            {
+                U32 const offset = (U32)(split - base) - bestEntry->offset;
+                rawSeq* const seq = rawSeqStore->seq + rawSeqStore->size;
+
+                /* Out of sequence storage */
+                if (rawSeqStore->size == rawSeqStore->capacity)
+                    return ERROR(dstSize_tooSmall);
+                seq->litLength = (U32)(split - backwardMatchLength - anchor);
+                seq->matchLength = (U32)mLength;
+                seq->offset = offset;
+                rawSeqStore->size++;
+            }
+
+            /* Insert the current entry into the hash table --- it must be
+             * done after the previous block to avoid clobbering bestEntry */
+            ZSTD_ldm_insertEntry(ldmState, hash, newEntry, *params);
+
+            anchor = split + forwardMatchLength;
+        }
+
+        ip += hashed;
+    }
+
+    return iend - anchor;
+}
+
+/*! ZSTD_ldm_reduceTable() :
+ *  reduce table indexes by `reducerValue` */
+static void ZSTD_ldm_reduceTable(ldmEntry_t* const table, U32 const size,
+                                 U32 const reducerValue)
+{
+    U32 u;
+    for (u = 0; u < size; u++) {
+        if (table[u].offset < reducerValue) table[u].offset = 0;
+        else table[u].offset -= reducerValue;
+    }
+}
+
+size_t ZSTD_ldm_generateSequences(
+        ldmState_t* ldmState, rawSeqStore_t* sequences,
+        ldmParams_t const* params, void const* src, size_t srcSize)
+{
+    U32 const maxDist = 1U << params->windowLog;
+    BYTE const* const istart = (BYTE const*)src;
+    BYTE const* const iend = istart + srcSize;
+    size_t const kMaxChunkSize = 1 << 20;
+    size_t const nbChunks = (srcSize / kMaxChunkSize) + ((srcSize % kMaxChunkSize) != 0);
+    size_t chunk;
+    size_t leftoverSize = 0;
+
+    assert(ZSTD_CHUNKSIZE_MAX >= kMaxChunkSize);
+    /* Check that ZSTD_window_update() has been called for this chunk prior
+     * to passing it to this function.
+     */
+    assert(ldmState->window.nextSrc >= (BYTE const*)src + srcSize);
+    /* The input could be very large (in zstdmt), so it must be broken up into
+     * chunks to enforce the maximum distance and handle overflow correction.
+     */
+    assert(sequences->pos <= sequences->size);
+    assert(sequences->size <= sequences->capacity);
+    for (chunk = 0; chunk < nbChunks && sequences->size < sequences->capacity; ++chunk) {
+        BYTE const* const chunkStart = istart + chunk * kMaxChunkSize;
+        size_t const remaining = (size_t)(iend - chunkStart);
+        BYTE const *const chunkEnd =
+            (remaining < kMaxChunkSize) ? iend : chunkStart + kMaxChunkSize;
+        size_t const chunkSize = chunkEnd - chunkStart;
+        size_t newLeftoverSize;
+        size_t const prevSize = sequences->size;
+
+        assert(chunkStart < iend);
+        /* 1. Perform overflow correction if necessary. */
+        if (ZSTD_window_needOverflowCorrection(ldmState->window, chunkEnd)) {
+            U32 const ldmHSize = 1U << params->hashLog;
+            U32 const correction = ZSTD_window_correctOverflow(
+                &ldmState->window, /* cycleLog */ 0, maxDist, chunkStart);
+            ZSTD_ldm_reduceTable(ldmState->hashTable, ldmHSize, correction);
+            /* invalidate dictionaries on overflow correction */
+            ldmState->loadedDictEnd = 0;
+        }
+        /* 2. We enforce the maximum offset allowed.
+         *
+         * kMaxChunkSize should be small enough that we don't lose too much of
+         * the window through early invalidation.
+         * TODO: * Test the chunk size.
+         *       * Try invalidation after the sequence generation and test the
+         *         the offset against maxDist directly.
+         *
+         * NOTE: Because of dictionaries + sequence splitting we MUST make sure
+         * that any offset used is valid at the END of the sequence, since it may
+         * be split into two sequences. This condition holds when using
+         * ZSTD_window_enforceMaxDist(), but if we move to checking offsets
+         * against maxDist directly, we'll have to carefully handle that case.
+         */
+        ZSTD_window_enforceMaxDist(&ldmState->window, chunkEnd, maxDist, &ldmState->loadedDictEnd, NULL);
+        /* 3. Generate the sequences for the chunk, and get newLeftoverSize. */
+        newLeftoverSize = ZSTD_ldm_generateSequences_internal(
+            ldmState, sequences, params, chunkStart, chunkSize);
+        if (ZSTD_isError(newLeftoverSize))
+            return newLeftoverSize;
+        /* 4. We add the leftover literals from previous iterations to the first
+         *    newly generated sequence, or add the `newLeftoverSize` if none are
+         *    generated.
+         */
+        /* Prepend the leftover literals from the last call */
+        if (prevSize < sequences->size) {
+            sequences->seq[prevSize].litLength += (U32)leftoverSize;
+            leftoverSize = newLeftoverSize;
+        } else {
+            assert(newLeftoverSize == chunkSize);
+            leftoverSize += chunkSize;
+        }
+    }
+    return 0;
+}
+
+void ZSTD_ldm_skipSequences(rawSeqStore_t* rawSeqStore, size_t srcSize, U32 const minMatch) {
+    while (srcSize > 0 && rawSeqStore->pos < rawSeqStore->size) {
+        rawSeq* seq = rawSeqStore->seq + rawSeqStore->pos;
+        if (srcSize <= seq->litLength) {
+            /* Skip past srcSize literals */
+            seq->litLength -= (U32)srcSize;
+            return;
+        }
+        srcSize -= seq->litLength;
+        seq->litLength = 0;
+        if (srcSize < seq->matchLength) {
+            /* Skip past the first srcSize of the match */
+            seq->matchLength -= (U32)srcSize;
+            if (seq->matchLength < minMatch) {
+                /* The match is too short, omit it */
+                if (rawSeqStore->pos + 1 < rawSeqStore->size) {
+                    seq[1].litLength += seq[0].matchLength;
+                }
+                rawSeqStore->pos++;
+            }
+            return;
+        }
+        srcSize -= seq->matchLength;
+        seq->matchLength = 0;
+        rawSeqStore->pos++;
+    }
+}
+
+/*
+ * If the sequence length is longer than remaining then the sequence is split
+ * between this block and the next.
+ *
+ * Returns the current sequence to handle, or if the rest of the block should
+ * be literals, it returns a sequence with offset == 0.
+ */
+static rawSeq maybeSplitSequence(rawSeqStore_t* rawSeqStore,
+                                 U32 const remaining, U32 const minMatch)
+{
+    rawSeq sequence = rawSeqStore->seq[rawSeqStore->pos];
+    assert(sequence.offset > 0);
+    /* Likely: No partial sequence */
+    if (remaining >= sequence.litLength + sequence.matchLength) {
+        rawSeqStore->pos++;
+        return sequence;
+    }
+    /* Cut the sequence short (offset == 0 ==> rest is literals). */
+    if (remaining <= sequence.litLength) {
+        sequence.offset = 0;
+    } else if (remaining < sequence.litLength + sequence.matchLength) {
+        sequence.matchLength = remaining - sequence.litLength;
+        if (sequence.matchLength < minMatch) {
+            sequence.offset = 0;
+        }
+    }
+    /* Skip past `remaining` bytes for the future sequences. */
+    ZSTD_ldm_skipSequences(rawSeqStore, remaining, minMatch);
+    return sequence;
+}
+
+void ZSTD_ldm_skipRawSeqStoreBytes(rawSeqStore_t* rawSeqStore, size_t nbBytes) {
+    U32 currPos = (U32)(rawSeqStore->posInSequence + nbBytes);
+    while (currPos && rawSeqStore->pos < rawSeqStore->size) {
+        rawSeq currSeq = rawSeqStore->seq[rawSeqStore->pos];
+        if (currPos >= currSeq.litLength + currSeq.matchLength) {
+            currPos -= currSeq.litLength + currSeq.matchLength;
+            rawSeqStore->pos++;
+        } else {
+            rawSeqStore->posInSequence = currPos;
+            break;
+        }
+    }
+    if (currPos == 0 || rawSeqStore->pos == rawSeqStore->size) {
+        rawSeqStore->posInSequence = 0;
+    }
+}
+
+size_t ZSTD_ldm_blockCompress(rawSeqStore_t* rawSeqStore,
+    ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+    void const* src, size_t srcSize)
+{
+    const ZSTD_compressionParameters* const cParams = &ms->cParams;
+    unsigned const minMatch = cParams->minMatch;
+    ZSTD_blockCompressor const blockCompressor =
+        ZSTD_selectBlockCompressor(cParams->strategy, ZSTD_matchState_dictMode(ms));
+    /* Input bounds */
+    BYTE const* const istart = (BYTE const*)src;
+    BYTE const* const iend = istart + srcSize;
+    /* Input positions */
+    BYTE const* ip = istart;
+
+    DEBUGLOG(5, "ZSTD_ldm_blockCompress: srcSize=%zu", srcSize);
+    /* If using opt parser, use LDMs only as candidates rather than always accepting them */
+    if (cParams->strategy >= ZSTD_btopt) {
+        size_t lastLLSize;
+        ms->ldmSeqStore = rawSeqStore;
+        lastLLSize = blockCompressor(ms, seqStore, rep, src, srcSize);
+        ZSTD_ldm_skipRawSeqStoreBytes(rawSeqStore, srcSize);
+        return lastLLSize;
+    }
+
+    assert(rawSeqStore->pos <= rawSeqStore->size);
+    assert(rawSeqStore->size <= rawSeqStore->capacity);
+    /* Loop through each sequence and apply the block compressor to the literals */
+    while (rawSeqStore->pos < rawSeqStore->size && ip < iend) {
+        /* maybeSplitSequence updates rawSeqStore->pos */
+        rawSeq const sequence = maybeSplitSequence(rawSeqStore,
+                                                   (U32)(iend - ip), minMatch);
+        int i;
+        /* End signal */
+        if (sequence.offset == 0)
+            break;
+
+        assert(ip + sequence.litLength + sequence.matchLength <= iend);
+
+        /* Fill tables for block compressor */
+        ZSTD_ldm_limitTableUpdate(ms, ip);
+        ZSTD_ldm_fillFastTables(ms, ip);
+        /* Run the block compressor */
+        DEBUGLOG(5, "pos %u : calling block compressor on segment of size %u", (unsigned)(ip-istart), sequence.litLength);
+        {
+            size_t const newLitLength =
+                blockCompressor(ms, seqStore, rep, ip, sequence.litLength);
+            ip += sequence.litLength;
+            /* Update the repcodes */
+            for (i = ZSTD_REP_NUM - 1; i > 0; i--)
+                rep[i] = rep[i-1];
+            rep[0] = sequence.offset;
+            /* Store the sequence */
+            ZSTD_storeSeq(seqStore, newLitLength, ip - newLitLength, iend,
+                          sequence.offset + ZSTD_REP_MOVE,
+                          sequence.matchLength - MINMATCH);
+            ip += sequence.matchLength;
+        }
+    }
+    /* Fill the tables for the block compressor */
+    ZSTD_ldm_limitTableUpdate(ms, ip);
+    ZSTD_ldm_fillFastTables(ms, ip);
+    /* Compress the last literals */
+    return blockCompressor(ms, seqStore, rep, ip, iend - ip);
+}
diff --git a/lib/zstd/compress/zstd_ldm.h b/lib/zstd/compress/zstd_ldm.h
new file mode 100644
index 000000000000..25b25270b72e
--- /dev/null
+++ b/lib/zstd/compress/zstd_ldm.h
@@ -0,0 +1,110 @@
+/*
+ * Copyright (c) Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+#ifndef ZSTD_LDM_H
+#define ZSTD_LDM_H
+
+
+#include "zstd_compress_internal.h"   /* ldmParams_t, U32 */
+#include <linux/zstd.h>   /* ZSTD_CCtx, size_t */
+
+/*-*************************************
+*  Long distance matching
+***************************************/
+
+#define ZSTD_LDM_DEFAULT_WINDOW_LOG ZSTD_WINDOWLOG_LIMIT_DEFAULT
+
+void ZSTD_ldm_fillHashTable(
+            ldmState_t* state, const BYTE* ip,
+            const BYTE* iend, ldmParams_t const* params);
+
+/*
+ * ZSTD_ldm_generateSequences():
+ *
+ * Generates the sequences using the long distance match finder.
+ * Generates long range matching sequences in `sequences`, which parse a prefix
+ * of the source. `sequences` must be large enough to store every sequence,
+ * which can be checked with `ZSTD_ldm_getMaxNbSeq()`.
+ * @returns 0 or an error code.
+ *
+ * NOTE: The user must have called ZSTD_window_update() for all of the input
+ * they have, even if they pass it to ZSTD_ldm_generateSequences() in chunks.
+ * NOTE: This function returns an error if it runs out of space to store
+ *       sequences.
+ */
+size_t ZSTD_ldm_generateSequences(
+            ldmState_t* ldms, rawSeqStore_t* sequences,
+            ldmParams_t const* params, void const* src, size_t srcSize);
+
+/*
+ * ZSTD_ldm_blockCompress():
+ *
+ * Compresses a block using the predefined sequences, along with a secondary
+ * block compressor. The literals section of every sequence is passed to the
+ * secondary block compressor, and those sequences are interspersed with the
+ * predefined sequences. Returns the length of the last literals.
+ * Updates `rawSeqStore.pos` to indicate how many sequences have been consumed.
+ * `rawSeqStore.seq` may also be updated to split the last sequence between two
+ * blocks.
+ * @return The length of the last literals.
+ *
+ * NOTE: The source must be at most the maximum block size, but the predefined
+ * sequences can be any size, and may be longer than the block. In the case that
+ * they are longer than the block, the last sequences may need to be split into
+ * two. We handle that case correctly, and update `rawSeqStore` appropriately.
+ * NOTE: This function does not return any errors.
+ */
+size_t ZSTD_ldm_blockCompress(rawSeqStore_t* rawSeqStore,
+            ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+            void const* src, size_t srcSize);
+
+/*
+ * ZSTD_ldm_skipSequences():
+ *
+ * Skip past `srcSize` bytes worth of sequences in `rawSeqStore`.
+ * Avoids emitting matches less than `minMatch` bytes.
+ * Must be called for data that is not passed to ZSTD_ldm_blockCompress().
+ */
+void ZSTD_ldm_skipSequences(rawSeqStore_t* rawSeqStore, size_t srcSize,
+    U32 const minMatch);
+
+/* ZSTD_ldm_skipRawSeqStoreBytes():
+ * Moves forward in rawSeqStore by nbBytes, updating fields 'pos' and 'posInSequence'.
+ * Not to be used in conjunction with ZSTD_ldm_skipSequences().
+ * Must be called for data with is not passed to ZSTD_ldm_blockCompress().
+ */
+void ZSTD_ldm_skipRawSeqStoreBytes(rawSeqStore_t* rawSeqStore, size_t nbBytes);
+
+/* ZSTD_ldm_getTableSize() :
+ *  Estimate the space needed for long distance matching tables or 0 if LDM is
+ *  disabled.
+ */
+size_t ZSTD_ldm_getTableSize(ldmParams_t params);
+
+/* ZSTD_ldm_getSeqSpace() :
+ *  Return an upper bound on the number of sequences that can be produced by
+ *  the long distance matcher, or 0 if LDM is disabled.
+ */
+size_t ZSTD_ldm_getMaxNbSeq(ldmParams_t params, size_t maxChunkSize);
+
+/* ZSTD_ldm_adjustParameters() :
+ *  If the params->hashRateLog is not set, set it to its default value based on
+ *  windowLog and params->hashLog.
+ *
+ *  Ensures that params->bucketSizeLog is <= params->hashLog (setting it to
+ *  params->hashLog if it is not).
+ *
+ *  Ensures that the minMatchLength >= targetLength during optimal parsing.
+ */
+void ZSTD_ldm_adjustParameters(ldmParams_t* params,
+                               ZSTD_compressionParameters const* cParams);
+
+
+#endif /* ZSTD_FAST_H */
diff --git a/lib/zstd/compress/zstd_ldm_geartab.h b/lib/zstd/compress/zstd_ldm_geartab.h
new file mode 100644
index 000000000000..e5c24d856b0a
--- /dev/null
+++ b/lib/zstd/compress/zstd_ldm_geartab.h
@@ -0,0 +1,103 @@
+/*
+ * Copyright (c) Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+#ifndef ZSTD_LDM_GEARTAB_H
+#define ZSTD_LDM_GEARTAB_H
+
+static U64 ZSTD_ldm_gearTab[256] = {
+    0xf5b8f72c5f77775c, 0x84935f266b7ac412, 0xb647ada9ca730ccc,
+    0xb065bb4b114fb1de, 0x34584e7e8c3a9fd0, 0x4e97e17c6ae26b05,
+    0x3a03d743bc99a604, 0xcecd042422c4044f, 0x76de76c58524259e,
+    0x9c8528f65badeaca, 0x86563706e2097529, 0x2902475fa375d889,
+    0xafb32a9739a5ebe6, 0xce2714da3883e639, 0x21eaf821722e69e,
+    0x37b628620b628,    0x49a8d455d88caf5,  0x8556d711e6958140,
+    0x4f7ae74fc605c1f,  0x829f0c3468bd3a20, 0x4ffdc885c625179e,
+    0x8473de048a3daf1b, 0x51008822b05646b2, 0x69d75d12b2d1cc5f,
+    0x8c9d4a19159154bc, 0xc3cc10f4abbd4003, 0xd06ddc1cecb97391,
+    0xbe48e6e7ed80302e, 0x3481db31cee03547, 0xacc3f67cdaa1d210,
+    0x65cb771d8c7f96cc, 0x8eb27177055723dd, 0xc789950d44cd94be,
+    0x934feadc3700b12b, 0x5e485f11edbdf182, 0x1e2e2a46fd64767a,
+    0x2969ca71d82efa7c, 0x9d46e9935ebbba2e, 0xe056b67e05e6822b,
+    0x94d73f55739d03a0, 0xcd7010bdb69b5a03, 0x455ef9fcd79b82f4,
+    0x869cb54a8749c161, 0x38d1a4fa6185d225, 0xb475166f94bbe9bb,
+    0xa4143548720959f1, 0x7aed4780ba6b26ba, 0xd0ce264439e02312,
+    0x84366d746078d508, 0xa8ce973c72ed17be, 0x21c323a29a430b01,
+    0x9962d617e3af80ee, 0xab0ce91d9c8cf75b, 0x530e8ee6d19a4dbc,
+    0x2ef68c0cf53f5d72, 0xc03a681640a85506, 0x496e4e9f9c310967,
+    0x78580472b59b14a0, 0x273824c23b388577, 0x66bf923ad45cb553,
+    0x47ae1a5a2492ba86, 0x35e304569e229659, 0x4765182a46870b6f,
+    0x6cbab625e9099412, 0xddac9a2e598522c1, 0x7172086e666624f2,
+    0xdf5003ca503b7837, 0x88c0c1db78563d09, 0x58d51865acfc289d,
+    0x177671aec65224f1, 0xfb79d8a241e967d7, 0x2be1e101cad9a49a,
+    0x6625682f6e29186b, 0x399553457ac06e50, 0x35dffb4c23abb74,
+    0x429db2591f54aade, 0xc52802a8037d1009, 0x6acb27381f0b25f3,
+    0xf45e2551ee4f823b, 0x8b0ea2d99580c2f7, 0x3bed519cbcb4e1e1,
+    0xff452823dbb010a,  0x9d42ed614f3dd267, 0x5b9313c06257c57b,
+    0xa114b8008b5e1442, 0xc1fe311c11c13d4b, 0x66e8763ea34c5568,
+    0x8b982af1c262f05d, 0xee8876faaa75fbb7, 0x8a62a4d0d172bb2a,
+    0xc13d94a3b7449a97, 0x6dbbba9dc15d037c, 0xc786101f1d92e0f1,
+    0xd78681a907a0b79b, 0xf61aaf2962c9abb9, 0x2cfd16fcd3cb7ad9,
+    0x868c5b6744624d21, 0x25e650899c74ddd7, 0xba042af4a7c37463,
+    0x4eb1a539465a3eca, 0xbe09dbf03b05d5ca, 0x774e5a362b5472ba,
+    0x47a1221229d183cd, 0x504b0ca18ef5a2df, 0xdffbdfbde2456eb9,
+    0x46cd2b2fbee34634, 0xf2aef8fe819d98c3, 0x357f5276d4599d61,
+    0x24a5483879c453e3, 0x88026889192b4b9,  0x28da96671782dbec,
+    0x4ef37c40588e9aaa, 0x8837b90651bc9fb3, 0xc164f741d3f0e5d6,
+    0xbc135a0a704b70ba, 0x69cd868f7622ada,  0xbc37ba89e0b9c0ab,
+    0x47c14a01323552f6, 0x4f00794bacee98bb, 0x7107de7d637a69d5,
+    0x88af793bb6f2255e, 0xf3c6466b8799b598, 0xc288c616aa7f3b59,
+    0x81ca63cf42fca3fd, 0x88d85ace36a2674b, 0xd056bd3792389e7,
+    0xe55c396c4e9dd32d, 0xbefb504571e6c0a6, 0x96ab32115e91e8cc,
+    0xbf8acb18de8f38d1, 0x66dae58801672606, 0x833b6017872317fb,
+    0xb87c16f2d1c92864, 0xdb766a74e58b669c, 0x89659f85c61417be,
+    0xc8daad856011ea0c, 0x76a4b565b6fe7eae, 0xa469d085f6237312,
+    0xaaf0365683a3e96c, 0x4dbb746f8424f7b8, 0x638755af4e4acc1,
+    0x3d7807f5bde64486, 0x17be6d8f5bbb7639, 0x903f0cd44dc35dc,
+    0x67b672eafdf1196c, 0xa676ff93ed4c82f1, 0x521d1004c5053d9d,
+    0x37ba9ad09ccc9202, 0x84e54d297aacfb51, 0xa0b4b776a143445,
+    0x820d471e20b348e,  0x1874383cb83d46dc, 0x97edeec7a1efe11c,
+    0xb330e50b1bdc42aa, 0x1dd91955ce70e032, 0xa514cdb88f2939d5,
+    0x2791233fd90db9d3, 0x7b670a4cc50f7a9b, 0x77c07d2a05c6dfa5,
+    0xe3778b6646d0a6fa, 0xb39c8eda47b56749, 0x933ed448addbef28,
+    0xaf846af6ab7d0bf4, 0xe5af208eb666e49,  0x5e6622f73534cd6a,
+    0x297daeca42ef5b6e, 0x862daef3d35539a6, 0xe68722498f8e1ea9,
+    0x981c53093dc0d572, 0xfa09b0bfbf86fbf5, 0x30b1e96166219f15,
+    0x70e7d466bdc4fb83, 0x5a66736e35f2a8e9, 0xcddb59d2b7c1baef,
+    0xd6c7d247d26d8996, 0xea4e39eac8de1ba3, 0x539c8bb19fa3aff2,
+    0x9f90e4c5fd508d8,  0xa34e5956fbaf3385, 0x2e2f8e151d3ef375,
+    0x173691e9b83faec1, 0xb85a8d56bf016379, 0x8382381267408ae3,
+    0xb90f901bbdc0096d, 0x7c6ad32933bcec65, 0x76bb5e2f2c8ad595,
+    0x390f851a6cf46d28, 0xc3e6064da1c2da72, 0xc52a0c101cfa5389,
+    0xd78eaf84a3fbc530, 0x3781b9e2288b997e, 0x73c2f6dea83d05c4,
+    0x4228e364c5b5ed7,  0x9d7a3edf0da43911, 0x8edcfeda24686756,
+    0x5e7667a7b7a9b3a1, 0x4c4f389fa143791d, 0xb08bc1023da7cddc,
+    0x7ab4be3ae529b1cc, 0x754e6132dbe74ff9, 0x71635442a839df45,
+    0x2f6fb1643fbe52de, 0x961e0a42cf7a8177, 0xf3b45d83d89ef2ea,
+    0xee3de4cf4a6e3e9b, 0xcd6848542c3295e7, 0xe4cee1664c78662f,
+    0x9947548b474c68c4, 0x25d73777a5ed8b0b, 0xc915b1d636b7fc,
+    0x21c2ba75d9b0d2da, 0x5f6b5dcf608a64a1, 0xdcf333255ff9570c,
+    0x633b922418ced4ee, 0xc136dde0b004b34a, 0x58cc83b05d4b2f5a,
+    0x5eb424dda28e42d2, 0x62df47369739cd98, 0xb4e0b42485e4ce17,
+    0x16e1f0c1f9a8d1e7, 0x8ec3916707560ebf, 0x62ba6e2df2cc9db3,
+    0xcbf9f4ff77d83a16, 0x78d9d7d07d2bbcc4, 0xef554ce1e02c41f4,
+    0x8d7581127eccf94d, 0xa9b53336cb3c8a05, 0x38c42c0bf45c4f91,
+    0x640893cdf4488863, 0x80ec34bc575ea568, 0x39f324f5b48eaa40,
+    0xe9d9ed1f8eff527f, 0x9224fc058cc5a214, 0xbaba00b04cfe7741,
+    0x309a9f120fcf52af, 0xa558f3ec65626212, 0x424bec8b7adabe2f,
+    0x41622513a6aea433, 0xb88da2d5324ca798, 0xd287733b245528a4,
+    0x9a44697e6d68aec3, 0x7b1093be2f49bb28, 0x50bbec632e3d8aad,
+    0x6cd90723e1ea8283, 0x897b9e7431b02bf3, 0x219efdcb338a7047,
+    0x3b0311f0a27c0656, 0xdb17bf91c0db96e7, 0x8cd4fd6b4e85a5b2,
+    0xfab071054ba6409d, 0x40d6fe831fa9dfd9, 0xaf358debad7d791e,
+    0xeb8d0e25a65e3e58, 0xbbcbd3df14e08580, 0xcf751f27ecdab2b,
+    0x2b4da14f2613d8f4
+};
+
+#endif /* ZSTD_LDM_GEARTAB_H */
diff --git a/lib/zstd/compress/zstd_opt.c b/lib/zstd/compress/zstd_opt.c
new file mode 100644
index 000000000000..dfc55e3e8119
--- /dev/null
+++ b/lib/zstd/compress/zstd_opt.c
@@ -0,0 +1,1358 @@
+/*
+ * Copyright (c) Przemyslaw Skibinski, Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+/*
+ * Disable inlining for the optimal parser for the kernel build.
+ * It is unlikely to be used in the kernel, and where it is used
+ * latency shouldn't matter because it is very slow to begin with.
+ * We prefer a ~180KB binary size win over faster optimal parsing.
+ *
+ * TODO(https://github.com/facebook/zstd/issues/2862):
+ * Improve the code size of the optimal parser in general, so we
+ * don't need this hack for the kernel build.
+ */
+#define ZSTD_NO_INLINE 1
+
+#include "zstd_compress_internal.h"
+#include "hist.h"
+#include "zstd_opt.h"
+
+
+#define ZSTD_LITFREQ_ADD    2   /* scaling factor for litFreq, so that frequencies adapt faster to new stats */
+#define ZSTD_FREQ_DIV       4   /* log factor when using previous stats to init next stats */
+#define ZSTD_MAX_PRICE     (1<<30)
+
+#define ZSTD_PREDEF_THRESHOLD 1024   /* if srcSize < ZSTD_PREDEF_THRESHOLD, symbols' cost is assumed static, directly determined by pre-defined distributions */
+
+
+/*-*************************************
+*  Price functions for optimal parser
+***************************************/
+
+#if 0    /* approximation at bit level */
+#  define BITCOST_ACCURACY 0
+#  define BITCOST_MULTIPLIER (1 << BITCOST_ACCURACY)
+#  define WEIGHT(stat)  ((void)opt, ZSTD_bitWeight(stat))
+#elif 0  /* fractional bit accuracy */
+#  define BITCOST_ACCURACY 8
+#  define BITCOST_MULTIPLIER (1 << BITCOST_ACCURACY)
+#  define WEIGHT(stat,opt) ((void)opt, ZSTD_fracWeight(stat))
+#else    /* opt==approx, ultra==accurate */
+#  define BITCOST_ACCURACY 8
+#  define BITCOST_MULTIPLIER (1 << BITCOST_ACCURACY)
+#  define WEIGHT(stat,opt) (opt ? ZSTD_fracWeight(stat) : ZSTD_bitWeight(stat))
+#endif
+
+MEM_STATIC U32 ZSTD_bitWeight(U32 stat)
+{
+    return (ZSTD_highbit32(stat+1) * BITCOST_MULTIPLIER);
+}
+
+MEM_STATIC U32 ZSTD_fracWeight(U32 rawStat)
+{
+    U32 const stat = rawStat + 1;
+    U32 const hb = ZSTD_highbit32(stat);
+    U32 const BWeight = hb * BITCOST_MULTIPLIER;
+    U32 const FWeight = (stat << BITCOST_ACCURACY) >> hb;
+    U32 const weight = BWeight + FWeight;
+    assert(hb + BITCOST_ACCURACY < 31);
+    return weight;
+}
+
+#if (DEBUGLEVEL>=2)
+/* debugging function,
+ * @return price in bytes as fractional value
+ * for debug messages only */
+MEM_STATIC double ZSTD_fCost(U32 price)
+{
+    return (double)price / (BITCOST_MULTIPLIER*8);
+}
+#endif
+
+static int ZSTD_compressedLiterals(optState_t const* const optPtr)
+{
+    return optPtr->literalCompressionMode != ZSTD_lcm_uncompressed;
+}
+
+static void ZSTD_setBasePrices(optState_t* optPtr, int optLevel)
+{
+    if (ZSTD_compressedLiterals(optPtr))
+        optPtr->litSumBasePrice = WEIGHT(optPtr->litSum, optLevel);
+    optPtr->litLengthSumBasePrice = WEIGHT(optPtr->litLengthSum, optLevel);
+    optPtr->matchLengthSumBasePrice = WEIGHT(optPtr->matchLengthSum, optLevel);
+    optPtr->offCodeSumBasePrice = WEIGHT(optPtr->offCodeSum, optLevel);
+}
+
+
+/* ZSTD_downscaleStat() :
+ * reduce all elements in table by a factor 2^(ZSTD_FREQ_DIV+malus)
+ * return the resulting sum of elements */
+static U32 ZSTD_downscaleStat(unsigned* table, U32 lastEltIndex, int malus)
+{
+    U32 s, sum=0;
+    DEBUGLOG(5, "ZSTD_downscaleStat (nbElts=%u)", (unsigned)lastEltIndex+1);
+    assert(ZSTD_FREQ_DIV+malus > 0 && ZSTD_FREQ_DIV+malus < 31);
+    for (s=0; s<lastEltIndex+1; s++) {
+        table[s] = 1 + (table[s] >> (ZSTD_FREQ_DIV+malus));
+        sum += table[s];
+    }
+    return sum;
+}
+
+/* ZSTD_rescaleFreqs() :
+ * if first block (detected by optPtr->litLengthSum == 0) : init statistics
+ *    take hints from dictionary if there is one
+ *    or init from zero, using src for literals stats, or flat 1 for match symbols
+ * otherwise downscale existing stats, to be used as seed for next block.
+ */
+static void
+ZSTD_rescaleFreqs(optState_t* const optPtr,
+            const BYTE* const src, size_t const srcSize,
+                  int const optLevel)
+{
+    int const compressedLiterals = ZSTD_compressedLiterals(optPtr);
+    DEBUGLOG(5, "ZSTD_rescaleFreqs (srcSize=%u)", (unsigned)srcSize);
+    optPtr->priceType = zop_dynamic;
+
+    if (optPtr->litLengthSum == 0) {  /* first block : init */
+        if (srcSize <= ZSTD_PREDEF_THRESHOLD) {  /* heuristic */
+            DEBUGLOG(5, "(srcSize <= ZSTD_PREDEF_THRESHOLD) => zop_predef");
+            optPtr->priceType = zop_predef;
+        }
+
+        assert(optPtr->symbolCosts != NULL);
+        if (optPtr->symbolCosts->huf.repeatMode == HUF_repeat_valid) {
+            /* huffman table presumed generated by dictionary */
+            optPtr->priceType = zop_dynamic;
+
+            if (compressedLiterals) {
+                unsigned lit;
+                assert(optPtr->litFreq != NULL);
+                optPtr->litSum = 0;
+                for (lit=0; lit<=MaxLit; lit++) {
+                    U32 const scaleLog = 11;   /* scale to 2K */
+                    U32 const bitCost = HUF_getNbBits(optPtr->symbolCosts->huf.CTable, lit);
+                    assert(bitCost <= scaleLog);
+                    optPtr->litFreq[lit] = bitCost ? 1 << (scaleLog-bitCost) : 1 /*minimum to calculate cost*/;
+                    optPtr->litSum += optPtr->litFreq[lit];
+            }   }
+
+            {   unsigned ll;
+                FSE_CState_t llstate;
+                FSE_initCState(&llstate, optPtr->symbolCosts->fse.litlengthCTable);
+                optPtr->litLengthSum = 0;
+                for (ll=0; ll<=MaxLL; ll++) {
+                    U32 const scaleLog = 10;   /* scale to 1K */
+                    U32 const bitCost = FSE_getMaxNbBits(llstate.symbolTT, ll);
+                    assert(bitCost < scaleLog);
+                    optPtr->litLengthFreq[ll] = bitCost ? 1 << (scaleLog-bitCost) : 1 /*minimum to calculate cost*/;
+                    optPtr->litLengthSum += optPtr->litLengthFreq[ll];
+            }   }
+
+            {   unsigned ml;
+                FSE_CState_t mlstate;
+                FSE_initCState(&mlstate, optPtr->symbolCosts->fse.matchlengthCTable);
+                optPtr->matchLengthSum = 0;
+                for (ml=0; ml<=MaxML; ml++) {
+                    U32 const scaleLog = 10;
+                    U32 const bitCost = FSE_getMaxNbBits(mlstate.symbolTT, ml);
+                    assert(bitCost < scaleLog);
+                    optPtr->matchLengthFreq[ml] = bitCost ? 1 << (scaleLog-bitCost) : 1 /*minimum to calculate cost*/;
+                    optPtr->matchLengthSum += optPtr->matchLengthFreq[ml];
+            }   }
+
+            {   unsigned of;
+                FSE_CState_t ofstate;
+                FSE_initCState(&ofstate, optPtr->symbolCosts->fse.offcodeCTable);
+                optPtr->offCodeSum = 0;
+                for (of=0; of<=MaxOff; of++) {
+                    U32 const scaleLog = 10;
+                    U32 const bitCost = FSE_getMaxNbBits(ofstate.symbolTT, of);
+                    assert(bitCost < scaleLog);
+                    optPtr->offCodeFreq[of] = bitCost ? 1 << (scaleLog-bitCost) : 1 /*minimum to calculate cost*/;
+                    optPtr->offCodeSum += optPtr->offCodeFreq[of];
+            }   }
+
+        } else {  /* not a dictionary */
+
+            assert(optPtr->litFreq != NULL);
+            if (compressedLiterals) {
+                unsigned lit = MaxLit;
+                HIST_count_simple(optPtr->litFreq, &lit, src, srcSize);   /* use raw first block to init statistics */
+                optPtr->litSum = ZSTD_downscaleStat(optPtr->litFreq, MaxLit, 1);
+            }
+
+            {   unsigned ll;
+                for (ll=0; ll<=MaxLL; ll++)
+                    optPtr->litLengthFreq[ll] = 1;
+            }
+            optPtr->litLengthSum = MaxLL+1;
+
+            {   unsigned ml;
+                for (ml=0; ml<=MaxML; ml++)
+                    optPtr->matchLengthFreq[ml] = 1;
+            }
+            optPtr->matchLengthSum = MaxML+1;
+
+            {   unsigned of;
+                for (of=0; of<=MaxOff; of++)
+                    optPtr->offCodeFreq[of] = 1;
+            }
+            optPtr->offCodeSum = MaxOff+1;
+
+        }
+
+    } else {   /* new block : re-use previous statistics, scaled down */
+
+        if (compressedLiterals)
+            optPtr->litSum = ZSTD_downscaleStat(optPtr->litFreq, MaxLit, 1);
+        optPtr->litLengthSum = ZSTD_downscaleStat(optPtr->litLengthFreq, MaxLL, 0);
+        optPtr->matchLengthSum = ZSTD_downscaleStat(optPtr->matchLengthFreq, MaxML, 0);
+        optPtr->offCodeSum = ZSTD_downscaleStat(optPtr->offCodeFreq, MaxOff, 0);
+    }
+
+    ZSTD_setBasePrices(optPtr, optLevel);
+}
+
+/* ZSTD_rawLiteralsCost() :
+ * price of literals (only) in specified segment (which length can be 0).
+ * does not include price of literalLength symbol */
+static U32 ZSTD_rawLiteralsCost(const BYTE* const literals, U32 const litLength,
+                                const optState_t* const optPtr,
+                                int optLevel)
+{
+    if (litLength == 0) return 0;
+
+    if (!ZSTD_compressedLiterals(optPtr))
+        return (litLength << 3) * BITCOST_MULTIPLIER;  /* Uncompressed - 8 bytes per literal. */
+
+    if (optPtr->priceType == zop_predef)
+        return (litLength*6) * BITCOST_MULTIPLIER;  /* 6 bit per literal - no statistic used */
+
+    /* dynamic statistics */
+    {   U32 price = litLength * optPtr->litSumBasePrice;
+        U32 u;
+        for (u=0; u < litLength; u++) {
+            assert(WEIGHT(optPtr->litFreq[literals[u]], optLevel) <= optPtr->litSumBasePrice);   /* literal cost should never be negative */
+            price -= WEIGHT(optPtr->litFreq[literals[u]], optLevel);
+        }
+        return price;
+    }
+}
+
+/* ZSTD_litLengthPrice() :
+ * cost of literalLength symbol */
+static U32 ZSTD_litLengthPrice(U32 const litLength, const optState_t* const optPtr, int optLevel)
+{
+    if (optPtr->priceType == zop_predef) return WEIGHT(litLength, optLevel);
+
+    /* dynamic statistics */
+    {   U32 const llCode = ZSTD_LLcode(litLength);
+        return (LL_bits[llCode] * BITCOST_MULTIPLIER)
+             + optPtr->litLengthSumBasePrice
+             - WEIGHT(optPtr->litLengthFreq[llCode], optLevel);
+    }
+}
+
+/* ZSTD_getMatchPrice() :
+ * Provides the cost of the match part (offset + matchLength) of a sequence
+ * Must be combined with ZSTD_fullLiteralsCost() to get the full cost of a sequence.
+ * optLevel: when <2, favors small offset for decompression speed (improved cache efficiency) */
+FORCE_INLINE_TEMPLATE U32
+ZSTD_getMatchPrice(U32 const offset,
+                   U32 const matchLength,
+             const optState_t* const optPtr,
+                   int const optLevel)
+{
+    U32 price;
+    U32 const offCode = ZSTD_highbit32(offset+1);
+    U32 const mlBase = matchLength - MINMATCH;
+    assert(matchLength >= MINMATCH);
+
+    if (optPtr->priceType == zop_predef)  /* fixed scheme, do not use statistics */
+        return WEIGHT(mlBase, optLevel) + ((16 + offCode) * BITCOST_MULTIPLIER);
+
+    /* dynamic statistics */
+    price = (offCode * BITCOST_MULTIPLIER) + (optPtr->offCodeSumBasePrice - WEIGHT(optPtr->offCodeFreq[offCode], optLevel));
+    if ((optLevel<2) /*static*/ && offCode >= 20)
+        price += (offCode-19)*2 * BITCOST_MULTIPLIER; /* handicap for long distance offsets, favor decompression speed */
+
+    /* match Length */
+    {   U32 const mlCode = ZSTD_MLcode(mlBase);
+        price += (ML_bits[mlCode] * BITCOST_MULTIPLIER) + (optPtr->matchLengthSumBasePrice - WEIGHT(optPtr->matchLengthFreq[mlCode], optLevel));
+    }
+
+    price += BITCOST_MULTIPLIER / 5;   /* heuristic : make matches a bit more costly to favor less sequences -> faster decompression speed */
+
+    DEBUGLOG(8, "ZSTD_getMatchPrice(ml:%u) = %u", matchLength, price);
+    return price;
+}
+
+/* ZSTD_updateStats() :
+ * assumption : literals + litLengtn <= iend */
+static void ZSTD_updateStats(optState_t* const optPtr,
+                             U32 litLength, const BYTE* literals,
+                             U32 offsetCode, U32 matchLength)
+{
+    /* literals */
+    if (ZSTD_compressedLiterals(optPtr)) {
+        U32 u;
+        for (u=0; u < litLength; u++)
+            optPtr->litFreq[literals[u]] += ZSTD_LITFREQ_ADD;
+        optPtr->litSum += litLength*ZSTD_LITFREQ_ADD;
+    }
+
+    /* literal Length */
+    {   U32 const llCode = ZSTD_LLcode(litLength);
+        optPtr->litLengthFreq[llCode]++;
+        optPtr->litLengthSum++;
+    }
+
+    /* match offset code (0-2=>repCode; 3+=>offset+2) */
+    {   U32 const offCode = ZSTD_highbit32(offsetCode+1);
+        assert(offCode <= MaxOff);
+        optPtr->offCodeFreq[offCode]++;
+        optPtr->offCodeSum++;
+    }
+
+    /* match Length */
+    {   U32 const mlBase = matchLength - MINMATCH;
+        U32 const mlCode = ZSTD_MLcode(mlBase);
+        optPtr->matchLengthFreq[mlCode]++;
+        optPtr->matchLengthSum++;
+    }
+}
+
+
+/* ZSTD_readMINMATCH() :
+ * function safe only for comparisons
+ * assumption : memPtr must be at least 4 bytes before end of buffer */
+MEM_STATIC U32 ZSTD_readMINMATCH(const void* memPtr, U32 length)
+{
+    switch (length)
+    {
+    default :
+    case 4 : return MEM_read32(memPtr);
+    case 3 : if (MEM_isLittleEndian())
+                return MEM_read32(memPtr)<<8;
+             else
+                return MEM_read32(memPtr)>>8;
+    }
+}
+
+
+/* Update hashTable3 up to ip (excluded)
+   Assumption : always within prefix (i.e. not within extDict) */
+static U32 ZSTD_insertAndFindFirstIndexHash3 (ZSTD_matchState_t* ms,
+                                              U32* nextToUpdate3,
+                                              const BYTE* const ip)
+{
+    U32* const hashTable3 = ms->hashTable3;
+    U32 const hashLog3 = ms->hashLog3;
+    const BYTE* const base = ms->window.base;
+    U32 idx = *nextToUpdate3;
+    U32 const target = (U32)(ip - base);
+    size_t const hash3 = ZSTD_hash3Ptr(ip, hashLog3);
+    assert(hashLog3 > 0);
+
+    while(idx < target) {
+        hashTable3[ZSTD_hash3Ptr(base+idx, hashLog3)] = idx;
+        idx++;
+    }
+
+    *nextToUpdate3 = target;
+    return hashTable3[hash3];
+}
+
+
+/*-*************************************
+*  Binary Tree search
+***************************************/
+/* ZSTD_insertBt1() : add one or multiple positions to tree.
+ *  ip : assumed <= iend-8 .
+ * @return : nb of positions added */
+static U32 ZSTD_insertBt1(
+                ZSTD_matchState_t* ms,
+                const BYTE* const ip, const BYTE* const iend,
+                U32 const mls, const int extDict)
+{
+    const ZSTD_compressionParameters* const cParams = &ms->cParams;
+    U32*   const hashTable = ms->hashTable;
+    U32    const hashLog = cParams->hashLog;
+    size_t const h  = ZSTD_hashPtr(ip, hashLog, mls);
+    U32*   const bt = ms->chainTable;
+    U32    const btLog  = cParams->chainLog - 1;
+    U32    const btMask = (1 << btLog) - 1;
+    U32 matchIndex = hashTable[h];
+    size_t commonLengthSmaller=0, commonLengthLarger=0;
+    const BYTE* const base = ms->window.base;
+    const BYTE* const dictBase = ms->window.dictBase;
+    const U32 dictLimit = ms->window.dictLimit;
+    const BYTE* const dictEnd = dictBase + dictLimit;
+    const BYTE* const prefixStart = base + dictLimit;
+    const BYTE* match;
+    const U32 curr = (U32)(ip-base);
+    const U32 btLow = btMask >= curr ? 0 : curr - btMask;
+    U32* smallerPtr = bt + 2*(curr&btMask);
+    U32* largerPtr  = smallerPtr + 1;
+    U32 dummy32;   /* to be nullified at the end */
+    U32 const windowLow = ms->window.lowLimit;
+    U32 matchEndIdx = curr+8+1;
+    size_t bestLength = 8;
+    U32 nbCompares = 1U << cParams->searchLog;
+#ifdef ZSTD_C_PREDICT
+    U32 predictedSmall = *(bt + 2*((curr-1)&btMask) + 0);
+    U32 predictedLarge = *(bt + 2*((curr-1)&btMask) + 1);
+    predictedSmall += (predictedSmall>0);
+    predictedLarge += (predictedLarge>0);
+#endif /* ZSTD_C_PREDICT */
+
+    DEBUGLOG(8, "ZSTD_insertBt1 (%u)", curr);
+
+    assert(ip <= iend-8);   /* required for h calculation */
+    hashTable[h] = curr;   /* Update Hash Table */
+
+    assert(windowLow > 0);
+    for (; nbCompares && (matchIndex >= windowLow); --nbCompares) {
+        U32* const nextPtr = bt + 2*(matchIndex & btMask);
+        size_t matchLength = MIN(commonLengthSmaller, commonLengthLarger);   /* guaranteed minimum nb of common bytes */
+        assert(matchIndex < curr);
+
+#ifdef ZSTD_C_PREDICT   /* note : can create issues when hlog small <= 11 */
+        const U32* predictPtr = bt + 2*((matchIndex-1) & btMask);   /* written this way, as bt is a roll buffer */
+        if (matchIndex == predictedSmall) {
+            /* no need to check length, result known */
+            *smallerPtr = matchIndex;
+            if (matchIndex <= btLow) { smallerPtr=&dummy32; break; }   /* beyond tree size, stop the search */
+            smallerPtr = nextPtr+1;               /* new "smaller" => larger of match */
+            matchIndex = nextPtr[1];              /* new matchIndex larger than previous (closer to current) */
+            predictedSmall = predictPtr[1] + (predictPtr[1]>0);
+            continue;
+        }
+        if (matchIndex == predictedLarge) {
+            *largerPtr = matchIndex;
+            if (matchIndex <= btLow) { largerPtr=&dummy32; break; }   /* beyond tree size, stop the search */
+            largerPtr = nextPtr;
+            matchIndex = nextPtr[0];
+            predictedLarge = predictPtr[0] + (predictPtr[0]>0);
+            continue;
+        }
+#endif
+
+        if (!extDict || (matchIndex+matchLength >= dictLimit)) {
+            assert(matchIndex+matchLength >= dictLimit);   /* might be wrong if actually extDict */
+            match = base + matchIndex;
+            matchLength += ZSTD_count(ip+matchLength, match+matchLength, iend);
+        } else {
+            match = dictBase + matchIndex;
+            matchLength += ZSTD_count_2segments(ip+matchLength, match+matchLength, iend, dictEnd, prefixStart);
+            if (matchIndex+matchLength >= dictLimit)
+                match = base + matchIndex;   /* to prepare for next usage of match[matchLength] */
+        }
+
+        if (matchLength > bestLength) {
+            bestLength = matchLength;
+            if (matchLength > matchEndIdx - matchIndex)
+                matchEndIdx = matchIndex + (U32)matchLength;
+        }
+
+        if (ip+matchLength == iend) {   /* equal : no way to know if inf or sup */
+            break;   /* drop , to guarantee consistency ; miss a bit of compression, but other solutions can corrupt tree */
+        }
+
+        if (match[matchLength] < ip[matchLength]) {  /* necessarily within buffer */
+            /* match is smaller than current */
+            *smallerPtr = matchIndex;             /* update smaller idx */
+            commonLengthSmaller = matchLength;    /* all smaller will now have at least this guaranteed common length */
+            if (matchIndex <= btLow) { smallerPtr=&dummy32; break; }   /* beyond tree size, stop searching */
+            smallerPtr = nextPtr+1;               /* new "candidate" => larger than match, which was smaller than target */
+            matchIndex = nextPtr[1];              /* new matchIndex, larger than previous and closer to current */
+        } else {
+            /* match is larger than current */
+            *largerPtr = matchIndex;
+            commonLengthLarger = matchLength;
+            if (matchIndex <= btLow) { largerPtr=&dummy32; break; }   /* beyond tree size, stop searching */
+            largerPtr = nextPtr;
+            matchIndex = nextPtr[0];
+    }   }
+
+    *smallerPtr = *largerPtr = 0;
+    {   U32 positions = 0;
+        if (bestLength > 384) positions = MIN(192, (U32)(bestLength - 384));   /* speed optimization */
+        assert(matchEndIdx > curr + 8);
+        return MAX(positions, matchEndIdx - (curr + 8));
+    }
+}
+
+FORCE_INLINE_TEMPLATE
+void ZSTD_updateTree_internal(
+                ZSTD_matchState_t* ms,
+                const BYTE* const ip, const BYTE* const iend,
+                const U32 mls, const ZSTD_dictMode_e dictMode)
+{
+    const BYTE* const base = ms->window.base;
+    U32 const target = (U32)(ip - base);
+    U32 idx = ms->nextToUpdate;
+    DEBUGLOG(6, "ZSTD_updateTree_internal, from %u to %u  (dictMode:%u)",
+                idx, target, dictMode);
+
+    while(idx < target) {
+        U32 const forward = ZSTD_insertBt1(ms, base+idx, iend, mls, dictMode == ZSTD_extDict);
+        assert(idx < (U32)(idx + forward));
+        idx += forward;
+    }
+    assert((size_t)(ip - base) <= (size_t)(U32)(-1));
+    assert((size_t)(iend - base) <= (size_t)(U32)(-1));
+    ms->nextToUpdate = target;
+}
+
+void ZSTD_updateTree(ZSTD_matchState_t* ms, const BYTE* ip, const BYTE* iend) {
+    ZSTD_updateTree_internal(ms, ip, iend, ms->cParams.minMatch, ZSTD_noDict);
+}
+
+FORCE_INLINE_TEMPLATE
+U32 ZSTD_insertBtAndGetAllMatches (
+                    ZSTD_match_t* matches,   /* store result (found matches) in this table (presumed large enough) */
+                    ZSTD_matchState_t* ms,
+                    U32* nextToUpdate3,
+                    const BYTE* const ip, const BYTE* const iLimit, const ZSTD_dictMode_e dictMode,
+                    const U32 rep[ZSTD_REP_NUM],
+                    U32 const ll0,   /* tells if associated literal length is 0 or not. This value must be 0 or 1 */
+                    const U32 lengthToBeat,
+                    U32 const mls /* template */)
+{
+    const ZSTD_compressionParameters* const cParams = &ms->cParams;
+    U32 const sufficient_len = MIN(cParams->targetLength, ZSTD_OPT_NUM -1);
+    const BYTE* const base = ms->window.base;
+    U32 const curr = (U32)(ip-base);
+    U32 const hashLog = cParams->hashLog;
+    U32 const minMatch = (mls==3) ? 3 : 4;
+    U32* const hashTable = ms->hashTable;
+    size_t const h  = ZSTD_hashPtr(ip, hashLog, mls);
+    U32 matchIndex  = hashTable[h];
+    U32* const bt   = ms->chainTable;
+    U32 const btLog = cParams->chainLog - 1;
+    U32 const btMask= (1U << btLog) - 1;
+    size_t commonLengthSmaller=0, commonLengthLarger=0;
+    const BYTE* const dictBase = ms->window.dictBase;
+    U32 const dictLimit = ms->window.dictLimit;
+    const BYTE* const dictEnd = dictBase + dictLimit;
+    const BYTE* const prefixStart = base + dictLimit;
+    U32 const btLow = (btMask >= curr) ? 0 : curr - btMask;
+    U32 const windowLow = ZSTD_getLowestMatchIndex(ms, curr, cParams->windowLog);
+    U32 const matchLow = windowLow ? windowLow : 1;
+    U32* smallerPtr = bt + 2*(curr&btMask);
+    U32* largerPtr  = bt + 2*(curr&btMask) + 1;
+    U32 matchEndIdx = curr+8+1;   /* farthest referenced position of any match => detects repetitive patterns */
+    U32 dummy32;   /* to be nullified at the end */
+    U32 mnum = 0;
+    U32 nbCompares = 1U << cParams->searchLog;
+
+    const ZSTD_matchState_t* dms    = dictMode == ZSTD_dictMatchState ? ms->dictMatchState : NULL;
+    const ZSTD_compressionParameters* const dmsCParams =
+                                      dictMode == ZSTD_dictMatchState ? &dms->cParams : NULL;
+    const BYTE* const dmsBase       = dictMode == ZSTD_dictMatchState ? dms->window.base : NULL;
+    const BYTE* const dmsEnd        = dictMode == ZSTD_dictMatchState ? dms->window.nextSrc : NULL;
+    U32         const dmsHighLimit  = dictMode == ZSTD_dictMatchState ? (U32)(dmsEnd - dmsBase) : 0;
+    U32         const dmsLowLimit   = dictMode == ZSTD_dictMatchState ? dms->window.lowLimit : 0;
+    U32         const dmsIndexDelta = dictMode == ZSTD_dictMatchState ? windowLow - dmsHighLimit : 0;
+    U32         const dmsHashLog    = dictMode == ZSTD_dictMatchState ? dmsCParams->hashLog : hashLog;
+    U32         const dmsBtLog      = dictMode == ZSTD_dictMatchState ? dmsCParams->chainLog - 1 : btLog;
+    U32         const dmsBtMask     = dictMode == ZSTD_dictMatchState ? (1U << dmsBtLog) - 1 : 0;
+    U32         const dmsBtLow      = dictMode == ZSTD_dictMatchState && dmsBtMask < dmsHighLimit - dmsLowLimit ? dmsHighLimit - dmsBtMask : dmsLowLimit;
+
+    size_t bestLength = lengthToBeat-1;
+    DEBUGLOG(8, "ZSTD_insertBtAndGetAllMatches: current=%u", curr);
+
+    /* check repCode */
+    assert(ll0 <= 1);   /* necessarily 1 or 0 */
+    {   U32 const lastR = ZSTD_REP_NUM + ll0;
+        U32 repCode;
+        for (repCode = ll0; repCode < lastR; repCode++) {
+            U32 const repOffset = (repCode==ZSTD_REP_NUM) ? (rep[0] - 1) : rep[repCode];
+            U32 const repIndex = curr - repOffset;
+            U32 repLen = 0;
+            assert(curr >= dictLimit);
+            if (repOffset-1 /* intentional overflow, discards 0 and -1 */ < curr-dictLimit) {  /* equivalent to `curr > repIndex >= dictLimit` */
+                /* We must validate the repcode offset because when we're using a dictionary the
+                 * valid offset range shrinks when the dictionary goes out of bounds.
+                 */
+                if ((repIndex >= windowLow) & (ZSTD_readMINMATCH(ip, minMatch) == ZSTD_readMINMATCH(ip - repOffset, minMatch))) {
+                    repLen = (U32)ZSTD_count(ip+minMatch, ip+minMatch-repOffset, iLimit) + minMatch;
+                }
+            } else {  /* repIndex < dictLimit || repIndex >= curr */
+                const BYTE* const repMatch = dictMode == ZSTD_dictMatchState ?
+                                             dmsBase + repIndex - dmsIndexDelta :
+                                             dictBase + repIndex;
+                assert(curr >= windowLow);
+                if ( dictMode == ZSTD_extDict
+                  && ( ((repOffset-1) /*intentional overflow*/ < curr - windowLow)  /* equivalent to `curr > repIndex >= windowLow` */
+                     & (((U32)((dictLimit-1) - repIndex) >= 3) ) /* intentional overflow : do not test positions overlapping 2 memory segments */)
+                  && (ZSTD_readMINMATCH(ip, minMatch) == ZSTD_readMINMATCH(repMatch, minMatch)) ) {
+                    repLen = (U32)ZSTD_count_2segments(ip+minMatch, repMatch+minMatch, iLimit, dictEnd, prefixStart) + minMatch;
+                }
+                if (dictMode == ZSTD_dictMatchState
+                  && ( ((repOffset-1) /*intentional overflow*/ < curr - (dmsLowLimit + dmsIndexDelta))  /* equivalent to `curr > repIndex >= dmsLowLimit` */
+                     & ((U32)((dictLimit-1) - repIndex) >= 3) ) /* intentional overflow : do not test positions overlapping 2 memory segments */
+                  && (ZSTD_readMINMATCH(ip, minMatch) == ZSTD_readMINMATCH(repMatch, minMatch)) ) {
+                    repLen = (U32)ZSTD_count_2segments(ip+minMatch, repMatch+minMatch, iLimit, dmsEnd, prefixStart) + minMatch;
+            }   }
+            /* save longer solution */
+            if (repLen > bestLength) {
+                DEBUGLOG(8, "found repCode %u (ll0:%u, offset:%u) of length %u",
+                            repCode, ll0, repOffset, repLen);
+                bestLength = repLen;
+                matches[mnum].off = repCode - ll0;
+                matches[mnum].len = (U32)repLen;
+                mnum++;
+                if ( (repLen > sufficient_len)
+                   | (ip+repLen == iLimit) ) {  /* best possible */
+                    return mnum;
+    }   }   }   }
+
+    /* HC3 match finder */
+    if ((mls == 3) /*static*/ && (bestLength < mls)) {
+        U32 const matchIndex3 = ZSTD_insertAndFindFirstIndexHash3(ms, nextToUpdate3, ip);
+        if ((matchIndex3 >= matchLow)
+          & (curr - matchIndex3 < (1<<18)) /*heuristic : longer distance likely too expensive*/ ) {
+            size_t mlen;
+            if ((dictMode == ZSTD_noDict) /*static*/ || (dictMode == ZSTD_dictMatchState) /*static*/ || (matchIndex3 >= dictLimit)) {
+                const BYTE* const match = base + matchIndex3;
+                mlen = ZSTD_count(ip, match, iLimit);
+            } else {
+                const BYTE* const match = dictBase + matchIndex3;
+                mlen = ZSTD_count_2segments(ip, match, iLimit, dictEnd, prefixStart);
+            }
+
+            /* save best solution */
+            if (mlen >= mls /* == 3 > bestLength */) {
+                DEBUGLOG(8, "found small match with hlog3, of length %u",
+                            (U32)mlen);
+                bestLength = mlen;
+                assert(curr > matchIndex3);
+                assert(mnum==0);  /* no prior solution */
+                matches[0].off = (curr - matchIndex3) + ZSTD_REP_MOVE;
+                matches[0].len = (U32)mlen;
+                mnum = 1;
+                if ( (mlen > sufficient_len) |
+                     (ip+mlen == iLimit) ) {  /* best possible length */
+                    ms->nextToUpdate = curr+1;  /* skip insertion */
+                    return 1;
+        }   }   }
+        /* no dictMatchState lookup: dicts don't have a populated HC3 table */
+    }
+
+    hashTable[h] = curr;   /* Update Hash Table */
+
+    for (; nbCompares && (matchIndex >= matchLow); --nbCompares) {
+        U32* const nextPtr = bt + 2*(matchIndex & btMask);
+        const BYTE* match;
+        size_t matchLength = MIN(commonLengthSmaller, commonLengthLarger);   /* guaranteed minimum nb of common bytes */
+        assert(curr > matchIndex);
+
+        if ((dictMode == ZSTD_noDict) || (dictMode == ZSTD_dictMatchState) || (matchIndex+matchLength >= dictLimit)) {
+            assert(matchIndex+matchLength >= dictLimit);  /* ensure the condition is correct when !extDict */
+            match = base + matchIndex;
+            if (matchIndex >= dictLimit) assert(memcmp(match, ip, matchLength) == 0);  /* ensure early section of match is equal as expected */
+            matchLength += ZSTD_count(ip+matchLength, match+matchLength, iLimit);
+        } else {
+            match = dictBase + matchIndex;
+            assert(memcmp(match, ip, matchLength) == 0);  /* ensure early section of match is equal as expected */
+            matchLength += ZSTD_count_2segments(ip+matchLength, match+matchLength, iLimit, dictEnd, prefixStart);
+            if (matchIndex+matchLength >= dictLimit)
+                match = base + matchIndex;   /* prepare for match[matchLength] read */
+        }
+
+        if (matchLength > bestLength) {
+            DEBUGLOG(8, "found match of length %u at distance %u (offCode=%u)",
+                    (U32)matchLength, curr - matchIndex, curr - matchIndex + ZSTD_REP_MOVE);
+            assert(matchEndIdx > matchIndex);
+            if (matchLength > matchEndIdx - matchIndex)
+                matchEndIdx = matchIndex + (U32)matchLength;
+            bestLength = matchLength;
+            matches[mnum].off = (curr - matchIndex) + ZSTD_REP_MOVE;
+            matches[mnum].len = (U32)matchLength;
+            mnum++;
+            if ( (matchLength > ZSTD_OPT_NUM)
+               | (ip+matchLength == iLimit) /* equal : no way to know if inf or sup */) {
+                if (dictMode == ZSTD_dictMatchState) nbCompares = 0; /* break should also skip searching dms */
+                break; /* drop, to preserve bt consistency (miss a little bit of compression) */
+            }
+        }
+
+        if (match[matchLength] < ip[matchLength]) {
+            /* match smaller than current */
+            *smallerPtr = matchIndex;             /* update smaller idx */
+            commonLengthSmaller = matchLength;    /* all smaller will now have at least this guaranteed common length */
+            if (matchIndex <= btLow) { smallerPtr=&dummy32; break; }   /* beyond tree size, stop the search */
+            smallerPtr = nextPtr+1;               /* new candidate => larger than match, which was smaller than current */
+            matchIndex = nextPtr[1];              /* new matchIndex, larger than previous, closer to current */
+        } else {
+            *largerPtr = matchIndex;
+            commonLengthLarger = matchLength;
+            if (matchIndex <= btLow) { largerPtr=&dummy32; break; }   /* beyond tree size, stop the search */
+            largerPtr = nextPtr;
+            matchIndex = nextPtr[0];
+    }   }
+
+    *smallerPtr = *largerPtr = 0;
+
+    assert(nbCompares <= (1U << ZSTD_SEARCHLOG_MAX)); /* Check we haven't underflowed. */
+    if (dictMode == ZSTD_dictMatchState && nbCompares) {
+        size_t const dmsH = ZSTD_hashPtr(ip, dmsHashLog, mls);
+        U32 dictMatchIndex = dms->hashTable[dmsH];
+        const U32* const dmsBt = dms->chainTable;
+        commonLengthSmaller = commonLengthLarger = 0;
+        for (; nbCompares && (dictMatchIndex > dmsLowLimit); --nbCompares) {
+            const U32* const nextPtr = dmsBt + 2*(dictMatchIndex & dmsBtMask);
+            size_t matchLength = MIN(commonLengthSmaller, commonLengthLarger);   /* guaranteed minimum nb of common bytes */
+            const BYTE* match = dmsBase + dictMatchIndex;
+            matchLength += ZSTD_count_2segments(ip+matchLength, match+matchLength, iLimit, dmsEnd, prefixStart);
+            if (dictMatchIndex+matchLength >= dmsHighLimit)
+                match = base + dictMatchIndex + dmsIndexDelta;   /* to prepare for next usage of match[matchLength] */
+
+            if (matchLength > bestLength) {
+                matchIndex = dictMatchIndex + dmsIndexDelta;
+                DEBUGLOG(8, "found dms match of length %u at distance %u (offCode=%u)",
+                        (U32)matchLength, curr - matchIndex, curr - matchIndex + ZSTD_REP_MOVE);
+                if (matchLength > matchEndIdx - matchIndex)
+                    matchEndIdx = matchIndex + (U32)matchLength;
+                bestLength = matchLength;
+                matches[mnum].off = (curr - matchIndex) + ZSTD_REP_MOVE;
+                matches[mnum].len = (U32)matchLength;
+                mnum++;
+                if ( (matchLength > ZSTD_OPT_NUM)
+                   | (ip+matchLength == iLimit) /* equal : no way to know if inf or sup */) {
+                    break;   /* drop, to guarantee consistency (miss a little bit of compression) */
+                }
+            }
+
+            if (dictMatchIndex <= dmsBtLow) { break; }   /* beyond tree size, stop the search */
+            if (match[matchLength] < ip[matchLength]) {
+                commonLengthSmaller = matchLength;    /* all smaller will now have at least this guaranteed common length */
+                dictMatchIndex = nextPtr[1];              /* new matchIndex larger than previous (closer to current) */
+            } else {
+                /* match is larger than current */
+                commonLengthLarger = matchLength;
+                dictMatchIndex = nextPtr[0];
+            }
+        }
+    }
+
+    assert(matchEndIdx > curr+8);
+    ms->nextToUpdate = matchEndIdx - 8;  /* skip repetitive patterns */
+    return mnum;
+}
+
+
+FORCE_INLINE_TEMPLATE U32 ZSTD_BtGetAllMatches (
+                        ZSTD_match_t* matches,   /* store result (match found, increasing size) in this table */
+                        ZSTD_matchState_t* ms,
+                        U32* nextToUpdate3,
+                        const BYTE* ip, const BYTE* const iHighLimit, const ZSTD_dictMode_e dictMode,
+                        const U32 rep[ZSTD_REP_NUM],
+                        U32 const ll0,
+                        U32 const lengthToBeat)
+{
+    const ZSTD_compressionParameters* const cParams = &ms->cParams;
+    U32 const matchLengthSearch = cParams->minMatch;
+    DEBUGLOG(8, "ZSTD_BtGetAllMatches");
+    if (ip < ms->window.base + ms->nextToUpdate) return 0;   /* skipped area */
+    ZSTD_updateTree_internal(ms, ip, iHighLimit, matchLengthSearch, dictMode);
+    switch(matchLengthSearch)
+    {
+    case 3 : return ZSTD_insertBtAndGetAllMatches(matches, ms, nextToUpdate3, ip, iHighLimit, dictMode, rep, ll0, lengthToBeat, 3);
+    default :
+    case 4 : return ZSTD_insertBtAndGetAllMatches(matches, ms, nextToUpdate3, ip, iHighLimit, dictMode, rep, ll0, lengthToBeat, 4);
+    case 5 : return ZSTD_insertBtAndGetAllMatches(matches, ms, nextToUpdate3, ip, iHighLimit, dictMode, rep, ll0, lengthToBeat, 5);
+    case 7 :
+    case 6 : return ZSTD_insertBtAndGetAllMatches(matches, ms, nextToUpdate3, ip, iHighLimit, dictMode, rep, ll0, lengthToBeat, 6);
+    }
+}
+
+/* ***********************
+*  LDM helper functions  *
+*************************/
+
+/* Struct containing info needed to make decision about ldm inclusion */
+typedef struct {
+    rawSeqStore_t seqStore;         /* External match candidates store for this block */
+    U32 startPosInBlock;            /* Start position of the current match candidate */
+    U32 endPosInBlock;              /* End position of the current match candidate */
+    U32 offset;                     /* Offset of the match candidate */
+} ZSTD_optLdm_t;
+
+/* ZSTD_optLdm_skipRawSeqStoreBytes():
+ * Moves forward in rawSeqStore by nbBytes, which will update the fields 'pos' and 'posInSequence'.
+ */
+static void ZSTD_optLdm_skipRawSeqStoreBytes(rawSeqStore_t* rawSeqStore, size_t nbBytes) {
+    U32 currPos = (U32)(rawSeqStore->posInSequence + nbBytes);
+    while (currPos && rawSeqStore->pos < rawSeqStore->size) {
+        rawSeq currSeq = rawSeqStore->seq[rawSeqStore->pos];
+        if (currPos >= currSeq.litLength + currSeq.matchLength) {
+            currPos -= currSeq.litLength + currSeq.matchLength;
+            rawSeqStore->pos++;
+        } else {
+            rawSeqStore->posInSequence = currPos;
+            break;
+        }
+    }
+    if (currPos == 0 || rawSeqStore->pos == rawSeqStore->size) {
+        rawSeqStore->posInSequence = 0;
+    }
+}
+
+/* ZSTD_opt_getNextMatchAndUpdateSeqStore():
+ * Calculates the beginning and end of the next match in the current block.
+ * Updates 'pos' and 'posInSequence' of the ldmSeqStore.
+ */
+static void ZSTD_opt_getNextMatchAndUpdateSeqStore(ZSTD_optLdm_t* optLdm, U32 currPosInBlock,
+                                                   U32 blockBytesRemaining) {
+    rawSeq currSeq;
+    U32 currBlockEndPos;
+    U32 literalsBytesRemaining;
+    U32 matchBytesRemaining;
+
+    /* Setting match end position to MAX to ensure we never use an LDM during this block */
+    if (optLdm->seqStore.size == 0 || optLdm->seqStore.pos >= optLdm->seqStore.size) {
+        optLdm->startPosInBlock = UINT_MAX;
+        optLdm->endPosInBlock = UINT_MAX;
+        return;
+    }
+    /* Calculate appropriate bytes left in matchLength and litLength after adjusting
+       based on ldmSeqStore->posInSequence */
+    currSeq = optLdm->seqStore.seq[optLdm->seqStore.pos];
+    assert(optLdm->seqStore.posInSequence <= currSeq.litLength + currSeq.matchLength);
+    currBlockEndPos = currPosInBlock + blockBytesRemaining;
+    literalsBytesRemaining = (optLdm->seqStore.posInSequence < currSeq.litLength) ?
+            currSeq.litLength - (U32)optLdm->seqStore.posInSequence :
+            0;
+    matchBytesRemaining = (literalsBytesRemaining == 0) ?
+            currSeq.matchLength - ((U32)optLdm->seqStore.posInSequence - currSeq.litLength) :
+            currSeq.matchLength;
+
+    /* If there are more literal bytes than bytes remaining in block, no ldm is possible */
+    if (literalsBytesRemaining >= blockBytesRemaining) {
+        optLdm->startPosInBlock = UINT_MAX;
+        optLdm->endPosInBlock = UINT_MAX;
+        ZSTD_optLdm_skipRawSeqStoreBytes(&optLdm->seqStore, blockBytesRemaining);
+        return;
+    }
+
+    /* Matches may be < MINMATCH by this process. In that case, we will reject them
+       when we are deciding whether or not to add the ldm */
+    optLdm->startPosInBlock = currPosInBlock + literalsBytesRemaining;
+    optLdm->endPosInBlock = optLdm->startPosInBlock + matchBytesRemaining;
+    optLdm->offset = currSeq.offset;
+
+    if (optLdm->endPosInBlock > currBlockEndPos) {
+        /* Match ends after the block ends, we can't use the whole match */
+        optLdm->endPosInBlock = currBlockEndPos;
+        ZSTD_optLdm_skipRawSeqStoreBytes(&optLdm->seqStore, currBlockEndPos - currPosInBlock);
+    } else {
+        /* Consume nb of bytes equal to size of sequence left */
+        ZSTD_optLdm_skipRawSeqStoreBytes(&optLdm->seqStore, literalsBytesRemaining + matchBytesRemaining);
+    }
+}
+
+/* ZSTD_optLdm_maybeAddMatch():
+ * Adds a match if it's long enough, based on it's 'matchStartPosInBlock'
+ * and 'matchEndPosInBlock', into 'matches'. Maintains the correct ordering of 'matches'
+ */
+static void ZSTD_optLdm_maybeAddMatch(ZSTD_match_t* matches, U32* nbMatches,
+                                      ZSTD_optLdm_t* optLdm, U32 currPosInBlock) {
+    U32 posDiff = currPosInBlock - optLdm->startPosInBlock;
+    /* Note: ZSTD_match_t actually contains offCode and matchLength (before subtracting MINMATCH) */
+    U32 candidateMatchLength = optLdm->endPosInBlock - optLdm->startPosInBlock - posDiff;
+    U32 candidateOffCode = optLdm->offset + ZSTD_REP_MOVE;
+
+    /* Ensure that current block position is not outside of the match */
+    if (currPosInBlock < optLdm->startPosInBlock
+      || currPosInBlock >= optLdm->endPosInBlock
+      || candidateMatchLength < MINMATCH) {
+        return;
+    }
+
+    if (*nbMatches == 0 || ((candidateMatchLength > matches[*nbMatches-1].len) && *nbMatches < ZSTD_OPT_NUM)) {
+        DEBUGLOG(6, "ZSTD_optLdm_maybeAddMatch(): Adding ldm candidate match (offCode: %u matchLength %u) at block position=%u",
+                 candidateOffCode, candidateMatchLength, currPosInBlock);
+        matches[*nbMatches].len = candidateMatchLength;
+        matches[*nbMatches].off = candidateOffCode;
+        (*nbMatches)++;
+    }
+}
+
+/* ZSTD_optLdm_processMatchCandidate():
+ * Wrapper function to update ldm seq store and call ldm functions as necessary.
+ */
+static void ZSTD_optLdm_processMatchCandidate(ZSTD_optLdm_t* optLdm, ZSTD_match_t* matches, U32* nbMatches,
+                                              U32 currPosInBlock, U32 remainingBytes) {
+    if (optLdm->seqStore.size == 0 || optLdm->seqStore.pos >= optLdm->seqStore.size) {
+        return;
+    }
+
+    if (currPosInBlock >= optLdm->endPosInBlock) {
+        if (currPosInBlock > optLdm->endPosInBlock) {
+            /* The position at which ZSTD_optLdm_processMatchCandidate() is called is not necessarily
+             * at the end of a match from the ldm seq store, and will often be some bytes
+             * over beyond matchEndPosInBlock. As such, we need to correct for these "overshoots"
+             */
+            U32 posOvershoot = currPosInBlock - optLdm->endPosInBlock;
+            ZSTD_optLdm_skipRawSeqStoreBytes(&optLdm->seqStore, posOvershoot);
+        } 
+        ZSTD_opt_getNextMatchAndUpdateSeqStore(optLdm, currPosInBlock, remainingBytes);
+    }
+    ZSTD_optLdm_maybeAddMatch(matches, nbMatches, optLdm, currPosInBlock);
+}
+
+/*-*******************************
+*  Optimal parser
+*********************************/
+
+
+static U32 ZSTD_totalLen(ZSTD_optimal_t sol)
+{
+    return sol.litlen + sol.mlen;
+}
+
+#if 0 /* debug */
+
+static void
+listStats(const U32* table, int lastEltID)
+{
+    int const nbElts = lastEltID + 1;
+    int enb;
+    for (enb=0; enb < nbElts; enb++) {
+        (void)table;
+        /* RAWLOG(2, "%3i:%3i,  ", enb, table[enb]); */
+        RAWLOG(2, "%4i,", table[enb]);
+    }
+    RAWLOG(2, " \n");
+}
+
+#endif
+
+FORCE_INLINE_TEMPLATE size_t
+ZSTD_compressBlock_opt_generic(ZSTD_matchState_t* ms,
+                               seqStore_t* seqStore,
+                               U32 rep[ZSTD_REP_NUM],
+                         const void* src, size_t srcSize,
+                         const int optLevel,
+                         const ZSTD_dictMode_e dictMode)
+{
+    optState_t* const optStatePtr = &ms->opt;
+    const BYTE* const istart = (const BYTE*)src;
+    const BYTE* ip = istart;
+    const BYTE* anchor = istart;
+    const BYTE* const iend = istart + srcSize;
+    const BYTE* const ilimit = iend - 8;
+    const BYTE* const base = ms->window.base;
+    const BYTE* const prefixStart = base + ms->window.dictLimit;
+    const ZSTD_compressionParameters* const cParams = &ms->cParams;
+
+    U32 const sufficient_len = MIN(cParams->targetLength, ZSTD_OPT_NUM -1);
+    U32 const minMatch = (cParams->minMatch == 3) ? 3 : 4;
+    U32 nextToUpdate3 = ms->nextToUpdate;
+
+    ZSTD_optimal_t* const opt = optStatePtr->priceTable;
+    ZSTD_match_t* const matches = optStatePtr->matchTable;
+    ZSTD_optimal_t lastSequence;
+    ZSTD_optLdm_t optLdm;
+
+    optLdm.seqStore = ms->ldmSeqStore ? *ms->ldmSeqStore : kNullRawSeqStore;
+    optLdm.endPosInBlock = optLdm.startPosInBlock = optLdm.offset = 0;
+    ZSTD_opt_getNextMatchAndUpdateSeqStore(&optLdm, (U32)(ip-istart), (U32)(iend-ip));
+
+    /* init */
+    DEBUGLOG(5, "ZSTD_compressBlock_opt_generic: current=%u, prefix=%u, nextToUpdate=%u",
+                (U32)(ip - base), ms->window.dictLimit, ms->nextToUpdate);
+    assert(optLevel <= 2);
+    ZSTD_rescaleFreqs(optStatePtr, (const BYTE*)src, srcSize, optLevel);
+    ip += (ip==prefixStart);
+
+    /* Match Loop */
+    while (ip < ilimit) {
+        U32 cur, last_pos = 0;
+
+        /* find first match */
+        {   U32 const litlen = (U32)(ip - anchor);
+            U32 const ll0 = !litlen;
+            U32 nbMatches = ZSTD_BtGetAllMatches(matches, ms, &nextToUpdate3, ip, iend, dictMode, rep, ll0, minMatch);
+            ZSTD_optLdm_processMatchCandidate(&optLdm, matches, &nbMatches,
+                                              (U32)(ip-istart), (U32)(iend - ip));
+            if (!nbMatches) { ip++; continue; }
+
+            /* initialize opt[0] */
+            { U32 i ; for (i=0; i<ZSTD_REP_NUM; i++) opt[0].rep[i] = rep[i]; }
+            opt[0].mlen = 0;  /* means is_a_literal */
+            opt[0].litlen = litlen;
+            /* We don't need to include the actual price of the literals because
+             * it is static for the duration of the forward pass, and is included
+             * in every price. We include the literal length to avoid negative
+             * prices when we subtract the previous literal length.
+             */
+            opt[0].price = ZSTD_litLengthPrice(litlen, optStatePtr, optLevel);
+
+            /* large match -> immediate encoding */
+            {   U32 const maxML = matches[nbMatches-1].len;
+                U32 const maxOffset = matches[nbMatches-1].off;
+                DEBUGLOG(6, "found %u matches of maxLength=%u and maxOffCode=%u at cPos=%u => start new series",
+                            nbMatches, maxML, maxOffset, (U32)(ip-prefixStart));
+
+                if (maxML > sufficient_len) {
+                    lastSequence.litlen = litlen;
+                    lastSequence.mlen = maxML;
+                    lastSequence.off = maxOffset;
+                    DEBUGLOG(6, "large match (%u>%u), immediate encoding",
+                                maxML, sufficient_len);
+                    cur = 0;
+                    last_pos = ZSTD_totalLen(lastSequence);
+                    goto _shortestPath;
+            }   }
+
+            /* set prices for first matches starting position == 0 */
+            {   U32 const literalsPrice = opt[0].price + ZSTD_litLengthPrice(0, optStatePtr, optLevel);
+                U32 pos;
+                U32 matchNb;
+                for (pos = 1; pos < minMatch; pos++) {
+                    opt[pos].price = ZSTD_MAX_PRICE;   /* mlen, litlen and price will be fixed during forward scanning */
+                }
+                for (matchNb = 0; matchNb < nbMatches; matchNb++) {
+                    U32 const offset = matches[matchNb].off;
+                    U32 const end = matches[matchNb].len;
+                    for ( ; pos <= end ; pos++ ) {
+                        U32 const matchPrice = ZSTD_getMatchPrice(offset, pos, optStatePtr, optLevel);
+                        U32 const sequencePrice = literalsPrice + matchPrice;
+                        DEBUGLOG(7, "rPos:%u => set initial price : %.2f",
+                                    pos, ZSTD_fCost(sequencePrice));
+                        opt[pos].mlen = pos;
+                        opt[pos].off = offset;
+                        opt[pos].litlen = litlen;
+                        opt[pos].price = sequencePrice;
+                }   }
+                last_pos = pos-1;
+            }
+        }
+
+        /* check further positions */
+        for (cur = 1; cur <= last_pos; cur++) {
+            const BYTE* const inr = ip + cur;
+            assert(cur < ZSTD_OPT_NUM);
+            DEBUGLOG(7, "cPos:%zi==rPos:%u", inr-istart, cur)
+
+            /* Fix current position with one literal if cheaper */
+            {   U32 const litlen = (opt[cur-1].mlen == 0) ? opt[cur-1].litlen + 1 : 1;
+                int const price = opt[cur-1].price
+                                + ZSTD_rawLiteralsCost(ip+cur-1, 1, optStatePtr, optLevel)
+                                + ZSTD_litLengthPrice(litlen, optStatePtr, optLevel)
+                                - ZSTD_litLengthPrice(litlen-1, optStatePtr, optLevel);
+                assert(price < 1000000000); /* overflow check */
+                if (price <= opt[cur].price) {
+                    DEBUGLOG(7, "cPos:%zi==rPos:%u : better price (%.2f<=%.2f) using literal (ll==%u) (hist:%u,%u,%u)",
+                                inr-istart, cur, ZSTD_fCost(price), ZSTD_fCost(opt[cur].price), litlen,
+                                opt[cur-1].rep[0], opt[cur-1].rep[1], opt[cur-1].rep[2]);
+                    opt[cur].mlen = 0;
+                    opt[cur].off = 0;
+                    opt[cur].litlen = litlen;
+                    opt[cur].price = price;
+                } else {
+                    DEBUGLOG(7, "cPos:%zi==rPos:%u : literal would cost more (%.2f>%.2f) (hist:%u,%u,%u)",
+                                inr-istart, cur, ZSTD_fCost(price), ZSTD_fCost(opt[cur].price),
+                                opt[cur].rep[0], opt[cur].rep[1], opt[cur].rep[2]);
+                }
+            }
+
+            /* Set the repcodes of the current position. We must do it here
+             * because we rely on the repcodes of the 2nd to last sequence being
+             * correct to set the next chunks repcodes during the backward
+             * traversal.
+             */
+            ZSTD_STATIC_ASSERT(sizeof(opt[cur].rep) == sizeof(repcodes_t));
+            assert(cur >= opt[cur].mlen);
+            if (opt[cur].mlen != 0) {
+                U32 const prev = cur - opt[cur].mlen;
+                repcodes_t newReps = ZSTD_updateRep(opt[prev].rep, opt[cur].off, opt[cur].litlen==0);
+                ZSTD_memcpy(opt[cur].rep, &newReps, sizeof(repcodes_t));
+            } else {
+                ZSTD_memcpy(opt[cur].rep, opt[cur - 1].rep, sizeof(repcodes_t));
+            }
+
+            /* last match must start at a minimum distance of 8 from oend */
+            if (inr > ilimit) continue;
+
+            if (cur == last_pos) break;
+
+            if ( (optLevel==0) /*static_test*/
+              && (opt[cur+1].price <= opt[cur].price + (BITCOST_MULTIPLIER/2)) ) {
+                DEBUGLOG(7, "move to next rPos:%u : price is <=", cur+1);
+                continue;  /* skip unpromising positions; about ~+6% speed, -0.01 ratio */
+            }
+
+            {   U32 const ll0 = (opt[cur].mlen != 0);
+                U32 const litlen = (opt[cur].mlen == 0) ? opt[cur].litlen : 0;
+                U32 const previousPrice = opt[cur].price;
+                U32 const basePrice = previousPrice + ZSTD_litLengthPrice(0, optStatePtr, optLevel);
+                U32 nbMatches = ZSTD_BtGetAllMatches(matches, ms, &nextToUpdate3, inr, iend, dictMode, opt[cur].rep, ll0, minMatch);
+                U32 matchNb;
+
+                ZSTD_optLdm_processMatchCandidate(&optLdm, matches, &nbMatches,
+                                                  (U32)(inr-istart), (U32)(iend-inr));
+
+                if (!nbMatches) {
+                    DEBUGLOG(7, "rPos:%u : no match found", cur);
+                    continue;
+                }
+
+                {   U32 const maxML = matches[nbMatches-1].len;
+                    DEBUGLOG(7, "cPos:%zi==rPos:%u, found %u matches, of maxLength=%u",
+                                inr-istart, cur, nbMatches, maxML);
+
+                    if ( (maxML > sufficient_len)
+                      || (cur + maxML >= ZSTD_OPT_NUM) ) {
+                        lastSequence.mlen = maxML;
+                        lastSequence.off = matches[nbMatches-1].off;
+                        lastSequence.litlen = litlen;
+                        cur -= (opt[cur].mlen==0) ? opt[cur].litlen : 0;  /* last sequence is actually only literals, fix cur to last match - note : may underflow, in which case, it's first sequence, and it's okay */
+                        last_pos = cur + ZSTD_totalLen(lastSequence);
+                        if (cur > ZSTD_OPT_NUM) cur = 0;   /* underflow => first match */
+                        goto _shortestPath;
+                }   }
+
+                /* set prices using matches found at position == cur */
+                for (matchNb = 0; matchNb < nbMatches; matchNb++) {
+                    U32 const offset = matches[matchNb].off;
+                    U32 const lastML = matches[matchNb].len;
+                    U32 const startML = (matchNb>0) ? matches[matchNb-1].len+1 : minMatch;
+                    U32 mlen;
+
+                    DEBUGLOG(7, "testing match %u => offCode=%4u, mlen=%2u, llen=%2u",
+                                matchNb, matches[matchNb].off, lastML, litlen);
+
+                    for (mlen = lastML; mlen >= startML; mlen--) {  /* scan downward */
+                        U32 const pos = cur + mlen;
+                        int const price = basePrice + ZSTD_getMatchPrice(offset, mlen, optStatePtr, optLevel);
+
+                        if ((pos > last_pos) || (price < opt[pos].price)) {
+                            DEBUGLOG(7, "rPos:%u (ml=%2u) => new better price (%.2f<%.2f)",
+                                        pos, mlen, ZSTD_fCost(price), ZSTD_fCost(opt[pos].price));
+                            while (last_pos < pos) { opt[last_pos+1].price = ZSTD_MAX_PRICE; last_pos++; }   /* fill empty positions */
+                            opt[pos].mlen = mlen;
+                            opt[pos].off = offset;
+                            opt[pos].litlen = litlen;
+                            opt[pos].price = price;
+                        } else {
+                            DEBUGLOG(7, "rPos:%u (ml=%2u) => new price is worse (%.2f>=%.2f)",
+                                        pos, mlen, ZSTD_fCost(price), ZSTD_fCost(opt[pos].price));
+                            if (optLevel==0) break;  /* early update abort; gets ~+10% speed for about -0.01 ratio loss */
+                        }
+            }   }   }
+        }  /* for (cur = 1; cur <= last_pos; cur++) */
+
+        lastSequence = opt[last_pos];
+        cur = last_pos > ZSTD_totalLen(lastSequence) ? last_pos - ZSTD_totalLen(lastSequence) : 0;  /* single sequence, and it starts before `ip` */
+        assert(cur < ZSTD_OPT_NUM);  /* control overflow*/
+
+_shortestPath:   /* cur, last_pos, best_mlen, best_off have to be set */
+        assert(opt[0].mlen == 0);
+
+        /* Set the next chunk's repcodes based on the repcodes of the beginning
+         * of the last match, and the last sequence. This avoids us having to
+         * update them while traversing the sequences.
+         */
+        if (lastSequence.mlen != 0) {
+            repcodes_t reps = ZSTD_updateRep(opt[cur].rep, lastSequence.off, lastSequence.litlen==0);
+            ZSTD_memcpy(rep, &reps, sizeof(reps));
+        } else {
+            ZSTD_memcpy(rep, opt[cur].rep, sizeof(repcodes_t));
+        }
+
+        {   U32 const storeEnd = cur + 1;
+            U32 storeStart = storeEnd;
+            U32 seqPos = cur;
+
+            DEBUGLOG(6, "start reverse traversal (last_pos:%u, cur:%u)",
+                        last_pos, cur); (void)last_pos;
+            assert(storeEnd < ZSTD_OPT_NUM);
+            DEBUGLOG(6, "last sequence copied into pos=%u (llen=%u,mlen=%u,ofc=%u)",
+                        storeEnd, lastSequence.litlen, lastSequence.mlen, lastSequence.off);
+            opt[storeEnd] = lastSequence;
+            while (seqPos > 0) {
+                U32 const backDist = ZSTD_totalLen(opt[seqPos]);
+                storeStart--;
+                DEBUGLOG(6, "sequence from rPos=%u copied into pos=%u (llen=%u,mlen=%u,ofc=%u)",
+                            seqPos, storeStart, opt[seqPos].litlen, opt[seqPos].mlen, opt[seqPos].off);
+                opt[storeStart] = opt[seqPos];
+                seqPos = (seqPos > backDist) ? seqPos - backDist : 0;
+            }
+
+            /* save sequences */
+            DEBUGLOG(6, "sending selected sequences into seqStore")
+            {   U32 storePos;
+                for (storePos=storeStart; storePos <= storeEnd; storePos++) {
+                    U32 const llen = opt[storePos].litlen;
+                    U32 const mlen = opt[storePos].mlen;
+                    U32 const offCode = opt[storePos].off;
+                    U32 const advance = llen + mlen;
+                    DEBUGLOG(6, "considering seq starting at %zi, llen=%u, mlen=%u",
+                                anchor - istart, (unsigned)llen, (unsigned)mlen);
+
+                    if (mlen==0) {  /* only literals => must be last "sequence", actually starting a new stream of sequences */
+                        assert(storePos == storeEnd);   /* must be last sequence */
+                        ip = anchor + llen;     /* last "sequence" is a bunch of literals => don't progress anchor */
+                        continue;   /* will finish */
+                    }
+
+                    assert(anchor + llen <= iend);
+                    ZSTD_updateStats(optStatePtr, llen, anchor, offCode, mlen);
+                    ZSTD_storeSeq(seqStore, llen, anchor, iend, offCode, mlen-MINMATCH);
+                    anchor += advance;
+                    ip = anchor;
+            }   }
+            ZSTD_setBasePrices(optStatePtr, optLevel);
+        }
+    }   /* while (ip < ilimit) */
+
+    /* Return the last literals size */
+    return (size_t)(iend - anchor);
+}
+
+
+size_t ZSTD_compressBlock_btopt(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        const void* src, size_t srcSize)
+{
+    DEBUGLOG(5, "ZSTD_compressBlock_btopt");
+    return ZSTD_compressBlock_opt_generic(ms, seqStore, rep, src, srcSize, 0 /*optLevel*/, ZSTD_noDict);
+}
+
+
+/* used in 2-pass strategy */
+static U32 ZSTD_upscaleStat(unsigned* table, U32 lastEltIndex, int bonus)
+{
+    U32 s, sum=0;
+    assert(ZSTD_FREQ_DIV+bonus >= 0);
+    for (s=0; s<lastEltIndex+1; s++) {
+        table[s] <<= ZSTD_FREQ_DIV+bonus;
+        table[s]--;
+        sum += table[s];
+    }
+    return sum;
+}
+
+/* used in 2-pass strategy */
+MEM_STATIC void ZSTD_upscaleStats(optState_t* optPtr)
+{
+    if (ZSTD_compressedLiterals(optPtr))
+        optPtr->litSum = ZSTD_upscaleStat(optPtr->litFreq, MaxLit, 0);
+    optPtr->litLengthSum = ZSTD_upscaleStat(optPtr->litLengthFreq, MaxLL, 0);
+    optPtr->matchLengthSum = ZSTD_upscaleStat(optPtr->matchLengthFreq, MaxML, 0);
+    optPtr->offCodeSum = ZSTD_upscaleStat(optPtr->offCodeFreq, MaxOff, 0);
+}
+
+/* ZSTD_initStats_ultra():
+ * make a first compression pass, just to seed stats with more accurate starting values.
+ * only works on first block, with no dictionary and no ldm.
+ * this function cannot error, hence its contract must be respected.
+ */
+static void
+ZSTD_initStats_ultra(ZSTD_matchState_t* ms,
+                     seqStore_t* seqStore,
+                     U32 rep[ZSTD_REP_NUM],
+               const void* src, size_t srcSize)
+{
+    U32 tmpRep[ZSTD_REP_NUM];  /* updated rep codes will sink here */
+    ZSTD_memcpy(tmpRep, rep, sizeof(tmpRep));
+
+    DEBUGLOG(4, "ZSTD_initStats_ultra (srcSize=%zu)", srcSize);
+    assert(ms->opt.litLengthSum == 0);    /* first block */
+    assert(seqStore->sequences == seqStore->sequencesStart);   /* no ldm */
+    assert(ms->window.dictLimit == ms->window.lowLimit);   /* no dictionary */
+    assert(ms->window.dictLimit - ms->nextToUpdate <= 1);  /* no prefix (note: intentional overflow, defined as 2-complement) */
+
+    ZSTD_compressBlock_opt_generic(ms, seqStore, tmpRep, src, srcSize, 2 /*optLevel*/, ZSTD_noDict);   /* generate stats into ms->opt*/
+
+    /* invalidate first scan from history */
+    ZSTD_resetSeqStore(seqStore);
+    ms->window.base -= srcSize;
+    ms->window.dictLimit += (U32)srcSize;
+    ms->window.lowLimit = ms->window.dictLimit;
+    ms->nextToUpdate = ms->window.dictLimit;
+
+    /* re-inforce weight of collected statistics */
+    ZSTD_upscaleStats(&ms->opt);
+}
+
+size_t ZSTD_compressBlock_btultra(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        const void* src, size_t srcSize)
+{
+    DEBUGLOG(5, "ZSTD_compressBlock_btultra (srcSize=%zu)", srcSize);
+    return ZSTD_compressBlock_opt_generic(ms, seqStore, rep, src, srcSize, 2 /*optLevel*/, ZSTD_noDict);
+}
+
+size_t ZSTD_compressBlock_btultra2(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        const void* src, size_t srcSize)
+{
+    U32 const curr = (U32)((const BYTE*)src - ms->window.base);
+    DEBUGLOG(5, "ZSTD_compressBlock_btultra2 (srcSize=%zu)", srcSize);
+
+    /* 2-pass strategy:
+     * this strategy makes a first pass over first block to collect statistics
+     * and seed next round's statistics with it.
+     * After 1st pass, function forgets everything, and starts a new block.
+     * Consequently, this can only work if no data has been previously loaded in tables,
+     * aka, no dictionary, no prefix, no ldm preprocessing.
+     * The compression ratio gain is generally small (~0.5% on first block),
+     * the cost is 2x cpu time on first block. */
+    assert(srcSize <= ZSTD_BLOCKSIZE_MAX);
+    if ( (ms->opt.litLengthSum==0)   /* first block */
+      && (seqStore->sequences == seqStore->sequencesStart)  /* no ldm */
+      && (ms->window.dictLimit == ms->window.lowLimit)   /* no dictionary */
+      && (curr == ms->window.dictLimit)   /* start of frame, nothing already loaded nor skipped */
+      && (srcSize > ZSTD_PREDEF_THRESHOLD)
+      ) {
+        ZSTD_initStats_ultra(ms, seqStore, rep, src, srcSize);
+    }
+
+    return ZSTD_compressBlock_opt_generic(ms, seqStore, rep, src, srcSize, 2 /*optLevel*/, ZSTD_noDict);
+}
+
+size_t ZSTD_compressBlock_btopt_dictMatchState(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        const void* src, size_t srcSize)
+{
+    return ZSTD_compressBlock_opt_generic(ms, seqStore, rep, src, srcSize, 0 /*optLevel*/, ZSTD_dictMatchState);
+}
+
+size_t ZSTD_compressBlock_btultra_dictMatchState(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        const void* src, size_t srcSize)
+{
+    return ZSTD_compressBlock_opt_generic(ms, seqStore, rep, src, srcSize, 2 /*optLevel*/, ZSTD_dictMatchState);
+}
+
+size_t ZSTD_compressBlock_btopt_extDict(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        const void* src, size_t srcSize)
+{
+    return ZSTD_compressBlock_opt_generic(ms, seqStore, rep, src, srcSize, 0 /*optLevel*/, ZSTD_extDict);
+}
+
+size_t ZSTD_compressBlock_btultra_extDict(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        const void* src, size_t srcSize)
+{
+    return ZSTD_compressBlock_opt_generic(ms, seqStore, rep, src, srcSize, 2 /*optLevel*/, ZSTD_extDict);
+}
+
+/* note : no btultra2 variant for extDict nor dictMatchState,
+ * because btultra2 is not meant to work with dictionaries
+ * and is only specific for the first block (no prefix) */
diff --git a/lib/zstd/compress/zstd_opt.h b/lib/zstd/compress/zstd_opt.h
new file mode 100644
index 000000000000..22b862858ba7
--- /dev/null
+++ b/lib/zstd/compress/zstd_opt.h
@@ -0,0 +1,50 @@
+/*
+ * Copyright (c) Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+#ifndef ZSTD_OPT_H
+#define ZSTD_OPT_H
+
+
+#include "zstd_compress_internal.h"
+
+/* used in ZSTD_loadDictionaryContent() */
+void ZSTD_updateTree(ZSTD_matchState_t* ms, const BYTE* ip, const BYTE* iend);
+
+size_t ZSTD_compressBlock_btopt(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize);
+size_t ZSTD_compressBlock_btultra(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize);
+size_t ZSTD_compressBlock_btultra2(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize);
+
+
+size_t ZSTD_compressBlock_btopt_dictMatchState(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize);
+size_t ZSTD_compressBlock_btultra_dictMatchState(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize);
+
+size_t ZSTD_compressBlock_btopt_extDict(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize);
+size_t ZSTD_compressBlock_btultra_extDict(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize);
+
+        /* note : no btultra2 variant for extDict nor dictMatchState,
+         * because btultra2 is not meant to work with dictionaries
+         * and is only specific for the first block (no prefix) */
+
+
+#endif /* ZSTD_OPT_H */
diff --git a/lib/zstd/decompress.c b/lib/zstd/decompress.c
deleted file mode 100644
index 66cd487a326a..000000000000
--- a/lib/zstd/decompress.c
+++ /dev/null
@@ -1,2531 +0,0 @@
-/**
- * Copyright (c) 2016-present, Yann Collet, Facebook, Inc.
- * All rights reserved.
- *
- * This source code is licensed under the BSD-style license found in the
- * LICENSE file in the root directory of https://github.com/facebook/zstd.
- * An additional grant of patent rights can be found in the PATENTS file in the
- * same directory.
- *
- * 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. This program is dual-licensed; you may select
- * either version 2 of the GNU General Public License ("GPL") or BSD license
- * ("BSD").
- */
-
-/* ***************************************************************
-*  Tuning parameters
-*****************************************************************/
-/*!
-*  MAXWINDOWSIZE_DEFAULT :
-*  maximum window size accepted by DStream, by default.
-*  Frames requiring more memory will be rejected.
-*/
-#ifndef ZSTD_MAXWINDOWSIZE_DEFAULT
-#define ZSTD_MAXWINDOWSIZE_DEFAULT ((1 << ZSTD_WINDOWLOG_MAX) + 1) /* defined within zstd.h */
-#endif
-
-/*-*******************************************************
-*  Dependencies
-*********************************************************/
-#include "fse.h"
-#include "huf.h"
-#include "mem.h" /* low level memory routines */
-#include "zstd_internal.h"
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/string.h> /* memcpy, memmove, memset */
-
-#define ZSTD_PREFETCH(ptr) __builtin_prefetch(ptr, 0, 0)
-
-/*-*************************************
-*  Macros
-***************************************/
-#define ZSTD_isError ERR_isError /* for inlining */
-#define FSE_isError ERR_isError
-#define HUF_isError ERR_isError
-
-/*_*******************************************************
-*  Memory operations
-**********************************************************/
-static void ZSTD_copy4(void *dst, const void *src) { memcpy(dst, src, 4); }
-
-/*-*************************************************************
-*   Context management
-***************************************************************/
-typedef enum {
-	ZSTDds_getFrameHeaderSize,
-	ZSTDds_decodeFrameHeader,
-	ZSTDds_decodeBlockHeader,
-	ZSTDds_decompressBlock,
-	ZSTDds_decompressLastBlock,
-	ZSTDds_checkChecksum,
-	ZSTDds_decodeSkippableHeader,
-	ZSTDds_skipFrame
-} ZSTD_dStage;
-
-typedef struct {
-	FSE_DTable LLTable[FSE_DTABLE_SIZE_U32(LLFSELog)];
-	FSE_DTable OFTable[FSE_DTABLE_SIZE_U32(OffFSELog)];
-	FSE_DTable MLTable[FSE_DTABLE_SIZE_U32(MLFSELog)];
-	HUF_DTable hufTable[HUF_DTABLE_SIZE(HufLog)]; /* can accommodate HUF_decompress4X */
-	U64 workspace[HUF_DECOMPRESS_WORKSPACE_SIZE_U32 / 2];
-	U32 rep[ZSTD_REP_NUM];
-} ZSTD_entropyTables_t;
-
-struct ZSTD_DCtx_s {
-	const FSE_DTable *LLTptr;
-	const FSE_DTable *MLTptr;
-	const FSE_DTable *OFTptr;
-	const HUF_DTable *HUFptr;
-	ZSTD_entropyTables_t entropy;
-	const void *previousDstEnd; /* detect continuity */
-	const void *base;	   /* start of curr segment */
-	const void *vBase;	  /* virtual start of previous segment if it was just before curr one */
-	const void *dictEnd;	/* end of previous segment */
-	size_t expected;
-	ZSTD_frameParams fParams;
-	blockType_e bType; /* used in ZSTD_decompressContinue(), to transfer blockType between header decoding and block decoding stages */
-	ZSTD_dStage stage;
-	U32 litEntropy;
-	U32 fseEntropy;
-	struct xxh64_state xxhState;
-	size_t headerSize;
-	U32 dictID;
-	const BYTE *litPtr;
-	ZSTD_customMem customMem;
-	size_t litSize;
-	size_t rleSize;
-	BYTE litBuffer[ZSTD_BLOCKSIZE_ABSOLUTEMAX + WILDCOPY_OVERLENGTH];
-	BYTE headerBuffer[ZSTD_FRAMEHEADERSIZE_MAX];
-}; /* typedef'd to ZSTD_DCtx within "zstd.h" */
-
-size_t ZSTD_DCtxWorkspaceBound(void) { return ZSTD_ALIGN(sizeof(ZSTD_stack)) + ZSTD_ALIGN(sizeof(ZSTD_DCtx)); }
-
-size_t ZSTD_decompressBegin(ZSTD_DCtx *dctx)
-{
-	dctx->expected = ZSTD_frameHeaderSize_prefix;
-	dctx->stage = ZSTDds_getFrameHeaderSize;
-	dctx->previousDstEnd = NULL;
-	dctx->base = NULL;
-	dctx->vBase = NULL;
-	dctx->dictEnd = NULL;
-	dctx->entropy.hufTable[0] = (HUF_DTable)((HufLog)*0x1000001); /* cover both little and big endian */
-	dctx->litEntropy = dctx->fseEntropy = 0;
-	dctx->dictID = 0;
-	ZSTD_STATIC_ASSERT(sizeof(dctx->entropy.rep) == sizeof(repStartValue));
-	memcpy(dctx->entropy.rep, repStartValue, sizeof(repStartValue)); /* initial repcodes */
-	dctx->LLTptr = dctx->entropy.LLTable;
-	dctx->MLTptr = dctx->entropy.MLTable;
-	dctx->OFTptr = dctx->entropy.OFTable;
-	dctx->HUFptr = dctx->entropy.hufTable;
-	return 0;
-}
-
-ZSTD_DCtx *ZSTD_createDCtx_advanced(ZSTD_customMem customMem)
-{
-	ZSTD_DCtx *dctx;
-
-	if (!customMem.customAlloc || !customMem.customFree)
-		return NULL;
-
-	dctx = (ZSTD_DCtx *)ZSTD_malloc(sizeof(ZSTD_DCtx), customMem);
-	if (!dctx)
-		return NULL;
-	memcpy(&dctx->customMem, &customMem, sizeof(customMem));
-	ZSTD_decompressBegin(dctx);
-	return dctx;
-}
-
-ZSTD_DCtx *ZSTD_initDCtx(void *workspace, size_t workspaceSize)
-{
-	ZSTD_customMem const stackMem = ZSTD_initStack(workspace, workspaceSize);
-	return ZSTD_createDCtx_advanced(stackMem);
-}
-
-size_t ZSTD_freeDCtx(ZSTD_DCtx *dctx)
-{
-	if (dctx == NULL)
-		return 0; /* support free on NULL */
-	ZSTD_free(dctx, dctx->customMem);
-	return 0; /* reserved as a potential error code in the future */
-}
-
-void ZSTD_copyDCtx(ZSTD_DCtx *dstDCtx, const ZSTD_DCtx *srcDCtx)
-{
-	size_t const workSpaceSize = (ZSTD_BLOCKSIZE_ABSOLUTEMAX + WILDCOPY_OVERLENGTH) + ZSTD_frameHeaderSize_max;
-	memcpy(dstDCtx, srcDCtx, sizeof(ZSTD_DCtx) - workSpaceSize); /* no need to copy workspace */
-}
-
-static void ZSTD_refDDict(ZSTD_DCtx *dstDCtx, const ZSTD_DDict *ddict);
-
-/*-*************************************************************
-*   Decompression section
-***************************************************************/
-
-/*! ZSTD_isFrame() :
- *  Tells if the content of `buffer` starts with a valid Frame Identifier.
- *  Note : Frame Identifier is 4 bytes. If `size < 4`, @return will always be 0.
- *  Note 2 : Legacy Frame Identifiers are considered valid only if Legacy Support is enabled.
- *  Note 3 : Skippable Frame Identifiers are considered valid. */
-unsigned ZSTD_isFrame(const void *buffer, size_t size)
-{
-	if (size < 4)
-		return 0;
-	{
-		U32 const magic = ZSTD_readLE32(buffer);
-		if (magic == ZSTD_MAGICNUMBER)
-			return 1;
-		if ((magic & 0xFFFFFFF0U) == ZSTD_MAGIC_SKIPPABLE_START)
-			return 1;
-	}
-	return 0;
-}
-
-/** ZSTD_frameHeaderSize() :
-*   srcSize must be >= ZSTD_frameHeaderSize_prefix.
-*   @return : size of the Frame Header */
-static size_t ZSTD_frameHeaderSize(const void *src, size_t srcSize)
-{
-	if (srcSize < ZSTD_frameHeaderSize_prefix)
-		return ERROR(srcSize_wrong);
-	{
-		BYTE const fhd = ((const BYTE *)src)[4];
-		U32 const dictID = fhd & 3;
-		U32 const singleSegment = (fhd >> 5) & 1;
-		U32 const fcsId = fhd >> 6;
-		return ZSTD_frameHeaderSize_prefix + !singleSegment + ZSTD_did_fieldSize[dictID] + ZSTD_fcs_fieldSize[fcsId] + (singleSegment && !fcsId);
-	}
-}
-
-/** ZSTD_getFrameParams() :
-*   decode Frame Header, or require larger `srcSize`.
-*   @return : 0, `fparamsPtr` is correctly filled,
-*            >0, `srcSize` is too small, result is expected `srcSize`,
-*             or an error code, which can be tested using ZSTD_isError() */
-size_t ZSTD_getFrameParams(ZSTD_frameParams *fparamsPtr, const void *src, size_t srcSize)
-{
-	const BYTE *ip = (const BYTE *)src;
-
-	if (srcSize < ZSTD_frameHeaderSize_prefix)
-		return ZSTD_frameHeaderSize_prefix;
-	if (ZSTD_readLE32(src) != ZSTD_MAGICNUMBER) {
-		if ((ZSTD_readLE32(src) & 0xFFFFFFF0U) == ZSTD_MAGIC_SKIPPABLE_START) {
-			if (srcSize < ZSTD_skippableHeaderSize)
-				return ZSTD_skippableHeaderSize; /* magic number + skippable frame length */
-			memset(fparamsPtr, 0, sizeof(*fparamsPtr));
-			fparamsPtr->frameContentSize = ZSTD_readLE32((const char *)src + 4);
-			fparamsPtr->windowSize = 0; /* windowSize==0 means a frame is skippable */
-			return 0;
-		}
-		return ERROR(prefix_unknown);
-	}
-
-	/* ensure there is enough `srcSize` to fully read/decode frame header */
-	{
-		size_t const fhsize = ZSTD_frameHeaderSize(src, srcSize);
-		if (srcSize < fhsize)
-			return fhsize;
-	}
-
-	{
-		BYTE const fhdByte = ip[4];
-		size_t pos = 5;
-		U32 const dictIDSizeCode = fhdByte & 3;
-		U32 const checksumFlag = (fhdByte >> 2) & 1;
-		U32 const singleSegment = (fhdByte >> 5) & 1;
-		U32 const fcsID = fhdByte >> 6;
-		U32 const windowSizeMax = 1U << ZSTD_WINDOWLOG_MAX;
-		U32 windowSize = 0;
-		U32 dictID = 0;
-		U64 frameContentSize = 0;
-		if ((fhdByte & 0x08) != 0)
-			return ERROR(frameParameter_unsupported); /* reserved bits, which must be zero */
-		if (!singleSegment) {
-			BYTE const wlByte = ip[pos++];
-			U32 const windowLog = (wlByte >> 3) + ZSTD_WINDOWLOG_ABSOLUTEMIN;
-			if (windowLog > ZSTD_WINDOWLOG_MAX)
-				return ERROR(frameParameter_windowTooLarge); /* avoids issue with 1 << windowLog */
-			windowSize = (1U << windowLog);
-			windowSize += (windowSize >> 3) * (wlByte & 7);
-		}
-
-		switch (dictIDSizeCode) {
-		default: /* impossible */
-		case 0: break;
-		case 1:
-			dictID = ip[pos];
-			pos++;
-			break;
-		case 2:
-			dictID = ZSTD_readLE16(ip + pos);
-			pos += 2;
-			break;
-		case 3:
-			dictID = ZSTD_readLE32(ip + pos);
-			pos += 4;
-			break;
-		}
-		switch (fcsID) {
-		default: /* impossible */
-		case 0:
-			if (singleSegment)
-				frameContentSize = ip[pos];
-			break;
-		case 1: frameContentSize = ZSTD_readLE16(ip + pos) + 256; break;
-		case 2: frameContentSize = ZSTD_readLE32(ip + pos); break;
-		case 3: frameContentSize = ZSTD_readLE64(ip + pos); break;
-		}
-		if (!windowSize)
-			windowSize = (U32)frameContentSize;
-		if (windowSize > windowSizeMax)
-			return ERROR(frameParameter_windowTooLarge);
-		fparamsPtr->frameContentSize = frameContentSize;
-		fparamsPtr->windowSize = windowSize;
-		fparamsPtr->dictID = dictID;
-		fparamsPtr->checksumFlag = checksumFlag;
-	}
-	return 0;
-}
-
-/** ZSTD_getFrameContentSize() :
-*   compatible with legacy mode
-*   @return : decompressed size of the single frame pointed to be `src` if known, otherwise
-*             - ZSTD_CONTENTSIZE_UNKNOWN if the size cannot be determined
-*             - ZSTD_CONTENTSIZE_ERROR if an error occurred (e.g. invalid magic number, srcSize too small) */
-unsigned long long ZSTD_getFrameContentSize(const void *src, size_t srcSize)
-{
-	{
-		ZSTD_frameParams fParams;
-		if (ZSTD_getFrameParams(&fParams, src, srcSize) != 0)
-			return ZSTD_CONTENTSIZE_ERROR;
-		if (fParams.windowSize == 0) {
-			/* Either skippable or empty frame, size == 0 either way */
-			return 0;
-		} else if (fParams.frameContentSize != 0) {
-			return fParams.frameContentSize;
-		} else {
-			return ZSTD_CONTENTSIZE_UNKNOWN;
-		}
-	}
-}
-
-/** ZSTD_findDecompressedSize() :
- *  compatible with legacy mode
- *  `srcSize` must be the exact length of some number of ZSTD compressed and/or
- *      skippable frames
- *  @return : decompressed size of the frames contained */
-unsigned long long ZSTD_findDecompressedSize(const void *src, size_t srcSize)
-{
-	{
-		unsigned long long totalDstSize = 0;
-		while (srcSize >= ZSTD_frameHeaderSize_prefix) {
-			const U32 magicNumber = ZSTD_readLE32(src);
-
-			if ((magicNumber & 0xFFFFFFF0U) == ZSTD_MAGIC_SKIPPABLE_START) {
-				size_t skippableSize;
-				if (srcSize < ZSTD_skippableHeaderSize)
-					return ERROR(srcSize_wrong);
-				skippableSize = ZSTD_readLE32((const BYTE *)src + 4) + ZSTD_skippableHeaderSize;
-				if (srcSize < skippableSize) {
-					return ZSTD_CONTENTSIZE_ERROR;
-				}
-
-				src = (const BYTE *)src + skippableSize;
-				srcSize -= skippableSize;
-				continue;
-			}
-
-			{
-				unsigned long long const ret = ZSTD_getFrameContentSize(src, srcSize);
-				if (ret >= ZSTD_CONTENTSIZE_ERROR)
-					return ret;
-
-				/* check for overflow */
-				if (totalDstSize + ret < totalDstSize)
-					return ZSTD_CONTENTSIZE_ERROR;
-				totalDstSize += ret;
-			}
-			{
-				size_t const frameSrcSize = ZSTD_findFrameCompressedSize(src, srcSize);
-				if (ZSTD_isError(frameSrcSize)) {
-					return ZSTD_CONTENTSIZE_ERROR;
-				}
-
-				src = (const BYTE *)src + frameSrcSize;
-				srcSize -= frameSrcSize;
-			}
-		}
-
-		if (srcSize) {
-			return ZSTD_CONTENTSIZE_ERROR;
-		}
-
-		return totalDstSize;
-	}
-}
-
-/** ZSTD_decodeFrameHeader() :
-*   `headerSize` must be the size provided by ZSTD_frameHeaderSize().
-*   @return : 0 if success, or an error code, which can be tested using ZSTD_isError() */
-static size_t ZSTD_decodeFrameHeader(ZSTD_DCtx *dctx, const void *src, size_t headerSize)
-{
-	size_t const result = ZSTD_getFrameParams(&(dctx->fParams), src, headerSize);
-	if (ZSTD_isError(result))
-		return result; /* invalid header */
-	if (result > 0)
-		return ERROR(srcSize_wrong); /* headerSize too small */
-	if (dctx->fParams.dictID && (dctx->dictID != dctx->fParams.dictID))
-		return ERROR(dictionary_wrong);
-	if (dctx->fParams.checksumFlag)
-		xxh64_reset(&dctx->xxhState, 0);
-	return 0;
-}
-
-typedef struct {
-	blockType_e blockType;
-	U32 lastBlock;
-	U32 origSize;
-} blockProperties_t;
-
-/*! ZSTD_getcBlockSize() :
-*   Provides the size of compressed block from block header `src` */
-size_t ZSTD_getcBlockSize(const void *src, size_t srcSize, blockProperties_t *bpPtr)
-{
-	if (srcSize < ZSTD_blockHeaderSize)
-		return ERROR(srcSize_wrong);
-	{
-		U32 const cBlockHeader = ZSTD_readLE24(src);
-		U32 const cSize = cBlockHeader >> 3;
-		bpPtr->lastBlock = cBlockHeader & 1;
-		bpPtr->blockType = (blockType_e)((cBlockHeader >> 1) & 3);
-		bpPtr->origSize = cSize; /* only useful for RLE */
-		if (bpPtr->blockType == bt_rle)
-			return 1;
-		if (bpPtr->blockType == bt_reserved)
-			return ERROR(corruption_detected);
-		return cSize;
-	}
-}
-
-static size_t ZSTD_copyRawBlock(void *dst, size_t dstCapacity, const void *src, size_t srcSize)
-{
-	if (srcSize > dstCapacity)
-		return ERROR(dstSize_tooSmall);
-	memcpy(dst, src, srcSize);
-	return srcSize;
-}
-
-static size_t ZSTD_setRleBlock(void *dst, size_t dstCapacity, const void *src, size_t srcSize, size_t regenSize)
-{
-	if (srcSize != 1)
-		return ERROR(srcSize_wrong);
-	if (regenSize > dstCapacity)
-		return ERROR(dstSize_tooSmall);
-	memset(dst, *(const BYTE *)src, regenSize);
-	return regenSize;
-}
-
-/*! ZSTD_decodeLiteralsBlock() :
-	@return : nb of bytes read from src (< srcSize ) */
-size_t ZSTD_decodeLiteralsBlock(ZSTD_DCtx *dctx, const void *src, size_t srcSize) /* note : srcSize < BLOCKSIZE */
-{
-	if (srcSize < MIN_CBLOCK_SIZE)
-		return ERROR(corruption_detected);
-
-	{
-		const BYTE *const istart = (const BYTE *)src;
-		symbolEncodingType_e const litEncType = (symbolEncodingType_e)(istart[0] & 3);
-
-		switch (litEncType) {
-		case set_repeat:
-			if (dctx->litEntropy == 0)
-				return ERROR(dictionary_corrupted);
-			fallthrough;
-		case set_compressed:
-			if (srcSize < 5)
-				return ERROR(corruption_detected); /* srcSize >= MIN_CBLOCK_SIZE == 3; here we need up to 5 for case 3 */
-			{
-				size_t lhSize, litSize, litCSize;
-				U32 singleStream = 0;
-				U32 const lhlCode = (istart[0] >> 2) & 3;
-				U32 const lhc = ZSTD_readLE32(istart);
-				switch (lhlCode) {
-				case 0:
-				case 1:
-				default: /* note : default is impossible, since lhlCode into [0..3] */
-					/* 2 - 2 - 10 - 10 */
-					singleStream = !lhlCode;
-					lhSize = 3;
-					litSize = (lhc >> 4) & 0x3FF;
-					litCSize = (lhc >> 14) & 0x3FF;
-					break;
-				case 2:
-					/* 2 - 2 - 14 - 14 */
-					lhSize = 4;
-					litSize = (lhc >> 4) & 0x3FFF;
-					litCSize = lhc >> 18;
-					break;
-				case 3:
-					/* 2 - 2 - 18 - 18 */
-					lhSize = 5;
-					litSize = (lhc >> 4) & 0x3FFFF;
-					litCSize = (lhc >> 22) + (istart[4] << 10);
-					break;
-				}
-				if (litSize > ZSTD_BLOCKSIZE_ABSOLUTEMAX)
-					return ERROR(corruption_detected);
-				if (litCSize + lhSize > srcSize)
-					return ERROR(corruption_detected);
-
-				if (HUF_isError(
-					(litEncType == set_repeat)
-					    ? (singleStream ? HUF_decompress1X_usingDTable(dctx->litBuffer, litSize, istart + lhSize, litCSize, dctx->HUFptr)
-							    : HUF_decompress4X_usingDTable(dctx->litBuffer, litSize, istart + lhSize, litCSize, dctx->HUFptr))
-					    : (singleStream
-						   ? HUF_decompress1X2_DCtx_wksp(dctx->entropy.hufTable, dctx->litBuffer, litSize, istart + lhSize, litCSize,
-										 dctx->entropy.workspace, sizeof(dctx->entropy.workspace))
-						   : HUF_decompress4X_hufOnly_wksp(dctx->entropy.hufTable, dctx->litBuffer, litSize, istart + lhSize, litCSize,
-										   dctx->entropy.workspace, sizeof(dctx->entropy.workspace)))))
-					return ERROR(corruption_detected);
-
-				dctx->litPtr = dctx->litBuffer;
-				dctx->litSize = litSize;
-				dctx->litEntropy = 1;
-				if (litEncType == set_compressed)
-					dctx->HUFptr = dctx->entropy.hufTable;
-				memset(dctx->litBuffer + dctx->litSize, 0, WILDCOPY_OVERLENGTH);
-				return litCSize + lhSize;
-			}
-
-		case set_basic: {
-			size_t litSize, lhSize;
-			U32 const lhlCode = ((istart[0]) >> 2) & 3;
-			switch (lhlCode) {
-			case 0:
-			case 2:
-			default: /* note : default is impossible, since lhlCode into [0..3] */
-				lhSize = 1;
-				litSize = istart[0] >> 3;
-				break;
-			case 1:
-				lhSize = 2;
-				litSize = ZSTD_readLE16(istart) >> 4;
-				break;
-			case 3:
-				lhSize = 3;
-				litSize = ZSTD_readLE24(istart) >> 4;
-				break;
-			}
-
-			if (lhSize + litSize + WILDCOPY_OVERLENGTH > srcSize) { /* risk reading beyond src buffer with wildcopy */
-				if (litSize + lhSize > srcSize)
-					return ERROR(corruption_detected);
-				memcpy(dctx->litBuffer, istart + lhSize, litSize);
-				dctx->litPtr = dctx->litBuffer;
-				dctx->litSize = litSize;
-				memset(dctx->litBuffer + dctx->litSize, 0, WILDCOPY_OVERLENGTH);
-				return lhSize + litSize;
-			}
-			/* direct reference into compressed stream */
-			dctx->litPtr = istart + lhSize;
-			dctx->litSize = litSize;
-			return lhSize + litSize;
-		}
-
-		case set_rle: {
-			U32 const lhlCode = ((istart[0]) >> 2) & 3;
-			size_t litSize, lhSize;
-			switch (lhlCode) {
-			case 0:
-			case 2:
-			default: /* note : default is impossible, since lhlCode into [0..3] */
-				lhSize = 1;
-				litSize = istart[0] >> 3;
-				break;
-			case 1:
-				lhSize = 2;
-				litSize = ZSTD_readLE16(istart) >> 4;
-				break;
-			case 3:
-				lhSize = 3;
-				litSize = ZSTD_readLE24(istart) >> 4;
-				if (srcSize < 4)
-					return ERROR(corruption_detected); /* srcSize >= MIN_CBLOCK_SIZE == 3; here we need lhSize+1 = 4 */
-				break;
-			}
-			if (litSize > ZSTD_BLOCKSIZE_ABSOLUTEMAX)
-				return ERROR(corruption_detected);
-			memset(dctx->litBuffer, istart[lhSize], litSize + WILDCOPY_OVERLENGTH);
-			dctx->litPtr = dctx->litBuffer;
-			dctx->litSize = litSize;
-			return lhSize + 1;
-		}
-		default:
-			return ERROR(corruption_detected); /* impossible */
-		}
-	}
-}
-
-typedef union {
-	FSE_decode_t realData;
-	U32 alignedBy4;
-} FSE_decode_t4;
-
-static const FSE_decode_t4 LL_defaultDTable[(1 << LL_DEFAULTNORMLOG) + 1] = {
-    {{LL_DEFAULTNORMLOG, 1, 1}}, /* header : tableLog, fastMode, fastMode */
-    {{0, 0, 4}},		 /* 0 : base, symbol, bits */
-    {{16, 0, 4}},
-    {{32, 1, 5}},
-    {{0, 3, 5}},
-    {{0, 4, 5}},
-    {{0, 6, 5}},
-    {{0, 7, 5}},
-    {{0, 9, 5}},
-    {{0, 10, 5}},
-    {{0, 12, 5}},
-    {{0, 14, 6}},
-    {{0, 16, 5}},
-    {{0, 18, 5}},
-    {{0, 19, 5}},
-    {{0, 21, 5}},
-    {{0, 22, 5}},
-    {{0, 24, 5}},
-    {{32, 25, 5}},
-    {{0, 26, 5}},
-    {{0, 27, 6}},
-    {{0, 29, 6}},
-    {{0, 31, 6}},
-    {{32, 0, 4}},
-    {{0, 1, 4}},
-    {{0, 2, 5}},
-    {{32, 4, 5}},
-    {{0, 5, 5}},
-    {{32, 7, 5}},
-    {{0, 8, 5}},
-    {{32, 10, 5}},
-    {{0, 11, 5}},
-    {{0, 13, 6}},
-    {{32, 16, 5}},
-    {{0, 17, 5}},
-    {{32, 19, 5}},
-    {{0, 20, 5}},
-    {{32, 22, 5}},
-    {{0, 23, 5}},
-    {{0, 25, 4}},
-    {{16, 25, 4}},
-    {{32, 26, 5}},
-    {{0, 28, 6}},
-    {{0, 30, 6}},
-    {{48, 0, 4}},
-    {{16, 1, 4}},
-    {{32, 2, 5}},
-    {{32, 3, 5}},
-    {{32, 5, 5}},
-    {{32, 6, 5}},
-    {{32, 8, 5}},
-    {{32, 9, 5}},
-    {{32, 11, 5}},
-    {{32, 12, 5}},
-    {{0, 15, 6}},
-    {{32, 17, 5}},
-    {{32, 18, 5}},
-    {{32, 20, 5}},
-    {{32, 21, 5}},
-    {{32, 23, 5}},
-    {{32, 24, 5}},
-    {{0, 35, 6}},
-    {{0, 34, 6}},
-    {{0, 33, 6}},
-    {{0, 32, 6}},
-}; /* LL_defaultDTable */
-
-static const FSE_decode_t4 ML_defaultDTable[(1 << ML_DEFAULTNORMLOG) + 1] = {
-    {{ML_DEFAULTNORMLOG, 1, 1}}, /* header : tableLog, fastMode, fastMode */
-    {{0, 0, 6}},		 /* 0 : base, symbol, bits */
-    {{0, 1, 4}},
-    {{32, 2, 5}},
-    {{0, 3, 5}},
-    {{0, 5, 5}},
-    {{0, 6, 5}},
-    {{0, 8, 5}},
-    {{0, 10, 6}},
-    {{0, 13, 6}},
-    {{0, 16, 6}},
-    {{0, 19, 6}},
-    {{0, 22, 6}},
-    {{0, 25, 6}},
-    {{0, 28, 6}},
-    {{0, 31, 6}},
-    {{0, 33, 6}},
-    {{0, 35, 6}},
-    {{0, 37, 6}},
-    {{0, 39, 6}},
-    {{0, 41, 6}},
-    {{0, 43, 6}},
-    {{0, 45, 6}},
-    {{16, 1, 4}},
-    {{0, 2, 4}},
-    {{32, 3, 5}},
-    {{0, 4, 5}},
-    {{32, 6, 5}},
-    {{0, 7, 5}},
-    {{0, 9, 6}},
-    {{0, 12, 6}},
-    {{0, 15, 6}},
-    {{0, 18, 6}},
-    {{0, 21, 6}},
-    {{0, 24, 6}},
-    {{0, 27, 6}},
-    {{0, 30, 6}},
-    {{0, 32, 6}},
-    {{0, 34, 6}},
-    {{0, 36, 6}},
-    {{0, 38, 6}},
-    {{0, 40, 6}},
-    {{0, 42, 6}},
-    {{0, 44, 6}},
-    {{32, 1, 4}},
-    {{48, 1, 4}},
-    {{16, 2, 4}},
-    {{32, 4, 5}},
-    {{32, 5, 5}},
-    {{32, 7, 5}},
-    {{32, 8, 5}},
-    {{0, 11, 6}},
-    {{0, 14, 6}},
-    {{0, 17, 6}},
-    {{0, 20, 6}},
-    {{0, 23, 6}},
-    {{0, 26, 6}},
-    {{0, 29, 6}},
-    {{0, 52, 6}},
-    {{0, 51, 6}},
-    {{0, 50, 6}},
-    {{0, 49, 6}},
-    {{0, 48, 6}},
-    {{0, 47, 6}},
-    {{0, 46, 6}},
-}; /* ML_defaultDTable */
-
-static const FSE_decode_t4 OF_defaultDTable[(1 << OF_DEFAULTNORMLOG) + 1] = {
-    {{OF_DEFAULTNORMLOG, 1, 1}}, /* header : tableLog, fastMode, fastMode */
-    {{0, 0, 5}},		 /* 0 : base, symbol, bits */
-    {{0, 6, 4}},
-    {{0, 9, 5}},
-    {{0, 15, 5}},
-    {{0, 21, 5}},
-    {{0, 3, 5}},
-    {{0, 7, 4}},
-    {{0, 12, 5}},
-    {{0, 18, 5}},
-    {{0, 23, 5}},
-    {{0, 5, 5}},
-    {{0, 8, 4}},
-    {{0, 14, 5}},
-    {{0, 20, 5}},
-    {{0, 2, 5}},
-    {{16, 7, 4}},
-    {{0, 11, 5}},
-    {{0, 17, 5}},
-    {{0, 22, 5}},
-    {{0, 4, 5}},
-    {{16, 8, 4}},
-    {{0, 13, 5}},
-    {{0, 19, 5}},
-    {{0, 1, 5}},
-    {{16, 6, 4}},
-    {{0, 10, 5}},
-    {{0, 16, 5}},
-    {{0, 28, 5}},
-    {{0, 27, 5}},
-    {{0, 26, 5}},
-    {{0, 25, 5}},
-    {{0, 24, 5}},
-}; /* OF_defaultDTable */
-
-/*! ZSTD_buildSeqTable() :
-	@return : nb bytes read from src,
-			  or an error code if it fails, testable with ZSTD_isError()
-*/
-static size_t ZSTD_buildSeqTable(FSE_DTable *DTableSpace, const FSE_DTable **DTablePtr, symbolEncodingType_e type, U32 max, U32 maxLog, const void *src,
-				 size_t srcSize, const FSE_decode_t4 *defaultTable, U32 flagRepeatTable, void *workspace, size_t workspaceSize)
-{
-	const void *const tmpPtr = defaultTable; /* bypass strict aliasing */
-	switch (type) {
-	case set_rle:
-		if (!srcSize)
-			return ERROR(srcSize_wrong);
-		if ((*(const BYTE *)src) > max)
-			return ERROR(corruption_detected);
-		FSE_buildDTable_rle(DTableSpace, *(const BYTE *)src);
-		*DTablePtr = DTableSpace;
-		return 1;
-	case set_basic: *DTablePtr = (const FSE_DTable *)tmpPtr; return 0;
-	case set_repeat:
-		if (!flagRepeatTable)
-			return ERROR(corruption_detected);
-		return 0;
-	default: /* impossible */
-	case set_compressed: {
-		U32 tableLog;
-		S16 *norm = (S16 *)workspace;
-		size_t const spaceUsed32 = ALIGN(sizeof(S16) * (MaxSeq + 1), sizeof(U32)) >> 2;
-
-		if ((spaceUsed32 << 2) > workspaceSize)
-			return ERROR(GENERIC);
-		workspace = (U32 *)workspace + spaceUsed32;
-		workspaceSize -= (spaceUsed32 << 2);
-		{
-			size_t const headerSize = FSE_readNCount(norm, &max, &tableLog, src, srcSize);
-			if (FSE_isError(headerSize))
-				return ERROR(corruption_detected);
-			if (tableLog > maxLog)
-				return ERROR(corruption_detected);
-			FSE_buildDTable_wksp(DTableSpace, norm, max, tableLog, workspace, workspaceSize);
-			*DTablePtr = DTableSpace;
-			return headerSize;
-		}
-	}
-	}
-}
-
-size_t ZSTD_decodeSeqHeaders(ZSTD_DCtx *dctx, int *nbSeqPtr, const void *src, size_t srcSize)
-{
-	const BYTE *const istart = (const BYTE *const)src;
-	const BYTE *const iend = istart + srcSize;
-	const BYTE *ip = istart;
-
-	/* check */
-	if (srcSize < MIN_SEQUENCES_SIZE)
-		return ERROR(srcSize_wrong);
-
-	/* SeqHead */
-	{
-		int nbSeq = *ip++;
-		if (!nbSeq) {
-			*nbSeqPtr = 0;
-			return 1;
-		}
-		if (nbSeq > 0x7F) {
-			if (nbSeq == 0xFF) {
-				if (ip + 2 > iend)
-					return ERROR(srcSize_wrong);
-				nbSeq = ZSTD_readLE16(ip) + LONGNBSEQ, ip += 2;
-			} else {
-				if (ip >= iend)
-					return ERROR(srcSize_wrong);
-				nbSeq = ((nbSeq - 0x80) << 8) + *ip++;
-			}
-		}
-		*nbSeqPtr = nbSeq;
-	}
-
-	/* FSE table descriptors */
-	if (ip + 4 > iend)
-		return ERROR(srcSize_wrong); /* minimum possible size */
-	{
-		symbolEncodingType_e const LLtype = (symbolEncodingType_e)(*ip >> 6);
-		symbolEncodingType_e const OFtype = (symbolEncodingType_e)((*ip >> 4) & 3);
-		symbolEncodingType_e const MLtype = (symbolEncodingType_e)((*ip >> 2) & 3);
-		ip++;
-
-		/* Build DTables */
-		{
-			size_t const llhSize = ZSTD_buildSeqTable(dctx->entropy.LLTable, &dctx->LLTptr, LLtype, MaxLL, LLFSELog, ip, iend - ip,
-								  LL_defaultDTable, dctx->fseEntropy, dctx->entropy.workspace, sizeof(dctx->entropy.workspace));
-			if (ZSTD_isError(llhSize))
-				return ERROR(corruption_detected);
-			ip += llhSize;
-		}
-		{
-			size_t const ofhSize = ZSTD_buildSeqTable(dctx->entropy.OFTable, &dctx->OFTptr, OFtype, MaxOff, OffFSELog, ip, iend - ip,
-								  OF_defaultDTable, dctx->fseEntropy, dctx->entropy.workspace, sizeof(dctx->entropy.workspace));
-			if (ZSTD_isError(ofhSize))
-				return ERROR(corruption_detected);
-			ip += ofhSize;
-		}
-		{
-			size_t const mlhSize = ZSTD_buildSeqTable(dctx->entropy.MLTable, &dctx->MLTptr, MLtype, MaxML, MLFSELog, ip, iend - ip,
-								  ML_defaultDTable, dctx->fseEntropy, dctx->entropy.workspace, sizeof(dctx->entropy.workspace));
-			if (ZSTD_isError(mlhSize))
-				return ERROR(corruption_detected);
-			ip += mlhSize;
-		}
-	}
-
-	return ip - istart;
-}
-
-typedef struct {
-	size_t litLength;
-	size_t matchLength;
-	size_t offset;
-	const BYTE *match;
-} seq_t;
-
-typedef struct {
-	BIT_DStream_t DStream;
-	FSE_DState_t stateLL;
-	FSE_DState_t stateOffb;
-	FSE_DState_t stateML;
-	size_t prevOffset[ZSTD_REP_NUM];
-	const BYTE *base;
-	size_t pos;
-	uPtrDiff gotoDict;
-} seqState_t;
-
-FORCE_NOINLINE
-size_t ZSTD_execSequenceLast7(BYTE *op, BYTE *const oend, seq_t sequence, const BYTE **litPtr, const BYTE *const litLimit, const BYTE *const base,
-			      const BYTE *const vBase, const BYTE *const dictEnd)
-{
-	BYTE *const oLitEnd = op + sequence.litLength;
-	size_t const sequenceLength = sequence.litLength + sequence.matchLength;
-	BYTE *const oMatchEnd = op + sequenceLength; /* risk : address space overflow (32-bits) */
-	BYTE *const oend_w = oend - WILDCOPY_OVERLENGTH;
-	const BYTE *const iLitEnd = *litPtr + sequence.litLength;
-	const BYTE *match = oLitEnd - sequence.offset;
-
-	/* check */
-	if (oMatchEnd > oend)
-		return ERROR(dstSize_tooSmall); /* last match must start at a minimum distance of WILDCOPY_OVERLENGTH from oend */
-	if (iLitEnd > litLimit)
-		return ERROR(corruption_detected); /* over-read beyond lit buffer */
-	if (oLitEnd <= oend_w)
-		return ERROR(GENERIC); /* Precondition */
-
-	/* copy literals */
-	if (op < oend_w) {
-		ZSTD_wildcopy(op, *litPtr, oend_w - op);
-		*litPtr += oend_w - op;
-		op = oend_w;
-	}
-	while (op < oLitEnd)
-		*op++ = *(*litPtr)++;
-
-	/* copy Match */
-	if (sequence.offset > (size_t)(oLitEnd - base)) {
-		/* offset beyond prefix */
-		if (sequence.offset > (size_t)(oLitEnd - vBase))
-			return ERROR(corruption_detected);
-		match = dictEnd - (base - match);
-		if (match + sequence.matchLength <= dictEnd) {
-			memmove(oLitEnd, match, sequence.matchLength);
-			return sequenceLength;
-		}
-		/* span extDict & currPrefixSegment */
-		{
-			size_t const length1 = dictEnd - match;
-			memmove(oLitEnd, match, length1);
-			op = oLitEnd + length1;
-			sequence.matchLength -= length1;
-			match = base;
-		}
-	}
-	while (op < oMatchEnd)
-		*op++ = *match++;
-	return sequenceLength;
-}
-
-static seq_t ZSTD_decodeSequence(seqState_t *seqState)
-{
-	seq_t seq;
-
-	U32 const llCode = FSE_peekSymbol(&seqState->stateLL);
-	U32 const mlCode = FSE_peekSymbol(&seqState->stateML);
-	U32 const ofCode = FSE_peekSymbol(&seqState->stateOffb); /* <= maxOff, by table construction */
-
-	U32 const llBits = LL_bits[llCode];
-	U32 const mlBits = ML_bits[mlCode];
-	U32 const ofBits = ofCode;
-	U32 const totalBits = llBits + mlBits + ofBits;
-
-	static const U32 LL_base[MaxLL + 1] = {0,  1,  2,  3,  4,  5,  6,  7,  8,    9,     10,    11,    12,    13,     14,     15,     16,     18,
-					       20, 22, 24, 28, 32, 40, 48, 64, 0x80, 0x100, 0x200, 0x400, 0x800, 0x1000, 0x2000, 0x4000, 0x8000, 0x10000};
-
-	static const U32 ML_base[MaxML + 1] = {3,  4,  5,  6,  7,  8,  9,  10,   11,    12,    13,    14,    15,     16,     17,     18,     19,     20,
-					       21, 22, 23, 24, 25, 26, 27, 28,   29,    30,    31,    32,    33,     34,     35,     37,     39,     41,
-					       43, 47, 51, 59, 67, 83, 99, 0x83, 0x103, 0x203, 0x403, 0x803, 0x1003, 0x2003, 0x4003, 0x8003, 0x10003};
-
-	static const U32 OF_base[MaxOff + 1] = {0,       1,	1,	5,	0xD,      0x1D,      0x3D,      0x7D,      0xFD,     0x1FD,
-						0x3FD,   0x7FD,    0xFFD,    0x1FFD,   0x3FFD,   0x7FFD,    0xFFFD,    0x1FFFD,   0x3FFFD,  0x7FFFD,
-						0xFFFFD, 0x1FFFFD, 0x3FFFFD, 0x7FFFFD, 0xFFFFFD, 0x1FFFFFD, 0x3FFFFFD, 0x7FFFFFD, 0xFFFFFFD};
-
-	/* sequence */
-	{
-		size_t offset;
-		if (!ofCode)
-			offset = 0;
-		else {
-			offset = OF_base[ofCode] + BIT_readBitsFast(&seqState->DStream, ofBits); /* <=  (ZSTD_WINDOWLOG_MAX-1) bits */
-			if (ZSTD_32bits())
-				BIT_reloadDStream(&seqState->DStream);
-		}
-
-		if (ofCode <= 1) {
-			offset += (llCode == 0);
-			if (offset) {
-				size_t temp = (offset == 3) ? seqState->prevOffset[0] - 1 : seqState->prevOffset[offset];
-				temp += !temp; /* 0 is not valid; input is corrupted; force offset to 1 */
-				if (offset != 1)
-					seqState->prevOffset[2] = seqState->prevOffset[1];
-				seqState->prevOffset[1] = seqState->prevOffset[0];
-				seqState->prevOffset[0] = offset = temp;
-			} else {
-				offset = seqState->prevOffset[0];
-			}
-		} else {
-			seqState->prevOffset[2] = seqState->prevOffset[1];
-			seqState->prevOffset[1] = seqState->prevOffset[0];
-			seqState->prevOffset[0] = offset;
-		}
-		seq.offset = offset;
-	}
-
-	seq.matchLength = ML_base[mlCode] + ((mlCode > 31) ? BIT_readBitsFast(&seqState->DStream, mlBits) : 0); /* <=  16 bits */
-	if (ZSTD_32bits() && (mlBits + llBits > 24))
-		BIT_reloadDStream(&seqState->DStream);
-
-	seq.litLength = LL_base[llCode] + ((llCode > 15) ? BIT_readBitsFast(&seqState->DStream, llBits) : 0); /* <=  16 bits */
-	if (ZSTD_32bits() || (totalBits > 64 - 7 - (LLFSELog + MLFSELog + OffFSELog)))
-		BIT_reloadDStream(&seqState->DStream);
-
-	/* ANS state update */
-	FSE_updateState(&seqState->stateLL, &seqState->DStream); /* <=  9 bits */
-	FSE_updateState(&seqState->stateML, &seqState->DStream); /* <=  9 bits */
-	if (ZSTD_32bits())
-		BIT_reloadDStream(&seqState->DStream);		   /* <= 18 bits */
-	FSE_updateState(&seqState->stateOffb, &seqState->DStream); /* <=  8 bits */
-
-	seq.match = NULL;
-
-	return seq;
-}
-
-FORCE_INLINE
-size_t ZSTD_execSequence(BYTE *op, BYTE *const oend, seq_t sequence, const BYTE **litPtr, const BYTE *const litLimit, const BYTE *const base,
-			 const BYTE *const vBase, const BYTE *const dictEnd)
-{
-	BYTE *const oLitEnd = op + sequence.litLength;
-	size_t const sequenceLength = sequence.litLength + sequence.matchLength;
-	BYTE *const oMatchEnd = op + sequenceLength; /* risk : address space overflow (32-bits) */
-	BYTE *const oend_w = oend - WILDCOPY_OVERLENGTH;
-	const BYTE *const iLitEnd = *litPtr + sequence.litLength;
-	const BYTE *match = oLitEnd - sequence.offset;
-
-	/* check */
-	if (oMatchEnd > oend)
-		return ERROR(dstSize_tooSmall); /* last match must start at a minimum distance of WILDCOPY_OVERLENGTH from oend */
-	if (iLitEnd > litLimit)
-		return ERROR(corruption_detected); /* over-read beyond lit buffer */
-	if (oLitEnd > oend_w)
-		return ZSTD_execSequenceLast7(op, oend, sequence, litPtr, litLimit, base, vBase, dictEnd);
-
-	/* copy Literals */
-	ZSTD_copy8(op, *litPtr);
-	if (sequence.litLength > 8)
-		ZSTD_wildcopy(op + 8, (*litPtr) + 8,
-			      sequence.litLength - 8); /* note : since oLitEnd <= oend-WILDCOPY_OVERLENGTH, no risk of overwrite beyond oend */
-	op = oLitEnd;
-	*litPtr = iLitEnd; /* update for next sequence */
-
-	/* copy Match */
-	if (sequence.offset > (size_t)(oLitEnd - base)) {
-		/* offset beyond prefix */
-		if (sequence.offset > (size_t)(oLitEnd - vBase))
-			return ERROR(corruption_detected);
-		match = dictEnd + (match - base);
-		if (match + sequence.matchLength <= dictEnd) {
-			memmove(oLitEnd, match, sequence.matchLength);
-			return sequenceLength;
-		}
-		/* span extDict & currPrefixSegment */
-		{
-			size_t const length1 = dictEnd - match;
-			memmove(oLitEnd, match, length1);
-			op = oLitEnd + length1;
-			sequence.matchLength -= length1;
-			match = base;
-			if (op > oend_w || sequence.matchLength < MINMATCH) {
-				U32 i;
-				for (i = 0; i < sequence.matchLength; ++i)
-					op[i] = match[i];
-				return sequenceLength;
-			}
-		}
-	}
-	/* Requirement: op <= oend_w && sequence.matchLength >= MINMATCH */
-
-	/* match within prefix */
-	if (sequence.offset < 8) {
-		/* close range match, overlap */
-		static const U32 dec32table[] = {0, 1, 2, 1, 4, 4, 4, 4};   /* added */
-		static const int dec64table[] = {8, 8, 8, 7, 8, 9, 10, 11}; /* subtracted */
-		int const sub2 = dec64table[sequence.offset];
-		op[0] = match[0];
-		op[1] = match[1];
-		op[2] = match[2];
-		op[3] = match[3];
-		match += dec32table[sequence.offset];
-		ZSTD_copy4(op + 4, match);
-		match -= sub2;
-	} else {
-		ZSTD_copy8(op, match);
-	}
-	op += 8;
-	match += 8;
-
-	if (oMatchEnd > oend - (16 - MINMATCH)) {
-		if (op < oend_w) {
-			ZSTD_wildcopy(op, match, oend_w - op);
-			match += oend_w - op;
-			op = oend_w;
-		}
-		while (op < oMatchEnd)
-			*op++ = *match++;
-	} else {
-		ZSTD_wildcopy(op, match, (ptrdiff_t)sequence.matchLength - 8); /* works even if matchLength < 8 */
-	}
-	return sequenceLength;
-}
-
-static size_t ZSTD_decompressSequences(ZSTD_DCtx *dctx, void *dst, size_t maxDstSize, const void *seqStart, size_t seqSize)
-{
-	const BYTE *ip = (const BYTE *)seqStart;
-	const BYTE *const iend = ip + seqSize;
-	BYTE *const ostart = (BYTE * const)dst;
-	BYTE *const oend = ostart + maxDstSize;
-	BYTE *op = ostart;
-	const BYTE *litPtr = dctx->litPtr;
-	const BYTE *const litEnd = litPtr + dctx->litSize;
-	const BYTE *const base = (const BYTE *)(dctx->base);
-	const BYTE *const vBase = (const BYTE *)(dctx->vBase);
-	const BYTE *const dictEnd = (const BYTE *)(dctx->dictEnd);
-	int nbSeq;
-
-	/* Build Decoding Tables */
-	{
-		size_t const seqHSize = ZSTD_decodeSeqHeaders(dctx, &nbSeq, ip, seqSize);
-		if (ZSTD_isError(seqHSize))
-			return seqHSize;
-		ip += seqHSize;
-	}
-
-	/* Regen sequences */
-	if (nbSeq) {
-		seqState_t seqState;
-		dctx->fseEntropy = 1;
-		{
-			U32 i;
-			for (i = 0; i < ZSTD_REP_NUM; i++)
-				seqState.prevOffset[i] = dctx->entropy.rep[i];
-		}
-		CHECK_E(BIT_initDStream(&seqState.DStream, ip, iend - ip), corruption_detected);
-		FSE_initDState(&seqState.stateLL, &seqState.DStream, dctx->LLTptr);
-		FSE_initDState(&seqState.stateOffb, &seqState.DStream, dctx->OFTptr);
-		FSE_initDState(&seqState.stateML, &seqState.DStream, dctx->MLTptr);
-
-		for (; (BIT_reloadDStream(&(seqState.DStream)) <= BIT_DStream_completed) && nbSeq;) {
-			nbSeq--;
-			{
-				seq_t const sequence = ZSTD_decodeSequence(&seqState);
-				size_t const oneSeqSize = ZSTD_execSequence(op, oend, sequence, &litPtr, litEnd, base, vBase, dictEnd);
-				if (ZSTD_isError(oneSeqSize))
-					return oneSeqSize;
-				op += oneSeqSize;
-			}
-		}
-
-		/* check if reached exact end */
-		if (nbSeq)
-			return ERROR(corruption_detected);
-		/* save reps for next block */
-		{
-			U32 i;
-			for (i = 0; i < ZSTD_REP_NUM; i++)
-				dctx->entropy.rep[i] = (U32)(seqState.prevOffset[i]);
-		}
-	}
-
-	/* last literal segment */
-	{
-		size_t const lastLLSize = litEnd - litPtr;
-		if (lastLLSize > (size_t)(oend - op))
-			return ERROR(dstSize_tooSmall);
-		memcpy(op, litPtr, lastLLSize);
-		op += lastLLSize;
-	}
-
-	return op - ostart;
-}
-
-FORCE_INLINE seq_t ZSTD_decodeSequenceLong_generic(seqState_t *seqState, int const longOffsets)
-{
-	seq_t seq;
-
-	U32 const llCode = FSE_peekSymbol(&seqState->stateLL);
-	U32 const mlCode = FSE_peekSymbol(&seqState->stateML);
-	U32 const ofCode = FSE_peekSymbol(&seqState->stateOffb); /* <= maxOff, by table construction */
-
-	U32 const llBits = LL_bits[llCode];
-	U32 const mlBits = ML_bits[mlCode];
-	U32 const ofBits = ofCode;
-	U32 const totalBits = llBits + mlBits + ofBits;
-
-	static const U32 LL_base[MaxLL + 1] = {0,  1,  2,  3,  4,  5,  6,  7,  8,    9,     10,    11,    12,    13,     14,     15,     16,     18,
-					       20, 22, 24, 28, 32, 40, 48, 64, 0x80, 0x100, 0x200, 0x400, 0x800, 0x1000, 0x2000, 0x4000, 0x8000, 0x10000};
-
-	static const U32 ML_base[MaxML + 1] = {3,  4,  5,  6,  7,  8,  9,  10,   11,    12,    13,    14,    15,     16,     17,     18,     19,     20,
-					       21, 22, 23, 24, 25, 26, 27, 28,   29,    30,    31,    32,    33,     34,     35,     37,     39,     41,
-					       43, 47, 51, 59, 67, 83, 99, 0x83, 0x103, 0x203, 0x403, 0x803, 0x1003, 0x2003, 0x4003, 0x8003, 0x10003};
-
-	static const U32 OF_base[MaxOff + 1] = {0,       1,	1,	5,	0xD,      0x1D,      0x3D,      0x7D,      0xFD,     0x1FD,
-						0x3FD,   0x7FD,    0xFFD,    0x1FFD,   0x3FFD,   0x7FFD,    0xFFFD,    0x1FFFD,   0x3FFFD,  0x7FFFD,
-						0xFFFFD, 0x1FFFFD, 0x3FFFFD, 0x7FFFFD, 0xFFFFFD, 0x1FFFFFD, 0x3FFFFFD, 0x7FFFFFD, 0xFFFFFFD};
-
-	/* sequence */
-	{
-		size_t offset;
-		if (!ofCode)
-			offset = 0;
-		else {
-			if (longOffsets) {
-				int const extraBits = ofBits - MIN(ofBits, STREAM_ACCUMULATOR_MIN);
-				offset = OF_base[ofCode] + (BIT_readBitsFast(&seqState->DStream, ofBits - extraBits) << extraBits);
-				if (ZSTD_32bits() || extraBits)
-					BIT_reloadDStream(&seqState->DStream);
-				if (extraBits)
-					offset += BIT_readBitsFast(&seqState->DStream, extraBits);
-			} else {
-				offset = OF_base[ofCode] + BIT_readBitsFast(&seqState->DStream, ofBits); /* <=  (ZSTD_WINDOWLOG_MAX-1) bits */
-				if (ZSTD_32bits())
-					BIT_reloadDStream(&seqState->DStream);
-			}
-		}
-
-		if (ofCode <= 1) {
-			offset += (llCode == 0);
-			if (offset) {
-				size_t temp = (offset == 3) ? seqState->prevOffset[0] - 1 : seqState->prevOffset[offset];
-				temp += !temp; /* 0 is not valid; input is corrupted; force offset to 1 */
-				if (offset != 1)
-					seqState->prevOffset[2] = seqState->prevOffset[1];
-				seqState->prevOffset[1] = seqState->prevOffset[0];
-				seqState->prevOffset[0] = offset = temp;
-			} else {
-				offset = seqState->prevOffset[0];
-			}
-		} else {
-			seqState->prevOffset[2] = seqState->prevOffset[1];
-			seqState->prevOffset[1] = seqState->prevOffset[0];
-			seqState->prevOffset[0] = offset;
-		}
-		seq.offset = offset;
-	}
-
-	seq.matchLength = ML_base[mlCode] + ((mlCode > 31) ? BIT_readBitsFast(&seqState->DStream, mlBits) : 0); /* <=  16 bits */
-	if (ZSTD_32bits() && (mlBits + llBits > 24))
-		BIT_reloadDStream(&seqState->DStream);
-
-	seq.litLength = LL_base[llCode] + ((llCode > 15) ? BIT_readBitsFast(&seqState->DStream, llBits) : 0); /* <=  16 bits */
-	if (ZSTD_32bits() || (totalBits > 64 - 7 - (LLFSELog + MLFSELog + OffFSELog)))
-		BIT_reloadDStream(&seqState->DStream);
-
-	{
-		size_t const pos = seqState->pos + seq.litLength;
-		seq.match = seqState->base + pos - seq.offset; /* single memory segment */
-		if (seq.offset > pos)
-			seq.match += seqState->gotoDict; /* separate memory segment */
-		seqState->pos = pos + seq.matchLength;
-	}
-
-	/* ANS state update */
-	FSE_updateState(&seqState->stateLL, &seqState->DStream); /* <=  9 bits */
-	FSE_updateState(&seqState->stateML, &seqState->DStream); /* <=  9 bits */
-	if (ZSTD_32bits())
-		BIT_reloadDStream(&seqState->DStream);		   /* <= 18 bits */
-	FSE_updateState(&seqState->stateOffb, &seqState->DStream); /* <=  8 bits */
-
-	return seq;
-}
-
-static seq_t ZSTD_decodeSequenceLong(seqState_t *seqState, unsigned const windowSize)
-{
-	if (ZSTD_highbit32(windowSize) > STREAM_ACCUMULATOR_MIN) {
-		return ZSTD_decodeSequenceLong_generic(seqState, 1);
-	} else {
-		return ZSTD_decodeSequenceLong_generic(seqState, 0);
-	}
-}
-
-FORCE_INLINE
-size_t ZSTD_execSequenceLong(BYTE *op, BYTE *const oend, seq_t sequence, const BYTE **litPtr, const BYTE *const litLimit, const BYTE *const base,
-			     const BYTE *const vBase, const BYTE *const dictEnd)
-{
-	BYTE *const oLitEnd = op + sequence.litLength;
-	size_t const sequenceLength = sequence.litLength + sequence.matchLength;
-	BYTE *const oMatchEnd = op + sequenceLength; /* risk : address space overflow (32-bits) */
-	BYTE *const oend_w = oend - WILDCOPY_OVERLENGTH;
-	const BYTE *const iLitEnd = *litPtr + sequence.litLength;
-	const BYTE *match = sequence.match;
-
-	/* check */
-	if (oMatchEnd > oend)
-		return ERROR(dstSize_tooSmall); /* last match must start at a minimum distance of WILDCOPY_OVERLENGTH from oend */
-	if (iLitEnd > litLimit)
-		return ERROR(corruption_detected); /* over-read beyond lit buffer */
-	if (oLitEnd > oend_w)
-		return ZSTD_execSequenceLast7(op, oend, sequence, litPtr, litLimit, base, vBase, dictEnd);
-
-	/* copy Literals */
-	ZSTD_copy8(op, *litPtr);
-	if (sequence.litLength > 8)
-		ZSTD_wildcopy(op + 8, (*litPtr) + 8,
-			      sequence.litLength - 8); /* note : since oLitEnd <= oend-WILDCOPY_OVERLENGTH, no risk of overwrite beyond oend */
-	op = oLitEnd;
-	*litPtr = iLitEnd; /* update for next sequence */
-
-	/* copy Match */
-	if (sequence.offset > (size_t)(oLitEnd - base)) {
-		/* offset beyond prefix */
-		if (sequence.offset > (size_t)(oLitEnd - vBase))
-			return ERROR(corruption_detected);
-		if (match + sequence.matchLength <= dictEnd) {
-			memmove(oLitEnd, match, sequence.matchLength);
-			return sequenceLength;
-		}
-		/* span extDict & currPrefixSegment */
-		{
-			size_t const length1 = dictEnd - match;
-			memmove(oLitEnd, match, length1);
-			op = oLitEnd + length1;
-			sequence.matchLength -= length1;
-			match = base;
-			if (op > oend_w || sequence.matchLength < MINMATCH) {
-				U32 i;
-				for (i = 0; i < sequence.matchLength; ++i)
-					op[i] = match[i];
-				return sequenceLength;
-			}
-		}
-	}
-	/* Requirement: op <= oend_w && sequence.matchLength >= MINMATCH */
-
-	/* match within prefix */
-	if (sequence.offset < 8) {
-		/* close range match, overlap */
-		static const U32 dec32table[] = {0, 1, 2, 1, 4, 4, 4, 4};   /* added */
-		static const int dec64table[] = {8, 8, 8, 7, 8, 9, 10, 11}; /* subtracted */
-		int const sub2 = dec64table[sequence.offset];
-		op[0] = match[0];
-		op[1] = match[1];
-		op[2] = match[2];
-		op[3] = match[3];
-		match += dec32table[sequence.offset];
-		ZSTD_copy4(op + 4, match);
-		match -= sub2;
-	} else {
-		ZSTD_copy8(op, match);
-	}
-	op += 8;
-	match += 8;
-
-	if (oMatchEnd > oend - (16 - MINMATCH)) {
-		if (op < oend_w) {
-			ZSTD_wildcopy(op, match, oend_w - op);
-			match += oend_w - op;
-			op = oend_w;
-		}
-		while (op < oMatchEnd)
-			*op++ = *match++;
-	} else {
-		ZSTD_wildcopy(op, match, (ptrdiff_t)sequence.matchLength - 8); /* works even if matchLength < 8 */
-	}
-	return sequenceLength;
-}
-
-static size_t ZSTD_decompressSequencesLong(ZSTD_DCtx *dctx, void *dst, size_t maxDstSize, const void *seqStart, size_t seqSize)
-{
-	const BYTE *ip = (const BYTE *)seqStart;
-	const BYTE *const iend = ip + seqSize;
-	BYTE *const ostart = (BYTE * const)dst;
-	BYTE *const oend = ostart + maxDstSize;
-	BYTE *op = ostart;
-	const BYTE *litPtr = dctx->litPtr;
-	const BYTE *const litEnd = litPtr + dctx->litSize;
-	const BYTE *const base = (const BYTE *)(dctx->base);
-	const BYTE *const vBase = (const BYTE *)(dctx->vBase);
-	const BYTE *const dictEnd = (const BYTE *)(dctx->dictEnd);
-	unsigned const windowSize = dctx->fParams.windowSize;
-	int nbSeq;
-
-	/* Build Decoding Tables */
-	{
-		size_t const seqHSize = ZSTD_decodeSeqHeaders(dctx, &nbSeq, ip, seqSize);
-		if (ZSTD_isError(seqHSize))
-			return seqHSize;
-		ip += seqHSize;
-	}
-
-	/* Regen sequences */
-	if (nbSeq) {
-#define STORED_SEQS 4
-#define STOSEQ_MASK (STORED_SEQS - 1)
-#define ADVANCED_SEQS 4
-		seq_t *sequences = (seq_t *)dctx->entropy.workspace;
-		int const seqAdvance = MIN(nbSeq, ADVANCED_SEQS);
-		seqState_t seqState;
-		int seqNb;
-		ZSTD_STATIC_ASSERT(sizeof(dctx->entropy.workspace) >= sizeof(seq_t) * STORED_SEQS);
-		dctx->fseEntropy = 1;
-		{
-			U32 i;
-			for (i = 0; i < ZSTD_REP_NUM; i++)
-				seqState.prevOffset[i] = dctx->entropy.rep[i];
-		}
-		seqState.base = base;
-		seqState.pos = (size_t)(op - base);
-		seqState.gotoDict = (uPtrDiff)dictEnd - (uPtrDiff)base; /* cast to avoid undefined behaviour */
-		CHECK_E(BIT_initDStream(&seqState.DStream, ip, iend - ip), corruption_detected);
-		FSE_initDState(&seqState.stateLL, &seqState.DStream, dctx->LLTptr);
-		FSE_initDState(&seqState.stateOffb, &seqState.DStream, dctx->OFTptr);
-		FSE_initDState(&seqState.stateML, &seqState.DStream, dctx->MLTptr);
-
-		/* prepare in advance */
-		for (seqNb = 0; (BIT_reloadDStream(&seqState.DStream) <= BIT_DStream_completed) && seqNb < seqAdvance; seqNb++) {
-			sequences[seqNb] = ZSTD_decodeSequenceLong(&seqState, windowSize);
-		}
-		if (seqNb < seqAdvance)
-			return ERROR(corruption_detected);
-
-		/* decode and decompress */
-		for (; (BIT_reloadDStream(&(seqState.DStream)) <= BIT_DStream_completed) && seqNb < nbSeq; seqNb++) {
-			seq_t const sequence = ZSTD_decodeSequenceLong(&seqState, windowSize);
-			size_t const oneSeqSize =
-			    ZSTD_execSequenceLong(op, oend, sequences[(seqNb - ADVANCED_SEQS) & STOSEQ_MASK], &litPtr, litEnd, base, vBase, dictEnd);
-			if (ZSTD_isError(oneSeqSize))
-				return oneSeqSize;
-			ZSTD_PREFETCH(sequence.match);
-			sequences[seqNb & STOSEQ_MASK] = sequence;
-			op += oneSeqSize;
-		}
-		if (seqNb < nbSeq)
-			return ERROR(corruption_detected);
-
-		/* finish queue */
-		seqNb -= seqAdvance;
-		for (; seqNb < nbSeq; seqNb++) {
-			size_t const oneSeqSize = ZSTD_execSequenceLong(op, oend, sequences[seqNb & STOSEQ_MASK], &litPtr, litEnd, base, vBase, dictEnd);
-			if (ZSTD_isError(oneSeqSize))
-				return oneSeqSize;
-			op += oneSeqSize;
-		}
-
-		/* save reps for next block */
-		{
-			U32 i;
-			for (i = 0; i < ZSTD_REP_NUM; i++)
-				dctx->entropy.rep[i] = (U32)(seqState.prevOffset[i]);
-		}
-	}
-
-	/* last literal segment */
-	{
-		size_t const lastLLSize = litEnd - litPtr;
-		if (lastLLSize > (size_t)(oend - op))
-			return ERROR(dstSize_tooSmall);
-		memcpy(op, litPtr, lastLLSize);
-		op += lastLLSize;
-	}
-
-	return op - ostart;
-}
-
-static size_t ZSTD_decompressBlock_internal(ZSTD_DCtx *dctx, void *dst, size_t dstCapacity, const void *src, size_t srcSize)
-{ /* blockType == blockCompressed */
-	const BYTE *ip = (const BYTE *)src;
-
-	if (srcSize >= ZSTD_BLOCKSIZE_ABSOLUTEMAX)
-		return ERROR(srcSize_wrong);
-
-	/* Decode literals section */
-	{
-		size_t const litCSize = ZSTD_decodeLiteralsBlock(dctx, src, srcSize);
-		if (ZSTD_isError(litCSize))
-			return litCSize;
-		ip += litCSize;
-		srcSize -= litCSize;
-	}
-	if (sizeof(size_t) > 4) /* do not enable prefetching on 32-bits x86, as it's performance detrimental */
-				/* likely because of register pressure */
-				/* if that's the correct cause, then 32-bits ARM should be affected differently */
-				/* it would be good to test this on ARM real hardware, to see if prefetch version improves speed */
-		if (dctx->fParams.windowSize > (1 << 23))
-			return ZSTD_decompressSequencesLong(dctx, dst, dstCapacity, ip, srcSize);
-	return ZSTD_decompressSequences(dctx, dst, dstCapacity, ip, srcSize);
-}
-
-static void ZSTD_checkContinuity(ZSTD_DCtx *dctx, const void *dst)
-{
-	if (dst != dctx->previousDstEnd) { /* not contiguous */
-		dctx->dictEnd = dctx->previousDstEnd;
-		dctx->vBase = (const char *)dst - ((const char *)(dctx->previousDstEnd) - (const char *)(dctx->base));
-		dctx->base = dst;
-		dctx->previousDstEnd = dst;
-	}
-}
-
-size_t ZSTD_decompressBlock(ZSTD_DCtx *dctx, void *dst, size_t dstCapacity, const void *src, size_t srcSize)
-{
-	size_t dSize;
-	ZSTD_checkContinuity(dctx, dst);
-	dSize = ZSTD_decompressBlock_internal(dctx, dst, dstCapacity, src, srcSize);
-	dctx->previousDstEnd = (char *)dst + dSize;
-	return dSize;
-}
-
-/** ZSTD_insertBlock() :
-	insert `src` block into `dctx` history. Useful to track uncompressed blocks. */
-size_t ZSTD_insertBlock(ZSTD_DCtx *dctx, const void *blockStart, size_t blockSize)
-{
-	ZSTD_checkContinuity(dctx, blockStart);
-	dctx->previousDstEnd = (const char *)blockStart + blockSize;
-	return blockSize;
-}
-
-size_t ZSTD_generateNxBytes(void *dst, size_t dstCapacity, BYTE byte, size_t length)
-{
-	if (length > dstCapacity)
-		return ERROR(dstSize_tooSmall);
-	memset(dst, byte, length);
-	return length;
-}
-
-/** ZSTD_findFrameCompressedSize() :
- *  compatible with legacy mode
- *  `src` must point to the start of a ZSTD frame, ZSTD legacy frame, or skippable frame
- *  `srcSize` must be at least as large as the frame contained
- *  @return : the compressed size of the frame starting at `src` */
-size_t ZSTD_findFrameCompressedSize(const void *src, size_t srcSize)
-{
-	if (srcSize >= ZSTD_skippableHeaderSize && (ZSTD_readLE32(src) & 0xFFFFFFF0U) == ZSTD_MAGIC_SKIPPABLE_START) {
-		return ZSTD_skippableHeaderSize + ZSTD_readLE32((const BYTE *)src + 4);
-	} else {
-		const BYTE *ip = (const BYTE *)src;
-		const BYTE *const ipstart = ip;
-		size_t remainingSize = srcSize;
-		ZSTD_frameParams fParams;
-
-		size_t const headerSize = ZSTD_frameHeaderSize(ip, remainingSize);
-		if (ZSTD_isError(headerSize))
-			return headerSize;
-
-		/* Frame Header */
-		{
-			size_t const ret = ZSTD_getFrameParams(&fParams, ip, remainingSize);
-			if (ZSTD_isError(ret))
-				return ret;
-			if (ret > 0)
-				return ERROR(srcSize_wrong);
-		}
-
-		ip += headerSize;
-		remainingSize -= headerSize;
-
-		/* Loop on each block */
-		while (1) {
-			blockProperties_t blockProperties;
-			size_t const cBlockSize = ZSTD_getcBlockSize(ip, remainingSize, &blockProperties);
-			if (ZSTD_isError(cBlockSize))
-				return cBlockSize;
-
-			if (ZSTD_blockHeaderSize + cBlockSize > remainingSize)
-				return ERROR(srcSize_wrong);
-
-			ip += ZSTD_blockHeaderSize + cBlockSize;
-			remainingSize -= ZSTD_blockHeaderSize + cBlockSize;
-
-			if (blockProperties.lastBlock)
-				break;
-		}
-
-		if (fParams.checksumFlag) { /* Frame content checksum */
-			if (remainingSize < 4)
-				return ERROR(srcSize_wrong);
-			ip += 4;
-			remainingSize -= 4;
-		}
-
-		return ip - ipstart;
-	}
-}
-
-/*! ZSTD_decompressFrame() :
-*   @dctx must be properly initialized */
-static size_t ZSTD_decompressFrame(ZSTD_DCtx *dctx, void *dst, size_t dstCapacity, const void **srcPtr, size_t *srcSizePtr)
-{
-	const BYTE *ip = (const BYTE *)(*srcPtr);
-	BYTE *const ostart = (BYTE * const)dst;
-	BYTE *const oend = ostart + dstCapacity;
-	BYTE *op = ostart;
-	size_t remainingSize = *srcSizePtr;
-
-	/* check */
-	if (remainingSize < ZSTD_frameHeaderSize_min + ZSTD_blockHeaderSize)
-		return ERROR(srcSize_wrong);
-
-	/* Frame Header */
-	{
-		size_t const frameHeaderSize = ZSTD_frameHeaderSize(ip, ZSTD_frameHeaderSize_prefix);
-		if (ZSTD_isError(frameHeaderSize))
-			return frameHeaderSize;
-		if (remainingSize < frameHeaderSize + ZSTD_blockHeaderSize)
-			return ERROR(srcSize_wrong);
-		CHECK_F(ZSTD_decodeFrameHeader(dctx, ip, frameHeaderSize));
-		ip += frameHeaderSize;
-		remainingSize -= frameHeaderSize;
-	}
-
-	/* Loop on each block */
-	while (1) {
-		size_t decodedSize;
-		blockProperties_t blockProperties;
-		size_t const cBlockSize = ZSTD_getcBlockSize(ip, remainingSize, &blockProperties);
-		if (ZSTD_isError(cBlockSize))
-			return cBlockSize;
-
-		ip += ZSTD_blockHeaderSize;
-		remainingSize -= ZSTD_blockHeaderSize;
-		if (cBlockSize > remainingSize)
-			return ERROR(srcSize_wrong);
-
-		switch (blockProperties.blockType) {
-		case bt_compressed: decodedSize = ZSTD_decompressBlock_internal(dctx, op, oend - op, ip, cBlockSize); break;
-		case bt_raw: decodedSize = ZSTD_copyRawBlock(op, oend - op, ip, cBlockSize); break;
-		case bt_rle: decodedSize = ZSTD_generateNxBytes(op, oend - op, *ip, blockProperties.origSize); break;
-		case bt_reserved:
-		default: return ERROR(corruption_detected);
-		}
-
-		if (ZSTD_isError(decodedSize))
-			return decodedSize;
-		if (dctx->fParams.checksumFlag)
-			xxh64_update(&dctx->xxhState, op, decodedSize);
-		op += decodedSize;
-		ip += cBlockSize;
-		remainingSize -= cBlockSize;
-		if (blockProperties.lastBlock)
-			break;
-	}
-
-	if (dctx->fParams.checksumFlag) { /* Frame content checksum verification */
-		U32 const checkCalc = (U32)xxh64_digest(&dctx->xxhState);
-		U32 checkRead;
-		if (remainingSize < 4)
-			return ERROR(checksum_wrong);
-		checkRead = ZSTD_readLE32(ip);
-		if (checkRead != checkCalc)
-			return ERROR(checksum_wrong);
-		ip += 4;
-		remainingSize -= 4;
-	}
-
-	/* Allow caller to get size read */
-	*srcPtr = ip;
-	*srcSizePtr = remainingSize;
-	return op - ostart;
-}
-
-static const void *ZSTD_DDictDictContent(const ZSTD_DDict *ddict);
-static size_t ZSTD_DDictDictSize(const ZSTD_DDict *ddict);
-
-static size_t ZSTD_decompressMultiFrame(ZSTD_DCtx *dctx, void *dst, size_t dstCapacity, const void *src, size_t srcSize, const void *dict, size_t dictSize,
-					const ZSTD_DDict *ddict)
-{
-	void *const dststart = dst;
-
-	if (ddict) {
-		if (dict) {
-			/* programmer error, these two cases should be mutually exclusive */
-			return ERROR(GENERIC);
-		}
-
-		dict = ZSTD_DDictDictContent(ddict);
-		dictSize = ZSTD_DDictDictSize(ddict);
-	}
-
-	while (srcSize >= ZSTD_frameHeaderSize_prefix) {
-		U32 magicNumber;
-
-		magicNumber = ZSTD_readLE32(src);
-		if (magicNumber != ZSTD_MAGICNUMBER) {
-			if ((magicNumber & 0xFFFFFFF0U) == ZSTD_MAGIC_SKIPPABLE_START) {
-				size_t skippableSize;
-				if (srcSize < ZSTD_skippableHeaderSize)
-					return ERROR(srcSize_wrong);
-				skippableSize = ZSTD_readLE32((const BYTE *)src + 4) + ZSTD_skippableHeaderSize;
-				if (srcSize < skippableSize) {
-					return ERROR(srcSize_wrong);
-				}
-
-				src = (const BYTE *)src + skippableSize;
-				srcSize -= skippableSize;
-				continue;
-			} else {
-				return ERROR(prefix_unknown);
-			}
-		}
-
-		if (ddict) {
-			/* we were called from ZSTD_decompress_usingDDict */
-			ZSTD_refDDict(dctx, ddict);
-		} else {
-			/* this will initialize correctly with no dict if dict == NULL, so
-			 * use this in all cases but ddict */
-			CHECK_F(ZSTD_decompressBegin_usingDict(dctx, dict, dictSize));
-		}
-		ZSTD_checkContinuity(dctx, dst);
-
-		{
-			const size_t res = ZSTD_decompressFrame(dctx, dst, dstCapacity, &src, &srcSize);
-			if (ZSTD_isError(res))
-				return res;
-			/* don't need to bounds check this, ZSTD_decompressFrame will have
-			 * already */
-			dst = (BYTE *)dst + res;
-			dstCapacity -= res;
-		}
-	}
-
-	if (srcSize)
-		return ERROR(srcSize_wrong); /* input not entirely consumed */
-
-	return (BYTE *)dst - (BYTE *)dststart;
-}
-
-size_t ZSTD_decompress_usingDict(ZSTD_DCtx *dctx, void *dst, size_t dstCapacity, const void *src, size_t srcSize, const void *dict, size_t dictSize)
-{
-	return ZSTD_decompressMultiFrame(dctx, dst, dstCapacity, src, srcSize, dict, dictSize, NULL);
-}
-
-size_t ZSTD_decompressDCtx(ZSTD_DCtx *dctx, void *dst, size_t dstCapacity, const void *src, size_t srcSize)
-{
-	return ZSTD_decompress_usingDict(dctx, dst, dstCapacity, src, srcSize, NULL, 0);
-}
-
-/*-**************************************
-*   Advanced Streaming Decompression API
-*   Bufferless and synchronous
-****************************************/
-size_t ZSTD_nextSrcSizeToDecompress(ZSTD_DCtx *dctx) { return dctx->expected; }
-
-ZSTD_nextInputType_e ZSTD_nextInputType(ZSTD_DCtx *dctx)
-{
-	switch (dctx->stage) {
-	default: /* should not happen */
-	case ZSTDds_getFrameHeaderSize:
-	case ZSTDds_decodeFrameHeader: return ZSTDnit_frameHeader;
-	case ZSTDds_decodeBlockHeader: return ZSTDnit_blockHeader;
-	case ZSTDds_decompressBlock: return ZSTDnit_block;
-	case ZSTDds_decompressLastBlock: return ZSTDnit_lastBlock;
-	case ZSTDds_checkChecksum: return ZSTDnit_checksum;
-	case ZSTDds_decodeSkippableHeader:
-	case ZSTDds_skipFrame: return ZSTDnit_skippableFrame;
-	}
-}
-
-int ZSTD_isSkipFrame(ZSTD_DCtx *dctx) { return dctx->stage == ZSTDds_skipFrame; } /* for zbuff */
-
-/** ZSTD_decompressContinue() :
-*   @return : nb of bytes generated into `dst` (necessarily <= `dstCapacity)
-*             or an error code, which can be tested using ZSTD_isError() */
-size_t ZSTD_decompressContinue(ZSTD_DCtx *dctx, void *dst, size_t dstCapacity, const void *src, size_t srcSize)
-{
-	/* Sanity check */
-	if (srcSize != dctx->expected)
-		return ERROR(srcSize_wrong);
-	if (dstCapacity)
-		ZSTD_checkContinuity(dctx, dst);
-
-	switch (dctx->stage) {
-	case ZSTDds_getFrameHeaderSize:
-		if (srcSize != ZSTD_frameHeaderSize_prefix)
-			return ERROR(srcSize_wrong);					/* impossible */
-		if ((ZSTD_readLE32(src) & 0xFFFFFFF0U) == ZSTD_MAGIC_SKIPPABLE_START) { /* skippable frame */
-			memcpy(dctx->headerBuffer, src, ZSTD_frameHeaderSize_prefix);
-			dctx->expected = ZSTD_skippableHeaderSize - ZSTD_frameHeaderSize_prefix; /* magic number + skippable frame length */
-			dctx->stage = ZSTDds_decodeSkippableHeader;
-			return 0;
-		}
-		dctx->headerSize = ZSTD_frameHeaderSize(src, ZSTD_frameHeaderSize_prefix);
-		if (ZSTD_isError(dctx->headerSize))
-			return dctx->headerSize;
-		memcpy(dctx->headerBuffer, src, ZSTD_frameHeaderSize_prefix);
-		if (dctx->headerSize > ZSTD_frameHeaderSize_prefix) {
-			dctx->expected = dctx->headerSize - ZSTD_frameHeaderSize_prefix;
-			dctx->stage = ZSTDds_decodeFrameHeader;
-			return 0;
-		}
-		dctx->expected = 0; /* not necessary to copy more */
-		fallthrough;
-
-	case ZSTDds_decodeFrameHeader:
-		memcpy(dctx->headerBuffer + ZSTD_frameHeaderSize_prefix, src, dctx->expected);
-		CHECK_F(ZSTD_decodeFrameHeader(dctx, dctx->headerBuffer, dctx->headerSize));
-		dctx->expected = ZSTD_blockHeaderSize;
-		dctx->stage = ZSTDds_decodeBlockHeader;
-		return 0;
-
-	case ZSTDds_decodeBlockHeader: {
-		blockProperties_t bp;
-		size_t const cBlockSize = ZSTD_getcBlockSize(src, ZSTD_blockHeaderSize, &bp);
-		if (ZSTD_isError(cBlockSize))
-			return cBlockSize;
-		dctx->expected = cBlockSize;
-		dctx->bType = bp.blockType;
-		dctx->rleSize = bp.origSize;
-		if (cBlockSize) {
-			dctx->stage = bp.lastBlock ? ZSTDds_decompressLastBlock : ZSTDds_decompressBlock;
-			return 0;
-		}
-		/* empty block */
-		if (bp.lastBlock) {
-			if (dctx->fParams.checksumFlag) {
-				dctx->expected = 4;
-				dctx->stage = ZSTDds_checkChecksum;
-			} else {
-				dctx->expected = 0; /* end of frame */
-				dctx->stage = ZSTDds_getFrameHeaderSize;
-			}
-		} else {
-			dctx->expected = 3; /* go directly to next header */
-			dctx->stage = ZSTDds_decodeBlockHeader;
-		}
-		return 0;
-	}
-	case ZSTDds_decompressLastBlock:
-	case ZSTDds_decompressBlock: {
-		size_t rSize;
-		switch (dctx->bType) {
-		case bt_compressed: rSize = ZSTD_decompressBlock_internal(dctx, dst, dstCapacity, src, srcSize); break;
-		case bt_raw: rSize = ZSTD_copyRawBlock(dst, dstCapacity, src, srcSize); break;
-		case bt_rle: rSize = ZSTD_setRleBlock(dst, dstCapacity, src, srcSize, dctx->rleSize); break;
-		case bt_reserved: /* should never happen */
-		default: return ERROR(corruption_detected);
-		}
-		if (ZSTD_isError(rSize))
-			return rSize;
-		if (dctx->fParams.checksumFlag)
-			xxh64_update(&dctx->xxhState, dst, rSize);
-
-		if (dctx->stage == ZSTDds_decompressLastBlock) { /* end of frame */
-			if (dctx->fParams.checksumFlag) {	/* another round for frame checksum */
-				dctx->expected = 4;
-				dctx->stage = ZSTDds_checkChecksum;
-			} else {
-				dctx->expected = 0; /* ends here */
-				dctx->stage = ZSTDds_getFrameHeaderSize;
-			}
-		} else {
-			dctx->stage = ZSTDds_decodeBlockHeader;
-			dctx->expected = ZSTD_blockHeaderSize;
-			dctx->previousDstEnd = (char *)dst + rSize;
-		}
-		return rSize;
-	}
-	case ZSTDds_checkChecksum: {
-		U32 const h32 = (U32)xxh64_digest(&dctx->xxhState);
-		U32 const check32 = ZSTD_readLE32(src); /* srcSize == 4, guaranteed by dctx->expected */
-		if (check32 != h32)
-			return ERROR(checksum_wrong);
-		dctx->expected = 0;
-		dctx->stage = ZSTDds_getFrameHeaderSize;
-		return 0;
-	}
-	case ZSTDds_decodeSkippableHeader: {
-		memcpy(dctx->headerBuffer + ZSTD_frameHeaderSize_prefix, src, dctx->expected);
-		dctx->expected = ZSTD_readLE32(dctx->headerBuffer + 4);
-		dctx->stage = ZSTDds_skipFrame;
-		return 0;
-	}
-	case ZSTDds_skipFrame: {
-		dctx->expected = 0;
-		dctx->stage = ZSTDds_getFrameHeaderSize;
-		return 0;
-	}
-	default:
-		return ERROR(GENERIC); /* impossible */
-	}
-}
-
-static size_t ZSTD_refDictContent(ZSTD_DCtx *dctx, const void *dict, size_t dictSize)
-{
-	dctx->dictEnd = dctx->previousDstEnd;
-	dctx->vBase = (const char *)dict - ((const char *)(dctx->previousDstEnd) - (const char *)(dctx->base));
-	dctx->base = dict;
-	dctx->previousDstEnd = (const char *)dict + dictSize;
-	return 0;
-}
-
-/* ZSTD_loadEntropy() :
- * dict : must point at beginning of a valid zstd dictionary
- * @return : size of entropy tables read */
-static size_t ZSTD_loadEntropy(ZSTD_entropyTables_t *entropy, const void *const dict, size_t const dictSize)
-{
-	const BYTE *dictPtr = (const BYTE *)dict;
-	const BYTE *const dictEnd = dictPtr + dictSize;
-
-	if (dictSize <= 8)
-		return ERROR(dictionary_corrupted);
-	dictPtr += 8; /* skip header = magic + dictID */
-
-	{
-		size_t const hSize = HUF_readDTableX4_wksp(entropy->hufTable, dictPtr, dictEnd - dictPtr, entropy->workspace, sizeof(entropy->workspace));
-		if (HUF_isError(hSize))
-			return ERROR(dictionary_corrupted);
-		dictPtr += hSize;
-	}
-
-	{
-		short offcodeNCount[MaxOff + 1];
-		U32 offcodeMaxValue = MaxOff, offcodeLog;
-		size_t const offcodeHeaderSize = FSE_readNCount(offcodeNCount, &offcodeMaxValue, &offcodeLog, dictPtr, dictEnd - dictPtr);
-		if (FSE_isError(offcodeHeaderSize))
-			return ERROR(dictionary_corrupted);
-		if (offcodeLog > OffFSELog)
-			return ERROR(dictionary_corrupted);
-		CHECK_E(FSE_buildDTable_wksp(entropy->OFTable, offcodeNCount, offcodeMaxValue, offcodeLog, entropy->workspace, sizeof(entropy->workspace)), dictionary_corrupted);
-		dictPtr += offcodeHeaderSize;
-	}
-
-	{
-		short matchlengthNCount[MaxML + 1];
-		unsigned matchlengthMaxValue = MaxML, matchlengthLog;
-		size_t const matchlengthHeaderSize = FSE_readNCount(matchlengthNCount, &matchlengthMaxValue, &matchlengthLog, dictPtr, dictEnd - dictPtr);
-		if (FSE_isError(matchlengthHeaderSize))
-			return ERROR(dictionary_corrupted);
-		if (matchlengthLog > MLFSELog)
-			return ERROR(dictionary_corrupted);
-		CHECK_E(FSE_buildDTable_wksp(entropy->MLTable, matchlengthNCount, matchlengthMaxValue, matchlengthLog, entropy->workspace, sizeof(entropy->workspace)), dictionary_corrupted);
-		dictPtr += matchlengthHeaderSize;
-	}
-
-	{
-		short litlengthNCount[MaxLL + 1];
-		unsigned litlengthMaxValue = MaxLL, litlengthLog;
-		size_t const litlengthHeaderSize = FSE_readNCount(litlengthNCount, &litlengthMaxValue, &litlengthLog, dictPtr, dictEnd - dictPtr);
-		if (FSE_isError(litlengthHeaderSize))
-			return ERROR(dictionary_corrupted);
-		if (litlengthLog > LLFSELog)
-			return ERROR(dictionary_corrupted);
-		CHECK_E(FSE_buildDTable_wksp(entropy->LLTable, litlengthNCount, litlengthMaxValue, litlengthLog, entropy->workspace, sizeof(entropy->workspace)), dictionary_corrupted);
-		dictPtr += litlengthHeaderSize;
-	}
-
-	if (dictPtr + 12 > dictEnd)
-		return ERROR(dictionary_corrupted);
-	{
-		int i;
-		size_t const dictContentSize = (size_t)(dictEnd - (dictPtr + 12));
-		for (i = 0; i < 3; i++) {
-			U32 const rep = ZSTD_readLE32(dictPtr);
-			dictPtr += 4;
-			if (rep == 0 || rep >= dictContentSize)
-				return ERROR(dictionary_corrupted);
-			entropy->rep[i] = rep;
-		}
-	}
-
-	return dictPtr - (const BYTE *)dict;
-}
-
-static size_t ZSTD_decompress_insertDictionary(ZSTD_DCtx *dctx, const void *dict, size_t dictSize)
-{
-	if (dictSize < 8)
-		return ZSTD_refDictContent(dctx, dict, dictSize);
-	{
-		U32 const magic = ZSTD_readLE32(dict);
-		if (magic != ZSTD_DICT_MAGIC) {
-			return ZSTD_refDictContent(dctx, dict, dictSize); /* pure content mode */
-		}
-	}
-	dctx->dictID = ZSTD_readLE32((const char *)dict + 4);
-
-	/* load entropy tables */
-	{
-		size_t const eSize = ZSTD_loadEntropy(&dctx->entropy, dict, dictSize);
-		if (ZSTD_isError(eSize))
-			return ERROR(dictionary_corrupted);
-		dict = (const char *)dict + eSize;
-		dictSize -= eSize;
-	}
-	dctx->litEntropy = dctx->fseEntropy = 1;
-
-	/* reference dictionary content */
-	return ZSTD_refDictContent(dctx, dict, dictSize);
-}
-
-size_t ZSTD_decompressBegin_usingDict(ZSTD_DCtx *dctx, const void *dict, size_t dictSize)
-{
-	CHECK_F(ZSTD_decompressBegin(dctx));
-	if (dict && dictSize)
-		CHECK_E(ZSTD_decompress_insertDictionary(dctx, dict, dictSize), dictionary_corrupted);
-	return 0;
-}
-
-/* ======   ZSTD_DDict   ====== */
-
-struct ZSTD_DDict_s {
-	void *dictBuffer;
-	const void *dictContent;
-	size_t dictSize;
-	ZSTD_entropyTables_t entropy;
-	U32 dictID;
-	U32 entropyPresent;
-	ZSTD_customMem cMem;
-}; /* typedef'd to ZSTD_DDict within "zstd.h" */
-
-size_t ZSTD_DDictWorkspaceBound(void) { return ZSTD_ALIGN(sizeof(ZSTD_stack)) + ZSTD_ALIGN(sizeof(ZSTD_DDict)); }
-
-static const void *ZSTD_DDictDictContent(const ZSTD_DDict *ddict) { return ddict->dictContent; }
-
-static size_t ZSTD_DDictDictSize(const ZSTD_DDict *ddict) { return ddict->dictSize; }
-
-static void ZSTD_refDDict(ZSTD_DCtx *dstDCtx, const ZSTD_DDict *ddict)
-{
-	ZSTD_decompressBegin(dstDCtx); /* init */
-	if (ddict) {		       /* support refDDict on NULL */
-		dstDCtx->dictID = ddict->dictID;
-		dstDCtx->base = ddict->dictContent;
-		dstDCtx->vBase = ddict->dictContent;
-		dstDCtx->dictEnd = (const BYTE *)ddict->dictContent + ddict->dictSize;
-		dstDCtx->previousDstEnd = dstDCtx->dictEnd;
-		if (ddict->entropyPresent) {
-			dstDCtx->litEntropy = 1;
-			dstDCtx->fseEntropy = 1;
-			dstDCtx->LLTptr = ddict->entropy.LLTable;
-			dstDCtx->MLTptr = ddict->entropy.MLTable;
-			dstDCtx->OFTptr = ddict->entropy.OFTable;
-			dstDCtx->HUFptr = ddict->entropy.hufTable;
-			dstDCtx->entropy.rep[0] = ddict->entropy.rep[0];
-			dstDCtx->entropy.rep[1] = ddict->entropy.rep[1];
-			dstDCtx->entropy.rep[2] = ddict->entropy.rep[2];
-		} else {
-			dstDCtx->litEntropy = 0;
-			dstDCtx->fseEntropy = 0;
-		}
-	}
-}
-
-static size_t ZSTD_loadEntropy_inDDict(ZSTD_DDict *ddict)
-{
-	ddict->dictID = 0;
-	ddict->entropyPresent = 0;
-	if (ddict->dictSize < 8)
-		return 0;
-	{
-		U32 const magic = ZSTD_readLE32(ddict->dictContent);
-		if (magic != ZSTD_DICT_MAGIC)
-			return 0; /* pure content mode */
-	}
-	ddict->dictID = ZSTD_readLE32((const char *)ddict->dictContent + 4);
-
-	/* load entropy tables */
-	CHECK_E(ZSTD_loadEntropy(&ddict->entropy, ddict->dictContent, ddict->dictSize), dictionary_corrupted);
-	ddict->entropyPresent = 1;
-	return 0;
-}
-
-static ZSTD_DDict *ZSTD_createDDict_advanced(const void *dict, size_t dictSize, unsigned byReference, ZSTD_customMem customMem)
-{
-	if (!customMem.customAlloc || !customMem.customFree)
-		return NULL;
-
-	{
-		ZSTD_DDict *const ddict = (ZSTD_DDict *)ZSTD_malloc(sizeof(ZSTD_DDict), customMem);
-		if (!ddict)
-			return NULL;
-		ddict->cMem = customMem;
-
-		if ((byReference) || (!dict) || (!dictSize)) {
-			ddict->dictBuffer = NULL;
-			ddict->dictContent = dict;
-		} else {
-			void *const internalBuffer = ZSTD_malloc(dictSize, customMem);
-			if (!internalBuffer) {
-				ZSTD_freeDDict(ddict);
-				return NULL;
-			}
-			memcpy(internalBuffer, dict, dictSize);
-			ddict->dictBuffer = internalBuffer;
-			ddict->dictContent = internalBuffer;
-		}
-		ddict->dictSize = dictSize;
-		ddict->entropy.hufTable[0] = (HUF_DTable)((HufLog)*0x1000001); /* cover both little and big endian */
-		/* parse dictionary content */
-		{
-			size_t const errorCode = ZSTD_loadEntropy_inDDict(ddict);
-			if (ZSTD_isError(errorCode)) {
-				ZSTD_freeDDict(ddict);
-				return NULL;
-			}
-		}
-
-		return ddict;
-	}
-}
-
-/*! ZSTD_initDDict() :
-*   Create a digested dictionary, to start decompression without startup delay.
-*   `dict` content is copied inside DDict.
-*   Consequently, `dict` can be released after `ZSTD_DDict` creation */
-ZSTD_DDict *ZSTD_initDDict(const void *dict, size_t dictSize, void *workspace, size_t workspaceSize)
-{
-	ZSTD_customMem const stackMem = ZSTD_initStack(workspace, workspaceSize);
-	return ZSTD_createDDict_advanced(dict, dictSize, 1, stackMem);
-}
-
-size_t ZSTD_freeDDict(ZSTD_DDict *ddict)
-{
-	if (ddict == NULL)
-		return 0; /* support free on NULL */
-	{
-		ZSTD_customMem const cMem = ddict->cMem;
-		ZSTD_free(ddict->dictBuffer, cMem);
-		ZSTD_free(ddict, cMem);
-		return 0;
-	}
-}
-
-/*! ZSTD_getDictID_fromDict() :
- *  Provides the dictID stored within dictionary.
- *  if @return == 0, the dictionary is not conformant with Zstandard specification.
- *  It can still be loaded, but as a content-only dictionary. */
-unsigned ZSTD_getDictID_fromDict(const void *dict, size_t dictSize)
-{
-	if (dictSize < 8)
-		return 0;
-	if (ZSTD_readLE32(dict) != ZSTD_DICT_MAGIC)
-		return 0;
-	return ZSTD_readLE32((const char *)dict + 4);
-}
-
-/*! ZSTD_getDictID_fromDDict() :
- *  Provides the dictID of the dictionary loaded into `ddict`.
- *  If @return == 0, the dictionary is not conformant to Zstandard specification, or empty.
- *  Non-conformant dictionaries can still be loaded, but as content-only dictionaries. */
-unsigned ZSTD_getDictID_fromDDict(const ZSTD_DDict *ddict)
-{
-	if (ddict == NULL)
-		return 0;
-	return ZSTD_getDictID_fromDict(ddict->dictContent, ddict->dictSize);
-}
-
-/*! ZSTD_getDictID_fromFrame() :
- *  Provides the dictID required to decompressed the frame stored within `src`.
- *  If @return == 0, the dictID could not be decoded.
- *  This could for one of the following reasons :
- *  - The frame does not require a dictionary to be decoded (most common case).
- *  - The frame was built with dictID intentionally removed. Whatever dictionary is necessary is a hidden information.
- *    Note : this use case also happens when using a non-conformant dictionary.
- *  - `srcSize` is too small, and as a result, the frame header could not be decoded (only possible if `srcSize < ZSTD_FRAMEHEADERSIZE_MAX`).
- *  - This is not a Zstandard frame.
- *  When identifying the exact failure cause, it's possible to used ZSTD_getFrameParams(), which will provide a more precise error code. */
-unsigned ZSTD_getDictID_fromFrame(const void *src, size_t srcSize)
-{
-	ZSTD_frameParams zfp = {0, 0, 0, 0};
-	size_t const hError = ZSTD_getFrameParams(&zfp, src, srcSize);
-	if (ZSTD_isError(hError))
-		return 0;
-	return zfp.dictID;
-}
-
-/*! ZSTD_decompress_usingDDict() :
-*   Decompression using a pre-digested Dictionary
-*   Use dictionary without significant overhead. */
-size_t ZSTD_decompress_usingDDict(ZSTD_DCtx *dctx, void *dst, size_t dstCapacity, const void *src, size_t srcSize, const ZSTD_DDict *ddict)
-{
-	/* pass content and size in case legacy frames are encountered */
-	return ZSTD_decompressMultiFrame(dctx, dst, dstCapacity, src, srcSize, NULL, 0, ddict);
-}
-
-/*=====================================
-*   Streaming decompression
-*====================================*/
-
-typedef enum { zdss_init, zdss_loadHeader, zdss_read, zdss_load, zdss_flush } ZSTD_dStreamStage;
-
-/* *** Resource management *** */
-struct ZSTD_DStream_s {
-	ZSTD_DCtx *dctx;
-	ZSTD_DDict *ddictLocal;
-	const ZSTD_DDict *ddict;
-	ZSTD_frameParams fParams;
-	ZSTD_dStreamStage stage;
-	char *inBuff;
-	size_t inBuffSize;
-	size_t inPos;
-	size_t maxWindowSize;
-	char *outBuff;
-	size_t outBuffSize;
-	size_t outStart;
-	size_t outEnd;
-	size_t blockSize;
-	BYTE headerBuffer[ZSTD_FRAMEHEADERSIZE_MAX]; /* tmp buffer to store frame header */
-	size_t lhSize;
-	ZSTD_customMem customMem;
-	void *legacyContext;
-	U32 previousLegacyVersion;
-	U32 legacyVersion;
-	U32 hostageByte;
-}; /* typedef'd to ZSTD_DStream within "zstd.h" */
-
-size_t ZSTD_DStreamWorkspaceBound(size_t maxWindowSize)
-{
-	size_t const blockSize = MIN(maxWindowSize, ZSTD_BLOCKSIZE_ABSOLUTEMAX);
-	size_t const inBuffSize = blockSize;
-	size_t const outBuffSize = maxWindowSize + blockSize + WILDCOPY_OVERLENGTH * 2;
-	return ZSTD_DCtxWorkspaceBound() + ZSTD_ALIGN(sizeof(ZSTD_DStream)) + ZSTD_ALIGN(inBuffSize) + ZSTD_ALIGN(outBuffSize);
-}
-
-static ZSTD_DStream *ZSTD_createDStream_advanced(ZSTD_customMem customMem)
-{
-	ZSTD_DStream *zds;
-
-	if (!customMem.customAlloc || !customMem.customFree)
-		return NULL;
-
-	zds = (ZSTD_DStream *)ZSTD_malloc(sizeof(ZSTD_DStream), customMem);
-	if (zds == NULL)
-		return NULL;
-	memset(zds, 0, sizeof(ZSTD_DStream));
-	memcpy(&zds->customMem, &customMem, sizeof(ZSTD_customMem));
-	zds->dctx = ZSTD_createDCtx_advanced(customMem);
-	if (zds->dctx == NULL) {
-		ZSTD_freeDStream(zds);
-		return NULL;
-	}
-	zds->stage = zdss_init;
-	zds->maxWindowSize = ZSTD_MAXWINDOWSIZE_DEFAULT;
-	return zds;
-}
-
-ZSTD_DStream *ZSTD_initDStream(size_t maxWindowSize, void *workspace, size_t workspaceSize)
-{
-	ZSTD_customMem const stackMem = ZSTD_initStack(workspace, workspaceSize);
-	ZSTD_DStream *zds = ZSTD_createDStream_advanced(stackMem);
-	if (!zds) {
-		return NULL;
-	}
-
-	zds->maxWindowSize = maxWindowSize;
-	zds->stage = zdss_loadHeader;
-	zds->lhSize = zds->inPos = zds->outStart = zds->outEnd = 0;
-	ZSTD_freeDDict(zds->ddictLocal);
-	zds->ddictLocal = NULL;
-	zds->ddict = zds->ddictLocal;
-	zds->legacyVersion = 0;
-	zds->hostageByte = 0;
-
-	{
-		size_t const blockSize = MIN(zds->maxWindowSize, ZSTD_BLOCKSIZE_ABSOLUTEMAX);
-		size_t const neededOutSize = zds->maxWindowSize + blockSize + WILDCOPY_OVERLENGTH * 2;
-
-		zds->inBuff = (char *)ZSTD_malloc(blockSize, zds->customMem);
-		zds->inBuffSize = blockSize;
-		zds->outBuff = (char *)ZSTD_malloc(neededOutSize, zds->customMem);
-		zds->outBuffSize = neededOutSize;
-		if (zds->inBuff == NULL || zds->outBuff == NULL) {
-			ZSTD_freeDStream(zds);
-			return NULL;
-		}
-	}
-	return zds;
-}
-
-ZSTD_DStream *ZSTD_initDStream_usingDDict(size_t maxWindowSize, const ZSTD_DDict *ddict, void *workspace, size_t workspaceSize)
-{
-	ZSTD_DStream *zds = ZSTD_initDStream(maxWindowSize, workspace, workspaceSize);
-	if (zds) {
-		zds->ddict = ddict;
-	}
-	return zds;
-}
-
-size_t ZSTD_freeDStream(ZSTD_DStream *zds)
-{
-	if (zds == NULL)
-		return 0; /* support free on null */
-	{
-		ZSTD_customMem const cMem = zds->customMem;
-		ZSTD_freeDCtx(zds->dctx);
-		zds->dctx = NULL;
-		ZSTD_freeDDict(zds->ddictLocal);
-		zds->ddictLocal = NULL;
-		ZSTD_free(zds->inBuff, cMem);
-		zds->inBuff = NULL;
-		ZSTD_free(zds->outBuff, cMem);
-		zds->outBuff = NULL;
-		ZSTD_free(zds, cMem);
-		return 0;
-	}
-}
-
-/* *** Initialization *** */
-
-size_t ZSTD_DStreamInSize(void) { return ZSTD_BLOCKSIZE_ABSOLUTEMAX + ZSTD_blockHeaderSize; }
-size_t ZSTD_DStreamOutSize(void) { return ZSTD_BLOCKSIZE_ABSOLUTEMAX; }
-
-size_t ZSTD_resetDStream(ZSTD_DStream *zds)
-{
-	zds->stage = zdss_loadHeader;
-	zds->lhSize = zds->inPos = zds->outStart = zds->outEnd = 0;
-	zds->legacyVersion = 0;
-	zds->hostageByte = 0;
-	return ZSTD_frameHeaderSize_prefix;
-}
-
-/* *****   Decompression   ***** */
-
-ZSTD_STATIC size_t ZSTD_limitCopy(void *dst, size_t dstCapacity, const void *src, size_t srcSize)
-{
-	size_t const length = MIN(dstCapacity, srcSize);
-	memcpy(dst, src, length);
-	return length;
-}
-
-size_t ZSTD_decompressStream(ZSTD_DStream *zds, ZSTD_outBuffer *output, ZSTD_inBuffer *input)
-{
-	const char *const istart = (const char *)(input->src) + input->pos;
-	const char *const iend = (const char *)(input->src) + input->size;
-	const char *ip = istart;
-	char *const ostart = (char *)(output->dst) + output->pos;
-	char *const oend = (char *)(output->dst) + output->size;
-	char *op = ostart;
-	U32 someMoreWork = 1;
-
-	while (someMoreWork) {
-		switch (zds->stage) {
-		case zdss_init:
-			ZSTD_resetDStream(zds); /* transparent reset on starting decoding a new frame */
-			fallthrough;
-
-		case zdss_loadHeader: {
-			size_t const hSize = ZSTD_getFrameParams(&zds->fParams, zds->headerBuffer, zds->lhSize);
-			if (ZSTD_isError(hSize))
-				return hSize;
-			if (hSize != 0) {				   /* need more input */
-				size_t const toLoad = hSize - zds->lhSize; /* if hSize!=0, hSize > zds->lhSize */
-				if (toLoad > (size_t)(iend - ip)) {	/* not enough input to load full header */
-					memcpy(zds->headerBuffer + zds->lhSize, ip, iend - ip);
-					zds->lhSize += iend - ip;
-					input->pos = input->size;
-					return (MAX(ZSTD_frameHeaderSize_min, hSize) - zds->lhSize) +
-					       ZSTD_blockHeaderSize; /* remaining header bytes + next block header */
-				}
-				memcpy(zds->headerBuffer + zds->lhSize, ip, toLoad);
-				zds->lhSize = hSize;
-				ip += toLoad;
-				break;
-			}
-
-			/* check for single-pass mode opportunity */
-			if (zds->fParams.frameContentSize && zds->fParams.windowSize /* skippable frame if == 0 */
-			    && (U64)(size_t)(oend - op) >= zds->fParams.frameContentSize) {
-				size_t const cSize = ZSTD_findFrameCompressedSize(istart, iend - istart);
-				if (cSize <= (size_t)(iend - istart)) {
-					size_t const decompressedSize = ZSTD_decompress_usingDDict(zds->dctx, op, oend - op, istart, cSize, zds->ddict);
-					if (ZSTD_isError(decompressedSize))
-						return decompressedSize;
-					ip = istart + cSize;
-					op += decompressedSize;
-					zds->dctx->expected = 0;
-					zds->stage = zdss_init;
-					someMoreWork = 0;
-					break;
-				}
-			}
-
-			/* Consume header */
-			ZSTD_refDDict(zds->dctx, zds->ddict);
-			{
-				size_t const h1Size = ZSTD_nextSrcSizeToDecompress(zds->dctx); /* == ZSTD_frameHeaderSize_prefix */
-				CHECK_F(ZSTD_decompressContinue(zds->dctx, NULL, 0, zds->headerBuffer, h1Size));
-				{
-					size_t const h2Size = ZSTD_nextSrcSizeToDecompress(zds->dctx);
-					CHECK_F(ZSTD_decompressContinue(zds->dctx, NULL, 0, zds->headerBuffer + h1Size, h2Size));
-				}
-			}
-
-			zds->fParams.windowSize = MAX(zds->fParams.windowSize, 1U << ZSTD_WINDOWLOG_ABSOLUTEMIN);
-			if (zds->fParams.windowSize > zds->maxWindowSize)
-				return ERROR(frameParameter_windowTooLarge);
-
-			/* Buffers are preallocated, but double check */
-			{
-				size_t const blockSize = MIN(zds->maxWindowSize, ZSTD_BLOCKSIZE_ABSOLUTEMAX);
-				size_t const neededOutSize = zds->maxWindowSize + blockSize + WILDCOPY_OVERLENGTH * 2;
-				if (zds->inBuffSize < blockSize) {
-					return ERROR(GENERIC);
-				}
-				if (zds->outBuffSize < neededOutSize) {
-					return ERROR(GENERIC);
-				}
-				zds->blockSize = blockSize;
-			}
-			zds->stage = zdss_read;
-		}
-			fallthrough;
-
-		case zdss_read: {
-			size_t const neededInSize = ZSTD_nextSrcSizeToDecompress(zds->dctx);
-			if (neededInSize == 0) { /* end of frame */
-				zds->stage = zdss_init;
-				someMoreWork = 0;
-				break;
-			}
-			if ((size_t)(iend - ip) >= neededInSize) { /* decode directly from src */
-				const int isSkipFrame = ZSTD_isSkipFrame(zds->dctx);
-				size_t const decodedSize = ZSTD_decompressContinue(zds->dctx, zds->outBuff + zds->outStart,
-										   (isSkipFrame ? 0 : zds->outBuffSize - zds->outStart), ip, neededInSize);
-				if (ZSTD_isError(decodedSize))
-					return decodedSize;
-				ip += neededInSize;
-				if (!decodedSize && !isSkipFrame)
-					break; /* this was just a header */
-				zds->outEnd = zds->outStart + decodedSize;
-				zds->stage = zdss_flush;
-				break;
-			}
-			if (ip == iend) {
-				someMoreWork = 0;
-				break;
-			} /* no more input */
-			zds->stage = zdss_load;
-			/* pass-through */
-		}
-			fallthrough;
-
-		case zdss_load: {
-			size_t const neededInSize = ZSTD_nextSrcSizeToDecompress(zds->dctx);
-			size_t const toLoad = neededInSize - zds->inPos; /* should always be <= remaining space within inBuff */
-			size_t loadedSize;
-			if (toLoad > zds->inBuffSize - zds->inPos)
-				return ERROR(corruption_detected); /* should never happen */
-			loadedSize = ZSTD_limitCopy(zds->inBuff + zds->inPos, toLoad, ip, iend - ip);
-			ip += loadedSize;
-			zds->inPos += loadedSize;
-			if (loadedSize < toLoad) {
-				someMoreWork = 0;
-				break;
-			} /* not enough input, wait for more */
-
-			/* decode loaded input */
-			{
-				const int isSkipFrame = ZSTD_isSkipFrame(zds->dctx);
-				size_t const decodedSize = ZSTD_decompressContinue(zds->dctx, zds->outBuff + zds->outStart, zds->outBuffSize - zds->outStart,
-										   zds->inBuff, neededInSize);
-				if (ZSTD_isError(decodedSize))
-					return decodedSize;
-				zds->inPos = 0; /* input is consumed */
-				if (!decodedSize && !isSkipFrame) {
-					zds->stage = zdss_read;
-					break;
-				} /* this was just a header */
-				zds->outEnd = zds->outStart + decodedSize;
-				zds->stage = zdss_flush;
-				/* pass-through */
-			}
-		}
-			fallthrough;
-
-		case zdss_flush: {
-			size_t const toFlushSize = zds->outEnd - zds->outStart;
-			size_t const flushedSize = ZSTD_limitCopy(op, oend - op, zds->outBuff + zds->outStart, toFlushSize);
-			op += flushedSize;
-			zds->outStart += flushedSize;
-			if (flushedSize == toFlushSize) { /* flush completed */
-				zds->stage = zdss_read;
-				if (zds->outStart + zds->blockSize > zds->outBuffSize)
-					zds->outStart = zds->outEnd = 0;
-				break;
-			}
-			/* cannot complete flush */
-			someMoreWork = 0;
-			break;
-		}
-		default:
-			return ERROR(GENERIC); /* impossible */
-		}
-	}
-
-	/* result */
-	input->pos += (size_t)(ip - istart);
-	output->pos += (size_t)(op - ostart);
-	{
-		size_t nextSrcSizeHint = ZSTD_nextSrcSizeToDecompress(zds->dctx);
-		if (!nextSrcSizeHint) {			    /* frame fully decoded */
-			if (zds->outEnd == zds->outStart) { /* output fully flushed */
-				if (zds->hostageByte) {
-					if (input->pos >= input->size) {
-						zds->stage = zdss_read;
-						return 1;
-					}	     /* can't release hostage (not present) */
-					input->pos++; /* release hostage */
-				}
-				return 0;
-			}
-			if (!zds->hostageByte) { /* output not fully flushed; keep last byte as hostage; will be released when all output is flushed */
-				input->pos--;    /* note : pos > 0, otherwise, impossible to finish reading last block */
-				zds->hostageByte = 1;
-			}
-			return 1;
-		}
-		nextSrcSizeHint += ZSTD_blockHeaderSize * (ZSTD_nextInputType(zds->dctx) == ZSTDnit_block); /* preload header of next block */
-		if (zds->inPos > nextSrcSizeHint)
-			return ERROR(GENERIC); /* should never happen */
-		nextSrcSizeHint -= zds->inPos; /* already loaded*/
-		return nextSrcSizeHint;
-	}
-}
-
-EXPORT_SYMBOL(ZSTD_DCtxWorkspaceBound);
-EXPORT_SYMBOL(ZSTD_initDCtx);
-EXPORT_SYMBOL(ZSTD_decompressDCtx);
-EXPORT_SYMBOL(ZSTD_decompress_usingDict);
-
-EXPORT_SYMBOL(ZSTD_DDictWorkspaceBound);
-EXPORT_SYMBOL(ZSTD_initDDict);
-EXPORT_SYMBOL(ZSTD_decompress_usingDDict);
-
-EXPORT_SYMBOL(ZSTD_DStreamWorkspaceBound);
-EXPORT_SYMBOL(ZSTD_initDStream);
-EXPORT_SYMBOL(ZSTD_initDStream_usingDDict);
-EXPORT_SYMBOL(ZSTD_resetDStream);
-EXPORT_SYMBOL(ZSTD_decompressStream);
-EXPORT_SYMBOL(ZSTD_DStreamInSize);
-EXPORT_SYMBOL(ZSTD_DStreamOutSize);
-
-EXPORT_SYMBOL(ZSTD_findFrameCompressedSize);
-EXPORT_SYMBOL(ZSTD_getFrameContentSize);
-EXPORT_SYMBOL(ZSTD_findDecompressedSize);
-
-EXPORT_SYMBOL(ZSTD_isFrame);
-EXPORT_SYMBOL(ZSTD_getDictID_fromDict);
-EXPORT_SYMBOL(ZSTD_getDictID_fromDDict);
-EXPORT_SYMBOL(ZSTD_getDictID_fromFrame);
-
-EXPORT_SYMBOL(ZSTD_getFrameParams);
-EXPORT_SYMBOL(ZSTD_decompressBegin);
-EXPORT_SYMBOL(ZSTD_decompressBegin_usingDict);
-EXPORT_SYMBOL(ZSTD_copyDCtx);
-EXPORT_SYMBOL(ZSTD_nextSrcSizeToDecompress);
-EXPORT_SYMBOL(ZSTD_decompressContinue);
-EXPORT_SYMBOL(ZSTD_nextInputType);
-
-EXPORT_SYMBOL(ZSTD_decompressBlock);
-EXPORT_SYMBOL(ZSTD_insertBlock);
-
-MODULE_LICENSE("Dual BSD/GPL");
-MODULE_DESCRIPTION("Zstd Decompressor");
diff --git a/lib/zstd/decompress/huf_decompress.c b/lib/zstd/decompress/huf_decompress.c
new file mode 100644
index 000000000000..5105e59ac04a
--- /dev/null
+++ b/lib/zstd/decompress/huf_decompress.c
@@ -0,0 +1,1206 @@
+/* ******************************************************************
+ * huff0 huffman decoder,
+ * part of Finite State Entropy library
+ * Copyright (c) Yann Collet, Facebook, Inc.
+ *
+ *  You can contact the author at :
+ *  - FSE+HUF source repository : https://github.com/Cyan4973/FiniteStateEntropy
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+****************************************************************** */
+
+/* **************************************************************
+*  Dependencies
+****************************************************************/
+#include "../common/zstd_deps.h"  /* ZSTD_memcpy, ZSTD_memset */
+#include "../common/compiler.h"
+#include "../common/bitstream.h"  /* BIT_* */
+#include "../common/fse.h"        /* to compress headers */
+#define HUF_STATIC_LINKING_ONLY
+#include "../common/huf.h"
+#include "../common/error_private.h"
+
+/* **************************************************************
+*  Macros
+****************************************************************/
+
+/* These two optional macros force the use one way or another of the two
+ * Huffman decompression implementations. You can't force in both directions
+ * at the same time.
+ */
+#if defined(HUF_FORCE_DECOMPRESS_X1) && \
+    defined(HUF_FORCE_DECOMPRESS_X2)
+#error "Cannot force the use of the X1 and X2 decoders at the same time!"
+#endif
+
+
+/* **************************************************************
+*  Error Management
+****************************************************************/
+#define HUF_isError ERR_isError
+
+
+/* **************************************************************
+*  Byte alignment for workSpace management
+****************************************************************/
+#define HUF_ALIGN(x, a)         HUF_ALIGN_MASK((x), (a) - 1)
+#define HUF_ALIGN_MASK(x, mask) (((x) + (mask)) & ~(mask))
+
+
+/* **************************************************************
+*  BMI2 Variant Wrappers
+****************************************************************/
+#if DYNAMIC_BMI2
+
+#define HUF_DGEN(fn)                                                        \
+                                                                            \
+    static size_t fn##_default(                                             \
+                  void* dst,  size_t dstSize,                               \
+            const void* cSrc, size_t cSrcSize,                              \
+            const HUF_DTable* DTable)                                       \
+    {                                                                       \
+        return fn##_body(dst, dstSize, cSrc, cSrcSize, DTable);             \
+    }                                                                       \
+                                                                            \
+    static TARGET_ATTRIBUTE("bmi2") size_t fn##_bmi2(                       \
+                  void* dst,  size_t dstSize,                               \
+            const void* cSrc, size_t cSrcSize,                              \
+            const HUF_DTable* DTable)                                       \
+    {                                                                       \
+        return fn##_body(dst, dstSize, cSrc, cSrcSize, DTable);             \
+    }                                                                       \
+                                                                            \
+    static size_t fn(void* dst, size_t dstSize, void const* cSrc,           \
+                     size_t cSrcSize, HUF_DTable const* DTable, int bmi2)   \
+    {                                                                       \
+        if (bmi2) {                                                         \
+            return fn##_bmi2(dst, dstSize, cSrc, cSrcSize, DTable);         \
+        }                                                                   \
+        return fn##_default(dst, dstSize, cSrc, cSrcSize, DTable);          \
+    }
+
+#else
+
+#define HUF_DGEN(fn)                                                        \
+    static size_t fn(void* dst, size_t dstSize, void const* cSrc,           \
+                     size_t cSrcSize, HUF_DTable const* DTable, int bmi2)   \
+    {                                                                       \
+        (void)bmi2;                                                         \
+        return fn##_body(dst, dstSize, cSrc, cSrcSize, DTable);             \
+    }
+
+#endif
+
+
+/*-***************************/
+/*  generic DTableDesc       */
+/*-***************************/
+typedef struct { BYTE maxTableLog; BYTE tableType; BYTE tableLog; BYTE reserved; } DTableDesc;
+
+static DTableDesc HUF_getDTableDesc(const HUF_DTable* table)
+{
+    DTableDesc dtd;
+    ZSTD_memcpy(&dtd, table, sizeof(dtd));
+    return dtd;
+}
+
+
+#ifndef HUF_FORCE_DECOMPRESS_X2
+
+/*-***************************/
+/*  single-symbol decoding   */
+/*-***************************/
+typedef struct { BYTE byte; BYTE nbBits; } HUF_DEltX1;   /* single-symbol decoding */
+
+/*
+ * Packs 4 HUF_DEltX1 structs into a U64. This is used to lay down 4 entries at
+ * a time.
+ */
+static U64 HUF_DEltX1_set4(BYTE symbol, BYTE nbBits) {
+    U64 D4;
+    if (MEM_isLittleEndian()) {
+        D4 = symbol + (nbBits << 8);
+    } else {
+        D4 = (symbol << 8) + nbBits;
+    }
+    D4 *= 0x0001000100010001ULL;
+    return D4;
+}
+
+typedef struct {
+        U32 rankVal[HUF_TABLELOG_ABSOLUTEMAX + 1];
+        U32 rankStart[HUF_TABLELOG_ABSOLUTEMAX + 1];
+        U32 statsWksp[HUF_READ_STATS_WORKSPACE_SIZE_U32];
+        BYTE symbols[HUF_SYMBOLVALUE_MAX + 1];
+        BYTE huffWeight[HUF_SYMBOLVALUE_MAX + 1];
+} HUF_ReadDTableX1_Workspace;
+
+
+size_t HUF_readDTableX1_wksp(HUF_DTable* DTable, const void* src, size_t srcSize, void* workSpace, size_t wkspSize)
+{
+    return HUF_readDTableX1_wksp_bmi2(DTable, src, srcSize, workSpace, wkspSize, /* bmi2 */ 0);
+}
+
+size_t HUF_readDTableX1_wksp_bmi2(HUF_DTable* DTable, const void* src, size_t srcSize, void* workSpace, size_t wkspSize, int bmi2)
+{
+    U32 tableLog = 0;
+    U32 nbSymbols = 0;
+    size_t iSize;
+    void* const dtPtr = DTable + 1;
+    HUF_DEltX1* const dt = (HUF_DEltX1*)dtPtr;
+    HUF_ReadDTableX1_Workspace* wksp = (HUF_ReadDTableX1_Workspace*)workSpace;
+
+    DEBUG_STATIC_ASSERT(HUF_DECOMPRESS_WORKSPACE_SIZE >= sizeof(*wksp));
+    if (sizeof(*wksp) > wkspSize) return ERROR(tableLog_tooLarge);
+
+    DEBUG_STATIC_ASSERT(sizeof(DTableDesc) == sizeof(HUF_DTable));
+    /* ZSTD_memset(huffWeight, 0, sizeof(huffWeight)); */   /* is not necessary, even though some analyzer complain ... */
+
+    iSize = HUF_readStats_wksp(wksp->huffWeight, HUF_SYMBOLVALUE_MAX + 1, wksp->rankVal, &nbSymbols, &tableLog, src, srcSize, wksp->statsWksp, sizeof(wksp->statsWksp), bmi2);
+    if (HUF_isError(iSize)) return iSize;
+
+    /* Table header */
+    {   DTableDesc dtd = HUF_getDTableDesc(DTable);
+        if (tableLog > (U32)(dtd.maxTableLog+1)) return ERROR(tableLog_tooLarge);   /* DTable too small, Huffman tree cannot fit in */
+        dtd.tableType = 0;
+        dtd.tableLog = (BYTE)tableLog;
+        ZSTD_memcpy(DTable, &dtd, sizeof(dtd));
+    }
+
+    /* Compute symbols and rankStart given rankVal:
+     *
+     * rankVal already contains the number of values of each weight.
+     *
+     * symbols contains the symbols ordered by weight. First are the rankVal[0]
+     * weight 0 symbols, followed by the rankVal[1] weight 1 symbols, and so on.
+     * symbols[0] is filled (but unused) to avoid a branch.
+     *
+     * rankStart contains the offset where each rank belongs in the DTable.
+     * rankStart[0] is not filled because there are no entries in the table for
+     * weight 0.
+     */
+    {
+        int n;
+        int nextRankStart = 0;
+        int const unroll = 4;
+        int const nLimit = (int)nbSymbols - unroll + 1;
+        for (n=0; n<(int)tableLog+1; n++) {
+            U32 const curr = nextRankStart;
+            nextRankStart += wksp->rankVal[n];
+            wksp->rankStart[n] = curr;
+        }
+        for (n=0; n < nLimit; n += unroll) {
+            int u;
+            for (u=0; u < unroll; ++u) {
+                size_t const w = wksp->huffWeight[n+u];
+                wksp->symbols[wksp->rankStart[w]++] = (BYTE)(n+u);
+            }
+        }
+        for (; n < (int)nbSymbols; ++n) {
+            size_t const w = wksp->huffWeight[n];
+            wksp->symbols[wksp->rankStart[w]++] = (BYTE)n;
+        }
+    }
+
+    /* fill DTable
+     * We fill all entries of each weight in order.
+     * That way length is a constant for each iteration of the outter loop.
+     * We can switch based on the length to a different inner loop which is
+     * optimized for that particular case.
+     */
+    {
+        U32 w;
+        int symbol=wksp->rankVal[0];
+        int rankStart=0;
+        for (w=1; w<tableLog+1; ++w) {
+            int const symbolCount = wksp->rankVal[w];
+            int const length = (1 << w) >> 1;
+            int uStart = rankStart;
+            BYTE const nbBits = (BYTE)(tableLog + 1 - w);
+            int s;
+            int u;
+            switch (length) {
+            case 1:
+                for (s=0; s<symbolCount; ++s) {
+                    HUF_DEltX1 D;
+                    D.byte = wksp->symbols[symbol + s];
+                    D.nbBits = nbBits;
+                    dt[uStart] = D;
+                    uStart += 1;
+                }
+                break;
+            case 2:
+                for (s=0; s<symbolCount; ++s) {
+                    HUF_DEltX1 D;
+                    D.byte = wksp->symbols[symbol + s];
+                    D.nbBits = nbBits;
+                    dt[uStart+0] = D;
+                    dt[uStart+1] = D;
+                    uStart += 2;
+                }
+                break;
+            case 4:
+                for (s=0; s<symbolCount; ++s) {
+                    U64 const D4 = HUF_DEltX1_set4(wksp->symbols[symbol + s], nbBits);
+                    MEM_write64(dt + uStart, D4);
+                    uStart += 4;
+                }
+                break;
+            case 8:
+                for (s=0; s<symbolCount; ++s) {
+                    U64 const D4 = HUF_DEltX1_set4(wksp->symbols[symbol + s], nbBits);
+                    MEM_write64(dt + uStart, D4);
+                    MEM_write64(dt + uStart + 4, D4);
+                    uStart += 8;
+                }
+                break;
+            default:
+                for (s=0; s<symbolCount; ++s) {
+                    U64 const D4 = HUF_DEltX1_set4(wksp->symbols[symbol + s], nbBits);
+                    for (u=0; u < length; u += 16) {
+                        MEM_write64(dt + uStart + u + 0, D4);
+                        MEM_write64(dt + uStart + u + 4, D4);
+                        MEM_write64(dt + uStart + u + 8, D4);
+                        MEM_write64(dt + uStart + u + 12, D4);
+                    }
+                    assert(u == length);
+                    uStart += length;
+                }
+                break;
+            }
+            symbol += symbolCount;
+            rankStart += symbolCount * length;
+        }
+    }
+    return iSize;
+}
+
+FORCE_INLINE_TEMPLATE BYTE
+HUF_decodeSymbolX1(BIT_DStream_t* Dstream, const HUF_DEltX1* dt, const U32 dtLog)
+{
+    size_t const val = BIT_lookBitsFast(Dstream, dtLog); /* note : dtLog >= 1 */
+    BYTE const c = dt[val].byte;
+    BIT_skipBits(Dstream, dt[val].nbBits);
+    return c;
+}
+
+#define HUF_DECODE_SYMBOLX1_0(ptr, DStreamPtr) \
+    *ptr++ = HUF_decodeSymbolX1(DStreamPtr, dt, dtLog)
+
+#define HUF_DECODE_SYMBOLX1_1(ptr, DStreamPtr)  \
+    if (MEM_64bits() || (HUF_TABLELOG_MAX<=12)) \
+        HUF_DECODE_SYMBOLX1_0(ptr, DStreamPtr)
+
+#define HUF_DECODE_SYMBOLX1_2(ptr, DStreamPtr) \
+    if (MEM_64bits()) \
+        HUF_DECODE_SYMBOLX1_0(ptr, DStreamPtr)
+
+HINT_INLINE size_t
+HUF_decodeStreamX1(BYTE* p, BIT_DStream_t* const bitDPtr, BYTE* const pEnd, const HUF_DEltX1* const dt, const U32 dtLog)
+{
+    BYTE* const pStart = p;
+
+    /* up to 4 symbols at a time */
+    while ((BIT_reloadDStream(bitDPtr) == BIT_DStream_unfinished) & (p < pEnd-3)) {
+        HUF_DECODE_SYMBOLX1_2(p, bitDPtr);
+        HUF_DECODE_SYMBOLX1_1(p, bitDPtr);
+        HUF_DECODE_SYMBOLX1_2(p, bitDPtr);
+        HUF_DECODE_SYMBOLX1_0(p, bitDPtr);
+    }
+
+    /* [0-3] symbols remaining */
+    if (MEM_32bits())
+        while ((BIT_reloadDStream(bitDPtr) == BIT_DStream_unfinished) & (p < pEnd))
+            HUF_DECODE_SYMBOLX1_0(p, bitDPtr);
+
+    /* no more data to retrieve from bitstream, no need to reload */
+    while (p < pEnd)
+        HUF_DECODE_SYMBOLX1_0(p, bitDPtr);
+
+    return pEnd-pStart;
+}
+
+FORCE_INLINE_TEMPLATE size_t
+HUF_decompress1X1_usingDTable_internal_body(
+          void* dst,  size_t dstSize,
+    const void* cSrc, size_t cSrcSize,
+    const HUF_DTable* DTable)
+{
+    BYTE* op = (BYTE*)dst;
+    BYTE* const oend = op + dstSize;
+    const void* dtPtr = DTable + 1;
+    const HUF_DEltX1* const dt = (const HUF_DEltX1*)dtPtr;
+    BIT_DStream_t bitD;
+    DTableDesc const dtd = HUF_getDTableDesc(DTable);
+    U32 const dtLog = dtd.tableLog;
+
+    CHECK_F( BIT_initDStream(&bitD, cSrc, cSrcSize) );
+
+    HUF_decodeStreamX1(op, &bitD, oend, dt, dtLog);
+
+    if (!BIT_endOfDStream(&bitD)) return ERROR(corruption_detected);
+
+    return dstSize;
+}
+
+FORCE_INLINE_TEMPLATE size_t
+HUF_decompress4X1_usingDTable_internal_body(
+          void* dst,  size_t dstSize,
+    const void* cSrc, size_t cSrcSize,
+    const HUF_DTable* DTable)
+{
+    /* Check */
+    if (cSrcSize < 10) return ERROR(corruption_detected);  /* strict minimum : jump table + 1 byte per stream */
+
+    {   const BYTE* const istart = (const BYTE*) cSrc;
+        BYTE* const ostart = (BYTE*) dst;
+        BYTE* const oend = ostart + dstSize;
+        BYTE* const olimit = oend - 3;
+        const void* const dtPtr = DTable + 1;
+        const HUF_DEltX1* const dt = (const HUF_DEltX1*)dtPtr;
+
+        /* Init */
+        BIT_DStream_t bitD1;
+        BIT_DStream_t bitD2;
+        BIT_DStream_t bitD3;
+        BIT_DStream_t bitD4;
+        size_t const length1 = MEM_readLE16(istart);
+        size_t const length2 = MEM_readLE16(istart+2);
+        size_t const length3 = MEM_readLE16(istart+4);
+        size_t const length4 = cSrcSize - (length1 + length2 + length3 + 6);
+        const BYTE* const istart1 = istart + 6;  /* jumpTable */
+        const BYTE* const istart2 = istart1 + length1;
+        const BYTE* const istart3 = istart2 + length2;
+        const BYTE* const istart4 = istart3 + length3;
+        const size_t segmentSize = (dstSize+3) / 4;
+        BYTE* const opStart2 = ostart + segmentSize;
+        BYTE* const opStart3 = opStart2 + segmentSize;
+        BYTE* const opStart4 = opStart3 + segmentSize;
+        BYTE* op1 = ostart;
+        BYTE* op2 = opStart2;
+        BYTE* op3 = opStart3;
+        BYTE* op4 = opStart4;
+        DTableDesc const dtd = HUF_getDTableDesc(DTable);
+        U32 const dtLog = dtd.tableLog;
+        U32 endSignal = 1;
+
+        if (length4 > cSrcSize) return ERROR(corruption_detected);   /* overflow */
+        CHECK_F( BIT_initDStream(&bitD1, istart1, length1) );
+        CHECK_F( BIT_initDStream(&bitD2, istart2, length2) );
+        CHECK_F( BIT_initDStream(&bitD3, istart3, length3) );
+        CHECK_F( BIT_initDStream(&bitD4, istart4, length4) );
+
+        /* up to 16 symbols per loop (4 symbols per stream) in 64-bit mode */
+        for ( ; (endSignal) & (op4 < olimit) ; ) {
+            HUF_DECODE_SYMBOLX1_2(op1, &bitD1);
+            HUF_DECODE_SYMBOLX1_2(op2, &bitD2);
+            HUF_DECODE_SYMBOLX1_2(op3, &bitD3);
+            HUF_DECODE_SYMBOLX1_2(op4, &bitD4);
+            HUF_DECODE_SYMBOLX1_1(op1, &bitD1);
+            HUF_DECODE_SYMBOLX1_1(op2, &bitD2);
+            HUF_DECODE_SYMBOLX1_1(op3, &bitD3);
+            HUF_DECODE_SYMBOLX1_1(op4, &bitD4);
+            HUF_DECODE_SYMBOLX1_2(op1, &bitD1);
+            HUF_DECODE_SYMBOLX1_2(op2, &bitD2);
+            HUF_DECODE_SYMBOLX1_2(op3, &bitD3);
+            HUF_DECODE_SYMBOLX1_2(op4, &bitD4);
+            HUF_DECODE_SYMBOLX1_0(op1, &bitD1);
+            HUF_DECODE_SYMBOLX1_0(op2, &bitD2);
+            HUF_DECODE_SYMBOLX1_0(op3, &bitD3);
+            HUF_DECODE_SYMBOLX1_0(op4, &bitD4);
+            endSignal &= BIT_reloadDStreamFast(&bitD1) == BIT_DStream_unfinished;
+            endSignal &= BIT_reloadDStreamFast(&bitD2) == BIT_DStream_unfinished;
+            endSignal &= BIT_reloadDStreamFast(&bitD3) == BIT_DStream_unfinished;
+            endSignal &= BIT_reloadDStreamFast(&bitD4) == BIT_DStream_unfinished;
+        }
+
+        /* check corruption */
+        /* note : should not be necessary : op# advance in lock step, and we control op4.
+         *        but curiously, binary generated by gcc 7.2 & 7.3 with -mbmi2 runs faster when >=1 test is present */
+        if (op1 > opStart2) return ERROR(corruption_detected);
+        if (op2 > opStart3) return ERROR(corruption_detected);
+        if (op3 > opStart4) return ERROR(corruption_detected);
+        /* note : op4 supposed already verified within main loop */
+
+        /* finish bitStreams one by one */
+        HUF_decodeStreamX1(op1, &bitD1, opStart2, dt, dtLog);
+        HUF_decodeStreamX1(op2, &bitD2, opStart3, dt, dtLog);
+        HUF_decodeStreamX1(op3, &bitD3, opStart4, dt, dtLog);
+        HUF_decodeStreamX1(op4, &bitD4, oend,     dt, dtLog);
+
+        /* check */
+        { U32 const endCheck = BIT_endOfDStream(&bitD1) & BIT_endOfDStream(&bitD2) & BIT_endOfDStream(&bitD3) & BIT_endOfDStream(&bitD4);
+          if (!endCheck) return ERROR(corruption_detected); }
+
+        /* decoded size */
+        return dstSize;
+    }
+}
+
+
+typedef size_t (*HUF_decompress_usingDTable_t)(void *dst, size_t dstSize,
+                                               const void *cSrc,
+                                               size_t cSrcSize,
+                                               const HUF_DTable *DTable);
+
+HUF_DGEN(HUF_decompress1X1_usingDTable_internal)
+HUF_DGEN(HUF_decompress4X1_usingDTable_internal)
+
+
+
+size_t HUF_decompress1X1_usingDTable(
+          void* dst,  size_t dstSize,
+    const void* cSrc, size_t cSrcSize,
+    const HUF_DTable* DTable)
+{
+    DTableDesc dtd = HUF_getDTableDesc(DTable);
+    if (dtd.tableType != 0) return ERROR(GENERIC);
+    return HUF_decompress1X1_usingDTable_internal(dst, dstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0);
+}
+
+size_t HUF_decompress1X1_DCtx_wksp(HUF_DTable* DCtx, void* dst, size_t dstSize,
+                                   const void* cSrc, size_t cSrcSize,
+                                   void* workSpace, size_t wkspSize)
+{
+    const BYTE* ip = (const BYTE*) cSrc;
+
+    size_t const hSize = HUF_readDTableX1_wksp(DCtx, cSrc, cSrcSize, workSpace, wkspSize);
+    if (HUF_isError(hSize)) return hSize;
+    if (hSize >= cSrcSize) return ERROR(srcSize_wrong);
+    ip += hSize; cSrcSize -= hSize;
+
+    return HUF_decompress1X1_usingDTable_internal(dst, dstSize, ip, cSrcSize, DCtx, /* bmi2 */ 0);
+}
+
+
+size_t HUF_decompress4X1_usingDTable(
+          void* dst,  size_t dstSize,
+    const void* cSrc, size_t cSrcSize,
+    const HUF_DTable* DTable)
+{
+    DTableDesc dtd = HUF_getDTableDesc(DTable);
+    if (dtd.tableType != 0) return ERROR(GENERIC);
+    return HUF_decompress4X1_usingDTable_internal(dst, dstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0);
+}
+
+static size_t HUF_decompress4X1_DCtx_wksp_bmi2(HUF_DTable* dctx, void* dst, size_t dstSize,
+                                   const void* cSrc, size_t cSrcSize,
+                                   void* workSpace, size_t wkspSize, int bmi2)
+{
+    const BYTE* ip = (const BYTE*) cSrc;
+
+    size_t const hSize = HUF_readDTableX1_wksp_bmi2(dctx, cSrc, cSrcSize, workSpace, wkspSize, bmi2);
+    if (HUF_isError(hSize)) return hSize;
+    if (hSize >= cSrcSize) return ERROR(srcSize_wrong);
+    ip += hSize; cSrcSize -= hSize;
+
+    return HUF_decompress4X1_usingDTable_internal(dst, dstSize, ip, cSrcSize, dctx, bmi2);
+}
+
+size_t HUF_decompress4X1_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize,
+                                   const void* cSrc, size_t cSrcSize,
+                                   void* workSpace, size_t wkspSize)
+{
+    return HUF_decompress4X1_DCtx_wksp_bmi2(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize, 0);
+}
+
+
+#endif /* HUF_FORCE_DECOMPRESS_X2 */
+
+
+#ifndef HUF_FORCE_DECOMPRESS_X1
+
+/* *************************/
+/* double-symbols decoding */
+/* *************************/
+
+typedef struct { U16 sequence; BYTE nbBits; BYTE length; } HUF_DEltX2;  /* double-symbols decoding */
+typedef struct { BYTE symbol; BYTE weight; } sortedSymbol_t;
+typedef U32 rankValCol_t[HUF_TABLELOG_MAX + 1];
+typedef rankValCol_t rankVal_t[HUF_TABLELOG_MAX];
+
+
+/* HUF_fillDTableX2Level2() :
+ * `rankValOrigin` must be a table of at least (HUF_TABLELOG_MAX + 1) U32 */
+static void HUF_fillDTableX2Level2(HUF_DEltX2* DTable, U32 sizeLog, const U32 consumed,
+                           const U32* rankValOrigin, const int minWeight,
+                           const sortedSymbol_t* sortedSymbols, const U32 sortedListSize,
+                           U32 nbBitsBaseline, U16 baseSeq, U32* wksp, size_t wkspSize)
+{
+    HUF_DEltX2 DElt;
+    U32* rankVal = wksp;
+
+    assert(wkspSize >= HUF_TABLELOG_MAX + 1);
+    (void)wkspSize;
+    /* get pre-calculated rankVal */
+    ZSTD_memcpy(rankVal, rankValOrigin, sizeof(U32) * (HUF_TABLELOG_MAX + 1));
+
+    /* fill skipped values */
+    if (minWeight>1) {
+        U32 i, skipSize = rankVal[minWeight];
+        MEM_writeLE16(&(DElt.sequence), baseSeq);
+        DElt.nbBits   = (BYTE)(consumed);
+        DElt.length   = 1;
+        for (i = 0; i < skipSize; i++)
+            DTable[i] = DElt;
+    }
+
+    /* fill DTable */
+    {   U32 s; for (s=0; s<sortedListSize; s++) {   /* note : sortedSymbols already skipped */
+            const U32 symbol = sortedSymbols[s].symbol;
+            const U32 weight = sortedSymbols[s].weight;
+            const U32 nbBits = nbBitsBaseline - weight;
+            const U32 length = 1 << (sizeLog-nbBits);
+            const U32 start = rankVal[weight];
+            U32 i = start;
+            const U32 end = start + length;
+
+            MEM_writeLE16(&(DElt.sequence), (U16)(baseSeq + (symbol << 8)));
+            DElt.nbBits = (BYTE)(nbBits + consumed);
+            DElt.length = 2;
+            do { DTable[i++] = DElt; } while (i<end);   /* since length >= 1 */
+
+            rankVal[weight] += length;
+    }   }
+}
+
+
+static void HUF_fillDTableX2(HUF_DEltX2* DTable, const U32 targetLog,
+                           const sortedSymbol_t* sortedList, const U32 sortedListSize,
+                           const U32* rankStart, rankVal_t rankValOrigin, const U32 maxWeight,
+                           const U32 nbBitsBaseline, U32* wksp, size_t wkspSize)
+{
+    U32* rankVal = wksp;
+    const int scaleLog = nbBitsBaseline - targetLog;   /* note : targetLog >= srcLog, hence scaleLog <= 1 */
+    const U32 minBits  = nbBitsBaseline - maxWeight;
+    U32 s;
+
+    assert(wkspSize >= HUF_TABLELOG_MAX + 1);
+    wksp += HUF_TABLELOG_MAX + 1;
+    wkspSize -= HUF_TABLELOG_MAX + 1;
+
+    ZSTD_memcpy(rankVal, rankValOrigin, sizeof(U32) * (HUF_TABLELOG_MAX + 1));
+
+    /* fill DTable */
+    for (s=0; s<sortedListSize; s++) {
+        const U16 symbol = sortedList[s].symbol;
+        const U32 weight = sortedList[s].weight;
+        const U32 nbBits = nbBitsBaseline - weight;
+        const U32 start = rankVal[weight];
+        const U32 length = 1 << (targetLog-nbBits);
+
+        if (targetLog-nbBits >= minBits) {   /* enough room for a second symbol */
+            U32 sortedRank;
+            int minWeight = nbBits + scaleLog;
+            if (minWeight < 1) minWeight = 1;
+            sortedRank = rankStart[minWeight];
+            HUF_fillDTableX2Level2(DTable+start, targetLog-nbBits, nbBits,
+                           rankValOrigin[nbBits], minWeight,
+                           sortedList+sortedRank, sortedListSize-sortedRank,
+                           nbBitsBaseline, symbol, wksp, wkspSize);
+        } else {
+            HUF_DEltX2 DElt;
+            MEM_writeLE16(&(DElt.sequence), symbol);
+            DElt.nbBits = (BYTE)(nbBits);
+            DElt.length = 1;
+            {   U32 const end = start + length;
+                U32 u;
+                for (u = start; u < end; u++) DTable[u] = DElt;
+        }   }
+        rankVal[weight] += length;
+    }
+}
+
+typedef struct {
+    rankValCol_t rankVal[HUF_TABLELOG_MAX];
+    U32 rankStats[HUF_TABLELOG_MAX + 1];
+    U32 rankStart0[HUF_TABLELOG_MAX + 2];
+    sortedSymbol_t sortedSymbol[HUF_SYMBOLVALUE_MAX + 1];
+    BYTE weightList[HUF_SYMBOLVALUE_MAX + 1];
+    U32 calleeWksp[HUF_READ_STATS_WORKSPACE_SIZE_U32];
+} HUF_ReadDTableX2_Workspace;
+
+size_t HUF_readDTableX2_wksp(HUF_DTable* DTable,
+                       const void* src, size_t srcSize,
+                             void* workSpace, size_t wkspSize)
+{
+    U32 tableLog, maxW, sizeOfSort, nbSymbols;
+    DTableDesc dtd = HUF_getDTableDesc(DTable);
+    U32 const maxTableLog = dtd.maxTableLog;
+    size_t iSize;
+    void* dtPtr = DTable+1;   /* force compiler to avoid strict-aliasing */
+    HUF_DEltX2* const dt = (HUF_DEltX2*)dtPtr;
+    U32 *rankStart;
+
+    HUF_ReadDTableX2_Workspace* const wksp = (HUF_ReadDTableX2_Workspace*)workSpace;
+
+    if (sizeof(*wksp) > wkspSize) return ERROR(GENERIC);
+
+    rankStart = wksp->rankStart0 + 1;
+    ZSTD_memset(wksp->rankStats, 0, sizeof(wksp->rankStats));
+    ZSTD_memset(wksp->rankStart0, 0, sizeof(wksp->rankStart0));
+
+    DEBUG_STATIC_ASSERT(sizeof(HUF_DEltX2) == sizeof(HUF_DTable));   /* if compiler fails here, assertion is wrong */
+    if (maxTableLog > HUF_TABLELOG_MAX) return ERROR(tableLog_tooLarge);
+    /* ZSTD_memset(weightList, 0, sizeof(weightList)); */  /* is not necessary, even though some analyzer complain ... */
+
+    iSize = HUF_readStats_wksp(wksp->weightList, HUF_SYMBOLVALUE_MAX + 1, wksp->rankStats, &nbSymbols, &tableLog, src, srcSize, wksp->calleeWksp, sizeof(wksp->calleeWksp), /* bmi2 */ 0);
+    if (HUF_isError(iSize)) return iSize;
+
+    /* check result */
+    if (tableLog > maxTableLog) return ERROR(tableLog_tooLarge);   /* DTable can't fit code depth */
+
+    /* find maxWeight */
+    for (maxW = tableLog; wksp->rankStats[maxW]==0; maxW--) {}  /* necessarily finds a solution before 0 */
+
+    /* Get start index of each weight */
+    {   U32 w, nextRankStart = 0;
+        for (w=1; w<maxW+1; w++) {
+            U32 curr = nextRankStart;
+            nextRankStart += wksp->rankStats[w];
+            rankStart[w] = curr;
+        }
+        rankStart[0] = nextRankStart;   /* put all 0w symbols at the end of sorted list*/
+        sizeOfSort = nextRankStart;
+    }
+
+    /* sort symbols by weight */
+    {   U32 s;
+        for (s=0; s<nbSymbols; s++) {
+            U32 const w = wksp->weightList[s];
+            U32 const r = rankStart[w]++;
+            wksp->sortedSymbol[r].symbol = (BYTE)s;
+            wksp->sortedSymbol[r].weight = (BYTE)w;
+        }
+        rankStart[0] = 0;   /* forget 0w symbols; this is beginning of weight(1) */
+    }
+
+    /* Build rankVal */
+    {   U32* const rankVal0 = wksp->rankVal[0];
+        {   int const rescale = (maxTableLog-tableLog) - 1;   /* tableLog <= maxTableLog */
+            U32 nextRankVal = 0;
+            U32 w;
+            for (w=1; w<maxW+1; w++) {
+                U32 curr = nextRankVal;
+                nextRankVal += wksp->rankStats[w] << (w+rescale);
+                rankVal0[w] = curr;
+        }   }
+        {   U32 const minBits = tableLog+1 - maxW;
+            U32 consumed;
+            for (consumed = minBits; consumed < maxTableLog - minBits + 1; consumed++) {
+                U32* const rankValPtr = wksp->rankVal[consumed];
+                U32 w;
+                for (w = 1; w < maxW+1; w++) {
+                    rankValPtr[w] = rankVal0[w] >> consumed;
+    }   }   }   }
+
+    HUF_fillDTableX2(dt, maxTableLog,
+                   wksp->sortedSymbol, sizeOfSort,
+                   wksp->rankStart0, wksp->rankVal, maxW,
+                   tableLog+1,
+                   wksp->calleeWksp, sizeof(wksp->calleeWksp) / sizeof(U32));
+
+    dtd.tableLog = (BYTE)maxTableLog;
+    dtd.tableType = 1;
+    ZSTD_memcpy(DTable, &dtd, sizeof(dtd));
+    return iSize;
+}
+
+
+FORCE_INLINE_TEMPLATE U32
+HUF_decodeSymbolX2(void* op, BIT_DStream_t* DStream, const HUF_DEltX2* dt, const U32 dtLog)
+{
+    size_t const val = BIT_lookBitsFast(DStream, dtLog);   /* note : dtLog >= 1 */
+    ZSTD_memcpy(op, dt+val, 2);
+    BIT_skipBits(DStream, dt[val].nbBits);
+    return dt[val].length;
+}
+
+FORCE_INLINE_TEMPLATE U32
+HUF_decodeLastSymbolX2(void* op, BIT_DStream_t* DStream, const HUF_DEltX2* dt, const U32 dtLog)
+{
+    size_t const val = BIT_lookBitsFast(DStream, dtLog);   /* note : dtLog >= 1 */
+    ZSTD_memcpy(op, dt+val, 1);
+    if (dt[val].length==1) BIT_skipBits(DStream, dt[val].nbBits);
+    else {
+        if (DStream->bitsConsumed < (sizeof(DStream->bitContainer)*8)) {
+            BIT_skipBits(DStream, dt[val].nbBits);
+            if (DStream->bitsConsumed > (sizeof(DStream->bitContainer)*8))
+                /* ugly hack; works only because it's the last symbol. Note : can't easily extract nbBits from just this symbol */
+                DStream->bitsConsumed = (sizeof(DStream->bitContainer)*8);
+    }   }
+    return 1;
+}
+
+#define HUF_DECODE_SYMBOLX2_0(ptr, DStreamPtr) \
+    ptr += HUF_decodeSymbolX2(ptr, DStreamPtr, dt, dtLog)
+
+#define HUF_DECODE_SYMBOLX2_1(ptr, DStreamPtr) \
+    if (MEM_64bits() || (HUF_TABLELOG_MAX<=12)) \
+        ptr += HUF_decodeSymbolX2(ptr, DStreamPtr, dt, dtLog)
+
+#define HUF_DECODE_SYMBOLX2_2(ptr, DStreamPtr) \
+    if (MEM_64bits()) \
+        ptr += HUF_decodeSymbolX2(ptr, DStreamPtr, dt, dtLog)
+
+HINT_INLINE size_t
+HUF_decodeStreamX2(BYTE* p, BIT_DStream_t* bitDPtr, BYTE* const pEnd,
+                const HUF_DEltX2* const dt, const U32 dtLog)
+{
+    BYTE* const pStart = p;
+
+    /* up to 8 symbols at a time */
+    while ((BIT_reloadDStream(bitDPtr) == BIT_DStream_unfinished) & (p < pEnd-(sizeof(bitDPtr->bitContainer)-1))) {
+        HUF_DECODE_SYMBOLX2_2(p, bitDPtr);
+        HUF_DECODE_SYMBOLX2_1(p, bitDPtr);
+        HUF_DECODE_SYMBOLX2_2(p, bitDPtr);
+        HUF_DECODE_SYMBOLX2_0(p, bitDPtr);
+    }
+
+    /* closer to end : up to 2 symbols at a time */
+    while ((BIT_reloadDStream(bitDPtr) == BIT_DStream_unfinished) & (p <= pEnd-2))
+        HUF_DECODE_SYMBOLX2_0(p, bitDPtr);
+
+    while (p <= pEnd-2)
+        HUF_DECODE_SYMBOLX2_0(p, bitDPtr);   /* no need to reload : reached the end of DStream */
+
+    if (p < pEnd)
+        p += HUF_decodeLastSymbolX2(p, bitDPtr, dt, dtLog);
+
+    return p-pStart;
+}
+
+FORCE_INLINE_TEMPLATE size_t
+HUF_decompress1X2_usingDTable_internal_body(
+          void* dst,  size_t dstSize,
+    const void* cSrc, size_t cSrcSize,
+    const HUF_DTable* DTable)
+{
+    BIT_DStream_t bitD;
+
+    /* Init */
+    CHECK_F( BIT_initDStream(&bitD, cSrc, cSrcSize) );
+
+    /* decode */
+    {   BYTE* const ostart = (BYTE*) dst;
+        BYTE* const oend = ostart + dstSize;
+        const void* const dtPtr = DTable+1;   /* force compiler to not use strict-aliasing */
+        const HUF_DEltX2* const dt = (const HUF_DEltX2*)dtPtr;
+        DTableDesc const dtd = HUF_getDTableDesc(DTable);
+        HUF_decodeStreamX2(ostart, &bitD, oend, dt, dtd.tableLog);
+    }
+
+    /* check */
+    if (!BIT_endOfDStream(&bitD)) return ERROR(corruption_detected);
+
+    /* decoded size */
+    return dstSize;
+}
+
+FORCE_INLINE_TEMPLATE size_t
+HUF_decompress4X2_usingDTable_internal_body(
+          void* dst,  size_t dstSize,
+    const void* cSrc, size_t cSrcSize,
+    const HUF_DTable* DTable)
+{
+    if (cSrcSize < 10) return ERROR(corruption_detected);   /* strict minimum : jump table + 1 byte per stream */
+
+    {   const BYTE* const istart = (const BYTE*) cSrc;
+        BYTE* const ostart = (BYTE*) dst;
+        BYTE* const oend = ostart + dstSize;
+        BYTE* const olimit = oend - (sizeof(size_t)-1);
+        const void* const dtPtr = DTable+1;
+        const HUF_DEltX2* const dt = (const HUF_DEltX2*)dtPtr;
+
+        /* Init */
+        BIT_DStream_t bitD1;
+        BIT_DStream_t bitD2;
+        BIT_DStream_t bitD3;
+        BIT_DStream_t bitD4;
+        size_t const length1 = MEM_readLE16(istart);
+        size_t const length2 = MEM_readLE16(istart+2);
+        size_t const length3 = MEM_readLE16(istart+4);
+        size_t const length4 = cSrcSize - (length1 + length2 + length3 + 6);
+        const BYTE* const istart1 = istart + 6;  /* jumpTable */
+        const BYTE* const istart2 = istart1 + length1;
+        const BYTE* const istart3 = istart2 + length2;
+        const BYTE* const istart4 = istart3 + length3;
+        size_t const segmentSize = (dstSize+3) / 4;
+        BYTE* const opStart2 = ostart + segmentSize;
+        BYTE* const opStart3 = opStart2 + segmentSize;
+        BYTE* const opStart4 = opStart3 + segmentSize;
+        BYTE* op1 = ostart;
+        BYTE* op2 = opStart2;
+        BYTE* op3 = opStart3;
+        BYTE* op4 = opStart4;
+        U32 endSignal = 1;
+        DTableDesc const dtd = HUF_getDTableDesc(DTable);
+        U32 const dtLog = dtd.tableLog;
+
+        if (length4 > cSrcSize) return ERROR(corruption_detected);   /* overflow */
+        CHECK_F( BIT_initDStream(&bitD1, istart1, length1) );
+        CHECK_F( BIT_initDStream(&bitD2, istart2, length2) );
+        CHECK_F( BIT_initDStream(&bitD3, istart3, length3) );
+        CHECK_F( BIT_initDStream(&bitD4, istart4, length4) );
+
+        /* 16-32 symbols per loop (4-8 symbols per stream) */
+        for ( ; (endSignal) & (op4 < olimit); ) {
+#if defined(__clang__) && (defined(__x86_64__) || defined(__i386__))
+            HUF_DECODE_SYMBOLX2_2(op1, &bitD1);
+            HUF_DECODE_SYMBOLX2_1(op1, &bitD1);
+            HUF_DECODE_SYMBOLX2_2(op1, &bitD1);
+            HUF_DECODE_SYMBOLX2_0(op1, &bitD1);
+            HUF_DECODE_SYMBOLX2_2(op2, &bitD2);
+            HUF_DECODE_SYMBOLX2_1(op2, &bitD2);
+            HUF_DECODE_SYMBOLX2_2(op2, &bitD2);
+            HUF_DECODE_SYMBOLX2_0(op2, &bitD2);
+            endSignal &= BIT_reloadDStreamFast(&bitD1) == BIT_DStream_unfinished;
+            endSignal &= BIT_reloadDStreamFast(&bitD2) == BIT_DStream_unfinished;
+            HUF_DECODE_SYMBOLX2_2(op3, &bitD3);
+            HUF_DECODE_SYMBOLX2_1(op3, &bitD3);
+            HUF_DECODE_SYMBOLX2_2(op3, &bitD3);
+            HUF_DECODE_SYMBOLX2_0(op3, &bitD3);
+            HUF_DECODE_SYMBOLX2_2(op4, &bitD4);
+            HUF_DECODE_SYMBOLX2_1(op4, &bitD4);
+            HUF_DECODE_SYMBOLX2_2(op4, &bitD4);
+            HUF_DECODE_SYMBOLX2_0(op4, &bitD4);
+            endSignal &= BIT_reloadDStreamFast(&bitD3) == BIT_DStream_unfinished;
+            endSignal &= BIT_reloadDStreamFast(&bitD4) == BIT_DStream_unfinished;
+#else
+            HUF_DECODE_SYMBOLX2_2(op1, &bitD1);
+            HUF_DECODE_SYMBOLX2_2(op2, &bitD2);
+            HUF_DECODE_SYMBOLX2_2(op3, &bitD3);
+            HUF_DECODE_SYMBOLX2_2(op4, &bitD4);
+            HUF_DECODE_SYMBOLX2_1(op1, &bitD1);
+            HUF_DECODE_SYMBOLX2_1(op2, &bitD2);
+            HUF_DECODE_SYMBOLX2_1(op3, &bitD3);
+            HUF_DECODE_SYMBOLX2_1(op4, &bitD4);
+            HUF_DECODE_SYMBOLX2_2(op1, &bitD1);
+            HUF_DECODE_SYMBOLX2_2(op2, &bitD2);
+            HUF_DECODE_SYMBOLX2_2(op3, &bitD3);
+            HUF_DECODE_SYMBOLX2_2(op4, &bitD4);
+            HUF_DECODE_SYMBOLX2_0(op1, &bitD1);
+            HUF_DECODE_SYMBOLX2_0(op2, &bitD2);
+            HUF_DECODE_SYMBOLX2_0(op3, &bitD3);
+            HUF_DECODE_SYMBOLX2_0(op4, &bitD4);
+            endSignal = (U32)LIKELY((U32)
+                        (BIT_reloadDStreamFast(&bitD1) == BIT_DStream_unfinished)
+                      & (BIT_reloadDStreamFast(&bitD2) == BIT_DStream_unfinished)
+                      & (BIT_reloadDStreamFast(&bitD3) == BIT_DStream_unfinished)
+                      & (BIT_reloadDStreamFast(&bitD4) == BIT_DStream_unfinished));
+#endif
+        }
+
+        /* check corruption */
+        if (op1 > opStart2) return ERROR(corruption_detected);
+        if (op2 > opStart3) return ERROR(corruption_detected);
+        if (op3 > opStart4) return ERROR(corruption_detected);
+        /* note : op4 already verified within main loop */
+
+        /* finish bitStreams one by one */
+        HUF_decodeStreamX2(op1, &bitD1, opStart2, dt, dtLog);
+        HUF_decodeStreamX2(op2, &bitD2, opStart3, dt, dtLog);
+        HUF_decodeStreamX2(op3, &bitD3, opStart4, dt, dtLog);
+        HUF_decodeStreamX2(op4, &bitD4, oend,     dt, dtLog);
+
+        /* check */
+        { U32 const endCheck = BIT_endOfDStream(&bitD1) & BIT_endOfDStream(&bitD2) & BIT_endOfDStream(&bitD3) & BIT_endOfDStream(&bitD4);
+          if (!endCheck) return ERROR(corruption_detected); }
+
+        /* decoded size */
+        return dstSize;
+    }
+}
+
+HUF_DGEN(HUF_decompress1X2_usingDTable_internal)
+HUF_DGEN(HUF_decompress4X2_usingDTable_internal)
+
+size_t HUF_decompress1X2_usingDTable(
+          void* dst,  size_t dstSize,
+    const void* cSrc, size_t cSrcSize,
+    const HUF_DTable* DTable)
+{
+    DTableDesc dtd = HUF_getDTableDesc(DTable);
+    if (dtd.tableType != 1) return ERROR(GENERIC);
+    return HUF_decompress1X2_usingDTable_internal(dst, dstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0);
+}
+
+size_t HUF_decompress1X2_DCtx_wksp(HUF_DTable* DCtx, void* dst, size_t dstSize,
+                                   const void* cSrc, size_t cSrcSize,
+                                   void* workSpace, size_t wkspSize)
+{
+    const BYTE* ip = (const BYTE*) cSrc;
+
+    size_t const hSize = HUF_readDTableX2_wksp(DCtx, cSrc, cSrcSize,
+                                               workSpace, wkspSize);
+    if (HUF_isError(hSize)) return hSize;
+    if (hSize >= cSrcSize) return ERROR(srcSize_wrong);
+    ip += hSize; cSrcSize -= hSize;
+
+    return HUF_decompress1X2_usingDTable_internal(dst, dstSize, ip, cSrcSize, DCtx, /* bmi2 */ 0);
+}
+
+
+size_t HUF_decompress4X2_usingDTable(
+          void* dst,  size_t dstSize,
+    const void* cSrc, size_t cSrcSize,
+    const HUF_DTable* DTable)
+{
+    DTableDesc dtd = HUF_getDTableDesc(DTable);
+    if (dtd.tableType != 1) return ERROR(GENERIC);
+    return HUF_decompress4X2_usingDTable_internal(dst, dstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0);
+}
+
+static size_t HUF_decompress4X2_DCtx_wksp_bmi2(HUF_DTable* dctx, void* dst, size_t dstSize,
+                                   const void* cSrc, size_t cSrcSize,
+                                   void* workSpace, size_t wkspSize, int bmi2)
+{
+    const BYTE* ip = (const BYTE*) cSrc;
+
+    size_t hSize = HUF_readDTableX2_wksp(dctx, cSrc, cSrcSize,
+                                         workSpace, wkspSize);
+    if (HUF_isError(hSize)) return hSize;
+    if (hSize >= cSrcSize) return ERROR(srcSize_wrong);
+    ip += hSize; cSrcSize -= hSize;
+
+    return HUF_decompress4X2_usingDTable_internal(dst, dstSize, ip, cSrcSize, dctx, bmi2);
+}
+
+size_t HUF_decompress4X2_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize,
+                                   const void* cSrc, size_t cSrcSize,
+                                   void* workSpace, size_t wkspSize)
+{
+    return HUF_decompress4X2_DCtx_wksp_bmi2(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize, /* bmi2 */ 0);
+}
+
+
+#endif /* HUF_FORCE_DECOMPRESS_X1 */
+
+
+/* ***********************************/
+/* Universal decompression selectors */
+/* ***********************************/
+
+size_t HUF_decompress1X_usingDTable(void* dst, size_t maxDstSize,
+                                    const void* cSrc, size_t cSrcSize,
+                                    const HUF_DTable* DTable)
+{
+    DTableDesc const dtd = HUF_getDTableDesc(DTable);
+#if defined(HUF_FORCE_DECOMPRESS_X1)
+    (void)dtd;
+    assert(dtd.tableType == 0);
+    return HUF_decompress1X1_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0);
+#elif defined(HUF_FORCE_DECOMPRESS_X2)
+    (void)dtd;
+    assert(dtd.tableType == 1);
+    return HUF_decompress1X2_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0);
+#else
+    return dtd.tableType ? HUF_decompress1X2_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0) :
+                           HUF_decompress1X1_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0);
+#endif
+}
+
+size_t HUF_decompress4X_usingDTable(void* dst, size_t maxDstSize,
+                                    const void* cSrc, size_t cSrcSize,
+                                    const HUF_DTable* DTable)
+{
+    DTableDesc const dtd = HUF_getDTableDesc(DTable);
+#if defined(HUF_FORCE_DECOMPRESS_X1)
+    (void)dtd;
+    assert(dtd.tableType == 0);
+    return HUF_decompress4X1_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0);
+#elif defined(HUF_FORCE_DECOMPRESS_X2)
+    (void)dtd;
+    assert(dtd.tableType == 1);
+    return HUF_decompress4X2_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0);
+#else
+    return dtd.tableType ? HUF_decompress4X2_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0) :
+                           HUF_decompress4X1_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0);
+#endif
+}
+
+
+#if !defined(HUF_FORCE_DECOMPRESS_X1) && !defined(HUF_FORCE_DECOMPRESS_X2)
+typedef struct { U32 tableTime; U32 decode256Time; } algo_time_t;
+static const algo_time_t algoTime[16 /* Quantization */][3 /* single, double, quad */] =
+{
+    /* single, double, quad */
+    {{0,0}, {1,1}, {2,2}},  /* Q==0 : impossible */
+    {{0,0}, {1,1}, {2,2}},  /* Q==1 : impossible */
+    {{  38,130}, {1313, 74}, {2151, 38}},   /* Q == 2 : 12-18% */
+    {{ 448,128}, {1353, 74}, {2238, 41}},   /* Q == 3 : 18-25% */
+    {{ 556,128}, {1353, 74}, {2238, 47}},   /* Q == 4 : 25-32% */
+    {{ 714,128}, {1418, 74}, {2436, 53}},   /* Q == 5 : 32-38% */
+    {{ 883,128}, {1437, 74}, {2464, 61}},   /* Q == 6 : 38-44% */
+    {{ 897,128}, {1515, 75}, {2622, 68}},   /* Q == 7 : 44-50% */
+    {{ 926,128}, {1613, 75}, {2730, 75}},   /* Q == 8 : 50-56% */
+    {{ 947,128}, {1729, 77}, {3359, 77}},   /* Q == 9 : 56-62% */
+    {{1107,128}, {2083, 81}, {4006, 84}},   /* Q ==10 : 62-69% */
+    {{1177,128}, {2379, 87}, {4785, 88}},   /* Q ==11 : 69-75% */
+    {{1242,128}, {2415, 93}, {5155, 84}},   /* Q ==12 : 75-81% */
+    {{1349,128}, {2644,106}, {5260,106}},   /* Q ==13 : 81-87% */
+    {{1455,128}, {2422,124}, {4174,124}},   /* Q ==14 : 87-93% */
+    {{ 722,128}, {1891,145}, {1936,146}},   /* Q ==15 : 93-99% */
+};
+#endif
+
+/* HUF_selectDecoder() :
+ *  Tells which decoder is likely to decode faster,
+ *  based on a set of pre-computed metrics.
+ * @return : 0==HUF_decompress4X1, 1==HUF_decompress4X2 .
+ *  Assumption : 0 < dstSize <= 128 KB */
+U32 HUF_selectDecoder (size_t dstSize, size_t cSrcSize)
+{
+    assert(dstSize > 0);
+    assert(dstSize <= 128*1024);
+#if defined(HUF_FORCE_DECOMPRESS_X1)
+    (void)dstSize;
+    (void)cSrcSize;
+    return 0;
+#elif defined(HUF_FORCE_DECOMPRESS_X2)
+    (void)dstSize;
+    (void)cSrcSize;
+    return 1;
+#else
+    /* decoder timing evaluation */
+    {   U32 const Q = (cSrcSize >= dstSize) ? 15 : (U32)(cSrcSize * 16 / dstSize);   /* Q < 16 */
+        U32 const D256 = (U32)(dstSize >> 8);
+        U32 const DTime0 = algoTime[Q][0].tableTime + (algoTime[Q][0].decode256Time * D256);
+        U32 DTime1 = algoTime[Q][1].tableTime + (algoTime[Q][1].decode256Time * D256);
+        DTime1 += DTime1 >> 3;  /* advantage to algorithm using less memory, to reduce cache eviction */
+        return DTime1 < DTime0;
+    }
+#endif
+}
+
+
+size_t HUF_decompress4X_hufOnly_wksp(HUF_DTable* dctx, void* dst,
+                                     size_t dstSize, const void* cSrc,
+                                     size_t cSrcSize, void* workSpace,
+                                     size_t wkspSize)
+{
+    /* validation checks */
+    if (dstSize == 0) return ERROR(dstSize_tooSmall);
+    if (cSrcSize == 0) return ERROR(corruption_detected);
+
+    {   U32 const algoNb = HUF_selectDecoder(dstSize, cSrcSize);
+#if defined(HUF_FORCE_DECOMPRESS_X1)
+        (void)algoNb;
+        assert(algoNb == 0);
+        return HUF_decompress4X1_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize);
+#elif defined(HUF_FORCE_DECOMPRESS_X2)
+        (void)algoNb;
+        assert(algoNb == 1);
+        return HUF_decompress4X2_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize);
+#else
+        return algoNb ? HUF_decompress4X2_DCtx_wksp(dctx, dst, dstSize, cSrc,
+                            cSrcSize, workSpace, wkspSize):
+                        HUF_decompress4X1_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize);
+#endif
+    }
+}
+
+size_t HUF_decompress1X_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize,
+                                  const void* cSrc, size_t cSrcSize,
+                                  void* workSpace, size_t wkspSize)
+{
+    /* validation checks */
+    if (dstSize == 0) return ERROR(dstSize_tooSmall);
+    if (cSrcSize > dstSize) return ERROR(corruption_detected);   /* invalid */
+    if (cSrcSize == dstSize) { ZSTD_memcpy(dst, cSrc, dstSize); return dstSize; }   /* not compressed */
+    if (cSrcSize == 1) { ZSTD_memset(dst, *(const BYTE*)cSrc, dstSize); return dstSize; }   /* RLE */
+
+    {   U32 const algoNb = HUF_selectDecoder(dstSize, cSrcSize);
+#if defined(HUF_FORCE_DECOMPRESS_X1)
+        (void)algoNb;
+        assert(algoNb == 0);
+        return HUF_decompress1X1_DCtx_wksp(dctx, dst, dstSize, cSrc,
+                                cSrcSize, workSpace, wkspSize);
+#elif defined(HUF_FORCE_DECOMPRESS_X2)
+        (void)algoNb;
+        assert(algoNb == 1);
+        return HUF_decompress1X2_DCtx_wksp(dctx, dst, dstSize, cSrc,
+                                cSrcSize, workSpace, wkspSize);
+#else
+        return algoNb ? HUF_decompress1X2_DCtx_wksp(dctx, dst, dstSize, cSrc,
+                                cSrcSize, workSpace, wkspSize):
+                        HUF_decompress1X1_DCtx_wksp(dctx, dst, dstSize, cSrc,
+                                cSrcSize, workSpace, wkspSize);
+#endif
+    }
+}
+
+
+size_t HUF_decompress1X_usingDTable_bmi2(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable, int bmi2)
+{
+    DTableDesc const dtd = HUF_getDTableDesc(DTable);
+#if defined(HUF_FORCE_DECOMPRESS_X1)
+    (void)dtd;
+    assert(dtd.tableType == 0);
+    return HUF_decompress1X1_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, bmi2);
+#elif defined(HUF_FORCE_DECOMPRESS_X2)
+    (void)dtd;
+    assert(dtd.tableType == 1);
+    return HUF_decompress1X2_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, bmi2);
+#else
+    return dtd.tableType ? HUF_decompress1X2_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, bmi2) :
+                           HUF_decompress1X1_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, bmi2);
+#endif
+}
+
+#ifndef HUF_FORCE_DECOMPRESS_X2
+size_t HUF_decompress1X1_DCtx_wksp_bmi2(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize, int bmi2)
+{
+    const BYTE* ip = (const BYTE*) cSrc;
+
+    size_t const hSize = HUF_readDTableX1_wksp_bmi2(dctx, cSrc, cSrcSize, workSpace, wkspSize, bmi2);
+    if (HUF_isError(hSize)) return hSize;
+    if (hSize >= cSrcSize) return ERROR(srcSize_wrong);
+    ip += hSize; cSrcSize -= hSize;
+
+    return HUF_decompress1X1_usingDTable_internal(dst, dstSize, ip, cSrcSize, dctx, bmi2);
+}
+#endif
+
+size_t HUF_decompress4X_usingDTable_bmi2(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable, int bmi2)
+{
+    DTableDesc const dtd = HUF_getDTableDesc(DTable);
+#if defined(HUF_FORCE_DECOMPRESS_X1)
+    (void)dtd;
+    assert(dtd.tableType == 0);
+    return HUF_decompress4X1_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, bmi2);
+#elif defined(HUF_FORCE_DECOMPRESS_X2)
+    (void)dtd;
+    assert(dtd.tableType == 1);
+    return HUF_decompress4X2_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, bmi2);
+#else
+    return dtd.tableType ? HUF_decompress4X2_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, bmi2) :
+                           HUF_decompress4X1_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, bmi2);
+#endif
+}
+
+size_t HUF_decompress4X_hufOnly_wksp_bmi2(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize, int bmi2)
+{
+    /* validation checks */
+    if (dstSize == 0) return ERROR(dstSize_tooSmall);
+    if (cSrcSize == 0) return ERROR(corruption_detected);
+
+    {   U32 const algoNb = HUF_selectDecoder(dstSize, cSrcSize);
+#if defined(HUF_FORCE_DECOMPRESS_X1)
+        (void)algoNb;
+        assert(algoNb == 0);
+        return HUF_decompress4X1_DCtx_wksp_bmi2(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize, bmi2);
+#elif defined(HUF_FORCE_DECOMPRESS_X2)
+        (void)algoNb;
+        assert(algoNb == 1);
+        return HUF_decompress4X2_DCtx_wksp_bmi2(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize, bmi2);
+#else
+        return algoNb ? HUF_decompress4X2_DCtx_wksp_bmi2(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize, bmi2) :
+                        HUF_decompress4X1_DCtx_wksp_bmi2(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize, bmi2);
+#endif
+    }
+}
+
diff --git a/lib/zstd/decompress/zstd_ddict.c b/lib/zstd/decompress/zstd_ddict.c
new file mode 100644
index 000000000000..dbbc7919de53
--- /dev/null
+++ b/lib/zstd/decompress/zstd_ddict.c
@@ -0,0 +1,241 @@
+/*
+ * Copyright (c) Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+/* zstd_ddict.c :
+ * concentrates all logic that needs to know the internals of ZSTD_DDict object */
+
+/*-*******************************************************
+*  Dependencies
+*********************************************************/
+#include "../common/zstd_deps.h"   /* ZSTD_memcpy, ZSTD_memmove, ZSTD_memset */
+#include "../common/cpu.h"         /* bmi2 */
+#include "../common/mem.h"         /* low level memory routines */
+#define FSE_STATIC_LINKING_ONLY
+#include "../common/fse.h"
+#define HUF_STATIC_LINKING_ONLY
+#include "../common/huf.h"
+#include "zstd_decompress_internal.h"
+#include "zstd_ddict.h"
+
+
+
+
+/*-*******************************************************
+*  Types
+*********************************************************/
+struct ZSTD_DDict_s {
+    void* dictBuffer;
+    const void* dictContent;
+    size_t dictSize;
+    ZSTD_entropyDTables_t entropy;
+    U32 dictID;
+    U32 entropyPresent;
+    ZSTD_customMem cMem;
+};  /* typedef'd to ZSTD_DDict within "zstd.h" */
+
+const void* ZSTD_DDict_dictContent(const ZSTD_DDict* ddict)
+{
+    assert(ddict != NULL);
+    return ddict->dictContent;
+}
+
+size_t ZSTD_DDict_dictSize(const ZSTD_DDict* ddict)
+{
+    assert(ddict != NULL);
+    return ddict->dictSize;
+}
+
+void ZSTD_copyDDictParameters(ZSTD_DCtx* dctx, const ZSTD_DDict* ddict)
+{
+    DEBUGLOG(4, "ZSTD_copyDDictParameters");
+    assert(dctx != NULL);
+    assert(ddict != NULL);
+    dctx->dictID = ddict->dictID;
+    dctx->prefixStart = ddict->dictContent;
+    dctx->virtualStart = ddict->dictContent;
+    dctx->dictEnd = (const BYTE*)ddict->dictContent + ddict->dictSize;
+    dctx->previousDstEnd = dctx->dictEnd;
+#ifdef FUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION
+    dctx->dictContentBeginForFuzzing = dctx->prefixStart;
+    dctx->dictContentEndForFuzzing = dctx->previousDstEnd;
+#endif
+    if (ddict->entropyPresent) {
+        dctx->litEntropy = 1;
+        dctx->fseEntropy = 1;
+        dctx->LLTptr = ddict->entropy.LLTable;
+        dctx->MLTptr = ddict->entropy.MLTable;
+        dctx->OFTptr = ddict->entropy.OFTable;
+        dctx->HUFptr = ddict->entropy.hufTable;
+        dctx->entropy.rep[0] = ddict->entropy.rep[0];
+        dctx->entropy.rep[1] = ddict->entropy.rep[1];
+        dctx->entropy.rep[2] = ddict->entropy.rep[2];
+    } else {
+        dctx->litEntropy = 0;
+        dctx->fseEntropy = 0;
+    }
+}
+
+
+static size_t
+ZSTD_loadEntropy_intoDDict(ZSTD_DDict* ddict,
+                           ZSTD_dictContentType_e dictContentType)
+{
+    ddict->dictID = 0;
+    ddict->entropyPresent = 0;
+    if (dictContentType == ZSTD_dct_rawContent) return 0;
+
+    if (ddict->dictSize < 8) {
+        if (dictContentType == ZSTD_dct_fullDict)
+            return ERROR(dictionary_corrupted);   /* only accept specified dictionaries */
+        return 0;   /* pure content mode */
+    }
+    {   U32 const magic = MEM_readLE32(ddict->dictContent);
+        if (magic != ZSTD_MAGIC_DICTIONARY) {
+            if (dictContentType == ZSTD_dct_fullDict)
+                return ERROR(dictionary_corrupted);   /* only accept specified dictionaries */
+            return 0;   /* pure content mode */
+        }
+    }
+    ddict->dictID = MEM_readLE32((const char*)ddict->dictContent + ZSTD_FRAMEIDSIZE);
+
+    /* load entropy tables */
+    RETURN_ERROR_IF(ZSTD_isError(ZSTD_loadDEntropy(
+            &ddict->entropy, ddict->dictContent, ddict->dictSize)),
+        dictionary_corrupted, "");
+    ddict->entropyPresent = 1;
+    return 0;
+}
+
+
+static size_t ZSTD_initDDict_internal(ZSTD_DDict* ddict,
+                                      const void* dict, size_t dictSize,
+                                      ZSTD_dictLoadMethod_e dictLoadMethod,
+                                      ZSTD_dictContentType_e dictContentType)
+{
+    if ((dictLoadMethod == ZSTD_dlm_byRef) || (!dict) || (!dictSize)) {
+        ddict->dictBuffer = NULL;
+        ddict->dictContent = dict;
+        if (!dict) dictSize = 0;
+    } else {
+        void* const internalBuffer = ZSTD_customMalloc(dictSize, ddict->cMem);
+        ddict->dictBuffer = internalBuffer;
+        ddict->dictContent = internalBuffer;
+        if (!internalBuffer) return ERROR(memory_allocation);
+        ZSTD_memcpy(internalBuffer, dict, dictSize);
+    }
+    ddict->dictSize = dictSize;
+    ddict->entropy.hufTable[0] = (HUF_DTable)((HufLog)*0x1000001);  /* cover both little and big endian */
+
+    /* parse dictionary content */
+    FORWARD_IF_ERROR( ZSTD_loadEntropy_intoDDict(ddict, dictContentType) , "");
+
+    return 0;
+}
+
+ZSTD_DDict* ZSTD_createDDict_advanced(const void* dict, size_t dictSize,
+                                      ZSTD_dictLoadMethod_e dictLoadMethod,
+                                      ZSTD_dictContentType_e dictContentType,
+                                      ZSTD_customMem customMem)
+{
+    if ((!customMem.customAlloc) ^ (!customMem.customFree)) return NULL;
+
+    {   ZSTD_DDict* const ddict = (ZSTD_DDict*) ZSTD_customMalloc(sizeof(ZSTD_DDict), customMem);
+        if (ddict == NULL) return NULL;
+        ddict->cMem = customMem;
+        {   size_t const initResult = ZSTD_initDDict_internal(ddict,
+                                            dict, dictSize,
+                                            dictLoadMethod, dictContentType);
+            if (ZSTD_isError(initResult)) {
+                ZSTD_freeDDict(ddict);
+                return NULL;
+        }   }
+        return ddict;
+    }
+}
+
+/*! ZSTD_createDDict() :
+*   Create a digested dictionary, to start decompression without startup delay.
+*   `dict` content is copied inside DDict.
+*   Consequently, `dict` can be released after `ZSTD_DDict` creation */
+ZSTD_DDict* ZSTD_createDDict(const void* dict, size_t dictSize)
+{
+    ZSTD_customMem const allocator = { NULL, NULL, NULL };
+    return ZSTD_createDDict_advanced(dict, dictSize, ZSTD_dlm_byCopy, ZSTD_dct_auto, allocator);
+}
+
+/*! ZSTD_createDDict_byReference() :
+ *  Create a digested dictionary, to start decompression without startup delay.
+ *  Dictionary content is simply referenced, it will be accessed during decompression.
+ *  Warning : dictBuffer must outlive DDict (DDict must be freed before dictBuffer) */
+ZSTD_DDict* ZSTD_createDDict_byReference(const void* dictBuffer, size_t dictSize)
+{
+    ZSTD_customMem const allocator = { NULL, NULL, NULL };
+    return ZSTD_createDDict_advanced(dictBuffer, dictSize, ZSTD_dlm_byRef, ZSTD_dct_auto, allocator);
+}
+
+
+const ZSTD_DDict* ZSTD_initStaticDDict(
+                                void* sBuffer, size_t sBufferSize,
+                                const void* dict, size_t dictSize,
+                                ZSTD_dictLoadMethod_e dictLoadMethod,
+                                ZSTD_dictContentType_e dictContentType)
+{
+    size_t const neededSpace = sizeof(ZSTD_DDict)
+                             + (dictLoadMethod == ZSTD_dlm_byRef ? 0 : dictSize);
+    ZSTD_DDict* const ddict = (ZSTD_DDict*)sBuffer;
+    assert(sBuffer != NULL);
+    assert(dict != NULL);
+    if ((size_t)sBuffer & 7) return NULL;   /* 8-aligned */
+    if (sBufferSize < neededSpace) return NULL;
+    if (dictLoadMethod == ZSTD_dlm_byCopy) {
+        ZSTD_memcpy(ddict+1, dict, dictSize);  /* local copy */
+        dict = ddict+1;
+    }
+    if (ZSTD_isError( ZSTD_initDDict_internal(ddict,
+                                              dict, dictSize,
+                                              ZSTD_dlm_byRef, dictContentType) ))
+        return NULL;
+    return ddict;
+}
+
+
+size_t ZSTD_freeDDict(ZSTD_DDict* ddict)
+{
+    if (ddict==NULL) return 0;   /* support free on NULL */
+    {   ZSTD_customMem const cMem = ddict->cMem;
+        ZSTD_customFree(ddict->dictBuffer, cMem);
+        ZSTD_customFree(ddict, cMem);
+        return 0;
+    }
+}
+
+/*! ZSTD_estimateDDictSize() :
+ *  Estimate amount of memory that will be needed to create a dictionary for decompression.
+ *  Note : dictionary created by reference using ZSTD_dlm_byRef are smaller */
+size_t ZSTD_estimateDDictSize(size_t dictSize, ZSTD_dictLoadMethod_e dictLoadMethod)
+{
+    return sizeof(ZSTD_DDict) + (dictLoadMethod == ZSTD_dlm_byRef ? 0 : dictSize);
+}
+
+size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict)
+{
+    if (ddict==NULL) return 0;   /* support sizeof on NULL */
+    return sizeof(*ddict) + (ddict->dictBuffer ? ddict->dictSize : 0) ;
+}
+
+/*! ZSTD_getDictID_fromDDict() :
+ *  Provides the dictID of the dictionary loaded into `ddict`.
+ *  If @return == 0, the dictionary is not conformant to Zstandard specification, or empty.
+ *  Non-conformant dictionaries can still be loaded, but as content-only dictionaries. */
+unsigned ZSTD_getDictID_fromDDict(const ZSTD_DDict* ddict)
+{
+    if (ddict==NULL) return 0;
+    return ZSTD_getDictID_fromDict(ddict->dictContent, ddict->dictSize);
+}
diff --git a/lib/zstd/decompress/zstd_ddict.h b/lib/zstd/decompress/zstd_ddict.h
new file mode 100644
index 000000000000..8c1a79d666f8
--- /dev/null
+++ b/lib/zstd/decompress/zstd_ddict.h
@@ -0,0 +1,44 @@
+/*
+ * Copyright (c) Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+
+#ifndef ZSTD_DDICT_H
+#define ZSTD_DDICT_H
+
+/*-*******************************************************
+ *  Dependencies
+ *********************************************************/
+#include "../common/zstd_deps.h"   /* size_t */
+#include <linux/zstd.h>     /* ZSTD_DDict, and several public functions */
+
+
+/*-*******************************************************
+ *  Interface
+ *********************************************************/
+
+/* note: several prototypes are already published in `zstd.h` :
+ * ZSTD_createDDict()
+ * ZSTD_createDDict_byReference()
+ * ZSTD_createDDict_advanced()
+ * ZSTD_freeDDict()
+ * ZSTD_initStaticDDict()
+ * ZSTD_sizeof_DDict()
+ * ZSTD_estimateDDictSize()
+ * ZSTD_getDictID_fromDict()
+ */
+
+const void* ZSTD_DDict_dictContent(const ZSTD_DDict* ddict);
+size_t ZSTD_DDict_dictSize(const ZSTD_DDict* ddict);
+
+void ZSTD_copyDDictParameters(ZSTD_DCtx* dctx, const ZSTD_DDict* ddict);
+
+
+
+#endif /* ZSTD_DDICT_H */
diff --git a/lib/zstd/decompress/zstd_decompress.c b/lib/zstd/decompress/zstd_decompress.c
new file mode 100644
index 000000000000..b4d81d84479a
--- /dev/null
+++ b/lib/zstd/decompress/zstd_decompress.c
@@ -0,0 +1,2085 @@
+/*
+ * Copyright (c) Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+
+/* ***************************************************************
+*  Tuning parameters
+*****************************************************************/
+/*!
+ * HEAPMODE :
+ * Select how default decompression function ZSTD_decompress() allocates its context,
+ * on stack (0), or into heap (1, default; requires malloc()).
+ * Note that functions with explicit context such as ZSTD_decompressDCtx() are unaffected.
+ */
+#ifndef ZSTD_HEAPMODE
+#  define ZSTD_HEAPMODE 1
+#endif
+
+/*!
+*  LEGACY_SUPPORT :
+*  if set to 1+, ZSTD_decompress() can decode older formats (v0.1+)
+*/
+
+/*!
+ *  MAXWINDOWSIZE_DEFAULT :
+ *  maximum window size accepted by DStream __by default__.
+ *  Frames requiring more memory will be rejected.
+ *  It's possible to set a different limit using ZSTD_DCtx_setMaxWindowSize().
+ */
+#ifndef ZSTD_MAXWINDOWSIZE_DEFAULT
+#  define ZSTD_MAXWINDOWSIZE_DEFAULT (((U32)1 << ZSTD_WINDOWLOG_LIMIT_DEFAULT) + 1)
+#endif
+
+/*!
+ *  NO_FORWARD_PROGRESS_MAX :
+ *  maximum allowed nb of calls to ZSTD_decompressStream()
+ *  without any forward progress
+ *  (defined as: no byte read from input, and no byte flushed to output)
+ *  before triggering an error.
+ */
+#ifndef ZSTD_NO_FORWARD_PROGRESS_MAX
+#  define ZSTD_NO_FORWARD_PROGRESS_MAX 16
+#endif
+
+
+/*-*******************************************************
+*  Dependencies
+*********************************************************/
+#include "../common/zstd_deps.h"   /* ZSTD_memcpy, ZSTD_memmove, ZSTD_memset */
+#include "../common/cpu.h"         /* bmi2 */
+#include "../common/mem.h"         /* low level memory routines */
+#define FSE_STATIC_LINKING_ONLY
+#include "../common/fse.h"
+#define HUF_STATIC_LINKING_ONLY
+#include "../common/huf.h"
+#include <linux/xxhash.h> /* xxh64_reset, xxh64_update, xxh64_digest, XXH64 */
+#include "../common/zstd_internal.h"  /* blockProperties_t */
+#include "zstd_decompress_internal.h"   /* ZSTD_DCtx */
+#include "zstd_ddict.h"  /* ZSTD_DDictDictContent */
+#include "zstd_decompress_block.h"   /* ZSTD_decompressBlock_internal */
+
+
+
+
+/* ***********************************
+ * Multiple DDicts Hashset internals *
+ *************************************/
+
+#define DDICT_HASHSET_MAX_LOAD_FACTOR_COUNT_MULT 4
+#define DDICT_HASHSET_MAX_LOAD_FACTOR_SIZE_MULT 3   /* These two constants represent SIZE_MULT/COUNT_MULT load factor without using a float.
+                                                     * Currently, that means a 0.75 load factor.
+                                                     * So, if count * COUNT_MULT / size * SIZE_MULT != 0, then we've exceeded
+                                                     * the load factor of the ddict hash set.
+                                                     */
+
+#define DDICT_HASHSET_TABLE_BASE_SIZE 64
+#define DDICT_HASHSET_RESIZE_FACTOR 2
+
+/* Hash function to determine starting position of dict insertion within the table
+ * Returns an index between [0, hashSet->ddictPtrTableSize]
+ */
+static size_t ZSTD_DDictHashSet_getIndex(const ZSTD_DDictHashSet* hashSet, U32 dictID) {
+    const U64 hash = xxh64(&dictID, sizeof(U32), 0);
+    /* DDict ptr table size is a multiple of 2, use size - 1 as mask to get index within [0, hashSet->ddictPtrTableSize) */
+    return hash & (hashSet->ddictPtrTableSize - 1);
+}
+
+/* Adds DDict to a hashset without resizing it.
+ * If inserting a DDict with a dictID that already exists in the set, replaces the one in the set.
+ * Returns 0 if successful, or a zstd error code if something went wrong.
+ */
+static size_t ZSTD_DDictHashSet_emplaceDDict(ZSTD_DDictHashSet* hashSet, const ZSTD_DDict* ddict) {
+    const U32 dictID = ZSTD_getDictID_fromDDict(ddict);
+    size_t idx = ZSTD_DDictHashSet_getIndex(hashSet, dictID);
+    const size_t idxRangeMask = hashSet->ddictPtrTableSize - 1;
+    RETURN_ERROR_IF(hashSet->ddictPtrCount == hashSet->ddictPtrTableSize, GENERIC, "Hash set is full!");
+    DEBUGLOG(4, "Hashed index: for dictID: %u is %zu", dictID, idx);
+    while (hashSet->ddictPtrTable[idx] != NULL) {
+        /* Replace existing ddict if inserting ddict with same dictID */
+        if (ZSTD_getDictID_fromDDict(hashSet->ddictPtrTable[idx]) == dictID) {
+            DEBUGLOG(4, "DictID already exists, replacing rather than adding");
+            hashSet->ddictPtrTable[idx] = ddict;
+            return 0;
+        }
+        idx &= idxRangeMask;
+        idx++;
+    }
+    DEBUGLOG(4, "Final idx after probing for dictID %u is: %zu", dictID, idx);
+    hashSet->ddictPtrTable[idx] = ddict;
+    hashSet->ddictPtrCount++;
+    return 0;
+}
+
+/* Expands hash table by factor of DDICT_HASHSET_RESIZE_FACTOR and
+ * rehashes all values, allocates new table, frees old table.
+ * Returns 0 on success, otherwise a zstd error code.
+ */
+static size_t ZSTD_DDictHashSet_expand(ZSTD_DDictHashSet* hashSet, ZSTD_customMem customMem) {
+    size_t newTableSize = hashSet->ddictPtrTableSize * DDICT_HASHSET_RESIZE_FACTOR;
+    const ZSTD_DDict** newTable = (const ZSTD_DDict**)ZSTD_customCalloc(sizeof(ZSTD_DDict*) * newTableSize, customMem);
+    const ZSTD_DDict** oldTable = hashSet->ddictPtrTable;
+    size_t oldTableSize = hashSet->ddictPtrTableSize;
+    size_t i;
+
+    DEBUGLOG(4, "Expanding DDict hash table! Old size: %zu new size: %zu", oldTableSize, newTableSize);
+    RETURN_ERROR_IF(!newTable, memory_allocation, "Expanded hashset allocation failed!");
+    hashSet->ddictPtrTable = newTable;
+    hashSet->ddictPtrTableSize = newTableSize;
+    hashSet->ddictPtrCount = 0;
+    for (i = 0; i < oldTableSize; ++i) {
+        if (oldTable[i] != NULL) {
+            FORWARD_IF_ERROR(ZSTD_DDictHashSet_emplaceDDict(hashSet, oldTable[i]), "");
+        }
+    }
+    ZSTD_customFree((void*)oldTable, customMem);
+    DEBUGLOG(4, "Finished re-hash");
+    return 0;
+}
+
+/* Fetches a DDict with the given dictID
+ * Returns the ZSTD_DDict* with the requested dictID. If it doesn't exist, then returns NULL.
+ */
+static const ZSTD_DDict* ZSTD_DDictHashSet_getDDict(ZSTD_DDictHashSet* hashSet, U32 dictID) {
+    size_t idx = ZSTD_DDictHashSet_getIndex(hashSet, dictID);
+    const size_t idxRangeMask = hashSet->ddictPtrTableSize - 1;
+    DEBUGLOG(4, "Hashed index: for dictID: %u is %zu", dictID, idx);
+    for (;;) {
+        size_t currDictID = ZSTD_getDictID_fromDDict(hashSet->ddictPtrTable[idx]);
+        if (currDictID == dictID || currDictID == 0) {
+            /* currDictID == 0 implies a NULL ddict entry */
+            break;
+        } else {
+            idx &= idxRangeMask;    /* Goes to start of table when we reach the end */
+            idx++;
+        }
+    }
+    DEBUGLOG(4, "Final idx after probing for dictID %u is: %zu", dictID, idx);
+    return hashSet->ddictPtrTable[idx];
+}
+
+/* Allocates space for and returns a ddict hash set
+ * The hash set's ZSTD_DDict* table has all values automatically set to NULL to begin with.
+ * Returns NULL if allocation failed.
+ */
+static ZSTD_DDictHashSet* ZSTD_createDDictHashSet(ZSTD_customMem customMem) {
+    ZSTD_DDictHashSet* ret = (ZSTD_DDictHashSet*)ZSTD_customMalloc(sizeof(ZSTD_DDictHashSet), customMem);
+    DEBUGLOG(4, "Allocating new hash set");
+    if (!ret)
+        return NULL;
+    ret->ddictPtrTable = (const ZSTD_DDict**)ZSTD_customCalloc(DDICT_HASHSET_TABLE_BASE_SIZE * sizeof(ZSTD_DDict*), customMem);
+    if (!ret->ddictPtrTable) {
+        ZSTD_customFree(ret, customMem);
+        return NULL;
+    }
+    ret->ddictPtrTableSize = DDICT_HASHSET_TABLE_BASE_SIZE;
+    ret->ddictPtrCount = 0;
+    return ret;
+}
+
+/* Frees the table of ZSTD_DDict* within a hashset, then frees the hashset itself.
+ * Note: The ZSTD_DDict* within the table are NOT freed.
+ */
+static void ZSTD_freeDDictHashSet(ZSTD_DDictHashSet* hashSet, ZSTD_customMem customMem) {
+    DEBUGLOG(4, "Freeing ddict hash set");
+    if (hashSet && hashSet->ddictPtrTable) {
+        ZSTD_customFree((void*)hashSet->ddictPtrTable, customMem);
+    }
+    if (hashSet) {
+        ZSTD_customFree(hashSet, customMem);
+    }
+}
+
+/* Public function: Adds a DDict into the ZSTD_DDictHashSet, possibly triggering a resize of the hash set.
+ * Returns 0 on success, or a ZSTD error.
+ */
+static size_t ZSTD_DDictHashSet_addDDict(ZSTD_DDictHashSet* hashSet, const ZSTD_DDict* ddict, ZSTD_customMem customMem) {
+    DEBUGLOG(4, "Adding dict ID: %u to hashset with - Count: %zu Tablesize: %zu", ZSTD_getDictID_fromDDict(ddict), hashSet->ddictPtrCount, hashSet->ddictPtrTableSize);
+    if (hashSet->ddictPtrCount * DDICT_HASHSET_MAX_LOAD_FACTOR_COUNT_MULT / hashSet->ddictPtrTableSize * DDICT_HASHSET_MAX_LOAD_FACTOR_SIZE_MULT != 0) {
+        FORWARD_IF_ERROR(ZSTD_DDictHashSet_expand(hashSet, customMem), "");
+    }
+    FORWARD_IF_ERROR(ZSTD_DDictHashSet_emplaceDDict(hashSet, ddict), "");
+    return 0;
+}
+
+/*-*************************************************************
+*   Context management
+***************************************************************/
+size_t ZSTD_sizeof_DCtx (const ZSTD_DCtx* dctx)
+{
+    if (dctx==NULL) return 0;   /* support sizeof NULL */
+    return sizeof(*dctx)
+           + ZSTD_sizeof_DDict(dctx->ddictLocal)
+           + dctx->inBuffSize + dctx->outBuffSize;
+}
+
+size_t ZSTD_estimateDCtxSize(void) { return sizeof(ZSTD_DCtx); }
+
+
+static size_t ZSTD_startingInputLength(ZSTD_format_e format)
+{
+    size_t const startingInputLength = ZSTD_FRAMEHEADERSIZE_PREFIX(format);
+    /* only supports formats ZSTD_f_zstd1 and ZSTD_f_zstd1_magicless */
+    assert( (format == ZSTD_f_zstd1) || (format == ZSTD_f_zstd1_magicless) );
+    return startingInputLength;
+}
+
+static void ZSTD_DCtx_resetParameters(ZSTD_DCtx* dctx)
+{
+    assert(dctx->streamStage == zdss_init);
+    dctx->format = ZSTD_f_zstd1;
+    dctx->maxWindowSize = ZSTD_MAXWINDOWSIZE_DEFAULT;
+    dctx->outBufferMode = ZSTD_bm_buffered;
+    dctx->forceIgnoreChecksum = ZSTD_d_validateChecksum;
+    dctx->refMultipleDDicts = ZSTD_rmd_refSingleDDict;
+}
+
+static void ZSTD_initDCtx_internal(ZSTD_DCtx* dctx)
+{
+    dctx->staticSize  = 0;
+    dctx->ddict       = NULL;
+    dctx->ddictLocal  = NULL;
+    dctx->dictEnd     = NULL;
+    dctx->ddictIsCold = 0;
+    dctx->dictUses = ZSTD_dont_use;
+    dctx->inBuff      = NULL;
+    dctx->inBuffSize  = 0;
+    dctx->outBuffSize = 0;
+    dctx->streamStage = zdss_init;
+    dctx->legacyContext = NULL;
+    dctx->previousLegacyVersion = 0;
+    dctx->noForwardProgress = 0;
+    dctx->oversizedDuration = 0;
+    dctx->bmi2 = ZSTD_cpuid_bmi2(ZSTD_cpuid());
+    dctx->ddictSet = NULL;
+    ZSTD_DCtx_resetParameters(dctx);
+#ifdef FUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION
+    dctx->dictContentEndForFuzzing = NULL;
+#endif
+}
+
+ZSTD_DCtx* ZSTD_initStaticDCtx(void *workspace, size_t workspaceSize)
+{
+    ZSTD_DCtx* const dctx = (ZSTD_DCtx*) workspace;
+
+    if ((size_t)workspace & 7) return NULL;  /* 8-aligned */
+    if (workspaceSize < sizeof(ZSTD_DCtx)) return NULL;  /* minimum size */
+
+    ZSTD_initDCtx_internal(dctx);
+    dctx->staticSize = workspaceSize;
+    dctx->inBuff = (char*)(dctx+1);
+    return dctx;
+}
+
+ZSTD_DCtx* ZSTD_createDCtx_advanced(ZSTD_customMem customMem)
+{
+    if ((!customMem.customAlloc) ^ (!customMem.customFree)) return NULL;
+
+    {   ZSTD_DCtx* const dctx = (ZSTD_DCtx*)ZSTD_customMalloc(sizeof(*dctx), customMem);
+        if (!dctx) return NULL;
+        dctx->customMem = customMem;
+        ZSTD_initDCtx_internal(dctx);
+        return dctx;
+    }
+}
+
+ZSTD_DCtx* ZSTD_createDCtx(void)
+{
+    DEBUGLOG(3, "ZSTD_createDCtx");
+    return ZSTD_createDCtx_advanced(ZSTD_defaultCMem);
+}
+
+static void ZSTD_clearDict(ZSTD_DCtx* dctx)
+{
+    ZSTD_freeDDict(dctx->ddictLocal);
+    dctx->ddictLocal = NULL;
+    dctx->ddict = NULL;
+    dctx->dictUses = ZSTD_dont_use;
+}
+
+size_t ZSTD_freeDCtx(ZSTD_DCtx* dctx)
+{
+    if (dctx==NULL) return 0;   /* support free on NULL */
+    RETURN_ERROR_IF(dctx->staticSize, memory_allocation, "not compatible with static DCtx");
+    {   ZSTD_customMem const cMem = dctx->customMem;
+        ZSTD_clearDict(dctx);
+        ZSTD_customFree(dctx->inBuff, cMem);
+        dctx->inBuff = NULL;
+        if (dctx->ddictSet) {
+            ZSTD_freeDDictHashSet(dctx->ddictSet, cMem);
+            dctx->ddictSet = NULL;
+        }
+        ZSTD_customFree(dctx, cMem);
+        return 0;
+    }
+}
+
+/* no longer useful */
+void ZSTD_copyDCtx(ZSTD_DCtx* dstDCtx, const ZSTD_DCtx* srcDCtx)
+{
+    size_t const toCopy = (size_t)((char*)(&dstDCtx->inBuff) - (char*)dstDCtx);
+    ZSTD_memcpy(dstDCtx, srcDCtx, toCopy);  /* no need to copy workspace */
+}
+
+/* Given a dctx with a digested frame params, re-selects the correct ZSTD_DDict based on
+ * the requested dict ID from the frame. If there exists a reference to the correct ZSTD_DDict, then
+ * accordingly sets the ddict to be used to decompress the frame.
+ *
+ * If no DDict is found, then no action is taken, and the ZSTD_DCtx::ddict remains as-is.
+ *
+ * ZSTD_d_refMultipleDDicts must be enabled for this function to be called.
+ */
+static void ZSTD_DCtx_selectFrameDDict(ZSTD_DCtx* dctx) {
+    assert(dctx->refMultipleDDicts && dctx->ddictSet);
+    DEBUGLOG(4, "Adjusting DDict based on requested dict ID from frame");
+    if (dctx->ddict) {
+        const ZSTD_DDict* frameDDict = ZSTD_DDictHashSet_getDDict(dctx->ddictSet, dctx->fParams.dictID);
+        if (frameDDict) {
+            DEBUGLOG(4, "DDict found!");
+            ZSTD_clearDict(dctx);
+            dctx->dictID = dctx->fParams.dictID;
+            dctx->ddict = frameDDict;
+            dctx->dictUses = ZSTD_use_indefinitely;
+        }
+    }
+}
+
+
+/*-*************************************************************
+ *   Frame header decoding
+ ***************************************************************/
+
+/*! ZSTD_isFrame() :
+ *  Tells if the content of `buffer` starts with a valid Frame Identifier.
+ *  Note : Frame Identifier is 4 bytes. If `size < 4`, @return will always be 0.
+ *  Note 2 : Legacy Frame Identifiers are considered valid only if Legacy Support is enabled.
+ *  Note 3 : Skippable Frame Identifiers are considered valid. */
+unsigned ZSTD_isFrame(const void* buffer, size_t size)
+{
+    if (size < ZSTD_FRAMEIDSIZE) return 0;
+    {   U32 const magic = MEM_readLE32(buffer);
+        if (magic == ZSTD_MAGICNUMBER) return 1;
+        if ((magic & ZSTD_MAGIC_SKIPPABLE_MASK) == ZSTD_MAGIC_SKIPPABLE_START) return 1;
+    }
+    return 0;
+}
+
+/* ZSTD_frameHeaderSize_internal() :
+ *  srcSize must be large enough to reach header size fields.
+ *  note : only works for formats ZSTD_f_zstd1 and ZSTD_f_zstd1_magicless.
+ * @return : size of the Frame Header
+ *           or an error code, which can be tested with ZSTD_isError() */
+static size_t ZSTD_frameHeaderSize_internal(const void* src, size_t srcSize, ZSTD_format_e format)
+{
+    size_t const minInputSize = ZSTD_startingInputLength(format);
+    RETURN_ERROR_IF(srcSize < minInputSize, srcSize_wrong, "");
+
+    {   BYTE const fhd = ((const BYTE*)src)[minInputSize-1];
+        U32 const dictID= fhd & 3;
+        U32 const singleSegment = (fhd >> 5) & 1;
+        U32 const fcsId = fhd >> 6;
+        return minInputSize + !singleSegment
+             + ZSTD_did_fieldSize[dictID] + ZSTD_fcs_fieldSize[fcsId]
+             + (singleSegment && !fcsId);
+    }
+}
+
+/* ZSTD_frameHeaderSize() :
+ *  srcSize must be >= ZSTD_frameHeaderSize_prefix.
+ * @return : size of the Frame Header,
+ *           or an error code (if srcSize is too small) */
+size_t ZSTD_frameHeaderSize(const void* src, size_t srcSize)
+{
+    return ZSTD_frameHeaderSize_internal(src, srcSize, ZSTD_f_zstd1);
+}
+
+
+/* ZSTD_getFrameHeader_advanced() :
+ *  decode Frame Header, or require larger `srcSize`.
+ *  note : only works for formats ZSTD_f_zstd1 and ZSTD_f_zstd1_magicless
+ * @return : 0, `zfhPtr` is correctly filled,
+ *          >0, `srcSize` is too small, value is wanted `srcSize` amount,
+ *           or an error code, which can be tested using ZSTD_isError() */
+size_t ZSTD_getFrameHeader_advanced(ZSTD_frameHeader* zfhPtr, const void* src, size_t srcSize, ZSTD_format_e format)
+{
+    const BYTE* ip = (const BYTE*)src;
+    size_t const minInputSize = ZSTD_startingInputLength(format);
+
+    ZSTD_memset(zfhPtr, 0, sizeof(*zfhPtr));   /* not strictly necessary, but static analyzer do not understand that zfhPtr is only going to be read only if return value is zero, since they are 2 different signals */
+    if (srcSize < minInputSize) return minInputSize;
+    RETURN_ERROR_IF(src==NULL, GENERIC, "invalid parameter");
+
+    if ( (format != ZSTD_f_zstd1_magicless)
+      && (MEM_readLE32(src) != ZSTD_MAGICNUMBER) ) {
+        if ((MEM_readLE32(src) & ZSTD_MAGIC_SKIPPABLE_MASK) == ZSTD_MAGIC_SKIPPABLE_START) {
+            /* skippable frame */
+            if (srcSize < ZSTD_SKIPPABLEHEADERSIZE)
+                return ZSTD_SKIPPABLEHEADERSIZE; /* magic number + frame length */
+            ZSTD_memset(zfhPtr, 0, sizeof(*zfhPtr));
+            zfhPtr->frameContentSize = MEM_readLE32((const char *)src + ZSTD_FRAMEIDSIZE);
+            zfhPtr->frameType = ZSTD_skippableFrame;
+            return 0;
+        }
+        RETURN_ERROR(prefix_unknown, "");
+    }
+
+    /* ensure there is enough `srcSize` to fully read/decode frame header */
+    {   size_t const fhsize = ZSTD_frameHeaderSize_internal(src, srcSize, format);
+        if (srcSize < fhsize) return fhsize;
+        zfhPtr->headerSize = (U32)fhsize;
+    }
+
+    {   BYTE const fhdByte = ip[minInputSize-1];
+        size_t pos = minInputSize;
+        U32 const dictIDSizeCode = fhdByte&3;
+        U32 const checksumFlag = (fhdByte>>2)&1;
+        U32 const singleSegment = (fhdByte>>5)&1;
+        U32 const fcsID = fhdByte>>6;
+        U64 windowSize = 0;
+        U32 dictID = 0;
+        U64 frameContentSize = ZSTD_CONTENTSIZE_UNKNOWN;
+        RETURN_ERROR_IF((fhdByte & 0x08) != 0, frameParameter_unsupported,
+                        "reserved bits, must be zero");
+
+        if (!singleSegment) {
+            BYTE const wlByte = ip[pos++];
+            U32 const windowLog = (wlByte >> 3) + ZSTD_WINDOWLOG_ABSOLUTEMIN;
+            RETURN_ERROR_IF(windowLog > ZSTD_WINDOWLOG_MAX, frameParameter_windowTooLarge, "");
+            windowSize = (1ULL << windowLog);
+            windowSize += (windowSize >> 3) * (wlByte&7);
+        }
+        switch(dictIDSizeCode)
+        {
+            default:
+                assert(0);  /* impossible */
+                ZSTD_FALLTHROUGH;
+            case 0 : break;
+            case 1 : dictID = ip[pos]; pos++; break;
+            case 2 : dictID = MEM_readLE16(ip+pos); pos+=2; break;
+            case 3 : dictID = MEM_readLE32(ip+pos); pos+=4; break;
+        }
+        switch(fcsID)
+        {
+            default:
+                assert(0);  /* impossible */
+                ZSTD_FALLTHROUGH;
+            case 0 : if (singleSegment) frameContentSize = ip[pos]; break;
+            case 1 : frameContentSize = MEM_readLE16(ip+pos)+256; break;
+            case 2 : frameContentSize = MEM_readLE32(ip+pos); break;
+            case 3 : frameContentSize = MEM_readLE64(ip+pos); break;
+        }
+        if (singleSegment) windowSize = frameContentSize;
+
+        zfhPtr->frameType = ZSTD_frame;
+        zfhPtr->frameContentSize = frameContentSize;
+        zfhPtr->windowSize = windowSize;
+        zfhPtr->blockSizeMax = (unsigned) MIN(windowSize, ZSTD_BLOCKSIZE_MAX);
+        zfhPtr->dictID = dictID;
+        zfhPtr->checksumFlag = checksumFlag;
+    }
+    return 0;
+}
+
+/* ZSTD_getFrameHeader() :
+ *  decode Frame Header, or require larger `srcSize`.
+ *  note : this function does not consume input, it only reads it.
+ * @return : 0, `zfhPtr` is correctly filled,
+ *          >0, `srcSize` is too small, value is wanted `srcSize` amount,
+ *           or an error code, which can be tested using ZSTD_isError() */
+size_t ZSTD_getFrameHeader(ZSTD_frameHeader* zfhPtr, const void* src, size_t srcSize)
+{
+    return ZSTD_getFrameHeader_advanced(zfhPtr, src, srcSize, ZSTD_f_zstd1);
+}
+
+
+/* ZSTD_getFrameContentSize() :
+ *  compatible with legacy mode
+ * @return : decompressed size of the single frame pointed to be `src` if known, otherwise
+ *         - ZSTD_CONTENTSIZE_UNKNOWN if the size cannot be determined
+ *         - ZSTD_CONTENTSIZE_ERROR if an error occurred (e.g. invalid magic number, srcSize too small) */
+unsigned long long ZSTD_getFrameContentSize(const void *src, size_t srcSize)
+{
+    {   ZSTD_frameHeader zfh;
+        if (ZSTD_getFrameHeader(&zfh, src, srcSize) != 0)
+            return ZSTD_CONTENTSIZE_ERROR;
+        if (zfh.frameType == ZSTD_skippableFrame) {
+            return 0;
+        } else {
+            return zfh.frameContentSize;
+    }   }
+}
+
+static size_t readSkippableFrameSize(void const* src, size_t srcSize)
+{
+    size_t const skippableHeaderSize = ZSTD_SKIPPABLEHEADERSIZE;
+    U32 sizeU32;
+
+    RETURN_ERROR_IF(srcSize < ZSTD_SKIPPABLEHEADERSIZE, srcSize_wrong, "");
+
+    sizeU32 = MEM_readLE32((BYTE const*)src + ZSTD_FRAMEIDSIZE);
+    RETURN_ERROR_IF((U32)(sizeU32 + ZSTD_SKIPPABLEHEADERSIZE) < sizeU32,
+                    frameParameter_unsupported, "");
+    {
+        size_t const skippableSize = skippableHeaderSize + sizeU32;
+        RETURN_ERROR_IF(skippableSize > srcSize, srcSize_wrong, "");
+        return skippableSize;
+    }
+}
+
+/* ZSTD_findDecompressedSize() :
+ *  compatible with legacy mode
+ *  `srcSize` must be the exact length of some number of ZSTD compressed and/or
+ *      skippable frames
+ *  @return : decompressed size of the frames contained */
+unsigned long long ZSTD_findDecompressedSize(const void* src, size_t srcSize)
+{
+    unsigned long long totalDstSize = 0;
+
+    while (srcSize >= ZSTD_startingInputLength(ZSTD_f_zstd1)) {
+        U32 const magicNumber = MEM_readLE32(src);
+
+        if ((magicNumber & ZSTD_MAGIC_SKIPPABLE_MASK) == ZSTD_MAGIC_SKIPPABLE_START) {
+            size_t const skippableSize = readSkippableFrameSize(src, srcSize);
+            if (ZSTD_isError(skippableSize)) {
+                return ZSTD_CONTENTSIZE_ERROR;
+            }
+            assert(skippableSize <= srcSize);
+
+            src = (const BYTE *)src + skippableSize;
+            srcSize -= skippableSize;
+            continue;
+        }
+
+        {   unsigned long long const ret = ZSTD_getFrameContentSize(src, srcSize);
+            if (ret >= ZSTD_CONTENTSIZE_ERROR) return ret;
+
+            /* check for overflow */
+            if (totalDstSize + ret < totalDstSize) return ZSTD_CONTENTSIZE_ERROR;
+            totalDstSize += ret;
+        }
+        {   size_t const frameSrcSize = ZSTD_findFrameCompressedSize(src, srcSize);
+            if (ZSTD_isError(frameSrcSize)) {
+                return ZSTD_CONTENTSIZE_ERROR;
+            }
+
+            src = (const BYTE *)src + frameSrcSize;
+            srcSize -= frameSrcSize;
+        }
+    }  /* while (srcSize >= ZSTD_frameHeaderSize_prefix) */
+
+    if (srcSize) return ZSTD_CONTENTSIZE_ERROR;
+
+    return totalDstSize;
+}
+
+/* ZSTD_getDecompressedSize() :
+ *  compatible with legacy mode
+ * @return : decompressed size if known, 0 otherwise
+             note : 0 can mean any of the following :
+                   - frame content is empty
+                   - decompressed size field is not present in frame header
+                   - frame header unknown / not supported
+                   - frame header not complete (`srcSize` too small) */
+unsigned long long ZSTD_getDecompressedSize(const void* src, size_t srcSize)
+{
+    unsigned long long const ret = ZSTD_getFrameContentSize(src, srcSize);
+    ZSTD_STATIC_ASSERT(ZSTD_CONTENTSIZE_ERROR < ZSTD_CONTENTSIZE_UNKNOWN);
+    return (ret >= ZSTD_CONTENTSIZE_ERROR) ? 0 : ret;
+}
+
+
+/* ZSTD_decodeFrameHeader() :
+ * `headerSize` must be the size provided by ZSTD_frameHeaderSize().
+ * If multiple DDict references are enabled, also will choose the correct DDict to use.
+ * @return : 0 if success, or an error code, which can be tested using ZSTD_isError() */
+static size_t ZSTD_decodeFrameHeader(ZSTD_DCtx* dctx, const void* src, size_t headerSize)
+{
+    size_t const result = ZSTD_getFrameHeader_advanced(&(dctx->fParams), src, headerSize, dctx->format);
+    if (ZSTD_isError(result)) return result;    /* invalid header */
+    RETURN_ERROR_IF(result>0, srcSize_wrong, "headerSize too small");
+
+    /* Reference DDict requested by frame if dctx references multiple ddicts */
+    if (dctx->refMultipleDDicts == ZSTD_rmd_refMultipleDDicts && dctx->ddictSet) {
+        ZSTD_DCtx_selectFrameDDict(dctx);
+    }
+
+#ifndef FUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION
+    /* Skip the dictID check in fuzzing mode, because it makes the search
+     * harder.
+     */
+    RETURN_ERROR_IF(dctx->fParams.dictID && (dctx->dictID != dctx->fParams.dictID),
+                    dictionary_wrong, "");
+#endif
+    dctx->validateChecksum = (dctx->fParams.checksumFlag && !dctx->forceIgnoreChecksum) ? 1 : 0;
+    if (dctx->validateChecksum) xxh64_reset(&dctx->xxhState, 0);
+    dctx->processedCSize += headerSize;
+    return 0;
+}
+
+static ZSTD_frameSizeInfo ZSTD_errorFrameSizeInfo(size_t ret)
+{
+    ZSTD_frameSizeInfo frameSizeInfo;
+    frameSizeInfo.compressedSize = ret;
+    frameSizeInfo.decompressedBound = ZSTD_CONTENTSIZE_ERROR;
+    return frameSizeInfo;
+}
+
+static ZSTD_frameSizeInfo ZSTD_findFrameSizeInfo(const void* src, size_t srcSize)
+{
+    ZSTD_frameSizeInfo frameSizeInfo;
+    ZSTD_memset(&frameSizeInfo, 0, sizeof(ZSTD_frameSizeInfo));
+
+
+    if ((srcSize >= ZSTD_SKIPPABLEHEADERSIZE)
+        && (MEM_readLE32(src) & ZSTD_MAGIC_SKIPPABLE_MASK) == ZSTD_MAGIC_SKIPPABLE_START) {
+        frameSizeInfo.compressedSize = readSkippableFrameSize(src, srcSize);
+        assert(ZSTD_isError(frameSizeInfo.compressedSize) ||
+               frameSizeInfo.compressedSize <= srcSize);
+        return frameSizeInfo;
+    } else {
+        const BYTE* ip = (const BYTE*)src;
+        const BYTE* const ipstart = ip;
+        size_t remainingSize = srcSize;
+        size_t nbBlocks = 0;
+        ZSTD_frameHeader zfh;
+
+        /* Extract Frame Header */
+        {   size_t const ret = ZSTD_getFrameHeader(&zfh, src, srcSize);
+            if (ZSTD_isError(ret))
+                return ZSTD_errorFrameSizeInfo(ret);
+            if (ret > 0)
+                return ZSTD_errorFrameSizeInfo(ERROR(srcSize_wrong));
+        }
+
+        ip += zfh.headerSize;
+        remainingSize -= zfh.headerSize;
+
+        /* Iterate over each block */
+        while (1) {
+            blockProperties_t blockProperties;
+            size_t const cBlockSize = ZSTD_getcBlockSize(ip, remainingSize, &blockProperties);
+            if (ZSTD_isError(cBlockSize))
+                return ZSTD_errorFrameSizeInfo(cBlockSize);
+
+            if (ZSTD_blockHeaderSize + cBlockSize > remainingSize)
+                return ZSTD_errorFrameSizeInfo(ERROR(srcSize_wrong));
+
+            ip += ZSTD_blockHeaderSize + cBlockSize;
+            remainingSize -= ZSTD_blockHeaderSize + cBlockSize;
+            nbBlocks++;
+
+            if (blockProperties.lastBlock) break;
+        }
+
+        /* Final frame content checksum */
+        if (zfh.checksumFlag) {
+            if (remainingSize < 4)
+                return ZSTD_errorFrameSizeInfo(ERROR(srcSize_wrong));
+            ip += 4;
+        }
+
+        frameSizeInfo.compressedSize = (size_t)(ip - ipstart);
+        frameSizeInfo.decompressedBound = (zfh.frameContentSize != ZSTD_CONTENTSIZE_UNKNOWN)
+                                        ? zfh.frameContentSize
+                                        : nbBlocks * zfh.blockSizeMax;
+        return frameSizeInfo;
+    }
+}
+
+/* ZSTD_findFrameCompressedSize() :
+ *  compatible with legacy mode
+ *  `src` must point to the start of a ZSTD frame, ZSTD legacy frame, or skippable frame
+ *  `srcSize` must be at least as large as the frame contained
+ *  @return : the compressed size of the frame starting at `src` */
+size_t ZSTD_findFrameCompressedSize(const void *src, size_t srcSize)
+{
+    ZSTD_frameSizeInfo const frameSizeInfo = ZSTD_findFrameSizeInfo(src, srcSize);
+    return frameSizeInfo.compressedSize;
+}
+
+/* ZSTD_decompressBound() :
+ *  compatible with legacy mode
+ *  `src` must point to the start of a ZSTD frame or a skippeable frame
+ *  `srcSize` must be at least as large as the frame contained
+ *  @return : the maximum decompressed size of the compressed source
+ */
+unsigned long long ZSTD_decompressBound(const void* src, size_t srcSize)
+{
+    unsigned long long bound = 0;
+    /* Iterate over each frame */
+    while (srcSize > 0) {
+        ZSTD_frameSizeInfo const frameSizeInfo = ZSTD_findFrameSizeInfo(src, srcSize);
+        size_t const compressedSize = frameSizeInfo.compressedSize;
+        unsigned long long const decompressedBound = frameSizeInfo.decompressedBound;
+        if (ZSTD_isError(compressedSize) || decompressedBound == ZSTD_CONTENTSIZE_ERROR)
+            return ZSTD_CONTENTSIZE_ERROR;
+        assert(srcSize >= compressedSize);
+        src = (const BYTE*)src + compressedSize;
+        srcSize -= compressedSize;
+        bound += decompressedBound;
+    }
+    return bound;
+}
+
+
+/*-*************************************************************
+ *   Frame decoding
+ ***************************************************************/
+
+/* ZSTD_insertBlock() :
+ *  insert `src` block into `dctx` history. Useful to track uncompressed blocks. */
+size_t ZSTD_insertBlock(ZSTD_DCtx* dctx, const void* blockStart, size_t blockSize)
+{
+    DEBUGLOG(5, "ZSTD_insertBlock: %u bytes", (unsigned)blockSize);
+    ZSTD_checkContinuity(dctx, blockStart, blockSize);
+    dctx->previousDstEnd = (const char*)blockStart + blockSize;
+    return blockSize;
+}
+
+
+static size_t ZSTD_copyRawBlock(void* dst, size_t dstCapacity,
+                          const void* src, size_t srcSize)
+{
+    DEBUGLOG(5, "ZSTD_copyRawBlock");
+    RETURN_ERROR_IF(srcSize > dstCapacity, dstSize_tooSmall, "");
+    if (dst == NULL) {
+        if (srcSize == 0) return 0;
+        RETURN_ERROR(dstBuffer_null, "");
+    }
+    ZSTD_memcpy(dst, src, srcSize);
+    return srcSize;
+}
+
+static size_t ZSTD_setRleBlock(void* dst, size_t dstCapacity,
+                               BYTE b,
+                               size_t regenSize)
+{
+    RETURN_ERROR_IF(regenSize > dstCapacity, dstSize_tooSmall, "");
+    if (dst == NULL) {
+        if (regenSize == 0) return 0;
+        RETURN_ERROR(dstBuffer_null, "");
+    }
+    ZSTD_memset(dst, b, regenSize);
+    return regenSize;
+}
+
+static void ZSTD_DCtx_trace_end(ZSTD_DCtx const* dctx, U64 uncompressedSize, U64 compressedSize, unsigned streaming)
+{
+    (void)dctx;
+    (void)uncompressedSize;
+    (void)compressedSize;
+    (void)streaming;
+}
+
+
+/*! ZSTD_decompressFrame() :
+ * @dctx must be properly initialized
+ *  will update *srcPtr and *srcSizePtr,
+ *  to make *srcPtr progress by one frame. */
+static size_t ZSTD_decompressFrame(ZSTD_DCtx* dctx,
+                                   void* dst, size_t dstCapacity,
+                             const void** srcPtr, size_t *srcSizePtr)
+{
+    const BYTE* const istart = (const BYTE*)(*srcPtr);
+    const BYTE* ip = istart;
+    BYTE* const ostart = (BYTE*)dst;
+    BYTE* const oend = dstCapacity != 0 ? ostart + dstCapacity : ostart;
+    BYTE* op = ostart;
+    size_t remainingSrcSize = *srcSizePtr;
+
+    DEBUGLOG(4, "ZSTD_decompressFrame (srcSize:%i)", (int)*srcSizePtr);
+
+    /* check */
+    RETURN_ERROR_IF(
+        remainingSrcSize < ZSTD_FRAMEHEADERSIZE_MIN(dctx->format)+ZSTD_blockHeaderSize,
+        srcSize_wrong, "");
+
+    /* Frame Header */
+    {   size_t const frameHeaderSize = ZSTD_frameHeaderSize_internal(
+                ip, ZSTD_FRAMEHEADERSIZE_PREFIX(dctx->format), dctx->format);
+        if (ZSTD_isError(frameHeaderSize)) return frameHeaderSize;
+        RETURN_ERROR_IF(remainingSrcSize < frameHeaderSize+ZSTD_blockHeaderSize,
+                        srcSize_wrong, "");
+        FORWARD_IF_ERROR( ZSTD_decodeFrameHeader(dctx, ip, frameHeaderSize) , "");
+        ip += frameHeaderSize; remainingSrcSize -= frameHeaderSize;
+    }
+
+    /* Loop on each block */
+    while (1) {
+        size_t decodedSize;
+        blockProperties_t blockProperties;
+        size_t const cBlockSize = ZSTD_getcBlockSize(ip, remainingSrcSize, &blockProperties);
+        if (ZSTD_isError(cBlockSize)) return cBlockSize;
+
+        ip += ZSTD_blockHeaderSize;
+        remainingSrcSize -= ZSTD_blockHeaderSize;
+        RETURN_ERROR_IF(cBlockSize > remainingSrcSize, srcSize_wrong, "");
+
+        switch(blockProperties.blockType)
+        {
+        case bt_compressed:
+            decodedSize = ZSTD_decompressBlock_internal(dctx, op, (size_t)(oend-op), ip, cBlockSize, /* frame */ 1);
+            break;
+        case bt_raw :
+            decodedSize = ZSTD_copyRawBlock(op, (size_t)(oend-op), ip, cBlockSize);
+            break;
+        case bt_rle :
+            decodedSize = ZSTD_setRleBlock(op, (size_t)(oend-op), *ip, blockProperties.origSize);
+            break;
+        case bt_reserved :
+        default:
+            RETURN_ERROR(corruption_detected, "invalid block type");
+        }
+
+        if (ZSTD_isError(decodedSize)) return decodedSize;
+        if (dctx->validateChecksum)
+            xxh64_update(&dctx->xxhState, op, decodedSize);
+        if (decodedSize != 0)
+            op += decodedSize;
+        assert(ip != NULL);
+        ip += cBlockSize;
+        remainingSrcSize -= cBlockSize;
+        if (blockProperties.lastBlock) break;
+    }
+
+    if (dctx->fParams.frameContentSize != ZSTD_CONTENTSIZE_UNKNOWN) {
+        RETURN_ERROR_IF((U64)(op-ostart) != dctx->fParams.frameContentSize,
+                        corruption_detected, "");
+    }
+    if (dctx->fParams.checksumFlag) { /* Frame content checksum verification */
+        RETURN_ERROR_IF(remainingSrcSize<4, checksum_wrong, "");
+        if (!dctx->forceIgnoreChecksum) {
+            U32 const checkCalc = (U32)xxh64_digest(&dctx->xxhState);
+            U32 checkRead;
+            checkRead = MEM_readLE32(ip);
+            RETURN_ERROR_IF(checkRead != checkCalc, checksum_wrong, "");
+        }
+        ip += 4;
+        remainingSrcSize -= 4;
+    }
+    ZSTD_DCtx_trace_end(dctx, (U64)(op-ostart), (U64)(ip-istart), /* streaming */ 0);
+    /* Allow caller to get size read */
+    *srcPtr = ip;
+    *srcSizePtr = remainingSrcSize;
+    return (size_t)(op-ostart);
+}
+
+static size_t ZSTD_decompressMultiFrame(ZSTD_DCtx* dctx,
+                                        void* dst, size_t dstCapacity,
+                                  const void* src, size_t srcSize,
+                                  const void* dict, size_t dictSize,
+                                  const ZSTD_DDict* ddict)
+{
+    void* const dststart = dst;
+    int moreThan1Frame = 0;
+
+    DEBUGLOG(5, "ZSTD_decompressMultiFrame");
+    assert(dict==NULL || ddict==NULL);  /* either dict or ddict set, not both */
+
+    if (ddict) {
+        dict = ZSTD_DDict_dictContent(ddict);
+        dictSize = ZSTD_DDict_dictSize(ddict);
+    }
+
+    while (srcSize >= ZSTD_startingInputLength(dctx->format)) {
+
+
+        {   U32 const magicNumber = MEM_readLE32(src);
+            DEBUGLOG(4, "reading magic number %08X (expecting %08X)",
+                        (unsigned)magicNumber, ZSTD_MAGICNUMBER);
+            if ((magicNumber & ZSTD_MAGIC_SKIPPABLE_MASK) == ZSTD_MAGIC_SKIPPABLE_START) {
+                size_t const skippableSize = readSkippableFrameSize(src, srcSize);
+                FORWARD_IF_ERROR(skippableSize, "readSkippableFrameSize failed");
+                assert(skippableSize <= srcSize);
+
+                src = (const BYTE *)src + skippableSize;
+                srcSize -= skippableSize;
+                continue;
+        }   }
+
+        if (ddict) {
+            /* we were called from ZSTD_decompress_usingDDict */
+            FORWARD_IF_ERROR(ZSTD_decompressBegin_usingDDict(dctx, ddict), "");
+        } else {
+            /* this will initialize correctly with no dict if dict == NULL, so
+             * use this in all cases but ddict */
+            FORWARD_IF_ERROR(ZSTD_decompressBegin_usingDict(dctx, dict, dictSize), "");
+        }
+        ZSTD_checkContinuity(dctx, dst, dstCapacity);
+
+        {   const size_t res = ZSTD_decompressFrame(dctx, dst, dstCapacity,
+                                                    &src, &srcSize);
+            RETURN_ERROR_IF(
+                (ZSTD_getErrorCode(res) == ZSTD_error_prefix_unknown)
+             && (moreThan1Frame==1),
+                srcSize_wrong,
+                "At least one frame successfully completed, "
+                "but following bytes are garbage: "
+                "it's more likely to be a srcSize error, "
+                "specifying more input bytes than size of frame(s). "
+                "Note: one could be unlucky, it might be a corruption error instead, "
+                "happening right at the place where we expect zstd magic bytes. "
+                "But this is _much_ less likely than a srcSize field error.");
+            if (ZSTD_isError(res)) return res;
+            assert(res <= dstCapacity);
+            if (res != 0)
+                dst = (BYTE*)dst + res;
+            dstCapacity -= res;
+        }
+        moreThan1Frame = 1;
+    }  /* while (srcSize >= ZSTD_frameHeaderSize_prefix) */
+
+    RETURN_ERROR_IF(srcSize, srcSize_wrong, "input not entirely consumed");
+
+    return (size_t)((BYTE*)dst - (BYTE*)dststart);
+}
+
+size_t ZSTD_decompress_usingDict(ZSTD_DCtx* dctx,
+                                 void* dst, size_t dstCapacity,
+                           const void* src, size_t srcSize,
+                           const void* dict, size_t dictSize)
+{
+    return ZSTD_decompressMultiFrame(dctx, dst, dstCapacity, src, srcSize, dict, dictSize, NULL);
+}
+
+
+static ZSTD_DDict const* ZSTD_getDDict(ZSTD_DCtx* dctx)
+{
+    switch (dctx->dictUses) {
+    default:
+        assert(0 /* Impossible */);
+        ZSTD_FALLTHROUGH;
+    case ZSTD_dont_use:
+        ZSTD_clearDict(dctx);
+        return NULL;
+    case ZSTD_use_indefinitely:
+        return dctx->ddict;
+    case ZSTD_use_once:
+        dctx->dictUses = ZSTD_dont_use;
+        return dctx->ddict;
+    }
+}
+
+size_t ZSTD_decompressDCtx(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize)
+{
+    return ZSTD_decompress_usingDDict(dctx, dst, dstCapacity, src, srcSize, ZSTD_getDDict(dctx));
+}
+
+
+size_t ZSTD_decompress(void* dst, size_t dstCapacity, const void* src, size_t srcSize)
+{
+#if defined(ZSTD_HEAPMODE) && (ZSTD_HEAPMODE>=1)
+    size_t regenSize;
+    ZSTD_DCtx* const dctx = ZSTD_createDCtx();
+    RETURN_ERROR_IF(dctx==NULL, memory_allocation, "NULL pointer!");
+    regenSize = ZSTD_decompressDCtx(dctx, dst, dstCapacity, src, srcSize);
+    ZSTD_freeDCtx(dctx);
+    return regenSize;
+#else   /* stack mode */
+    ZSTD_DCtx dctx;
+    ZSTD_initDCtx_internal(&dctx);
+    return ZSTD_decompressDCtx(&dctx, dst, dstCapacity, src, srcSize);
+#endif
+}
+
+
+/*-**************************************
+*   Advanced Streaming Decompression API
+*   Bufferless and synchronous
+****************************************/
+size_t ZSTD_nextSrcSizeToDecompress(ZSTD_DCtx* dctx) { return dctx->expected; }
+
+/*
+ * Similar to ZSTD_nextSrcSizeToDecompress(), but when when a block input can be streamed,
+ * we allow taking a partial block as the input. Currently only raw uncompressed blocks can
+ * be streamed.
+ *
+ * For blocks that can be streamed, this allows us to reduce the latency until we produce
+ * output, and avoid copying the input.
+ *
+ * @param inputSize - The total amount of input that the caller currently has.
+ */
+static size_t ZSTD_nextSrcSizeToDecompressWithInputSize(ZSTD_DCtx* dctx, size_t inputSize) {
+    if (!(dctx->stage == ZSTDds_decompressBlock || dctx->stage == ZSTDds_decompressLastBlock))
+        return dctx->expected;
+    if (dctx->bType != bt_raw)
+        return dctx->expected;
+    return MIN(MAX(inputSize, 1), dctx->expected);
+}
+
+ZSTD_nextInputType_e ZSTD_nextInputType(ZSTD_DCtx* dctx) {
+    switch(dctx->stage)
+    {
+    default:   /* should not happen */
+        assert(0);
+        ZSTD_FALLTHROUGH;
+    case ZSTDds_getFrameHeaderSize:
+        ZSTD_FALLTHROUGH;
+    case ZSTDds_decodeFrameHeader:
+        return ZSTDnit_frameHeader;
+    case ZSTDds_decodeBlockHeader:
+        return ZSTDnit_blockHeader;
+    case ZSTDds_decompressBlock:
+        return ZSTDnit_block;
+    case ZSTDds_decompressLastBlock:
+        return ZSTDnit_lastBlock;
+    case ZSTDds_checkChecksum:
+        return ZSTDnit_checksum;
+    case ZSTDds_decodeSkippableHeader:
+        ZSTD_FALLTHROUGH;
+    case ZSTDds_skipFrame:
+        return ZSTDnit_skippableFrame;
+    }
+}
+
+static int ZSTD_isSkipFrame(ZSTD_DCtx* dctx) { return dctx->stage == ZSTDds_skipFrame; }
+
+/* ZSTD_decompressContinue() :
+ *  srcSize : must be the exact nb of bytes expected (see ZSTD_nextSrcSizeToDecompress())
+ *  @return : nb of bytes generated into `dst` (necessarily <= `dstCapacity)
+ *            or an error code, which can be tested using ZSTD_isError() */
+size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize)
+{
+    DEBUGLOG(5, "ZSTD_decompressContinue (srcSize:%u)", (unsigned)srcSize);
+    /* Sanity check */
+    RETURN_ERROR_IF(srcSize != ZSTD_nextSrcSizeToDecompressWithInputSize(dctx, srcSize), srcSize_wrong, "not allowed");
+    ZSTD_checkContinuity(dctx, dst, dstCapacity);
+
+    dctx->processedCSize += srcSize;
+
+    switch (dctx->stage)
+    {
+    case ZSTDds_getFrameHeaderSize :
+        assert(src != NULL);
+        if (dctx->format == ZSTD_f_zstd1) {  /* allows header */
+            assert(srcSize >= ZSTD_FRAMEIDSIZE);  /* to read skippable magic number */
+            if ((MEM_readLE32(src) & ZSTD_MAGIC_SKIPPABLE_MASK) == ZSTD_MAGIC_SKIPPABLE_START) {        /* skippable frame */
+                ZSTD_memcpy(dctx->headerBuffer, src, srcSize);
+                dctx->expected = ZSTD_SKIPPABLEHEADERSIZE - srcSize;  /* remaining to load to get full skippable frame header */
+                dctx->stage = ZSTDds_decodeSkippableHeader;
+                return 0;
+        }   }
+        dctx->headerSize = ZSTD_frameHeaderSize_internal(src, srcSize, dctx->format);
+        if (ZSTD_isError(dctx->headerSize)) return dctx->headerSize;
+        ZSTD_memcpy(dctx->headerBuffer, src, srcSize);
+        dctx->expected = dctx->headerSize - srcSize;
+        dctx->stage = ZSTDds_decodeFrameHeader;
+        return 0;
+
+    case ZSTDds_decodeFrameHeader:
+        assert(src != NULL);
+        ZSTD_memcpy(dctx->headerBuffer + (dctx->headerSize - srcSize), src, srcSize);
+        FORWARD_IF_ERROR(ZSTD_decodeFrameHeader(dctx, dctx->headerBuffer, dctx->headerSize), "");
+        dctx->expected = ZSTD_blockHeaderSize;
+        dctx->stage = ZSTDds_decodeBlockHeader;
+        return 0;
+
+    case ZSTDds_decodeBlockHeader:
+        {   blockProperties_t bp;
+            size_t const cBlockSize = ZSTD_getcBlockSize(src, ZSTD_blockHeaderSize, &bp);
+            if (ZSTD_isError(cBlockSize)) return cBlockSize;
+            RETURN_ERROR_IF(cBlockSize > dctx->fParams.blockSizeMax, corruption_detected, "Block Size Exceeds Maximum");
+            dctx->expected = cBlockSize;
+            dctx->bType = bp.blockType;
+            dctx->rleSize = bp.origSize;
+            if (cBlockSize) {
+                dctx->stage = bp.lastBlock ? ZSTDds_decompressLastBlock : ZSTDds_decompressBlock;
+                return 0;
+            }
+            /* empty block */
+            if (bp.lastBlock) {
+                if (dctx->fParams.checksumFlag) {
+                    dctx->expected = 4;
+                    dctx->stage = ZSTDds_checkChecksum;
+                } else {
+                    dctx->expected = 0; /* end of frame */
+                    dctx->stage = ZSTDds_getFrameHeaderSize;
+                }
+            } else {
+                dctx->expected = ZSTD_blockHeaderSize;  /* jump to next header */
+                dctx->stage = ZSTDds_decodeBlockHeader;
+            }
+            return 0;
+        }
+
+    case ZSTDds_decompressLastBlock:
+    case ZSTDds_decompressBlock:
+        DEBUGLOG(5, "ZSTD_decompressContinue: case ZSTDds_decompressBlock");
+        {   size_t rSize;
+            switch(dctx->bType)
+            {
+            case bt_compressed:
+                DEBUGLOG(5, "ZSTD_decompressContinue: case bt_compressed");
+                rSize = ZSTD_decompressBlock_internal(dctx, dst, dstCapacity, src, srcSize, /* frame */ 1);
+                dctx->expected = 0;  /* Streaming not supported */
+                break;
+            case bt_raw :
+                assert(srcSize <= dctx->expected);
+                rSize = ZSTD_copyRawBlock(dst, dstCapacity, src, srcSize);
+                FORWARD_IF_ERROR(rSize, "ZSTD_copyRawBlock failed");
+                assert(rSize == srcSize);
+                dctx->expected -= rSize;
+                break;
+            case bt_rle :
+                rSize = ZSTD_setRleBlock(dst, dstCapacity, *(const BYTE*)src, dctx->rleSize);
+                dctx->expected = 0;  /* Streaming not supported */
+                break;
+            case bt_reserved :   /* should never happen */
+            default:
+                RETURN_ERROR(corruption_detected, "invalid block type");
+            }
+            FORWARD_IF_ERROR(rSize, "");
+            RETURN_ERROR_IF(rSize > dctx->fParams.blockSizeMax, corruption_detected, "Decompressed Block Size Exceeds Maximum");
+            DEBUGLOG(5, "ZSTD_decompressContinue: decoded size from block : %u", (unsigned)rSize);
+            dctx->decodedSize += rSize;
+            if (dctx->validateChecksum) xxh64_update(&dctx->xxhState, dst, rSize);
+            dctx->previousDstEnd = (char*)dst + rSize;
+
+            /* Stay on the same stage until we are finished streaming the block. */
+            if (dctx->expected > 0) {
+                return rSize;
+            }
+
+            if (dctx->stage == ZSTDds_decompressLastBlock) {   /* end of frame */
+                DEBUGLOG(4, "ZSTD_decompressContinue: decoded size from frame : %u", (unsigned)dctx->decodedSize);
+                RETURN_ERROR_IF(
+                    dctx->fParams.frameContentSize != ZSTD_CONTENTSIZE_UNKNOWN
+                 && dctx->decodedSize != dctx->fParams.frameContentSize,
+                    corruption_detected, "");
+                if (dctx->fParams.checksumFlag) {  /* another round for frame checksum */
+                    dctx->expected = 4;
+                    dctx->stage = ZSTDds_checkChecksum;
+                } else {
+                    ZSTD_DCtx_trace_end(dctx, dctx->decodedSize, dctx->processedCSize, /* streaming */ 1);
+                    dctx->expected = 0;   /* ends here */
+                    dctx->stage = ZSTDds_getFrameHeaderSize;
+                }
+            } else {
+                dctx->stage = ZSTDds_decodeBlockHeader;
+                dctx->expected = ZSTD_blockHeaderSize;
+            }
+            return rSize;
+        }
+
+    case ZSTDds_checkChecksum:
+        assert(srcSize == 4);  /* guaranteed by dctx->expected */
+        {
+            if (dctx->validateChecksum) {
+                U32 const h32 = (U32)xxh64_digest(&dctx->xxhState);
+                U32 const check32 = MEM_readLE32(src);
+                DEBUGLOG(4, "ZSTD_decompressContinue: checksum : calculated %08X :: %08X read", (unsigned)h32, (unsigned)check32);
+                RETURN_ERROR_IF(check32 != h32, checksum_wrong, "");
+            }
+            ZSTD_DCtx_trace_end(dctx, dctx->decodedSize, dctx->processedCSize, /* streaming */ 1);
+            dctx->expected = 0;
+            dctx->stage = ZSTDds_getFrameHeaderSize;
+            return 0;
+        }
+
+    case ZSTDds_decodeSkippableHeader:
+        assert(src != NULL);
+        assert(srcSize <= ZSTD_SKIPPABLEHEADERSIZE);
+        ZSTD_memcpy(dctx->headerBuffer + (ZSTD_SKIPPABLEHEADERSIZE - srcSize), src, srcSize);   /* complete skippable header */
+        dctx->expected = MEM_readLE32(dctx->headerBuffer + ZSTD_FRAMEIDSIZE);   /* note : dctx->expected can grow seriously large, beyond local buffer size */
+        dctx->stage = ZSTDds_skipFrame;
+        return 0;
+
+    case ZSTDds_skipFrame:
+        dctx->expected = 0;
+        dctx->stage = ZSTDds_getFrameHeaderSize;
+        return 0;
+
+    default:
+        assert(0);   /* impossible */
+        RETURN_ERROR(GENERIC, "impossible to reach");   /* some compiler require default to do something */
+    }
+}
+
+
+static size_t ZSTD_refDictContent(ZSTD_DCtx* dctx, const void* dict, size_t dictSize)
+{
+    dctx->dictEnd = dctx->previousDstEnd;
+    dctx->virtualStart = (const char*)dict - ((const char*)(dctx->previousDstEnd) - (const char*)(dctx->prefixStart));
+    dctx->prefixStart = dict;
+    dctx->previousDstEnd = (const char*)dict + dictSize;
+#ifdef FUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION
+    dctx->dictContentBeginForFuzzing = dctx->prefixStart;
+    dctx->dictContentEndForFuzzing = dctx->previousDstEnd;
+#endif
+    return 0;
+}
+
+/*! ZSTD_loadDEntropy() :
+ *  dict : must point at beginning of a valid zstd dictionary.
+ * @return : size of entropy tables read */
+size_t
+ZSTD_loadDEntropy(ZSTD_entropyDTables_t* entropy,
+                  const void* const dict, size_t const dictSize)
+{
+    const BYTE* dictPtr = (const BYTE*)dict;
+    const BYTE* const dictEnd = dictPtr + dictSize;
+
+    RETURN_ERROR_IF(dictSize <= 8, dictionary_corrupted, "dict is too small");
+    assert(MEM_readLE32(dict) == ZSTD_MAGIC_DICTIONARY);   /* dict must be valid */
+    dictPtr += 8;   /* skip header = magic + dictID */
+
+    ZSTD_STATIC_ASSERT(offsetof(ZSTD_entropyDTables_t, OFTable) == offsetof(ZSTD_entropyDTables_t, LLTable) + sizeof(entropy->LLTable));
+    ZSTD_STATIC_ASSERT(offsetof(ZSTD_entropyDTables_t, MLTable) == offsetof(ZSTD_entropyDTables_t, OFTable) + sizeof(entropy->OFTable));
+    ZSTD_STATIC_ASSERT(sizeof(entropy->LLTable) + sizeof(entropy->OFTable) + sizeof(entropy->MLTable) >= HUF_DECOMPRESS_WORKSPACE_SIZE);
+    {   void* const workspace = &entropy->LLTable;   /* use fse tables as temporary workspace; implies fse tables are grouped together */
+        size_t const workspaceSize = sizeof(entropy->LLTable) + sizeof(entropy->OFTable) + sizeof(entropy->MLTable);
+#ifdef HUF_FORCE_DECOMPRESS_X1
+        /* in minimal huffman, we always use X1 variants */
+        size_t const hSize = HUF_readDTableX1_wksp(entropy->hufTable,
+                                                dictPtr, dictEnd - dictPtr,
+                                                workspace, workspaceSize);
+#else
+        size_t const hSize = HUF_readDTableX2_wksp(entropy->hufTable,
+                                                dictPtr, (size_t)(dictEnd - dictPtr),
+                                                workspace, workspaceSize);
+#endif
+        RETURN_ERROR_IF(HUF_isError(hSize), dictionary_corrupted, "");
+        dictPtr += hSize;
+    }
+
+    {   short offcodeNCount[MaxOff+1];
+        unsigned offcodeMaxValue = MaxOff, offcodeLog;
+        size_t const offcodeHeaderSize = FSE_readNCount(offcodeNCount, &offcodeMaxValue, &offcodeLog, dictPtr, (size_t)(dictEnd-dictPtr));
+        RETURN_ERROR_IF(FSE_isError(offcodeHeaderSize), dictionary_corrupted, "");
+        RETURN_ERROR_IF(offcodeMaxValue > MaxOff, dictionary_corrupted, "");
+        RETURN_ERROR_IF(offcodeLog > OffFSELog, dictionary_corrupted, "");
+        ZSTD_buildFSETable( entropy->OFTable,
+                            offcodeNCount, offcodeMaxValue,
+                            OF_base, OF_bits,
+                            offcodeLog,
+                            entropy->workspace, sizeof(entropy->workspace),
+                            /* bmi2 */0);
+        dictPtr += offcodeHeaderSize;
+    }
+
+    {   short matchlengthNCount[MaxML+1];
+        unsigned matchlengthMaxValue = MaxML, matchlengthLog;
+        size_t const matchlengthHeaderSize = FSE_readNCount(matchlengthNCount, &matchlengthMaxValue, &matchlengthLog, dictPtr, (size_t)(dictEnd-dictPtr));
+        RETURN_ERROR_IF(FSE_isError(matchlengthHeaderSize), dictionary_corrupted, "");
+        RETURN_ERROR_IF(matchlengthMaxValue > MaxML, dictionary_corrupted, "");
+        RETURN_ERROR_IF(matchlengthLog > MLFSELog, dictionary_corrupted, "");
+        ZSTD_buildFSETable( entropy->MLTable,
+                            matchlengthNCount, matchlengthMaxValue,
+                            ML_base, ML_bits,
+                            matchlengthLog,
+                            entropy->workspace, sizeof(entropy->workspace),
+                            /* bmi2 */ 0);
+        dictPtr += matchlengthHeaderSize;
+    }
+
+    {   short litlengthNCount[MaxLL+1];
+        unsigned litlengthMaxValue = MaxLL, litlengthLog;
+        size_t const litlengthHeaderSize = FSE_readNCount(litlengthNCount, &litlengthMaxValue, &litlengthLog, dictPtr, (size_t)(dictEnd-dictPtr));
+        RETURN_ERROR_IF(FSE_isError(litlengthHeaderSize), dictionary_corrupted, "");
+        RETURN_ERROR_IF(litlengthMaxValue > MaxLL, dictionary_corrupted, "");
+        RETURN_ERROR_IF(litlengthLog > LLFSELog, dictionary_corrupted, "");
+        ZSTD_buildFSETable( entropy->LLTable,
+                            litlengthNCount, litlengthMaxValue,
+                            LL_base, LL_bits,
+                            litlengthLog,
+                            entropy->workspace, sizeof(entropy->workspace),
+                            /* bmi2 */ 0);
+        dictPtr += litlengthHeaderSize;
+    }
+
+    RETURN_ERROR_IF(dictPtr+12 > dictEnd, dictionary_corrupted, "");
+    {   int i;
+        size_t const dictContentSize = (size_t)(dictEnd - (dictPtr+12));
+        for (i=0; i<3; i++) {
+            U32 const rep = MEM_readLE32(dictPtr); dictPtr += 4;
+            RETURN_ERROR_IF(rep==0 || rep > dictContentSize,
+                            dictionary_corrupted, "");
+            entropy->rep[i] = rep;
+    }   }
+
+    return (size_t)(dictPtr - (const BYTE*)dict);
+}
+
+static size_t ZSTD_decompress_insertDictionary(ZSTD_DCtx* dctx, const void* dict, size_t dictSize)
+{
+    if (dictSize < 8) return ZSTD_refDictContent(dctx, dict, dictSize);
+    {   U32 const magic = MEM_readLE32(dict);
+        if (magic != ZSTD_MAGIC_DICTIONARY) {
+            return ZSTD_refDictContent(dctx, dict, dictSize);   /* pure content mode */
+    }   }
+    dctx->dictID = MEM_readLE32((const char*)dict + ZSTD_FRAMEIDSIZE);
+
+    /* load entropy tables */
+    {   size_t const eSize = ZSTD_loadDEntropy(&dctx->entropy, dict, dictSize);
+        RETURN_ERROR_IF(ZSTD_isError(eSize), dictionary_corrupted, "");
+        dict = (const char*)dict + eSize;
+        dictSize -= eSize;
+    }
+    dctx->litEntropy = dctx->fseEntropy = 1;
+
+    /* reference dictionary content */
+    return ZSTD_refDictContent(dctx, dict, dictSize);
+}
+
+size_t ZSTD_decompressBegin(ZSTD_DCtx* dctx)
+{
+    assert(dctx != NULL);
+    dctx->expected = ZSTD_startingInputLength(dctx->format);  /* dctx->format must be properly set */
+    dctx->stage = ZSTDds_getFrameHeaderSize;
+    dctx->processedCSize = 0;
+    dctx->decodedSize = 0;
+    dctx->previousDstEnd = NULL;
+    dctx->prefixStart = NULL;
+    dctx->virtualStart = NULL;
+    dctx->dictEnd = NULL;
+    dctx->entropy.hufTable[0] = (HUF_DTable)((HufLog)*0x1000001);  /* cover both little and big endian */
+    dctx->litEntropy = dctx->fseEntropy = 0;
+    dctx->dictID = 0;
+    dctx->bType = bt_reserved;
+    ZSTD_STATIC_ASSERT(sizeof(dctx->entropy.rep) == sizeof(repStartValue));
+    ZSTD_memcpy(dctx->entropy.rep, repStartValue, sizeof(repStartValue));  /* initial repcodes */
+    dctx->LLTptr = dctx->entropy.LLTable;
+    dctx->MLTptr = dctx->entropy.MLTable;
+    dctx->OFTptr = dctx->entropy.OFTable;
+    dctx->HUFptr = dctx->entropy.hufTable;
+    return 0;
+}
+
+size_t ZSTD_decompressBegin_usingDict(ZSTD_DCtx* dctx, const void* dict, size_t dictSize)
+{
+    FORWARD_IF_ERROR( ZSTD_decompressBegin(dctx) , "");
+    if (dict && dictSize)
+        RETURN_ERROR_IF(
+            ZSTD_isError(ZSTD_decompress_insertDictionary(dctx, dict, dictSize)),
+            dictionary_corrupted, "");
+    return 0;
+}
+
+
+/* ======   ZSTD_DDict   ====== */
+
+size_t ZSTD_decompressBegin_usingDDict(ZSTD_DCtx* dctx, const ZSTD_DDict* ddict)
+{
+    DEBUGLOG(4, "ZSTD_decompressBegin_usingDDict");
+    assert(dctx != NULL);
+    if (ddict) {
+        const char* const dictStart = (const char*)ZSTD_DDict_dictContent(ddict);
+        size_t const dictSize = ZSTD_DDict_dictSize(ddict);
+        const void* const dictEnd = dictStart + dictSize;
+        dctx->ddictIsCold = (dctx->dictEnd != dictEnd);
+        DEBUGLOG(4, "DDict is %s",
+                    dctx->ddictIsCold ? "~cold~" : "hot!");
+    }
+    FORWARD_IF_ERROR( ZSTD_decompressBegin(dctx) , "");
+    if (ddict) {   /* NULL ddict is equivalent to no dictionary */
+        ZSTD_copyDDictParameters(dctx, ddict);
+    }
+    return 0;
+}
+
+/*! ZSTD_getDictID_fromDict() :
+ *  Provides the dictID stored within dictionary.
+ *  if @return == 0, the dictionary is not conformant with Zstandard specification.
+ *  It can still be loaded, but as a content-only dictionary. */
+unsigned ZSTD_getDictID_fromDict(const void* dict, size_t dictSize)
+{
+    if (dictSize < 8) return 0;
+    if (MEM_readLE32(dict) != ZSTD_MAGIC_DICTIONARY) return 0;
+    return MEM_readLE32((const char*)dict + ZSTD_FRAMEIDSIZE);
+}
+
+/*! ZSTD_getDictID_fromFrame() :
+ *  Provides the dictID required to decompress frame stored within `src`.
+ *  If @return == 0, the dictID could not be decoded.
+ *  This could for one of the following reasons :
+ *  - The frame does not require a dictionary (most common case).
+ *  - The frame was built with dictID intentionally removed.
+ *    Needed dictionary is a hidden information.
+ *    Note : this use case also happens when using a non-conformant dictionary.
+ *  - `srcSize` is too small, and as a result, frame header could not be decoded.
+ *    Note : possible if `srcSize < ZSTD_FRAMEHEADERSIZE_MAX`.
+ *  - This is not a Zstandard frame.
+ *  When identifying the exact failure cause, it's possible to use
+ *  ZSTD_getFrameHeader(), which will provide a more precise error code. */
+unsigned ZSTD_getDictID_fromFrame(const void* src, size_t srcSize)
+{
+    ZSTD_frameHeader zfp = { 0, 0, 0, ZSTD_frame, 0, 0, 0 };
+    size_t const hError = ZSTD_getFrameHeader(&zfp, src, srcSize);
+    if (ZSTD_isError(hError)) return 0;
+    return zfp.dictID;
+}
+
+
+/*! ZSTD_decompress_usingDDict() :
+*   Decompression using a pre-digested Dictionary
+*   Use dictionary without significant overhead. */
+size_t ZSTD_decompress_usingDDict(ZSTD_DCtx* dctx,
+                                  void* dst, size_t dstCapacity,
+                            const void* src, size_t srcSize,
+                            const ZSTD_DDict* ddict)
+{
+    /* pass content and size in case legacy frames are encountered */
+    return ZSTD_decompressMultiFrame(dctx, dst, dstCapacity, src, srcSize,
+                                     NULL, 0,
+                                     ddict);
+}
+
+
+/*=====================================
+*   Streaming decompression
+*====================================*/
+
+ZSTD_DStream* ZSTD_createDStream(void)
+{
+    DEBUGLOG(3, "ZSTD_createDStream");
+    return ZSTD_createDStream_advanced(ZSTD_defaultCMem);
+}
+
+ZSTD_DStream* ZSTD_initStaticDStream(void *workspace, size_t workspaceSize)
+{
+    return ZSTD_initStaticDCtx(workspace, workspaceSize);
+}
+
+ZSTD_DStream* ZSTD_createDStream_advanced(ZSTD_customMem customMem)
+{
+    return ZSTD_createDCtx_advanced(customMem);
+}
+
+size_t ZSTD_freeDStream(ZSTD_DStream* zds)
+{
+    return ZSTD_freeDCtx(zds);
+}
+
+
+/* ***  Initialization  *** */
+
+size_t ZSTD_DStreamInSize(void)  { return ZSTD_BLOCKSIZE_MAX + ZSTD_blockHeaderSize; }
+size_t ZSTD_DStreamOutSize(void) { return ZSTD_BLOCKSIZE_MAX; }
+
+size_t ZSTD_DCtx_loadDictionary_advanced(ZSTD_DCtx* dctx,
+                                   const void* dict, size_t dictSize,
+                                         ZSTD_dictLoadMethod_e dictLoadMethod,
+                                         ZSTD_dictContentType_e dictContentType)
+{
+    RETURN_ERROR_IF(dctx->streamStage != zdss_init, stage_wrong, "");
+    ZSTD_clearDict(dctx);
+    if (dict && dictSize != 0) {
+        dctx->ddictLocal = ZSTD_createDDict_advanced(dict, dictSize, dictLoadMethod, dictContentType, dctx->customMem);
+        RETURN_ERROR_IF(dctx->ddictLocal == NULL, memory_allocation, "NULL pointer!");
+        dctx->ddict = dctx->ddictLocal;
+        dctx->dictUses = ZSTD_use_indefinitely;
+    }
+    return 0;
+}
+
+size_t ZSTD_DCtx_loadDictionary_byReference(ZSTD_DCtx* dctx, const void* dict, size_t dictSize)
+{
+    return ZSTD_DCtx_loadDictionary_advanced(dctx, dict, dictSize, ZSTD_dlm_byRef, ZSTD_dct_auto);
+}
+
+size_t ZSTD_DCtx_loadDictionary(ZSTD_DCtx* dctx, const void* dict, size_t dictSize)
+{
+    return ZSTD_DCtx_loadDictionary_advanced(dctx, dict, dictSize, ZSTD_dlm_byCopy, ZSTD_dct_auto);
+}
+
+size_t ZSTD_DCtx_refPrefix_advanced(ZSTD_DCtx* dctx, const void* prefix, size_t prefixSize, ZSTD_dictContentType_e dictContentType)
+{
+    FORWARD_IF_ERROR(ZSTD_DCtx_loadDictionary_advanced(dctx, prefix, prefixSize, ZSTD_dlm_byRef, dictContentType), "");
+    dctx->dictUses = ZSTD_use_once;
+    return 0;
+}
+
+size_t ZSTD_DCtx_refPrefix(ZSTD_DCtx* dctx, const void* prefix, size_t prefixSize)
+{
+    return ZSTD_DCtx_refPrefix_advanced(dctx, prefix, prefixSize, ZSTD_dct_rawContent);
+}
+
+
+/* ZSTD_initDStream_usingDict() :
+ * return : expected size, aka ZSTD_startingInputLength().
+ * this function cannot fail */
+size_t ZSTD_initDStream_usingDict(ZSTD_DStream* zds, const void* dict, size_t dictSize)
+{
+    DEBUGLOG(4, "ZSTD_initDStream_usingDict");
+    FORWARD_IF_ERROR( ZSTD_DCtx_reset(zds, ZSTD_reset_session_only) , "");
+    FORWARD_IF_ERROR( ZSTD_DCtx_loadDictionary(zds, dict, dictSize) , "");
+    return ZSTD_startingInputLength(zds->format);
+}
+
+/* note : this variant can't fail */
+size_t ZSTD_initDStream(ZSTD_DStream* zds)
+{
+    DEBUGLOG(4, "ZSTD_initDStream");
+    return ZSTD_initDStream_usingDDict(zds, NULL);
+}
+
+/* ZSTD_initDStream_usingDDict() :
+ * ddict will just be referenced, and must outlive decompression session
+ * this function cannot fail */
+size_t ZSTD_initDStream_usingDDict(ZSTD_DStream* dctx, const ZSTD_DDict* ddict)
+{
+    FORWARD_IF_ERROR( ZSTD_DCtx_reset(dctx, ZSTD_reset_session_only) , "");
+    FORWARD_IF_ERROR( ZSTD_DCtx_refDDict(dctx, ddict) , "");
+    return ZSTD_startingInputLength(dctx->format);
+}
+
+/* ZSTD_resetDStream() :
+ * return : expected size, aka ZSTD_startingInputLength().
+ * this function cannot fail */
+size_t ZSTD_resetDStream(ZSTD_DStream* dctx)
+{
+    FORWARD_IF_ERROR(ZSTD_DCtx_reset(dctx, ZSTD_reset_session_only), "");
+    return ZSTD_startingInputLength(dctx->format);
+}
+
+
+size_t ZSTD_DCtx_refDDict(ZSTD_DCtx* dctx, const ZSTD_DDict* ddict)
+{
+    RETURN_ERROR_IF(dctx->streamStage != zdss_init, stage_wrong, "");
+    ZSTD_clearDict(dctx);
+    if (ddict) {
+        dctx->ddict = ddict;
+        dctx->dictUses = ZSTD_use_indefinitely;
+        if (dctx->refMultipleDDicts == ZSTD_rmd_refMultipleDDicts) {
+            if (dctx->ddictSet == NULL) {
+                dctx->ddictSet = ZSTD_createDDictHashSet(dctx->customMem);
+                if (!dctx->ddictSet) {
+                    RETURN_ERROR(memory_allocation, "Failed to allocate memory for hash set!");
+                }
+            }
+            assert(!dctx->staticSize);  /* Impossible: ddictSet cannot have been allocated if static dctx */
+            FORWARD_IF_ERROR(ZSTD_DDictHashSet_addDDict(dctx->ddictSet, ddict, dctx->customMem), "");
+        }
+    }
+    return 0;
+}
+
+/* ZSTD_DCtx_setMaxWindowSize() :
+ * note : no direct equivalence in ZSTD_DCtx_setParameter,
+ * since this version sets windowSize, and the other sets windowLog */
+size_t ZSTD_DCtx_setMaxWindowSize(ZSTD_DCtx* dctx, size_t maxWindowSize)
+{
+    ZSTD_bounds const bounds = ZSTD_dParam_getBounds(ZSTD_d_windowLogMax);
+    size_t const min = (size_t)1 << bounds.lowerBound;
+    size_t const max = (size_t)1 << bounds.upperBound;
+    RETURN_ERROR_IF(dctx->streamStage != zdss_init, stage_wrong, "");
+    RETURN_ERROR_IF(maxWindowSize < min, parameter_outOfBound, "");
+    RETURN_ERROR_IF(maxWindowSize > max, parameter_outOfBound, "");
+    dctx->maxWindowSize = maxWindowSize;
+    return 0;
+}
+
+size_t ZSTD_DCtx_setFormat(ZSTD_DCtx* dctx, ZSTD_format_e format)
+{
+    return ZSTD_DCtx_setParameter(dctx, ZSTD_d_format, (int)format);
+}
+
+ZSTD_bounds ZSTD_dParam_getBounds(ZSTD_dParameter dParam)
+{
+    ZSTD_bounds bounds = { 0, 0, 0 };
+    switch(dParam) {
+        case ZSTD_d_windowLogMax:
+            bounds.lowerBound = ZSTD_WINDOWLOG_ABSOLUTEMIN;
+            bounds.upperBound = ZSTD_WINDOWLOG_MAX;
+            return bounds;
+        case ZSTD_d_format:
+            bounds.lowerBound = (int)ZSTD_f_zstd1;
+            bounds.upperBound = (int)ZSTD_f_zstd1_magicless;
+            ZSTD_STATIC_ASSERT(ZSTD_f_zstd1 < ZSTD_f_zstd1_magicless);
+            return bounds;
+        case ZSTD_d_stableOutBuffer:
+            bounds.lowerBound = (int)ZSTD_bm_buffered;
+            bounds.upperBound = (int)ZSTD_bm_stable;
+            return bounds;
+        case ZSTD_d_forceIgnoreChecksum:
+            bounds.lowerBound = (int)ZSTD_d_validateChecksum;
+            bounds.upperBound = (int)ZSTD_d_ignoreChecksum;
+            return bounds;
+        case ZSTD_d_refMultipleDDicts:
+            bounds.lowerBound = (int)ZSTD_rmd_refSingleDDict;
+            bounds.upperBound = (int)ZSTD_rmd_refMultipleDDicts;
+            return bounds;
+        default:;
+    }
+    bounds.error = ERROR(parameter_unsupported);
+    return bounds;
+}
+
+/* ZSTD_dParam_withinBounds:
+ * @return 1 if value is within dParam bounds,
+ * 0 otherwise */
+static int ZSTD_dParam_withinBounds(ZSTD_dParameter dParam, int value)
+{
+    ZSTD_bounds const bounds = ZSTD_dParam_getBounds(dParam);
+    if (ZSTD_isError(bounds.error)) return 0;
+    if (value < bounds.lowerBound) return 0;
+    if (value > bounds.upperBound) return 0;
+    return 1;
+}
+
+#define CHECK_DBOUNDS(p,v) {                \
+    RETURN_ERROR_IF(!ZSTD_dParam_withinBounds(p, v), parameter_outOfBound, ""); \
+}
+
+size_t ZSTD_DCtx_getParameter(ZSTD_DCtx* dctx, ZSTD_dParameter param, int* value)
+{
+    switch (param) {
+        case ZSTD_d_windowLogMax:
+            *value = (int)ZSTD_highbit32((U32)dctx->maxWindowSize);
+            return 0;
+        case ZSTD_d_format:
+            *value = (int)dctx->format;
+            return 0;
+        case ZSTD_d_stableOutBuffer:
+            *value = (int)dctx->outBufferMode;
+            return 0;
+        case ZSTD_d_forceIgnoreChecksum:
+            *value = (int)dctx->forceIgnoreChecksum;
+            return 0;
+        case ZSTD_d_refMultipleDDicts:
+            *value = (int)dctx->refMultipleDDicts;
+            return 0;
+        default:;
+    }
+    RETURN_ERROR(parameter_unsupported, "");
+}
+
+size_t ZSTD_DCtx_setParameter(ZSTD_DCtx* dctx, ZSTD_dParameter dParam, int value)
+{
+    RETURN_ERROR_IF(dctx->streamStage != zdss_init, stage_wrong, "");
+    switch(dParam) {
+        case ZSTD_d_windowLogMax:
+            if (value == 0) value = ZSTD_WINDOWLOG_LIMIT_DEFAULT;
+            CHECK_DBOUNDS(ZSTD_d_windowLogMax, value);
+            dctx->maxWindowSize = ((size_t)1) << value;
+            return 0;
+        case ZSTD_d_format:
+            CHECK_DBOUNDS(ZSTD_d_format, value);
+            dctx->format = (ZSTD_format_e)value;
+            return 0;
+        case ZSTD_d_stableOutBuffer:
+            CHECK_DBOUNDS(ZSTD_d_stableOutBuffer, value);
+            dctx->outBufferMode = (ZSTD_bufferMode_e)value;
+            return 0;
+        case ZSTD_d_forceIgnoreChecksum:
+            CHECK_DBOUNDS(ZSTD_d_forceIgnoreChecksum, value);
+            dctx->forceIgnoreChecksum = (ZSTD_forceIgnoreChecksum_e)value;
+            return 0;
+        case ZSTD_d_refMultipleDDicts:
+            CHECK_DBOUNDS(ZSTD_d_refMultipleDDicts, value);
+            if (dctx->staticSize != 0) {
+                RETURN_ERROR(parameter_unsupported, "Static dctx does not support multiple DDicts!");
+            }
+            dctx->refMultipleDDicts = (ZSTD_refMultipleDDicts_e)value;
+            return 0;
+        default:;
+    }
+    RETURN_ERROR(parameter_unsupported, "");
+}
+
+size_t ZSTD_DCtx_reset(ZSTD_DCtx* dctx, ZSTD_ResetDirective reset)
+{
+    if ( (reset == ZSTD_reset_session_only)
+      || (reset == ZSTD_reset_session_and_parameters) ) {
+        dctx->streamStage = zdss_init;
+        dctx->noForwardProgress = 0;
+    }
+    if ( (reset == ZSTD_reset_parameters)
+      || (reset == ZSTD_reset_session_and_parameters) ) {
+        RETURN_ERROR_IF(dctx->streamStage != zdss_init, stage_wrong, "");
+        ZSTD_clearDict(dctx);
+        ZSTD_DCtx_resetParameters(dctx);
+    }
+    return 0;
+}
+
+
+size_t ZSTD_sizeof_DStream(const ZSTD_DStream* dctx)
+{
+    return ZSTD_sizeof_DCtx(dctx);
+}
+
+size_t ZSTD_decodingBufferSize_min(unsigned long long windowSize, unsigned long long frameContentSize)
+{
+    size_t const blockSize = (size_t) MIN(windowSize, ZSTD_BLOCKSIZE_MAX);
+    unsigned long long const neededRBSize = windowSize + blockSize + (WILDCOPY_OVERLENGTH * 2);
+    unsigned long long const neededSize = MIN(frameContentSize, neededRBSize);
+    size_t const minRBSize = (size_t) neededSize;
+    RETURN_ERROR_IF((unsigned long long)minRBSize != neededSize,
+                    frameParameter_windowTooLarge, "");
+    return minRBSize;
+}
+
+size_t ZSTD_estimateDStreamSize(size_t windowSize)
+{
+    size_t const blockSize = MIN(windowSize, ZSTD_BLOCKSIZE_MAX);
+    size_t const inBuffSize = blockSize;  /* no block can be larger */
+    size_t const outBuffSize = ZSTD_decodingBufferSize_min(windowSize, ZSTD_CONTENTSIZE_UNKNOWN);
+    return ZSTD_estimateDCtxSize() + inBuffSize + outBuffSize;
+}
+
+size_t ZSTD_estimateDStreamSize_fromFrame(const void* src, size_t srcSize)
+{
+    U32 const windowSizeMax = 1U << ZSTD_WINDOWLOG_MAX;   /* note : should be user-selectable, but requires an additional parameter (or a dctx) */
+    ZSTD_frameHeader zfh;
+    size_t const err = ZSTD_getFrameHeader(&zfh, src, srcSize);
+    if (ZSTD_isError(err)) return err;
+    RETURN_ERROR_IF(err>0, srcSize_wrong, "");
+    RETURN_ERROR_IF(zfh.windowSize > windowSizeMax,
+                    frameParameter_windowTooLarge, "");
+    return ZSTD_estimateDStreamSize((size_t)zfh.windowSize);
+}
+
+
+/* *****   Decompression   ***** */
+
+static int ZSTD_DCtx_isOverflow(ZSTD_DStream* zds, size_t const neededInBuffSize, size_t const neededOutBuffSize)
+{
+    return (zds->inBuffSize + zds->outBuffSize) >= (neededInBuffSize + neededOutBuffSize) * ZSTD_WORKSPACETOOLARGE_FACTOR;
+}
+
+static void ZSTD_DCtx_updateOversizedDuration(ZSTD_DStream* zds, size_t const neededInBuffSize, size_t const neededOutBuffSize)
+{
+    if (ZSTD_DCtx_isOverflow(zds, neededInBuffSize, neededOutBuffSize))
+        zds->oversizedDuration++;
+    else
+        zds->oversizedDuration = 0;
+}
+
+static int ZSTD_DCtx_isOversizedTooLong(ZSTD_DStream* zds)
+{
+    return zds->oversizedDuration >= ZSTD_WORKSPACETOOLARGE_MAXDURATION;
+}
+
+/* Checks that the output buffer hasn't changed if ZSTD_obm_stable is used. */
+static size_t ZSTD_checkOutBuffer(ZSTD_DStream const* zds, ZSTD_outBuffer const* output)
+{
+    ZSTD_outBuffer const expect = zds->expectedOutBuffer;
+    /* No requirement when ZSTD_obm_stable is not enabled. */
+    if (zds->outBufferMode != ZSTD_bm_stable)
+        return 0;
+    /* Any buffer is allowed in zdss_init, this must be the same for every other call until
+     * the context is reset.
+     */
+    if (zds->streamStage == zdss_init)
+        return 0;
+    /* The buffer must match our expectation exactly. */
+    if (expect.dst == output->dst && expect.pos == output->pos && expect.size == output->size)
+        return 0;
+    RETURN_ERROR(dstBuffer_wrong, "ZSTD_d_stableOutBuffer enabled but output differs!");
+}
+
+/* Calls ZSTD_decompressContinue() with the right parameters for ZSTD_decompressStream()
+ * and updates the stage and the output buffer state. This call is extracted so it can be
+ * used both when reading directly from the ZSTD_inBuffer, and in buffered input mode.
+ * NOTE: You must break after calling this function since the streamStage is modified.
+ */
+static size_t ZSTD_decompressContinueStream(
+            ZSTD_DStream* zds, char** op, char* oend,
+            void const* src, size_t srcSize) {
+    int const isSkipFrame = ZSTD_isSkipFrame(zds);
+    if (zds->outBufferMode == ZSTD_bm_buffered) {
+        size_t const dstSize = isSkipFrame ? 0 : zds->outBuffSize - zds->outStart;
+        size_t const decodedSize = ZSTD_decompressContinue(zds,
+                zds->outBuff + zds->outStart, dstSize, src, srcSize);
+        FORWARD_IF_ERROR(decodedSize, "");
+        if (!decodedSize && !isSkipFrame) {
+            zds->streamStage = zdss_read;
+        } else {
+            zds->outEnd = zds->outStart + decodedSize;
+            zds->streamStage = zdss_flush;
+        }
+    } else {
+        /* Write directly into the output buffer */
+        size_t const dstSize = isSkipFrame ? 0 : (size_t)(oend - *op);
+        size_t const decodedSize = ZSTD_decompressContinue(zds, *op, dstSize, src, srcSize);
+        FORWARD_IF_ERROR(decodedSize, "");
+        *op += decodedSize;
+        /* Flushing is not needed. */
+        zds->streamStage = zdss_read;
+        assert(*op <= oend);
+        assert(zds->outBufferMode == ZSTD_bm_stable);
+    }
+    return 0;
+}
+
+size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inBuffer* input)
+{
+    const char* const src = (const char*)input->src;
+    const char* const istart = input->pos != 0 ? src + input->pos : src;
+    const char* const iend = input->size != 0 ? src + input->size : src;
+    const char* ip = istart;
+    char* const dst = (char*)output->dst;
+    char* const ostart = output->pos != 0 ? dst + output->pos : dst;
+    char* const oend = output->size != 0 ? dst + output->size : dst;
+    char* op = ostart;
+    U32 someMoreWork = 1;
+
+    DEBUGLOG(5, "ZSTD_decompressStream");
+    RETURN_ERROR_IF(
+        input->pos > input->size,
+        srcSize_wrong,
+        "forbidden. in: pos: %u   vs size: %u",
+        (U32)input->pos, (U32)input->size);
+    RETURN_ERROR_IF(
+        output->pos > output->size,
+        dstSize_tooSmall,
+        "forbidden. out: pos: %u   vs size: %u",
+        (U32)output->pos, (U32)output->size);
+    DEBUGLOG(5, "input size : %u", (U32)(input->size - input->pos));
+    FORWARD_IF_ERROR(ZSTD_checkOutBuffer(zds, output), "");
+
+    while (someMoreWork) {
+        switch(zds->streamStage)
+        {
+        case zdss_init :
+            DEBUGLOG(5, "stage zdss_init => transparent reset ");
+            zds->streamStage = zdss_loadHeader;
+            zds->lhSize = zds->inPos = zds->outStart = zds->outEnd = 0;
+            zds->legacyVersion = 0;
+            zds->hostageByte = 0;
+            zds->expectedOutBuffer = *output;
+            ZSTD_FALLTHROUGH;
+
+        case zdss_loadHeader :
+            DEBUGLOG(5, "stage zdss_loadHeader (srcSize : %u)", (U32)(iend - ip));
+            {   size_t const hSize = ZSTD_getFrameHeader_advanced(&zds->fParams, zds->headerBuffer, zds->lhSize, zds->format);
+                if (zds->refMultipleDDicts && zds->ddictSet) {
+                    ZSTD_DCtx_selectFrameDDict(zds);
+                }
+                DEBUGLOG(5, "header size : %u", (U32)hSize);
+                if (ZSTD_isError(hSize)) {
+                    return hSize;   /* error */
+                }
+                if (hSize != 0) {   /* need more input */
+                    size_t const toLoad = hSize - zds->lhSize;   /* if hSize!=0, hSize > zds->lhSize */
+                    size_t const remainingInput = (size_t)(iend-ip);
+                    assert(iend >= ip);
+                    if (toLoad > remainingInput) {   /* not enough input to load full header */
+                        if (remainingInput > 0) {
+                            ZSTD_memcpy(zds->headerBuffer + zds->lhSize, ip, remainingInput);
+                            zds->lhSize += remainingInput;
+                        }
+                        input->pos = input->size;
+                        return (MAX((size_t)ZSTD_FRAMEHEADERSIZE_MIN(zds->format), hSize) - zds->lhSize) + ZSTD_blockHeaderSize;   /* remaining header bytes + next block header */
+                    }
+                    assert(ip != NULL);
+                    ZSTD_memcpy(zds->headerBuffer + zds->lhSize, ip, toLoad); zds->lhSize = hSize; ip += toLoad;
+                    break;
+            }   }
+
+            /* check for single-pass mode opportunity */
+            if (zds->fParams.frameContentSize != ZSTD_CONTENTSIZE_UNKNOWN
+                && zds->fParams.frameType != ZSTD_skippableFrame
+                && (U64)(size_t)(oend-op) >= zds->fParams.frameContentSize) {
+                size_t const cSize = ZSTD_findFrameCompressedSize(istart, (size_t)(iend-istart));
+                if (cSize <= (size_t)(iend-istart)) {
+                    /* shortcut : using single-pass mode */
+                    size_t const decompressedSize = ZSTD_decompress_usingDDict(zds, op, (size_t)(oend-op), istart, cSize, ZSTD_getDDict(zds));
+                    if (ZSTD_isError(decompressedSize)) return decompressedSize;
+                    DEBUGLOG(4, "shortcut to single-pass ZSTD_decompress_usingDDict()")
+                    ip = istart + cSize;
+                    op += decompressedSize;
+                    zds->expected = 0;
+                    zds->streamStage = zdss_init;
+                    someMoreWork = 0;
+                    break;
+            }   }
+
+            /* Check output buffer is large enough for ZSTD_odm_stable. */
+            if (zds->outBufferMode == ZSTD_bm_stable
+                && zds->fParams.frameType != ZSTD_skippableFrame
+                && zds->fParams.frameContentSize != ZSTD_CONTENTSIZE_UNKNOWN
+                && (U64)(size_t)(oend-op) < zds->fParams.frameContentSize) {
+                RETURN_ERROR(dstSize_tooSmall, "ZSTD_obm_stable passed but ZSTD_outBuffer is too small");
+            }
+
+            /* Consume header (see ZSTDds_decodeFrameHeader) */
+            DEBUGLOG(4, "Consume header");
+            FORWARD_IF_ERROR(ZSTD_decompressBegin_usingDDict(zds, ZSTD_getDDict(zds)), "");
+
+            if ((MEM_readLE32(zds->headerBuffer) & ZSTD_MAGIC_SKIPPABLE_MASK) == ZSTD_MAGIC_SKIPPABLE_START) {  /* skippable frame */
+                zds->expected = MEM_readLE32(zds->headerBuffer + ZSTD_FRAMEIDSIZE);
+                zds->stage = ZSTDds_skipFrame;
+            } else {
+                FORWARD_IF_ERROR(ZSTD_decodeFrameHeader(zds, zds->headerBuffer, zds->lhSize), "");
+                zds->expected = ZSTD_blockHeaderSize;
+                zds->stage = ZSTDds_decodeBlockHeader;
+            }
+
+            /* control buffer memory usage */
+            DEBUGLOG(4, "Control max memory usage (%u KB <= max %u KB)",
+                        (U32)(zds->fParams.windowSize >>10),
+                        (U32)(zds->maxWindowSize >> 10) );
+            zds->fParams.windowSize = MAX(zds->fParams.windowSize, 1U << ZSTD_WINDOWLOG_ABSOLUTEMIN);
+            RETURN_ERROR_IF(zds->fParams.windowSize > zds->maxWindowSize,
+                            frameParameter_windowTooLarge, "");
+
+            /* Adapt buffer sizes to frame header instructions */
+            {   size_t const neededInBuffSize = MAX(zds->fParams.blockSizeMax, 4 /* frame checksum */);
+                size_t const neededOutBuffSize = zds->outBufferMode == ZSTD_bm_buffered
+                        ? ZSTD_decodingBufferSize_min(zds->fParams.windowSize, zds->fParams.frameContentSize)
+                        : 0;
+
+                ZSTD_DCtx_updateOversizedDuration(zds, neededInBuffSize, neededOutBuffSize);
+
+                {   int const tooSmall = (zds->inBuffSize < neededInBuffSize) || (zds->outBuffSize < neededOutBuffSize);
+                    int const tooLarge = ZSTD_DCtx_isOversizedTooLong(zds);
+
+                    if (tooSmall || tooLarge) {
+                        size_t const bufferSize = neededInBuffSize + neededOutBuffSize;
+                        DEBUGLOG(4, "inBuff  : from %u to %u",
+                                    (U32)zds->inBuffSize, (U32)neededInBuffSize);
+                        DEBUGLOG(4, "outBuff : from %u to %u",
+                                    (U32)zds->outBuffSize, (U32)neededOutBuffSize);
+                        if (zds->staticSize) {  /* static DCtx */
+                            DEBUGLOG(4, "staticSize : %u", (U32)zds->staticSize);
+                            assert(zds->staticSize >= sizeof(ZSTD_DCtx));  /* controlled at init */
+                            RETURN_ERROR_IF(
+                                bufferSize > zds->staticSize - sizeof(ZSTD_DCtx),
+                                memory_allocation, "");
+                        } else {
+                            ZSTD_customFree(zds->inBuff, zds->customMem);
+                            zds->inBuffSize = 0;
+                            zds->outBuffSize = 0;
+                            zds->inBuff = (char*)ZSTD_customMalloc(bufferSize, zds->customMem);
+                            RETURN_ERROR_IF(zds->inBuff == NULL, memory_allocation, "");
+                        }
+                        zds->inBuffSize = neededInBuffSize;
+                        zds->outBuff = zds->inBuff + zds->inBuffSize;
+                        zds->outBuffSize = neededOutBuffSize;
+            }   }   }
+            zds->streamStage = zdss_read;
+            ZSTD_FALLTHROUGH;
+
+        case zdss_read:
+            DEBUGLOG(5, "stage zdss_read");
+            {   size_t const neededInSize = ZSTD_nextSrcSizeToDecompressWithInputSize(zds, (size_t)(iend - ip));
+                DEBUGLOG(5, "neededInSize = %u", (U32)neededInSize);
+                if (neededInSize==0) {  /* end of frame */
+                    zds->streamStage = zdss_init;
+                    someMoreWork = 0;
+                    break;
+                }
+                if ((size_t)(iend-ip) >= neededInSize) {  /* decode directly from src */
+                    FORWARD_IF_ERROR(ZSTD_decompressContinueStream(zds, &op, oend, ip, neededInSize), "");
+                    ip += neededInSize;
+                    /* Function modifies the stage so we must break */
+                    break;
+            }   }
+            if (ip==iend) { someMoreWork = 0; break; }   /* no more input */
+            zds->streamStage = zdss_load;
+            ZSTD_FALLTHROUGH;
+
+        case zdss_load:
+            {   size_t const neededInSize = ZSTD_nextSrcSizeToDecompress(zds);
+                size_t const toLoad = neededInSize - zds->inPos;
+                int const isSkipFrame = ZSTD_isSkipFrame(zds);
+                size_t loadedSize;
+                /* At this point we shouldn't be decompressing a block that we can stream. */
+                assert(neededInSize == ZSTD_nextSrcSizeToDecompressWithInputSize(zds, iend - ip));
+                if (isSkipFrame) {
+                    loadedSize = MIN(toLoad, (size_t)(iend-ip));
+                } else {
+                    RETURN_ERROR_IF(toLoad > zds->inBuffSize - zds->inPos,
+                                    corruption_detected,
+                                    "should never happen");
+                    loadedSize = ZSTD_limitCopy(zds->inBuff + zds->inPos, toLoad, ip, (size_t)(iend-ip));
+                }
+                ip += loadedSize;
+                zds->inPos += loadedSize;
+                if (loadedSize < toLoad) { someMoreWork = 0; break; }   /* not enough input, wait for more */
+
+                /* decode loaded input */
+                zds->inPos = 0;   /* input is consumed */
+                FORWARD_IF_ERROR(ZSTD_decompressContinueStream(zds, &op, oend, zds->inBuff, neededInSize), "");
+                /* Function modifies the stage so we must break */
+                break;
+            }
+        case zdss_flush:
+            {   size_t const toFlushSize = zds->outEnd - zds->outStart;
+                size_t const flushedSize = ZSTD_limitCopy(op, (size_t)(oend-op), zds->outBuff + zds->outStart, toFlushSize);
+                op += flushedSize;
+                zds->outStart += flushedSize;
+                if (flushedSize == toFlushSize) {  /* flush completed */
+                    zds->streamStage = zdss_read;
+                    if ( (zds->outBuffSize < zds->fParams.frameContentSize)
+                      && (zds->outStart + zds->fParams.blockSizeMax > zds->outBuffSize) ) {
+                        DEBUGLOG(5, "restart filling outBuff from beginning (left:%i, needed:%u)",
+                                (int)(zds->outBuffSize - zds->outStart),
+                                (U32)zds->fParams.blockSizeMax);
+                        zds->outStart = zds->outEnd = 0;
+                    }
+                    break;
+            }   }
+            /* cannot complete flush */
+            someMoreWork = 0;
+            break;
+
+        default:
+            assert(0);    /* impossible */
+            RETURN_ERROR(GENERIC, "impossible to reach");   /* some compiler require default to do something */
+    }   }
+
+    /* result */
+    input->pos = (size_t)(ip - (const char*)(input->src));
+    output->pos = (size_t)(op - (char*)(output->dst));
+
+    /* Update the expected output buffer for ZSTD_obm_stable. */
+    zds->expectedOutBuffer = *output;
+
+    if ((ip==istart) && (op==ostart)) {  /* no forward progress */
+        zds->noForwardProgress ++;
+        if (zds->noForwardProgress >= ZSTD_NO_FORWARD_PROGRESS_MAX) {
+            RETURN_ERROR_IF(op==oend, dstSize_tooSmall, "");
+            RETURN_ERROR_IF(ip==iend, srcSize_wrong, "");
+            assert(0);
+        }
+    } else {
+        zds->noForwardProgress = 0;
+    }
+    {   size_t nextSrcSizeHint = ZSTD_nextSrcSizeToDecompress(zds);
+        if (!nextSrcSizeHint) {   /* frame fully decoded */
+            if (zds->outEnd == zds->outStart) {  /* output fully flushed */
+                if (zds->hostageByte) {
+                    if (input->pos >= input->size) {
+                        /* can't release hostage (not present) */
+                        zds->streamStage = zdss_read;
+                        return 1;
+                    }
+                    input->pos++;  /* release hostage */
+                }   /* zds->hostageByte */
+                return 0;
+            }  /* zds->outEnd == zds->outStart */
+            if (!zds->hostageByte) { /* output not fully flushed; keep last byte as hostage; will be released when all output is flushed */
+                input->pos--;   /* note : pos > 0, otherwise, impossible to finish reading last block */
+                zds->hostageByte=1;
+            }
+            return 1;
+        }  /* nextSrcSizeHint==0 */
+        nextSrcSizeHint += ZSTD_blockHeaderSize * (ZSTD_nextInputType(zds) == ZSTDnit_block);   /* preload header of next block */
+        assert(zds->inPos <= nextSrcSizeHint);
+        nextSrcSizeHint -= zds->inPos;   /* part already loaded*/
+        return nextSrcSizeHint;
+    }
+}
+
+size_t ZSTD_decompressStream_simpleArgs (
+                            ZSTD_DCtx* dctx,
+                            void* dst, size_t dstCapacity, size_t* dstPos,
+                      const void* src, size_t srcSize, size_t* srcPos)
+{
+    ZSTD_outBuffer output = { dst, dstCapacity, *dstPos };
+    ZSTD_inBuffer  input  = { src, srcSize, *srcPos };
+    /* ZSTD_compress_generic() will check validity of dstPos and srcPos */
+    size_t const cErr = ZSTD_decompressStream(dctx, &output, &input);
+    *dstPos = output.pos;
+    *srcPos = input.pos;
+    return cErr;
+}
diff --git a/lib/zstd/decompress/zstd_decompress_block.c b/lib/zstd/decompress/zstd_decompress_block.c
new file mode 100644
index 000000000000..2d101d9a842e
--- /dev/null
+++ b/lib/zstd/decompress/zstd_decompress_block.c
@@ -0,0 +1,1540 @@
+/*
+ * Copyright (c) Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+/* zstd_decompress_block :
+ * this module takes care of decompressing _compressed_ block */
+
+/*-*******************************************************
+*  Dependencies
+*********************************************************/
+#include "../common/zstd_deps.h"   /* ZSTD_memcpy, ZSTD_memmove, ZSTD_memset */
+#include "../common/compiler.h"    /* prefetch */
+#include "../common/cpu.h"         /* bmi2 */
+#include "../common/mem.h"         /* low level memory routines */
+#define FSE_STATIC_LINKING_ONLY
+#include "../common/fse.h"
+#define HUF_STATIC_LINKING_ONLY
+#include "../common/huf.h"
+#include "../common/zstd_internal.h"
+#include "zstd_decompress_internal.h"   /* ZSTD_DCtx */
+#include "zstd_ddict.h"  /* ZSTD_DDictDictContent */
+#include "zstd_decompress_block.h"
+
+/*_*******************************************************
+*  Macros
+**********************************************************/
+
+/* These two optional macros force the use one way or another of the two
+ * ZSTD_decompressSequences implementations. You can't force in both directions
+ * at the same time.
+ */
+#if defined(ZSTD_FORCE_DECOMPRESS_SEQUENCES_SHORT) && \
+    defined(ZSTD_FORCE_DECOMPRESS_SEQUENCES_LONG)
+#error "Cannot force the use of the short and the long ZSTD_decompressSequences variants!"
+#endif
+
+
+/*_*******************************************************
+*  Memory operations
+**********************************************************/
+static void ZSTD_copy4(void* dst, const void* src) { ZSTD_memcpy(dst, src, 4); }
+
+
+/*-*************************************************************
+ *   Block decoding
+ ***************************************************************/
+
+/*! ZSTD_getcBlockSize() :
+ *  Provides the size of compressed block from block header `src` */
+size_t ZSTD_getcBlockSize(const void* src, size_t srcSize,
+                          blockProperties_t* bpPtr)
+{
+    RETURN_ERROR_IF(srcSize < ZSTD_blockHeaderSize, srcSize_wrong, "");
+
+    {   U32 const cBlockHeader = MEM_readLE24(src);
+        U32 const cSize = cBlockHeader >> 3;
+        bpPtr->lastBlock = cBlockHeader & 1;
+        bpPtr->blockType = (blockType_e)((cBlockHeader >> 1) & 3);
+        bpPtr->origSize = cSize;   /* only useful for RLE */
+        if (bpPtr->blockType == bt_rle) return 1;
+        RETURN_ERROR_IF(bpPtr->blockType == bt_reserved, corruption_detected, "");
+        return cSize;
+    }
+}
+
+
+/* Hidden declaration for fullbench */
+size_t ZSTD_decodeLiteralsBlock(ZSTD_DCtx* dctx,
+                          const void* src, size_t srcSize);
+/*! ZSTD_decodeLiteralsBlock() :
+ * @return : nb of bytes read from src (< srcSize )
+ *  note : symbol not declared but exposed for fullbench */
+size_t ZSTD_decodeLiteralsBlock(ZSTD_DCtx* dctx,
+                          const void* src, size_t srcSize)   /* note : srcSize < BLOCKSIZE */
+{
+    DEBUGLOG(5, "ZSTD_decodeLiteralsBlock");
+    RETURN_ERROR_IF(srcSize < MIN_CBLOCK_SIZE, corruption_detected, "");
+
+    {   const BYTE* const istart = (const BYTE*) src;
+        symbolEncodingType_e const litEncType = (symbolEncodingType_e)(istart[0] & 3);
+
+        switch(litEncType)
+        {
+        case set_repeat:
+            DEBUGLOG(5, "set_repeat flag : re-using stats from previous compressed literals block");
+            RETURN_ERROR_IF(dctx->litEntropy==0, dictionary_corrupted, "");
+            ZSTD_FALLTHROUGH;
+
+        case set_compressed:
+            RETURN_ERROR_IF(srcSize < 5, corruption_detected, "srcSize >= MIN_CBLOCK_SIZE == 3; here we need up to 5 for case 3");
+            {   size_t lhSize, litSize, litCSize;
+                U32 singleStream=0;
+                U32 const lhlCode = (istart[0] >> 2) & 3;
+                U32 const lhc = MEM_readLE32(istart);
+                size_t hufSuccess;
+                switch(lhlCode)
+                {
+                case 0: case 1: default:   /* note : default is impossible, since lhlCode into [0..3] */
+                    /* 2 - 2 - 10 - 10 */
+                    singleStream = !lhlCode;
+                    lhSize = 3;
+                    litSize  = (lhc >> 4) & 0x3FF;
+                    litCSize = (lhc >> 14) & 0x3FF;
+                    break;
+                case 2:
+                    /* 2 - 2 - 14 - 14 */
+                    lhSize = 4;
+                    litSize  = (lhc >> 4) & 0x3FFF;
+                    litCSize = lhc >> 18;
+                    break;
+                case 3:
+                    /* 2 - 2 - 18 - 18 */
+                    lhSize = 5;
+                    litSize  = (lhc >> 4) & 0x3FFFF;
+                    litCSize = (lhc >> 22) + ((size_t)istart[4] << 10);
+                    break;
+                }
+                RETURN_ERROR_IF(litSize > ZSTD_BLOCKSIZE_MAX, corruption_detected, "");
+                RETURN_ERROR_IF(litCSize + lhSize > srcSize, corruption_detected, "");
+
+                /* prefetch huffman table if cold */
+                if (dctx->ddictIsCold && (litSize > 768 /* heuristic */)) {
+                    PREFETCH_AREA(dctx->HUFptr, sizeof(dctx->entropy.hufTable));
+                }
+
+                if (litEncType==set_repeat) {
+                    if (singleStream) {
+                        hufSuccess = HUF_decompress1X_usingDTable_bmi2(
+                            dctx->litBuffer, litSize, istart+lhSize, litCSize,
+                            dctx->HUFptr, dctx->bmi2);
+                    } else {
+                        hufSuccess = HUF_decompress4X_usingDTable_bmi2(
+                            dctx->litBuffer, litSize, istart+lhSize, litCSize,
+                            dctx->HUFptr, dctx->bmi2);
+                    }
+                } else {
+                    if (singleStream) {
+#if defined(HUF_FORCE_DECOMPRESS_X2)
+                        hufSuccess = HUF_decompress1X_DCtx_wksp(
+                            dctx->entropy.hufTable, dctx->litBuffer, litSize,
+                            istart+lhSize, litCSize, dctx->workspace,
+                            sizeof(dctx->workspace));
+#else
+                        hufSuccess = HUF_decompress1X1_DCtx_wksp_bmi2(
+                            dctx->entropy.hufTable, dctx->litBuffer, litSize,
+                            istart+lhSize, litCSize, dctx->workspace,
+                            sizeof(dctx->workspace), dctx->bmi2);
+#endif
+                    } else {
+                        hufSuccess = HUF_decompress4X_hufOnly_wksp_bmi2(
+                            dctx->entropy.hufTable, dctx->litBuffer, litSize,
+                            istart+lhSize, litCSize, dctx->workspace,
+                            sizeof(dctx->workspace), dctx->bmi2);
+                    }
+                }
+
+                RETURN_ERROR_IF(HUF_isError(hufSuccess), corruption_detected, "");
+
+                dctx->litPtr = dctx->litBuffer;
+                dctx->litSize = litSize;
+                dctx->litEntropy = 1;
+                if (litEncType==set_compressed) dctx->HUFptr = dctx->entropy.hufTable;
+                ZSTD_memset(dctx->litBuffer + dctx->litSize, 0, WILDCOPY_OVERLENGTH);
+                return litCSize + lhSize;
+            }
+
+        case set_basic:
+            {   size_t litSize, lhSize;
+                U32 const lhlCode = ((istart[0]) >> 2) & 3;
+                switch(lhlCode)
+                {
+                case 0: case 2: default:   /* note : default is impossible, since lhlCode into [0..3] */
+                    lhSize = 1;
+                    litSize = istart[0] >> 3;
+                    break;
+                case 1:
+                    lhSize = 2;
+                    litSize = MEM_readLE16(istart) >> 4;
+                    break;
+                case 3:
+                    lhSize = 3;
+                    litSize = MEM_readLE24(istart) >> 4;
+                    break;
+                }
+
+                if (lhSize+litSize+WILDCOPY_OVERLENGTH > srcSize) {  /* risk reading beyond src buffer with wildcopy */
+                    RETURN_ERROR_IF(litSize+lhSize > srcSize, corruption_detected, "");
+                    ZSTD_memcpy(dctx->litBuffer, istart+lhSize, litSize);
+                    dctx->litPtr = dctx->litBuffer;
+                    dctx->litSize = litSize;
+                    ZSTD_memset(dctx->litBuffer + dctx->litSize, 0, WILDCOPY_OVERLENGTH);
+                    return lhSize+litSize;
+                }
+                /* direct reference into compressed stream */
+                dctx->litPtr = istart+lhSize;
+                dctx->litSize = litSize;
+                return lhSize+litSize;
+            }
+
+        case set_rle:
+            {   U32 const lhlCode = ((istart[0]) >> 2) & 3;
+                size_t litSize, lhSize;
+                switch(lhlCode)
+                {
+                case 0: case 2: default:   /* note : default is impossible, since lhlCode into [0..3] */
+                    lhSize = 1;
+                    litSize = istart[0] >> 3;
+                    break;
+                case 1:
+                    lhSize = 2;
+                    litSize = MEM_readLE16(istart) >> 4;
+                    break;
+                case 3:
+                    lhSize = 3;
+                    litSize = MEM_readLE24(istart) >> 4;
+                    RETURN_ERROR_IF(srcSize<4, corruption_detected, "srcSize >= MIN_CBLOCK_SIZE == 3; here we need lhSize+1 = 4");
+                    break;
+                }
+                RETURN_ERROR_IF(litSize > ZSTD_BLOCKSIZE_MAX, corruption_detected, "");
+                ZSTD_memset(dctx->litBuffer, istart[lhSize], litSize + WILDCOPY_OVERLENGTH);
+                dctx->litPtr = dctx->litBuffer;
+                dctx->litSize = litSize;
+                return lhSize+1;
+            }
+        default:
+            RETURN_ERROR(corruption_detected, "impossible");
+        }
+    }
+}
+
+/* Default FSE distribution tables.
+ * These are pre-calculated FSE decoding tables using default distributions as defined in specification :
+ * https://github.com/facebook/zstd/blob/release/doc/zstd_compression_format.md#default-distributions
+ * They were generated programmatically with following method :
+ * - start from default distributions, present in /lib/common/zstd_internal.h
+ * - generate tables normally, using ZSTD_buildFSETable()
+ * - printout the content of tables
+ * - pretify output, report below, test with fuzzer to ensure it's correct */
+
+/* Default FSE distribution table for Literal Lengths */
+static const ZSTD_seqSymbol LL_defaultDTable[(1<<LL_DEFAULTNORMLOG)+1] = {
+     {  1,  1,  1, LL_DEFAULTNORMLOG},  /* header : fastMode, tableLog */
+     /* nextState, nbAddBits, nbBits, baseVal */
+     {  0,  0,  4,    0},  { 16,  0,  4,    0},
+     { 32,  0,  5,    1},  {  0,  0,  5,    3},
+     {  0,  0,  5,    4},  {  0,  0,  5,    6},
+     {  0,  0,  5,    7},  {  0,  0,  5,    9},
+     {  0,  0,  5,   10},  {  0,  0,  5,   12},
+     {  0,  0,  6,   14},  {  0,  1,  5,   16},
+     {  0,  1,  5,   20},  {  0,  1,  5,   22},
+     {  0,  2,  5,   28},  {  0,  3,  5,   32},
+     {  0,  4,  5,   48},  { 32,  6,  5,   64},
+     {  0,  7,  5,  128},  {  0,  8,  6,  256},
+     {  0, 10,  6, 1024},  {  0, 12,  6, 4096},
+     { 32,  0,  4,    0},  {  0,  0,  4,    1},
+     {  0,  0,  5,    2},  { 32,  0,  5,    4},
+     {  0,  0,  5,    5},  { 32,  0,  5,    7},
+     {  0,  0,  5,    8},  { 32,  0,  5,   10},
+     {  0,  0,  5,   11},  {  0,  0,  6,   13},
+     { 32,  1,  5,   16},  {  0,  1,  5,   18},
+     { 32,  1,  5,   22},  {  0,  2,  5,   24},
+     { 32,  3,  5,   32},  {  0,  3,  5,   40},
+     {  0,  6,  4,   64},  { 16,  6,  4,   64},
+     { 32,  7,  5,  128},  {  0,  9,  6,  512},
+     {  0, 11,  6, 2048},  { 48,  0,  4,    0},
+     { 16,  0,  4,    1},  { 32,  0,  5,    2},
+     { 32,  0,  5,    3},  { 32,  0,  5,    5},
+     { 32,  0,  5,    6},  { 32,  0,  5,    8},
+     { 32,  0,  5,    9},  { 32,  0,  5,   11},
+     { 32,  0,  5,   12},  {  0,  0,  6,   15},
+     { 32,  1,  5,   18},  { 32,  1,  5,   20},
+     { 32,  2,  5,   24},  { 32,  2,  5,   28},
+     { 32,  3,  5,   40},  { 32,  4,  5,   48},
+     {  0, 16,  6,65536},  {  0, 15,  6,32768},
+     {  0, 14,  6,16384},  {  0, 13,  6, 8192},
+};   /* LL_defaultDTable */
+
+/* Default FSE distribution table for Offset Codes */
+static const ZSTD_seqSymbol OF_defaultDTable[(1<<OF_DEFAULTNORMLOG)+1] = {
+    {  1,  1,  1, OF_DEFAULTNORMLOG},  /* header : fastMode, tableLog */
+    /* nextState, nbAddBits, nbBits, baseVal */
+    {  0,  0,  5,    0},     {  0,  6,  4,   61},
+    {  0,  9,  5,  509},     {  0, 15,  5,32765},
+    {  0, 21,  5,2097149},   {  0,  3,  5,    5},
+    {  0,  7,  4,  125},     {  0, 12,  5, 4093},
+    {  0, 18,  5,262141},    {  0, 23,  5,8388605},
+    {  0,  5,  5,   29},     {  0,  8,  4,  253},
+    {  0, 14,  5,16381},     {  0, 20,  5,1048573},
+    {  0,  2,  5,    1},     { 16,  7,  4,  125},
+    {  0, 11,  5, 2045},     {  0, 17,  5,131069},
+    {  0, 22,  5,4194301},   {  0,  4,  5,   13},
+    { 16,  8,  4,  253},     {  0, 13,  5, 8189},
+    {  0, 19,  5,524285},    {  0,  1,  5,    1},
+    { 16,  6,  4,   61},     {  0, 10,  5, 1021},
+    {  0, 16,  5,65533},     {  0, 28,  5,268435453},
+    {  0, 27,  5,134217725}, {  0, 26,  5,67108861},
+    {  0, 25,  5,33554429},  {  0, 24,  5,16777213},
+};   /* OF_defaultDTable */
+
+
+/* Default FSE distribution table for Match Lengths */
+static const ZSTD_seqSymbol ML_defaultDTable[(1<<ML_DEFAULTNORMLOG)+1] = {
+    {  1,  1,  1, ML_DEFAULTNORMLOG},  /* header : fastMode, tableLog */
+    /* nextState, nbAddBits, nbBits, baseVal */
+    {  0,  0,  6,    3},  {  0,  0,  4,    4},
+    { 32,  0,  5,    5},  {  0,  0,  5,    6},
+    {  0,  0,  5,    8},  {  0,  0,  5,    9},
+    {  0,  0,  5,   11},  {  0,  0,  6,   13},
+    {  0,  0,  6,   16},  {  0,  0,  6,   19},
+    {  0,  0,  6,   22},  {  0,  0,  6,   25},
+    {  0,  0,  6,   28},  {  0,  0,  6,   31},
+    {  0,  0,  6,   34},  {  0,  1,  6,   37},
+    {  0,  1,  6,   41},  {  0,  2,  6,   47},
+    {  0,  3,  6,   59},  {  0,  4,  6,   83},
+    {  0,  7,  6,  131},  {  0,  9,  6,  515},
+    { 16,  0,  4,    4},  {  0,  0,  4,    5},
+    { 32,  0,  5,    6},  {  0,  0,  5,    7},
+    { 32,  0,  5,    9},  {  0,  0,  5,   10},
+    {  0,  0,  6,   12},  {  0,  0,  6,   15},
+    {  0,  0,  6,   18},  {  0,  0,  6,   21},
+    {  0,  0,  6,   24},  {  0,  0,  6,   27},
+    {  0,  0,  6,   30},  {  0,  0,  6,   33},
+    {  0,  1,  6,   35},  {  0,  1,  6,   39},
+    {  0,  2,  6,   43},  {  0,  3,  6,   51},
+    {  0,  4,  6,   67},  {  0,  5,  6,   99},
+    {  0,  8,  6,  259},  { 32,  0,  4,    4},
+    { 48,  0,  4,    4},  { 16,  0,  4,    5},
+    { 32,  0,  5,    7},  { 32,  0,  5,    8},
+    { 32,  0,  5,   10},  { 32,  0,  5,   11},
+    {  0,  0,  6,   14},  {  0,  0,  6,   17},
+    {  0,  0,  6,   20},  {  0,  0,  6,   23},
+    {  0,  0,  6,   26},  {  0,  0,  6,   29},
+    {  0,  0,  6,   32},  {  0, 16,  6,65539},
+    {  0, 15,  6,32771},  {  0, 14,  6,16387},
+    {  0, 13,  6, 8195},  {  0, 12,  6, 4099},
+    {  0, 11,  6, 2051},  {  0, 10,  6, 1027},
+};   /* ML_defaultDTable */
+
+
+static void ZSTD_buildSeqTable_rle(ZSTD_seqSymbol* dt, U32 baseValue, U32 nbAddBits)
+{
+    void* ptr = dt;
+    ZSTD_seqSymbol_header* const DTableH = (ZSTD_seqSymbol_header*)ptr;
+    ZSTD_seqSymbol* const cell = dt + 1;
+
+    DTableH->tableLog = 0;
+    DTableH->fastMode = 0;
+
+    cell->nbBits = 0;
+    cell->nextState = 0;
+    assert(nbAddBits < 255);
+    cell->nbAdditionalBits = (BYTE)nbAddBits;
+    cell->baseValue = baseValue;
+}
+
+
+/* ZSTD_buildFSETable() :
+ * generate FSE decoding table for one symbol (ll, ml or off)
+ * cannot fail if input is valid =>
+ * all inputs are presumed validated at this stage */
+FORCE_INLINE_TEMPLATE
+void ZSTD_buildFSETable_body(ZSTD_seqSymbol* dt,
+            const short* normalizedCounter, unsigned maxSymbolValue,
+            const U32* baseValue, const U32* nbAdditionalBits,
+            unsigned tableLog, void* wksp, size_t wkspSize)
+{
+    ZSTD_seqSymbol* const tableDecode = dt+1;
+    U32 const maxSV1 = maxSymbolValue + 1;
+    U32 const tableSize = 1 << tableLog;
+
+    U16* symbolNext = (U16*)wksp;
+    BYTE* spread = (BYTE*)(symbolNext + MaxSeq + 1);
+    U32 highThreshold = tableSize - 1;
+
+
+    /* Sanity Checks */
+    assert(maxSymbolValue <= MaxSeq);
+    assert(tableLog <= MaxFSELog);
+    assert(wkspSize >= ZSTD_BUILD_FSE_TABLE_WKSP_SIZE);
+    (void)wkspSize;
+    /* Init, lay down lowprob symbols */
+    {   ZSTD_seqSymbol_header DTableH;
+        DTableH.tableLog = tableLog;
+        DTableH.fastMode = 1;
+        {   S16 const largeLimit= (S16)(1 << (tableLog-1));
+            U32 s;
+            for (s=0; s<maxSV1; s++) {
+                if (normalizedCounter[s]==-1) {
+                    tableDecode[highThreshold--].baseValue = s;
+                    symbolNext[s] = 1;
+                } else {
+                    if (normalizedCounter[s] >= largeLimit) DTableH.fastMode=0;
+                    assert(normalizedCounter[s]>=0);
+                    symbolNext[s] = (U16)normalizedCounter[s];
+        }   }   }
+        ZSTD_memcpy(dt, &DTableH, sizeof(DTableH));
+    }
+
+    /* Spread symbols */
+    assert(tableSize <= 512);
+    /* Specialized symbol spreading for the case when there are
+     * no low probability (-1 count) symbols. When compressing
+     * small blocks we avoid low probability symbols to hit this
+     * case, since header decoding speed matters more.
+     */
+    if (highThreshold == tableSize - 1) {
+        size_t const tableMask = tableSize-1;
+        size_t const step = FSE_TABLESTEP(tableSize);
+        /* First lay down the symbols in order.
+         * We use a uint64_t to lay down 8 bytes at a time. This reduces branch
+         * misses since small blocks generally have small table logs, so nearly
+         * all symbols have counts <= 8. We ensure we have 8 bytes at the end of
+         * our buffer to handle the over-write.
+         */
+        {
+            U64 const add = 0x0101010101010101ull;
+            size_t pos = 0;
+            U64 sv = 0;
+            U32 s;
+            for (s=0; s<maxSV1; ++s, sv += add) {
+                int i;
+                int const n = normalizedCounter[s];
+                MEM_write64(spread + pos, sv);
+                for (i = 8; i < n; i += 8) {
+                    MEM_write64(spread + pos + i, sv);
+                }
+                pos += n;
+            }
+        }
+        /* Now we spread those positions across the table.
+         * The benefit of doing it in two stages is that we avoid the the
+         * variable size inner loop, which caused lots of branch misses.
+         * Now we can run through all the positions without any branch misses.
+         * We unroll the loop twice, since that is what emperically worked best.
+         */
+        {
+            size_t position = 0;
+            size_t s;
+            size_t const unroll = 2;
+            assert(tableSize % unroll == 0); /* FSE_MIN_TABLELOG is 5 */
+            for (s = 0; s < (size_t)tableSize; s += unroll) {
+                size_t u;
+                for (u = 0; u < unroll; ++u) {
+                    size_t const uPosition = (position + (u * step)) & tableMask;
+                    tableDecode[uPosition].baseValue = spread[s + u];
+                }
+                position = (position + (unroll * step)) & tableMask;
+            }
+            assert(position == 0);
+        }
+    } else {
+        U32 const tableMask = tableSize-1;
+        U32 const step = FSE_TABLESTEP(tableSize);
+        U32 s, position = 0;
+        for (s=0; s<maxSV1; s++) {
+            int i;
+            int const n = normalizedCounter[s];
+            for (i=0; i<n; i++) {
+                tableDecode[position].baseValue = s;
+                position = (position + step) & tableMask;
+                while (position > highThreshold) position = (position + step) & tableMask;   /* lowprob area */
+        }   }
+        assert(position == 0); /* position must reach all cells once, otherwise normalizedCounter is incorrect */
+    }
+
+    /* Build Decoding table */
+    {
+        U32 u;
+        for (u=0; u<tableSize; u++) {
+            U32 const symbol = tableDecode[u].baseValue;
+            U32 const nextState = symbolNext[symbol]++;
+            tableDecode[u].nbBits = (BYTE) (tableLog - BIT_highbit32(nextState) );
+            tableDecode[u].nextState = (U16) ( (nextState << tableDecode[u].nbBits) - tableSize);
+            assert(nbAdditionalBits[symbol] < 255);
+            tableDecode[u].nbAdditionalBits = (BYTE)nbAdditionalBits[symbol];
+            tableDecode[u].baseValue = baseValue[symbol];
+        }
+    }
+}
+
+/* Avoids the FORCE_INLINE of the _body() function. */
+static void ZSTD_buildFSETable_body_default(ZSTD_seqSymbol* dt,
+            const short* normalizedCounter, unsigned maxSymbolValue,
+            const U32* baseValue, const U32* nbAdditionalBits,
+            unsigned tableLog, void* wksp, size_t wkspSize)
+{
+    ZSTD_buildFSETable_body(dt, normalizedCounter, maxSymbolValue,
+            baseValue, nbAdditionalBits, tableLog, wksp, wkspSize);
+}
+
+#if DYNAMIC_BMI2
+TARGET_ATTRIBUTE("bmi2") static void ZSTD_buildFSETable_body_bmi2(ZSTD_seqSymbol* dt,
+            const short* normalizedCounter, unsigned maxSymbolValue,
+            const U32* baseValue, const U32* nbAdditionalBits,
+            unsigned tableLog, void* wksp, size_t wkspSize)
+{
+    ZSTD_buildFSETable_body(dt, normalizedCounter, maxSymbolValue,
+            baseValue, nbAdditionalBits, tableLog, wksp, wkspSize);
+}
+#endif
+
+void ZSTD_buildFSETable(ZSTD_seqSymbol* dt,
+            const short* normalizedCounter, unsigned maxSymbolValue,
+            const U32* baseValue, const U32* nbAdditionalBits,
+            unsigned tableLog, void* wksp, size_t wkspSize, int bmi2)
+{
+#if DYNAMIC_BMI2
+    if (bmi2) {
+        ZSTD_buildFSETable_body_bmi2(dt, normalizedCounter, maxSymbolValue,
+                baseValue, nbAdditionalBits, tableLog, wksp, wkspSize);
+        return;
+    }
+#endif
+    (void)bmi2;
+    ZSTD_buildFSETable_body_default(dt, normalizedCounter, maxSymbolValue,
+            baseValue, nbAdditionalBits, tableLog, wksp, wkspSize);
+}
+
+
+/*! ZSTD_buildSeqTable() :
+ * @return : nb bytes read from src,
+ *           or an error code if it fails */
+static size_t ZSTD_buildSeqTable(ZSTD_seqSymbol* DTableSpace, const ZSTD_seqSymbol** DTablePtr,
+                                 symbolEncodingType_e type, unsigned max, U32 maxLog,
+                                 const void* src, size_t srcSize,
+                                 const U32* baseValue, const U32* nbAdditionalBits,
+                                 const ZSTD_seqSymbol* defaultTable, U32 flagRepeatTable,
+                                 int ddictIsCold, int nbSeq, U32* wksp, size_t wkspSize,
+                                 int bmi2)
+{
+    switch(type)
+    {
+    case set_rle :
+        RETURN_ERROR_IF(!srcSize, srcSize_wrong, "");
+        RETURN_ERROR_IF((*(const BYTE*)src) > max, corruption_detected, "");
+        {   U32 const symbol = *(const BYTE*)src;
+            U32 const baseline = baseValue[symbol];
+            U32 const nbBits = nbAdditionalBits[symbol];
+            ZSTD_buildSeqTable_rle(DTableSpace, baseline, nbBits);
+        }
+        *DTablePtr = DTableSpace;
+        return 1;
+    case set_basic :
+        *DTablePtr = defaultTable;
+        return 0;
+    case set_repeat:
+        RETURN_ERROR_IF(!flagRepeatTable, corruption_detected, "");
+        /* prefetch FSE table if used */
+        if (ddictIsCold && (nbSeq > 24 /* heuristic */)) {
+            const void* const pStart = *DTablePtr;
+            size_t const pSize = sizeof(ZSTD_seqSymbol) * (SEQSYMBOL_TABLE_SIZE(maxLog));
+            PREFETCH_AREA(pStart, pSize);
+        }
+        return 0;
+    case set_compressed :
+        {   unsigned tableLog;
+            S16 norm[MaxSeq+1];
+            size_t const headerSize = FSE_readNCount(norm, &max, &tableLog, src, srcSize);
+            RETURN_ERROR_IF(FSE_isError(headerSize), corruption_detected, "");
+            RETURN_ERROR_IF(tableLog > maxLog, corruption_detected, "");
+            ZSTD_buildFSETable(DTableSpace, norm, max, baseValue, nbAdditionalBits, tableLog, wksp, wkspSize, bmi2);
+            *DTablePtr = DTableSpace;
+            return headerSize;
+        }
+    default :
+        assert(0);
+        RETURN_ERROR(GENERIC, "impossible");
+    }
+}
+
+size_t ZSTD_decodeSeqHeaders(ZSTD_DCtx* dctx, int* nbSeqPtr,
+                             const void* src, size_t srcSize)
+{
+    const BYTE* const istart = (const BYTE*)src;
+    const BYTE* const iend = istart + srcSize;
+    const BYTE* ip = istart;
+    int nbSeq;
+    DEBUGLOG(5, "ZSTD_decodeSeqHeaders");
+
+    /* check */
+    RETURN_ERROR_IF(srcSize < MIN_SEQUENCES_SIZE, srcSize_wrong, "");
+
+    /* SeqHead */
+    nbSeq = *ip++;
+    if (!nbSeq) {
+        *nbSeqPtr=0;
+        RETURN_ERROR_IF(srcSize != 1, srcSize_wrong, "");
+        return 1;
+    }
+    if (nbSeq > 0x7F) {
+        if (nbSeq == 0xFF) {
+            RETURN_ERROR_IF(ip+2 > iend, srcSize_wrong, "");
+            nbSeq = MEM_readLE16(ip) + LONGNBSEQ;
+            ip+=2;
+        } else {
+            RETURN_ERROR_IF(ip >= iend, srcSize_wrong, "");
+            nbSeq = ((nbSeq-0x80)<<8) + *ip++;
+        }
+    }
+    *nbSeqPtr = nbSeq;
+
+    /* FSE table descriptors */
+    RETURN_ERROR_IF(ip+1 > iend, srcSize_wrong, ""); /* minimum possible size: 1 byte for symbol encoding types */
+    {   symbolEncodingType_e const LLtype = (symbolEncodingType_e)(*ip >> 6);
+        symbolEncodingType_e const OFtype = (symbolEncodingType_e)((*ip >> 4) & 3);
+        symbolEncodingType_e const MLtype = (symbolEncodingType_e)((*ip >> 2) & 3);
+        ip++;
+
+        /* Build DTables */
+        {   size_t const llhSize = ZSTD_buildSeqTable(dctx->entropy.LLTable, &dctx->LLTptr,
+                                                      LLtype, MaxLL, LLFSELog,
+                                                      ip, iend-ip,
+                                                      LL_base, LL_bits,
+                                                      LL_defaultDTable, dctx->fseEntropy,
+                                                      dctx->ddictIsCold, nbSeq,
+                                                      dctx->workspace, sizeof(dctx->workspace),
+                                                      dctx->bmi2);
+            RETURN_ERROR_IF(ZSTD_isError(llhSize), corruption_detected, "ZSTD_buildSeqTable failed");
+            ip += llhSize;
+        }
+
+        {   size_t const ofhSize = ZSTD_buildSeqTable(dctx->entropy.OFTable, &dctx->OFTptr,
+                                                      OFtype, MaxOff, OffFSELog,
+                                                      ip, iend-ip,
+                                                      OF_base, OF_bits,
+                                                      OF_defaultDTable, dctx->fseEntropy,
+                                                      dctx->ddictIsCold, nbSeq,
+                                                      dctx->workspace, sizeof(dctx->workspace),
+                                                      dctx->bmi2);
+            RETURN_ERROR_IF(ZSTD_isError(ofhSize), corruption_detected, "ZSTD_buildSeqTable failed");
+            ip += ofhSize;
+        }
+
+        {   size_t const mlhSize = ZSTD_buildSeqTable(dctx->entropy.MLTable, &dctx->MLTptr,
+                                                      MLtype, MaxML, MLFSELog,
+                                                      ip, iend-ip,
+                                                      ML_base, ML_bits,
+                                                      ML_defaultDTable, dctx->fseEntropy,
+                                                      dctx->ddictIsCold, nbSeq,
+                                                      dctx->workspace, sizeof(dctx->workspace),
+                                                      dctx->bmi2);
+            RETURN_ERROR_IF(ZSTD_isError(mlhSize), corruption_detected, "ZSTD_buildSeqTable failed");
+            ip += mlhSize;
+        }
+    }
+
+    return ip-istart;
+}
+
+
+typedef struct {
+    size_t litLength;
+    size_t matchLength;
+    size_t offset;
+    const BYTE* match;
+} seq_t;
+
+typedef struct {
+    size_t state;
+    const ZSTD_seqSymbol* table;
+} ZSTD_fseState;
+
+typedef struct {
+    BIT_DStream_t DStream;
+    ZSTD_fseState stateLL;
+    ZSTD_fseState stateOffb;
+    ZSTD_fseState stateML;
+    size_t prevOffset[ZSTD_REP_NUM];
+    const BYTE* prefixStart;
+    const BYTE* dictEnd;
+    size_t pos;
+} seqState_t;
+
+/*! ZSTD_overlapCopy8() :
+ *  Copies 8 bytes from ip to op and updates op and ip where ip <= op.
+ *  If the offset is < 8 then the offset is spread to at least 8 bytes.
+ *
+ *  Precondition: *ip <= *op
+ *  Postcondition: *op - *op >= 8
+ */
+HINT_INLINE void ZSTD_overlapCopy8(BYTE** op, BYTE const** ip, size_t offset) {
+    assert(*ip <= *op);
+    if (offset < 8) {
+        /* close range match, overlap */
+        static const U32 dec32table[] = { 0, 1, 2, 1, 4, 4, 4, 4 };   /* added */
+        static const int dec64table[] = { 8, 8, 8, 7, 8, 9,10,11 };   /* subtracted */
+        int const sub2 = dec64table[offset];
+        (*op)[0] = (*ip)[0];
+        (*op)[1] = (*ip)[1];
+        (*op)[2] = (*ip)[2];
+        (*op)[3] = (*ip)[3];
+        *ip += dec32table[offset];
+        ZSTD_copy4(*op+4, *ip);
+        *ip -= sub2;
+    } else {
+        ZSTD_copy8(*op, *ip);
+    }
+    *ip += 8;
+    *op += 8;
+    assert(*op - *ip >= 8);
+}
+
+/*! ZSTD_safecopy() :
+ *  Specialized version of memcpy() that is allowed to READ up to WILDCOPY_OVERLENGTH past the input buffer
+ *  and write up to 16 bytes past oend_w (op >= oend_w is allowed).
+ *  This function is only called in the uncommon case where the sequence is near the end of the block. It
+ *  should be fast for a single long sequence, but can be slow for several short sequences.
+ *
+ *  @param ovtype controls the overlap detection
+ *         - ZSTD_no_overlap: The source and destination are guaranteed to be at least WILDCOPY_VECLEN bytes apart.
+ *         - ZSTD_overlap_src_before_dst: The src and dst may overlap and may be any distance apart.
+ *           The src buffer must be before the dst buffer.
+ */
+static void ZSTD_safecopy(BYTE* op, BYTE* const oend_w, BYTE const* ip, ptrdiff_t length, ZSTD_overlap_e ovtype) {
+    ptrdiff_t const diff = op - ip;
+    BYTE* const oend = op + length;
+
+    assert((ovtype == ZSTD_no_overlap && (diff <= -8 || diff >= 8 || op >= oend_w)) ||
+           (ovtype == ZSTD_overlap_src_before_dst && diff >= 0));
+
+    if (length < 8) {
+        /* Handle short lengths. */
+        while (op < oend) *op++ = *ip++;
+        return;
+    }
+    if (ovtype == ZSTD_overlap_src_before_dst) {
+        /* Copy 8 bytes and ensure the offset >= 8 when there can be overlap. */
+        assert(length >= 8);
+        ZSTD_overlapCopy8(&op, &ip, diff);
+        assert(op - ip >= 8);
+        assert(op <= oend);
+    }
+
+    if (oend <= oend_w) {
+        /* No risk of overwrite. */
+        ZSTD_wildcopy(op, ip, length, ovtype);
+        return;
+    }
+    if (op <= oend_w) {
+        /* Wildcopy until we get close to the end. */
+        assert(oend > oend_w);
+        ZSTD_wildcopy(op, ip, oend_w - op, ovtype);
+        ip += oend_w - op;
+        op = oend_w;
+    }
+    /* Handle the leftovers. */
+    while (op < oend) *op++ = *ip++;
+}
+
+/* ZSTD_execSequenceEnd():
+ * This version handles cases that are near the end of the output buffer. It requires
+ * more careful checks to make sure there is no overflow. By separating out these hard
+ * and unlikely cases, we can speed up the common cases.
+ *
+ * NOTE: This function needs to be fast for a single long sequence, but doesn't need
+ * to be optimized for many small sequences, since those fall into ZSTD_execSequence().
+ */
+FORCE_NOINLINE
+size_t ZSTD_execSequenceEnd(BYTE* op,
+                            BYTE* const oend, seq_t sequence,
+                            const BYTE** litPtr, const BYTE* const litLimit,
+                            const BYTE* const prefixStart, const BYTE* const virtualStart, const BYTE* const dictEnd)
+{
+    BYTE* const oLitEnd = op + sequence.litLength;
+    size_t const sequenceLength = sequence.litLength + sequence.matchLength;
+    const BYTE* const iLitEnd = *litPtr + sequence.litLength;
+    const BYTE* match = oLitEnd - sequence.offset;
+    BYTE* const oend_w = oend - WILDCOPY_OVERLENGTH;
+
+    /* bounds checks : careful of address space overflow in 32-bit mode */
+    RETURN_ERROR_IF(sequenceLength > (size_t)(oend - op), dstSize_tooSmall, "last match must fit within dstBuffer");
+    RETURN_ERROR_IF(sequence.litLength > (size_t)(litLimit - *litPtr), corruption_detected, "try to read beyond literal buffer");
+    assert(op < op + sequenceLength);
+    assert(oLitEnd < op + sequenceLength);
+
+    /* copy literals */
+    ZSTD_safecopy(op, oend_w, *litPtr, sequence.litLength, ZSTD_no_overlap);
+    op = oLitEnd;
+    *litPtr = iLitEnd;
+
+    /* copy Match */
+    if (sequence.offset > (size_t)(oLitEnd - prefixStart)) {
+        /* offset beyond prefix */
+        RETURN_ERROR_IF(sequence.offset > (size_t)(oLitEnd - virtualStart), corruption_detected, "");
+        match = dictEnd - (prefixStart-match);
+        if (match + sequence.matchLength <= dictEnd) {
+            ZSTD_memmove(oLitEnd, match, sequence.matchLength);
+            return sequenceLength;
+        }
+        /* span extDict & currentPrefixSegment */
+        {   size_t const length1 = dictEnd - match;
+            ZSTD_memmove(oLitEnd, match, length1);
+            op = oLitEnd + length1;
+            sequence.matchLength -= length1;
+            match = prefixStart;
+    }   }
+    ZSTD_safecopy(op, oend_w, match, sequence.matchLength, ZSTD_overlap_src_before_dst);
+    return sequenceLength;
+}
+
+HINT_INLINE
+size_t ZSTD_execSequence(BYTE* op,
+                         BYTE* const oend, seq_t sequence,
+                         const BYTE** litPtr, const BYTE* const litLimit,
+                         const BYTE* const prefixStart, const BYTE* const virtualStart, const BYTE* const dictEnd)
+{
+    BYTE* const oLitEnd = op + sequence.litLength;
+    size_t const sequenceLength = sequence.litLength + sequence.matchLength;
+    BYTE* const oMatchEnd = op + sequenceLength;   /* risk : address space overflow (32-bits) */
+    BYTE* const oend_w = oend - WILDCOPY_OVERLENGTH;   /* risk : address space underflow on oend=NULL */
+    const BYTE* const iLitEnd = *litPtr + sequence.litLength;
+    const BYTE* match = oLitEnd - sequence.offset;
+
+    assert(op != NULL /* Precondition */);
+    assert(oend_w < oend /* No underflow */);
+    /* Handle edge cases in a slow path:
+     *   - Read beyond end of literals
+     *   - Match end is within WILDCOPY_OVERLIMIT of oend
+     *   - 32-bit mode and the match length overflows
+     */
+    if (UNLIKELY(
+            iLitEnd > litLimit ||
+            oMatchEnd > oend_w ||
+            (MEM_32bits() && (size_t)(oend - op) < sequenceLength + WILDCOPY_OVERLENGTH)))
+        return ZSTD_execSequenceEnd(op, oend, sequence, litPtr, litLimit, prefixStart, virtualStart, dictEnd);
+
+    /* Assumptions (everything else goes into ZSTD_execSequenceEnd()) */
+    assert(op <= oLitEnd /* No overflow */);
+    assert(oLitEnd < oMatchEnd /* Non-zero match & no overflow */);
+    assert(oMatchEnd <= oend /* No underflow */);
+    assert(iLitEnd <= litLimit /* Literal length is in bounds */);
+    assert(oLitEnd <= oend_w /* Can wildcopy literals */);
+    assert(oMatchEnd <= oend_w /* Can wildcopy matches */);
+
+    /* Copy Literals:
+     * Split out litLength <= 16 since it is nearly always true. +1.6% on gcc-9.
+     * We likely don't need the full 32-byte wildcopy.
+     */
+    assert(WILDCOPY_OVERLENGTH >= 16);
+    ZSTD_copy16(op, (*litPtr));
+    if (UNLIKELY(sequence.litLength > 16)) {
+        ZSTD_wildcopy(op+16, (*litPtr)+16, sequence.litLength-16, ZSTD_no_overlap);
+    }
+    op = oLitEnd;
+    *litPtr = iLitEnd;   /* update for next sequence */
+
+    /* Copy Match */
+    if (sequence.offset > (size_t)(oLitEnd - prefixStart)) {
+        /* offset beyond prefix -> go into extDict */
+        RETURN_ERROR_IF(UNLIKELY(sequence.offset > (size_t)(oLitEnd - virtualStart)), corruption_detected, "");
+        match = dictEnd + (match - prefixStart);
+        if (match + sequence.matchLength <= dictEnd) {
+            ZSTD_memmove(oLitEnd, match, sequence.matchLength);
+            return sequenceLength;
+        }
+        /* span extDict & currentPrefixSegment */
+        {   size_t const length1 = dictEnd - match;
+            ZSTD_memmove(oLitEnd, match, length1);
+            op = oLitEnd + length1;
+            sequence.matchLength -= length1;
+            match = prefixStart;
+    }   }
+    /* Match within prefix of 1 or more bytes */
+    assert(op <= oMatchEnd);
+    assert(oMatchEnd <= oend_w);
+    assert(match >= prefixStart);
+    assert(sequence.matchLength >= 1);
+
+    /* Nearly all offsets are >= WILDCOPY_VECLEN bytes, which means we can use wildcopy
+     * without overlap checking.
+     */
+    if (LIKELY(sequence.offset >= WILDCOPY_VECLEN)) {
+        /* We bet on a full wildcopy for matches, since we expect matches to be
+         * longer than literals (in general). In silesia, ~10% of matches are longer
+         * than 16 bytes.
+         */
+        ZSTD_wildcopy(op, match, (ptrdiff_t)sequence.matchLength, ZSTD_no_overlap);
+        return sequenceLength;
+    }
+    assert(sequence.offset < WILDCOPY_VECLEN);
+
+    /* Copy 8 bytes and spread the offset to be >= 8. */
+    ZSTD_overlapCopy8(&op, &match, sequence.offset);
+
+    /* If the match length is > 8 bytes, then continue with the wildcopy. */
+    if (sequence.matchLength > 8) {
+        assert(op < oMatchEnd);
+        ZSTD_wildcopy(op, match, (ptrdiff_t)sequence.matchLength-8, ZSTD_overlap_src_before_dst);
+    }
+    return sequenceLength;
+}
+
+static void
+ZSTD_initFseState(ZSTD_fseState* DStatePtr, BIT_DStream_t* bitD, const ZSTD_seqSymbol* dt)
+{
+    const void* ptr = dt;
+    const ZSTD_seqSymbol_header* const DTableH = (const ZSTD_seqSymbol_header*)ptr;
+    DStatePtr->state = BIT_readBits(bitD, DTableH->tableLog);
+    DEBUGLOG(6, "ZSTD_initFseState : val=%u using %u bits",
+                (U32)DStatePtr->state, DTableH->tableLog);
+    BIT_reloadDStream(bitD);
+    DStatePtr->table = dt + 1;
+}
+
+FORCE_INLINE_TEMPLATE void
+ZSTD_updateFseState(ZSTD_fseState* DStatePtr, BIT_DStream_t* bitD)
+{
+    ZSTD_seqSymbol const DInfo = DStatePtr->table[DStatePtr->state];
+    U32 const nbBits = DInfo.nbBits;
+    size_t const lowBits = BIT_readBits(bitD, nbBits);
+    DStatePtr->state = DInfo.nextState + lowBits;
+}
+
+FORCE_INLINE_TEMPLATE void
+ZSTD_updateFseStateWithDInfo(ZSTD_fseState* DStatePtr, BIT_DStream_t* bitD, ZSTD_seqSymbol const DInfo)
+{
+    U32 const nbBits = DInfo.nbBits;
+    size_t const lowBits = BIT_readBits(bitD, nbBits);
+    DStatePtr->state = DInfo.nextState + lowBits;
+}
+
+/* We need to add at most (ZSTD_WINDOWLOG_MAX_32 - 1) bits to read the maximum
+ * offset bits. But we can only read at most (STREAM_ACCUMULATOR_MIN_32 - 1)
+ * bits before reloading. This value is the maximum number of bytes we read
+ * after reloading when we are decoding long offsets.
+ */
+#define LONG_OFFSETS_MAX_EXTRA_BITS_32                       \
+    (ZSTD_WINDOWLOG_MAX_32 > STREAM_ACCUMULATOR_MIN_32       \
+        ? ZSTD_WINDOWLOG_MAX_32 - STREAM_ACCUMULATOR_MIN_32  \
+        : 0)
+
+typedef enum { ZSTD_lo_isRegularOffset, ZSTD_lo_isLongOffset=1 } ZSTD_longOffset_e;
+typedef enum { ZSTD_p_noPrefetch=0, ZSTD_p_prefetch=1 } ZSTD_prefetch_e;
+
+FORCE_INLINE_TEMPLATE seq_t
+ZSTD_decodeSequence(seqState_t* seqState, const ZSTD_longOffset_e longOffsets, const ZSTD_prefetch_e prefetch)
+{
+    seq_t seq;
+    ZSTD_seqSymbol const llDInfo = seqState->stateLL.table[seqState->stateLL.state];
+    ZSTD_seqSymbol const mlDInfo = seqState->stateML.table[seqState->stateML.state];
+    ZSTD_seqSymbol const ofDInfo = seqState->stateOffb.table[seqState->stateOffb.state];
+    U32 const llBase = llDInfo.baseValue;
+    U32 const mlBase = mlDInfo.baseValue;
+    U32 const ofBase = ofDInfo.baseValue;
+    BYTE const llBits = llDInfo.nbAdditionalBits;
+    BYTE const mlBits = mlDInfo.nbAdditionalBits;
+    BYTE const ofBits = ofDInfo.nbAdditionalBits;
+    BYTE const totalBits = llBits+mlBits+ofBits;
+
+    /* sequence */
+    {   size_t offset;
+        if (ofBits > 1) {
+            ZSTD_STATIC_ASSERT(ZSTD_lo_isLongOffset == 1);
+            ZSTD_STATIC_ASSERT(LONG_OFFSETS_MAX_EXTRA_BITS_32 == 5);
+            assert(ofBits <= MaxOff);
+            if (MEM_32bits() && longOffsets && (ofBits >= STREAM_ACCUMULATOR_MIN_32)) {
+                U32 const extraBits = ofBits - MIN(ofBits, 32 - seqState->DStream.bitsConsumed);
+                offset = ofBase + (BIT_readBitsFast(&seqState->DStream, ofBits - extraBits) << extraBits);
+                BIT_reloadDStream(&seqState->DStream);
+                if (extraBits) offset += BIT_readBitsFast(&seqState->DStream, extraBits);
+                assert(extraBits <= LONG_OFFSETS_MAX_EXTRA_BITS_32);   /* to avoid another reload */
+            } else {
+                offset = ofBase + BIT_readBitsFast(&seqState->DStream, ofBits/*>0*/);   /* <=  (ZSTD_WINDOWLOG_MAX-1) bits */
+                if (MEM_32bits()) BIT_reloadDStream(&seqState->DStream);
+            }
+            seqState->prevOffset[2] = seqState->prevOffset[1];
+            seqState->prevOffset[1] = seqState->prevOffset[0];
+            seqState->prevOffset[0] = offset;
+        } else {
+            U32 const ll0 = (llBase == 0);
+            if (LIKELY((ofBits == 0))) {
+                if (LIKELY(!ll0))
+                    offset = seqState->prevOffset[0];
+                else {
+                    offset = seqState->prevOffset[1];
+                    seqState->prevOffset[1] = seqState->prevOffset[0];
+                    seqState->prevOffset[0] = offset;
+                }
+            } else {
+                offset = ofBase + ll0 + BIT_readBitsFast(&seqState->DStream, 1);
+                {   size_t temp = (offset==3) ? seqState->prevOffset[0] - 1 : seqState->prevOffset[offset];
+                    temp += !temp;   /* 0 is not valid; input is corrupted; force offset to 1 */
+                    if (offset != 1) seqState->prevOffset[2] = seqState->prevOffset[1];
+                    seqState->prevOffset[1] = seqState->prevOffset[0];
+                    seqState->prevOffset[0] = offset = temp;
+        }   }   }
+        seq.offset = offset;
+    }
+
+    seq.matchLength = mlBase;
+    if (mlBits > 0)
+        seq.matchLength += BIT_readBitsFast(&seqState->DStream, mlBits/*>0*/);
+
+    if (MEM_32bits() && (mlBits+llBits >= STREAM_ACCUMULATOR_MIN_32-LONG_OFFSETS_MAX_EXTRA_BITS_32))
+        BIT_reloadDStream(&seqState->DStream);
+    if (MEM_64bits() && UNLIKELY(totalBits >= STREAM_ACCUMULATOR_MIN_64-(LLFSELog+MLFSELog+OffFSELog)))
+        BIT_reloadDStream(&seqState->DStream);
+    /* Ensure there are enough bits to read the rest of data in 64-bit mode. */
+    ZSTD_STATIC_ASSERT(16+LLFSELog+MLFSELog+OffFSELog < STREAM_ACCUMULATOR_MIN_64);
+
+    seq.litLength = llBase;
+    if (llBits > 0)
+        seq.litLength += BIT_readBitsFast(&seqState->DStream, llBits/*>0*/);
+
+    if (MEM_32bits())
+        BIT_reloadDStream(&seqState->DStream);
+
+    DEBUGLOG(6, "seq: litL=%u, matchL=%u, offset=%u",
+                (U32)seq.litLength, (U32)seq.matchLength, (U32)seq.offset);
+
+    if (prefetch == ZSTD_p_prefetch) {
+        size_t const pos = seqState->pos + seq.litLength;
+        const BYTE* const matchBase = (seq.offset > pos) ? seqState->dictEnd : seqState->prefixStart;
+        seq.match = matchBase + pos - seq.offset;  /* note : this operation can overflow when seq.offset is really too large, which can only happen when input is corrupted.
+                                                    * No consequence though : no memory access will occur, offset is only used for prefetching */
+        seqState->pos = pos + seq.matchLength;
+    }
+
+    /* ANS state update
+     * gcc-9.0.0 does 2.5% worse with ZSTD_updateFseStateWithDInfo().
+     * clang-9.2.0 does 7% worse with ZSTD_updateFseState().
+     * Naturally it seems like ZSTD_updateFseStateWithDInfo() should be the
+     * better option, so it is the default for other compilers. But, if you
+     * measure that it is worse, please put up a pull request.
+     */
+    {
+#if !defined(__clang__)
+        const int kUseUpdateFseState = 1;
+#else
+        const int kUseUpdateFseState = 0;
+#endif
+        if (kUseUpdateFseState) {
+            ZSTD_updateFseState(&seqState->stateLL, &seqState->DStream);    /* <=  9 bits */
+            ZSTD_updateFseState(&seqState->stateML, &seqState->DStream);    /* <=  9 bits */
+            if (MEM_32bits()) BIT_reloadDStream(&seqState->DStream);    /* <= 18 bits */
+            ZSTD_updateFseState(&seqState->stateOffb, &seqState->DStream);  /* <=  8 bits */
+        } else {
+            ZSTD_updateFseStateWithDInfo(&seqState->stateLL, &seqState->DStream, llDInfo);    /* <=  9 bits */
+            ZSTD_updateFseStateWithDInfo(&seqState->stateML, &seqState->DStream, mlDInfo);    /* <=  9 bits */
+            if (MEM_32bits()) BIT_reloadDStream(&seqState->DStream);    /* <= 18 bits */
+            ZSTD_updateFseStateWithDInfo(&seqState->stateOffb, &seqState->DStream, ofDInfo);  /* <=  8 bits */
+        }
+    }
+
+    return seq;
+}
+
+#ifdef FUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION
+MEM_STATIC int ZSTD_dictionaryIsActive(ZSTD_DCtx const* dctx, BYTE const* prefixStart, BYTE const* oLitEnd)
+{
+    size_t const windowSize = dctx->fParams.windowSize;
+    /* No dictionary used. */
+    if (dctx->dictContentEndForFuzzing == NULL) return 0;
+    /* Dictionary is our prefix. */
+    if (prefixStart == dctx->dictContentBeginForFuzzing) return 1;
+    /* Dictionary is not our ext-dict. */
+    if (dctx->dictEnd != dctx->dictContentEndForFuzzing) return 0;
+    /* Dictionary is not within our window size. */
+    if ((size_t)(oLitEnd - prefixStart) >= windowSize) return 0;
+    /* Dictionary is active. */
+    return 1;
+}
+
+MEM_STATIC void ZSTD_assertValidSequence(
+        ZSTD_DCtx const* dctx,
+        BYTE const* op, BYTE const* oend,
+        seq_t const seq,
+        BYTE const* prefixStart, BYTE const* virtualStart)
+{
+#if DEBUGLEVEL >= 1
+    size_t const windowSize = dctx->fParams.windowSize;
+    size_t const sequenceSize = seq.litLength + seq.matchLength;
+    BYTE const* const oLitEnd = op + seq.litLength;
+    DEBUGLOG(6, "Checking sequence: litL=%u matchL=%u offset=%u",
+            (U32)seq.litLength, (U32)seq.matchLength, (U32)seq.offset);
+    assert(op <= oend);
+    assert((size_t)(oend - op) >= sequenceSize);
+    assert(sequenceSize <= ZSTD_BLOCKSIZE_MAX);
+    if (ZSTD_dictionaryIsActive(dctx, prefixStart, oLitEnd)) {
+        size_t const dictSize = (size_t)((char const*)dctx->dictContentEndForFuzzing - (char const*)dctx->dictContentBeginForFuzzing);
+        /* Offset must be within the dictionary. */
+        assert(seq.offset <= (size_t)(oLitEnd - virtualStart));
+        assert(seq.offset <= windowSize + dictSize);
+    } else {
+        /* Offset must be within our window. */
+        assert(seq.offset <= windowSize);
+    }
+#else
+    (void)dctx, (void)op, (void)oend, (void)seq, (void)prefixStart, (void)virtualStart;
+#endif
+}
+#endif
+
+#ifndef ZSTD_FORCE_DECOMPRESS_SEQUENCES_LONG
+FORCE_INLINE_TEMPLATE size_t
+DONT_VECTORIZE
+ZSTD_decompressSequences_body( ZSTD_DCtx* dctx,
+                               void* dst, size_t maxDstSize,
+                         const void* seqStart, size_t seqSize, int nbSeq,
+                         const ZSTD_longOffset_e isLongOffset,
+                         const int frame)
+{
+    const BYTE* ip = (const BYTE*)seqStart;
+    const BYTE* const iend = ip + seqSize;
+    BYTE* const ostart = (BYTE*)dst;
+    BYTE* const oend = ostart + maxDstSize;
+    BYTE* op = ostart;
+    const BYTE* litPtr = dctx->litPtr;
+    const BYTE* const litEnd = litPtr + dctx->litSize;
+    const BYTE* const prefixStart = (const BYTE*) (dctx->prefixStart);
+    const BYTE* const vBase = (const BYTE*) (dctx->virtualStart);
+    const BYTE* const dictEnd = (const BYTE*) (dctx->dictEnd);
+    DEBUGLOG(5, "ZSTD_decompressSequences_body");
+    (void)frame;
+
+    /* Regen sequences */
+    if (nbSeq) {
+        seqState_t seqState;
+        size_t error = 0;
+        dctx->fseEntropy = 1;
+        { U32 i; for (i=0; i<ZSTD_REP_NUM; i++) seqState.prevOffset[i] = dctx->entropy.rep[i]; }
+        RETURN_ERROR_IF(
+            ERR_isError(BIT_initDStream(&seqState.DStream, ip, iend-ip)),
+            corruption_detected, "");
+        ZSTD_initFseState(&seqState.stateLL, &seqState.DStream, dctx->LLTptr);
+        ZSTD_initFseState(&seqState.stateOffb, &seqState.DStream, dctx->OFTptr);
+        ZSTD_initFseState(&seqState.stateML, &seqState.DStream, dctx->MLTptr);
+        assert(dst != NULL);
+
+        ZSTD_STATIC_ASSERT(
+                BIT_DStream_unfinished < BIT_DStream_completed &&
+                BIT_DStream_endOfBuffer < BIT_DStream_completed &&
+                BIT_DStream_completed < BIT_DStream_overflow);
+
+#if defined(__x86_64__)
+        /* Align the decompression loop to 32 + 16 bytes.
+         *
+         * zstd compiled with gcc-9 on an Intel i9-9900k shows 10% decompression
+         * speed swings based on the alignment of the decompression loop. This
+         * performance swing is caused by parts of the decompression loop falling
+         * out of the DSB. The entire decompression loop should fit in the DSB,
+         * when it can't we get much worse performance. You can measure if you've
+         * hit the good case or the bad case with this perf command for some
+         * compressed file test.zst:
+         *
+         *   perf stat -e cycles -e instructions -e idq.all_dsb_cycles_any_uops \
+         *             -e idq.all_mite_cycles_any_uops -- ./zstd -tq test.zst
+         *
+         * If you see most cycles served out of the MITE you've hit the bad case.
+         * If you see most cycles served out of the DSB you've hit the good case.
+         * If it is pretty even then you may be in an okay case.
+         *
+         * I've been able to reproduce this issue on the following CPUs:
+         *   - Kabylake: Macbook Pro (15-inch, 2019) 2.4 GHz Intel Core i9
+         *               Use Instruments->Counters to get DSB/MITE cycles.
+         *               I never got performance swings, but I was able to
+         *               go from the good case of mostly DSB to half of the
+         *               cycles served from MITE.
+         *   - Coffeelake: Intel i9-9900k
+         *
+         * I haven't been able to reproduce the instability or DSB misses on any
+         * of the following CPUS:
+         *   - Haswell
+         *   - Broadwell: Intel(R) Xeon(R) CPU E5-2680 v4 @ 2.40GH
+         *   - Skylake
+         *
+         * If you are seeing performance stability this script can help test.
+         * It tests on 4 commits in zstd where I saw performance change.
+         *
+         *   https://gist.github.com/terrelln/9889fc06a423fd5ca6e99351564473f4
+         */
+        __asm__(".p2align 5");
+        __asm__("nop");
+        __asm__(".p2align 4");
+#endif
+        for ( ; ; ) {
+            seq_t const sequence = ZSTD_decodeSequence(&seqState, isLongOffset, ZSTD_p_noPrefetch);
+            size_t const oneSeqSize = ZSTD_execSequence(op, oend, sequence, &litPtr, litEnd, prefixStart, vBase, dictEnd);
+#if defined(FUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION) && defined(FUZZING_ASSERT_VALID_SEQUENCE)
+            assert(!ZSTD_isError(oneSeqSize));
+            if (frame) ZSTD_assertValidSequence(dctx, op, oend, sequence, prefixStart, vBase);
+#endif
+            DEBUGLOG(6, "regenerated sequence size : %u", (U32)oneSeqSize);
+            BIT_reloadDStream(&(seqState.DStream));
+            op += oneSeqSize;
+            /* gcc and clang both don't like early returns in this loop.
+             * Instead break and check for an error at the end of the loop.
+             */
+            if (UNLIKELY(ZSTD_isError(oneSeqSize))) {
+                error = oneSeqSize;
+                break;
+            }
+            if (UNLIKELY(!--nbSeq)) break;
+        }
+
+        /* check if reached exact end */
+        DEBUGLOG(5, "ZSTD_decompressSequences_body: after decode loop, remaining nbSeq : %i", nbSeq);
+        if (ZSTD_isError(error)) return error;
+        RETURN_ERROR_IF(nbSeq, corruption_detected, "");
+        RETURN_ERROR_IF(BIT_reloadDStream(&seqState.DStream) < BIT_DStream_completed, corruption_detected, "");
+        /* save reps for next block */
+        { U32 i; for (i=0; i<ZSTD_REP_NUM; i++) dctx->entropy.rep[i] = (U32)(seqState.prevOffset[i]); }
+    }
+
+    /* last literal segment */
+    {   size_t const lastLLSize = litEnd - litPtr;
+        RETURN_ERROR_IF(lastLLSize > (size_t)(oend-op), dstSize_tooSmall, "");
+        if (op != NULL) {
+            ZSTD_memcpy(op, litPtr, lastLLSize);
+            op += lastLLSize;
+        }
+    }
+
+    return op-ostart;
+}
+
+static size_t
+ZSTD_decompressSequences_default(ZSTD_DCtx* dctx,
+                                 void* dst, size_t maxDstSize,
+                           const void* seqStart, size_t seqSize, int nbSeq,
+                           const ZSTD_longOffset_e isLongOffset,
+                           const int frame)
+{
+    return ZSTD_decompressSequences_body(dctx, dst, maxDstSize, seqStart, seqSize, nbSeq, isLongOffset, frame);
+}
+#endif /* ZSTD_FORCE_DECOMPRESS_SEQUENCES_LONG */
+
+#ifndef ZSTD_FORCE_DECOMPRESS_SEQUENCES_SHORT
+FORCE_INLINE_TEMPLATE size_t
+ZSTD_decompressSequencesLong_body(
+                               ZSTD_DCtx* dctx,
+                               void* dst, size_t maxDstSize,
+                         const void* seqStart, size_t seqSize, int nbSeq,
+                         const ZSTD_longOffset_e isLongOffset,
+                         const int frame)
+{
+    const BYTE* ip = (const BYTE*)seqStart;
+    const BYTE* const iend = ip + seqSize;
+    BYTE* const ostart = (BYTE*)dst;
+    BYTE* const oend = ostart + maxDstSize;
+    BYTE* op = ostart;
+    const BYTE* litPtr = dctx->litPtr;
+    const BYTE* const litEnd = litPtr + dctx->litSize;
+    const BYTE* const prefixStart = (const BYTE*) (dctx->prefixStart);
+    const BYTE* const dictStart = (const BYTE*) (dctx->virtualStart);
+    const BYTE* const dictEnd = (const BYTE*) (dctx->dictEnd);
+    (void)frame;
+
+    /* Regen sequences */
+    if (nbSeq) {
+#define STORED_SEQS 4
+#define STORED_SEQS_MASK (STORED_SEQS-1)
+#define ADVANCED_SEQS 4
+        seq_t sequences[STORED_SEQS];
+        int const seqAdvance = MIN(nbSeq, ADVANCED_SEQS);
+        seqState_t seqState;
+        int seqNb;
+        dctx->fseEntropy = 1;
+        { int i; for (i=0; i<ZSTD_REP_NUM; i++) seqState.prevOffset[i] = dctx->entropy.rep[i]; }
+        seqState.prefixStart = prefixStart;
+        seqState.pos = (size_t)(op-prefixStart);
+        seqState.dictEnd = dictEnd;
+        assert(dst != NULL);
+        assert(iend >= ip);
+        RETURN_ERROR_IF(
+            ERR_isError(BIT_initDStream(&seqState.DStream, ip, iend-ip)),
+            corruption_detected, "");
+        ZSTD_initFseState(&seqState.stateLL, &seqState.DStream, dctx->LLTptr);
+        ZSTD_initFseState(&seqState.stateOffb, &seqState.DStream, dctx->OFTptr);
+        ZSTD_initFseState(&seqState.stateML, &seqState.DStream, dctx->MLTptr);
+
+        /* prepare in advance */
+        for (seqNb=0; (BIT_reloadDStream(&seqState.DStream) <= BIT_DStream_completed) && (seqNb<seqAdvance); seqNb++) {
+            sequences[seqNb] = ZSTD_decodeSequence(&seqState, isLongOffset, ZSTD_p_prefetch);
+            PREFETCH_L1(sequences[seqNb].match); PREFETCH_L1(sequences[seqNb].match + sequences[seqNb].matchLength - 1); /* note : it's safe to invoke PREFETCH() on any memory address, including invalid ones */
+        }
+        RETURN_ERROR_IF(seqNb<seqAdvance, corruption_detected, "");
+
+        /* decode and decompress */
+        for ( ; (BIT_reloadDStream(&(seqState.DStream)) <= BIT_DStream_completed) && (seqNb<nbSeq) ; seqNb++) {
+            seq_t const sequence = ZSTD_decodeSequence(&seqState, isLongOffset, ZSTD_p_prefetch);
+            size_t const oneSeqSize = ZSTD_execSequence(op, oend, sequences[(seqNb-ADVANCED_SEQS) & STORED_SEQS_MASK], &litPtr, litEnd, prefixStart, dictStart, dictEnd);
+#if defined(FUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION) && defined(FUZZING_ASSERT_VALID_SEQUENCE)
+            assert(!ZSTD_isError(oneSeqSize));
+            if (frame) ZSTD_assertValidSequence(dctx, op, oend, sequences[(seqNb-ADVANCED_SEQS) & STORED_SEQS_MASK], prefixStart, dictStart);
+#endif
+            if (ZSTD_isError(oneSeqSize)) return oneSeqSize;
+            PREFETCH_L1(sequence.match); PREFETCH_L1(sequence.match + sequence.matchLength - 1); /* note : it's safe to invoke PREFETCH() on any memory address, including invalid ones */
+            sequences[seqNb & STORED_SEQS_MASK] = sequence;
+            op += oneSeqSize;
+        }
+        RETURN_ERROR_IF(seqNb<nbSeq, corruption_detected, "");
+
+        /* finish queue */
+        seqNb -= seqAdvance;
+        for ( ; seqNb<nbSeq ; seqNb++) {
+            size_t const oneSeqSize = ZSTD_execSequence(op, oend, sequences[seqNb&STORED_SEQS_MASK], &litPtr, litEnd, prefixStart, dictStart, dictEnd);
+#if defined(FUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION) && defined(FUZZING_ASSERT_VALID_SEQUENCE)
+            assert(!ZSTD_isError(oneSeqSize));
+            if (frame) ZSTD_assertValidSequence(dctx, op, oend, sequences[seqNb&STORED_SEQS_MASK], prefixStart, dictStart);
+#endif
+            if (ZSTD_isError(oneSeqSize)) return oneSeqSize;
+            op += oneSeqSize;
+        }
+
+        /* save reps for next block */
+        { U32 i; for (i=0; i<ZSTD_REP_NUM; i++) dctx->entropy.rep[i] = (U32)(seqState.prevOffset[i]); }
+    }
+
+    /* last literal segment */
+    {   size_t const lastLLSize = litEnd - litPtr;
+        RETURN_ERROR_IF(lastLLSize > (size_t)(oend-op), dstSize_tooSmall, "");
+        if (op != NULL) {
+            ZSTD_memcpy(op, litPtr, lastLLSize);
+            op += lastLLSize;
+        }
+    }
+
+    return op-ostart;
+}
+
+static size_t
+ZSTD_decompressSequencesLong_default(ZSTD_DCtx* dctx,
+                                 void* dst, size_t maxDstSize,
+                           const void* seqStart, size_t seqSize, int nbSeq,
+                           const ZSTD_longOffset_e isLongOffset,
+                           const int frame)
+{
+    return ZSTD_decompressSequencesLong_body(dctx, dst, maxDstSize, seqStart, seqSize, nbSeq, isLongOffset, frame);
+}
+#endif /* ZSTD_FORCE_DECOMPRESS_SEQUENCES_SHORT */
+
+
+
+#if DYNAMIC_BMI2
+
+#ifndef ZSTD_FORCE_DECOMPRESS_SEQUENCES_LONG
+static TARGET_ATTRIBUTE("bmi2") size_t
+DONT_VECTORIZE
+ZSTD_decompressSequences_bmi2(ZSTD_DCtx* dctx,
+                                 void* dst, size_t maxDstSize,
+                           const void* seqStart, size_t seqSize, int nbSeq,
+                           const ZSTD_longOffset_e isLongOffset,
+                           const int frame)
+{
+    return ZSTD_decompressSequences_body(dctx, dst, maxDstSize, seqStart, seqSize, nbSeq, isLongOffset, frame);
+}
+#endif /* ZSTD_FORCE_DECOMPRESS_SEQUENCES_LONG */
+
+#ifndef ZSTD_FORCE_DECOMPRESS_SEQUENCES_SHORT
+static TARGET_ATTRIBUTE("bmi2") size_t
+ZSTD_decompressSequencesLong_bmi2(ZSTD_DCtx* dctx,
+                                 void* dst, size_t maxDstSize,
+                           const void* seqStart, size_t seqSize, int nbSeq,
+                           const ZSTD_longOffset_e isLongOffset,
+                           const int frame)
+{
+    return ZSTD_decompressSequencesLong_body(dctx, dst, maxDstSize, seqStart, seqSize, nbSeq, isLongOffset, frame);
+}
+#endif /* ZSTD_FORCE_DECOMPRESS_SEQUENCES_SHORT */
+
+#endif /* DYNAMIC_BMI2 */
+
+typedef size_t (*ZSTD_decompressSequences_t)(
+                            ZSTD_DCtx* dctx,
+                            void* dst, size_t maxDstSize,
+                            const void* seqStart, size_t seqSize, int nbSeq,
+                            const ZSTD_longOffset_e isLongOffset,
+                            const int frame);
+
+#ifndef ZSTD_FORCE_DECOMPRESS_SEQUENCES_LONG
+static size_t
+ZSTD_decompressSequences(ZSTD_DCtx* dctx, void* dst, size_t maxDstSize,
+                   const void* seqStart, size_t seqSize, int nbSeq,
+                   const ZSTD_longOffset_e isLongOffset,
+                   const int frame)
+{
+    DEBUGLOG(5, "ZSTD_decompressSequences");
+#if DYNAMIC_BMI2
+    if (dctx->bmi2) {
+        return ZSTD_decompressSequences_bmi2(dctx, dst, maxDstSize, seqStart, seqSize, nbSeq, isLongOffset, frame);
+    }
+#endif
+  return ZSTD_decompressSequences_default(dctx, dst, maxDstSize, seqStart, seqSize, nbSeq, isLongOffset, frame);
+}
+#endif /* ZSTD_FORCE_DECOMPRESS_SEQUENCES_LONG */
+
+
+#ifndef ZSTD_FORCE_DECOMPRESS_SEQUENCES_SHORT
+/* ZSTD_decompressSequencesLong() :
+ * decompression function triggered when a minimum share of offsets is considered "long",
+ * aka out of cache.
+ * note : "long" definition seems overloaded here, sometimes meaning "wider than bitstream register", and sometimes meaning "farther than memory cache distance".
+ * This function will try to mitigate main memory latency through the use of prefetching */
+static size_t
+ZSTD_decompressSequencesLong(ZSTD_DCtx* dctx,
+                             void* dst, size_t maxDstSize,
+                             const void* seqStart, size_t seqSize, int nbSeq,
+                             const ZSTD_longOffset_e isLongOffset,
+                             const int frame)
+{
+    DEBUGLOG(5, "ZSTD_decompressSequencesLong");
+#if DYNAMIC_BMI2
+    if (dctx->bmi2) {
+        return ZSTD_decompressSequencesLong_bmi2(dctx, dst, maxDstSize, seqStart, seqSize, nbSeq, isLongOffset, frame);
+    }
+#endif
+  return ZSTD_decompressSequencesLong_default(dctx, dst, maxDstSize, seqStart, seqSize, nbSeq, isLongOffset, frame);
+}
+#endif /* ZSTD_FORCE_DECOMPRESS_SEQUENCES_SHORT */
+
+
+
+#if !defined(ZSTD_FORCE_DECOMPRESS_SEQUENCES_SHORT) && \
+    !defined(ZSTD_FORCE_DECOMPRESS_SEQUENCES_LONG)
+/* ZSTD_getLongOffsetsShare() :
+ * condition : offTable must be valid
+ * @return : "share" of long offsets (arbitrarily defined as > (1<<23))
+ *           compared to maximum possible of (1<<OffFSELog) */
+static unsigned
+ZSTD_getLongOffsetsShare(const ZSTD_seqSymbol* offTable)
+{
+    const void* ptr = offTable;
+    U32 const tableLog = ((const ZSTD_seqSymbol_header*)ptr)[0].tableLog;
+    const ZSTD_seqSymbol* table = offTable + 1;
+    U32 const max = 1 << tableLog;
+    U32 u, total = 0;
+    DEBUGLOG(5, "ZSTD_getLongOffsetsShare: (tableLog=%u)", tableLog);
+
+    assert(max <= (1 << OffFSELog));  /* max not too large */
+    for (u=0; u<max; u++) {
+        if (table[u].nbAdditionalBits > 22) total += 1;
+    }
+
+    assert(tableLog <= OffFSELog);
+    total <<= (OffFSELog - tableLog);  /* scale to OffFSELog */
+
+    return total;
+}
+#endif
+
+size_t
+ZSTD_decompressBlock_internal(ZSTD_DCtx* dctx,
+                              void* dst, size_t dstCapacity,
+                        const void* src, size_t srcSize, const int frame)
+{   /* blockType == blockCompressed */
+    const BYTE* ip = (const BYTE*)src;
+    /* isLongOffset must be true if there are long offsets.
+     * Offsets are long if they are larger than 2^STREAM_ACCUMULATOR_MIN.
+     * We don't expect that to be the case in 64-bit mode.
+     * In block mode, window size is not known, so we have to be conservative.
+     * (note: but it could be evaluated from current-lowLimit)
+     */
+    ZSTD_longOffset_e const isLongOffset = (ZSTD_longOffset_e)(MEM_32bits() && (!frame || (dctx->fParams.windowSize > (1ULL << STREAM_ACCUMULATOR_MIN))));
+    DEBUGLOG(5, "ZSTD_decompressBlock_internal (size : %u)", (U32)srcSize);
+
+    RETURN_ERROR_IF(srcSize >= ZSTD_BLOCKSIZE_MAX, srcSize_wrong, "");
+
+    /* Decode literals section */
+    {   size_t const litCSize = ZSTD_decodeLiteralsBlock(dctx, src, srcSize);
+        DEBUGLOG(5, "ZSTD_decodeLiteralsBlock : %u", (U32)litCSize);
+        if (ZSTD_isError(litCSize)) return litCSize;
+        ip += litCSize;
+        srcSize -= litCSize;
+    }
+
+    /* Build Decoding Tables */
+    {
+        /* These macros control at build-time which decompressor implementation
+         * we use. If neither is defined, we do some inspection and dispatch at
+         * runtime.
+         */
+#if !defined(ZSTD_FORCE_DECOMPRESS_SEQUENCES_SHORT) && \
+    !defined(ZSTD_FORCE_DECOMPRESS_SEQUENCES_LONG)
+        int usePrefetchDecoder = dctx->ddictIsCold;
+#endif
+        int nbSeq;
+        size_t const seqHSize = ZSTD_decodeSeqHeaders(dctx, &nbSeq, ip, srcSize);
+        if (ZSTD_isError(seqHSize)) return seqHSize;
+        ip += seqHSize;
+        srcSize -= seqHSize;
+
+        RETURN_ERROR_IF(dst == NULL && nbSeq > 0, dstSize_tooSmall, "NULL not handled");
+
+#if !defined(ZSTD_FORCE_DECOMPRESS_SEQUENCES_SHORT) && \
+    !defined(ZSTD_FORCE_DECOMPRESS_SEQUENCES_LONG)
+        if ( !usePrefetchDecoder
+          && (!frame || (dctx->fParams.windowSize > (1<<24)))
+          && (nbSeq>ADVANCED_SEQS) ) {  /* could probably use a larger nbSeq limit */
+            U32 const shareLongOffsets = ZSTD_getLongOffsetsShare(dctx->OFTptr);
+            U32 const minShare = MEM_64bits() ? 7 : 20; /* heuristic values, correspond to 2.73% and 7.81% */
+            usePrefetchDecoder = (shareLongOffsets >= minShare);
+        }
+#endif
+
+        dctx->ddictIsCold = 0;
+
+#if !defined(ZSTD_FORCE_DECOMPRESS_SEQUENCES_SHORT) && \
+    !defined(ZSTD_FORCE_DECOMPRESS_SEQUENCES_LONG)
+        if (usePrefetchDecoder)
+#endif
+#ifndef ZSTD_FORCE_DECOMPRESS_SEQUENCES_SHORT
+            return ZSTD_decompressSequencesLong(dctx, dst, dstCapacity, ip, srcSize, nbSeq, isLongOffset, frame);
+#endif
+
+#ifndef ZSTD_FORCE_DECOMPRESS_SEQUENCES_LONG
+        /* else */
+        return ZSTD_decompressSequences(dctx, dst, dstCapacity, ip, srcSize, nbSeq, isLongOffset, frame);
+#endif
+    }
+}
+
+
+void ZSTD_checkContinuity(ZSTD_DCtx* dctx, const void* dst, size_t dstSize)
+{
+    if (dst != dctx->previousDstEnd && dstSize > 0) {   /* not contiguous */
+        dctx->dictEnd = dctx->previousDstEnd;
+        dctx->virtualStart = (const char*)dst - ((const char*)(dctx->previousDstEnd) - (const char*)(dctx->prefixStart));
+        dctx->prefixStart = dst;
+        dctx->previousDstEnd = dst;
+    }
+}
+
+
+size_t ZSTD_decompressBlock(ZSTD_DCtx* dctx,
+                            void* dst, size_t dstCapacity,
+                      const void* src, size_t srcSize)
+{
+    size_t dSize;
+    ZSTD_checkContinuity(dctx, dst, dstCapacity);
+    dSize = ZSTD_decompressBlock_internal(dctx, dst, dstCapacity, src, srcSize, /* frame */ 0);
+    dctx->previousDstEnd = (char*)dst + dSize;
+    return dSize;
+}
diff --git a/lib/zstd/decompress/zstd_decompress_block.h b/lib/zstd/decompress/zstd_decompress_block.h
new file mode 100644
index 000000000000..e7f5f6689459
--- /dev/null
+++ b/lib/zstd/decompress/zstd_decompress_block.h
@@ -0,0 +1,62 @@
+/*
+ * Copyright (c) Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+
+#ifndef ZSTD_DEC_BLOCK_H
+#define ZSTD_DEC_BLOCK_H
+
+/*-*******************************************************
+ *  Dependencies
+ *********************************************************/
+#include "../common/zstd_deps.h"   /* size_t */
+#include <linux/zstd.h>    /* DCtx, and some public functions */
+#include "../common/zstd_internal.h"  /* blockProperties_t, and some public functions */
+#include "zstd_decompress_internal.h"  /* ZSTD_seqSymbol */
+
+
+/* ===   Prototypes   === */
+
+/* note: prototypes already published within `zstd.h` :
+ * ZSTD_decompressBlock()
+ */
+
+/* note: prototypes already published within `zstd_internal.h` :
+ * ZSTD_getcBlockSize()
+ * ZSTD_decodeSeqHeaders()
+ */
+
+
+/* ZSTD_decompressBlock_internal() :
+ * decompress block, starting at `src`,
+ * into destination buffer `dst`.
+ * @return : decompressed block size,
+ *           or an error code (which can be tested using ZSTD_isError())
+ */
+size_t ZSTD_decompressBlock_internal(ZSTD_DCtx* dctx,
+                               void* dst, size_t dstCapacity,
+                         const void* src, size_t srcSize, const int frame);
+
+/* ZSTD_buildFSETable() :
+ * generate FSE decoding table for one symbol (ll, ml or off)
+ * this function must be called with valid parameters only
+ * (dt is large enough, normalizedCounter distribution total is a power of 2, max is within range, etc.)
+ * in which case it cannot fail.
+ * The workspace must be 4-byte aligned and at least ZSTD_BUILD_FSE_TABLE_WKSP_SIZE bytes, which is
+ * defined in zstd_decompress_internal.h.
+ * Internal use only.
+ */
+void ZSTD_buildFSETable(ZSTD_seqSymbol* dt,
+             const short* normalizedCounter, unsigned maxSymbolValue,
+             const U32* baseValue, const U32* nbAdditionalBits,
+                   unsigned tableLog, void* wksp, size_t wkspSize,
+                   int bmi2);
+
+
+#endif /* ZSTD_DEC_BLOCK_H */
diff --git a/lib/zstd/decompress/zstd_decompress_internal.h b/lib/zstd/decompress/zstd_decompress_internal.h
new file mode 100644
index 000000000000..4b9052f68755
--- /dev/null
+++ b/lib/zstd/decompress/zstd_decompress_internal.h
@@ -0,0 +1,202 @@
+/*
+ * Copyright (c) Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+
+/* zstd_decompress_internal:
+ * objects and definitions shared within lib/decompress modules */
+
+ #ifndef ZSTD_DECOMPRESS_INTERNAL_H
+ #define ZSTD_DECOMPRESS_INTERNAL_H
+
+
+/*-*******************************************************
+ *  Dependencies
+ *********************************************************/
+#include "../common/mem.h"             /* BYTE, U16, U32 */
+#include "../common/zstd_internal.h"   /* ZSTD_seqSymbol */
+
+
+
+/*-*******************************************************
+ *  Constants
+ *********************************************************/
+static UNUSED_ATTR const U32 LL_base[MaxLL+1] = {
+                 0,    1,    2,     3,     4,     5,     6,      7,
+                 8,    9,   10,    11,    12,    13,    14,     15,
+                16,   18,   20,    22,    24,    28,    32,     40,
+                48,   64, 0x80, 0x100, 0x200, 0x400, 0x800, 0x1000,
+                0x2000, 0x4000, 0x8000, 0x10000 };
+
+static UNUSED_ATTR const U32 OF_base[MaxOff+1] = {
+                 0,        1,       1,       5,     0xD,     0x1D,     0x3D,     0x7D,
+                 0xFD,   0x1FD,   0x3FD,   0x7FD,   0xFFD,   0x1FFD,   0x3FFD,   0x7FFD,
+                 0xFFFD, 0x1FFFD, 0x3FFFD, 0x7FFFD, 0xFFFFD, 0x1FFFFD, 0x3FFFFD, 0x7FFFFD,
+                 0xFFFFFD, 0x1FFFFFD, 0x3FFFFFD, 0x7FFFFFD, 0xFFFFFFD, 0x1FFFFFFD, 0x3FFFFFFD, 0x7FFFFFFD };
+
+static UNUSED_ATTR const U32 OF_bits[MaxOff+1] = {
+                     0,  1,  2,  3,  4,  5,  6,  7,
+                     8,  9, 10, 11, 12, 13, 14, 15,
+                    16, 17, 18, 19, 20, 21, 22, 23,
+                    24, 25, 26, 27, 28, 29, 30, 31 };
+
+static UNUSED_ATTR const U32 ML_base[MaxML+1] = {
+                     3,  4,  5,    6,     7,     8,     9,    10,
+                    11, 12, 13,   14,    15,    16,    17,    18,
+                    19, 20, 21,   22,    23,    24,    25,    26,
+                    27, 28, 29,   30,    31,    32,    33,    34,
+                    35, 37, 39,   41,    43,    47,    51,    59,
+                    67, 83, 99, 0x83, 0x103, 0x203, 0x403, 0x803,
+                    0x1003, 0x2003, 0x4003, 0x8003, 0x10003 };
+
+
+/*-*******************************************************
+ *  Decompression types
+ *********************************************************/
+ typedef struct {
+     U32 fastMode;
+     U32 tableLog;
+ } ZSTD_seqSymbol_header;
+
+ typedef struct {
+     U16  nextState;
+     BYTE nbAdditionalBits;
+     BYTE nbBits;
+     U32  baseValue;
+ } ZSTD_seqSymbol;
+
+ #define SEQSYMBOL_TABLE_SIZE(log)   (1 + (1 << (log)))
+
+#define ZSTD_BUILD_FSE_TABLE_WKSP_SIZE (sizeof(S16) * (MaxSeq + 1) + (1u << MaxFSELog) + sizeof(U64))
+#define ZSTD_BUILD_FSE_TABLE_WKSP_SIZE_U32 ((ZSTD_BUILD_FSE_TABLE_WKSP_SIZE + sizeof(U32) - 1) / sizeof(U32))
+
+typedef struct {
+    ZSTD_seqSymbol LLTable[SEQSYMBOL_TABLE_SIZE(LLFSELog)];    /* Note : Space reserved for FSE Tables */
+    ZSTD_seqSymbol OFTable[SEQSYMBOL_TABLE_SIZE(OffFSELog)];   /* is also used as temporary workspace while building hufTable during DDict creation */
+    ZSTD_seqSymbol MLTable[SEQSYMBOL_TABLE_SIZE(MLFSELog)];    /* and therefore must be at least HUF_DECOMPRESS_WORKSPACE_SIZE large */
+    HUF_DTable hufTable[HUF_DTABLE_SIZE(HufLog)];  /* can accommodate HUF_decompress4X */
+    U32 rep[ZSTD_REP_NUM];
+    U32 workspace[ZSTD_BUILD_FSE_TABLE_WKSP_SIZE_U32];
+} ZSTD_entropyDTables_t;
+
+typedef enum { ZSTDds_getFrameHeaderSize, ZSTDds_decodeFrameHeader,
+               ZSTDds_decodeBlockHeader, ZSTDds_decompressBlock,
+               ZSTDds_decompressLastBlock, ZSTDds_checkChecksum,
+               ZSTDds_decodeSkippableHeader, ZSTDds_skipFrame } ZSTD_dStage;
+
+typedef enum { zdss_init=0, zdss_loadHeader,
+               zdss_read, zdss_load, zdss_flush } ZSTD_dStreamStage;
+
+typedef enum {
+    ZSTD_use_indefinitely = -1,  /* Use the dictionary indefinitely */
+    ZSTD_dont_use = 0,           /* Do not use the dictionary (if one exists free it) */
+    ZSTD_use_once = 1            /* Use the dictionary once and set to ZSTD_dont_use */
+} ZSTD_dictUses_e;
+
+/* Hashset for storing references to multiple ZSTD_DDict within ZSTD_DCtx */
+typedef struct {
+    const ZSTD_DDict** ddictPtrTable;
+    size_t ddictPtrTableSize;
+    size_t ddictPtrCount;
+} ZSTD_DDictHashSet;
+
+struct ZSTD_DCtx_s
+{
+    const ZSTD_seqSymbol* LLTptr;
+    const ZSTD_seqSymbol* MLTptr;
+    const ZSTD_seqSymbol* OFTptr;
+    const HUF_DTable* HUFptr;
+    ZSTD_entropyDTables_t entropy;
+    U32 workspace[HUF_DECOMPRESS_WORKSPACE_SIZE_U32];   /* space needed when building huffman tables */
+    const void* previousDstEnd;   /* detect continuity */
+    const void* prefixStart;      /* start of current segment */
+    const void* virtualStart;     /* virtual start of previous segment if it was just before current one */
+    const void* dictEnd;          /* end of previous segment */
+    size_t expected;
+    ZSTD_frameHeader fParams;
+    U64 processedCSize;
+    U64 decodedSize;
+    blockType_e bType;            /* used in ZSTD_decompressContinue(), store blockType between block header decoding and block decompression stages */
+    ZSTD_dStage stage;
+    U32 litEntropy;
+    U32 fseEntropy;
+    struct xxh64_state xxhState;
+    size_t headerSize;
+    ZSTD_format_e format;
+    ZSTD_forceIgnoreChecksum_e forceIgnoreChecksum;   /* User specified: if == 1, will ignore checksums in compressed frame. Default == 0 */
+    U32 validateChecksum;         /* if == 1, will validate checksum. Is == 1 if (fParams.checksumFlag == 1) and (forceIgnoreChecksum == 0). */
+    const BYTE* litPtr;
+    ZSTD_customMem customMem;
+    size_t litSize;
+    size_t rleSize;
+    size_t staticSize;
+    int bmi2;                     /* == 1 if the CPU supports BMI2 and 0 otherwise. CPU support is determined dynamically once per context lifetime. */
+
+    /* dictionary */
+    ZSTD_DDict* ddictLocal;
+    const ZSTD_DDict* ddict;     /* set by ZSTD_initDStream_usingDDict(), or ZSTD_DCtx_refDDict() */
+    U32 dictID;
+    int ddictIsCold;             /* if == 1 : dictionary is "new" for working context, and presumed "cold" (not in cpu cache) */
+    ZSTD_dictUses_e dictUses;
+    ZSTD_DDictHashSet* ddictSet;                    /* Hash set for multiple ddicts */
+    ZSTD_refMultipleDDicts_e refMultipleDDicts;     /* User specified: if == 1, will allow references to multiple DDicts. Default == 0 (disabled) */
+
+    /* streaming */
+    ZSTD_dStreamStage streamStage;
+    char*  inBuff;
+    size_t inBuffSize;
+    size_t inPos;
+    size_t maxWindowSize;
+    char*  outBuff;
+    size_t outBuffSize;
+    size_t outStart;
+    size_t outEnd;
+    size_t lhSize;
+    void* legacyContext;
+    U32 previousLegacyVersion;
+    U32 legacyVersion;
+    U32 hostageByte;
+    int noForwardProgress;
+    ZSTD_bufferMode_e outBufferMode;
+    ZSTD_outBuffer expectedOutBuffer;
+
+    /* workspace */
+    BYTE litBuffer[ZSTD_BLOCKSIZE_MAX + WILDCOPY_OVERLENGTH];
+    BYTE headerBuffer[ZSTD_FRAMEHEADERSIZE_MAX];
+
+    size_t oversizedDuration;
+
+#ifdef FUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION
+    void const* dictContentBeginForFuzzing;
+    void const* dictContentEndForFuzzing;
+#endif
+
+    /* Tracing */
+};  /* typedef'd to ZSTD_DCtx within "zstd.h" */
+
+
+/*-*******************************************************
+ *  Shared internal functions
+ *********************************************************/
+
+/*! ZSTD_loadDEntropy() :
+ *  dict : must point at beginning of a valid zstd dictionary.
+ * @return : size of dictionary header (size of magic number + dict ID + entropy tables) */
+size_t ZSTD_loadDEntropy(ZSTD_entropyDTables_t* entropy,
+                   const void* const dict, size_t const dictSize);
+
+/*! ZSTD_checkContinuity() :
+ *  check if next `dst` follows previous position, where decompression ended.
+ *  If yes, do nothing (continue on current segment).
+ *  If not, classify previous segment as "external dictionary", and start a new segment.
+ *  This function cannot fail. */
+void ZSTD_checkContinuity(ZSTD_DCtx* dctx, const void* dst, size_t dstSize);
+
+
+#endif /* ZSTD_DECOMPRESS_INTERNAL_H */
diff --git a/lib/zstd/decompress_sources.h b/lib/zstd/decompress_sources.h
new file mode 100644
index 000000000000..0fbec508f285
--- /dev/null
+++ b/lib/zstd/decompress_sources.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause */
+/*
+ * Copyright (c) Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+/*
+ * This file includes every .c file needed for decompression.
+ * It is used by lib/decompress_unzstd.c to include the decompression
+ * source into the translation-unit, so it can be used for kernel
+ * decompression.
+ */
+
+#include "common/debug.c"
+#include "common/entropy_common.c"
+#include "common/error_private.c"
+#include "common/fse_decompress.c"
+#include "common/zstd_common.c"
+#include "decompress/huf_decompress.c"
+#include "decompress/zstd_ddict.c"
+#include "decompress/zstd_decompress.c"
+#include "decompress/zstd_decompress_block.c"
+#include "zstd_decompress_module.c"
diff --git a/lib/zstd/entropy_common.c b/lib/zstd/entropy_common.c
deleted file mode 100644
index 2b0a643c32c4..000000000000
--- a/lib/zstd/entropy_common.c
+++ /dev/null
@@ -1,243 +0,0 @@
-/*
- * Common functions of New Generation Entropy library
- * Copyright (C) 2016, Yann Collet.
- *
- * BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are
- * met:
- *
- *   * Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- *   * Redistributions in binary form must reproduce the above
- * copyright notice, this list of conditions and the following disclaimer
- * in the documentation and/or other materials provided with the
- * distribution.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * 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. This program is dual-licensed; you may select
- * either version 2 of the GNU General Public License ("GPL") or BSD license
- * ("BSD").
- *
- * You can contact the author at :
- * - Source repository : https://github.com/Cyan4973/FiniteStateEntropy
- */
-
-/* *************************************
-*  Dependencies
-***************************************/
-#include "error_private.h" /* ERR_*, ERROR */
-#include "fse.h"
-#include "huf.h"
-#include "mem.h"
-
-/*===   Version   ===*/
-unsigned FSE_versionNumber(void) { return FSE_VERSION_NUMBER; }
-
-/*===   Error Management   ===*/
-unsigned FSE_isError(size_t code) { return ERR_isError(code); }
-
-unsigned HUF_isError(size_t code) { return ERR_isError(code); }
-
-/*-**************************************************************
-*  FSE NCount encoding-decoding
-****************************************************************/
-size_t FSE_readNCount(short *normalizedCounter, unsigned *maxSVPtr, unsigned *tableLogPtr, const void *headerBuffer, size_t hbSize)
-{
-	const BYTE *const istart = (const BYTE *)headerBuffer;
-	const BYTE *const iend = istart + hbSize;
-	const BYTE *ip = istart;
-	int nbBits;
-	int remaining;
-	int threshold;
-	U32 bitStream;
-	int bitCount;
-	unsigned charnum = 0;
-	int previous0 = 0;
-
-	if (hbSize < 4)
-		return ERROR(srcSize_wrong);
-	bitStream = ZSTD_readLE32(ip);
-	nbBits = (bitStream & 0xF) + FSE_MIN_TABLELOG; /* extract tableLog */
-	if (nbBits > FSE_TABLELOG_ABSOLUTE_MAX)
-		return ERROR(tableLog_tooLarge);
-	bitStream >>= 4;
-	bitCount = 4;
-	*tableLogPtr = nbBits;
-	remaining = (1 << nbBits) + 1;
-	threshold = 1 << nbBits;
-	nbBits++;
-
-	while ((remaining > 1) & (charnum <= *maxSVPtr)) {
-		if (previous0) {
-			unsigned n0 = charnum;
-			while ((bitStream & 0xFFFF) == 0xFFFF) {
-				n0 += 24;
-				if (ip < iend - 5) {
-					ip += 2;
-					bitStream = ZSTD_readLE32(ip) >> bitCount;
-				} else {
-					bitStream >>= 16;
-					bitCount += 16;
-				}
-			}
-			while ((bitStream & 3) == 3) {
-				n0 += 3;
-				bitStream >>= 2;
-				bitCount += 2;
-			}
-			n0 += bitStream & 3;
-			bitCount += 2;
-			if (n0 > *maxSVPtr)
-				return ERROR(maxSymbolValue_tooSmall);
-			while (charnum < n0)
-				normalizedCounter[charnum++] = 0;
-			if ((ip <= iend - 7) || (ip + (bitCount >> 3) <= iend - 4)) {
-				ip += bitCount >> 3;
-				bitCount &= 7;
-				bitStream = ZSTD_readLE32(ip) >> bitCount;
-			} else {
-				bitStream >>= 2;
-			}
-		}
-		{
-			int const max = (2 * threshold - 1) - remaining;
-			int count;
-
-			if ((bitStream & (threshold - 1)) < (U32)max) {
-				count = bitStream & (threshold - 1);
-				bitCount += nbBits - 1;
-			} else {
-				count = bitStream & (2 * threshold - 1);
-				if (count >= threshold)
-					count -= max;
-				bitCount += nbBits;
-			}
-
-			count--;				 /* extra accuracy */
-			remaining -= count < 0 ? -count : count; /* -1 means +1 */
-			normalizedCounter[charnum++] = (short)count;
-			previous0 = !count;
-			while (remaining < threshold) {
-				nbBits--;
-				threshold >>= 1;
-			}
-
-			if ((ip <= iend - 7) || (ip + (bitCount >> 3) <= iend - 4)) {
-				ip += bitCount >> 3;
-				bitCount &= 7;
-			} else {
-				bitCount -= (int)(8 * (iend - 4 - ip));
-				ip = iend - 4;
-			}
-			bitStream = ZSTD_readLE32(ip) >> (bitCount & 31);
-		}
-	} /* while ((remaining>1) & (charnum<=*maxSVPtr)) */
-	if (remaining != 1)
-		return ERROR(corruption_detected);
-	if (bitCount > 32)
-		return ERROR(corruption_detected);
-	*maxSVPtr = charnum - 1;
-
-	ip += (bitCount + 7) >> 3;
-	return ip - istart;
-}
-
-/*! HUF_readStats() :
-	Read compact Huffman tree, saved by HUF_writeCTable().
-	`huffWeight` is destination buffer.
-	`rankStats` is assumed to be a table of at least HUF_TABLELOG_MAX U32.
-	@return : size read from `src` , or an error Code .
-	Note : Needed by HUF_readCTable() and HUF_readDTableX?() .
-*/
-size_t HUF_readStats_wksp(BYTE *huffWeight, size_t hwSize, U32 *rankStats, U32 *nbSymbolsPtr, U32 *tableLogPtr, const void *src, size_t srcSize, void *workspace, size_t workspaceSize)
-{
-	U32 weightTotal;
-	const BYTE *ip = (const BYTE *)src;
-	size_t iSize;
-	size_t oSize;
-
-	if (!srcSize)
-		return ERROR(srcSize_wrong);
-	iSize = ip[0];
-	/* memset(huffWeight, 0, hwSize);   */ /* is not necessary, even though some analyzer complain ... */
-
-	if (iSize >= 128) { /* special header */
-		oSize = iSize - 127;
-		iSize = ((oSize + 1) / 2);
-		if (iSize + 1 > srcSize)
-			return ERROR(srcSize_wrong);
-		if (oSize >= hwSize)
-			return ERROR(corruption_detected);
-		ip += 1;
-		{
-			U32 n;
-			for (n = 0; n < oSize; n += 2) {
-				huffWeight[n] = ip[n / 2] >> 4;
-				huffWeight[n + 1] = ip[n / 2] & 15;
-			}
-		}
-	} else {						 /* header compressed with FSE (normal case) */
-		if (iSize + 1 > srcSize)
-			return ERROR(srcSize_wrong);
-		oSize = FSE_decompress_wksp(huffWeight, hwSize - 1, ip + 1, iSize, 6, workspace, workspaceSize); /* max (hwSize-1) values decoded, as last one is implied */
-		if (FSE_isError(oSize))
-			return oSize;
-	}
-
-	/* collect weight stats */
-	memset(rankStats, 0, (HUF_TABLELOG_MAX + 1) * sizeof(U32));
-	weightTotal = 0;
-	{
-		U32 n;
-		for (n = 0; n < oSize; n++) {
-			if (huffWeight[n] >= HUF_TABLELOG_MAX)
-				return ERROR(corruption_detected);
-			rankStats[huffWeight[n]]++;
-			weightTotal += (1 << huffWeight[n]) >> 1;
-		}
-	}
-	if (weightTotal == 0)
-		return ERROR(corruption_detected);
-
-	/* get last non-null symbol weight (implied, total must be 2^n) */
-	{
-		U32 const tableLog = BIT_highbit32(weightTotal) + 1;
-		if (tableLog > HUF_TABLELOG_MAX)
-			return ERROR(corruption_detected);
-		*tableLogPtr = tableLog;
-		/* determine last weight */
-		{
-			U32 const total = 1 << tableLog;
-			U32 const rest = total - weightTotal;
-			U32 const verif = 1 << BIT_highbit32(rest);
-			U32 const lastWeight = BIT_highbit32(rest) + 1;
-			if (verif != rest)
-				return ERROR(corruption_detected); /* last value must be a clean power of 2 */
-			huffWeight[oSize] = (BYTE)lastWeight;
-			rankStats[lastWeight]++;
-		}
-	}
-
-	/* check tree construction validity */
-	if ((rankStats[1] < 2) || (rankStats[1] & 1))
-		return ERROR(corruption_detected); /* by construction : at least 2 elts of rank 1, must be even */
-
-	/* results */
-	*nbSymbolsPtr = (U32)(oSize + 1);
-	return iSize + 1;
-}
diff --git a/lib/zstd/error_private.h b/lib/zstd/error_private.h
deleted file mode 100644
index 1a60b31f706c..000000000000
--- a/lib/zstd/error_private.h
+++ /dev/null
@@ -1,53 +0,0 @@
-/**
- * Copyright (c) 2016-present, Yann Collet, Facebook, Inc.
- * All rights reserved.
- *
- * This source code is licensed under the BSD-style license found in the
- * LICENSE file in the root directory of https://github.com/facebook/zstd.
- * An additional grant of patent rights can be found in the PATENTS file in the
- * same directory.
- *
- * 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. This program is dual-licensed; you may select
- * either version 2 of the GNU General Public License ("GPL") or BSD license
- * ("BSD").
- */
-
-/* Note : this module is expected to remain private, do not expose it */
-
-#ifndef ERROR_H_MODULE
-#define ERROR_H_MODULE
-
-/* ****************************************
-*  Dependencies
-******************************************/
-#include <linux/types.h> /* size_t */
-#include <linux/zstd.h>  /* enum list */
-
-/* ****************************************
-*  Compiler-specific
-******************************************/
-#define ERR_STATIC static __attribute__((unused))
-
-/*-****************************************
-*  Customization (error_public.h)
-******************************************/
-typedef ZSTD_ErrorCode ERR_enum;
-#define PREFIX(name) ZSTD_error_##name
-
-/*-****************************************
-*  Error codes handling
-******************************************/
-#define ERROR(name) ((size_t)-PREFIX(name))
-
-ERR_STATIC unsigned ERR_isError(size_t code) { return (code > ERROR(maxCode)); }
-
-ERR_STATIC ERR_enum ERR_getErrorCode(size_t code)
-{
-	if (!ERR_isError(code))
-		return (ERR_enum)0;
-	return (ERR_enum)(0 - code);
-}
-
-#endif /* ERROR_H_MODULE */
diff --git a/lib/zstd/fse.h b/lib/zstd/fse.h
deleted file mode 100644
index 7460ab04b191..000000000000
--- a/lib/zstd/fse.h
+++ /dev/null
@@ -1,575 +0,0 @@
-/*
- * FSE : Finite State Entropy codec
- * Public Prototypes declaration
- * Copyright (C) 2013-2016, Yann Collet.
- *
- * BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are
- * met:
- *
- *   * Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- *   * Redistributions in binary form must reproduce the above
- * copyright notice, this list of conditions and the following disclaimer
- * in the documentation and/or other materials provided with the
- * distribution.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * 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. This program is dual-licensed; you may select
- * either version 2 of the GNU General Public License ("GPL") or BSD license
- * ("BSD").
- *
- * You can contact the author at :
- * - Source repository : https://github.com/Cyan4973/FiniteStateEntropy
- */
-#ifndef FSE_H
-#define FSE_H
-
-/*-*****************************************
-*  Dependencies
-******************************************/
-#include <linux/types.h> /* size_t, ptrdiff_t */
-
-/*-*****************************************
-*  FSE_PUBLIC_API : control library symbols visibility
-******************************************/
-#define FSE_PUBLIC_API
-
-/*------   Version   ------*/
-#define FSE_VERSION_MAJOR 0
-#define FSE_VERSION_MINOR 9
-#define FSE_VERSION_RELEASE 0
-
-#define FSE_LIB_VERSION FSE_VERSION_MAJOR.FSE_VERSION_MINOR.FSE_VERSION_RELEASE
-#define FSE_QUOTE(str) #str
-#define FSE_EXPAND_AND_QUOTE(str) FSE_QUOTE(str)
-#define FSE_VERSION_STRING FSE_EXPAND_AND_QUOTE(FSE_LIB_VERSION)
-
-#define FSE_VERSION_NUMBER (FSE_VERSION_MAJOR * 100 * 100 + FSE_VERSION_MINOR * 100 + FSE_VERSION_RELEASE)
-FSE_PUBLIC_API unsigned FSE_versionNumber(void); /**< library version number; to be used when checking dll version */
-
-/*-*****************************************
-*  Tool functions
-******************************************/
-FSE_PUBLIC_API size_t FSE_compressBound(size_t size); /* maximum compressed size */
-
-/* Error Management */
-FSE_PUBLIC_API unsigned FSE_isError(size_t code); /* tells if a return value is an error code */
-
-/*-*****************************************
-*  FSE detailed API
-******************************************/
-/*!
-FSE_compress() does the following:
-1. count symbol occurrence from source[] into table count[]
-2. normalize counters so that sum(count[]) == Power_of_2 (2^tableLog)
-3. save normalized counters to memory buffer using writeNCount()
-4. build encoding table 'CTable' from normalized counters
-5. encode the data stream using encoding table 'CTable'
-
-FSE_decompress() does the following:
-1. read normalized counters with readNCount()
-2. build decoding table 'DTable' from normalized counters
-3. decode the data stream using decoding table 'DTable'
-
-The following API allows targeting specific sub-functions for advanced tasks.
-For example, it's possible to compress several blocks using the same 'CTable',
-or to save and provide normalized distribution using external method.
-*/
-
-/* *** COMPRESSION *** */
-/*! FSE_optimalTableLog():
-	dynamically downsize 'tableLog' when conditions are met.
-	It saves CPU time, by using smaller tables, while preserving or even improving compression ratio.
-	@return : recommended tableLog (necessarily <= 'maxTableLog') */
-FSE_PUBLIC_API unsigned FSE_optimalTableLog(unsigned maxTableLog, size_t srcSize, unsigned maxSymbolValue);
-
-/*! FSE_normalizeCount():
-	normalize counts so that sum(count[]) == Power_of_2 (2^tableLog)
-	'normalizedCounter' is a table of short, of minimum size (maxSymbolValue+1).
-	@return : tableLog,
-			  or an errorCode, which can be tested using FSE_isError() */
-FSE_PUBLIC_API size_t FSE_normalizeCount(short *normalizedCounter, unsigned tableLog, const unsigned *count, size_t srcSize, unsigned maxSymbolValue);
-
-/*! FSE_NCountWriteBound():
-	Provides the maximum possible size of an FSE normalized table, given 'maxSymbolValue' and 'tableLog'.
-	Typically useful for allocation purpose. */
-FSE_PUBLIC_API size_t FSE_NCountWriteBound(unsigned maxSymbolValue, unsigned tableLog);
-
-/*! FSE_writeNCount():
-	Compactly save 'normalizedCounter' into 'buffer'.
-	@return : size of the compressed table,
-			  or an errorCode, which can be tested using FSE_isError(). */
-FSE_PUBLIC_API size_t FSE_writeNCount(void *buffer, size_t bufferSize, const short *normalizedCounter, unsigned maxSymbolValue, unsigned tableLog);
-
-/*! Constructor and Destructor of FSE_CTable.
-	Note that FSE_CTable size depends on 'tableLog' and 'maxSymbolValue' */
-typedef unsigned FSE_CTable; /* don't allocate that. It's only meant to be more restrictive than void* */
-
-/*! FSE_compress_usingCTable():
-	Compress `src` using `ct` into `dst` which must be already allocated.
-	@return : size of compressed data (<= `dstCapacity`),
-			  or 0 if compressed data could not fit into `dst`,
-			  or an errorCode, which can be tested using FSE_isError() */
-FSE_PUBLIC_API size_t FSE_compress_usingCTable(void *dst, size_t dstCapacity, const void *src, size_t srcSize, const FSE_CTable *ct);
-
-/*!
-Tutorial :
-----------
-The first step is to count all symbols. FSE_count() does this job very fast.
-Result will be saved into 'count', a table of unsigned int, which must be already allocated, and have 'maxSymbolValuePtr[0]+1' cells.
-'src' is a table of bytes of size 'srcSize'. All values within 'src' MUST be <= maxSymbolValuePtr[0]
-maxSymbolValuePtr[0] will be updated, with its real value (necessarily <= original value)
-FSE_count() will return the number of occurrence of the most frequent symbol.
-This can be used to know if there is a single symbol within 'src', and to quickly evaluate its compressibility.
-If there is an error, the function will return an ErrorCode (which can be tested using FSE_isError()).
-
-The next step is to normalize the frequencies.
-FSE_normalizeCount() will ensure that sum of frequencies is == 2 ^'tableLog'.
-It also guarantees a minimum of 1 to any Symbol with frequency >= 1.
-You can use 'tableLog'==0 to mean "use default tableLog value".
-If you are unsure of which tableLog value to use, you can ask FSE_optimalTableLog(),
-which will provide the optimal valid tableLog given sourceSize, maxSymbolValue, and a user-defined maximum (0 means "default").
-
-The result of FSE_normalizeCount() will be saved into a table,
-called 'normalizedCounter', which is a table of signed short.
-'normalizedCounter' must be already allocated, and have at least 'maxSymbolValue+1' cells.
-The return value is tableLog if everything proceeded as expected.
-It is 0 if there is a single symbol within distribution.
-If there is an error (ex: invalid tableLog value), the function will return an ErrorCode (which can be tested using FSE_isError()).
-
-'normalizedCounter' can be saved in a compact manner to a memory area using FSE_writeNCount().
-'buffer' must be already allocated.
-For guaranteed success, buffer size must be at least FSE_headerBound().
-The result of the function is the number of bytes written into 'buffer'.
-If there is an error, the function will return an ErrorCode (which can be tested using FSE_isError(); ex : buffer size too small).
-
-'normalizedCounter' can then be used to create the compression table 'CTable'.
-The space required by 'CTable' must be already allocated, using FSE_createCTable().
-You can then use FSE_buildCTable() to fill 'CTable'.
-If there is an error, both functions will return an ErrorCode (which can be tested using FSE_isError()).
-
-'CTable' can then be used to compress 'src', with FSE_compress_usingCTable().
-Similar to FSE_count(), the convention is that 'src' is assumed to be a table of char of size 'srcSize'
-The function returns the size of compressed data (without header), necessarily <= `dstCapacity`.
-If it returns '0', compressed data could not fit into 'dst'.
-If there is an error, the function will return an ErrorCode (which can be tested using FSE_isError()).
-*/
-
-/* *** DECOMPRESSION *** */
-
-/*! FSE_readNCount():
-	Read compactly saved 'normalizedCounter' from 'rBuffer'.
-	@return : size read from 'rBuffer',
-			  or an errorCode, which can be tested using FSE_isError().
-			  maxSymbolValuePtr[0] and tableLogPtr[0] will also be updated with their respective values */
-FSE_PUBLIC_API size_t FSE_readNCount(short *normalizedCounter, unsigned *maxSymbolValuePtr, unsigned *tableLogPtr, const void *rBuffer, size_t rBuffSize);
-
-/*! Constructor and Destructor of FSE_DTable.
-	Note that its size depends on 'tableLog' */
-typedef unsigned FSE_DTable; /* don't allocate that. It's just a way to be more restrictive than void* */
-
-/*! FSE_buildDTable():
-	Builds 'dt', which must be already allocated, using FSE_createDTable().
-	return : 0, or an errorCode, which can be tested using FSE_isError() */
-FSE_PUBLIC_API size_t FSE_buildDTable_wksp(FSE_DTable *dt, const short *normalizedCounter, unsigned maxSymbolValue, unsigned tableLog, void *workspace, size_t workspaceSize);
-
-/*! FSE_decompress_usingDTable():
-	Decompress compressed source `cSrc` of size `cSrcSize` using `dt`
-	into `dst` which must be already allocated.
-	@return : size of regenerated data (necessarily <= `dstCapacity`),
-			  or an errorCode, which can be tested using FSE_isError() */
-FSE_PUBLIC_API size_t FSE_decompress_usingDTable(void *dst, size_t dstCapacity, const void *cSrc, size_t cSrcSize, const FSE_DTable *dt);
-
-/*!
-Tutorial :
-----------
-(Note : these functions only decompress FSE-compressed blocks.
- If block is uncompressed, use memcpy() instead
- If block is a single repeated byte, use memset() instead )
-
-The first step is to obtain the normalized frequencies of symbols.
-This can be performed by FSE_readNCount() if it was saved using FSE_writeNCount().
-'normalizedCounter' must be already allocated, and have at least 'maxSymbolValuePtr[0]+1' cells of signed short.
-In practice, that means it's necessary to know 'maxSymbolValue' beforehand,
-or size the table to handle worst case situations (typically 256).
-FSE_readNCount() will provide 'tableLog' and 'maxSymbolValue'.
-The result of FSE_readNCount() is the number of bytes read from 'rBuffer'.
-Note that 'rBufferSize' must be at least 4 bytes, even if useful information is less than that.
-If there is an error, the function will return an error code, which can be tested using FSE_isError().
-
-The next step is to build the decompression tables 'FSE_DTable' from 'normalizedCounter'.
-This is performed by the function FSE_buildDTable().
-The space required by 'FSE_DTable' must be already allocated using FSE_createDTable().
-If there is an error, the function will return an error code, which can be tested using FSE_isError().
-
-`FSE_DTable` can then be used to decompress `cSrc`, with FSE_decompress_usingDTable().
-`cSrcSize` must be strictly correct, otherwise decompression will fail.
-FSE_decompress_usingDTable() result will tell how many bytes were regenerated (<=`dstCapacity`).
-If there is an error, the function will return an error code, which can be tested using FSE_isError(). (ex: dst buffer too small)
-*/
-
-/* *** Dependency *** */
-#include "bitstream.h"
-
-/* *****************************************
-*  Static allocation
-*******************************************/
-/* FSE buffer bounds */
-#define FSE_NCOUNTBOUND 512
-#define FSE_BLOCKBOUND(size) (size + (size >> 7))
-#define FSE_COMPRESSBOUND(size) (FSE_NCOUNTBOUND + FSE_BLOCKBOUND(size)) /* Macro version, useful for static allocation */
-
-/* It is possible to statically allocate FSE CTable/DTable as a table of FSE_CTable/FSE_DTable using below macros */
-#define FSE_CTABLE_SIZE_U32(maxTableLog, maxSymbolValue) (1 + (1 << (maxTableLog - 1)) + ((maxSymbolValue + 1) * 2))
-#define FSE_DTABLE_SIZE_U32(maxTableLog) (1 + (1 << maxTableLog))
-
-/* *****************************************
-*  FSE advanced API
-*******************************************/
-/* FSE_count_wksp() :
- * Same as FSE_count(), but using an externally provided scratch buffer.
- * `workSpace` size must be table of >= `1024` unsigned
- */
-size_t FSE_count_wksp(unsigned *count, unsigned *maxSymbolValuePtr, const void *source, size_t sourceSize, unsigned *workSpace);
-
-/* FSE_countFast_wksp() :
- * Same as FSE_countFast(), but using an externally provided scratch buffer.
- * `workSpace` must be a table of minimum `1024` unsigned
- */
-size_t FSE_countFast_wksp(unsigned *count, unsigned *maxSymbolValuePtr, const void *src, size_t srcSize, unsigned *workSpace);
-
-/*! FSE_count_simple
- * Same as FSE_countFast(), but does not use any additional memory (not even on stack).
- * This function is unsafe, and will segfault if any value within `src` is `> *maxSymbolValuePtr` (presuming it's also the size of `count`).
-*/
-size_t FSE_count_simple(unsigned *count, unsigned *maxSymbolValuePtr, const void *src, size_t srcSize);
-
-unsigned FSE_optimalTableLog_internal(unsigned maxTableLog, size_t srcSize, unsigned maxSymbolValue, unsigned minus);
-/**< same as FSE_optimalTableLog(), which used `minus==2` */
-
-size_t FSE_buildCTable_raw(FSE_CTable *ct, unsigned nbBits);
-/**< build a fake FSE_CTable, designed for a flat distribution, where each symbol uses nbBits */
-
-size_t FSE_buildCTable_rle(FSE_CTable *ct, unsigned char symbolValue);
-/**< build a fake FSE_CTable, designed to compress always the same symbolValue */
-
-/* FSE_buildCTable_wksp() :
- * Same as FSE_buildCTable(), but using an externally allocated scratch buffer (`workSpace`).
- * `wkspSize` must be >= `(1<<tableLog)`.
- */
-size_t FSE_buildCTable_wksp(FSE_CTable *ct, const short *normalizedCounter, unsigned maxSymbolValue, unsigned tableLog, void *workSpace, size_t wkspSize);
-
-size_t FSE_buildDTable_raw(FSE_DTable *dt, unsigned nbBits);
-/**< build a fake FSE_DTable, designed to read a flat distribution where each symbol uses nbBits */
-
-size_t FSE_buildDTable_rle(FSE_DTable *dt, unsigned char symbolValue);
-/**< build a fake FSE_DTable, designed to always generate the same symbolValue */
-
-size_t FSE_decompress_wksp(void *dst, size_t dstCapacity, const void *cSrc, size_t cSrcSize, unsigned maxLog, void *workspace, size_t workspaceSize);
-/**< same as FSE_decompress(), using an externally allocated `workSpace` produced with `FSE_DTABLE_SIZE_U32(maxLog)` */
-
-/* *****************************************
-*  FSE symbol compression API
-*******************************************/
-/*!
-   This API consists of small unitary functions, which highly benefit from being inlined.
-   Hence their body are included in next section.
-*/
-typedef struct {
-	ptrdiff_t value;
-	const void *stateTable;
-	const void *symbolTT;
-	unsigned stateLog;
-} FSE_CState_t;
-
-static void FSE_initCState(FSE_CState_t *CStatePtr, const FSE_CTable *ct);
-
-static void FSE_encodeSymbol(BIT_CStream_t *bitC, FSE_CState_t *CStatePtr, unsigned symbol);
-
-static void FSE_flushCState(BIT_CStream_t *bitC, const FSE_CState_t *CStatePtr);
-
-/**<
-These functions are inner components of FSE_compress_usingCTable().
-They allow the creation of custom streams, mixing multiple tables and bit sources.
-
-A key property to keep in mind is that encoding and decoding are done **in reverse direction**.
-So the first symbol you will encode is the last you will decode, like a LIFO stack.
-
-You will need a few variables to track your CStream. They are :
-
-FSE_CTable    ct;         // Provided by FSE_buildCTable()
-BIT_CStream_t bitStream;  // bitStream tracking structure
-FSE_CState_t  state;      // State tracking structure (can have several)
-
-
-The first thing to do is to init bitStream and state.
-	size_t errorCode = BIT_initCStream(&bitStream, dstBuffer, maxDstSize);
-	FSE_initCState(&state, ct);
-
-Note that BIT_initCStream() can produce an error code, so its result should be tested, using FSE_isError();
-You can then encode your input data, byte after byte.
-FSE_encodeSymbol() outputs a maximum of 'tableLog' bits at a time.
-Remember decoding will be done in reverse direction.
-	FSE_encodeByte(&bitStream, &state, symbol);
-
-At any time, you can also add any bit sequence.
-Note : maximum allowed nbBits is 25, for compatibility with 32-bits decoders
-	BIT_addBits(&bitStream, bitField, nbBits);
-
-The above methods don't commit data to memory, they just store it into local register, for speed.
-Local register size is 64-bits on 64-bits systems, 32-bits on 32-bits systems (size_t).
-Writing data to memory is a manual operation, performed by the flushBits function.
-	BIT_flushBits(&bitStream);
-
-Your last FSE encoding operation shall be to flush your last state value(s).
-	FSE_flushState(&bitStream, &state);
-
-Finally, you must close the bitStream.
-The function returns the size of CStream in bytes.
-If data couldn't fit into dstBuffer, it will return a 0 ( == not compressible)
-If there is an error, it returns an errorCode (which can be tested using FSE_isError()).
-	size_t size = BIT_closeCStream(&bitStream);
-*/
-
-/* *****************************************
-*  FSE symbol decompression API
-*******************************************/
-typedef struct {
-	size_t state;
-	const void *table; /* precise table may vary, depending on U16 */
-} FSE_DState_t;
-
-static void FSE_initDState(FSE_DState_t *DStatePtr, BIT_DStream_t *bitD, const FSE_DTable *dt);
-
-static unsigned char FSE_decodeSymbol(FSE_DState_t *DStatePtr, BIT_DStream_t *bitD);
-
-static unsigned FSE_endOfDState(const FSE_DState_t *DStatePtr);
-
-/**<
-Let's now decompose FSE_decompress_usingDTable() into its unitary components.
-You will decode FSE-encoded symbols from the bitStream,
-and also any other bitFields you put in, **in reverse order**.
-
-You will need a few variables to track your bitStream. They are :
-
-BIT_DStream_t DStream;    // Stream context
-FSE_DState_t  DState;     // State context. Multiple ones are possible
-FSE_DTable*   DTablePtr;  // Decoding table, provided by FSE_buildDTable()
-
-The first thing to do is to init the bitStream.
-	errorCode = BIT_initDStream(&DStream, srcBuffer, srcSize);
-
-You should then retrieve your initial state(s)
-(in reverse flushing order if you have several ones) :
-	errorCode = FSE_initDState(&DState, &DStream, DTablePtr);
-
-You can then decode your data, symbol after symbol.
-For information the maximum number of bits read by FSE_decodeSymbol() is 'tableLog'.
-Keep in mind that symbols are decoded in reverse order, like a LIFO stack (last in, first out).
-	unsigned char symbol = FSE_decodeSymbol(&DState, &DStream);
-
-You can retrieve any bitfield you eventually stored into the bitStream (in reverse order)
-Note : maximum allowed nbBits is 25, for 32-bits compatibility
-	size_t bitField = BIT_readBits(&DStream, nbBits);
-
-All above operations only read from local register (which size depends on size_t).
-Refueling the register from memory is manually performed by the reload method.
-	endSignal = FSE_reloadDStream(&DStream);
-
-BIT_reloadDStream() result tells if there is still some more data to read from DStream.
-BIT_DStream_unfinished : there is still some data left into the DStream.
-BIT_DStream_endOfBuffer : Dstream reached end of buffer. Its container may no longer be completely filled.
-BIT_DStream_completed : Dstream reached its exact end, corresponding in general to decompression completed.
-BIT_DStream_tooFar : Dstream went too far. Decompression result is corrupted.
-
-When reaching end of buffer (BIT_DStream_endOfBuffer), progress slowly, notably if you decode multiple symbols per loop,
-to properly detect the exact end of stream.
-After each decoded symbol, check if DStream is fully consumed using this simple test :
-	BIT_reloadDStream(&DStream) >= BIT_DStream_completed
-
-When it's done, verify decompression is fully completed, by checking both DStream and the relevant states.
-Checking if DStream has reached its end is performed by :
-	BIT_endOfDStream(&DStream);
-Check also the states. There might be some symbols left there, if some high probability ones (>50%) are possible.
-	FSE_endOfDState(&DState);
-*/
-
-/* *****************************************
-*  FSE unsafe API
-*******************************************/
-static unsigned char FSE_decodeSymbolFast(FSE_DState_t *DStatePtr, BIT_DStream_t *bitD);
-/* faster, but works only if nbBits is always >= 1 (otherwise, result will be corrupted) */
-
-/* *****************************************
-*  Implementation of inlined functions
-*******************************************/
-typedef struct {
-	int deltaFindState;
-	U32 deltaNbBits;
-} FSE_symbolCompressionTransform; /* total 8 bytes */
-
-ZSTD_STATIC void FSE_initCState(FSE_CState_t *statePtr, const FSE_CTable *ct)
-{
-	const void *ptr = ct;
-	const U16 *u16ptr = (const U16 *)ptr;
-	const U32 tableLog = ZSTD_read16(ptr);
-	statePtr->value = (ptrdiff_t)1 << tableLog;
-	statePtr->stateTable = u16ptr + 2;
-	statePtr->symbolTT = ((const U32 *)ct + 1 + (tableLog ? (1 << (tableLog - 1)) : 1));
-	statePtr->stateLog = tableLog;
-}
-
-/*! FSE_initCState2() :
-*   Same as FSE_initCState(), but the first symbol to include (which will be the last to be read)
-*   uses the smallest state value possible, saving the cost of this symbol */
-ZSTD_STATIC void FSE_initCState2(FSE_CState_t *statePtr, const FSE_CTable *ct, U32 symbol)
-{
-	FSE_initCState(statePtr, ct);
-	{
-		const FSE_symbolCompressionTransform symbolTT = ((const FSE_symbolCompressionTransform *)(statePtr->symbolTT))[symbol];
-		const U16 *stateTable = (const U16 *)(statePtr->stateTable);
-		U32 nbBitsOut = (U32)((symbolTT.deltaNbBits + (1 << 15)) >> 16);
-		statePtr->value = (nbBitsOut << 16) - symbolTT.deltaNbBits;
-		statePtr->value = stateTable[(statePtr->value >> nbBitsOut) + symbolTT.deltaFindState];
-	}
-}
-
-ZSTD_STATIC void FSE_encodeSymbol(BIT_CStream_t *bitC, FSE_CState_t *statePtr, U32 symbol)
-{
-	const FSE_symbolCompressionTransform symbolTT = ((const FSE_symbolCompressionTransform *)(statePtr->symbolTT))[symbol];
-	const U16 *const stateTable = (const U16 *)(statePtr->stateTable);
-	U32 nbBitsOut = (U32)((statePtr->value + symbolTT.deltaNbBits) >> 16);
-	BIT_addBits(bitC, statePtr->value, nbBitsOut);
-	statePtr->value = stateTable[(statePtr->value >> nbBitsOut) + symbolTT.deltaFindState];
-}
-
-ZSTD_STATIC void FSE_flushCState(BIT_CStream_t *bitC, const FSE_CState_t *statePtr)
-{
-	BIT_addBits(bitC, statePtr->value, statePtr->stateLog);
-	BIT_flushBits(bitC);
-}
-
-/* ======    Decompression    ====== */
-
-typedef struct {
-	U16 tableLog;
-	U16 fastMode;
-} FSE_DTableHeader; /* sizeof U32 */
-
-typedef struct {
-	unsigned short newState;
-	unsigned char symbol;
-	unsigned char nbBits;
-} FSE_decode_t; /* size == U32 */
-
-ZSTD_STATIC void FSE_initDState(FSE_DState_t *DStatePtr, BIT_DStream_t *bitD, const FSE_DTable *dt)
-{
-	const void *ptr = dt;
-	const FSE_DTableHeader *const DTableH = (const FSE_DTableHeader *)ptr;
-	DStatePtr->state = BIT_readBits(bitD, DTableH->tableLog);
-	BIT_reloadDStream(bitD);
-	DStatePtr->table = dt + 1;
-}
-
-ZSTD_STATIC BYTE FSE_peekSymbol(const FSE_DState_t *DStatePtr)
-{
-	FSE_decode_t const DInfo = ((const FSE_decode_t *)(DStatePtr->table))[DStatePtr->state];
-	return DInfo.symbol;
-}
-
-ZSTD_STATIC void FSE_updateState(FSE_DState_t *DStatePtr, BIT_DStream_t *bitD)
-{
-	FSE_decode_t const DInfo = ((const FSE_decode_t *)(DStatePtr->table))[DStatePtr->state];
-	U32 const nbBits = DInfo.nbBits;
-	size_t const lowBits = BIT_readBits(bitD, nbBits);
-	DStatePtr->state = DInfo.newState + lowBits;
-}
-
-ZSTD_STATIC BYTE FSE_decodeSymbol(FSE_DState_t *DStatePtr, BIT_DStream_t *bitD)
-{
-	FSE_decode_t const DInfo = ((const FSE_decode_t *)(DStatePtr->table))[DStatePtr->state];
-	U32 const nbBits = DInfo.nbBits;
-	BYTE const symbol = DInfo.symbol;
-	size_t const lowBits = BIT_readBits(bitD, nbBits);
-
-	DStatePtr->state = DInfo.newState + lowBits;
-	return symbol;
-}
-
-/*! FSE_decodeSymbolFast() :
-	unsafe, only works if no symbol has a probability > 50% */
-ZSTD_STATIC BYTE FSE_decodeSymbolFast(FSE_DState_t *DStatePtr, BIT_DStream_t *bitD)
-{
-	FSE_decode_t const DInfo = ((const FSE_decode_t *)(DStatePtr->table))[DStatePtr->state];
-	U32 const nbBits = DInfo.nbBits;
-	BYTE const symbol = DInfo.symbol;
-	size_t const lowBits = BIT_readBitsFast(bitD, nbBits);
-
-	DStatePtr->state = DInfo.newState + lowBits;
-	return symbol;
-}
-
-ZSTD_STATIC unsigned FSE_endOfDState(const FSE_DState_t *DStatePtr) { return DStatePtr->state == 0; }
-
-/* **************************************************************
-*  Tuning parameters
-****************************************************************/
-/*!MEMORY_USAGE :
-*  Memory usage formula : N->2^N Bytes (examples : 10 -> 1KB; 12 -> 4KB ; 16 -> 64KB; 20 -> 1MB; etc.)
-*  Increasing memory usage improves compression ratio
-*  Reduced memory usage can improve speed, due to cache effect
-*  Recommended max value is 14, for 16KB, which nicely fits into Intel x86 L1 cache */
-#ifndef FSE_MAX_MEMORY_USAGE
-#define FSE_MAX_MEMORY_USAGE 14
-#endif
-#ifndef FSE_DEFAULT_MEMORY_USAGE
-#define FSE_DEFAULT_MEMORY_USAGE 13
-#endif
-
-/*!FSE_MAX_SYMBOL_VALUE :
-*  Maximum symbol value authorized.
-*  Required for proper stack allocation */
-#ifndef FSE_MAX_SYMBOL_VALUE
-#define FSE_MAX_SYMBOL_VALUE 255
-#endif
-
-/* **************************************************************
-*  template functions type & suffix
-****************************************************************/
-#define FSE_FUNCTION_TYPE BYTE
-#define FSE_FUNCTION_EXTENSION
-#define FSE_DECODE_TYPE FSE_decode_t
-
-/* ***************************************************************
-*  Constants
-*****************************************************************/
-#define FSE_MAX_TABLELOG (FSE_MAX_MEMORY_USAGE - 2)
-#define FSE_MAX_TABLESIZE (1U << FSE_MAX_TABLELOG)
-#define FSE_MAXTABLESIZE_MASK (FSE_MAX_TABLESIZE - 1)
-#define FSE_DEFAULT_TABLELOG (FSE_DEFAULT_MEMORY_USAGE - 2)
-#define FSE_MIN_TABLELOG 5
-
-#define FSE_TABLELOG_ABSOLUTE_MAX 15
-#if FSE_MAX_TABLELOG > FSE_TABLELOG_ABSOLUTE_MAX
-#error "FSE_MAX_TABLELOG > FSE_TABLELOG_ABSOLUTE_MAX is not supported"
-#endif
-
-#define FSE_TABLESTEP(tableSize) ((tableSize >> 1) + (tableSize >> 3) + 3)
-
-#endif /* FSE_H */
diff --git a/lib/zstd/fse_compress.c b/lib/zstd/fse_compress.c
deleted file mode 100644
index ef3d1741d532..000000000000
--- a/lib/zstd/fse_compress.c
+++ /dev/null
@@ -1,795 +0,0 @@
-/*
- * FSE : Finite State Entropy encoder
- * Copyright (C) 2013-2015, Yann Collet.
- *
- * BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are
- * met:
- *
- *   * Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- *   * Redistributions in binary form must reproduce the above
- * copyright notice, this list of conditions and the following disclaimer
- * in the documentation and/or other materials provided with the
- * distribution.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * 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. This program is dual-licensed; you may select
- * either version 2 of the GNU General Public License ("GPL") or BSD license
- * ("BSD").
- *
- * You can contact the author at :
- * - Source repository : https://github.com/Cyan4973/FiniteStateEntropy
- */
-
-/* **************************************************************
-*  Compiler specifics
-****************************************************************/
-#define FORCE_INLINE static __always_inline
-
-/* **************************************************************
-*  Includes
-****************************************************************/
-#include "bitstream.h"
-#include "fse.h"
-#include <linux/compiler.h>
-#include <linux/kernel.h>
-#include <linux/math64.h>
-#include <linux/string.h> /* memcpy, memset */
-
-/* **************************************************************
-*  Error Management
-****************************************************************/
-#define FSE_STATIC_ASSERT(c)                                   \
-	{                                                      \
-		enum { FSE_static_assert = 1 / (int)(!!(c)) }; \
-	} /* use only *after* variable declarations */
-
-/* **************************************************************
-*  Templates
-****************************************************************/
-/*
-  designed to be included
-  for type-specific functions (template emulation in C)
-  Objective is to write these functions only once, for improved maintenance
-*/
-
-/* safety checks */
-#ifndef FSE_FUNCTION_EXTENSION
-#error "FSE_FUNCTION_EXTENSION must be defined"
-#endif
-#ifndef FSE_FUNCTION_TYPE
-#error "FSE_FUNCTION_TYPE must be defined"
-#endif
-
-/* Function names */
-#define FSE_CAT(X, Y) X##Y
-#define FSE_FUNCTION_NAME(X, Y) FSE_CAT(X, Y)
-#define FSE_TYPE_NAME(X, Y) FSE_CAT(X, Y)
-
-/* Function templates */
-
-/* FSE_buildCTable_wksp() :
- * Same as FSE_buildCTable(), but using an externally allocated scratch buffer (`workSpace`).
- * wkspSize should be sized to handle worst case situation, which is `1<<max_tableLog * sizeof(FSE_FUNCTION_TYPE)`
- * workSpace must also be properly aligned with FSE_FUNCTION_TYPE requirements
- */
-size_t FSE_buildCTable_wksp(FSE_CTable *ct, const short *normalizedCounter, unsigned maxSymbolValue, unsigned tableLog, void *workspace, size_t workspaceSize)
-{
-	U32 const tableSize = 1 << tableLog;
-	U32 const tableMask = tableSize - 1;
-	void *const ptr = ct;
-	U16 *const tableU16 = ((U16 *)ptr) + 2;
-	void *const FSCT = ((U32 *)ptr) + 1 /* header */ + (tableLog ? tableSize >> 1 : 1);
-	FSE_symbolCompressionTransform *const symbolTT = (FSE_symbolCompressionTransform *)(FSCT);
-	U32 const step = FSE_TABLESTEP(tableSize);
-	U32 highThreshold = tableSize - 1;
-
-	U32 *cumul;
-	FSE_FUNCTION_TYPE *tableSymbol;
-	size_t spaceUsed32 = 0;
-
-	cumul = (U32 *)workspace + spaceUsed32;
-	spaceUsed32 += FSE_MAX_SYMBOL_VALUE + 2;
-	tableSymbol = (FSE_FUNCTION_TYPE *)((U32 *)workspace + spaceUsed32);
-	spaceUsed32 += ALIGN(sizeof(FSE_FUNCTION_TYPE) * ((size_t)1 << tableLog), sizeof(U32)) >> 2;
-
-	if ((spaceUsed32 << 2) > workspaceSize)
-		return ERROR(tableLog_tooLarge);
-	workspace = (U32 *)workspace + spaceUsed32;
-	workspaceSize -= (spaceUsed32 << 2);
-
-	/* CTable header */
-	tableU16[-2] = (U16)tableLog;
-	tableU16[-1] = (U16)maxSymbolValue;
-
-	/* For explanations on how to distribute symbol values over the table :
-	*  http://fastcompression.blogspot.fr/2014/02/fse-distributing-symbol-values.html */
-
-	/* symbol start positions */
-	{
-		U32 u;
-		cumul[0] = 0;
-		for (u = 1; u <= maxSymbolValue + 1; u++) {
-			if (normalizedCounter[u - 1] == -1) { /* Low proba symbol */
-				cumul[u] = cumul[u - 1] + 1;
-				tableSymbol[highThreshold--] = (FSE_FUNCTION_TYPE)(u - 1);
-			} else {
-				cumul[u] = cumul[u - 1] + normalizedCounter[u - 1];
-			}
-		}
-		cumul[maxSymbolValue + 1] = tableSize + 1;
-	}
-
-	/* Spread symbols */
-	{
-		U32 position = 0;
-		U32 symbol;
-		for (symbol = 0; symbol <= maxSymbolValue; symbol++) {
-			int nbOccurences;
-			for (nbOccurences = 0; nbOccurences < normalizedCounter[symbol]; nbOccurences++) {
-				tableSymbol[position] = (FSE_FUNCTION_TYPE)symbol;
-				position = (position + step) & tableMask;
-				while (position > highThreshold)
-					position = (position + step) & tableMask; /* Low proba area */
-			}
-		}
-
-		if (position != 0)
-			return ERROR(GENERIC); /* Must have gone through all positions */
-	}
-
-	/* Build table */
-	{
-		U32 u;
-		for (u = 0; u < tableSize; u++) {
-			FSE_FUNCTION_TYPE s = tableSymbol[u];	/* note : static analyzer may not understand tableSymbol is properly initialized */
-			tableU16[cumul[s]++] = (U16)(tableSize + u); /* TableU16 : sorted by symbol order; gives next state value */
-		}
-	}
-
-	/* Build Symbol Transformation Table */
-	{
-		unsigned total = 0;
-		unsigned s;
-		for (s = 0; s <= maxSymbolValue; s++) {
-			switch (normalizedCounter[s]) {
-			case 0: break;
-
-			case -1:
-			case 1:
-				symbolTT[s].deltaNbBits = (tableLog << 16) - (1 << tableLog);
-				symbolTT[s].deltaFindState = total - 1;
-				total++;
-				break;
-			default: {
-				U32 const maxBitsOut = tableLog - BIT_highbit32(normalizedCounter[s] - 1);
-				U32 const minStatePlus = normalizedCounter[s] << maxBitsOut;
-				symbolTT[s].deltaNbBits = (maxBitsOut << 16) - minStatePlus;
-				symbolTT[s].deltaFindState = total - normalizedCounter[s];
-				total += normalizedCounter[s];
-			}
-			}
-		}
-	}
-
-	return 0;
-}
-
-/*-**************************************************************
-*  FSE NCount encoding-decoding
-****************************************************************/
-size_t FSE_NCountWriteBound(unsigned maxSymbolValue, unsigned tableLog)
-{
-	size_t const maxHeaderSize = (((maxSymbolValue + 1) * tableLog) >> 3) + 3;
-	return maxSymbolValue ? maxHeaderSize : FSE_NCOUNTBOUND; /* maxSymbolValue==0 ? use default */
-}
-
-static size_t FSE_writeNCount_generic(void *header, size_t headerBufferSize, const short *normalizedCounter, unsigned maxSymbolValue, unsigned tableLog,
-				      unsigned writeIsSafe)
-{
-	BYTE *const ostart = (BYTE *)header;
-	BYTE *out = ostart;
-	BYTE *const oend = ostart + headerBufferSize;
-	int nbBits;
-	const int tableSize = 1 << tableLog;
-	int remaining;
-	int threshold;
-	U32 bitStream;
-	int bitCount;
-	unsigned charnum = 0;
-	int previous0 = 0;
-
-	bitStream = 0;
-	bitCount = 0;
-	/* Table Size */
-	bitStream += (tableLog - FSE_MIN_TABLELOG) << bitCount;
-	bitCount += 4;
-
-	/* Init */
-	remaining = tableSize + 1; /* +1 for extra accuracy */
-	threshold = tableSize;
-	nbBits = tableLog + 1;
-
-	while (remaining > 1) { /* stops at 1 */
-		if (previous0) {
-			unsigned start = charnum;
-			while (!normalizedCounter[charnum])
-				charnum++;
-			while (charnum >= start + 24) {
-				start += 24;
-				bitStream += 0xFFFFU << bitCount;
-				if ((!writeIsSafe) && (out > oend - 2))
-					return ERROR(dstSize_tooSmall); /* Buffer overflow */
-				out[0] = (BYTE)bitStream;
-				out[1] = (BYTE)(bitStream >> 8);
-				out += 2;
-				bitStream >>= 16;
-			}
-			while (charnum >= start + 3) {
-				start += 3;
-				bitStream += 3 << bitCount;
-				bitCount += 2;
-			}
-			bitStream += (charnum - start) << bitCount;
-			bitCount += 2;
-			if (bitCount > 16) {
-				if ((!writeIsSafe) && (out > oend - 2))
-					return ERROR(dstSize_tooSmall); /* Buffer overflow */
-				out[0] = (BYTE)bitStream;
-				out[1] = (BYTE)(bitStream >> 8);
-				out += 2;
-				bitStream >>= 16;
-				bitCount -= 16;
-			}
-		}
-		{
-			int count = normalizedCounter[charnum++];
-			int const max = (2 * threshold - 1) - remaining;
-			remaining -= count < 0 ? -count : count;
-			count++; /* +1 for extra accuracy */
-			if (count >= threshold)
-				count += max; /* [0..max[ [max..threshold[ (...) [threshold+max 2*threshold[ */
-			bitStream += count << bitCount;
-			bitCount += nbBits;
-			bitCount -= (count < max);
-			previous0 = (count == 1);
-			if (remaining < 1)
-				return ERROR(GENERIC);
-			while (remaining < threshold)
-				nbBits--, threshold >>= 1;
-		}
-		if (bitCount > 16) {
-			if ((!writeIsSafe) && (out > oend - 2))
-				return ERROR(dstSize_tooSmall); /* Buffer overflow */
-			out[0] = (BYTE)bitStream;
-			out[1] = (BYTE)(bitStream >> 8);
-			out += 2;
-			bitStream >>= 16;
-			bitCount -= 16;
-		}
-	}
-
-	/* flush remaining bitStream */
-	if ((!writeIsSafe) && (out > oend - 2))
-		return ERROR(dstSize_tooSmall); /* Buffer overflow */
-	out[0] = (BYTE)bitStream;
-	out[1] = (BYTE)(bitStream >> 8);
-	out += (bitCount + 7) / 8;
-
-	if (charnum > maxSymbolValue + 1)
-		return ERROR(GENERIC);
-
-	return (out - ostart);
-}
-
-size_t FSE_writeNCount(void *buffer, size_t bufferSize, const short *normalizedCounter, unsigned maxSymbolValue, unsigned tableLog)
-{
-	if (tableLog > FSE_MAX_TABLELOG)
-		return ERROR(tableLog_tooLarge); /* Unsupported */
-	if (tableLog < FSE_MIN_TABLELOG)
-		return ERROR(GENERIC); /* Unsupported */
-
-	if (bufferSize < FSE_NCountWriteBound(maxSymbolValue, tableLog))
-		return FSE_writeNCount_generic(buffer, bufferSize, normalizedCounter, maxSymbolValue, tableLog, 0);
-
-	return FSE_writeNCount_generic(buffer, bufferSize, normalizedCounter, maxSymbolValue, tableLog, 1);
-}
-
-/*-**************************************************************
-*  Counting histogram
-****************************************************************/
-/*! FSE_count_simple
-	This function counts byte values within `src`, and store the histogram into table `count`.
-	It doesn't use any additional memory.
-	But this function is unsafe : it doesn't check that all values within `src` can fit into `count`.
-	For this reason, prefer using a table `count` with 256 elements.
-	@return : count of most numerous element
-*/
-size_t FSE_count_simple(unsigned *count, unsigned *maxSymbolValuePtr, const void *src, size_t srcSize)
-{
-	const BYTE *ip = (const BYTE *)src;
-	const BYTE *const end = ip + srcSize;
-	unsigned maxSymbolValue = *maxSymbolValuePtr;
-	unsigned max = 0;
-
-	memset(count, 0, (maxSymbolValue + 1) * sizeof(*count));
-	if (srcSize == 0) {
-		*maxSymbolValuePtr = 0;
-		return 0;
-	}
-
-	while (ip < end)
-		count[*ip++]++;
-
-	while (!count[maxSymbolValue])
-		maxSymbolValue--;
-	*maxSymbolValuePtr = maxSymbolValue;
-
-	{
-		U32 s;
-		for (s = 0; s <= maxSymbolValue; s++)
-			if (count[s] > max)
-				max = count[s];
-	}
-
-	return (size_t)max;
-}
-
-/* FSE_count_parallel_wksp() :
- * Same as FSE_count_parallel(), but using an externally provided scratch buffer.
- * `workSpace` size must be a minimum of `1024 * sizeof(unsigned)`` */
-static size_t FSE_count_parallel_wksp(unsigned *count, unsigned *maxSymbolValuePtr, const void *source, size_t sourceSize, unsigned checkMax,
-				      unsigned *const workSpace)
-{
-	const BYTE *ip = (const BYTE *)source;
-	const BYTE *const iend = ip + sourceSize;
-	unsigned maxSymbolValue = *maxSymbolValuePtr;
-	unsigned max = 0;
-	U32 *const Counting1 = workSpace;
-	U32 *const Counting2 = Counting1 + 256;
-	U32 *const Counting3 = Counting2 + 256;
-	U32 *const Counting4 = Counting3 + 256;
-
-	memset(Counting1, 0, 4 * 256 * sizeof(unsigned));
-
-	/* safety checks */
-	if (!sourceSize) {
-		memset(count, 0, maxSymbolValue + 1);
-		*maxSymbolValuePtr = 0;
-		return 0;
-	}
-	if (!maxSymbolValue)
-		maxSymbolValue = 255; /* 0 == default */
-
-	/* by stripes of 16 bytes */
-	{
-		U32 cached = ZSTD_read32(ip);
-		ip += 4;
-		while (ip < iend - 15) {
-			U32 c = cached;
-			cached = ZSTD_read32(ip);
-			ip += 4;
-			Counting1[(BYTE)c]++;
-			Counting2[(BYTE)(c >> 8)]++;
-			Counting3[(BYTE)(c >> 16)]++;
-			Counting4[c >> 24]++;
-			c = cached;
-			cached = ZSTD_read32(ip);
-			ip += 4;
-			Counting1[(BYTE)c]++;
-			Counting2[(BYTE)(c >> 8)]++;
-			Counting3[(BYTE)(c >> 16)]++;
-			Counting4[c >> 24]++;
-			c = cached;
-			cached = ZSTD_read32(ip);
-			ip += 4;
-			Counting1[(BYTE)c]++;
-			Counting2[(BYTE)(c >> 8)]++;
-			Counting3[(BYTE)(c >> 16)]++;
-			Counting4[c >> 24]++;
-			c = cached;
-			cached = ZSTD_read32(ip);
-			ip += 4;
-			Counting1[(BYTE)c]++;
-			Counting2[(BYTE)(c >> 8)]++;
-			Counting3[(BYTE)(c >> 16)]++;
-			Counting4[c >> 24]++;
-		}
-		ip -= 4;
-	}
-
-	/* finish last symbols */
-	while (ip < iend)
-		Counting1[*ip++]++;
-
-	if (checkMax) { /* verify stats will fit into destination table */
-		U32 s;
-		for (s = 255; s > maxSymbolValue; s--) {
-			Counting1[s] += Counting2[s] + Counting3[s] + Counting4[s];
-			if (Counting1[s])
-				return ERROR(maxSymbolValue_tooSmall);
-		}
-	}
-
-	{
-		U32 s;
-		for (s = 0; s <= maxSymbolValue; s++) {
-			count[s] = Counting1[s] + Counting2[s] + Counting3[s] + Counting4[s];
-			if (count[s] > max)
-				max = count[s];
-		}
-	}
-
-	while (!count[maxSymbolValue])
-		maxSymbolValue--;
-	*maxSymbolValuePtr = maxSymbolValue;
-	return (size_t)max;
-}
-
-/* FSE_countFast_wksp() :
- * Same as FSE_countFast(), but using an externally provided scratch buffer.
- * `workSpace` size must be table of >= `1024` unsigned */
-size_t FSE_countFast_wksp(unsigned *count, unsigned *maxSymbolValuePtr, const void *source, size_t sourceSize, unsigned *workSpace)
-{
-	if (sourceSize < 1500)
-		return FSE_count_simple(count, maxSymbolValuePtr, source, sourceSize);
-	return FSE_count_parallel_wksp(count, maxSymbolValuePtr, source, sourceSize, 0, workSpace);
-}
-
-/* FSE_count_wksp() :
- * Same as FSE_count(), but using an externally provided scratch buffer.
- * `workSpace` size must be table of >= `1024` unsigned */
-size_t FSE_count_wksp(unsigned *count, unsigned *maxSymbolValuePtr, const void *source, size_t sourceSize, unsigned *workSpace)
-{
-	if (*maxSymbolValuePtr < 255)
-		return FSE_count_parallel_wksp(count, maxSymbolValuePtr, source, sourceSize, 1, workSpace);
-	*maxSymbolValuePtr = 255;
-	return FSE_countFast_wksp(count, maxSymbolValuePtr, source, sourceSize, workSpace);
-}
-
-/*-**************************************************************
-*  FSE Compression Code
-****************************************************************/
-/*! FSE_sizeof_CTable() :
-	FSE_CTable is a variable size structure which contains :
-	`U16 tableLog;`
-	`U16 maxSymbolValue;`
-	`U16 nextStateNumber[1 << tableLog];`                         // This size is variable
-	`FSE_symbolCompressionTransform symbolTT[maxSymbolValue+1];`  // This size is variable
-Allocation is manual (C standard does not support variable-size structures).
-*/
-size_t FSE_sizeof_CTable(unsigned maxSymbolValue, unsigned tableLog)
-{
-	if (tableLog > FSE_MAX_TABLELOG)
-		return ERROR(tableLog_tooLarge);
-	return FSE_CTABLE_SIZE_U32(tableLog, maxSymbolValue) * sizeof(U32);
-}
-
-/* provides the minimum logSize to safely represent a distribution */
-static unsigned FSE_minTableLog(size_t srcSize, unsigned maxSymbolValue)
-{
-	U32 minBitsSrc = BIT_highbit32((U32)(srcSize - 1)) + 1;
-	U32 minBitsSymbols = BIT_highbit32(maxSymbolValue) + 2;
-	U32 minBits = minBitsSrc < minBitsSymbols ? minBitsSrc : minBitsSymbols;
-	return minBits;
-}
-
-unsigned FSE_optimalTableLog_internal(unsigned maxTableLog, size_t srcSize, unsigned maxSymbolValue, unsigned minus)
-{
-	U32 maxBitsSrc = BIT_highbit32((U32)(srcSize - 1)) - minus;
-	U32 tableLog = maxTableLog;
-	U32 minBits = FSE_minTableLog(srcSize, maxSymbolValue);
-	if (tableLog == 0)
-		tableLog = FSE_DEFAULT_TABLELOG;
-	if (maxBitsSrc < tableLog)
-		tableLog = maxBitsSrc; /* Accuracy can be reduced */
-	if (minBits > tableLog)
-		tableLog = minBits; /* Need a minimum to safely represent all symbol values */
-	if (tableLog < FSE_MIN_TABLELOG)
-		tableLog = FSE_MIN_TABLELOG;
-	if (tableLog > FSE_MAX_TABLELOG)
-		tableLog = FSE_MAX_TABLELOG;
-	return tableLog;
-}
-
-unsigned FSE_optimalTableLog(unsigned maxTableLog, size_t srcSize, unsigned maxSymbolValue)
-{
-	return FSE_optimalTableLog_internal(maxTableLog, srcSize, maxSymbolValue, 2);
-}
-
-/* Secondary normalization method.
-   To be used when primary method fails. */
-
-static size_t FSE_normalizeM2(short *norm, U32 tableLog, const unsigned *count, size_t total, U32 maxSymbolValue)
-{
-	short const NOT_YET_ASSIGNED = -2;
-	U32 s;
-	U32 distributed = 0;
-	U32 ToDistribute;
-
-	/* Init */
-	U32 const lowThreshold = (U32)(total >> tableLog);
-	U32 lowOne = (U32)((total * 3) >> (tableLog + 1));
-
-	for (s = 0; s <= maxSymbolValue; s++) {
-		if (count[s] == 0) {
-			norm[s] = 0;
-			continue;
-		}
-		if (count[s] <= lowThreshold) {
-			norm[s] = -1;
-			distributed++;
-			total -= count[s];
-			continue;
-		}
-		if (count[s] <= lowOne) {
-			norm[s] = 1;
-			distributed++;
-			total -= count[s];
-			continue;
-		}
-
-		norm[s] = NOT_YET_ASSIGNED;
-	}
-	ToDistribute = (1 << tableLog) - distributed;
-
-	if ((total / ToDistribute) > lowOne) {
-		/* risk of rounding to zero */
-		lowOne = (U32)((total * 3) / (ToDistribute * 2));
-		for (s = 0; s <= maxSymbolValue; s++) {
-			if ((norm[s] == NOT_YET_ASSIGNED) && (count[s] <= lowOne)) {
-				norm[s] = 1;
-				distributed++;
-				total -= count[s];
-				continue;
-			}
-		}
-		ToDistribute = (1 << tableLog) - distributed;
-	}
-
-	if (distributed == maxSymbolValue + 1) {
-		/* all values are pretty poor;
-		   probably incompressible data (should have already been detected);
-		   find max, then give all remaining points to max */
-		U32 maxV = 0, maxC = 0;
-		for (s = 0; s <= maxSymbolValue; s++)
-			if (count[s] > maxC)
-				maxV = s, maxC = count[s];
-		norm[maxV] += (short)ToDistribute;
-		return 0;
-	}
-
-	if (total == 0) {
-		/* all of the symbols were low enough for the lowOne or lowThreshold */
-		for (s = 0; ToDistribute > 0; s = (s + 1) % (maxSymbolValue + 1))
-			if (norm[s] > 0)
-				ToDistribute--, norm[s]++;
-		return 0;
-	}
-
-	{
-		U64 const vStepLog = 62 - tableLog;
-		U64 const mid = (1ULL << (vStepLog - 1)) - 1;
-		U64 const rStep = div_u64((((U64)1 << vStepLog) * ToDistribute) + mid, (U32)total); /* scale on remaining */
-		U64 tmpTotal = mid;
-		for (s = 0; s <= maxSymbolValue; s++) {
-			if (norm[s] == NOT_YET_ASSIGNED) {
-				U64 const end = tmpTotal + (count[s] * rStep);
-				U32 const sStart = (U32)(tmpTotal >> vStepLog);
-				U32 const sEnd = (U32)(end >> vStepLog);
-				U32 const weight = sEnd - sStart;
-				if (weight < 1)
-					return ERROR(GENERIC);
-				norm[s] = (short)weight;
-				tmpTotal = end;
-			}
-		}
-	}
-
-	return 0;
-}
-
-size_t FSE_normalizeCount(short *normalizedCounter, unsigned tableLog, const unsigned *count, size_t total, unsigned maxSymbolValue)
-{
-	/* Sanity checks */
-	if (tableLog == 0)
-		tableLog = FSE_DEFAULT_TABLELOG;
-	if (tableLog < FSE_MIN_TABLELOG)
-		return ERROR(GENERIC); /* Unsupported size */
-	if (tableLog > FSE_MAX_TABLELOG)
-		return ERROR(tableLog_tooLarge); /* Unsupported size */
-	if (tableLog < FSE_minTableLog(total, maxSymbolValue))
-		return ERROR(GENERIC); /* Too small tableLog, compression potentially impossible */
-
-	{
-		U32 const rtbTable[] = {0, 473195, 504333, 520860, 550000, 700000, 750000, 830000};
-		U64 const scale = 62 - tableLog;
-		U64 const step = div_u64((U64)1 << 62, (U32)total); /* <== here, one division ! */
-		U64 const vStep = 1ULL << (scale - 20);
-		int stillToDistribute = 1 << tableLog;
-		unsigned s;
-		unsigned largest = 0;
-		short largestP = 0;
-		U32 lowThreshold = (U32)(total >> tableLog);
-
-		for (s = 0; s <= maxSymbolValue; s++) {
-			if (count[s] == total)
-				return 0; /* rle special case */
-			if (count[s] == 0) {
-				normalizedCounter[s] = 0;
-				continue;
-			}
-			if (count[s] <= lowThreshold) {
-				normalizedCounter[s] = -1;
-				stillToDistribute--;
-			} else {
-				short proba = (short)((count[s] * step) >> scale);
-				if (proba < 8) {
-					U64 restToBeat = vStep * rtbTable[proba];
-					proba += (count[s] * step) - ((U64)proba << scale) > restToBeat;
-				}
-				if (proba > largestP)
-					largestP = proba, largest = s;
-				normalizedCounter[s] = proba;
-				stillToDistribute -= proba;
-			}
-		}
-		if (-stillToDistribute >= (normalizedCounter[largest] >> 1)) {
-			/* corner case, need another normalization method */
-			size_t const errorCode = FSE_normalizeM2(normalizedCounter, tableLog, count, total, maxSymbolValue);
-			if (FSE_isError(errorCode))
-				return errorCode;
-		} else
-			normalizedCounter[largest] += (short)stillToDistribute;
-	}
-
-	return tableLog;
-}
-
-/* fake FSE_CTable, for raw (uncompressed) input */
-size_t FSE_buildCTable_raw(FSE_CTable *ct, unsigned nbBits)
-{
-	const unsigned tableSize = 1 << nbBits;
-	const unsigned tableMask = tableSize - 1;
-	const unsigned maxSymbolValue = tableMask;
-	void *const ptr = ct;
-	U16 *const tableU16 = ((U16 *)ptr) + 2;
-	void *const FSCT = ((U32 *)ptr) + 1 /* header */ + (tableSize >> 1); /* assumption : tableLog >= 1 */
-	FSE_symbolCompressionTransform *const symbolTT = (FSE_symbolCompressionTransform *)(FSCT);
-	unsigned s;
-
-	/* Sanity checks */
-	if (nbBits < 1)
-		return ERROR(GENERIC); /* min size */
-
-	/* header */
-	tableU16[-2] = (U16)nbBits;
-	tableU16[-1] = (U16)maxSymbolValue;
-
-	/* Build table */
-	for (s = 0; s < tableSize; s++)
-		tableU16[s] = (U16)(tableSize + s);
-
-	/* Build Symbol Transformation Table */
-	{
-		const U32 deltaNbBits = (nbBits << 16) - (1 << nbBits);
-		for (s = 0; s <= maxSymbolValue; s++) {
-			symbolTT[s].deltaNbBits = deltaNbBits;
-			symbolTT[s].deltaFindState = s - 1;
-		}
-	}
-
-	return 0;
-}
-
-/* fake FSE_CTable, for rle input (always same symbol) */
-size_t FSE_buildCTable_rle(FSE_CTable *ct, BYTE symbolValue)
-{
-	void *ptr = ct;
-	U16 *tableU16 = ((U16 *)ptr) + 2;
-	void *FSCTptr = (U32 *)ptr + 2;
-	FSE_symbolCompressionTransform *symbolTT = (FSE_symbolCompressionTransform *)FSCTptr;
-
-	/* header */
-	tableU16[-2] = (U16)0;
-	tableU16[-1] = (U16)symbolValue;
-
-	/* Build table */
-	tableU16[0] = 0;
-	tableU16[1] = 0; /* just in case */
-
-	/* Build Symbol Transformation Table */
-	symbolTT[symbolValue].deltaNbBits = 0;
-	symbolTT[symbolValue].deltaFindState = 0;
-
-	return 0;
-}
-
-static size_t FSE_compress_usingCTable_generic(void *dst, size_t dstSize, const void *src, size_t srcSize, const FSE_CTable *ct, const unsigned fast)
-{
-	const BYTE *const istart = (const BYTE *)src;
-	const BYTE *const iend = istart + srcSize;
-	const BYTE *ip = iend;
-
-	BIT_CStream_t bitC;
-	FSE_CState_t CState1, CState2;
-
-	/* init */
-	if (srcSize <= 2)
-		return 0;
-	{
-		size_t const initError = BIT_initCStream(&bitC, dst, dstSize);
-		if (FSE_isError(initError))
-			return 0; /* not enough space available to write a bitstream */
-	}
-
-#define FSE_FLUSHBITS(s) (fast ? BIT_flushBitsFast(s) : BIT_flushBits(s))
-
-	if (srcSize & 1) {
-		FSE_initCState2(&CState1, ct, *--ip);
-		FSE_initCState2(&CState2, ct, *--ip);
-		FSE_encodeSymbol(&bitC, &CState1, *--ip);
-		FSE_FLUSHBITS(&bitC);
-	} else {
-		FSE_initCState2(&CState2, ct, *--ip);
-		FSE_initCState2(&CState1, ct, *--ip);
-	}
-
-	/* join to mod 4 */
-	srcSize -= 2;
-	if ((sizeof(bitC.bitContainer) * 8 > FSE_MAX_TABLELOG * 4 + 7) && (srcSize & 2)) { /* test bit 2 */
-		FSE_encodeSymbol(&bitC, &CState2, *--ip);
-		FSE_encodeSymbol(&bitC, &CState1, *--ip);
-		FSE_FLUSHBITS(&bitC);
-	}
-
-	/* 2 or 4 encoding per loop */
-	while (ip > istart) {
-
-		FSE_encodeSymbol(&bitC, &CState2, *--ip);
-
-		if (sizeof(bitC.bitContainer) * 8 < FSE_MAX_TABLELOG * 2 + 7) /* this test must be static */
-			FSE_FLUSHBITS(&bitC);
-
-		FSE_encodeSymbol(&bitC, &CState1, *--ip);
-
-		if (sizeof(bitC.bitContainer) * 8 > FSE_MAX_TABLELOG * 4 + 7) { /* this test must be static */
-			FSE_encodeSymbol(&bitC, &CState2, *--ip);
-			FSE_encodeSymbol(&bitC, &CState1, *--ip);
-		}
-
-		FSE_FLUSHBITS(&bitC);
-	}
-
-	FSE_flushCState(&bitC, &CState2);
-	FSE_flushCState(&bitC, &CState1);
-	return BIT_closeCStream(&bitC);
-}
-
-size_t FSE_compress_usingCTable(void *dst, size_t dstSize, const void *src, size_t srcSize, const FSE_CTable *ct)
-{
-	unsigned const fast = (dstSize >= FSE_BLOCKBOUND(srcSize));
-
-	if (fast)
-		return FSE_compress_usingCTable_generic(dst, dstSize, src, srcSize, ct, 1);
-	else
-		return FSE_compress_usingCTable_generic(dst, dstSize, src, srcSize, ct, 0);
-}
-
-size_t FSE_compressBound(size_t size) { return FSE_COMPRESSBOUND(size); }
diff --git a/lib/zstd/fse_decompress.c b/lib/zstd/fse_decompress.c
deleted file mode 100644
index 0b353530fb3f..000000000000
--- a/lib/zstd/fse_decompress.c
+++ /dev/null
@@ -1,325 +0,0 @@
-/*
- * FSE : Finite State Entropy decoder
- * Copyright (C) 2013-2015, Yann Collet.
- *
- * BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are
- * met:
- *
- *   * Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- *   * Redistributions in binary form must reproduce the above
- * copyright notice, this list of conditions and the following disclaimer
- * in the documentation and/or other materials provided with the
- * distribution.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * 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. This program is dual-licensed; you may select
- * either version 2 of the GNU General Public License ("GPL") or BSD license
- * ("BSD").
- *
- * You can contact the author at :
- * - Source repository : https://github.com/Cyan4973/FiniteStateEntropy
- */
-
-/* **************************************************************
-*  Compiler specifics
-****************************************************************/
-#define FORCE_INLINE static __always_inline
-
-/* **************************************************************
-*  Includes
-****************************************************************/
-#include "bitstream.h"
-#include "fse.h"
-#include "zstd_internal.h"
-#include <linux/compiler.h>
-#include <linux/kernel.h>
-#include <linux/string.h> /* memcpy, memset */
-
-/* **************************************************************
-*  Error Management
-****************************************************************/
-#define FSE_isError ERR_isError
-#define FSE_STATIC_ASSERT(c)                                   \
-	{                                                      \
-		enum { FSE_static_assert = 1 / (int)(!!(c)) }; \
-	} /* use only *after* variable declarations */
-
-/* **************************************************************
-*  Templates
-****************************************************************/
-/*
-  designed to be included
-  for type-specific functions (template emulation in C)
-  Objective is to write these functions only once, for improved maintenance
-*/
-
-/* safety checks */
-#ifndef FSE_FUNCTION_EXTENSION
-#error "FSE_FUNCTION_EXTENSION must be defined"
-#endif
-#ifndef FSE_FUNCTION_TYPE
-#error "FSE_FUNCTION_TYPE must be defined"
-#endif
-
-/* Function names */
-#define FSE_CAT(X, Y) X##Y
-#define FSE_FUNCTION_NAME(X, Y) FSE_CAT(X, Y)
-#define FSE_TYPE_NAME(X, Y) FSE_CAT(X, Y)
-
-/* Function templates */
-
-size_t FSE_buildDTable_wksp(FSE_DTable *dt, const short *normalizedCounter, unsigned maxSymbolValue, unsigned tableLog, void *workspace, size_t workspaceSize)
-{
-	void *const tdPtr = dt + 1; /* because *dt is unsigned, 32-bits aligned on 32-bits */
-	FSE_DECODE_TYPE *const tableDecode = (FSE_DECODE_TYPE *)(tdPtr);
-	U16 *symbolNext = (U16 *)workspace;
-
-	U32 const maxSV1 = maxSymbolValue + 1;
-	U32 const tableSize = 1 << tableLog;
-	U32 highThreshold = tableSize - 1;
-
-	/* Sanity Checks */
-	if (workspaceSize < sizeof(U16) * (FSE_MAX_SYMBOL_VALUE + 1))
-		return ERROR(tableLog_tooLarge);
-	if (maxSymbolValue > FSE_MAX_SYMBOL_VALUE)
-		return ERROR(maxSymbolValue_tooLarge);
-	if (tableLog > FSE_MAX_TABLELOG)
-		return ERROR(tableLog_tooLarge);
-
-	/* Init, lay down lowprob symbols */
-	{
-		FSE_DTableHeader DTableH;
-		DTableH.tableLog = (U16)tableLog;
-		DTableH.fastMode = 1;
-		{
-			S16 const largeLimit = (S16)(1 << (tableLog - 1));
-			U32 s;
-			for (s = 0; s < maxSV1; s++) {
-				if (normalizedCounter[s] == -1) {
-					tableDecode[highThreshold--].symbol = (FSE_FUNCTION_TYPE)s;
-					symbolNext[s] = 1;
-				} else {
-					if (normalizedCounter[s] >= largeLimit)
-						DTableH.fastMode = 0;
-					symbolNext[s] = normalizedCounter[s];
-				}
-			}
-		}
-		memcpy(dt, &DTableH, sizeof(DTableH));
-	}
-
-	/* Spread symbols */
-	{
-		U32 const tableMask = tableSize - 1;
-		U32 const step = FSE_TABLESTEP(tableSize);
-		U32 s, position = 0;
-		for (s = 0; s < maxSV1; s++) {
-			int i;
-			for (i = 0; i < normalizedCounter[s]; i++) {
-				tableDecode[position].symbol = (FSE_FUNCTION_TYPE)s;
-				position = (position + step) & tableMask;
-				while (position > highThreshold)
-					position = (position + step) & tableMask; /* lowprob area */
-			}
-		}
-		if (position != 0)
-			return ERROR(GENERIC); /* position must reach all cells once, otherwise normalizedCounter is incorrect */
-	}
-
-	/* Build Decoding table */
-	{
-		U32 u;
-		for (u = 0; u < tableSize; u++) {
-			FSE_FUNCTION_TYPE const symbol = (FSE_FUNCTION_TYPE)(tableDecode[u].symbol);
-			U16 nextState = symbolNext[symbol]++;
-			tableDecode[u].nbBits = (BYTE)(tableLog - BIT_highbit32((U32)nextState));
-			tableDecode[u].newState = (U16)((nextState << tableDecode[u].nbBits) - tableSize);
-		}
-	}
-
-	return 0;
-}
-
-/*-*******************************************************
-*  Decompression (Byte symbols)
-*********************************************************/
-size_t FSE_buildDTable_rle(FSE_DTable *dt, BYTE symbolValue)
-{
-	void *ptr = dt;
-	FSE_DTableHeader *const DTableH = (FSE_DTableHeader *)ptr;
-	void *dPtr = dt + 1;
-	FSE_decode_t *const cell = (FSE_decode_t *)dPtr;
-
-	DTableH->tableLog = 0;
-	DTableH->fastMode = 0;
-
-	cell->newState = 0;
-	cell->symbol = symbolValue;
-	cell->nbBits = 0;
-
-	return 0;
-}
-
-size_t FSE_buildDTable_raw(FSE_DTable *dt, unsigned nbBits)
-{
-	void *ptr = dt;
-	FSE_DTableHeader *const DTableH = (FSE_DTableHeader *)ptr;
-	void *dPtr = dt + 1;
-	FSE_decode_t *const dinfo = (FSE_decode_t *)dPtr;
-	const unsigned tableSize = 1 << nbBits;
-	const unsigned tableMask = tableSize - 1;
-	const unsigned maxSV1 = tableMask + 1;
-	unsigned s;
-
-	/* Sanity checks */
-	if (nbBits < 1)
-		return ERROR(GENERIC); /* min size */
-
-	/* Build Decoding Table */
-	DTableH->tableLog = (U16)nbBits;
-	DTableH->fastMode = 1;
-	for (s = 0; s < maxSV1; s++) {
-		dinfo[s].newState = 0;
-		dinfo[s].symbol = (BYTE)s;
-		dinfo[s].nbBits = (BYTE)nbBits;
-	}
-
-	return 0;
-}
-
-FORCE_INLINE size_t FSE_decompress_usingDTable_generic(void *dst, size_t maxDstSize, const void *cSrc, size_t cSrcSize, const FSE_DTable *dt,
-						       const unsigned fast)
-{
-	BYTE *const ostart = (BYTE *)dst;
-	BYTE *op = ostart;
-	BYTE *const omax = op + maxDstSize;
-	BYTE *const olimit = omax - 3;
-
-	BIT_DStream_t bitD;
-	FSE_DState_t state1;
-	FSE_DState_t state2;
-
-	/* Init */
-	CHECK_F(BIT_initDStream(&bitD, cSrc, cSrcSize));
-
-	FSE_initDState(&state1, &bitD, dt);
-	FSE_initDState(&state2, &bitD, dt);
-
-#define FSE_GETSYMBOL(statePtr) fast ? FSE_decodeSymbolFast(statePtr, &bitD) : FSE_decodeSymbol(statePtr, &bitD)
-
-	/* 4 symbols per loop */
-	for (; (BIT_reloadDStream(&bitD) == BIT_DStream_unfinished) & (op < olimit); op += 4) {
-		op[0] = FSE_GETSYMBOL(&state1);
-
-		if (FSE_MAX_TABLELOG * 2 + 7 > sizeof(bitD.bitContainer) * 8) /* This test must be static */
-			BIT_reloadDStream(&bitD);
-
-		op[1] = FSE_GETSYMBOL(&state2);
-
-		if (FSE_MAX_TABLELOG * 4 + 7 > sizeof(bitD.bitContainer) * 8) /* This test must be static */
-		{
-			if (BIT_reloadDStream(&bitD) > BIT_DStream_unfinished) {
-				op += 2;
-				break;
-			}
-		}
-
-		op[2] = FSE_GETSYMBOL(&state1);
-
-		if (FSE_MAX_TABLELOG * 2 + 7 > sizeof(bitD.bitContainer) * 8) /* This test must be static */
-			BIT_reloadDStream(&bitD);
-
-		op[3] = FSE_GETSYMBOL(&state2);
-	}
-
-	/* tail */
-	/* note : BIT_reloadDStream(&bitD) >= FSE_DStream_partiallyFilled; Ends at exactly BIT_DStream_completed */
-	while (1) {
-		if (op > (omax - 2))
-			return ERROR(dstSize_tooSmall);
-		*op++ = FSE_GETSYMBOL(&state1);
-		if (BIT_reloadDStream(&bitD) == BIT_DStream_overflow) {
-			*op++ = FSE_GETSYMBOL(&state2);
-			break;
-		}
-
-		if (op > (omax - 2))
-			return ERROR(dstSize_tooSmall);
-		*op++ = FSE_GETSYMBOL(&state2);
-		if (BIT_reloadDStream(&bitD) == BIT_DStream_overflow) {
-			*op++ = FSE_GETSYMBOL(&state1);
-			break;
-		}
-	}
-
-	return op - ostart;
-}
-
-size_t FSE_decompress_usingDTable(void *dst, size_t originalSize, const void *cSrc, size_t cSrcSize, const FSE_DTable *dt)
-{
-	const void *ptr = dt;
-	const FSE_DTableHeader *DTableH = (const FSE_DTableHeader *)ptr;
-	const U32 fastMode = DTableH->fastMode;
-
-	/* select fast mode (static) */
-	if (fastMode)
-		return FSE_decompress_usingDTable_generic(dst, originalSize, cSrc, cSrcSize, dt, 1);
-	return FSE_decompress_usingDTable_generic(dst, originalSize, cSrc, cSrcSize, dt, 0);
-}
-
-size_t FSE_decompress_wksp(void *dst, size_t dstCapacity, const void *cSrc, size_t cSrcSize, unsigned maxLog, void *workspace, size_t workspaceSize)
-{
-	const BYTE *const istart = (const BYTE *)cSrc;
-	const BYTE *ip = istart;
-	unsigned tableLog;
-	unsigned maxSymbolValue = FSE_MAX_SYMBOL_VALUE;
-	size_t NCountLength;
-
-	FSE_DTable *dt;
-	short *counting;
-	size_t spaceUsed32 = 0;
-
-	FSE_STATIC_ASSERT(sizeof(FSE_DTable) == sizeof(U32));
-
-	dt = (FSE_DTable *)((U32 *)workspace + spaceUsed32);
-	spaceUsed32 += FSE_DTABLE_SIZE_U32(maxLog);
-	counting = (short *)((U32 *)workspace + spaceUsed32);
-	spaceUsed32 += ALIGN(sizeof(short) * (FSE_MAX_SYMBOL_VALUE + 1), sizeof(U32)) >> 2;
-
-	if ((spaceUsed32 << 2) > workspaceSize)
-		return ERROR(tableLog_tooLarge);
-	workspace = (U32 *)workspace + spaceUsed32;
-	workspaceSize -= (spaceUsed32 << 2);
-
-	/* normal FSE decoding mode */
-	NCountLength = FSE_readNCount(counting, &maxSymbolValue, &tableLog, istart, cSrcSize);
-	if (FSE_isError(NCountLength))
-		return NCountLength;
-	// if (NCountLength >= cSrcSize) return ERROR(srcSize_wrong);   /* too small input size; supposed to be already checked in NCountLength, only remaining
-	// case : NCountLength==cSrcSize */
-	if (tableLog > maxLog)
-		return ERROR(tableLog_tooLarge);
-	ip += NCountLength;
-	cSrcSize -= NCountLength;
-
-	CHECK_F(FSE_buildDTable_wksp(dt, counting, maxSymbolValue, tableLog, workspace, workspaceSize));
-
-	return FSE_decompress_usingDTable(dst, dstCapacity, ip, cSrcSize, dt); /* always return, even if it is an error code */
-}
diff --git a/lib/zstd/huf.h b/lib/zstd/huf.h
deleted file mode 100644
index 923218d12e28..000000000000
--- a/lib/zstd/huf.h
+++ /dev/null
@@ -1,212 +0,0 @@
-/*
- * Huffman coder, part of New Generation Entropy library
- * header file
- * Copyright (C) 2013-2016, Yann Collet.
- *
- * BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are
- * met:
- *
- *   * Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- *   * Redistributions in binary form must reproduce the above
- * copyright notice, this list of conditions and the following disclaimer
- * in the documentation and/or other materials provided with the
- * distribution.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * 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. This program is dual-licensed; you may select
- * either version 2 of the GNU General Public License ("GPL") or BSD license
- * ("BSD").
- *
- * You can contact the author at :
- * - Source repository : https://github.com/Cyan4973/FiniteStateEntropy
- */
-#ifndef HUF_H_298734234
-#define HUF_H_298734234
-
-/* *** Dependencies *** */
-#include <linux/types.h> /* size_t */
-
-/* ***   Tool functions *** */
-#define HUF_BLOCKSIZE_MAX (128 * 1024) /**< maximum input size for a single block compressed with HUF_compress */
-size_t HUF_compressBound(size_t size); /**< maximum compressed size (worst case) */
-
-/* Error Management */
-unsigned HUF_isError(size_t code); /**< tells if a return value is an error code */
-
-/* ***   Advanced function   *** */
-
-/** HUF_compress4X_wksp() :
-*   Same as HUF_compress2(), but uses externally allocated `workSpace`, which must be a table of >= 1024 unsigned */
-size_t HUF_compress4X_wksp(void *dst, size_t dstSize, const void *src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog, void *workSpace,
-			   size_t wkspSize); /**< `workSpace` must be a table of at least HUF_COMPRESS_WORKSPACE_SIZE_U32 unsigned */
-
-/* *** Dependencies *** */
-#include "mem.h" /* U32 */
-
-/* *** Constants *** */
-#define HUF_TABLELOG_MAX 12     /* max configured tableLog (for static allocation); can be modified up to HUF_ABSOLUTEMAX_TABLELOG */
-#define HUF_TABLELOG_DEFAULT 11 /* tableLog by default, when not specified */
-#define HUF_SYMBOLVALUE_MAX 255
-
-#define HUF_TABLELOG_ABSOLUTEMAX 15 /* absolute limit of HUF_MAX_TABLELOG. Beyond that value, code does not work */
-#if (HUF_TABLELOG_MAX > HUF_TABLELOG_ABSOLUTEMAX)
-#error "HUF_TABLELOG_MAX is too large !"
-#endif
-
-/* ****************************************
-*  Static allocation
-******************************************/
-/* HUF buffer bounds */
-#define HUF_CTABLEBOUND 129
-#define HUF_BLOCKBOUND(size) (size + (size >> 8) + 8)			 /* only true if incompressible pre-filtered with fast heuristic */
-#define HUF_COMPRESSBOUND(size) (HUF_CTABLEBOUND + HUF_BLOCKBOUND(size)) /* Macro version, useful for static allocation */
-
-/* static allocation of HUF's Compression Table */
-#define HUF_CREATE_STATIC_CTABLE(name, maxSymbolValue) \
-	U32 name##hb[maxSymbolValue + 1];              \
-	void *name##hv = &(name##hb);                  \
-	HUF_CElt *name = (HUF_CElt *)(name##hv) /* no final ; */
-
-/* static allocation of HUF's DTable */
-typedef U32 HUF_DTable;
-#define HUF_DTABLE_SIZE(maxTableLog) (1 + (1 << (maxTableLog)))
-#define HUF_CREATE_STATIC_DTABLEX2(DTable, maxTableLog) HUF_DTable DTable[HUF_DTABLE_SIZE((maxTableLog)-1)] = {((U32)((maxTableLog)-1) * 0x01000001)}
-#define HUF_CREATE_STATIC_DTABLEX4(DTable, maxTableLog) HUF_DTable DTable[HUF_DTABLE_SIZE(maxTableLog)] = {((U32)(maxTableLog)*0x01000001)}
-
-/* The workspace must have alignment at least 4 and be at least this large */
-#define HUF_COMPRESS_WORKSPACE_SIZE (6 << 10)
-#define HUF_COMPRESS_WORKSPACE_SIZE_U32 (HUF_COMPRESS_WORKSPACE_SIZE / sizeof(U32))
-
-/* The workspace must have alignment at least 4 and be at least this large */
-#define HUF_DECOMPRESS_WORKSPACE_SIZE (3 << 10)
-#define HUF_DECOMPRESS_WORKSPACE_SIZE_U32 (HUF_DECOMPRESS_WORKSPACE_SIZE / sizeof(U32))
-
-/* ****************************************
-*  Advanced decompression functions
-******************************************/
-size_t HUF_decompress4X_DCtx_wksp(HUF_DTable *dctx, void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, void *workspace, size_t workspaceSize); /**< decodes RLE and uncompressed */
-size_t HUF_decompress4X_hufOnly_wksp(HUF_DTable *dctx, void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, void *workspace,
-				size_t workspaceSize);							       /**< considers RLE and uncompressed as errors */
-size_t HUF_decompress4X2_DCtx_wksp(HUF_DTable *dctx, void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, void *workspace,
-				   size_t workspaceSize); /**< single-symbol decoder */
-size_t HUF_decompress4X4_DCtx_wksp(HUF_DTable *dctx, void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, void *workspace,
-				   size_t workspaceSize); /**< double-symbols decoder */
-
-/* ****************************************
-*  HUF detailed API
-******************************************/
-/*!
-HUF_compress() does the following:
-1. count symbol occurrence from source[] into table count[] using FSE_count()
-2. (optional) refine tableLog using HUF_optimalTableLog()
-3. build Huffman table from count using HUF_buildCTable()
-4. save Huffman table to memory buffer using HUF_writeCTable_wksp()
-5. encode the data stream using HUF_compress4X_usingCTable()
-
-The following API allows targeting specific sub-functions for advanced tasks.
-For example, it's possible to compress several blocks using the same 'CTable',
-or to save and regenerate 'CTable' using external methods.
-*/
-/* FSE_count() : find it within "fse.h" */
-unsigned HUF_optimalTableLog(unsigned maxTableLog, size_t srcSize, unsigned maxSymbolValue);
-typedef struct HUF_CElt_s HUF_CElt; /* incomplete type */
-size_t HUF_writeCTable_wksp(void *dst, size_t maxDstSize, const HUF_CElt *CTable, unsigned maxSymbolValue, unsigned huffLog, void *workspace, size_t workspaceSize);
-size_t HUF_compress4X_usingCTable(void *dst, size_t dstSize, const void *src, size_t srcSize, const HUF_CElt *CTable);
-
-typedef enum {
-	HUF_repeat_none,  /**< Cannot use the previous table */
-	HUF_repeat_check, /**< Can use the previous table but it must be checked. Note : The previous table must have been constructed by HUF_compress{1,
-			     4}X_repeat */
-	HUF_repeat_valid  /**< Can use the previous table and it is assumed to be valid */
-} HUF_repeat;
-/** HUF_compress4X_repeat() :
-*   Same as HUF_compress4X_wksp(), but considers using hufTable if *repeat != HUF_repeat_none.
-*   If it uses hufTable it does not modify hufTable or repeat.
-*   If it doesn't, it sets *repeat = HUF_repeat_none, and it sets hufTable to the table used.
-*   If preferRepeat then the old table will always be used if valid. */
-size_t HUF_compress4X_repeat(void *dst, size_t dstSize, const void *src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog, void *workSpace,
-			     size_t wkspSize, HUF_CElt *hufTable, HUF_repeat *repeat,
-			     int preferRepeat); /**< `workSpace` must be a table of at least HUF_COMPRESS_WORKSPACE_SIZE_U32 unsigned */
-
-/** HUF_buildCTable_wksp() :
- *  Same as HUF_buildCTable(), but using externally allocated scratch buffer.
- *  `workSpace` must be aligned on 4-bytes boundaries, and be at least as large as a table of 1024 unsigned.
- */
-size_t HUF_buildCTable_wksp(HUF_CElt *tree, const U32 *count, U32 maxSymbolValue, U32 maxNbBits, void *workSpace, size_t wkspSize);
-
-/*! HUF_readStats() :
-	Read compact Huffman tree, saved by HUF_writeCTable().
-	`huffWeight` is destination buffer.
-	@return : size read from `src` , or an error Code .
-	Note : Needed by HUF_readCTable() and HUF_readDTableXn() . */
-size_t HUF_readStats_wksp(BYTE *huffWeight, size_t hwSize, U32 *rankStats, U32 *nbSymbolsPtr, U32 *tableLogPtr, const void *src, size_t srcSize,
-			  void *workspace, size_t workspaceSize);
-
-/** HUF_readCTable() :
-*   Loading a CTable saved with HUF_writeCTable() */
-size_t HUF_readCTable_wksp(HUF_CElt *CTable, unsigned maxSymbolValue, const void *src, size_t srcSize, void *workspace, size_t workspaceSize);
-
-/*
-HUF_decompress() does the following:
-1. select the decompression algorithm (X2, X4) based on pre-computed heuristics
-2. build Huffman table from save, using HUF_readDTableXn()
-3. decode 1 or 4 segments in parallel using HUF_decompressSXn_usingDTable
-*/
-
-/** HUF_selectDecoder() :
-*   Tells which decoder is likely to decode faster,
-*   based on a set of pre-determined metrics.
-*   @return : 0==HUF_decompress4X2, 1==HUF_decompress4X4 .
-*   Assumption : 0 < cSrcSize < dstSize <= 128 KB */
-U32 HUF_selectDecoder(size_t dstSize, size_t cSrcSize);
-
-size_t HUF_readDTableX2_wksp(HUF_DTable *DTable, const void *src, size_t srcSize, void *workspace, size_t workspaceSize);
-size_t HUF_readDTableX4_wksp(HUF_DTable *DTable, const void *src, size_t srcSize, void *workspace, size_t workspaceSize);
-
-size_t HUF_decompress4X_usingDTable(void *dst, size_t maxDstSize, const void *cSrc, size_t cSrcSize, const HUF_DTable *DTable);
-size_t HUF_decompress4X2_usingDTable(void *dst, size_t maxDstSize, const void *cSrc, size_t cSrcSize, const HUF_DTable *DTable);
-size_t HUF_decompress4X4_usingDTable(void *dst, size_t maxDstSize, const void *cSrc, size_t cSrcSize, const HUF_DTable *DTable);
-
-/* single stream variants */
-
-size_t HUF_compress1X_wksp(void *dst, size_t dstSize, const void *src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog, void *workSpace,
-			   size_t wkspSize); /**< `workSpace` must be a table of at least HUF_COMPRESS_WORKSPACE_SIZE_U32 unsigned */
-size_t HUF_compress1X_usingCTable(void *dst, size_t dstSize, const void *src, size_t srcSize, const HUF_CElt *CTable);
-/** HUF_compress1X_repeat() :
-*   Same as HUF_compress1X_wksp(), but considers using hufTable if *repeat != HUF_repeat_none.
-*   If it uses hufTable it does not modify hufTable or repeat.
-*   If it doesn't, it sets *repeat = HUF_repeat_none, and it sets hufTable to the table used.
-*   If preferRepeat then the old table will always be used if valid. */
-size_t HUF_compress1X_repeat(void *dst, size_t dstSize, const void *src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog, void *workSpace,
-			     size_t wkspSize, HUF_CElt *hufTable, HUF_repeat *repeat,
-			     int preferRepeat); /**< `workSpace` must be a table of at least HUF_COMPRESS_WORKSPACE_SIZE_U32 unsigned */
-
-size_t HUF_decompress1X_DCtx_wksp(HUF_DTable *dctx, void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, void *workspace, size_t workspaceSize);
-size_t HUF_decompress1X2_DCtx_wksp(HUF_DTable *dctx, void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, void *workspace,
-				   size_t workspaceSize); /**< single-symbol decoder */
-size_t HUF_decompress1X4_DCtx_wksp(HUF_DTable *dctx, void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, void *workspace,
-				   size_t workspaceSize); /**< double-symbols decoder */
-
-size_t HUF_decompress1X_usingDTable(void *dst, size_t maxDstSize, const void *cSrc, size_t cSrcSize,
-				    const HUF_DTable *DTable); /**< automatic selection of sing or double symbol decoder, based on DTable */
-size_t HUF_decompress1X2_usingDTable(void *dst, size_t maxDstSize, const void *cSrc, size_t cSrcSize, const HUF_DTable *DTable);
-size_t HUF_decompress1X4_usingDTable(void *dst, size_t maxDstSize, const void *cSrc, size_t cSrcSize, const HUF_DTable *DTable);
-
-#endif /* HUF_H_298734234 */
diff --git a/lib/zstd/huf_compress.c b/lib/zstd/huf_compress.c
deleted file mode 100644
index fd32838c185f..000000000000
--- a/lib/zstd/huf_compress.c
+++ /dev/null
@@ -1,773 +0,0 @@
-/*
- * Huffman encoder, part of New Generation Entropy library
- * Copyright (C) 2013-2016, Yann Collet.
- *
- * BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are
- * met:
- *
- *   * Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- *   * Redistributions in binary form must reproduce the above
- * copyright notice, this list of conditions and the following disclaimer
- * in the documentation and/or other materials provided with the
- * distribution.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * 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. This program is dual-licensed; you may select
- * either version 2 of the GNU General Public License ("GPL") or BSD license
- * ("BSD").
- *
- * You can contact the author at :
- * - Source repository : https://github.com/Cyan4973/FiniteStateEntropy
- */
-
-/* **************************************************************
-*  Includes
-****************************************************************/
-#include "bitstream.h"
-#include "fse.h" /* header compression */
-#include "huf.h"
-#include <linux/kernel.h>
-#include <linux/string.h> /* memcpy, memset */
-
-/* **************************************************************
-*  Error Management
-****************************************************************/
-#define HUF_STATIC_ASSERT(c)                                   \
-	{                                                      \
-		enum { HUF_static_assert = 1 / (int)(!!(c)) }; \
-	} /* use only *after* variable declarations */
-#define CHECK_V_F(e, f)     \
-	size_t const e = f; \
-	if (ERR_isError(e)) \
-	return f
-#define CHECK_F(f)                        \
-	{                                 \
-		CHECK_V_F(_var_err__, f); \
-	}
-
-/* **************************************************************
-*  Utils
-****************************************************************/
-unsigned HUF_optimalTableLog(unsigned maxTableLog, size_t srcSize, unsigned maxSymbolValue)
-{
-	return FSE_optimalTableLog_internal(maxTableLog, srcSize, maxSymbolValue, 1);
-}
-
-/* *******************************************************
-*  HUF : Huffman block compression
-*********************************************************/
-/* HUF_compressWeights() :
- * Same as FSE_compress(), but dedicated to huff0's weights compression.
- * The use case needs much less stack memory.
- * Note : all elements within weightTable are supposed to be <= HUF_TABLELOG_MAX.
- */
-#define MAX_FSE_TABLELOG_FOR_HUFF_HEADER 6
-size_t HUF_compressWeights_wksp(void *dst, size_t dstSize, const void *weightTable, size_t wtSize, void *workspace, size_t workspaceSize)
-{
-	BYTE *const ostart = (BYTE *)dst;
-	BYTE *op = ostart;
-	BYTE *const oend = ostart + dstSize;
-
-	U32 maxSymbolValue = HUF_TABLELOG_MAX;
-	U32 tableLog = MAX_FSE_TABLELOG_FOR_HUFF_HEADER;
-
-	FSE_CTable *CTable;
-	U32 *count;
-	S16 *norm;
-	size_t spaceUsed32 = 0;
-
-	HUF_STATIC_ASSERT(sizeof(FSE_CTable) == sizeof(U32));
-
-	CTable = (FSE_CTable *)((U32 *)workspace + spaceUsed32);
-	spaceUsed32 += FSE_CTABLE_SIZE_U32(MAX_FSE_TABLELOG_FOR_HUFF_HEADER, HUF_TABLELOG_MAX);
-	count = (U32 *)workspace + spaceUsed32;
-	spaceUsed32 += HUF_TABLELOG_MAX + 1;
-	norm = (S16 *)((U32 *)workspace + spaceUsed32);
-	spaceUsed32 += ALIGN(sizeof(S16) * (HUF_TABLELOG_MAX + 1), sizeof(U32)) >> 2;
-
-	if ((spaceUsed32 << 2) > workspaceSize)
-		return ERROR(tableLog_tooLarge);
-	workspace = (U32 *)workspace + spaceUsed32;
-	workspaceSize -= (spaceUsed32 << 2);
-
-	/* init conditions */
-	if (wtSize <= 1)
-		return 0; /* Not compressible */
-
-	/* Scan input and build symbol stats */
-	{
-		CHECK_V_F(maxCount, FSE_count_simple(count, &maxSymbolValue, weightTable, wtSize));
-		if (maxCount == wtSize)
-			return 1; /* only a single symbol in src : rle */
-		if (maxCount == 1)
-			return 0; /* each symbol present maximum once => not compressible */
-	}
-
-	tableLog = FSE_optimalTableLog(tableLog, wtSize, maxSymbolValue);
-	CHECK_F(FSE_normalizeCount(norm, tableLog, count, wtSize, maxSymbolValue));
-
-	/* Write table description header */
-	{
-		CHECK_V_F(hSize, FSE_writeNCount(op, oend - op, norm, maxSymbolValue, tableLog));
-		op += hSize;
-	}
-
-	/* Compress */
-	CHECK_F(FSE_buildCTable_wksp(CTable, norm, maxSymbolValue, tableLog, workspace, workspaceSize));
-	{
-		CHECK_V_F(cSize, FSE_compress_usingCTable(op, oend - op, weightTable, wtSize, CTable));
-		if (cSize == 0)
-			return 0; /* not enough space for compressed data */
-		op += cSize;
-	}
-
-	return op - ostart;
-}
-
-struct HUF_CElt_s {
-	U16 val;
-	BYTE nbBits;
-}; /* typedef'd to HUF_CElt within "huf.h" */
-
-/*! HUF_writeCTable_wksp() :
-	`CTable` : Huffman tree to save, using huf representation.
-	@return : size of saved CTable */
-size_t HUF_writeCTable_wksp(void *dst, size_t maxDstSize, const HUF_CElt *CTable, U32 maxSymbolValue, U32 huffLog, void *workspace, size_t workspaceSize)
-{
-	BYTE *op = (BYTE *)dst;
-	U32 n;
-
-	BYTE *bitsToWeight;
-	BYTE *huffWeight;
-	size_t spaceUsed32 = 0;
-
-	bitsToWeight = (BYTE *)((U32 *)workspace + spaceUsed32);
-	spaceUsed32 += ALIGN(HUF_TABLELOG_MAX + 1, sizeof(U32)) >> 2;
-	huffWeight = (BYTE *)((U32 *)workspace + spaceUsed32);
-	spaceUsed32 += ALIGN(HUF_SYMBOLVALUE_MAX, sizeof(U32)) >> 2;
-
-	if ((spaceUsed32 << 2) > workspaceSize)
-		return ERROR(tableLog_tooLarge);
-	workspace = (U32 *)workspace + spaceUsed32;
-	workspaceSize -= (spaceUsed32 << 2);
-
-	/* check conditions */
-	if (maxSymbolValue > HUF_SYMBOLVALUE_MAX)
-		return ERROR(maxSymbolValue_tooLarge);
-
-	/* convert to weight */
-	bitsToWeight[0] = 0;
-	for (n = 1; n < huffLog + 1; n++)
-		bitsToWeight[n] = (BYTE)(huffLog + 1 - n);
-	for (n = 0; n < maxSymbolValue; n++)
-		huffWeight[n] = bitsToWeight[CTable[n].nbBits];
-
-	/* attempt weights compression by FSE */
-	{
-		CHECK_V_F(hSize, HUF_compressWeights_wksp(op + 1, maxDstSize - 1, huffWeight, maxSymbolValue, workspace, workspaceSize));
-		if ((hSize > 1) & (hSize < maxSymbolValue / 2)) { /* FSE compressed */
-			op[0] = (BYTE)hSize;
-			return hSize + 1;
-		}
-	}
-
-	/* write raw values as 4-bits (max : 15) */
-	if (maxSymbolValue > (256 - 128))
-		return ERROR(GENERIC); /* should not happen : likely means source cannot be compressed */
-	if (((maxSymbolValue + 1) / 2) + 1 > maxDstSize)
-		return ERROR(dstSize_tooSmall); /* not enough space within dst buffer */
-	op[0] = (BYTE)(128 /*special case*/ + (maxSymbolValue - 1));
-	huffWeight[maxSymbolValue] = 0; /* to be sure it doesn't cause msan issue in final combination */
-	for (n = 0; n < maxSymbolValue; n += 2)
-		op[(n / 2) + 1] = (BYTE)((huffWeight[n] << 4) + huffWeight[n + 1]);
-	return ((maxSymbolValue + 1) / 2) + 1;
-}
-
-size_t HUF_readCTable_wksp(HUF_CElt *CTable, U32 maxSymbolValue, const void *src, size_t srcSize, void *workspace, size_t workspaceSize)
-{
-	U32 *rankVal;
-	BYTE *huffWeight;
-	U32 tableLog = 0;
-	U32 nbSymbols = 0;
-	size_t readSize;
-	size_t spaceUsed32 = 0;
-
-	rankVal = (U32 *)workspace + spaceUsed32;
-	spaceUsed32 += HUF_TABLELOG_ABSOLUTEMAX + 1;
-	huffWeight = (BYTE *)((U32 *)workspace + spaceUsed32);
-	spaceUsed32 += ALIGN(HUF_SYMBOLVALUE_MAX + 1, sizeof(U32)) >> 2;
-
-	if ((spaceUsed32 << 2) > workspaceSize)
-		return ERROR(tableLog_tooLarge);
-	workspace = (U32 *)workspace + spaceUsed32;
-	workspaceSize -= (spaceUsed32 << 2);
-
-	/* get symbol weights */
-	readSize = HUF_readStats_wksp(huffWeight, HUF_SYMBOLVALUE_MAX + 1, rankVal, &nbSymbols, &tableLog, src, srcSize, workspace, workspaceSize);
-	if (ERR_isError(readSize))
-		return readSize;
-
-	/* check result */
-	if (tableLog > HUF_TABLELOG_MAX)
-		return ERROR(tableLog_tooLarge);
-	if (nbSymbols > maxSymbolValue + 1)
-		return ERROR(maxSymbolValue_tooSmall);
-
-	/* Prepare base value per rank */
-	{
-		U32 n, nextRankStart = 0;
-		for (n = 1; n <= tableLog; n++) {
-			U32 curr = nextRankStart;
-			nextRankStart += (rankVal[n] << (n - 1));
-			rankVal[n] = curr;
-		}
-	}
-
-	/* fill nbBits */
-	{
-		U32 n;
-		for (n = 0; n < nbSymbols; n++) {
-			const U32 w = huffWeight[n];
-			CTable[n].nbBits = (BYTE)(tableLog + 1 - w);
-		}
-	}
-
-	/* fill val */
-	{
-		U16 nbPerRank[HUF_TABLELOG_MAX + 2] = {0}; /* support w=0=>n=tableLog+1 */
-		U16 valPerRank[HUF_TABLELOG_MAX + 2] = {0};
-		{
-			U32 n;
-			for (n = 0; n < nbSymbols; n++)
-				nbPerRank[CTable[n].nbBits]++;
-		}
-		/* determine stating value per rank */
-		valPerRank[tableLog + 1] = 0; /* for w==0 */
-		{
-			U16 min = 0;
-			U32 n;
-			for (n = tableLog; n > 0; n--) { /* start at n=tablelog <-> w=1 */
-				valPerRank[n] = min;     /* get starting value within each rank */
-				min += nbPerRank[n];
-				min >>= 1;
-			}
-		}
-		/* assign value within rank, symbol order */
-		{
-			U32 n;
-			for (n = 0; n <= maxSymbolValue; n++)
-				CTable[n].val = valPerRank[CTable[n].nbBits]++;
-		}
-	}
-
-	return readSize;
-}
-
-typedef struct nodeElt_s {
-	U32 count;
-	U16 parent;
-	BYTE byte;
-	BYTE nbBits;
-} nodeElt;
-
-static U32 HUF_setMaxHeight(nodeElt *huffNode, U32 lastNonNull, U32 maxNbBits)
-{
-	const U32 largestBits = huffNode[lastNonNull].nbBits;
-	if (largestBits <= maxNbBits)
-		return largestBits; /* early exit : no elt > maxNbBits */
-
-	/* there are several too large elements (at least >= 2) */
-	{
-		int totalCost = 0;
-		const U32 baseCost = 1 << (largestBits - maxNbBits);
-		U32 n = lastNonNull;
-
-		while (huffNode[n].nbBits > maxNbBits) {
-			totalCost += baseCost - (1 << (largestBits - huffNode[n].nbBits));
-			huffNode[n].nbBits = (BYTE)maxNbBits;
-			n--;
-		} /* n stops at huffNode[n].nbBits <= maxNbBits */
-		while (huffNode[n].nbBits == maxNbBits)
-			n--; /* n end at index of smallest symbol using < maxNbBits */
-
-		/* renorm totalCost */
-		totalCost >>= (largestBits - maxNbBits); /* note : totalCost is necessarily a multiple of baseCost */
-
-		/* repay normalized cost */
-		{
-			U32 const noSymbol = 0xF0F0F0F0;
-			U32 rankLast[HUF_TABLELOG_MAX + 2];
-			int pos;
-
-			/* Get pos of last (smallest) symbol per rank */
-			memset(rankLast, 0xF0, sizeof(rankLast));
-			{
-				U32 currNbBits = maxNbBits;
-				for (pos = n; pos >= 0; pos--) {
-					if (huffNode[pos].nbBits >= currNbBits)
-						continue;
-					currNbBits = huffNode[pos].nbBits; /* < maxNbBits */
-					rankLast[maxNbBits - currNbBits] = pos;
-				}
-			}
-
-			while (totalCost > 0) {
-				U32 nBitsToDecrease = BIT_highbit32(totalCost) + 1;
-				for (; nBitsToDecrease > 1; nBitsToDecrease--) {
-					U32 highPos = rankLast[nBitsToDecrease];
-					U32 lowPos = rankLast[nBitsToDecrease - 1];
-					if (highPos == noSymbol)
-						continue;
-					if (lowPos == noSymbol)
-						break;
-					{
-						U32 const highTotal = huffNode[highPos].count;
-						U32 const lowTotal = 2 * huffNode[lowPos].count;
-						if (highTotal <= lowTotal)
-							break;
-					}
-				}
-				/* only triggered when no more rank 1 symbol left => find closest one (note : there is necessarily at least one !) */
-				/* HUF_MAX_TABLELOG test just to please gcc 5+; but it should not be necessary */
-				while ((nBitsToDecrease <= HUF_TABLELOG_MAX) && (rankLast[nBitsToDecrease] == noSymbol))
-					nBitsToDecrease++;
-				totalCost -= 1 << (nBitsToDecrease - 1);
-				if (rankLast[nBitsToDecrease - 1] == noSymbol)
-					rankLast[nBitsToDecrease - 1] = rankLast[nBitsToDecrease]; /* this rank is no longer empty */
-				huffNode[rankLast[nBitsToDecrease]].nbBits++;
-				if (rankLast[nBitsToDecrease] == 0) /* special case, reached largest symbol */
-					rankLast[nBitsToDecrease] = noSymbol;
-				else {
-					rankLast[nBitsToDecrease]--;
-					if (huffNode[rankLast[nBitsToDecrease]].nbBits != maxNbBits - nBitsToDecrease)
-						rankLast[nBitsToDecrease] = noSymbol; /* this rank is now empty */
-				}
-			} /* while (totalCost > 0) */
-
-			while (totalCost < 0) {		       /* Sometimes, cost correction overshoot */
-				if (rankLast[1] == noSymbol) { /* special case : no rank 1 symbol (using maxNbBits-1); let's create one from largest rank 0
-								  (using maxNbBits) */
-					while (huffNode[n].nbBits == maxNbBits)
-						n--;
-					huffNode[n + 1].nbBits--;
-					rankLast[1] = n + 1;
-					totalCost++;
-					continue;
-				}
-				huffNode[rankLast[1] + 1].nbBits--;
-				rankLast[1]++;
-				totalCost++;
-			}
-		}
-	} /* there are several too large elements (at least >= 2) */
-
-	return maxNbBits;
-}
-
-typedef struct {
-	U32 base;
-	U32 curr;
-} rankPos;
-
-static void HUF_sort(nodeElt *huffNode, const U32 *count, U32 maxSymbolValue)
-{
-	rankPos rank[32];
-	U32 n;
-
-	memset(rank, 0, sizeof(rank));
-	for (n = 0; n <= maxSymbolValue; n++) {
-		U32 r = BIT_highbit32(count[n] + 1);
-		rank[r].base++;
-	}
-	for (n = 30; n > 0; n--)
-		rank[n - 1].base += rank[n].base;
-	for (n = 0; n < 32; n++)
-		rank[n].curr = rank[n].base;
-	for (n = 0; n <= maxSymbolValue; n++) {
-		U32 const c = count[n];
-		U32 const r = BIT_highbit32(c + 1) + 1;
-		U32 pos = rank[r].curr++;
-		while ((pos > rank[r].base) && (c > huffNode[pos - 1].count))
-			huffNode[pos] = huffNode[pos - 1], pos--;
-		huffNode[pos].count = c;
-		huffNode[pos].byte = (BYTE)n;
-	}
-}
-
-/** HUF_buildCTable_wksp() :
- *  Same as HUF_buildCTable(), but using externally allocated scratch buffer.
- *  `workSpace` must be aligned on 4-bytes boundaries, and be at least as large as a table of 1024 unsigned.
- */
-#define STARTNODE (HUF_SYMBOLVALUE_MAX + 1)
-typedef nodeElt huffNodeTable[2 * HUF_SYMBOLVALUE_MAX + 1 + 1];
-size_t HUF_buildCTable_wksp(HUF_CElt *tree, const U32 *count, U32 maxSymbolValue, U32 maxNbBits, void *workSpace, size_t wkspSize)
-{
-	nodeElt *const huffNode0 = (nodeElt *)workSpace;
-	nodeElt *const huffNode = huffNode0 + 1;
-	U32 n, nonNullRank;
-	int lowS, lowN;
-	U16 nodeNb = STARTNODE;
-	U32 nodeRoot;
-
-	/* safety checks */
-	if (wkspSize < sizeof(huffNodeTable))
-		return ERROR(GENERIC); /* workSpace is not large enough */
-	if (maxNbBits == 0)
-		maxNbBits = HUF_TABLELOG_DEFAULT;
-	if (maxSymbolValue > HUF_SYMBOLVALUE_MAX)
-		return ERROR(GENERIC);
-	memset(huffNode0, 0, sizeof(huffNodeTable));
-
-	/* sort, decreasing order */
-	HUF_sort(huffNode, count, maxSymbolValue);
-
-	/* init for parents */
-	nonNullRank = maxSymbolValue;
-	while (huffNode[nonNullRank].count == 0)
-		nonNullRank--;
-	lowS = nonNullRank;
-	nodeRoot = nodeNb + lowS - 1;
-	lowN = nodeNb;
-	huffNode[nodeNb].count = huffNode[lowS].count + huffNode[lowS - 1].count;
-	huffNode[lowS].parent = huffNode[lowS - 1].parent = nodeNb;
-	nodeNb++;
-	lowS -= 2;
-	for (n = nodeNb; n <= nodeRoot; n++)
-		huffNode[n].count = (U32)(1U << 30);
-	huffNode0[0].count = (U32)(1U << 31); /* fake entry, strong barrier */
-
-	/* create parents */
-	while (nodeNb <= nodeRoot) {
-		U32 n1 = (huffNode[lowS].count < huffNode[lowN].count) ? lowS-- : lowN++;
-		U32 n2 = (huffNode[lowS].count < huffNode[lowN].count) ? lowS-- : lowN++;
-		huffNode[nodeNb].count = huffNode[n1].count + huffNode[n2].count;
-		huffNode[n1].parent = huffNode[n2].parent = nodeNb;
-		nodeNb++;
-	}
-
-	/* distribute weights (unlimited tree height) */
-	huffNode[nodeRoot].nbBits = 0;
-	for (n = nodeRoot - 1; n >= STARTNODE; n--)
-		huffNode[n].nbBits = huffNode[huffNode[n].parent].nbBits + 1;
-	for (n = 0; n <= nonNullRank; n++)
-		huffNode[n].nbBits = huffNode[huffNode[n].parent].nbBits + 1;
-
-	/* enforce maxTableLog */
-	maxNbBits = HUF_setMaxHeight(huffNode, nonNullRank, maxNbBits);
-
-	/* fill result into tree (val, nbBits) */
-	{
-		U16 nbPerRank[HUF_TABLELOG_MAX + 1] = {0};
-		U16 valPerRank[HUF_TABLELOG_MAX + 1] = {0};
-		if (maxNbBits > HUF_TABLELOG_MAX)
-			return ERROR(GENERIC); /* check fit into table */
-		for (n = 0; n <= nonNullRank; n++)
-			nbPerRank[huffNode[n].nbBits]++;
-		/* determine stating value per rank */
-		{
-			U16 min = 0;
-			for (n = maxNbBits; n > 0; n--) {
-				valPerRank[n] = min; /* get starting value within each rank */
-				min += nbPerRank[n];
-				min >>= 1;
-			}
-		}
-		for (n = 0; n <= maxSymbolValue; n++)
-			tree[huffNode[n].byte].nbBits = huffNode[n].nbBits; /* push nbBits per symbol, symbol order */
-		for (n = 0; n <= maxSymbolValue; n++)
-			tree[n].val = valPerRank[tree[n].nbBits]++; /* assign value within rank, symbol order */
-	}
-
-	return maxNbBits;
-}
-
-static size_t HUF_estimateCompressedSize(HUF_CElt *CTable, const unsigned *count, unsigned maxSymbolValue)
-{
-	size_t nbBits = 0;
-	int s;
-	for (s = 0; s <= (int)maxSymbolValue; ++s) {
-		nbBits += CTable[s].nbBits * count[s];
-	}
-	return nbBits >> 3;
-}
-
-static int HUF_validateCTable(const HUF_CElt *CTable, const unsigned *count, unsigned maxSymbolValue)
-{
-	int bad = 0;
-	int s;
-	for (s = 0; s <= (int)maxSymbolValue; ++s) {
-		bad |= (count[s] != 0) & (CTable[s].nbBits == 0);
-	}
-	return !bad;
-}
-
-static void HUF_encodeSymbol(BIT_CStream_t *bitCPtr, U32 symbol, const HUF_CElt *CTable)
-{
-	BIT_addBitsFast(bitCPtr, CTable[symbol].val, CTable[symbol].nbBits);
-}
-
-size_t HUF_compressBound(size_t size) { return HUF_COMPRESSBOUND(size); }
-
-#define HUF_FLUSHBITS(s)  BIT_flushBits(s)
-
-#define HUF_FLUSHBITS_1(stream)                                            \
-	if (sizeof((stream)->bitContainer) * 8 < HUF_TABLELOG_MAX * 2 + 7) \
-	HUF_FLUSHBITS(stream)
-
-#define HUF_FLUSHBITS_2(stream)                                            \
-	if (sizeof((stream)->bitContainer) * 8 < HUF_TABLELOG_MAX * 4 + 7) \
-	HUF_FLUSHBITS(stream)
-
-size_t HUF_compress1X_usingCTable(void *dst, size_t dstSize, const void *src, size_t srcSize, const HUF_CElt *CTable)
-{
-	const BYTE *ip = (const BYTE *)src;
-	BYTE *const ostart = (BYTE *)dst;
-	BYTE *const oend = ostart + dstSize;
-	BYTE *op = ostart;
-	size_t n;
-	BIT_CStream_t bitC;
-
-	/* init */
-	if (dstSize < 8)
-		return 0; /* not enough space to compress */
-	{
-		size_t const initErr = BIT_initCStream(&bitC, op, oend - op);
-		if (HUF_isError(initErr))
-			return 0;
-	}
-
-	n = srcSize & ~3; /* join to mod 4 */
-	switch (srcSize & 3) {
-	case 3: HUF_encodeSymbol(&bitC, ip[n + 2], CTable); HUF_FLUSHBITS_2(&bitC);
-		fallthrough;
-	case 2: HUF_encodeSymbol(&bitC, ip[n + 1], CTable); HUF_FLUSHBITS_1(&bitC);
-		fallthrough;
-	case 1: HUF_encodeSymbol(&bitC, ip[n + 0], CTable); HUF_FLUSHBITS(&bitC);
-		fallthrough;
-	case 0:
-	default:;
-	}
-
-	for (; n > 0; n -= 4) { /* note : n&3==0 at this stage */
-		HUF_encodeSymbol(&bitC, ip[n - 1], CTable);
-		HUF_FLUSHBITS_1(&bitC);
-		HUF_encodeSymbol(&bitC, ip[n - 2], CTable);
-		HUF_FLUSHBITS_2(&bitC);
-		HUF_encodeSymbol(&bitC, ip[n - 3], CTable);
-		HUF_FLUSHBITS_1(&bitC);
-		HUF_encodeSymbol(&bitC, ip[n - 4], CTable);
-		HUF_FLUSHBITS(&bitC);
-	}
-
-	return BIT_closeCStream(&bitC);
-}
-
-size_t HUF_compress4X_usingCTable(void *dst, size_t dstSize, const void *src, size_t srcSize, const HUF_CElt *CTable)
-{
-	size_t const segmentSize = (srcSize + 3) / 4; /* first 3 segments */
-	const BYTE *ip = (const BYTE *)src;
-	const BYTE *const iend = ip + srcSize;
-	BYTE *const ostart = (BYTE *)dst;
-	BYTE *const oend = ostart + dstSize;
-	BYTE *op = ostart;
-
-	if (dstSize < 6 + 1 + 1 + 1 + 8)
-		return 0; /* minimum space to compress successfully */
-	if (srcSize < 12)
-		return 0; /* no saving possible : too small input */
-	op += 6;	  /* jumpTable */
-
-	{
-		CHECK_V_F(cSize, HUF_compress1X_usingCTable(op, oend - op, ip, segmentSize, CTable));
-		if (cSize == 0)
-			return 0;
-		ZSTD_writeLE16(ostart, (U16)cSize);
-		op += cSize;
-	}
-
-	ip += segmentSize;
-	{
-		CHECK_V_F(cSize, HUF_compress1X_usingCTable(op, oend - op, ip, segmentSize, CTable));
-		if (cSize == 0)
-			return 0;
-		ZSTD_writeLE16(ostart + 2, (U16)cSize);
-		op += cSize;
-	}
-
-	ip += segmentSize;
-	{
-		CHECK_V_F(cSize, HUF_compress1X_usingCTable(op, oend - op, ip, segmentSize, CTable));
-		if (cSize == 0)
-			return 0;
-		ZSTD_writeLE16(ostart + 4, (U16)cSize);
-		op += cSize;
-	}
-
-	ip += segmentSize;
-	{
-		CHECK_V_F(cSize, HUF_compress1X_usingCTable(op, oend - op, ip, iend - ip, CTable));
-		if (cSize == 0)
-			return 0;
-		op += cSize;
-	}
-
-	return op - ostart;
-}
-
-static size_t HUF_compressCTable_internal(BYTE *const ostart, BYTE *op, BYTE *const oend, const void *src, size_t srcSize, unsigned singleStream,
-					  const HUF_CElt *CTable)
-{
-	size_t const cSize =
-	    singleStream ? HUF_compress1X_usingCTable(op, oend - op, src, srcSize, CTable) : HUF_compress4X_usingCTable(op, oend - op, src, srcSize, CTable);
-	if (HUF_isError(cSize)) {
-		return cSize;
-	}
-	if (cSize == 0) {
-		return 0;
-	} /* uncompressible */
-	op += cSize;
-	/* check compressibility */
-	if ((size_t)(op - ostart) >= srcSize - 1) {
-		return 0;
-	}
-	return op - ostart;
-}
-
-/* `workSpace` must a table of at least 1024 unsigned */
-static size_t HUF_compress_internal(void *dst, size_t dstSize, const void *src, size_t srcSize, unsigned maxSymbolValue, unsigned huffLog,
-				    unsigned singleStream, void *workSpace, size_t wkspSize, HUF_CElt *oldHufTable, HUF_repeat *repeat, int preferRepeat)
-{
-	BYTE *const ostart = (BYTE *)dst;
-	BYTE *const oend = ostart + dstSize;
-	BYTE *op = ostart;
-
-	U32 *count;
-	size_t const countSize = sizeof(U32) * (HUF_SYMBOLVALUE_MAX + 1);
-	HUF_CElt *CTable;
-	size_t const CTableSize = sizeof(HUF_CElt) * (HUF_SYMBOLVALUE_MAX + 1);
-
-	/* checks & inits */
-	if (wkspSize < sizeof(huffNodeTable) + countSize + CTableSize)
-		return ERROR(GENERIC);
-	if (!srcSize)
-		return 0; /* Uncompressed (note : 1 means rle, so first byte must be correct) */
-	if (!dstSize)
-		return 0; /* cannot fit within dst budget */
-	if (srcSize > HUF_BLOCKSIZE_MAX)
-		return ERROR(srcSize_wrong); /* curr block size limit */
-	if (huffLog > HUF_TABLELOG_MAX)
-		return ERROR(tableLog_tooLarge);
-	if (!maxSymbolValue)
-		maxSymbolValue = HUF_SYMBOLVALUE_MAX;
-	if (!huffLog)
-		huffLog = HUF_TABLELOG_DEFAULT;
-
-	count = (U32 *)workSpace;
-	workSpace = (BYTE *)workSpace + countSize;
-	wkspSize -= countSize;
-	CTable = (HUF_CElt *)workSpace;
-	workSpace = (BYTE *)workSpace + CTableSize;
-	wkspSize -= CTableSize;
-
-	/* Heuristic : If we don't need to check the validity of the old table use the old table for small inputs */
-	if (preferRepeat && repeat && *repeat == HUF_repeat_valid) {
-		return HUF_compressCTable_internal(ostart, op, oend, src, srcSize, singleStream, oldHufTable);
-	}
-
-	/* Scan input and build symbol stats */
-	{
-		CHECK_V_F(largest, FSE_count_wksp(count, &maxSymbolValue, (const BYTE *)src, srcSize, (U32 *)workSpace));
-		if (largest == srcSize) {
-			*ostart = ((const BYTE *)src)[0];
-			return 1;
-		} /* single symbol, rle */
-		if (largest <= (srcSize >> 7) + 1)
-			return 0; /* Fast heuristic : not compressible enough */
-	}
-
-	/* Check validity of previous table */
-	if (repeat && *repeat == HUF_repeat_check && !HUF_validateCTable(oldHufTable, count, maxSymbolValue)) {
-		*repeat = HUF_repeat_none;
-	}
-	/* Heuristic : use existing table for small inputs */
-	if (preferRepeat && repeat && *repeat != HUF_repeat_none) {
-		return HUF_compressCTable_internal(ostart, op, oend, src, srcSize, singleStream, oldHufTable);
-	}
-
-	/* Build Huffman Tree */
-	huffLog = HUF_optimalTableLog(huffLog, srcSize, maxSymbolValue);
-	{
-		CHECK_V_F(maxBits, HUF_buildCTable_wksp(CTable, count, maxSymbolValue, huffLog, workSpace, wkspSize));
-		huffLog = (U32)maxBits;
-		/* Zero the unused symbols so we can check it for validity */
-		memset(CTable + maxSymbolValue + 1, 0, CTableSize - (maxSymbolValue + 1) * sizeof(HUF_CElt));
-	}
-
-	/* Write table description header */
-	{
-		CHECK_V_F(hSize, HUF_writeCTable_wksp(op, dstSize, CTable, maxSymbolValue, huffLog, workSpace, wkspSize));
-		/* Check if using the previous table will be beneficial */
-		if (repeat && *repeat != HUF_repeat_none) {
-			size_t const oldSize = HUF_estimateCompressedSize(oldHufTable, count, maxSymbolValue);
-			size_t const newSize = HUF_estimateCompressedSize(CTable, count, maxSymbolValue);
-			if (oldSize <= hSize + newSize || hSize + 12 >= srcSize) {
-				return HUF_compressCTable_internal(ostart, op, oend, src, srcSize, singleStream, oldHufTable);
-			}
-		}
-		/* Use the new table */
-		if (hSize + 12ul >= srcSize) {
-			return 0;
-		}
-		op += hSize;
-		if (repeat) {
-			*repeat = HUF_repeat_none;
-		}
-		if (oldHufTable) {
-			memcpy(oldHufTable, CTable, CTableSize);
-		} /* Save the new table */
-	}
-	return HUF_compressCTable_internal(ostart, op, oend, src, srcSize, singleStream, CTable);
-}
-
-size_t HUF_compress1X_wksp(void *dst, size_t dstSize, const void *src, size_t srcSize, unsigned maxSymbolValue, unsigned huffLog, void *workSpace,
-			   size_t wkspSize)
-{
-	return HUF_compress_internal(dst, dstSize, src, srcSize, maxSymbolValue, huffLog, 1 /* single stream */, workSpace, wkspSize, NULL, NULL, 0);
-}
-
-size_t HUF_compress1X_repeat(void *dst, size_t dstSize, const void *src, size_t srcSize, unsigned maxSymbolValue, unsigned huffLog, void *workSpace,
-			     size_t wkspSize, HUF_CElt *hufTable, HUF_repeat *repeat, int preferRepeat)
-{
-	return HUF_compress_internal(dst, dstSize, src, srcSize, maxSymbolValue, huffLog, 1 /* single stream */, workSpace, wkspSize, hufTable, repeat,
-				     preferRepeat);
-}
-
-size_t HUF_compress4X_wksp(void *dst, size_t dstSize, const void *src, size_t srcSize, unsigned maxSymbolValue, unsigned huffLog, void *workSpace,
-			   size_t wkspSize)
-{
-	return HUF_compress_internal(dst, dstSize, src, srcSize, maxSymbolValue, huffLog, 0 /* 4 streams */, workSpace, wkspSize, NULL, NULL, 0);
-}
-
-size_t HUF_compress4X_repeat(void *dst, size_t dstSize, const void *src, size_t srcSize, unsigned maxSymbolValue, unsigned huffLog, void *workSpace,
-			     size_t wkspSize, HUF_CElt *hufTable, HUF_repeat *repeat, int preferRepeat)
-{
-	return HUF_compress_internal(dst, dstSize, src, srcSize, maxSymbolValue, huffLog, 0 /* 4 streams */, workSpace, wkspSize, hufTable, repeat,
-				     preferRepeat);
-}
diff --git a/lib/zstd/huf_decompress.c b/lib/zstd/huf_decompress.c
deleted file mode 100644
index 6526482047dc..000000000000
--- a/lib/zstd/huf_decompress.c
+++ /dev/null
@@ -1,960 +0,0 @@
-/*
- * Huffman decoder, part of New Generation Entropy library
- * Copyright (C) 2013-2016, Yann Collet.
- *
- * BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are
- * met:
- *
- *   * Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- *   * Redistributions in binary form must reproduce the above
- * copyright notice, this list of conditions and the following disclaimer
- * in the documentation and/or other materials provided with the
- * distribution.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * 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. This program is dual-licensed; you may select
- * either version 2 of the GNU General Public License ("GPL") or BSD license
- * ("BSD").
- *
- * You can contact the author at :
- * - Source repository : https://github.com/Cyan4973/FiniteStateEntropy
- */
-
-/* **************************************************************
-*  Compiler specifics
-****************************************************************/
-#define FORCE_INLINE static __always_inline
-
-/* **************************************************************
-*  Dependencies
-****************************************************************/
-#include "bitstream.h" /* BIT_* */
-#include "fse.h"       /* header compression */
-#include "huf.h"
-#include <linux/compiler.h>
-#include <linux/kernel.h>
-#include <linux/string.h> /* memcpy, memset */
-
-/* **************************************************************
-*  Error Management
-****************************************************************/
-#define HUF_STATIC_ASSERT(c)                                   \
-	{                                                      \
-		enum { HUF_static_assert = 1 / (int)(!!(c)) }; \
-	} /* use only *after* variable declarations */
-
-/*-***************************/
-/*  generic DTableDesc       */
-/*-***************************/
-
-typedef struct {
-	BYTE maxTableLog;
-	BYTE tableType;
-	BYTE tableLog;
-	BYTE reserved;
-} DTableDesc;
-
-static DTableDesc HUF_getDTableDesc(const HUF_DTable *table)
-{
-	DTableDesc dtd;
-	memcpy(&dtd, table, sizeof(dtd));
-	return dtd;
-}
-
-/*-***************************/
-/*  single-symbol decoding   */
-/*-***************************/
-
-typedef struct {
-	BYTE byte;
-	BYTE nbBits;
-} HUF_DEltX2; /* single-symbol decoding */
-
-size_t HUF_readDTableX2_wksp(HUF_DTable *DTable, const void *src, size_t srcSize, void *workspace, size_t workspaceSize)
-{
-	U32 tableLog = 0;
-	U32 nbSymbols = 0;
-	size_t iSize;
-	void *const dtPtr = DTable + 1;
-	HUF_DEltX2 *const dt = (HUF_DEltX2 *)dtPtr;
-
-	U32 *rankVal;
-	BYTE *huffWeight;
-	size_t spaceUsed32 = 0;
-
-	rankVal = (U32 *)workspace + spaceUsed32;
-	spaceUsed32 += HUF_TABLELOG_ABSOLUTEMAX + 1;
-	huffWeight = (BYTE *)((U32 *)workspace + spaceUsed32);
-	spaceUsed32 += ALIGN(HUF_SYMBOLVALUE_MAX + 1, sizeof(U32)) >> 2;
-
-	if ((spaceUsed32 << 2) > workspaceSize)
-		return ERROR(tableLog_tooLarge);
-	workspace = (U32 *)workspace + spaceUsed32;
-	workspaceSize -= (spaceUsed32 << 2);
-
-	HUF_STATIC_ASSERT(sizeof(DTableDesc) == sizeof(HUF_DTable));
-	/* memset(huffWeight, 0, sizeof(huffWeight)); */ /* is not necessary, even though some analyzer complain ... */
-
-	iSize = HUF_readStats_wksp(huffWeight, HUF_SYMBOLVALUE_MAX + 1, rankVal, &nbSymbols, &tableLog, src, srcSize, workspace, workspaceSize);
-	if (HUF_isError(iSize))
-		return iSize;
-
-	/* Table header */
-	{
-		DTableDesc dtd = HUF_getDTableDesc(DTable);
-		if (tableLog > (U32)(dtd.maxTableLog + 1))
-			return ERROR(tableLog_tooLarge); /* DTable too small, Huffman tree cannot fit in */
-		dtd.tableType = 0;
-		dtd.tableLog = (BYTE)tableLog;
-		memcpy(DTable, &dtd, sizeof(dtd));
-	}
-
-	/* Calculate starting value for each rank */
-	{
-		U32 n, nextRankStart = 0;
-		for (n = 1; n < tableLog + 1; n++) {
-			U32 const curr = nextRankStart;
-			nextRankStart += (rankVal[n] << (n - 1));
-			rankVal[n] = curr;
-		}
-	}
-
-	/* fill DTable */
-	{
-		U32 n;
-		for (n = 0; n < nbSymbols; n++) {
-			U32 const w = huffWeight[n];
-			U32 const length = (1 << w) >> 1;
-			U32 u;
-			HUF_DEltX2 D;
-			D.byte = (BYTE)n;
-			D.nbBits = (BYTE)(tableLog + 1 - w);
-			for (u = rankVal[w]; u < rankVal[w] + length; u++)
-				dt[u] = D;
-			rankVal[w] += length;
-		}
-	}
-
-	return iSize;
-}
-
-static BYTE HUF_decodeSymbolX2(BIT_DStream_t *Dstream, const HUF_DEltX2 *dt, const U32 dtLog)
-{
-	size_t const val = BIT_lookBitsFast(Dstream, dtLog); /* note : dtLog >= 1 */
-	BYTE const c = dt[val].byte;
-	BIT_skipBits(Dstream, dt[val].nbBits);
-	return c;
-}
-
-#define HUF_DECODE_SYMBOLX2_0(ptr, DStreamPtr) *ptr++ = HUF_decodeSymbolX2(DStreamPtr, dt, dtLog)
-
-#define HUF_DECODE_SYMBOLX2_1(ptr, DStreamPtr)         \
-	if (ZSTD_64bits() || (HUF_TABLELOG_MAX <= 12)) \
-	HUF_DECODE_SYMBOLX2_0(ptr, DStreamPtr)
-
-#define HUF_DECODE_SYMBOLX2_2(ptr, DStreamPtr) \
-	if (ZSTD_64bits())                     \
-	HUF_DECODE_SYMBOLX2_0(ptr, DStreamPtr)
-
-FORCE_INLINE size_t HUF_decodeStreamX2(BYTE *p, BIT_DStream_t *const bitDPtr, BYTE *const pEnd, const HUF_DEltX2 *const dt, const U32 dtLog)
-{
-	BYTE *const pStart = p;
-
-	/* up to 4 symbols at a time */
-	while ((BIT_reloadDStream(bitDPtr) == BIT_DStream_unfinished) && (p <= pEnd - 4)) {
-		HUF_DECODE_SYMBOLX2_2(p, bitDPtr);
-		HUF_DECODE_SYMBOLX2_1(p, bitDPtr);
-		HUF_DECODE_SYMBOLX2_2(p, bitDPtr);
-		HUF_DECODE_SYMBOLX2_0(p, bitDPtr);
-	}
-
-	/* closer to the end */
-	while ((BIT_reloadDStream(bitDPtr) == BIT_DStream_unfinished) && (p < pEnd))
-		HUF_DECODE_SYMBOLX2_0(p, bitDPtr);
-
-	/* no more data to retrieve from bitstream, hence no need to reload */
-	while (p < pEnd)
-		HUF_DECODE_SYMBOLX2_0(p, bitDPtr);
-
-	return pEnd - pStart;
-}
-
-static size_t HUF_decompress1X2_usingDTable_internal(void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, const HUF_DTable *DTable)
-{
-	BYTE *op = (BYTE *)dst;
-	BYTE *const oend = op + dstSize;
-	const void *dtPtr = DTable + 1;
-	const HUF_DEltX2 *const dt = (const HUF_DEltX2 *)dtPtr;
-	BIT_DStream_t bitD;
-	DTableDesc const dtd = HUF_getDTableDesc(DTable);
-	U32 const dtLog = dtd.tableLog;
-
-	{
-		size_t const errorCode = BIT_initDStream(&bitD, cSrc, cSrcSize);
-		if (HUF_isError(errorCode))
-			return errorCode;
-	}
-
-	HUF_decodeStreamX2(op, &bitD, oend, dt, dtLog);
-
-	/* check */
-	if (!BIT_endOfDStream(&bitD))
-		return ERROR(corruption_detected);
-
-	return dstSize;
-}
-
-size_t HUF_decompress1X2_usingDTable(void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, const HUF_DTable *DTable)
-{
-	DTableDesc dtd = HUF_getDTableDesc(DTable);
-	if (dtd.tableType != 0)
-		return ERROR(GENERIC);
-	return HUF_decompress1X2_usingDTable_internal(dst, dstSize, cSrc, cSrcSize, DTable);
-}
-
-size_t HUF_decompress1X2_DCtx_wksp(HUF_DTable *DCtx, void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, void *workspace, size_t workspaceSize)
-{
-	const BYTE *ip = (const BYTE *)cSrc;
-
-	size_t const hSize = HUF_readDTableX2_wksp(DCtx, cSrc, cSrcSize, workspace, workspaceSize);
-	if (HUF_isError(hSize))
-		return hSize;
-	if (hSize >= cSrcSize)
-		return ERROR(srcSize_wrong);
-	ip += hSize;
-	cSrcSize -= hSize;
-
-	return HUF_decompress1X2_usingDTable_internal(dst, dstSize, ip, cSrcSize, DCtx);
-}
-
-static size_t HUF_decompress4X2_usingDTable_internal(void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, const HUF_DTable *DTable)
-{
-	/* Check */
-	if (cSrcSize < 10)
-		return ERROR(corruption_detected); /* strict minimum : jump table + 1 byte per stream */
-
-	{
-		const BYTE *const istart = (const BYTE *)cSrc;
-		BYTE *const ostart = (BYTE *)dst;
-		BYTE *const oend = ostart + dstSize;
-		const void *const dtPtr = DTable + 1;
-		const HUF_DEltX2 *const dt = (const HUF_DEltX2 *)dtPtr;
-
-		/* Init */
-		BIT_DStream_t bitD1;
-		BIT_DStream_t bitD2;
-		BIT_DStream_t bitD3;
-		BIT_DStream_t bitD4;
-		size_t const length1 = ZSTD_readLE16(istart);
-		size_t const length2 = ZSTD_readLE16(istart + 2);
-		size_t const length3 = ZSTD_readLE16(istart + 4);
-		size_t const length4 = cSrcSize - (length1 + length2 + length3 + 6);
-		const BYTE *const istart1 = istart + 6; /* jumpTable */
-		const BYTE *const istart2 = istart1 + length1;
-		const BYTE *const istart3 = istart2 + length2;
-		const BYTE *const istart4 = istart3 + length3;
-		const size_t segmentSize = (dstSize + 3) / 4;
-		BYTE *const opStart2 = ostart + segmentSize;
-		BYTE *const opStart3 = opStart2 + segmentSize;
-		BYTE *const opStart4 = opStart3 + segmentSize;
-		BYTE *op1 = ostart;
-		BYTE *op2 = opStart2;
-		BYTE *op3 = opStart3;
-		BYTE *op4 = opStart4;
-		U32 endSignal;
-		DTableDesc const dtd = HUF_getDTableDesc(DTable);
-		U32 const dtLog = dtd.tableLog;
-
-		if (length4 > cSrcSize)
-			return ERROR(corruption_detected); /* overflow */
-		{
-			size_t const errorCode = BIT_initDStream(&bitD1, istart1, length1);
-			if (HUF_isError(errorCode))
-				return errorCode;
-		}
-		{
-			size_t const errorCode = BIT_initDStream(&bitD2, istart2, length2);
-			if (HUF_isError(errorCode))
-				return errorCode;
-		}
-		{
-			size_t const errorCode = BIT_initDStream(&bitD3, istart3, length3);
-			if (HUF_isError(errorCode))
-				return errorCode;
-		}
-		{
-			size_t const errorCode = BIT_initDStream(&bitD4, istart4, length4);
-			if (HUF_isError(errorCode))
-				return errorCode;
-		}
-
-		/* 16-32 symbols per loop (4-8 symbols per stream) */
-		endSignal = BIT_reloadDStream(&bitD1) | BIT_reloadDStream(&bitD2) | BIT_reloadDStream(&bitD3) | BIT_reloadDStream(&bitD4);
-		for (; (endSignal == BIT_DStream_unfinished) && (op4 < (oend - 7));) {
-			HUF_DECODE_SYMBOLX2_2(op1, &bitD1);
-			HUF_DECODE_SYMBOLX2_2(op2, &bitD2);
-			HUF_DECODE_SYMBOLX2_2(op3, &bitD3);
-			HUF_DECODE_SYMBOLX2_2(op4, &bitD4);
-			HUF_DECODE_SYMBOLX2_1(op1, &bitD1);
-			HUF_DECODE_SYMBOLX2_1(op2, &bitD2);
-			HUF_DECODE_SYMBOLX2_1(op3, &bitD3);
-			HUF_DECODE_SYMBOLX2_1(op4, &bitD4);
-			HUF_DECODE_SYMBOLX2_2(op1, &bitD1);
-			HUF_DECODE_SYMBOLX2_2(op2, &bitD2);
-			HUF_DECODE_SYMBOLX2_2(op3, &bitD3);
-			HUF_DECODE_SYMBOLX2_2(op4, &bitD4);
-			HUF_DECODE_SYMBOLX2_0(op1, &bitD1);
-			HUF_DECODE_SYMBOLX2_0(op2, &bitD2);
-			HUF_DECODE_SYMBOLX2_0(op3, &bitD3);
-			HUF_DECODE_SYMBOLX2_0(op4, &bitD4);
-			endSignal = BIT_reloadDStream(&bitD1) | BIT_reloadDStream(&bitD2) | BIT_reloadDStream(&bitD3) | BIT_reloadDStream(&bitD4);
-		}
-
-		/* check corruption */
-		if (op1 > opStart2)
-			return ERROR(corruption_detected);
-		if (op2 > opStart3)
-			return ERROR(corruption_detected);
-		if (op3 > opStart4)
-			return ERROR(corruption_detected);
-		/* note : op4 supposed already verified within main loop */
-
-		/* finish bitStreams one by one */
-		HUF_decodeStreamX2(op1, &bitD1, opStart2, dt, dtLog);
-		HUF_decodeStreamX2(op2, &bitD2, opStart3, dt, dtLog);
-		HUF_decodeStreamX2(op3, &bitD3, opStart4, dt, dtLog);
-		HUF_decodeStreamX2(op4, &bitD4, oend, dt, dtLog);
-
-		/* check */
-		endSignal = BIT_endOfDStream(&bitD1) & BIT_endOfDStream(&bitD2) & BIT_endOfDStream(&bitD3) & BIT_endOfDStream(&bitD4);
-		if (!endSignal)
-			return ERROR(corruption_detected);
-
-		/* decoded size */
-		return dstSize;
-	}
-}
-
-size_t HUF_decompress4X2_usingDTable(void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, const HUF_DTable *DTable)
-{
-	DTableDesc dtd = HUF_getDTableDesc(DTable);
-	if (dtd.tableType != 0)
-		return ERROR(GENERIC);
-	return HUF_decompress4X2_usingDTable_internal(dst, dstSize, cSrc, cSrcSize, DTable);
-}
-
-size_t HUF_decompress4X2_DCtx_wksp(HUF_DTable *dctx, void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, void *workspace, size_t workspaceSize)
-{
-	const BYTE *ip = (const BYTE *)cSrc;
-
-	size_t const hSize = HUF_readDTableX2_wksp(dctx, cSrc, cSrcSize, workspace, workspaceSize);
-	if (HUF_isError(hSize))
-		return hSize;
-	if (hSize >= cSrcSize)
-		return ERROR(srcSize_wrong);
-	ip += hSize;
-	cSrcSize -= hSize;
-
-	return HUF_decompress4X2_usingDTable_internal(dst, dstSize, ip, cSrcSize, dctx);
-}
-
-/* *************************/
-/* double-symbols decoding */
-/* *************************/
-typedef struct {
-	U16 sequence;
-	BYTE nbBits;
-	BYTE length;
-} HUF_DEltX4; /* double-symbols decoding */
-
-typedef struct {
-	BYTE symbol;
-	BYTE weight;
-} sortedSymbol_t;
-
-/* HUF_fillDTableX4Level2() :
- * `rankValOrigin` must be a table of at least (HUF_TABLELOG_MAX + 1) U32 */
-static void HUF_fillDTableX4Level2(HUF_DEltX4 *DTable, U32 sizeLog, const U32 consumed, const U32 *rankValOrigin, const int minWeight,
-				   const sortedSymbol_t *sortedSymbols, const U32 sortedListSize, U32 nbBitsBaseline, U16 baseSeq)
-{
-	HUF_DEltX4 DElt;
-	U32 rankVal[HUF_TABLELOG_MAX + 1];
-
-	/* get pre-calculated rankVal */
-	memcpy(rankVal, rankValOrigin, sizeof(rankVal));
-
-	/* fill skipped values */
-	if (minWeight > 1) {
-		U32 i, skipSize = rankVal[minWeight];
-		ZSTD_writeLE16(&(DElt.sequence), baseSeq);
-		DElt.nbBits = (BYTE)(consumed);
-		DElt.length = 1;
-		for (i = 0; i < skipSize; i++)
-			DTable[i] = DElt;
-	}
-
-	/* fill DTable */
-	{
-		U32 s;
-		for (s = 0; s < sortedListSize; s++) { /* note : sortedSymbols already skipped */
-			const U32 symbol = sortedSymbols[s].symbol;
-			const U32 weight = sortedSymbols[s].weight;
-			const U32 nbBits = nbBitsBaseline - weight;
-			const U32 length = 1 << (sizeLog - nbBits);
-			const U32 start = rankVal[weight];
-			U32 i = start;
-			const U32 end = start + length;
-
-			ZSTD_writeLE16(&(DElt.sequence), (U16)(baseSeq + (symbol << 8)));
-			DElt.nbBits = (BYTE)(nbBits + consumed);
-			DElt.length = 2;
-			do {
-				DTable[i++] = DElt;
-			} while (i < end); /* since length >= 1 */
-
-			rankVal[weight] += length;
-		}
-	}
-}
-
-typedef U32 rankVal_t[HUF_TABLELOG_MAX][HUF_TABLELOG_MAX + 1];
-typedef U32 rankValCol_t[HUF_TABLELOG_MAX + 1];
-
-static void HUF_fillDTableX4(HUF_DEltX4 *DTable, const U32 targetLog, const sortedSymbol_t *sortedList, const U32 sortedListSize, const U32 *rankStart,
-			     rankVal_t rankValOrigin, const U32 maxWeight, const U32 nbBitsBaseline)
-{
-	U32 rankVal[HUF_TABLELOG_MAX + 1];
-	const int scaleLog = nbBitsBaseline - targetLog; /* note : targetLog >= srcLog, hence scaleLog <= 1 */
-	const U32 minBits = nbBitsBaseline - maxWeight;
-	U32 s;
-
-	memcpy(rankVal, rankValOrigin, sizeof(rankVal));
-
-	/* fill DTable */
-	for (s = 0; s < sortedListSize; s++) {
-		const U16 symbol = sortedList[s].symbol;
-		const U32 weight = sortedList[s].weight;
-		const U32 nbBits = nbBitsBaseline - weight;
-		const U32 start = rankVal[weight];
-		const U32 length = 1 << (targetLog - nbBits);
-
-		if (targetLog - nbBits >= minBits) { /* enough room for a second symbol */
-			U32 sortedRank;
-			int minWeight = nbBits + scaleLog;
-			if (minWeight < 1)
-				minWeight = 1;
-			sortedRank = rankStart[minWeight];
-			HUF_fillDTableX4Level2(DTable + start, targetLog - nbBits, nbBits, rankValOrigin[nbBits], minWeight, sortedList + sortedRank,
-					       sortedListSize - sortedRank, nbBitsBaseline, symbol);
-		} else {
-			HUF_DEltX4 DElt;
-			ZSTD_writeLE16(&(DElt.sequence), symbol);
-			DElt.nbBits = (BYTE)(nbBits);
-			DElt.length = 1;
-			{
-				U32 const end = start + length;
-				U32 u;
-				for (u = start; u < end; u++)
-					DTable[u] = DElt;
-			}
-		}
-		rankVal[weight] += length;
-	}
-}
-
-size_t HUF_readDTableX4_wksp(HUF_DTable *DTable, const void *src, size_t srcSize, void *workspace, size_t workspaceSize)
-{
-	U32 tableLog, maxW, sizeOfSort, nbSymbols;
-	DTableDesc dtd = HUF_getDTableDesc(DTable);
-	U32 const maxTableLog = dtd.maxTableLog;
-	size_t iSize;
-	void *dtPtr = DTable + 1; /* force compiler to avoid strict-aliasing */
-	HUF_DEltX4 *const dt = (HUF_DEltX4 *)dtPtr;
-	U32 *rankStart;
-
-	rankValCol_t *rankVal;
-	U32 *rankStats;
-	U32 *rankStart0;
-	sortedSymbol_t *sortedSymbol;
-	BYTE *weightList;
-	size_t spaceUsed32 = 0;
-
-	HUF_STATIC_ASSERT((sizeof(rankValCol_t) & 3) == 0);
-
-	rankVal = (rankValCol_t *)((U32 *)workspace + spaceUsed32);
-	spaceUsed32 += (sizeof(rankValCol_t) * HUF_TABLELOG_MAX) >> 2;
-	rankStats = (U32 *)workspace + spaceUsed32;
-	spaceUsed32 += HUF_TABLELOG_MAX + 1;
-	rankStart0 = (U32 *)workspace + spaceUsed32;
-	spaceUsed32 += HUF_TABLELOG_MAX + 2;
-	sortedSymbol = (sortedSymbol_t *)((U32 *)workspace + spaceUsed32);
-	spaceUsed32 += ALIGN(sizeof(sortedSymbol_t) * (HUF_SYMBOLVALUE_MAX + 1), sizeof(U32)) >> 2;
-	weightList = (BYTE *)((U32 *)workspace + spaceUsed32);
-	spaceUsed32 += ALIGN(HUF_SYMBOLVALUE_MAX + 1, sizeof(U32)) >> 2;
-
-	if ((spaceUsed32 << 2) > workspaceSize)
-		return ERROR(tableLog_tooLarge);
-	workspace = (U32 *)workspace + spaceUsed32;
-	workspaceSize -= (spaceUsed32 << 2);
-
-	rankStart = rankStart0 + 1;
-	memset(rankStats, 0, sizeof(U32) * (2 * HUF_TABLELOG_MAX + 2 + 1));
-
-	HUF_STATIC_ASSERT(sizeof(HUF_DEltX4) == sizeof(HUF_DTable)); /* if compiler fails here, assertion is wrong */
-	if (maxTableLog > HUF_TABLELOG_MAX)
-		return ERROR(tableLog_tooLarge);
-	/* memset(weightList, 0, sizeof(weightList)); */ /* is not necessary, even though some analyzer complain ... */
-
-	iSize = HUF_readStats_wksp(weightList, HUF_SYMBOLVALUE_MAX + 1, rankStats, &nbSymbols, &tableLog, src, srcSize, workspace, workspaceSize);
-	if (HUF_isError(iSize))
-		return iSize;
-
-	/* check result */
-	if (tableLog > maxTableLog)
-		return ERROR(tableLog_tooLarge); /* DTable can't fit code depth */
-
-	/* find maxWeight */
-	for (maxW = tableLog; rankStats[maxW] == 0; maxW--) {
-	} /* necessarily finds a solution before 0 */
-
-	/* Get start index of each weight */
-	{
-		U32 w, nextRankStart = 0;
-		for (w = 1; w < maxW + 1; w++) {
-			U32 curr = nextRankStart;
-			nextRankStart += rankStats[w];
-			rankStart[w] = curr;
-		}
-		rankStart[0] = nextRankStart; /* put all 0w symbols at the end of sorted list*/
-		sizeOfSort = nextRankStart;
-	}
-
-	/* sort symbols by weight */
-	{
-		U32 s;
-		for (s = 0; s < nbSymbols; s++) {
-			U32 const w = weightList[s];
-			U32 const r = rankStart[w]++;
-			sortedSymbol[r].symbol = (BYTE)s;
-			sortedSymbol[r].weight = (BYTE)w;
-		}
-		rankStart[0] = 0; /* forget 0w symbols; this is beginning of weight(1) */
-	}
-
-	/* Build rankVal */
-	{
-		U32 *const rankVal0 = rankVal[0];
-		{
-			int const rescale = (maxTableLog - tableLog) - 1; /* tableLog <= maxTableLog */
-			U32 nextRankVal = 0;
-			U32 w;
-			for (w = 1; w < maxW + 1; w++) {
-				U32 curr = nextRankVal;
-				nextRankVal += rankStats[w] << (w + rescale);
-				rankVal0[w] = curr;
-			}
-		}
-		{
-			U32 const minBits = tableLog + 1 - maxW;
-			U32 consumed;
-			for (consumed = minBits; consumed < maxTableLog - minBits + 1; consumed++) {
-				U32 *const rankValPtr = rankVal[consumed];
-				U32 w;
-				for (w = 1; w < maxW + 1; w++) {
-					rankValPtr[w] = rankVal0[w] >> consumed;
-				}
-			}
-		}
-	}
-
-	HUF_fillDTableX4(dt, maxTableLog, sortedSymbol, sizeOfSort, rankStart0, rankVal, maxW, tableLog + 1);
-
-	dtd.tableLog = (BYTE)maxTableLog;
-	dtd.tableType = 1;
-	memcpy(DTable, &dtd, sizeof(dtd));
-	return iSize;
-}
-
-static U32 HUF_decodeSymbolX4(void *op, BIT_DStream_t *DStream, const HUF_DEltX4 *dt, const U32 dtLog)
-{
-	size_t const val = BIT_lookBitsFast(DStream, dtLog); /* note : dtLog >= 1 */
-	memcpy(op, dt + val, 2);
-	BIT_skipBits(DStream, dt[val].nbBits);
-	return dt[val].length;
-}
-
-static U32 HUF_decodeLastSymbolX4(void *op, BIT_DStream_t *DStream, const HUF_DEltX4 *dt, const U32 dtLog)
-{
-	size_t const val = BIT_lookBitsFast(DStream, dtLog); /* note : dtLog >= 1 */
-	memcpy(op, dt + val, 1);
-	if (dt[val].length == 1)
-		BIT_skipBits(DStream, dt[val].nbBits);
-	else {
-		if (DStream->bitsConsumed < (sizeof(DStream->bitContainer) * 8)) {
-			BIT_skipBits(DStream, dt[val].nbBits);
-			if (DStream->bitsConsumed > (sizeof(DStream->bitContainer) * 8))
-				/* ugly hack; works only because it's the last symbol. Note : can't easily extract nbBits from just this symbol */
-				DStream->bitsConsumed = (sizeof(DStream->bitContainer) * 8);
-		}
-	}
-	return 1;
-}
-
-#define HUF_DECODE_SYMBOLX4_0(ptr, DStreamPtr) ptr += HUF_decodeSymbolX4(ptr, DStreamPtr, dt, dtLog)
-
-#define HUF_DECODE_SYMBOLX4_1(ptr, DStreamPtr)         \
-	if (ZSTD_64bits() || (HUF_TABLELOG_MAX <= 12)) \
-	ptr += HUF_decodeSymbolX4(ptr, DStreamPtr, dt, dtLog)
-
-#define HUF_DECODE_SYMBOLX4_2(ptr, DStreamPtr) \
-	if (ZSTD_64bits())                     \
-	ptr += HUF_decodeSymbolX4(ptr, DStreamPtr, dt, dtLog)
-
-FORCE_INLINE size_t HUF_decodeStreamX4(BYTE *p, BIT_DStream_t *bitDPtr, BYTE *const pEnd, const HUF_DEltX4 *const dt, const U32 dtLog)
-{
-	BYTE *const pStart = p;
-
-	/* up to 8 symbols at a time */
-	while ((BIT_reloadDStream(bitDPtr) == BIT_DStream_unfinished) & (p < pEnd - (sizeof(bitDPtr->bitContainer) - 1))) {
-		HUF_DECODE_SYMBOLX4_2(p, bitDPtr);
-		HUF_DECODE_SYMBOLX4_1(p, bitDPtr);
-		HUF_DECODE_SYMBOLX4_2(p, bitDPtr);
-		HUF_DECODE_SYMBOLX4_0(p, bitDPtr);
-	}
-
-	/* closer to end : up to 2 symbols at a time */
-	while ((BIT_reloadDStream(bitDPtr) == BIT_DStream_unfinished) & (p <= pEnd - 2))
-		HUF_DECODE_SYMBOLX4_0(p, bitDPtr);
-
-	while (p <= pEnd - 2)
-		HUF_DECODE_SYMBOLX4_0(p, bitDPtr); /* no need to reload : reached the end of DStream */
-
-	if (p < pEnd)
-		p += HUF_decodeLastSymbolX4(p, bitDPtr, dt, dtLog);
-
-	return p - pStart;
-}
-
-static size_t HUF_decompress1X4_usingDTable_internal(void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, const HUF_DTable *DTable)
-{
-	BIT_DStream_t bitD;
-
-	/* Init */
-	{
-		size_t const errorCode = BIT_initDStream(&bitD, cSrc, cSrcSize);
-		if (HUF_isError(errorCode))
-			return errorCode;
-	}
-
-	/* decode */
-	{
-		BYTE *const ostart = (BYTE *)dst;
-		BYTE *const oend = ostart + dstSize;
-		const void *const dtPtr = DTable + 1; /* force compiler to not use strict-aliasing */
-		const HUF_DEltX4 *const dt = (const HUF_DEltX4 *)dtPtr;
-		DTableDesc const dtd = HUF_getDTableDesc(DTable);
-		HUF_decodeStreamX4(ostart, &bitD, oend, dt, dtd.tableLog);
-	}
-
-	/* check */
-	if (!BIT_endOfDStream(&bitD))
-		return ERROR(corruption_detected);
-
-	/* decoded size */
-	return dstSize;
-}
-
-size_t HUF_decompress1X4_usingDTable(void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, const HUF_DTable *DTable)
-{
-	DTableDesc dtd = HUF_getDTableDesc(DTable);
-	if (dtd.tableType != 1)
-		return ERROR(GENERIC);
-	return HUF_decompress1X4_usingDTable_internal(dst, dstSize, cSrc, cSrcSize, DTable);
-}
-
-size_t HUF_decompress1X4_DCtx_wksp(HUF_DTable *DCtx, void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, void *workspace, size_t workspaceSize)
-{
-	const BYTE *ip = (const BYTE *)cSrc;
-
-	size_t const hSize = HUF_readDTableX4_wksp(DCtx, cSrc, cSrcSize, workspace, workspaceSize);
-	if (HUF_isError(hSize))
-		return hSize;
-	if (hSize >= cSrcSize)
-		return ERROR(srcSize_wrong);
-	ip += hSize;
-	cSrcSize -= hSize;
-
-	return HUF_decompress1X4_usingDTable_internal(dst, dstSize, ip, cSrcSize, DCtx);
-}
-
-static size_t HUF_decompress4X4_usingDTable_internal(void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, const HUF_DTable *DTable)
-{
-	if (cSrcSize < 10)
-		return ERROR(corruption_detected); /* strict minimum : jump table + 1 byte per stream */
-
-	{
-		const BYTE *const istart = (const BYTE *)cSrc;
-		BYTE *const ostart = (BYTE *)dst;
-		BYTE *const oend = ostart + dstSize;
-		const void *const dtPtr = DTable + 1;
-		const HUF_DEltX4 *const dt = (const HUF_DEltX4 *)dtPtr;
-
-		/* Init */
-		BIT_DStream_t bitD1;
-		BIT_DStream_t bitD2;
-		BIT_DStream_t bitD3;
-		BIT_DStream_t bitD4;
-		size_t const length1 = ZSTD_readLE16(istart);
-		size_t const length2 = ZSTD_readLE16(istart + 2);
-		size_t const length3 = ZSTD_readLE16(istart + 4);
-		size_t const length4 = cSrcSize - (length1 + length2 + length3 + 6);
-		const BYTE *const istart1 = istart + 6; /* jumpTable */
-		const BYTE *const istart2 = istart1 + length1;
-		const BYTE *const istart3 = istart2 + length2;
-		const BYTE *const istart4 = istart3 + length3;
-		size_t const segmentSize = (dstSize + 3) / 4;
-		BYTE *const opStart2 = ostart + segmentSize;
-		BYTE *const opStart3 = opStart2 + segmentSize;
-		BYTE *const opStart4 = opStart3 + segmentSize;
-		BYTE *op1 = ostart;
-		BYTE *op2 = opStart2;
-		BYTE *op3 = opStart3;
-		BYTE *op4 = opStart4;
-		U32 endSignal;
-		DTableDesc const dtd = HUF_getDTableDesc(DTable);
-		U32 const dtLog = dtd.tableLog;
-
-		if (length4 > cSrcSize)
-			return ERROR(corruption_detected); /* overflow */
-		{
-			size_t const errorCode = BIT_initDStream(&bitD1, istart1, length1);
-			if (HUF_isError(errorCode))
-				return errorCode;
-		}
-		{
-			size_t const errorCode = BIT_initDStream(&bitD2, istart2, length2);
-			if (HUF_isError(errorCode))
-				return errorCode;
-		}
-		{
-			size_t const errorCode = BIT_initDStream(&bitD3, istart3, length3);
-			if (HUF_isError(errorCode))
-				return errorCode;
-		}
-		{
-			size_t const errorCode = BIT_initDStream(&bitD4, istart4, length4);
-			if (HUF_isError(errorCode))
-				return errorCode;
-		}
-
-		/* 16-32 symbols per loop (4-8 symbols per stream) */
-		endSignal = BIT_reloadDStream(&bitD1) | BIT_reloadDStream(&bitD2) | BIT_reloadDStream(&bitD3) | BIT_reloadDStream(&bitD4);
-		for (; (endSignal == BIT_DStream_unfinished) & (op4 < (oend - (sizeof(bitD4.bitContainer) - 1)));) {
-			HUF_DECODE_SYMBOLX4_2(op1, &bitD1);
-			HUF_DECODE_SYMBOLX4_2(op2, &bitD2);
-			HUF_DECODE_SYMBOLX4_2(op3, &bitD3);
-			HUF_DECODE_SYMBOLX4_2(op4, &bitD4);
-			HUF_DECODE_SYMBOLX4_1(op1, &bitD1);
-			HUF_DECODE_SYMBOLX4_1(op2, &bitD2);
-			HUF_DECODE_SYMBOLX4_1(op3, &bitD3);
-			HUF_DECODE_SYMBOLX4_1(op4, &bitD4);
-			HUF_DECODE_SYMBOLX4_2(op1, &bitD1);
-			HUF_DECODE_SYMBOLX4_2(op2, &bitD2);
-			HUF_DECODE_SYMBOLX4_2(op3, &bitD3);
-			HUF_DECODE_SYMBOLX4_2(op4, &bitD4);
-			HUF_DECODE_SYMBOLX4_0(op1, &bitD1);
-			HUF_DECODE_SYMBOLX4_0(op2, &bitD2);
-			HUF_DECODE_SYMBOLX4_0(op3, &bitD3);
-			HUF_DECODE_SYMBOLX4_0(op4, &bitD4);
-
-			endSignal = BIT_reloadDStream(&bitD1) | BIT_reloadDStream(&bitD2) | BIT_reloadDStream(&bitD3) | BIT_reloadDStream(&bitD4);
-		}
-
-		/* check corruption */
-		if (op1 > opStart2)
-			return ERROR(corruption_detected);
-		if (op2 > opStart3)
-			return ERROR(corruption_detected);
-		if (op3 > opStart4)
-			return ERROR(corruption_detected);
-		/* note : op4 already verified within main loop */
-
-		/* finish bitStreams one by one */
-		HUF_decodeStreamX4(op1, &bitD1, opStart2, dt, dtLog);
-		HUF_decodeStreamX4(op2, &bitD2, opStart3, dt, dtLog);
-		HUF_decodeStreamX4(op3, &bitD3, opStart4, dt, dtLog);
-		HUF_decodeStreamX4(op4, &bitD4, oend, dt, dtLog);
-
-		/* check */
-		{
-			U32 const endCheck = BIT_endOfDStream(&bitD1) & BIT_endOfDStream(&bitD2) & BIT_endOfDStream(&bitD3) & BIT_endOfDStream(&bitD4);
-			if (!endCheck)
-				return ERROR(corruption_detected);
-		}
-
-		/* decoded size */
-		return dstSize;
-	}
-}
-
-size_t HUF_decompress4X4_usingDTable(void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, const HUF_DTable *DTable)
-{
-	DTableDesc dtd = HUF_getDTableDesc(DTable);
-	if (dtd.tableType != 1)
-		return ERROR(GENERIC);
-	return HUF_decompress4X4_usingDTable_internal(dst, dstSize, cSrc, cSrcSize, DTable);
-}
-
-size_t HUF_decompress4X4_DCtx_wksp(HUF_DTable *dctx, void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, void *workspace, size_t workspaceSize)
-{
-	const BYTE *ip = (const BYTE *)cSrc;
-
-	size_t hSize = HUF_readDTableX4_wksp(dctx, cSrc, cSrcSize, workspace, workspaceSize);
-	if (HUF_isError(hSize))
-		return hSize;
-	if (hSize >= cSrcSize)
-		return ERROR(srcSize_wrong);
-	ip += hSize;
-	cSrcSize -= hSize;
-
-	return HUF_decompress4X4_usingDTable_internal(dst, dstSize, ip, cSrcSize, dctx);
-}
-
-/* ********************************/
-/* Generic decompression selector */
-/* ********************************/
-
-size_t HUF_decompress1X_usingDTable(void *dst, size_t maxDstSize, const void *cSrc, size_t cSrcSize, const HUF_DTable *DTable)
-{
-	DTableDesc const dtd = HUF_getDTableDesc(DTable);
-	return dtd.tableType ? HUF_decompress1X4_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable)
-			     : HUF_decompress1X2_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable);
-}
-
-size_t HUF_decompress4X_usingDTable(void *dst, size_t maxDstSize, const void *cSrc, size_t cSrcSize, const HUF_DTable *DTable)
-{
-	DTableDesc const dtd = HUF_getDTableDesc(DTable);
-	return dtd.tableType ? HUF_decompress4X4_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable)
-			     : HUF_decompress4X2_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable);
-}
-
-typedef struct {
-	U32 tableTime;
-	U32 decode256Time;
-} algo_time_t;
-static const algo_time_t algoTime[16 /* Quantization */][3 /* single, double, quad */] = {
-    /* single, double, quad */
-    {{0, 0}, {1, 1}, {2, 2}},		     /* Q==0 : impossible */
-    {{0, 0}, {1, 1}, {2, 2}},		     /* Q==1 : impossible */
-    {{38, 130}, {1313, 74}, {2151, 38}},     /* Q == 2 : 12-18% */
-    {{448, 128}, {1353, 74}, {2238, 41}},    /* Q == 3 : 18-25% */
-    {{556, 128}, {1353, 74}, {2238, 47}},    /* Q == 4 : 25-32% */
-    {{714, 128}, {1418, 74}, {2436, 53}},    /* Q == 5 : 32-38% */
-    {{883, 128}, {1437, 74}, {2464, 61}},    /* Q == 6 : 38-44% */
-    {{897, 128}, {1515, 75}, {2622, 68}},    /* Q == 7 : 44-50% */
-    {{926, 128}, {1613, 75}, {2730, 75}},    /* Q == 8 : 50-56% */
-    {{947, 128}, {1729, 77}, {3359, 77}},    /* Q == 9 : 56-62% */
-    {{1107, 128}, {2083, 81}, {4006, 84}},   /* Q ==10 : 62-69% */
-    {{1177, 128}, {2379, 87}, {4785, 88}},   /* Q ==11 : 69-75% */
-    {{1242, 128}, {2415, 93}, {5155, 84}},   /* Q ==12 : 75-81% */
-    {{1349, 128}, {2644, 106}, {5260, 106}}, /* Q ==13 : 81-87% */
-    {{1455, 128}, {2422, 124}, {4174, 124}}, /* Q ==14 : 87-93% */
-    {{722, 128}, {1891, 145}, {1936, 146}},  /* Q ==15 : 93-99% */
-};
-
-/** HUF_selectDecoder() :
-*   Tells which decoder is likely to decode faster,
-*   based on a set of pre-determined metrics.
-*   @return : 0==HUF_decompress4X2, 1==HUF_decompress4X4 .
-*   Assumption : 0 < cSrcSize < dstSize <= 128 KB */
-U32 HUF_selectDecoder(size_t dstSize, size_t cSrcSize)
-{
-	/* decoder timing evaluation */
-	U32 const Q = (U32)(cSrcSize * 16 / dstSize); /* Q < 16 since dstSize > cSrcSize */
-	U32 const D256 = (U32)(dstSize >> 8);
-	U32 const DTime0 = algoTime[Q][0].tableTime + (algoTime[Q][0].decode256Time * D256);
-	U32 DTime1 = algoTime[Q][1].tableTime + (algoTime[Q][1].decode256Time * D256);
-	DTime1 += DTime1 >> 3; /* advantage to algorithm using less memory, for cache eviction */
-
-	return DTime1 < DTime0;
-}
-
-typedef size_t (*decompressionAlgo)(void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize);
-
-size_t HUF_decompress4X_DCtx_wksp(HUF_DTable *dctx, void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, void *workspace, size_t workspaceSize)
-{
-	/* validation checks */
-	if (dstSize == 0)
-		return ERROR(dstSize_tooSmall);
-	if (cSrcSize > dstSize)
-		return ERROR(corruption_detected); /* invalid */
-	if (cSrcSize == dstSize) {
-		memcpy(dst, cSrc, dstSize);
-		return dstSize;
-	} /* not compressed */
-	if (cSrcSize == 1) {
-		memset(dst, *(const BYTE *)cSrc, dstSize);
-		return dstSize;
-	} /* RLE */
-
-	{
-		U32 const algoNb = HUF_selectDecoder(dstSize, cSrcSize);
-		return algoNb ? HUF_decompress4X4_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize, workspace, workspaceSize)
-			      : HUF_decompress4X2_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize, workspace, workspaceSize);
-	}
-}
-
-size_t HUF_decompress4X_hufOnly_wksp(HUF_DTable *dctx, void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, void *workspace, size_t workspaceSize)
-{
-	/* validation checks */
-	if (dstSize == 0)
-		return ERROR(dstSize_tooSmall);
-	if ((cSrcSize >= dstSize) || (cSrcSize <= 1))
-		return ERROR(corruption_detected); /* invalid */
-
-	{
-		U32 const algoNb = HUF_selectDecoder(dstSize, cSrcSize);
-		return algoNb ? HUF_decompress4X4_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize, workspace, workspaceSize)
-			      : HUF_decompress4X2_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize, workspace, workspaceSize);
-	}
-}
-
-size_t HUF_decompress1X_DCtx_wksp(HUF_DTable *dctx, void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, void *workspace, size_t workspaceSize)
-{
-	/* validation checks */
-	if (dstSize == 0)
-		return ERROR(dstSize_tooSmall);
-	if (cSrcSize > dstSize)
-		return ERROR(corruption_detected); /* invalid */
-	if (cSrcSize == dstSize) {
-		memcpy(dst, cSrc, dstSize);
-		return dstSize;
-	} /* not compressed */
-	if (cSrcSize == 1) {
-		memset(dst, *(const BYTE *)cSrc, dstSize);
-		return dstSize;
-	} /* RLE */
-
-	{
-		U32 const algoNb = HUF_selectDecoder(dstSize, cSrcSize);
-		return algoNb ? HUF_decompress1X4_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize, workspace, workspaceSize)
-			      : HUF_decompress1X2_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize, workspace, workspaceSize);
-	}
-}
diff --git a/lib/zstd/mem.h b/lib/zstd/mem.h
deleted file mode 100644
index 93d7a2c377fe..000000000000
--- a/lib/zstd/mem.h
+++ /dev/null
@@ -1,151 +0,0 @@
-/**
- * Copyright (c) 2016-present, Yann Collet, Facebook, Inc.
- * All rights reserved.
- *
- * This source code is licensed under the BSD-style license found in the
- * LICENSE file in the root directory of https://github.com/facebook/zstd.
- * An additional grant of patent rights can be found in the PATENTS file in the
- * same directory.
- *
- * 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. This program is dual-licensed; you may select
- * either version 2 of the GNU General Public License ("GPL") or BSD license
- * ("BSD").
- */
-
-#ifndef MEM_H_MODULE
-#define MEM_H_MODULE
-
-/*-****************************************
-*  Dependencies
-******************************************/
-#include <asm/unaligned.h>
-#include <linux/string.h> /* memcpy */
-#include <linux/types.h>  /* size_t, ptrdiff_t */
-
-/*-****************************************
-*  Compiler specifics
-******************************************/
-#define ZSTD_STATIC static inline
-
-/*-**************************************************************
-*  Basic Types
-*****************************************************************/
-typedef uint8_t BYTE;
-typedef uint16_t U16;
-typedef int16_t S16;
-typedef uint32_t U32;
-typedef int32_t S32;
-typedef uint64_t U64;
-typedef int64_t S64;
-typedef ptrdiff_t iPtrDiff;
-typedef uintptr_t uPtrDiff;
-
-/*-**************************************************************
-*  Memory I/O
-*****************************************************************/
-ZSTD_STATIC unsigned ZSTD_32bits(void) { return sizeof(size_t) == 4; }
-ZSTD_STATIC unsigned ZSTD_64bits(void) { return sizeof(size_t) == 8; }
-
-#if defined(__LITTLE_ENDIAN)
-#define ZSTD_LITTLE_ENDIAN 1
-#else
-#define ZSTD_LITTLE_ENDIAN 0
-#endif
-
-ZSTD_STATIC unsigned ZSTD_isLittleEndian(void) { return ZSTD_LITTLE_ENDIAN; }
-
-ZSTD_STATIC U16 ZSTD_read16(const void *memPtr) { return get_unaligned((const U16 *)memPtr); }
-
-ZSTD_STATIC U32 ZSTD_read32(const void *memPtr) { return get_unaligned((const U32 *)memPtr); }
-
-ZSTD_STATIC U64 ZSTD_read64(const void *memPtr) { return get_unaligned((const U64 *)memPtr); }
-
-ZSTD_STATIC size_t ZSTD_readST(const void *memPtr) { return get_unaligned((const size_t *)memPtr); }
-
-ZSTD_STATIC void ZSTD_write16(void *memPtr, U16 value) { put_unaligned(value, (U16 *)memPtr); }
-
-ZSTD_STATIC void ZSTD_write32(void *memPtr, U32 value) { put_unaligned(value, (U32 *)memPtr); }
-
-ZSTD_STATIC void ZSTD_write64(void *memPtr, U64 value) { put_unaligned(value, (U64 *)memPtr); }
-
-/*=== Little endian r/w ===*/
-
-ZSTD_STATIC U16 ZSTD_readLE16(const void *memPtr) { return get_unaligned_le16(memPtr); }
-
-ZSTD_STATIC void ZSTD_writeLE16(void *memPtr, U16 val) { put_unaligned_le16(val, memPtr); }
-
-ZSTD_STATIC U32 ZSTD_readLE24(const void *memPtr) { return ZSTD_readLE16(memPtr) + (((const BYTE *)memPtr)[2] << 16); }
-
-ZSTD_STATIC void ZSTD_writeLE24(void *memPtr, U32 val)
-{
-	ZSTD_writeLE16(memPtr, (U16)val);
-	((BYTE *)memPtr)[2] = (BYTE)(val >> 16);
-}
-
-ZSTD_STATIC U32 ZSTD_readLE32(const void *memPtr) { return get_unaligned_le32(memPtr); }
-
-ZSTD_STATIC void ZSTD_writeLE32(void *memPtr, U32 val32) { put_unaligned_le32(val32, memPtr); }
-
-ZSTD_STATIC U64 ZSTD_readLE64(const void *memPtr) { return get_unaligned_le64(memPtr); }
-
-ZSTD_STATIC void ZSTD_writeLE64(void *memPtr, U64 val64) { put_unaligned_le64(val64, memPtr); }
-
-ZSTD_STATIC size_t ZSTD_readLEST(const void *memPtr)
-{
-	if (ZSTD_32bits())
-		return (size_t)ZSTD_readLE32(memPtr);
-	else
-		return (size_t)ZSTD_readLE64(memPtr);
-}
-
-ZSTD_STATIC void ZSTD_writeLEST(void *memPtr, size_t val)
-{
-	if (ZSTD_32bits())
-		ZSTD_writeLE32(memPtr, (U32)val);
-	else
-		ZSTD_writeLE64(memPtr, (U64)val);
-}
-
-/*=== Big endian r/w ===*/
-
-ZSTD_STATIC U32 ZSTD_readBE32(const void *memPtr) { return get_unaligned_be32(memPtr); }
-
-ZSTD_STATIC void ZSTD_writeBE32(void *memPtr, U32 val32) { put_unaligned_be32(val32, memPtr); }
-
-ZSTD_STATIC U64 ZSTD_readBE64(const void *memPtr) { return get_unaligned_be64(memPtr); }
-
-ZSTD_STATIC void ZSTD_writeBE64(void *memPtr, U64 val64) { put_unaligned_be64(val64, memPtr); }
-
-ZSTD_STATIC size_t ZSTD_readBEST(const void *memPtr)
-{
-	if (ZSTD_32bits())
-		return (size_t)ZSTD_readBE32(memPtr);
-	else
-		return (size_t)ZSTD_readBE64(memPtr);
-}
-
-ZSTD_STATIC void ZSTD_writeBEST(void *memPtr, size_t val)
-{
-	if (ZSTD_32bits())
-		ZSTD_writeBE32(memPtr, (U32)val);
-	else
-		ZSTD_writeBE64(memPtr, (U64)val);
-}
-
-/* function safe only for comparisons */
-ZSTD_STATIC U32 ZSTD_readMINMATCH(const void *memPtr, U32 length)
-{
-	switch (length) {
-	default:
-	case 4: return ZSTD_read32(memPtr);
-	case 3:
-		if (ZSTD_isLittleEndian())
-			return ZSTD_read32(memPtr) << 8;
-		else
-			return ZSTD_read32(memPtr) >> 8;
-	}
-}
-
-#endif /* MEM_H_MODULE */
diff --git a/lib/zstd/zstd_common.c b/lib/zstd/zstd_common.c
deleted file mode 100644
index a282624ee155..000000000000
--- a/lib/zstd/zstd_common.c
+++ /dev/null
@@ -1,75 +0,0 @@
-/**
- * Copyright (c) 2016-present, Yann Collet, Facebook, Inc.
- * All rights reserved.
- *
- * This source code is licensed under the BSD-style license found in the
- * LICENSE file in the root directory of https://github.com/facebook/zstd.
- * An additional grant of patent rights can be found in the PATENTS file in the
- * same directory.
- *
- * 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. This program is dual-licensed; you may select
- * either version 2 of the GNU General Public License ("GPL") or BSD license
- * ("BSD").
- */
-
-/*-*************************************
-*  Dependencies
-***************************************/
-#include "error_private.h"
-#include "zstd_internal.h" /* declaration of ZSTD_isError, ZSTD_getErrorName, ZSTD_getErrorCode, ZSTD_getErrorString, ZSTD_versionNumber */
-#include <linux/kernel.h>
-
-/*=**************************************************************
-*  Custom allocator
-****************************************************************/
-
-#define stack_push(stack, size)                                 \
-	({                                                      \
-		void *const ptr = ZSTD_PTR_ALIGN((stack)->ptr); \
-		(stack)->ptr = (char *)ptr + (size);            \
-		(stack)->ptr <= (stack)->end ? ptr : NULL;      \
-	})
-
-ZSTD_customMem ZSTD_initStack(void *workspace, size_t workspaceSize)
-{
-	ZSTD_customMem stackMem = {ZSTD_stackAlloc, ZSTD_stackFree, workspace};
-	ZSTD_stack *stack = (ZSTD_stack *)workspace;
-	/* Verify preconditions */
-	if (!workspace || workspaceSize < sizeof(ZSTD_stack) || workspace != ZSTD_PTR_ALIGN(workspace)) {
-		ZSTD_customMem error = {NULL, NULL, NULL};
-		return error;
-	}
-	/* Initialize the stack */
-	stack->ptr = workspace;
-	stack->end = (char *)workspace + workspaceSize;
-	stack_push(stack, sizeof(ZSTD_stack));
-	return stackMem;
-}
-
-void *ZSTD_stackAllocAll(void *opaque, size_t *size)
-{
-	ZSTD_stack *stack = (ZSTD_stack *)opaque;
-	*size = (BYTE const *)stack->end - (BYTE *)ZSTD_PTR_ALIGN(stack->ptr);
-	return stack_push(stack, *size);
-}
-
-void *ZSTD_stackAlloc(void *opaque, size_t size)
-{
-	ZSTD_stack *stack = (ZSTD_stack *)opaque;
-	return stack_push(stack, size);
-}
-void ZSTD_stackFree(void *opaque, void *address)
-{
-	(void)opaque;
-	(void)address;
-}
-
-void *ZSTD_malloc(size_t size, ZSTD_customMem customMem) { return customMem.customAlloc(customMem.opaque, size); }
-
-void ZSTD_free(void *ptr, ZSTD_customMem customMem)
-{
-	if (ptr != NULL)
-		customMem.customFree(customMem.opaque, ptr);
-}
diff --git a/lib/zstd/zstd_compress_module.c b/lib/zstd/zstd_compress_module.c
new file mode 100644
index 000000000000..65548a4bb934
--- /dev/null
+++ b/lib/zstd/zstd_compress_module.c
@@ -0,0 +1,160 @@
+// SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause
+/*
+ * Copyright (c) Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/zstd.h>
+
+#include "common/zstd_deps.h"
+#include "common/zstd_internal.h"
+
+#define ZSTD_FORWARD_IF_ERR(ret)            \
+	do {                                \
+		size_t const __ret = (ret); \
+		if (ZSTD_isError(__ret))    \
+			return __ret;       \
+	} while (0)
+
+static size_t zstd_cctx_init(zstd_cctx *cctx, const zstd_parameters *parameters,
+	unsigned long long pledged_src_size)
+{
+	ZSTD_FORWARD_IF_ERR(ZSTD_CCtx_reset(
+		cctx, ZSTD_reset_session_and_parameters));
+	ZSTD_FORWARD_IF_ERR(ZSTD_CCtx_setPledgedSrcSize(
+		cctx, pledged_src_size));
+	ZSTD_FORWARD_IF_ERR(ZSTD_CCtx_setParameter(
+		cctx, ZSTD_c_windowLog, parameters->cParams.windowLog));
+	ZSTD_FORWARD_IF_ERR(ZSTD_CCtx_setParameter(
+		cctx, ZSTD_c_hashLog, parameters->cParams.hashLog));
+	ZSTD_FORWARD_IF_ERR(ZSTD_CCtx_setParameter(
+		cctx, ZSTD_c_chainLog, parameters->cParams.chainLog));
+	ZSTD_FORWARD_IF_ERR(ZSTD_CCtx_setParameter(
+		cctx, ZSTD_c_searchLog, parameters->cParams.searchLog));
+	ZSTD_FORWARD_IF_ERR(ZSTD_CCtx_setParameter(
+		cctx, ZSTD_c_minMatch, parameters->cParams.minMatch));
+	ZSTD_FORWARD_IF_ERR(ZSTD_CCtx_setParameter(
+		cctx, ZSTD_c_targetLength, parameters->cParams.targetLength));
+	ZSTD_FORWARD_IF_ERR(ZSTD_CCtx_setParameter(
+		cctx, ZSTD_c_strategy, parameters->cParams.strategy));
+	ZSTD_FORWARD_IF_ERR(ZSTD_CCtx_setParameter(
+		cctx, ZSTD_c_contentSizeFlag, parameters->fParams.contentSizeFlag));
+	ZSTD_FORWARD_IF_ERR(ZSTD_CCtx_setParameter(
+		cctx, ZSTD_c_checksumFlag, parameters->fParams.checksumFlag));
+	ZSTD_FORWARD_IF_ERR(ZSTD_CCtx_setParameter(
+		cctx, ZSTD_c_dictIDFlag, !parameters->fParams.noDictIDFlag));
+	return 0;
+}
+
+int zstd_min_clevel(void)
+{
+	return ZSTD_minCLevel();
+}
+EXPORT_SYMBOL(zstd_min_clevel);
+
+int zstd_max_clevel(void)
+{
+	return ZSTD_maxCLevel();
+}
+EXPORT_SYMBOL(zstd_max_clevel);
+
+size_t zstd_compress_bound(size_t src_size)
+{
+	return ZSTD_compressBound(src_size);
+}
+EXPORT_SYMBOL(zstd_compress_bound);
+
+zstd_parameters zstd_get_params(int level,
+	unsigned long long estimated_src_size)
+{
+	return ZSTD_getParams(level, estimated_src_size, 0);
+}
+EXPORT_SYMBOL(zstd_get_params);
+
+size_t zstd_cctx_workspace_bound(const zstd_compression_parameters *cparams)
+{
+	return ZSTD_estimateCCtxSize_usingCParams(*cparams);
+}
+EXPORT_SYMBOL(zstd_cctx_workspace_bound);
+
+zstd_cctx *zstd_init_cctx(void *workspace, size_t workspace_size)
+{
+	if (workspace == NULL)
+		return NULL;
+	return ZSTD_initStaticCCtx(workspace, workspace_size);
+}
+EXPORT_SYMBOL(zstd_init_cctx);
+
+size_t zstd_compress_cctx(zstd_cctx *cctx, void *dst, size_t dst_capacity,
+	const void *src, size_t src_size, const zstd_parameters *parameters)
+{
+	ZSTD_FORWARD_IF_ERR(zstd_cctx_init(cctx, parameters, src_size));
+	return ZSTD_compress2(cctx, dst, dst_capacity, src, src_size);
+}
+EXPORT_SYMBOL(zstd_compress_cctx);
+
+size_t zstd_cstream_workspace_bound(const zstd_compression_parameters *cparams)
+{
+	return ZSTD_estimateCStreamSize_usingCParams(*cparams);
+}
+EXPORT_SYMBOL(zstd_cstream_workspace_bound);
+
+zstd_cstream *zstd_init_cstream(const zstd_parameters *parameters,
+	unsigned long long pledged_src_size, void *workspace, size_t workspace_size)
+{
+	zstd_cstream *cstream;
+
+	if (workspace == NULL)
+		return NULL;
+
+	cstream = ZSTD_initStaticCStream(workspace, workspace_size);
+	if (cstream == NULL)
+		return NULL;
+
+	/* 0 means unknown in linux zstd API but means 0 in new zstd API */
+	if (pledged_src_size == 0)
+		pledged_src_size = ZSTD_CONTENTSIZE_UNKNOWN;
+
+	if (ZSTD_isError(zstd_cctx_init(cstream, parameters, pledged_src_size)))
+		return NULL;
+
+	return cstream;
+}
+EXPORT_SYMBOL(zstd_init_cstream);
+
+size_t zstd_reset_cstream(zstd_cstream *cstream,
+	unsigned long long pledged_src_size)
+{
+	return ZSTD_resetCStream(cstream, pledged_src_size);
+}
+EXPORT_SYMBOL(zstd_reset_cstream);
+
+size_t zstd_compress_stream(zstd_cstream *cstream, zstd_out_buffer *output,
+	zstd_in_buffer *input)
+{
+	return ZSTD_compressStream(cstream, output, input);
+}
+EXPORT_SYMBOL(zstd_compress_stream);
+
+size_t zstd_flush_stream(zstd_cstream *cstream, zstd_out_buffer *output)
+{
+	return ZSTD_flushStream(cstream, output);
+}
+EXPORT_SYMBOL(zstd_flush_stream);
+
+size_t zstd_end_stream(zstd_cstream *cstream, zstd_out_buffer *output)
+{
+	return ZSTD_endStream(cstream, output);
+}
+EXPORT_SYMBOL(zstd_end_stream);
+
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("Zstd Compressor");
diff --git a/lib/zstd/zstd_decompress_module.c b/lib/zstd/zstd_decompress_module.c
new file mode 100644
index 000000000000..f4ed952ed485
--- /dev/null
+++ b/lib/zstd/zstd_decompress_module.c
@@ -0,0 +1,105 @@
+// SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause
+/*
+ * Copyright (c) Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/zstd.h>
+
+#include "common/zstd_deps.h"
+
+/* Common symbols. zstd_compress must depend on zstd_decompress. */
+
+unsigned int zstd_is_error(size_t code)
+{
+	return ZSTD_isError(code);
+}
+EXPORT_SYMBOL(zstd_is_error);
+
+zstd_error_code zstd_get_error_code(size_t code)
+{
+	return ZSTD_getErrorCode(code);
+}
+EXPORT_SYMBOL(zstd_get_error_code);
+
+const char *zstd_get_error_name(size_t code)
+{
+	return ZSTD_getErrorName(code);
+}
+EXPORT_SYMBOL(zstd_get_error_name);
+
+/* Decompression symbols. */
+
+size_t zstd_dctx_workspace_bound(void)
+{
+	return ZSTD_estimateDCtxSize();
+}
+EXPORT_SYMBOL(zstd_dctx_workspace_bound);
+
+zstd_dctx *zstd_init_dctx(void *workspace, size_t workspace_size)
+{
+	if (workspace == NULL)
+		return NULL;
+	return ZSTD_initStaticDCtx(workspace, workspace_size);
+}
+EXPORT_SYMBOL(zstd_init_dctx);
+
+size_t zstd_decompress_dctx(zstd_dctx *dctx, void *dst, size_t dst_capacity,
+	const void *src, size_t src_size)
+{
+	return ZSTD_decompressDCtx(dctx, dst, dst_capacity, src, src_size);
+}
+EXPORT_SYMBOL(zstd_decompress_dctx);
+
+size_t zstd_dstream_workspace_bound(size_t max_window_size)
+{
+	return ZSTD_estimateDStreamSize(max_window_size);
+}
+EXPORT_SYMBOL(zstd_dstream_workspace_bound);
+
+zstd_dstream *zstd_init_dstream(size_t max_window_size, void *workspace,
+	size_t workspace_size)
+{
+	if (workspace == NULL)
+		return NULL;
+	(void)max_window_size;
+	return ZSTD_initStaticDStream(workspace, workspace_size);
+}
+EXPORT_SYMBOL(zstd_init_dstream);
+
+size_t zstd_reset_dstream(zstd_dstream *dstream)
+{
+	return ZSTD_resetDStream(dstream);
+}
+EXPORT_SYMBOL(zstd_reset_dstream);
+
+size_t zstd_decompress_stream(zstd_dstream *dstream, zstd_out_buffer *output,
+	zstd_in_buffer *input)
+{
+	return ZSTD_decompressStream(dstream, output, input);
+}
+EXPORT_SYMBOL(zstd_decompress_stream);
+
+size_t zstd_find_frame_compressed_size(const void *src, size_t src_size)
+{
+	return ZSTD_findFrameCompressedSize(src, src_size);
+}
+EXPORT_SYMBOL(zstd_find_frame_compressed_size);
+
+size_t zstd_get_frame_header(zstd_frame_header *header, const void *src,
+	size_t src_size)
+{
+	return ZSTD_getFrameHeader(header, src, src_size);
+}
+EXPORT_SYMBOL(zstd_get_frame_header);
+
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("Zstd Decompressor");
diff --git a/lib/zstd/zstd_internal.h b/lib/zstd/zstd_internal.h
deleted file mode 100644
index dac753397f86..000000000000
--- a/lib/zstd/zstd_internal.h
+++ /dev/null
@@ -1,273 +0,0 @@
-/**
- * Copyright (c) 2016-present, Yann Collet, Facebook, Inc.
- * All rights reserved.
- *
- * This source code is licensed under the BSD-style license found in the
- * LICENSE file in the root directory of https://github.com/facebook/zstd.
- * An additional grant of patent rights can be found in the PATENTS file in the
- * same directory.
- *
- * 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. This program is dual-licensed; you may select
- * either version 2 of the GNU General Public License ("GPL") or BSD license
- * ("BSD").
- */
-
-#ifndef ZSTD_CCOMMON_H_MODULE
-#define ZSTD_CCOMMON_H_MODULE
-
-/*-*******************************************************
-*  Compiler specifics
-*********************************************************/
-#define FORCE_INLINE static __always_inline
-#define FORCE_NOINLINE static noinline
-
-/*-*************************************
-*  Dependencies
-***************************************/
-#include "error_private.h"
-#include "mem.h"
-#include <linux/compiler.h>
-#include <linux/kernel.h>
-#include <linux/xxhash.h>
-#include <linux/zstd.h>
-
-/*-*************************************
-*  shared macros
-***************************************/
-#define MIN(a, b) ((a) < (b) ? (a) : (b))
-#define MAX(a, b) ((a) > (b) ? (a) : (b))
-#define CHECK_F(f)                       \
-	{                                \
-		size_t const errcod = f; \
-		if (ERR_isError(errcod)) \
-			return errcod;   \
-	} /* check and Forward error code */
-#define CHECK_E(f, e)                    \
-	{                                \
-		size_t const errcod = f; \
-		if (ERR_isError(errcod)) \
-			return ERROR(e); \
-	} /* check and send Error code */
-#define ZSTD_STATIC_ASSERT(c)                                   \
-	{                                                       \
-		enum { ZSTD_static_assert = 1 / (int)(!!(c)) }; \
-	}
-
-/*-*************************************
-*  Common constants
-***************************************/
-#define ZSTD_OPT_NUM (1 << 12)
-#define ZSTD_DICT_MAGIC 0xEC30A437 /* v0.7+ */
-
-#define ZSTD_REP_NUM 3		      /* number of repcodes */
-#define ZSTD_REP_CHECK (ZSTD_REP_NUM) /* number of repcodes to check by the optimal parser */
-#define ZSTD_REP_MOVE (ZSTD_REP_NUM - 1)
-#define ZSTD_REP_MOVE_OPT (ZSTD_REP_NUM)
-static const U32 repStartValue[ZSTD_REP_NUM] = {1, 4, 8};
-
-#define KB *(1 << 10)
-#define MB *(1 << 20)
-#define GB *(1U << 30)
-
-#define BIT7 128
-#define BIT6 64
-#define BIT5 32
-#define BIT4 16
-#define BIT1 2
-#define BIT0 1
-
-#define ZSTD_WINDOWLOG_ABSOLUTEMIN 10
-static const size_t ZSTD_fcs_fieldSize[4] = {0, 2, 4, 8};
-static const size_t ZSTD_did_fieldSize[4] = {0, 1, 2, 4};
-
-#define ZSTD_BLOCKHEADERSIZE 3 /* C standard doesn't allow `static const` variable to be init using another `static const` variable */
-static const size_t ZSTD_blockHeaderSize = ZSTD_BLOCKHEADERSIZE;
-typedef enum { bt_raw, bt_rle, bt_compressed, bt_reserved } blockType_e;
-
-#define MIN_SEQUENCES_SIZE 1									  /* nbSeq==0 */
-#define MIN_CBLOCK_SIZE (1 /*litCSize*/ + 1 /* RLE or RAW */ + MIN_SEQUENCES_SIZE /* nbSeq==0 */) /* for a non-null block */
-
-#define HufLog 12
-typedef enum { set_basic, set_rle, set_compressed, set_repeat } symbolEncodingType_e;
-
-#define LONGNBSEQ 0x7F00
-
-#define MINMATCH 3
-#define EQUAL_READ32 4
-
-#define Litbits 8
-#define MaxLit ((1 << Litbits) - 1)
-#define MaxML 52
-#define MaxLL 35
-#define MaxOff 28
-#define MaxSeq MAX(MaxLL, MaxML) /* Assumption : MaxOff < MaxLL,MaxML */
-#define MLFSELog 9
-#define LLFSELog 9
-#define OffFSELog 8
-
-static const U32 LL_bits[MaxLL + 1] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 2, 2, 3, 3, 4, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16};
-static const S16 LL_defaultNorm[MaxLL + 1] = {4, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 1, 1, 1, 1, 1, -1, -1, -1, -1};
-#define LL_DEFAULTNORMLOG 6 /* for static allocation */
-static const U32 LL_defaultNormLog = LL_DEFAULTNORMLOG;
-
-static const U32 ML_bits[MaxML + 1] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  0,  0,  0,  0,  0,  0, 0,
-				       0, 0, 0, 0, 0, 1, 1, 1, 1, 2, 2, 3, 3, 4, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16};
-static const S16 ML_defaultNorm[MaxML + 1] = {1, 4, 3, 2, 2, 2, 2, 2, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,  1,  1,  1,  1,  1,  1, 1,
-					      1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, -1, -1, -1, -1, -1, -1, -1};
-#define ML_DEFAULTNORMLOG 6 /* for static allocation */
-static const U32 ML_defaultNormLog = ML_DEFAULTNORMLOG;
-
-static const S16 OF_defaultNorm[MaxOff + 1] = {1, 1, 1, 1, 1, 1, 2, 2, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, -1, -1, -1, -1, -1};
-#define OF_DEFAULTNORMLOG 5 /* for static allocation */
-static const U32 OF_defaultNormLog = OF_DEFAULTNORMLOG;
-
-/*-*******************************************
-*  Shared functions to include for inlining
-*********************************************/
-ZSTD_STATIC void ZSTD_copy8(void *dst, const void *src) {
-	/*
-	 * zstd relies heavily on gcc being able to analyze and inline this
-	 * memcpy() call, since it is called in a tight loop. Preboot mode
-	 * is compiled in freestanding mode, which stops gcc from analyzing
-	 * memcpy(). Use __builtin_memcpy() to tell gcc to analyze this as a
-	 * regular memcpy().
-	 */
-	__builtin_memcpy(dst, src, 8);
-}
-/*! ZSTD_wildcopy() :
-*   custom version of memcpy(), can copy up to 7 bytes too many (8 bytes if length==0) */
-#define WILDCOPY_OVERLENGTH 8
-ZSTD_STATIC void ZSTD_wildcopy(void *dst, const void *src, ptrdiff_t length)
-{
-	const BYTE* ip = (const BYTE*)src;
-	BYTE* op = (BYTE*)dst;
-	BYTE* const oend = op + length;
-#if defined(GCC_VERSION) && GCC_VERSION >= 70000 && GCC_VERSION < 70200
-	/*
-	 * Work around https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81388.
-	 * Avoid the bad case where the loop only runs once by handling the
-	 * special case separately. This doesn't trigger the bug because it
-	 * doesn't involve pointer/integer overflow.
-	 */
-	if (length <= 8)
-		return ZSTD_copy8(dst, src);
-#endif
-	do {
-		ZSTD_copy8(op, ip);
-		op += 8;
-		ip += 8;
-	} while (op < oend);
-}
-
-/*-*******************************************
-*  Private interfaces
-*********************************************/
-typedef struct ZSTD_stats_s ZSTD_stats_t;
-
-typedef struct {
-	U32 off;
-	U32 len;
-} ZSTD_match_t;
-
-typedef struct {
-	U32 price;
-	U32 off;
-	U32 mlen;
-	U32 litlen;
-	U32 rep[ZSTD_REP_NUM];
-} ZSTD_optimal_t;
-
-typedef struct seqDef_s {
-	U32 offset;
-	U16 litLength;
-	U16 matchLength;
-} seqDef;
-
-typedef struct {
-	seqDef *sequencesStart;
-	seqDef *sequences;
-	BYTE *litStart;
-	BYTE *lit;
-	BYTE *llCode;
-	BYTE *mlCode;
-	BYTE *ofCode;
-	U32 longLengthID; /* 0 == no longLength; 1 == Lit.longLength; 2 == Match.longLength; */
-	U32 longLengthPos;
-	/* opt */
-	ZSTD_optimal_t *priceTable;
-	ZSTD_match_t *matchTable;
-	U32 *matchLengthFreq;
-	U32 *litLengthFreq;
-	U32 *litFreq;
-	U32 *offCodeFreq;
-	U32 matchLengthSum;
-	U32 matchSum;
-	U32 litLengthSum;
-	U32 litSum;
-	U32 offCodeSum;
-	U32 log2matchLengthSum;
-	U32 log2matchSum;
-	U32 log2litLengthSum;
-	U32 log2litSum;
-	U32 log2offCodeSum;
-	U32 factor;
-	U32 staticPrices;
-	U32 cachedPrice;
-	U32 cachedLitLength;
-	const BYTE *cachedLiterals;
-} seqStore_t;
-
-const seqStore_t *ZSTD_getSeqStore(const ZSTD_CCtx *ctx);
-void ZSTD_seqToCodes(const seqStore_t *seqStorePtr);
-int ZSTD_isSkipFrame(ZSTD_DCtx *dctx);
-
-/*= Custom memory allocation functions */
-typedef void *(*ZSTD_allocFunction)(void *opaque, size_t size);
-typedef void (*ZSTD_freeFunction)(void *opaque, void *address);
-typedef struct {
-	ZSTD_allocFunction customAlloc;
-	ZSTD_freeFunction customFree;
-	void *opaque;
-} ZSTD_customMem;
-
-void *ZSTD_malloc(size_t size, ZSTD_customMem customMem);
-void ZSTD_free(void *ptr, ZSTD_customMem customMem);
-
-/*====== stack allocation  ======*/
-
-typedef struct {
-	void *ptr;
-	const void *end;
-} ZSTD_stack;
-
-#define ZSTD_ALIGN(x) ALIGN(x, sizeof(size_t))
-#define ZSTD_PTR_ALIGN(p) PTR_ALIGN(p, sizeof(size_t))
-
-ZSTD_customMem ZSTD_initStack(void *workspace, size_t workspaceSize);
-
-void *ZSTD_stackAllocAll(void *opaque, size_t *size);
-void *ZSTD_stackAlloc(void *opaque, size_t size);
-void ZSTD_stackFree(void *opaque, void *address);
-
-/*======  common function  ======*/
-
-ZSTD_STATIC U32 ZSTD_highbit32(U32 val) { return 31 - __builtin_clz(val); }
-
-/* hidden functions */
-
-/* ZSTD_invalidateRepCodes() :
- * ensures next compression will not use repcodes from previous block.
- * Note : only works with regular variant;
- *        do not use with extDict variant ! */
-void ZSTD_invalidateRepCodes(ZSTD_CCtx *cctx);
-
-size_t ZSTD_freeCCtx(ZSTD_CCtx *cctx);
-size_t ZSTD_freeDCtx(ZSTD_DCtx *dctx);
-size_t ZSTD_freeCDict(ZSTD_CDict *cdict);
-size_t ZSTD_freeDDict(ZSTD_DDict *cdict);
-size_t ZSTD_freeCStream(ZSTD_CStream *zcs);
-size_t ZSTD_freeDStream(ZSTD_DStream *zds);
-
-#endif /* ZSTD_CCOMMON_H_MODULE */
diff --git a/lib/zstd/zstd_opt.h b/lib/zstd/zstd_opt.h
deleted file mode 100644
index 55e1b4cba808..000000000000
--- a/lib/zstd/zstd_opt.h
+++ /dev/null
@@ -1,1014 +0,0 @@
-/**
- * Copyright (c) 2016-present, Przemyslaw Skibinski, Yann Collet, Facebook, Inc.
- * All rights reserved.
- *
- * This source code is licensed under the BSD-style license found in the
- * LICENSE file in the root directory of https://github.com/facebook/zstd.
- * An additional grant of patent rights can be found in the PATENTS file in the
- * same directory.
- *
- * 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. This program is dual-licensed; you may select
- * either version 2 of the GNU General Public License ("GPL") or BSD license
- * ("BSD").
- */
-
-/* Note : this file is intended to be included within zstd_compress.c */
-
-#ifndef ZSTD_OPT_H_91842398743
-#define ZSTD_OPT_H_91842398743
-
-#define ZSTD_LITFREQ_ADD 2
-#define ZSTD_FREQ_DIV 4
-#define ZSTD_MAX_PRICE (1 << 30)
-
-/*-*************************************
-*  Price functions for optimal parser
-***************************************/
-FORCE_INLINE void ZSTD_setLog2Prices(seqStore_t *ssPtr)
-{
-	ssPtr->log2matchLengthSum = ZSTD_highbit32(ssPtr->matchLengthSum + 1);
-	ssPtr->log2litLengthSum = ZSTD_highbit32(ssPtr->litLengthSum + 1);
-	ssPtr->log2litSum = ZSTD_highbit32(ssPtr->litSum + 1);
-	ssPtr->log2offCodeSum = ZSTD_highbit32(ssPtr->offCodeSum + 1);
-	ssPtr->factor = 1 + ((ssPtr->litSum >> 5) / ssPtr->litLengthSum) + ((ssPtr->litSum << 1) / (ssPtr->litSum + ssPtr->matchSum));
-}
-
-ZSTD_STATIC void ZSTD_rescaleFreqs(seqStore_t *ssPtr, const BYTE *src, size_t srcSize)
-{
-	unsigned u;
-
-	ssPtr->cachedLiterals = NULL;
-	ssPtr->cachedPrice = ssPtr->cachedLitLength = 0;
-	ssPtr->staticPrices = 0;
-
-	if (ssPtr->litLengthSum == 0) {
-		if (srcSize <= 1024)
-			ssPtr->staticPrices = 1;
-
-		for (u = 0; u <= MaxLit; u++)
-			ssPtr->litFreq[u] = 0;
-		for (u = 0; u < srcSize; u++)
-			ssPtr->litFreq[src[u]]++;
-
-		ssPtr->litSum = 0;
-		ssPtr->litLengthSum = MaxLL + 1;
-		ssPtr->matchLengthSum = MaxML + 1;
-		ssPtr->offCodeSum = (MaxOff + 1);
-		ssPtr->matchSum = (ZSTD_LITFREQ_ADD << Litbits);
-
-		for (u = 0; u <= MaxLit; u++) {
-			ssPtr->litFreq[u] = 1 + (ssPtr->litFreq[u] >> ZSTD_FREQ_DIV);
-			ssPtr->litSum += ssPtr->litFreq[u];
-		}
-		for (u = 0; u <= MaxLL; u++)
-			ssPtr->litLengthFreq[u] = 1;
-		for (u = 0; u <= MaxML; u++)
-			ssPtr->matchLengthFreq[u] = 1;
-		for (u = 0; u <= MaxOff; u++)
-			ssPtr->offCodeFreq[u] = 1;
-	} else {
-		ssPtr->matchLengthSum = 0;
-		ssPtr->litLengthSum = 0;
-		ssPtr->offCodeSum = 0;
-		ssPtr->matchSum = 0;
-		ssPtr->litSum = 0;
-
-		for (u = 0; u <= MaxLit; u++) {
-			ssPtr->litFreq[u] = 1 + (ssPtr->litFreq[u] >> (ZSTD_FREQ_DIV + 1));
-			ssPtr->litSum += ssPtr->litFreq[u];
-		}
-		for (u = 0; u <= MaxLL; u++) {
-			ssPtr->litLengthFreq[u] = 1 + (ssPtr->litLengthFreq[u] >> (ZSTD_FREQ_DIV + 1));
-			ssPtr->litLengthSum += ssPtr->litLengthFreq[u];
-		}
-		for (u = 0; u <= MaxML; u++) {
-			ssPtr->matchLengthFreq[u] = 1 + (ssPtr->matchLengthFreq[u] >> ZSTD_FREQ_DIV);
-			ssPtr->matchLengthSum += ssPtr->matchLengthFreq[u];
-			ssPtr->matchSum += ssPtr->matchLengthFreq[u] * (u + 3);
-		}
-		ssPtr->matchSum *= ZSTD_LITFREQ_ADD;
-		for (u = 0; u <= MaxOff; u++) {
-			ssPtr->offCodeFreq[u] = 1 + (ssPtr->offCodeFreq[u] >> ZSTD_FREQ_DIV);
-			ssPtr->offCodeSum += ssPtr->offCodeFreq[u];
-		}
-	}
-
-	ZSTD_setLog2Prices(ssPtr);
-}
-
-FORCE_INLINE U32 ZSTD_getLiteralPrice(seqStore_t *ssPtr, U32 litLength, const BYTE *literals)
-{
-	U32 price, u;
-
-	if (ssPtr->staticPrices)
-		return ZSTD_highbit32((U32)litLength + 1) + (litLength * 6);
-
-	if (litLength == 0)
-		return ssPtr->log2litLengthSum - ZSTD_highbit32(ssPtr->litLengthFreq[0] + 1);
-
-	/* literals */
-	if (ssPtr->cachedLiterals == literals) {
-		U32 const additional = litLength - ssPtr->cachedLitLength;
-		const BYTE *literals2 = ssPtr->cachedLiterals + ssPtr->cachedLitLength;
-		price = ssPtr->cachedPrice + additional * ssPtr->log2litSum;
-		for (u = 0; u < additional; u++)
-			price -= ZSTD_highbit32(ssPtr->litFreq[literals2[u]] + 1);
-		ssPtr->cachedPrice = price;
-		ssPtr->cachedLitLength = litLength;
-	} else {
-		price = litLength * ssPtr->log2litSum;
-		for (u = 0; u < litLength; u++)
-			price -= ZSTD_highbit32(ssPtr->litFreq[literals[u]] + 1);
-
-		if (litLength >= 12) {
-			ssPtr->cachedLiterals = literals;
-			ssPtr->cachedPrice = price;
-			ssPtr->cachedLitLength = litLength;
-		}
-	}
-
-	/* literal Length */
-	{
-		const BYTE LL_deltaCode = 19;
-		const BYTE llCode = (litLength > 63) ? (BYTE)ZSTD_highbit32(litLength) + LL_deltaCode : LL_Code[litLength];
-		price += LL_bits[llCode] + ssPtr->log2litLengthSum - ZSTD_highbit32(ssPtr->litLengthFreq[llCode] + 1);
-	}
-
-	return price;
-}
-
-FORCE_INLINE U32 ZSTD_getPrice(seqStore_t *seqStorePtr, U32 litLength, const BYTE *literals, U32 offset, U32 matchLength, const int ultra)
-{
-	/* offset */
-	U32 price;
-	BYTE const offCode = (BYTE)ZSTD_highbit32(offset + 1);
-
-	if (seqStorePtr->staticPrices)
-		return ZSTD_getLiteralPrice(seqStorePtr, litLength, literals) + ZSTD_highbit32((U32)matchLength + 1) + 16 + offCode;
-
-	price = offCode + seqStorePtr->log2offCodeSum - ZSTD_highbit32(seqStorePtr->offCodeFreq[offCode] + 1);
-	if (!ultra && offCode >= 20)
-		price += (offCode - 19) * 2;
-
-	/* match Length */
-	{
-		const BYTE ML_deltaCode = 36;
-		const BYTE mlCode = (matchLength > 127) ? (BYTE)ZSTD_highbit32(matchLength) + ML_deltaCode : ML_Code[matchLength];
-		price += ML_bits[mlCode] + seqStorePtr->log2matchLengthSum - ZSTD_highbit32(seqStorePtr->matchLengthFreq[mlCode] + 1);
-	}
-
-	return price + ZSTD_getLiteralPrice(seqStorePtr, litLength, literals) + seqStorePtr->factor;
-}
-
-ZSTD_STATIC void ZSTD_updatePrice(seqStore_t *seqStorePtr, U32 litLength, const BYTE *literals, U32 offset, U32 matchLength)
-{
-	U32 u;
-
-	/* literals */
-	seqStorePtr->litSum += litLength * ZSTD_LITFREQ_ADD;
-	for (u = 0; u < litLength; u++)
-		seqStorePtr->litFreq[literals[u]] += ZSTD_LITFREQ_ADD;
-
-	/* literal Length */
-	{
-		const BYTE LL_deltaCode = 19;
-		const BYTE llCode = (litLength > 63) ? (BYTE)ZSTD_highbit32(litLength) + LL_deltaCode : LL_Code[litLength];
-		seqStorePtr->litLengthFreq[llCode]++;
-		seqStorePtr->litLengthSum++;
-	}
-
-	/* match offset */
-	{
-		BYTE const offCode = (BYTE)ZSTD_highbit32(offset + 1);
-		seqStorePtr->offCodeSum++;
-		seqStorePtr->offCodeFreq[offCode]++;
-	}
-
-	/* match Length */
-	{
-		const BYTE ML_deltaCode = 36;
-		const BYTE mlCode = (matchLength > 127) ? (BYTE)ZSTD_highbit32(matchLength) + ML_deltaCode : ML_Code[matchLength];
-		seqStorePtr->matchLengthFreq[mlCode]++;
-		seqStorePtr->matchLengthSum++;
-	}
-
-	ZSTD_setLog2Prices(seqStorePtr);
-}
-
-#define SET_PRICE(pos, mlen_, offset_, litlen_, price_)           \
-	{                                                         \
-		while (last_pos < pos) {                          \
-			opt[last_pos + 1].price = ZSTD_MAX_PRICE; \
-			last_pos++;                               \
-		}                                                 \
-		opt[pos].mlen = mlen_;                            \
-		opt[pos].off = offset_;                           \
-		opt[pos].litlen = litlen_;                        \
-		opt[pos].price = price_;                          \
-	}
-
-/* Update hashTable3 up to ip (excluded)
-   Assumption : always within prefix (i.e. not within extDict) */
-FORCE_INLINE
-U32 ZSTD_insertAndFindFirstIndexHash3(ZSTD_CCtx *zc, const BYTE *ip)
-{
-	U32 *const hashTable3 = zc->hashTable3;
-	U32 const hashLog3 = zc->hashLog3;
-	const BYTE *const base = zc->base;
-	U32 idx = zc->nextToUpdate3;
-	const U32 target = zc->nextToUpdate3 = (U32)(ip - base);
-	const size_t hash3 = ZSTD_hash3Ptr(ip, hashLog3);
-
-	while (idx < target) {
-		hashTable3[ZSTD_hash3Ptr(base + idx, hashLog3)] = idx;
-		idx++;
-	}
-
-	return hashTable3[hash3];
-}
-
-/*-*************************************
-*  Binary Tree search
-***************************************/
-static U32 ZSTD_insertBtAndGetAllMatches(ZSTD_CCtx *zc, const BYTE *const ip, const BYTE *const iLimit, U32 nbCompares, const U32 mls, U32 extDict,
-					 ZSTD_match_t *matches, const U32 minMatchLen)
-{
-	const BYTE *const base = zc->base;
-	const U32 curr = (U32)(ip - base);
-	const U32 hashLog = zc->params.cParams.hashLog;
-	const size_t h = ZSTD_hashPtr(ip, hashLog, mls);
-	U32 *const hashTable = zc->hashTable;
-	U32 matchIndex = hashTable[h];
-	U32 *const bt = zc->chainTable;
-	const U32 btLog = zc->params.cParams.chainLog - 1;
-	const U32 btMask = (1U << btLog) - 1;
-	size_t commonLengthSmaller = 0, commonLengthLarger = 0;
-	const BYTE *const dictBase = zc->dictBase;
-	const U32 dictLimit = zc->dictLimit;
-	const BYTE *const dictEnd = dictBase + dictLimit;
-	const BYTE *const prefixStart = base + dictLimit;
-	const U32 btLow = btMask >= curr ? 0 : curr - btMask;
-	const U32 windowLow = zc->lowLimit;
-	U32 *smallerPtr = bt + 2 * (curr & btMask);
-	U32 *largerPtr = bt + 2 * (curr & btMask) + 1;
-	U32 matchEndIdx = curr + 8;
-	U32 dummy32; /* to be nullified at the end */
-	U32 mnum = 0;
-
-	const U32 minMatch = (mls == 3) ? 3 : 4;
-	size_t bestLength = minMatchLen - 1;
-
-	if (minMatch == 3) { /* HC3 match finder */
-		U32 const matchIndex3 = ZSTD_insertAndFindFirstIndexHash3(zc, ip);
-		if (matchIndex3 > windowLow && (curr - matchIndex3 < (1 << 18))) {
-			const BYTE *match;
-			size_t currMl = 0;
-			if ((!extDict) || matchIndex3 >= dictLimit) {
-				match = base + matchIndex3;
-				if (match[bestLength] == ip[bestLength])
-					currMl = ZSTD_count(ip, match, iLimit);
-			} else {
-				match = dictBase + matchIndex3;
-				if (ZSTD_readMINMATCH(match, MINMATCH) ==
-				    ZSTD_readMINMATCH(ip, MINMATCH)) /* assumption : matchIndex3 <= dictLimit-4 (by table construction) */
-					currMl = ZSTD_count_2segments(ip + MINMATCH, match + MINMATCH, iLimit, dictEnd, prefixStart) + MINMATCH;
-			}
-
-			/* save best solution */
-			if (currMl > bestLength) {
-				bestLength = currMl;
-				matches[mnum].off = ZSTD_REP_MOVE_OPT + curr - matchIndex3;
-				matches[mnum].len = (U32)currMl;
-				mnum++;
-				if (currMl > ZSTD_OPT_NUM)
-					goto update;
-				if (ip + currMl == iLimit)
-					goto update; /* best possible, and avoid read overflow*/
-			}
-		}
-	}
-
-	hashTable[h] = curr; /* Update Hash Table */
-
-	while (nbCompares-- && (matchIndex > windowLow)) {
-		U32 *nextPtr = bt + 2 * (matchIndex & btMask);
-		size_t matchLength = MIN(commonLengthSmaller, commonLengthLarger); /* guaranteed minimum nb of common bytes */
-		const BYTE *match;
-
-		if ((!extDict) || (matchIndex + matchLength >= dictLimit)) {
-			match = base + matchIndex;
-			if (match[matchLength] == ip[matchLength]) {
-				matchLength += ZSTD_count(ip + matchLength + 1, match + matchLength + 1, iLimit) + 1;
-			}
-		} else {
-			match = dictBase + matchIndex;
-			matchLength += ZSTD_count_2segments(ip + matchLength, match + matchLength, iLimit, dictEnd, prefixStart);
-			if (matchIndex + matchLength >= dictLimit)
-				match = base + matchIndex; /* to prepare for next usage of match[matchLength] */
-		}
-
-		if (matchLength > bestLength) {
-			if (matchLength > matchEndIdx - matchIndex)
-				matchEndIdx = matchIndex + (U32)matchLength;
-			bestLength = matchLength;
-			matches[mnum].off = ZSTD_REP_MOVE_OPT + curr - matchIndex;
-			matches[mnum].len = (U32)matchLength;
-			mnum++;
-			if (matchLength > ZSTD_OPT_NUM)
-				break;
-			if (ip + matchLength == iLimit) /* equal : no way to know if inf or sup */
-				break;			/* drop, to guarantee consistency (miss a little bit of compression) */
-		}
-
-		if (match[matchLength] < ip[matchLength]) {
-			/* match is smaller than curr */
-			*smallerPtr = matchIndex;	  /* update smaller idx */
-			commonLengthSmaller = matchLength; /* all smaller will now have at least this guaranteed common length */
-			if (matchIndex <= btLow) {
-				smallerPtr = &dummy32;
-				break;
-			}			  /* beyond tree size, stop the search */
-			smallerPtr = nextPtr + 1; /* new "smaller" => larger of match */
-			matchIndex = nextPtr[1];  /* new matchIndex larger than previous (closer to curr) */
-		} else {
-			/* match is larger than curr */
-			*largerPtr = matchIndex;
-			commonLengthLarger = matchLength;
-			if (matchIndex <= btLow) {
-				largerPtr = &dummy32;
-				break;
-			} /* beyond tree size, stop the search */
-			largerPtr = nextPtr;
-			matchIndex = nextPtr[0];
-		}
-	}
-
-	*smallerPtr = *largerPtr = 0;
-
-update:
-	zc->nextToUpdate = (matchEndIdx > curr + 8) ? matchEndIdx - 8 : curr + 1;
-	return mnum;
-}
-
-/** Tree updater, providing best match */
-static U32 ZSTD_BtGetAllMatches(ZSTD_CCtx *zc, const BYTE *const ip, const BYTE *const iLimit, const U32 maxNbAttempts, const U32 mls, ZSTD_match_t *matches,
-				const U32 minMatchLen)
-{
-	if (ip < zc->base + zc->nextToUpdate)
-		return 0; /* skipped area */
-	ZSTD_updateTree(zc, ip, iLimit, maxNbAttempts, mls);
-	return ZSTD_insertBtAndGetAllMatches(zc, ip, iLimit, maxNbAttempts, mls, 0, matches, minMatchLen);
-}
-
-static U32 ZSTD_BtGetAllMatches_selectMLS(ZSTD_CCtx *zc, /* Index table will be updated */
-					  const BYTE *ip, const BYTE *const iHighLimit, const U32 maxNbAttempts, const U32 matchLengthSearch,
-					  ZSTD_match_t *matches, const U32 minMatchLen)
-{
-	switch (matchLengthSearch) {
-	case 3: return ZSTD_BtGetAllMatches(zc, ip, iHighLimit, maxNbAttempts, 3, matches, minMatchLen);
-	default:
-	case 4: return ZSTD_BtGetAllMatches(zc, ip, iHighLimit, maxNbAttempts, 4, matches, minMatchLen);
-	case 5: return ZSTD_BtGetAllMatches(zc, ip, iHighLimit, maxNbAttempts, 5, matches, minMatchLen);
-	case 7:
-	case 6: return ZSTD_BtGetAllMatches(zc, ip, iHighLimit, maxNbAttempts, 6, matches, minMatchLen);
-	}
-}
-
-/** Tree updater, providing best match */
-static U32 ZSTD_BtGetAllMatches_extDict(ZSTD_CCtx *zc, const BYTE *const ip, const BYTE *const iLimit, const U32 maxNbAttempts, const U32 mls,
-					ZSTD_match_t *matches, const U32 minMatchLen)
-{
-	if (ip < zc->base + zc->nextToUpdate)
-		return 0; /* skipped area */
-	ZSTD_updateTree_extDict(zc, ip, iLimit, maxNbAttempts, mls);
-	return ZSTD_insertBtAndGetAllMatches(zc, ip, iLimit, maxNbAttempts, mls, 1, matches, minMatchLen);
-}
-
-static U32 ZSTD_BtGetAllMatches_selectMLS_extDict(ZSTD_CCtx *zc, /* Index table will be updated */
-						  const BYTE *ip, const BYTE *const iHighLimit, const U32 maxNbAttempts, const U32 matchLengthSearch,
-						  ZSTD_match_t *matches, const U32 minMatchLen)
-{
-	switch (matchLengthSearch) {
-	case 3: return ZSTD_BtGetAllMatches_extDict(zc, ip, iHighLimit, maxNbAttempts, 3, matches, minMatchLen);
-	default:
-	case 4: return ZSTD_BtGetAllMatches_extDict(zc, ip, iHighLimit, maxNbAttempts, 4, matches, minMatchLen);
-	case 5: return ZSTD_BtGetAllMatches_extDict(zc, ip, iHighLimit, maxNbAttempts, 5, matches, minMatchLen);
-	case 7:
-	case 6: return ZSTD_BtGetAllMatches_extDict(zc, ip, iHighLimit, maxNbAttempts, 6, matches, minMatchLen);
-	}
-}
-
-/*-*******************************
-*  Optimal parser
-*********************************/
-FORCE_INLINE
-void ZSTD_compressBlock_opt_generic(ZSTD_CCtx *ctx, const void *src, size_t srcSize, const int ultra)
-{
-	seqStore_t *seqStorePtr = &(ctx->seqStore);
-	const BYTE *const istart = (const BYTE *)src;
-	const BYTE *ip = istart;
-	const BYTE *anchor = istart;
-	const BYTE *const iend = istart + srcSize;
-	const BYTE *const ilimit = iend - 8;
-	const BYTE *const base = ctx->base;
-	const BYTE *const prefixStart = base + ctx->dictLimit;
-
-	const U32 maxSearches = 1U << ctx->params.cParams.searchLog;
-	const U32 sufficient_len = ctx->params.cParams.targetLength;
-	const U32 mls = ctx->params.cParams.searchLength;
-	const U32 minMatch = (ctx->params.cParams.searchLength == 3) ? 3 : 4;
-
-	ZSTD_optimal_t *opt = seqStorePtr->priceTable;
-	ZSTD_match_t *matches = seqStorePtr->matchTable;
-	const BYTE *inr;
-	U32 offset, rep[ZSTD_REP_NUM];
-
-	/* init */
-	ctx->nextToUpdate3 = ctx->nextToUpdate;
-	ZSTD_rescaleFreqs(seqStorePtr, (const BYTE *)src, srcSize);
-	ip += (ip == prefixStart);
-	{
-		U32 i;
-		for (i = 0; i < ZSTD_REP_NUM; i++)
-			rep[i] = ctx->rep[i];
-	}
-
-	/* Match Loop */
-	while (ip < ilimit) {
-		U32 cur, match_num, last_pos, litlen, price;
-		U32 u, mlen, best_mlen, best_off, litLength;
-		memset(opt, 0, sizeof(ZSTD_optimal_t));
-		last_pos = 0;
-		litlen = (U32)(ip - anchor);
-
-		/* check repCode */
-		{
-			U32 i, last_i = ZSTD_REP_CHECK + (ip == anchor);
-			for (i = (ip == anchor); i < last_i; i++) {
-				const S32 repCur = (i == ZSTD_REP_MOVE_OPT) ? (rep[0] - 1) : rep[i];
-				if ((repCur > 0) && (repCur < (S32)(ip - prefixStart)) &&
-				    (ZSTD_readMINMATCH(ip, minMatch) == ZSTD_readMINMATCH(ip - repCur, minMatch))) {
-					mlen = (U32)ZSTD_count(ip + minMatch, ip + minMatch - repCur, iend) + minMatch;
-					if (mlen > sufficient_len || mlen >= ZSTD_OPT_NUM) {
-						best_mlen = mlen;
-						best_off = i;
-						cur = 0;
-						last_pos = 1;
-						goto _storeSequence;
-					}
-					best_off = i - (ip == anchor);
-					do {
-						price = ZSTD_getPrice(seqStorePtr, litlen, anchor, best_off, mlen - MINMATCH, ultra);
-						if (mlen > last_pos || price < opt[mlen].price)
-							SET_PRICE(mlen, mlen, i, litlen, price); /* note : macro modifies last_pos */
-						mlen--;
-					} while (mlen >= minMatch);
-				}
-			}
-		}
-
-		match_num = ZSTD_BtGetAllMatches_selectMLS(ctx, ip, iend, maxSearches, mls, matches, minMatch);
-
-		if (!last_pos && !match_num) {
-			ip++;
-			continue;
-		}
-
-		if (match_num && (matches[match_num - 1].len > sufficient_len || matches[match_num - 1].len >= ZSTD_OPT_NUM)) {
-			best_mlen = matches[match_num - 1].len;
-			best_off = matches[match_num - 1].off;
-			cur = 0;
-			last_pos = 1;
-			goto _storeSequence;
-		}
-
-		/* set prices using matches at position = 0 */
-		best_mlen = (last_pos) ? last_pos : minMatch;
-		for (u = 0; u < match_num; u++) {
-			mlen = (u > 0) ? matches[u - 1].len + 1 : best_mlen;
-			best_mlen = matches[u].len;
-			while (mlen <= best_mlen) {
-				price = ZSTD_getPrice(seqStorePtr, litlen, anchor, matches[u].off - 1, mlen - MINMATCH, ultra);
-				if (mlen > last_pos || price < opt[mlen].price)
-					SET_PRICE(mlen, mlen, matches[u].off, litlen, price); /* note : macro modifies last_pos */
-				mlen++;
-			}
-		}
-
-		if (last_pos < minMatch) {
-			ip++;
-			continue;
-		}
-
-		/* initialize opt[0] */
-		{
-			U32 i;
-			for (i = 0; i < ZSTD_REP_NUM; i++)
-				opt[0].rep[i] = rep[i];
-		}
-		opt[0].mlen = 1;
-		opt[0].litlen = litlen;
-
-		/* check further positions */
-		for (cur = 1; cur <= last_pos; cur++) {
-			inr = ip + cur;
-
-			if (opt[cur - 1].mlen == 1) {
-				litlen = opt[cur - 1].litlen + 1;
-				if (cur > litlen) {
-					price = opt[cur - litlen].price + ZSTD_getLiteralPrice(seqStorePtr, litlen, inr - litlen);
-				} else
-					price = ZSTD_getLiteralPrice(seqStorePtr, litlen, anchor);
-			} else {
-				litlen = 1;
-				price = opt[cur - 1].price + ZSTD_getLiteralPrice(seqStorePtr, litlen, inr - 1);
-			}
-
-			if (cur > last_pos || price <= opt[cur].price)
-				SET_PRICE(cur, 1, 0, litlen, price);
-
-			if (cur == last_pos)
-				break;
-
-			if (inr > ilimit) /* last match must start at a minimum distance of 8 from oend */
-				continue;
-
-			mlen = opt[cur].mlen;
-			if (opt[cur].off > ZSTD_REP_MOVE_OPT) {
-				opt[cur].rep[2] = opt[cur - mlen].rep[1];
-				opt[cur].rep[1] = opt[cur - mlen].rep[0];
-				opt[cur].rep[0] = opt[cur].off - ZSTD_REP_MOVE_OPT;
-			} else {
-				opt[cur].rep[2] = (opt[cur].off > 1) ? opt[cur - mlen].rep[1] : opt[cur - mlen].rep[2];
-				opt[cur].rep[1] = (opt[cur].off > 0) ? opt[cur - mlen].rep[0] : opt[cur - mlen].rep[1];
-				opt[cur].rep[0] =
-				    ((opt[cur].off == ZSTD_REP_MOVE_OPT) && (mlen != 1)) ? (opt[cur - mlen].rep[0] - 1) : (opt[cur - mlen].rep[opt[cur].off]);
-			}
-
-			best_mlen = minMatch;
-			{
-				U32 i, last_i = ZSTD_REP_CHECK + (mlen != 1);
-				for (i = (opt[cur].mlen != 1); i < last_i; i++) { /* check rep */
-					const S32 repCur = (i == ZSTD_REP_MOVE_OPT) ? (opt[cur].rep[0] - 1) : opt[cur].rep[i];
-					if ((repCur > 0) && (repCur < (S32)(inr - prefixStart)) &&
-					    (ZSTD_readMINMATCH(inr, minMatch) == ZSTD_readMINMATCH(inr - repCur, minMatch))) {
-						mlen = (U32)ZSTD_count(inr + minMatch, inr + minMatch - repCur, iend) + minMatch;
-
-						if (mlen > sufficient_len || cur + mlen >= ZSTD_OPT_NUM) {
-							best_mlen = mlen;
-							best_off = i;
-							last_pos = cur + 1;
-							goto _storeSequence;
-						}
-
-						best_off = i - (opt[cur].mlen != 1);
-						if (mlen > best_mlen)
-							best_mlen = mlen;
-
-						do {
-							if (opt[cur].mlen == 1) {
-								litlen = opt[cur].litlen;
-								if (cur > litlen) {
-									price = opt[cur - litlen].price + ZSTD_getPrice(seqStorePtr, litlen, inr - litlen,
-															best_off, mlen - MINMATCH, ultra);
-								} else
-									price = ZSTD_getPrice(seqStorePtr, litlen, anchor, best_off, mlen - MINMATCH, ultra);
-							} else {
-								litlen = 0;
-								price = opt[cur].price + ZSTD_getPrice(seqStorePtr, 0, NULL, best_off, mlen - MINMATCH, ultra);
-							}
-
-							if (cur + mlen > last_pos || price <= opt[cur + mlen].price)
-								SET_PRICE(cur + mlen, mlen, i, litlen, price);
-							mlen--;
-						} while (mlen >= minMatch);
-					}
-				}
-			}
-
-			match_num = ZSTD_BtGetAllMatches_selectMLS(ctx, inr, iend, maxSearches, mls, matches, best_mlen);
-
-			if (match_num > 0 && (matches[match_num - 1].len > sufficient_len || cur + matches[match_num - 1].len >= ZSTD_OPT_NUM)) {
-				best_mlen = matches[match_num - 1].len;
-				best_off = matches[match_num - 1].off;
-				last_pos = cur + 1;
-				goto _storeSequence;
-			}
-
-			/* set prices using matches at position = cur */
-			for (u = 0; u < match_num; u++) {
-				mlen = (u > 0) ? matches[u - 1].len + 1 : best_mlen;
-				best_mlen = matches[u].len;
-
-				while (mlen <= best_mlen) {
-					if (opt[cur].mlen == 1) {
-						litlen = opt[cur].litlen;
-						if (cur > litlen)
-							price = opt[cur - litlen].price + ZSTD_getPrice(seqStorePtr, litlen, ip + cur - litlen,
-													matches[u].off - 1, mlen - MINMATCH, ultra);
-						else
-							price = ZSTD_getPrice(seqStorePtr, litlen, anchor, matches[u].off - 1, mlen - MINMATCH, ultra);
-					} else {
-						litlen = 0;
-						price = opt[cur].price + ZSTD_getPrice(seqStorePtr, 0, NULL, matches[u].off - 1, mlen - MINMATCH, ultra);
-					}
-
-					if (cur + mlen > last_pos || (price < opt[cur + mlen].price))
-						SET_PRICE(cur + mlen, mlen, matches[u].off, litlen, price);
-
-					mlen++;
-				}
-			}
-		}
-
-		best_mlen = opt[last_pos].mlen;
-		best_off = opt[last_pos].off;
-		cur = last_pos - best_mlen;
-
-	/* store sequence */
-_storeSequence: /* cur, last_pos, best_mlen, best_off have to be set */
-		opt[0].mlen = 1;
-
-		while (1) {
-			mlen = opt[cur].mlen;
-			offset = opt[cur].off;
-			opt[cur].mlen = best_mlen;
-			opt[cur].off = best_off;
-			best_mlen = mlen;
-			best_off = offset;
-			if (mlen > cur)
-				break;
-			cur -= mlen;
-		}
-
-		for (u = 0; u <= last_pos;) {
-			u += opt[u].mlen;
-		}
-
-		for (cur = 0; cur < last_pos;) {
-			mlen = opt[cur].mlen;
-			if (mlen == 1) {
-				ip++;
-				cur++;
-				continue;
-			}
-			offset = opt[cur].off;
-			cur += mlen;
-			litLength = (U32)(ip - anchor);
-
-			if (offset > ZSTD_REP_MOVE_OPT) {
-				rep[2] = rep[1];
-				rep[1] = rep[0];
-				rep[0] = offset - ZSTD_REP_MOVE_OPT;
-				offset--;
-			} else {
-				if (offset != 0) {
-					best_off = (offset == ZSTD_REP_MOVE_OPT) ? (rep[0] - 1) : (rep[offset]);
-					if (offset != 1)
-						rep[2] = rep[1];
-					rep[1] = rep[0];
-					rep[0] = best_off;
-				}
-				if (litLength == 0)
-					offset--;
-			}
-
-			ZSTD_updatePrice(seqStorePtr, litLength, anchor, offset, mlen - MINMATCH);
-			ZSTD_storeSeq(seqStorePtr, litLength, anchor, offset, mlen - MINMATCH);
-			anchor = ip = ip + mlen;
-		}
-	} /* for (cur=0; cur < last_pos; ) */
-
-	/* Save reps for next block */
-	{
-		int i;
-		for (i = 0; i < ZSTD_REP_NUM; i++)
-			ctx->repToConfirm[i] = rep[i];
-	}
-
-	/* Last Literals */
-	{
-		size_t const lastLLSize = iend - anchor;
-		memcpy(seqStorePtr->lit, anchor, lastLLSize);
-		seqStorePtr->lit += lastLLSize;
-	}
-}
-
-FORCE_INLINE
-void ZSTD_compressBlock_opt_extDict_generic(ZSTD_CCtx *ctx, const void *src, size_t srcSize, const int ultra)
-{
-	seqStore_t *seqStorePtr = &(ctx->seqStore);
-	const BYTE *const istart = (const BYTE *)src;
-	const BYTE *ip = istart;
-	const BYTE *anchor = istart;
-	const BYTE *const iend = istart + srcSize;
-	const BYTE *const ilimit = iend - 8;
-	const BYTE *const base = ctx->base;
-	const U32 lowestIndex = ctx->lowLimit;
-	const U32 dictLimit = ctx->dictLimit;
-	const BYTE *const prefixStart = base + dictLimit;
-	const BYTE *const dictBase = ctx->dictBase;
-	const BYTE *const dictEnd = dictBase + dictLimit;
-
-	const U32 maxSearches = 1U << ctx->params.cParams.searchLog;
-	const U32 sufficient_len = ctx->params.cParams.targetLength;
-	const U32 mls = ctx->params.cParams.searchLength;
-	const U32 minMatch = (ctx->params.cParams.searchLength == 3) ? 3 : 4;
-
-	ZSTD_optimal_t *opt = seqStorePtr->priceTable;
-	ZSTD_match_t *matches = seqStorePtr->matchTable;
-	const BYTE *inr;
-
-	/* init */
-	U32 offset, rep[ZSTD_REP_NUM];
-	{
-		U32 i;
-		for (i = 0; i < ZSTD_REP_NUM; i++)
-			rep[i] = ctx->rep[i];
-	}
-
-	ctx->nextToUpdate3 = ctx->nextToUpdate;
-	ZSTD_rescaleFreqs(seqStorePtr, (const BYTE *)src, srcSize);
-	ip += (ip == prefixStart);
-
-	/* Match Loop */
-	while (ip < ilimit) {
-		U32 cur, match_num, last_pos, litlen, price;
-		U32 u, mlen, best_mlen, best_off, litLength;
-		U32 curr = (U32)(ip - base);
-		memset(opt, 0, sizeof(ZSTD_optimal_t));
-		last_pos = 0;
-		opt[0].litlen = (U32)(ip - anchor);
-
-		/* check repCode */
-		{
-			U32 i, last_i = ZSTD_REP_CHECK + (ip == anchor);
-			for (i = (ip == anchor); i < last_i; i++) {
-				const S32 repCur = (i == ZSTD_REP_MOVE_OPT) ? (rep[0] - 1) : rep[i];
-				const U32 repIndex = (U32)(curr - repCur);
-				const BYTE *const repBase = repIndex < dictLimit ? dictBase : base;
-				const BYTE *const repMatch = repBase + repIndex;
-				if ((repCur > 0 && repCur <= (S32)curr) &&
-				    (((U32)((dictLimit - 1) - repIndex) >= 3) & (repIndex > lowestIndex)) /* intentional overflow */
-				    && (ZSTD_readMINMATCH(ip, minMatch) == ZSTD_readMINMATCH(repMatch, minMatch))) {
-					/* repcode detected we should take it */
-					const BYTE *const repEnd = repIndex < dictLimit ? dictEnd : iend;
-					mlen = (U32)ZSTD_count_2segments(ip + minMatch, repMatch + minMatch, iend, repEnd, prefixStart) + minMatch;
-
-					if (mlen > sufficient_len || mlen >= ZSTD_OPT_NUM) {
-						best_mlen = mlen;
-						best_off = i;
-						cur = 0;
-						last_pos = 1;
-						goto _storeSequence;
-					}
-
-					best_off = i - (ip == anchor);
-					litlen = opt[0].litlen;
-					do {
-						price = ZSTD_getPrice(seqStorePtr, litlen, anchor, best_off, mlen - MINMATCH, ultra);
-						if (mlen > last_pos || price < opt[mlen].price)
-							SET_PRICE(mlen, mlen, i, litlen, price); /* note : macro modifies last_pos */
-						mlen--;
-					} while (mlen >= minMatch);
-				}
-			}
-		}
-
-		match_num = ZSTD_BtGetAllMatches_selectMLS_extDict(ctx, ip, iend, maxSearches, mls, matches, minMatch); /* first search (depth 0) */
-
-		if (!last_pos && !match_num) {
-			ip++;
-			continue;
-		}
-
-		{
-			U32 i;
-			for (i = 0; i < ZSTD_REP_NUM; i++)
-				opt[0].rep[i] = rep[i];
-		}
-		opt[0].mlen = 1;
-
-		if (match_num && (matches[match_num - 1].len > sufficient_len || matches[match_num - 1].len >= ZSTD_OPT_NUM)) {
-			best_mlen = matches[match_num - 1].len;
-			best_off = matches[match_num - 1].off;
-			cur = 0;
-			last_pos = 1;
-			goto _storeSequence;
-		}
-
-		best_mlen = (last_pos) ? last_pos : minMatch;
-
-		/* set prices using matches at position = 0 */
-		for (u = 0; u < match_num; u++) {
-			mlen = (u > 0) ? matches[u - 1].len + 1 : best_mlen;
-			best_mlen = matches[u].len;
-			litlen = opt[0].litlen;
-			while (mlen <= best_mlen) {
-				price = ZSTD_getPrice(seqStorePtr, litlen, anchor, matches[u].off - 1, mlen - MINMATCH, ultra);
-				if (mlen > last_pos || price < opt[mlen].price)
-					SET_PRICE(mlen, mlen, matches[u].off, litlen, price);
-				mlen++;
-			}
-		}
-
-		if (last_pos < minMatch) {
-			ip++;
-			continue;
-		}
-
-		/* check further positions */
-		for (cur = 1; cur <= last_pos; cur++) {
-			inr = ip + cur;
-
-			if (opt[cur - 1].mlen == 1) {
-				litlen = opt[cur - 1].litlen + 1;
-				if (cur > litlen) {
-					price = opt[cur - litlen].price + ZSTD_getLiteralPrice(seqStorePtr, litlen, inr - litlen);
-				} else
-					price = ZSTD_getLiteralPrice(seqStorePtr, litlen, anchor);
-			} else {
-				litlen = 1;
-				price = opt[cur - 1].price + ZSTD_getLiteralPrice(seqStorePtr, litlen, inr - 1);
-			}
-
-			if (cur > last_pos || price <= opt[cur].price)
-				SET_PRICE(cur, 1, 0, litlen, price);
-
-			if (cur == last_pos)
-				break;
-
-			if (inr > ilimit) /* last match must start at a minimum distance of 8 from oend */
-				continue;
-
-			mlen = opt[cur].mlen;
-			if (opt[cur].off > ZSTD_REP_MOVE_OPT) {
-				opt[cur].rep[2] = opt[cur - mlen].rep[1];
-				opt[cur].rep[1] = opt[cur - mlen].rep[0];
-				opt[cur].rep[0] = opt[cur].off - ZSTD_REP_MOVE_OPT;
-			} else {
-				opt[cur].rep[2] = (opt[cur].off > 1) ? opt[cur - mlen].rep[1] : opt[cur - mlen].rep[2];
-				opt[cur].rep[1] = (opt[cur].off > 0) ? opt[cur - mlen].rep[0] : opt[cur - mlen].rep[1];
-				opt[cur].rep[0] =
-				    ((opt[cur].off == ZSTD_REP_MOVE_OPT) && (mlen != 1)) ? (opt[cur - mlen].rep[0] - 1) : (opt[cur - mlen].rep[opt[cur].off]);
-			}
-
-			best_mlen = minMatch;
-			{
-				U32 i, last_i = ZSTD_REP_CHECK + (mlen != 1);
-				for (i = (mlen != 1); i < last_i; i++) {
-					const S32 repCur = (i == ZSTD_REP_MOVE_OPT) ? (opt[cur].rep[0] - 1) : opt[cur].rep[i];
-					const U32 repIndex = (U32)(curr + cur - repCur);
-					const BYTE *const repBase = repIndex < dictLimit ? dictBase : base;
-					const BYTE *const repMatch = repBase + repIndex;
-					if ((repCur > 0 && repCur <= (S32)(curr + cur)) &&
-					    (((U32)((dictLimit - 1) - repIndex) >= 3) & (repIndex > lowestIndex)) /* intentional overflow */
-					    && (ZSTD_readMINMATCH(inr, minMatch) == ZSTD_readMINMATCH(repMatch, minMatch))) {
-						/* repcode detected */
-						const BYTE *const repEnd = repIndex < dictLimit ? dictEnd : iend;
-						mlen = (U32)ZSTD_count_2segments(inr + minMatch, repMatch + minMatch, iend, repEnd, prefixStart) + minMatch;
-
-						if (mlen > sufficient_len || cur + mlen >= ZSTD_OPT_NUM) {
-							best_mlen = mlen;
-							best_off = i;
-							last_pos = cur + 1;
-							goto _storeSequence;
-						}
-
-						best_off = i - (opt[cur].mlen != 1);
-						if (mlen > best_mlen)
-							best_mlen = mlen;
-
-						do {
-							if (opt[cur].mlen == 1) {
-								litlen = opt[cur].litlen;
-								if (cur > litlen) {
-									price = opt[cur - litlen].price + ZSTD_getPrice(seqStorePtr, litlen, inr - litlen,
-															best_off, mlen - MINMATCH, ultra);
-								} else
-									price = ZSTD_getPrice(seqStorePtr, litlen, anchor, best_off, mlen - MINMATCH, ultra);
-							} else {
-								litlen = 0;
-								price = opt[cur].price + ZSTD_getPrice(seqStorePtr, 0, NULL, best_off, mlen - MINMATCH, ultra);
-							}
-
-							if (cur + mlen > last_pos || price <= opt[cur + mlen].price)
-								SET_PRICE(cur + mlen, mlen, i, litlen, price);
-							mlen--;
-						} while (mlen >= minMatch);
-					}
-				}
-			}
-
-			match_num = ZSTD_BtGetAllMatches_selectMLS_extDict(ctx, inr, iend, maxSearches, mls, matches, minMatch);
-
-			if (match_num > 0 && (matches[match_num - 1].len > sufficient_len || cur + matches[match_num - 1].len >= ZSTD_OPT_NUM)) {
-				best_mlen = matches[match_num - 1].len;
-				best_off = matches[match_num - 1].off;
-				last_pos = cur + 1;
-				goto _storeSequence;
-			}
-
-			/* set prices using matches at position = cur */
-			for (u = 0; u < match_num; u++) {
-				mlen = (u > 0) ? matches[u - 1].len + 1 : best_mlen;
-				best_mlen = matches[u].len;
-
-				while (mlen <= best_mlen) {
-					if (opt[cur].mlen == 1) {
-						litlen = opt[cur].litlen;
-						if (cur > litlen)
-							price = opt[cur - litlen].price + ZSTD_getPrice(seqStorePtr, litlen, ip + cur - litlen,
-													matches[u].off - 1, mlen - MINMATCH, ultra);
-						else
-							price = ZSTD_getPrice(seqStorePtr, litlen, anchor, matches[u].off - 1, mlen - MINMATCH, ultra);
-					} else {
-						litlen = 0;
-						price = opt[cur].price + ZSTD_getPrice(seqStorePtr, 0, NULL, matches[u].off - 1, mlen - MINMATCH, ultra);
-					}
-
-					if (cur + mlen > last_pos || (price < opt[cur + mlen].price))
-						SET_PRICE(cur + mlen, mlen, matches[u].off, litlen, price);
-
-					mlen++;
-				}
-			}
-		} /* for (cur = 1; cur <= last_pos; cur++) */
-
-		best_mlen = opt[last_pos].mlen;
-		best_off = opt[last_pos].off;
-		cur = last_pos - best_mlen;
-
-	/* store sequence */
-_storeSequence: /* cur, last_pos, best_mlen, best_off have to be set */
-		opt[0].mlen = 1;
-
-		while (1) {
-			mlen = opt[cur].mlen;
-			offset = opt[cur].off;
-			opt[cur].mlen = best_mlen;
-			opt[cur].off = best_off;
-			best_mlen = mlen;
-			best_off = offset;
-			if (mlen > cur)
-				break;
-			cur -= mlen;
-		}
-
-		for (u = 0; u <= last_pos;) {
-			u += opt[u].mlen;
-		}
-
-		for (cur = 0; cur < last_pos;) {
-			mlen = opt[cur].mlen;
-			if (mlen == 1) {
-				ip++;
-				cur++;
-				continue;
-			}
-			offset = opt[cur].off;
-			cur += mlen;
-			litLength = (U32)(ip - anchor);
-
-			if (offset > ZSTD_REP_MOVE_OPT) {
-				rep[2] = rep[1];
-				rep[1] = rep[0];
-				rep[0] = offset - ZSTD_REP_MOVE_OPT;
-				offset--;
-			} else {
-				if (offset != 0) {
-					best_off = (offset == ZSTD_REP_MOVE_OPT) ? (rep[0] - 1) : (rep[offset]);
-					if (offset != 1)
-						rep[2] = rep[1];
-					rep[1] = rep[0];
-					rep[0] = best_off;
-				}
-
-				if (litLength == 0)
-					offset--;
-			}
-
-			ZSTD_updatePrice(seqStorePtr, litLength, anchor, offset, mlen - MINMATCH);
-			ZSTD_storeSeq(seqStorePtr, litLength, anchor, offset, mlen - MINMATCH);
-			anchor = ip = ip + mlen;
-		}
-	} /* for (cur=0; cur < last_pos; ) */
-
-	/* Save reps for next block */
-	{
-		int i;
-		for (i = 0; i < ZSTD_REP_NUM; i++)
-			ctx->repToConfirm[i] = rep[i];
-	}
-
-	/* Last Literals */
-	{
-		size_t lastLLSize = iend - anchor;
-		memcpy(seqStorePtr->lit, anchor, lastLLSize);
-		seqStorePtr->lit += lastLLSize;
-	}
-}
-
-#endif /* ZSTD_OPT_H_91842398743 */
diff --git a/mm/Kconfig b/mm/Kconfig
index 068ce591a13a..356f4f2c779e 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -428,7 +428,7 @@ config THP_SWAP
 # UP and nommu archs use km based percpu allocator
 #
 config NEED_PER_CPU_KM
-	depends on !SMP
+	depends on !SMP || !MMU
 	bool
 	default y
 
@@ -890,6 +890,9 @@ config MAPPING_DIRTY_HELPERS
 config KMAP_LOCAL
 	bool
 
+config KMAP_LOCAL_NON_LINEAR_PTE_ARRAY
+	bool
+
 # struct io_mapping based helper.  Selected by drivers that need them
 config IO_MAPPING
 	bool
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 1eead4761011..eae96dfe0261 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -945,6 +945,13 @@ void bdi_unregister(struct backing_dev_info *bdi)
 	wb_shutdown(&bdi->wb);
 	cgwb_bdi_unregister(bdi);
 
+	/*
+	 * If this BDI's min ratio has been set, use bdi_set_min_ratio() to
+	 * update the global bdi_min_ratio.
+	 */
+	if (bdi->min_ratio)
+		bdi_set_min_ratio(bdi, 0);
+
 	if (bdi->dev) {
 		bdi_debug_unregister(bdi);
 		device_unregister(bdi->dev);
diff --git a/mm/damon/core.c b/mm/damon/core.c
index c381b3c525d0..e92497895202 100644
--- a/mm/damon/core.c
+++ b/mm/damon/core.c
@@ -282,7 +282,6 @@ int damon_set_targets(struct damon_ctx *ctx,
 	for (i = 0; i < nr_ids; i++) {
 		t = damon_new_target(ids[i]);
 		if (!t) {
-			pr_err("Failed to alloc damon_target\n");
 			/* The caller should do cleanup of the ids itself */
 			damon_for_each_target_safe(t, next, ctx)
 				damon_destroy_target(t);
@@ -312,16 +311,10 @@ int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int,
 		    unsigned long aggr_int, unsigned long primitive_upd_int,
 		    unsigned long min_nr_reg, unsigned long max_nr_reg)
 {
-	if (min_nr_reg < 3) {
-		pr_err("min_nr_regions (%lu) must be at least 3\n",
-				min_nr_reg);
+	if (min_nr_reg < 3)
 		return -EINVAL;
-	}
-	if (min_nr_reg > max_nr_reg) {
-		pr_err("invalid nr_regions.  min (%lu) > max (%lu)\n",
-				min_nr_reg, max_nr_reg);
+	if (min_nr_reg > max_nr_reg)
 		return -EINVAL;
-	}
 
 	ctx->sample_interval = sample_int;
 	ctx->aggr_interval = aggr_int;
@@ -980,10 +973,11 @@ static unsigned long damos_wmark_wait_us(struct damos *scheme)
 
 static void kdamond_usleep(unsigned long usecs)
 {
-	if (usecs > 100 * 1000)
-		schedule_timeout_interruptible(usecs_to_jiffies(usecs));
+	/* See Documentation/timers/timers-howto.rst for the thresholds */
+	if (usecs > 20 * USEC_PER_MSEC)
+		schedule_timeout_idle(usecs_to_jiffies(usecs));
 	else
-		usleep_range(usecs, usecs + 1);
+		usleep_idle_range(usecs, usecs + 1);
 }
 
 /* Returns negative error code if it's not activated but should return */
@@ -1038,7 +1032,7 @@ static int kdamond_fn(void *data)
 				ctx->callback.after_sampling(ctx))
 			done = true;
 
-		usleep_range(ctx->sample_interval, ctx->sample_interval + 1);
+		kdamond_usleep(ctx->sample_interval);
 
 		if (ctx->primitive.check_accesses)
 			max_nr_accesses = ctx->primitive.check_accesses(ctx);
diff --git a/mm/damon/dbgfs.c b/mm/damon/dbgfs.c
index eccc14b34901..4fbd729edc9e 100644
--- a/mm/damon/dbgfs.c
+++ b/mm/damon/dbgfs.c
@@ -32,7 +32,7 @@ static char *user_input_str(const char __user *buf, size_t count, loff_t *ppos)
 	if (*ppos)
 		return ERR_PTR(-EINVAL);
 
-	kbuf = kmalloc(count + 1, GFP_KERNEL);
+	kbuf = kmalloc(count + 1, GFP_KERNEL | __GFP_NOWARN);
 	if (!kbuf)
 		return ERR_PTR(-ENOMEM);
 
@@ -133,7 +133,7 @@ static ssize_t dbgfs_schemes_read(struct file *file, char __user *buf,
 	char *kbuf;
 	ssize_t len;
 
-	kbuf = kmalloc(count, GFP_KERNEL);
+	kbuf = kmalloc(count, GFP_KERNEL | __GFP_NOWARN);
 	if (!kbuf)
 		return -ENOMEM;
 
@@ -210,10 +210,8 @@ static struct damos **str_to_schemes(const char *str, ssize_t len,
 				&wmarks.low, &parsed);
 		if (ret != 18)
 			break;
-		if (!damos_action_valid(action)) {
-			pr_err("wrong action %d\n", action);
+		if (!damos_action_valid(action))
 			goto fail;
-		}
 
 		pos += parsed;
 		scheme = damon_new_scheme(min_sz, max_sz, min_nr_a, max_nr_a,
@@ -452,7 +450,7 @@ static ssize_t dbgfs_init_regions_read(struct file *file, char __user *buf,
 	char *kbuf;
 	ssize_t len;
 
-	kbuf = kmalloc(count, GFP_KERNEL);
+	kbuf = kmalloc(count, GFP_KERNEL | __GFP_NOWARN);
 	if (!kbuf)
 		return -ENOMEM;
 
@@ -578,7 +576,7 @@ static ssize_t dbgfs_kdamond_pid_read(struct file *file,
 	char *kbuf;
 	ssize_t len;
 
-	kbuf = kmalloc(count, GFP_KERNEL);
+	kbuf = kmalloc(count, GFP_KERNEL | __GFP_NOWARN);
 	if (!kbuf)
 		return -ENOMEM;
 
@@ -652,10 +650,12 @@ static void dbgfs_before_terminate(struct damon_ctx *ctx)
 	if (!targetid_is_pid(ctx))
 		return;
 
+	mutex_lock(&ctx->kdamond_lock);
 	damon_for_each_target_safe(t, next, ctx) {
 		put_pid((struct pid *)t->id);
 		damon_destroy_target(t);
 	}
+	mutex_unlock(&ctx->kdamond_lock);
 }
 
 static struct damon_ctx *dbgfs_new_ctx(void)
@@ -877,12 +877,14 @@ static ssize_t dbgfs_monitor_on_write(struct file *file,
 		return -EINVAL;
 	}
 
+	mutex_lock(&damon_dbgfs_lock);
 	if (!strncmp(kbuf, "on", count)) {
 		int i;
 
 		for (i = 0; i < dbgfs_nr_ctxs; i++) {
 			if (damon_targets_empty(dbgfs_ctxs[i])) {
 				kfree(kbuf);
+				mutex_unlock(&damon_dbgfs_lock);
 				return -EINVAL;
 			}
 		}
@@ -892,6 +894,7 @@ static ssize_t dbgfs_monitor_on_write(struct file *file,
 	} else {
 		ret = -EINVAL;
 	}
+	mutex_unlock(&damon_dbgfs_lock);
 
 	if (!ret)
 		ret = count;
@@ -944,15 +947,16 @@ static int __init __damon_dbgfs_init(void)
 
 static int __init damon_dbgfs_init(void)
 {
-	int rc;
+	int rc = -ENOMEM;
 
+	mutex_lock(&damon_dbgfs_lock);
 	dbgfs_ctxs = kmalloc(sizeof(*dbgfs_ctxs), GFP_KERNEL);
 	if (!dbgfs_ctxs)
-		return -ENOMEM;
+		goto out;
 	dbgfs_ctxs[0] = dbgfs_new_ctx();
 	if (!dbgfs_ctxs[0]) {
 		kfree(dbgfs_ctxs);
-		return -ENOMEM;
+		goto out;
 	}
 	dbgfs_nr_ctxs = 1;
 
@@ -963,6 +967,8 @@ static int __init damon_dbgfs_init(void)
 		pr_err("%s: dbgfs init failed\n", __func__);
 	}
 
+out:
+	mutex_unlock(&damon_dbgfs_lock);
 	return rc;
 }
 
diff --git a/mm/damon/vaddr-test.h b/mm/damon/vaddr-test.h
index ecfd0b2ed222..6a1b9272ea12 100644
--- a/mm/damon/vaddr-test.h
+++ b/mm/damon/vaddr-test.h
@@ -135,7 +135,6 @@ static void damon_do_test_apply_three_regions(struct kunit *test,
 				struct damon_addr_range *three_regions,
 				unsigned long *expected, int nr_expected)
 {
-	struct damon_ctx *ctx = damon_new_ctx();
 	struct damon_target *t;
 	struct damon_region *r;
 	int i;
@@ -145,7 +144,6 @@ static void damon_do_test_apply_three_regions(struct kunit *test,
 		r = damon_new_region(regions[i * 2], regions[i * 2 + 1]);
 		damon_add_region(r, t);
 	}
-	damon_add_target(ctx, t);
 
 	damon_va_apply_three_regions(t, three_regions);
 
@@ -154,8 +152,6 @@ static void damon_do_test_apply_three_regions(struct kunit *test,
 		KUNIT_EXPECT_EQ(test, r->ar.start, expected[i * 2]);
 		KUNIT_EXPECT_EQ(test, r->ar.end, expected[i * 2 + 1]);
 	}
-
-	damon_destroy_ctx(ctx);
 }
 
 /*
@@ -252,60 +248,59 @@ static void damon_test_apply_three_regions4(struct kunit *test)
 			new_three_regions, expected, ARRAY_SIZE(expected));
 }
 
-static void damon_test_split_evenly(struct kunit *test)
+static void damon_test_split_evenly_fail(struct kunit *test,
+		unsigned long start, unsigned long end, unsigned int nr_pieces)
 {
-	struct damon_ctx *c = damon_new_ctx();
-	struct damon_target *t;
-	struct damon_region *r;
-	unsigned long i;
-
-	KUNIT_EXPECT_EQ(test, damon_va_evenly_split_region(NULL, NULL, 5),
-			-EINVAL);
-
-	t = damon_new_target(42);
-	r = damon_new_region(0, 100);
-	KUNIT_EXPECT_EQ(test, damon_va_evenly_split_region(t, r, 0), -EINVAL);
+	struct damon_target *t = damon_new_target(42);
+	struct damon_region *r = damon_new_region(start, end);
 
 	damon_add_region(r, t);
-	KUNIT_EXPECT_EQ(test, damon_va_evenly_split_region(t, r, 10), 0);
-	KUNIT_EXPECT_EQ(test, damon_nr_regions(t), 10u);
+	KUNIT_EXPECT_EQ(test,
+			damon_va_evenly_split_region(t, r, nr_pieces), -EINVAL);
+	KUNIT_EXPECT_EQ(test, damon_nr_regions(t), 1u);
 
-	i = 0;
 	damon_for_each_region(r, t) {
-		KUNIT_EXPECT_EQ(test, r->ar.start, i++ * 10);
-		KUNIT_EXPECT_EQ(test, r->ar.end, i * 10);
+		KUNIT_EXPECT_EQ(test, r->ar.start, start);
+		KUNIT_EXPECT_EQ(test, r->ar.end, end);
 	}
+
 	damon_free_target(t);
+}
+
+static void damon_test_split_evenly_succ(struct kunit *test,
+	unsigned long start, unsigned long end, unsigned int nr_pieces)
+{
+	struct damon_target *t = damon_new_target(42);
+	struct damon_region *r = damon_new_region(start, end);
+	unsigned long expected_width = (end - start) / nr_pieces;
+	unsigned long i = 0;
 
-	t = damon_new_target(42);
-	r = damon_new_region(5, 59);
 	damon_add_region(r, t);
-	KUNIT_EXPECT_EQ(test, damon_va_evenly_split_region(t, r, 5), 0);
-	KUNIT_EXPECT_EQ(test, damon_nr_regions(t), 5u);
+	KUNIT_EXPECT_EQ(test,
+			damon_va_evenly_split_region(t, r, nr_pieces), 0);
+	KUNIT_EXPECT_EQ(test, damon_nr_regions(t), nr_pieces);
 
-	i = 0;
 	damon_for_each_region(r, t) {
-		if (i == 4)
+		if (i == nr_pieces - 1)
 			break;
-		KUNIT_EXPECT_EQ(test, r->ar.start, 5 + 10 * i++);
-		KUNIT_EXPECT_EQ(test, r->ar.end, 5 + 10 * i);
+		KUNIT_EXPECT_EQ(test,
+				r->ar.start, start + i++ * expected_width);
+		KUNIT_EXPECT_EQ(test, r->ar.end, start + i * expected_width);
 	}
-	KUNIT_EXPECT_EQ(test, r->ar.start, 5 + 10 * i);
-	KUNIT_EXPECT_EQ(test, r->ar.end, 59ul);
+	KUNIT_EXPECT_EQ(test, r->ar.start, start + i * expected_width);
+	KUNIT_EXPECT_EQ(test, r->ar.end, end);
 	damon_free_target(t);
+}
 
-	t = damon_new_target(42);
-	r = damon_new_region(5, 6);
-	damon_add_region(r, t);
-	KUNIT_EXPECT_EQ(test, damon_va_evenly_split_region(t, r, 2), -EINVAL);
-	KUNIT_EXPECT_EQ(test, damon_nr_regions(t), 1u);
+static void damon_test_split_evenly(struct kunit *test)
+{
+	KUNIT_EXPECT_EQ(test, damon_va_evenly_split_region(NULL, NULL, 5),
+			-EINVAL);
 
-	damon_for_each_region(r, t) {
-		KUNIT_EXPECT_EQ(test, r->ar.start, 5ul);
-		KUNIT_EXPECT_EQ(test, r->ar.end, 6ul);
-	}
-	damon_free_target(t);
-	damon_destroy_ctx(c);
+	damon_test_split_evenly_fail(test, 0, 100, 0);
+	damon_test_split_evenly_succ(test, 0, 100, 10);
+	damon_test_split_evenly_succ(test, 5, 59, 5);
+	damon_test_split_evenly_fail(test, 5, 6, 2);
 }
 
 static struct kunit_case damon_test_cases[] = {
diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c
index 35fe49080ee9..20a9a9d69eb1 100644
--- a/mm/damon/vaddr.c
+++ b/mm/damon/vaddr.c
@@ -13,6 +13,7 @@
 #include <linux/mmu_notifier.h>
 #include <linux/page_idle.h>
 #include <linux/pagewalk.h>
+#include <linux/sched/mm.h>
 
 #include "prmtv-common.h"
 
@@ -626,7 +627,6 @@ int damon_va_apply_scheme(struct damon_ctx *ctx, struct damon_target *t,
 	case DAMOS_STAT:
 		return 0;
 	default:
-		pr_warn("Wrong action %d\n", scheme->action);
 		return -EINVAL;
 	}
 
diff --git a/mm/filemap.c b/mm/filemap.c
index daa0e23a6ee6..39c4c46c6133 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -3253,8 +3253,6 @@ static struct page *next_uptodate_page(struct page *page,
 			goto skip;
 		if (!PageUptodate(page) || PageReadahead(page))
 			goto skip;
-		if (PageHWPoison(page))
-			goto skip;
 		if (!trylock_page(page))
 			goto skip;
 		if (page->mapping != mapping)
diff --git a/mm/highmem.c b/mm/highmem.c
index 88f65f155845..762679050c9a 100644
--- a/mm/highmem.c
+++ b/mm/highmem.c
@@ -359,7 +359,6 @@ void kunmap_high(struct page *page)
 }
 EXPORT_SYMBOL(kunmap_high);
 
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
 void zero_user_segments(struct page *page, unsigned start1, unsigned end1,
 		unsigned start2, unsigned end2)
 {
@@ -416,7 +415,6 @@ void zero_user_segments(struct page *page, unsigned start1, unsigned end1,
 	BUG_ON((start1 | start2 | end1 | end2) != 0);
 }
 EXPORT_SYMBOL(zero_user_segments);
-#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 #endif /* CONFIG_HIGHMEM */
 
 #ifdef CONFIG_KMAP_LOCAL
@@ -503,16 +501,22 @@ static inline int kmap_local_calc_idx(int idx)
 
 static pte_t *__kmap_pte;
 
-static pte_t *kmap_get_pte(void)
+static pte_t *kmap_get_pte(unsigned long vaddr, int idx)
 {
+	if (IS_ENABLED(CONFIG_KMAP_LOCAL_NON_LINEAR_PTE_ARRAY))
+		/*
+		 * Set by the arch if __kmap_pte[-idx] does not produce
+		 * the correct entry.
+		 */
+		return virt_to_kpte(vaddr);
 	if (!__kmap_pte)
 		__kmap_pte = virt_to_kpte(__fix_to_virt(FIX_KMAP_BEGIN));
-	return __kmap_pte;
+	return &__kmap_pte[-idx];
 }
 
 void *__kmap_local_pfn_prot(unsigned long pfn, pgprot_t prot)
 {
-	pte_t pteval, *kmap_pte = kmap_get_pte();
+	pte_t pteval, *kmap_pte;
 	unsigned long vaddr;
 	int idx;
 
@@ -524,9 +528,10 @@ void *__kmap_local_pfn_prot(unsigned long pfn, pgprot_t prot)
 	preempt_disable();
 	idx = arch_kmap_local_map_idx(kmap_local_idx_push(), pfn);
 	vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
-	BUG_ON(!pte_none(*(kmap_pte - idx)));
+	kmap_pte = kmap_get_pte(vaddr, idx);
+	BUG_ON(!pte_none(*kmap_pte));
 	pteval = pfn_pte(pfn, prot);
-	arch_kmap_local_set_pte(&init_mm, vaddr, kmap_pte - idx, pteval);
+	arch_kmap_local_set_pte(&init_mm, vaddr, kmap_pte, pteval);
 	arch_kmap_local_post_map(vaddr, pteval);
 	current->kmap_ctrl.pteval[kmap_local_idx()] = pteval;
 	preempt_enable();
@@ -559,7 +564,7 @@ EXPORT_SYMBOL(__kmap_local_page_prot);
 void kunmap_local_indexed(void *vaddr)
 {
 	unsigned long addr = (unsigned long) vaddr & PAGE_MASK;
-	pte_t *kmap_pte = kmap_get_pte();
+	pte_t *kmap_pte;
 	int idx;
 
 	if (addr < __fix_to_virt(FIX_KMAP_END) ||
@@ -584,8 +589,9 @@ void kunmap_local_indexed(void *vaddr)
 	idx = arch_kmap_local_unmap_idx(kmap_local_idx(), addr);
 	WARN_ON_ONCE(addr != __fix_to_virt(FIX_KMAP_BEGIN + idx));
 
+	kmap_pte = kmap_get_pte(addr, idx);
 	arch_kmap_local_pre_unmap(addr);
-	pte_clear(&init_mm, addr, kmap_pte - idx);
+	pte_clear(&init_mm, addr, kmap_pte);
 	arch_kmap_local_post_unmap(addr);
 	current->kmap_ctrl.pteval[kmap_local_idx()] = __pte(0);
 	kmap_local_idx_pop();
@@ -607,7 +613,7 @@ EXPORT_SYMBOL(kunmap_local_indexed);
 void __kmap_local_sched_out(void)
 {
 	struct task_struct *tsk = current;
-	pte_t *kmap_pte = kmap_get_pte();
+	pte_t *kmap_pte;
 	int i;
 
 	/* Clear kmaps */
@@ -634,8 +640,9 @@ void __kmap_local_sched_out(void)
 		idx = arch_kmap_local_map_idx(i, pte_pfn(pteval));
 
 		addr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
+		kmap_pte = kmap_get_pte(addr, idx);
 		arch_kmap_local_pre_unmap(addr);
-		pte_clear(&init_mm, addr, kmap_pte - idx);
+		pte_clear(&init_mm, addr, kmap_pte);
 		arch_kmap_local_post_unmap(addr);
 	}
 }
@@ -643,7 +650,7 @@ void __kmap_local_sched_out(void)
 void __kmap_local_sched_in(void)
 {
 	struct task_struct *tsk = current;
-	pte_t *kmap_pte = kmap_get_pte();
+	pte_t *kmap_pte;
 	int i;
 
 	/* Restore kmaps */
@@ -663,7 +670,8 @@ void __kmap_local_sched_in(void)
 		/* See comment in __kmap_local_sched_out() */
 		idx = arch_kmap_local_map_idx(i, pte_pfn(pteval));
 		addr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
-		set_pte_at(&init_mm, addr, kmap_pte - idx, pteval);
+		kmap_pte = kmap_get_pte(addr, idx);
+		set_pte_at(&init_mm, addr, kmap_pte, pteval);
 		arch_kmap_local_post_map(addr, pteval);
 	}
 }
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index e09159c957e3..a1baa198519a 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1037,8 +1037,10 @@ void clear_vma_resv_huge_pages(struct vm_area_struct *vma)
 	 */
 	struct resv_map *reservations = vma_resv_map(vma);
 
-	if (reservations && is_vma_resv_set(vma, HPAGE_RESV_OWNER))
+	if (reservations && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) {
+		resv_map_put_hugetlb_cgroup_uncharge_info(reservations);
 		kref_put(&reservations->refs, resv_map_release);
+	}
 
 	reset_vma_resv_huge_pages(vma);
 }
@@ -2971,7 +2973,7 @@ int __alloc_bootmem_huge_page(struct hstate *h, int nid)
 	struct huge_bootmem_page *m = NULL; /* initialize for clang */
 	int nr_nodes, node;
 
-	if (nid >= nr_online_nodes)
+	if (nid != NUMA_NO_NODE && nid >= nr_online_nodes)
 		return 0;
 	/* do node specific alloc */
 	if (nid != NUMA_NO_NODE) {
@@ -4917,9 +4919,9 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma,
 
 		move_huge_pte(vma, old_addr, new_addr, src_pte);
 	}
-	i_mmap_unlock_write(mapping);
 	flush_tlb_range(vma, old_end - len, old_end);
 	mmu_notifier_invalidate_range_end(&range);
+	i_mmap_unlock_write(mapping);
 
 	return len + old_addr - old_end;
 }
@@ -4937,6 +4939,7 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct
 	struct hstate *h = hstate_vma(vma);
 	unsigned long sz = huge_page_size(h);
 	struct mmu_notifier_range range;
+	bool force_flush = false;
 
 	WARN_ON(!is_vm_hugetlb_page(vma));
 	BUG_ON(start & ~huge_page_mask(h));
@@ -4965,10 +4968,8 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct
 		ptl = huge_pte_lock(h, mm, ptep);
 		if (huge_pmd_unshare(mm, vma, &address, ptep)) {
 			spin_unlock(ptl);
-			/*
-			 * We just unmapped a page of PMDs by clearing a PUD.
-			 * The caller's TLB flush range should cover this area.
-			 */
+			tlb_flush_pmd_range(tlb, address & PUD_MASK, PUD_SIZE);
+			force_flush = true;
 			continue;
 		}
 
@@ -5025,6 +5026,22 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct
 	}
 	mmu_notifier_invalidate_range_end(&range);
 	tlb_end_vma(tlb, vma);
+
+	/*
+	 * If we unshared PMDs, the TLB flush was not recorded in mmu_gather. We
+	 * could defer the flush until now, since by holding i_mmap_rwsem we
+	 * guaranteed that the last refernece would not be dropped. But we must
+	 * do the flushing before we return, as otherwise i_mmap_rwsem will be
+	 * dropped and the last reference to the shared PMDs page might be
+	 * dropped as well.
+	 *
+	 * In theory we could defer the freeing of the PMD pages as well, but
+	 * huge_pmd_unshare() relies on the exact page_count for the PMD page to
+	 * detect sharing, so we cannot defer the release of the page either.
+	 * Instead, do flush now.
+	 */
+	if (force_flush)
+		tlb_flush_mmu_tlbonly(tlb);
 }
 
 void __unmap_hugepage_range_final(struct mmu_gather *tlb,
@@ -5734,13 +5751,14 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
 	int ret = -ENOMEM;
 	struct page *page;
 	int writable;
-	bool new_pagecache_page = false;
+	bool page_in_pagecache = false;
 
 	if (is_continue) {
 		ret = -EFAULT;
 		page = find_lock_page(mapping, idx);
 		if (!page)
 			goto out;
+		page_in_pagecache = true;
 	} else if (!*pagep) {
 		/* If a page already exists, then it's UFFDIO_COPY for
 		 * a non-missing case. Return -EEXIST.
@@ -5828,7 +5846,7 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
 		ret = huge_add_to_page_cache(page, mapping, idx);
 		if (ret)
 			goto out_release_nounlock;
-		new_pagecache_page = true;
+		page_in_pagecache = true;
 	}
 
 	ptl = huge_pte_lockptr(h, dst_mm, dst_pte);
@@ -5892,7 +5910,7 @@ out_release_unlock:
 	if (vm_shared || is_continue)
 		unlock_page(page);
 out_release_nounlock:
-	if (!new_pagecache_page)
+	if (!page_in_pagecache)
 		restore_reserve_on_error(h, dst_vma, dst_addr, page);
 	put_page(page);
 	goto out;
diff --git a/mm/kfence/core.c b/mm/kfence/core.c
index 09945784df9e..a19154a8d196 100644
--- a/mm/kfence/core.c
+++ b/mm/kfence/core.c
@@ -683,6 +683,7 @@ static const struct file_operations objects_fops = {
 	.open = open_objects,
 	.read = seq_read,
 	.llseek = seq_lseek,
+	.release = seq_release,
 };
 
 static int __init kfence_debugfs_init(void)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 781605e92015..2ed5f2a0879d 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -776,24 +776,6 @@ void __mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val)
 	rcu_read_unlock();
 }
 
-/*
- * mod_objcg_mlstate() may be called with irq enabled, so
- * mod_memcg_lruvec_state() should be used.
- */
-static inline void mod_objcg_mlstate(struct obj_cgroup *objcg,
-				     struct pglist_data *pgdat,
-				     enum node_stat_item idx, int nr)
-{
-	struct mem_cgroup *memcg;
-	struct lruvec *lruvec;
-
-	rcu_read_lock();
-	memcg = obj_cgroup_memcg(objcg);
-	lruvec = mem_cgroup_lruvec(memcg, pgdat);
-	mod_memcg_lruvec_state(lruvec, idx, nr);
-	rcu_read_unlock();
-}
-
 /**
  * __count_memcg_events - account VM events in a cgroup
  * @memcg: the memory cgroup
@@ -2137,41 +2119,6 @@ static bool obj_stock_flush_required(struct memcg_stock_pcp *stock,
 }
 #endif
 
-/*
- * Most kmem_cache_alloc() calls are from user context. The irq disable/enable
- * sequence used in this case to access content from object stock is slow.
- * To optimize for user context access, there are now two object stocks for
- * task context and interrupt context access respectively.
- *
- * The task context object stock can be accessed by disabling preemption only
- * which is cheap in non-preempt kernel. The interrupt context object stock
- * can only be accessed after disabling interrupt. User context code can
- * access interrupt object stock, but not vice versa.
- */
-static inline struct obj_stock *get_obj_stock(unsigned long *pflags)
-{
-	struct memcg_stock_pcp *stock;
-
-	if (likely(in_task())) {
-		*pflags = 0UL;
-		preempt_disable();
-		stock = this_cpu_ptr(&memcg_stock);
-		return &stock->task_obj;
-	}
-
-	local_irq_save(*pflags);
-	stock = this_cpu_ptr(&memcg_stock);
-	return &stock->irq_obj;
-}
-
-static inline void put_obj_stock(unsigned long flags)
-{
-	if (likely(in_task()))
-		preempt_enable();
-	else
-		local_irq_restore(flags);
-}
-
 /**
  * consume_stock: Try to consume stocked charge on this cpu.
  * @memcg: memcg to consume from.
@@ -2816,6 +2763,59 @@ retry:
  */
 #define OBJCGS_CLEAR_MASK	(__GFP_DMA | __GFP_RECLAIMABLE | __GFP_ACCOUNT)
 
+/*
+ * Most kmem_cache_alloc() calls are from user context. The irq disable/enable
+ * sequence used in this case to access content from object stock is slow.
+ * To optimize for user context access, there are now two object stocks for
+ * task context and interrupt context access respectively.
+ *
+ * The task context object stock can be accessed by disabling preemption only
+ * which is cheap in non-preempt kernel. The interrupt context object stock
+ * can only be accessed after disabling interrupt. User context code can
+ * access interrupt object stock, but not vice versa.
+ */
+static inline struct obj_stock *get_obj_stock(unsigned long *pflags)
+{
+	struct memcg_stock_pcp *stock;
+
+	if (likely(in_task())) {
+		*pflags = 0UL;
+		preempt_disable();
+		stock = this_cpu_ptr(&memcg_stock);
+		return &stock->task_obj;
+	}
+
+	local_irq_save(*pflags);
+	stock = this_cpu_ptr(&memcg_stock);
+	return &stock->irq_obj;
+}
+
+static inline void put_obj_stock(unsigned long flags)
+{
+	if (likely(in_task()))
+		preempt_enable();
+	else
+		local_irq_restore(flags);
+}
+
+/*
+ * mod_objcg_mlstate() may be called with irq enabled, so
+ * mod_memcg_lruvec_state() should be used.
+ */
+static inline void mod_objcg_mlstate(struct obj_cgroup *objcg,
+				     struct pglist_data *pgdat,
+				     enum node_stat_item idx, int nr)
+{
+	struct mem_cgroup *memcg;
+	struct lruvec *lruvec;
+
+	rcu_read_lock();
+	memcg = obj_cgroup_memcg(objcg);
+	lruvec = mem_cgroup_lruvec(memcg, pgdat);
+	mod_memcg_lruvec_state(lruvec, idx, nr);
+	rcu_read_unlock();
+}
+
 int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s,
 				 gfp_t gfp, bool new_page)
 {
@@ -5558,7 +5558,7 @@ static int mem_cgroup_move_account(struct page *page,
 
 	VM_BUG_ON(from == to);
 	VM_BUG_ON_FOLIO(folio_test_lru(folio), folio);
-	VM_BUG_ON(compound && !folio_test_multi(folio));
+	VM_BUG_ON(compound && !folio_test_large(folio));
 
 	/*
 	 * Prevent mem_cgroup_migrate() from looking at
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index f64ebb6226cb..3a274468f193 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -58,7 +58,6 @@
 #include <linux/ratelimit.h>
 #include <linux/page-isolation.h>
 #include <linux/pagewalk.h>
-#include <linux/shmem_fs.h>
 #include "internal.h"
 #include "ras/ras_event.h"
 
@@ -868,7 +867,6 @@ static int me_pagecache_clean(struct page_state *ps, struct page *p)
 {
 	int ret;
 	struct address_space *mapping;
-	bool extra_pins;
 
 	delete_from_lru_cache(p);
 
@@ -898,23 +896,17 @@ static int me_pagecache_clean(struct page_state *ps, struct page *p)
 	}
 
 	/*
-	 * The shmem page is kept in page cache instead of truncating
-	 * so is expected to have an extra refcount after error-handling.
-	 */
-	extra_pins = shmem_mapping(mapping);
-
-	/*
 	 * Truncation is a bit tricky. Enable it per file system for now.
 	 *
 	 * Open: to take i_rwsem or not for this? Right now we don't.
 	 */
 	ret = truncate_error_page(p, page_to_pfn(p), mapping);
-	if (has_extra_refcount(ps, p, extra_pins))
-		ret = MF_FAILED;
-
 out:
 	unlock_page(p);
 
+	if (has_extra_refcount(ps, p, false))
+		ret = MF_FAILED;
+
 	return ret;
 }
 
@@ -1478,17 +1470,12 @@ static int memory_failure_hugetlb(unsigned long pfn, int flags)
 	if (!(flags & MF_COUNT_INCREASED)) {
 		res = get_hwpoison_page(p, flags);
 		if (!res) {
-			/*
-			 * Check "filter hit" and "race with other subpage."
-			 */
 			lock_page(head);
-			if (PageHWPoison(head)) {
-				if ((hwpoison_filter(p) && TestClearPageHWPoison(p))
-				    || (p != head && TestSetPageHWPoison(head))) {
+			if (hwpoison_filter(p)) {
+				if (TestClearPageHWPoison(head))
 					num_poisoned_pages_dec();
-					unlock_page(head);
-					return 0;
-				}
+				unlock_page(head);
+				return 0;
 			}
 			unlock_page(head);
 			res = MF_FAILED;
@@ -2247,6 +2234,7 @@ retry:
 	} else if (ret == 0) {
 		if (soft_offline_free_page(page) && try_again) {
 			try_again = false;
+			flags &= ~MF_COUNT_INCREASED;
 			goto retry;
 		}
 	}
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 852041f6be41..2a9627dc784c 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -35,6 +35,7 @@
 #include <linux/memblock.h>
 #include <linux/compaction.h>
 #include <linux/rmap.h>
+#include <linux/module.h>
 
 #include <asm/tlbflush.h>
 
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 10e9c87260ed..f6248affaf38 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2140,8 +2140,7 @@ struct page *alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
 			 * memory with both reclaim and compact as well.
 			 */
 			if (!page && (gfp & __GFP_DIRECT_RECLAIM))
-				page = __alloc_pages_node(hpage_node,
-								gfp, order);
+				page = __alloc_pages(gfp, order, hpage_node, nmask);
 
 			goto out;
 		}
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 2d498bb62248..a613f8ef6a02 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2967,7 +2967,7 @@ EXPORT_SYMBOL_GPL(folio_wait_writeback_killable);
  */
 void folio_wait_stable(struct folio *folio)
 {
-	if (folio->mapping->host->i_sb->s_iflags & SB_I_STABLE_WRITES)
+	if (folio_inode(folio)->i_sb->s_iflags & SB_I_STABLE_WRITES)
 		folio_wait_writeback(folio);
 }
 EXPORT_SYMBOL_GPL(folio_wait_stable);
diff --git a/mm/shmem.c b/mm/shmem.c
index f0eee4e221a7..18f93c2d68f1 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2303,6 +2303,7 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode
 		INIT_LIST_HEAD(&info->swaplist);
 		simple_xattrs_init(&info->xattrs);
 		cache_no_acl(inode);
+		mapping_set_large_folios(inode->i_mapping);
 
 		switch (mode & S_IFMT) {
 		default:
@@ -2456,7 +2457,6 @@ shmem_write_begin(struct file *file, struct address_space *mapping,
 	struct inode *inode = mapping->host;
 	struct shmem_inode_info *info = SHMEM_I(inode);
 	pgoff_t index = pos >> PAGE_SHIFT;
-	int ret = 0;
 
 	/* i_rwsem is held by caller */
 	if (unlikely(info->seals & (F_SEAL_GROW |
@@ -2467,15 +2467,7 @@ shmem_write_begin(struct file *file, struct address_space *mapping,
 			return -EPERM;
 	}
 
-	ret = shmem_getpage(inode, index, pagep, SGP_WRITE);
-
-	if (*pagep && PageHWPoison(*pagep)) {
-		unlock_page(*pagep);
-		put_page(*pagep);
-		ret = -EIO;
-	}
-
-	return ret;
+	return shmem_getpage(inode, index, pagep, SGP_WRITE);
 }
 
 static int
@@ -2562,12 +2554,6 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 			if (sgp == SGP_CACHE)
 				set_page_dirty(page);
 			unlock_page(page);
-
-			if (PageHWPoison(page)) {
-				put_page(page);
-				error = -EIO;
-				break;
-			}
 		}
 
 		/*
@@ -3107,8 +3093,7 @@ static const char *shmem_get_link(struct dentry *dentry,
 		page = find_get_page(inode->i_mapping, 0);
 		if (!page)
 			return ERR_PTR(-ECHILD);
-		if (PageHWPoison(page) ||
-		    !PageUptodate(page)) {
+		if (!PageUptodate(page)) {
 			put_page(page);
 			return ERR_PTR(-ECHILD);
 		}
@@ -3116,11 +3101,6 @@ static const char *shmem_get_link(struct dentry *dentry,
 		error = shmem_getpage(inode, 0, &page, SGP_READ);
 		if (error)
 			return ERR_PTR(error);
-		if (page && PageHWPoison(page)) {
-			unlock_page(page);
-			put_page(page);
-			return ERR_PTR(-ECHILD);
-		}
 		unlock_page(page);
 	}
 	set_delayed_call(done, shmem_put_link, page);
@@ -3771,13 +3751,6 @@ static void shmem_destroy_inodecache(void)
 	kmem_cache_destroy(shmem_inode_cachep);
 }
 
-/* Keep the page in page cache instead of truncating it */
-static int shmem_error_remove_page(struct address_space *mapping,
-				   struct page *page)
-{
-	return 0;
-}
-
 const struct address_space_operations shmem_aops = {
 	.writepage	= shmem_writepage,
 	.set_page_dirty	= __set_page_dirty_no_writeback,
@@ -3788,7 +3761,7 @@ const struct address_space_operations shmem_aops = {
 #ifdef CONFIG_MIGRATION
 	.migratepage	= migrate_page,
 #endif
-	.error_remove_page = shmem_error_remove_page,
+	.error_remove_page = generic_error_remove_page,
 };
 EXPORT_SYMBOL(shmem_aops);
 
@@ -3898,7 +3871,7 @@ static struct file_system_type shmem_fs_type = {
 	.parameters	= shmem_fs_parameters,
 #endif
 	.kill_sb	= kill_litter_super,
-	.fs_flags	= FS_USERNS_MOUNT | FS_THP_SUPPORT,
+	.fs_flags	= FS_USERNS_MOUNT,
 };
 
 int __init shmem_init(void)
@@ -4199,10 +4172,6 @@ struct page *shmem_read_mapping_page_gfp(struct address_space *mapping,
 		page = ERR_PTR(error);
 	else
 		unlock_page(page);
-
-	if (PageHWPoison(page))
-		page = ERR_PTR(-EIO);
-
 	return page;
 #else
 	/*
diff --git a/mm/slab.c b/mm/slab.c
index da132a9ae6f8..ca4822f6b2b6 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -3733,14 +3733,13 @@ void kmem_cache_free(struct kmem_cache *cachep, void *objp)
 	if (!cachep)
 		return;
 
+	trace_kmem_cache_free(_RET_IP_, objp, cachep->name);
 	local_irq_save(flags);
 	debug_check_no_locks_freed(objp, cachep->object_size);
 	if (!(cachep->flags & SLAB_DEBUG_OBJECTS))
 		debug_check_no_obj_freed(objp, cachep->object_size);
 	__cache_free(cachep, objp, _RET_IP_);
 	local_irq_restore(flags);
-
-	trace_kmem_cache_free(_RET_IP_, objp, cachep->name);
 }
 EXPORT_SYMBOL(kmem_cache_free);
 
diff --git a/mm/slab.h b/mm/slab.h
index 58c01a34e5b8..56ad7eea3ddf 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -147,7 +147,7 @@ static inline slab_flags_t kmem_cache_flags(unsigned int object_size,
 #define SLAB_CACHE_FLAGS (SLAB_NOLEAKTRACE | SLAB_RECLAIM_ACCOUNT | \
 			  SLAB_TEMPORARY | SLAB_ACCOUNT)
 #else
-#define SLAB_CACHE_FLAGS (0)
+#define SLAB_CACHE_FLAGS (SLAB_NOLEAKTRACE)
 #endif
 
 /* Common flags available with current configuration */
diff --git a/mm/slob.c b/mm/slob.c
index 74d3f6e60666..03deee1e6a94 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -666,6 +666,7 @@ static void kmem_rcu_free(struct rcu_head *head)
 void kmem_cache_free(struct kmem_cache *c, void *b)
 {
 	kmemleak_free_recursive(b, c->flags);
+	trace_kmem_cache_free(_RET_IP_, b, c->name);
 	if (unlikely(c->flags & SLAB_TYPESAFE_BY_RCU)) {
 		struct slob_rcu *slob_rcu;
 		slob_rcu = b + (c->size - sizeof(struct slob_rcu));
@@ -674,8 +675,6 @@ void kmem_cache_free(struct kmem_cache *c, void *b)
 	} else {
 		__kmem_cache_free(b, c->size);
 	}
-
-	trace_kmem_cache_free(_RET_IP_, b, c->name);
 }
 EXPORT_SYMBOL(kmem_cache_free);
 
diff --git a/mm/slub.c b/mm/slub.c
index f7368bfffb7a..abe7db581d68 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -3526,8 +3526,8 @@ void kmem_cache_free(struct kmem_cache *s, void *x)
 	s = cache_from_obj(s, x);
 	if (!s)
 		return;
-	slab_free(s, virt_to_head_page(x), x, NULL, 1, _RET_IP_);
 	trace_kmem_cache_free(_RET_IP_, x, s->name);
+	slab_free(s, virt_to_head_page(x), x, NULL, 1, _RET_IP_);
 }
 EXPORT_SYMBOL(kmem_cache_free);
 
@@ -5081,6 +5081,7 @@ struct loc_track {
 	unsigned long max;
 	unsigned long count;
 	struct location *loc;
+	loff_t idx;
 };
 
 static struct dentry *slab_debugfs_root;
@@ -6052,11 +6053,11 @@ __initcall(slab_sysfs_init);
 #if defined(CONFIG_SLUB_DEBUG) && defined(CONFIG_DEBUG_FS)
 static int slab_debugfs_show(struct seq_file *seq, void *v)
 {
-
-	struct location *l;
-	unsigned int idx = *(unsigned int *)v;
 	struct loc_track *t = seq->private;
+	struct location *l;
+	unsigned long idx;
 
+	idx = (unsigned long) t->idx;
 	if (idx < t->count) {
 		l = &t->loc[idx];
 
@@ -6105,16 +6106,18 @@ static void *slab_debugfs_next(struct seq_file *seq, void *v, loff_t *ppos)
 {
 	struct loc_track *t = seq->private;
 
-	v = ppos;
-	++*ppos;
+	t->idx = ++(*ppos);
 	if (*ppos <= t->count)
-		return v;
+		return ppos;
 
 	return NULL;
 }
 
 static void *slab_debugfs_start(struct seq_file *seq, loff_t *ppos)
 {
+	struct loc_track *t = seq->private;
+
+	t->idx = *ppos;
 	return ppos;
 }
 
diff --git a/mm/swap.c b/mm/swap.c
index 1841c24682f8..e8c9dc6d0377 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -156,6 +156,7 @@ void put_pages_list(struct list_head *pages)
 	}
 
 	free_unref_page_list(pages);
+	INIT_LIST_HEAD(pages);
 }
 EXPORT_SYMBOL(put_pages_list);
 
diff --git a/mm/swap_slots.c b/mm/swap_slots.c
index 16f706c55d92..2b5531840583 100644
--- a/mm/swap_slots.c
+++ b/mm/swap_slots.c
@@ -30,6 +30,7 @@
 #include <linux/swap_slots.h>
 #include <linux/cpu.h>
 #include <linux/cpumask.h>
+#include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/mutex.h>
 #include <linux/mm.h>
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 0780c2a57ff1..ac6f036298cd 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -232,11 +232,6 @@ static int mcontinue_atomic_pte(struct mm_struct *dst_mm,
 		goto out;
 	}
 
-	if (PageHWPoison(page)) {
-		ret = -EIO;
-		goto out_release;
-	}
-
 	ret = mfill_atomic_install_pte(dst_mm, dst_pmd, dst_vma, dst_addr,
 				       page, false, wp_copy);
 	if (ret)
diff --git a/mm/util.c b/mm/util.c
index e58151a61255..741ba32a43ac 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -670,7 +670,7 @@ bool folio_mapped(struct folio *folio)
 {
 	long i, nr;
 
-	if (folio_test_single(folio))
+	if (!folio_test_large(folio))
 		return atomic_read(&folio->_mapcount) >= 0;
 	if (atomic_read(folio_mapcount_ptr(folio)) >= 0)
 		return true;
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index a3a0a5e994f5..abaa5d96ded2 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -184,9 +184,6 @@ int register_vlan_dev(struct net_device *dev, struct netlink_ext_ack *extack)
 	if (err)
 		goto out_unregister_netdev;
 
-	/* Account for reference in struct vlan_dev_priv */
-	dev_hold(real_dev);
-
 	vlan_stacked_transfer_operstate(real_dev, dev, vlan);
 	linkwatch_fire_event(dev); /* _MUST_ call rfc2863_policy() */
 
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index ab6dee28536d..a54535cbcf4c 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -615,6 +615,9 @@ static int vlan_dev_init(struct net_device *dev)
 	if (!vlan->vlan_pcpu_stats)
 		return -ENOMEM;
 
+	/* Get vlan's reference to real_dev */
+	dev_hold(real_dev);
+
 	return 0;
 }
 
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index 2f34bbdde0e8..cfca99e295b8 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -85,8 +85,10 @@ static void ax25_kill_by_device(struct net_device *dev)
 again:
 	ax25_for_each(s, &ax25_list) {
 		if (s->ax25_dev == ax25_dev) {
-			s->ax25_dev = NULL;
 			spin_unlock_bh(&ax25_list_lock);
+			lock_sock(s->sk);
+			s->ax25_dev = NULL;
+			release_sock(s->sk);
 			ax25_disconnect(s, ENETUNREACH);
 			spin_lock_bh(&ax25_list_lock);
 
diff --git a/net/bridge/br_ioctl.c b/net/bridge/br_ioctl.c
index db4ab2c2ce18..891cfcf45644 100644
--- a/net/bridge/br_ioctl.c
+++ b/net/bridge/br_ioctl.c
@@ -337,7 +337,7 @@ static int old_deviceless(struct net *net, void __user *uarg)
 
 		args[2] = get_bridge_ifindices(net, indices, args[2]);
 
-		ret = copy_to_user(uarg, indices,
+		ret = copy_to_user((void __user *)args[1], indices,
 				   array_size(args[2], sizeof(int)))
 			? -EFAULT : args[2];
 
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index f3d751105343..de2409889489 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -4522,6 +4522,38 @@ int br_multicast_set_mld_version(struct net_bridge_mcast *brmctx,
 }
 #endif
 
+void br_multicast_set_query_intvl(struct net_bridge_mcast *brmctx,
+				  unsigned long val)
+{
+	unsigned long intvl_jiffies = clock_t_to_jiffies(val);
+
+	if (intvl_jiffies < BR_MULTICAST_QUERY_INTVL_MIN) {
+		br_info(brmctx->br,
+			"trying to set multicast query interval below minimum, setting to %lu (%ums)\n",
+			jiffies_to_clock_t(BR_MULTICAST_QUERY_INTVL_MIN),
+			jiffies_to_msecs(BR_MULTICAST_QUERY_INTVL_MIN));
+		intvl_jiffies = BR_MULTICAST_QUERY_INTVL_MIN;
+	}
+
+	brmctx->multicast_query_interval = intvl_jiffies;
+}
+
+void br_multicast_set_startup_query_intvl(struct net_bridge_mcast *brmctx,
+					  unsigned long val)
+{
+	unsigned long intvl_jiffies = clock_t_to_jiffies(val);
+
+	if (intvl_jiffies < BR_MULTICAST_STARTUP_QUERY_INTVL_MIN) {
+		br_info(brmctx->br,
+			"trying to set multicast startup query interval below minimum, setting to %lu (%ums)\n",
+			jiffies_to_clock_t(BR_MULTICAST_STARTUP_QUERY_INTVL_MIN),
+			jiffies_to_msecs(BR_MULTICAST_STARTUP_QUERY_INTVL_MIN));
+		intvl_jiffies = BR_MULTICAST_STARTUP_QUERY_INTVL_MIN;
+	}
+
+	brmctx->multicast_startup_query_interval = intvl_jiffies;
+}
+
 /**
  * br_multicast_list_adjacent - Returns snooped multicast addresses
  * @dev:	The bridge port adjacent to which to retrieve addresses
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 0c8b5f1a15bc..2ff83d84230d 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -1357,7 +1357,7 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[],
 	if (data[IFLA_BR_MCAST_QUERY_INTVL]) {
 		u64 val = nla_get_u64(data[IFLA_BR_MCAST_QUERY_INTVL]);
 
-		br->multicast_ctx.multicast_query_interval = clock_t_to_jiffies(val);
+		br_multicast_set_query_intvl(&br->multicast_ctx, val);
 	}
 
 	if (data[IFLA_BR_MCAST_QUERY_RESPONSE_INTVL]) {
@@ -1369,7 +1369,7 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[],
 	if (data[IFLA_BR_MCAST_STARTUP_QUERY_INTVL]) {
 		u64 val = nla_get_u64(data[IFLA_BR_MCAST_STARTUP_QUERY_INTVL]);
 
-		br->multicast_ctx.multicast_startup_query_interval = clock_t_to_jiffies(val);
+		br_multicast_set_startup_query_intvl(&br->multicast_ctx, val);
 	}
 
 	if (data[IFLA_BR_MCAST_STATS_ENABLED]) {
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index c0efd697865a..e8c6ee322c71 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -28,6 +28,8 @@
 #define BR_MAX_PORTS	(1<<BR_PORT_BITS)
 
 #define BR_MULTICAST_DEFAULT_HASH_MAX 4096
+#define BR_MULTICAST_QUERY_INTVL_MIN msecs_to_jiffies(1000)
+#define BR_MULTICAST_STARTUP_QUERY_INTVL_MIN BR_MULTICAST_QUERY_INTVL_MIN
 
 #define BR_HWDOM_MAX BITS_PER_LONG
 
@@ -963,6 +965,10 @@ int br_multicast_dump_querier_state(struct sk_buff *skb,
 				    int nest_attr);
 size_t br_multicast_querier_state_size(void);
 size_t br_rports_size(const struct net_bridge_mcast *brmctx);
+void br_multicast_set_query_intvl(struct net_bridge_mcast *brmctx,
+				  unsigned long val);
+void br_multicast_set_startup_query_intvl(struct net_bridge_mcast *brmctx,
+					  unsigned long val);
 
 static inline bool br_group_is_l2(const struct br_ip *group)
 {
@@ -1147,9 +1153,9 @@ br_multicast_port_ctx_get_global(const struct net_bridge_mcast_port *pmctx)
 static inline bool
 br_multicast_ctx_vlan_global_disabled(const struct net_bridge_mcast *brmctx)
 {
-	return br_opt_get(brmctx->br, BROPT_MCAST_VLAN_SNOOPING_ENABLED) &&
-	       br_multicast_ctx_is_vlan(brmctx) &&
-	       !(brmctx->vlan->priv_flags & BR_VLFLAG_GLOBAL_MCAST_ENABLED);
+	return br_multicast_ctx_is_vlan(brmctx) &&
+	       (!br_opt_get(brmctx->br, BROPT_MCAST_VLAN_SNOOPING_ENABLED) ||
+		!(brmctx->vlan->priv_flags & BR_VLFLAG_GLOBAL_MCAST_ENABLED));
 }
 
 static inline bool
diff --git a/net/bridge/br_sysfs_br.c b/net/bridge/br_sysfs_br.c
index d9a89ddd0331..7b0c19772111 100644
--- a/net/bridge/br_sysfs_br.c
+++ b/net/bridge/br_sysfs_br.c
@@ -658,7 +658,7 @@ static ssize_t multicast_query_interval_show(struct device *d,
 static int set_query_interval(struct net_bridge *br, unsigned long val,
 			      struct netlink_ext_ack *extack)
 {
-	br->multicast_ctx.multicast_query_interval = clock_t_to_jiffies(val);
+	br_multicast_set_query_intvl(&br->multicast_ctx, val);
 	return 0;
 }
 
@@ -706,7 +706,7 @@ static ssize_t multicast_startup_query_interval_show(
 static int set_startup_query_interval(struct net_bridge *br, unsigned long val,
 				      struct netlink_ext_ack *extack)
 {
-	br->multicast_ctx.multicast_startup_query_interval = clock_t_to_jiffies(val);
+	br_multicast_set_startup_query_intvl(&br->multicast_ctx, val);
 	return 0;
 }
 
diff --git a/net/bridge/br_vlan_options.c b/net/bridge/br_vlan_options.c
index 8ffd4ed2563c..a6382973b3e7 100644
--- a/net/bridge/br_vlan_options.c
+++ b/net/bridge/br_vlan_options.c
@@ -521,7 +521,7 @@ static int br_vlan_process_global_one_opts(const struct net_bridge *br,
 		u64 val;
 
 		val = nla_get_u64(tb[BRIDGE_VLANDB_GOPTS_MCAST_QUERY_INTVL]);
-		v->br_mcast_ctx.multicast_query_interval = clock_t_to_jiffies(val);
+		br_multicast_set_query_intvl(&v->br_mcast_ctx, val);
 		*changed = true;
 	}
 	if (tb[BRIDGE_VLANDB_GOPTS_MCAST_QUERY_RESPONSE_INTVL]) {
@@ -535,7 +535,7 @@ static int br_vlan_process_global_one_opts(const struct net_bridge *br,
 		u64 val;
 
 		val = nla_get_u64(tb[BRIDGE_VLANDB_GOPTS_MCAST_STARTUP_QUERY_INTVL]);
-		v->br_mcast_ctx.multicast_startup_query_interval = clock_t_to_jiffies(val);
+		br_multicast_set_startup_query_intvl(&v->br_mcast_ctx, val);
 		*changed = true;
 	}
 	if (tb[BRIDGE_VLANDB_GOPTS_MCAST_QUERIER]) {
diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c
index 013cbdb6cfe2..6a6898ee4049 100644
--- a/net/ceph/mon_client.c
+++ b/net/ceph/mon_client.c
@@ -1153,12 +1153,11 @@ static int build_initial_monmap(struct ceph_mon_client *monc)
 
 int ceph_monc_init(struct ceph_mon_client *monc, struct ceph_client *cl)
 {
-	int err = 0;
+	int err;
 
 	dout("init\n");
 	memset(monc, 0, sizeof(*monc));
 	monc->client = cl;
-	monc->monmap = NULL;
 	mutex_init(&monc->mutex);
 
 	err = build_initial_monmap(monc);
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index ff8624a7c964..1c5815530e0d 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -5310,14 +5310,14 @@ void ceph_osdc_stop(struct ceph_osd_client *osdc)
 	ceph_msgpool_destroy(&osdc->msgpool_op_reply);
 }
 
-static int osd_req_op_copy_from_init(struct ceph_osd_request *req,
-				     u64 src_snapid, u64 src_version,
-				     struct ceph_object_id *src_oid,
-				     struct ceph_object_locator *src_oloc,
-				     u32 src_fadvise_flags,
-				     u32 dst_fadvise_flags,
-				     u32 truncate_seq, u64 truncate_size,
-				     u8 copy_from_flags)
+int osd_req_op_copy_from_init(struct ceph_osd_request *req,
+			      u64 src_snapid, u64 src_version,
+			      struct ceph_object_id *src_oid,
+			      struct ceph_object_locator *src_oloc,
+			      u32 src_fadvise_flags,
+			      u32 dst_fadvise_flags,
+			      u32 truncate_seq, u64 truncate_size,
+			      u8 copy_from_flags)
 {
 	struct ceph_osd_req_op *op;
 	struct page **pages;
@@ -5346,49 +5346,7 @@ static int osd_req_op_copy_from_init(struct ceph_osd_request *req,
 				 op->indata_len, 0, false, true);
 	return 0;
 }
-
-int ceph_osdc_copy_from(struct ceph_osd_client *osdc,
-			u64 src_snapid, u64 src_version,
-			struct ceph_object_id *src_oid,
-			struct ceph_object_locator *src_oloc,
-			u32 src_fadvise_flags,
-			struct ceph_object_id *dst_oid,
-			struct ceph_object_locator *dst_oloc,
-			u32 dst_fadvise_flags,
-			u32 truncate_seq, u64 truncate_size,
-			u8 copy_from_flags)
-{
-	struct ceph_osd_request *req;
-	int ret;
-
-	req = ceph_osdc_alloc_request(osdc, NULL, 1, false, GFP_KERNEL);
-	if (!req)
-		return -ENOMEM;
-
-	req->r_flags = CEPH_OSD_FLAG_WRITE;
-
-	ceph_oloc_copy(&req->r_t.base_oloc, dst_oloc);
-	ceph_oid_copy(&req->r_t.base_oid, dst_oid);
-
-	ret = osd_req_op_copy_from_init(req, src_snapid, src_version, src_oid,
-					src_oloc, src_fadvise_flags,
-					dst_fadvise_flags, truncate_seq,
-					truncate_size, copy_from_flags);
-	if (ret)
-		goto out;
-
-	ret = ceph_osdc_alloc_messages(req, GFP_KERNEL);
-	if (ret)
-		goto out;
-
-	ceph_osdc_start_request(osdc, req, false);
-	ret = ceph_osdc_wait_request(osdc, req);
-
-out:
-	ceph_osdc_put_request(req);
-	return ret;
-}
-EXPORT_SYMBOL(ceph_osdc_copy_from);
+EXPORT_SYMBOL(osd_req_op_copy_from_init);
 
 int __init ceph_osdc_setup(void)
 {
diff --git a/net/core/dev.c b/net/core/dev.c
index 15ac064b5562..c4708e2487fb 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3941,8 +3941,8 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev)
 		return skb;
 
 	/* qdisc_skb_cb(skb)->pkt_len was already set by the caller. */
-	qdisc_skb_cb(skb)->mru = 0;
-	qdisc_skb_cb(skb)->post_ct = false;
+	tc_skb_cb(skb)->mru = 0;
+	tc_skb_cb(skb)->post_ct = false;
 	mini_qdisc_bstats_cpu_update(miniq, skb);
 
 	switch (tcf_classify(skb, miniq->block, miniq->filter_list, &cl_res, false)) {
@@ -4210,7 +4210,10 @@ static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
 	if (dev->flags & IFF_UP) {
 		int cpu = smp_processor_id(); /* ok because BHs are off */
 
-		if (txq->xmit_lock_owner != cpu) {
+		/* Other cpus might concurrently change txq->xmit_lock_owner
+		 * to -1 or to their cpu id, but not to our id.
+		 */
+		if (READ_ONCE(txq->xmit_lock_owner) != cpu) {
 			if (dev_xmit_recursion())
 				goto recursion_alert;
 
@@ -5100,8 +5103,8 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret,
 	}
 
 	qdisc_skb_cb(skb)->pkt_len = skb->len;
-	qdisc_skb_cb(skb)->mru = 0;
-	qdisc_skb_cb(skb)->post_ct = false;
+	tc_skb_cb(skb)->mru = 0;
+	tc_skb_cb(skb)->post_ct = false;
 	skb->tc_at_ingress = 1;
 	mini_qdisc_bstats_cpu_update(miniq, skb);
 
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 5ba4f9434acd..c06c9ba6e8c5 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -4110,14 +4110,6 @@ static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info)
 		return err;
 	}
 
-	if (info->attrs[DEVLINK_ATTR_NETNS_PID] ||
-	    info->attrs[DEVLINK_ATTR_NETNS_FD] ||
-	    info->attrs[DEVLINK_ATTR_NETNS_ID]) {
-		dest_net = devlink_netns_get(skb, info);
-		if (IS_ERR(dest_net))
-			return PTR_ERR(dest_net);
-	}
-
 	if (info->attrs[DEVLINK_ATTR_RELOAD_ACTION])
 		action = nla_get_u8(info->attrs[DEVLINK_ATTR_RELOAD_ACTION]);
 	else
@@ -4160,6 +4152,14 @@ static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info)
 			return -EINVAL;
 		}
 	}
+	if (info->attrs[DEVLINK_ATTR_NETNS_PID] ||
+	    info->attrs[DEVLINK_ATTR_NETNS_FD] ||
+	    info->attrs[DEVLINK_ATTR_NETNS_ID]) {
+		dest_net = devlink_netns_get(skb, info);
+		if (IS_ERR(dest_net))
+			return PTR_ERR(dest_net);
+	}
+
 	err = devlink_reload(devlink, dest_net, action, limit, &actions_performed, info->extack);
 
 	if (dest_net)
@@ -4229,7 +4229,9 @@ static void __devlink_flash_update_notify(struct devlink *devlink,
 	WARN_ON(cmd != DEVLINK_CMD_FLASH_UPDATE &&
 		cmd != DEVLINK_CMD_FLASH_UPDATE_END &&
 		cmd != DEVLINK_CMD_FLASH_UPDATE_STATUS);
-	WARN_ON(!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED));
+
+	if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED))
+		return;
 
 	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
 	if (!msg)
diff --git a/net/core/dst_cache.c b/net/core/dst_cache.c
index be74ab4551c2..0ccfd5fa5cb9 100644
--- a/net/core/dst_cache.c
+++ b/net/core/dst_cache.c
@@ -162,3 +162,22 @@ void dst_cache_destroy(struct dst_cache *dst_cache)
 	free_percpu(dst_cache->cache);
 }
 EXPORT_SYMBOL_GPL(dst_cache_destroy);
+
+void dst_cache_reset_now(struct dst_cache *dst_cache)
+{
+	int i;
+
+	if (!dst_cache->cache)
+		return;
+
+	dst_cache->reset_ts = jiffies;
+	for_each_possible_cpu(i) {
+		struct dst_cache_pcpu *idst = per_cpu_ptr(dst_cache->cache, i);
+		struct dst_entry *dst = idst->dst;
+
+		idst->cookie = 0;
+		idst->dst = NULL;
+		dst_release(dst);
+	}
+}
+EXPORT_SYMBOL_GPL(dst_cache_reset_now);
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 79df7cd9dbc1..1bb567a3b329 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -323,7 +323,7 @@ jumped:
 		if (!err && ops->suppress && INDIRECT_CALL_MT(ops->suppress,
 							      fib6_rule_suppress,
 							      fib4_rule_suppress,
-							      rule, arg))
+							      rule, flags, arg))
 			continue;
 
 		if (err != -EAGAIN) {
diff --git a/net/core/filter.c b/net/core/filter.c
index e471c9b09670..6102f093d59a 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -7162,6 +7162,8 @@ sock_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 #endif
 	case BPF_FUNC_sk_storage_get:
 		return &bpf_sk_storage_get_cg_sock_proto;
+	case BPF_FUNC_ktime_get_coarse_ns:
+		return &bpf_ktime_get_coarse_ns_proto;
 	default:
 		return bpf_base_func_proto(func_id);
 	}
@@ -10327,6 +10329,8 @@ sk_reuseport_func_proto(enum bpf_func_id func_id,
 		return &sk_reuseport_load_bytes_relative_proto;
 	case BPF_FUNC_get_socket_cookie:
 		return &bpf_get_socket_ptr_cookie_proto;
+	case BPF_FUNC_ktime_get_coarse_ns:
+		return &bpf_ktime_get_coarse_ns_proto;
 	default:
 		return bpf_base_func_proto(func_id);
 	}
@@ -10833,6 +10837,8 @@ bpf_sk_base_func_proto(enum bpf_func_id func_id)
 	case BPF_FUNC_skc_to_unix_sock:
 		func = &bpf_skc_to_unix_sock_proto;
 		break;
+	case BPF_FUNC_ktime_get_coarse_ns:
+		return &bpf_ktime_get_coarse_ns_proto;
 	default:
 		return bpf_base_func_proto(func_id);
 	}
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 3255f57f5131..1b094c481f1d 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -238,7 +238,7 @@ void
 skb_flow_dissect_ct(const struct sk_buff *skb,
 		    struct flow_dissector *flow_dissector,
 		    void *target_container, u16 *ctinfo_map,
-		    size_t mapsize, bool post_ct)
+		    size_t mapsize, bool post_ct, u16 zone)
 {
 #if IS_ENABLED(CONFIG_NF_CONNTRACK)
 	struct flow_dissector_key_ct *key;
@@ -260,6 +260,7 @@ skb_flow_dissect_ct(const struct sk_buff *skb,
 	if (!ct) {
 		key->ct_state = TCA_FLOWER_KEY_CT_FLAGS_TRACKED |
 				TCA_FLOWER_KEY_CT_FLAGS_INVALID;
+		key->ct_zone = zone;
 		return;
 	}
 
diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c
index 2820aca2173a..9ccd64e8a666 100644
--- a/net/core/lwtunnel.c
+++ b/net/core/lwtunnel.c
@@ -197,6 +197,10 @@ int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int remaining,
 			nla_entype = nla_find(attrs, attrlen, RTA_ENCAP_TYPE);
 
 			if (nla_entype) {
+				if (nla_len(nla_entype) < sizeof(u16)) {
+					NL_SET_ERR_MSG(extack, "Invalid RTA_ENCAP_TYPE");
+					return -EINVAL;
+				}
 				encap_type = nla_get_u16(nla_entype);
 
 				if (lwtunnel_valid_encap_type(encap_type,
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 47931c8be04b..dda12fbd177b 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -763,11 +763,10 @@ struct pneigh_entry * pneigh_lookup(struct neigh_table *tbl,
 
 	ASSERT_RTNL();
 
-	n = kmalloc(sizeof(*n) + key_len, GFP_KERNEL);
+	n = kzalloc(sizeof(*n) + key_len, GFP_KERNEL);
 	if (!n)
 		goto out;
 
-	n->protocol = 0;
 	write_pnet(&n->net, net);
 	memcpy(n->key, pkey, key_len);
 	n->dev = dev;
@@ -1779,6 +1778,7 @@ int neigh_table_clear(int index, struct neigh_table *tbl)
 {
 	neigh_tables[index] = NULL;
 	/* It is not clean... Fix it to unload IPv6 module safely */
+	cancel_delayed_work_sync(&tbl->managed_work);
 	cancel_delayed_work_sync(&tbl->gc_work);
 	del_timer_sync(&tbl->proxy_timer);
 	pneigh_queue_purge(&tbl->proxy_queue);
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index 9b60e4301a44..1a6978427d6c 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -49,12 +49,6 @@ static int page_pool_init(struct page_pool *pool,
 	 * which is the XDP_TX use-case.
 	 */
 	if (pool->p.flags & PP_FLAG_DMA_MAP) {
-		/* DMA-mapping is not supported on 32-bit systems with
-		 * 64-bit DMA mapping.
-		 */
-		if (sizeof(dma_addr_t) > sizeof(unsigned long))
-			return -EOPNOTSUPP;
-
 		if ((pool->p.dma_dir != DMA_FROM_DEVICE) &&
 		    (pool->p.dma_dir != DMA_BIDIRECTIONAL))
 			return -EINVAL;
@@ -75,6 +69,10 @@ static int page_pool_init(struct page_pool *pool,
 		 */
 	}
 
+	if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT &&
+	    pool->p.flags & PP_FLAG_PAGE_FRAG)
+		return -EINVAL;
+
 	if (ptr_ring_init(&pool->ring, ring_qsize, GFP_KERNEL) < 0)
 		return -ENOMEM;
 
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index ba2f38246f07..909db87d7383 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -832,7 +832,7 @@ void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt)
 	       ntohs(skb->protocol), skb->pkt_type, skb->skb_iif);
 
 	if (dev)
-		printk("%sdev name=%s feat=0x%pNF\n",
+		printk("%sdev name=%s feat=%pNF\n",
 		       level, dev->name, &dev->features);
 	if (sk)
 		printk("%ssk family=%hu type=%u proto=%u\n",
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 1ae52ac943f6..8eb671c827f9 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -1124,6 +1124,8 @@ void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock)
 
 void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock)
 {
+	psock_set_prog(&psock->progs.stream_parser, NULL);
+
 	if (!psock->saved_data_ready)
 		return;
 
@@ -1212,6 +1214,9 @@ void sk_psock_start_verdict(struct sock *sk, struct sk_psock *psock)
 
 void sk_psock_stop_verdict(struct sock *sk, struct sk_psock *psock)
 {
+	psock_set_prog(&psock->progs.stream_verdict, NULL);
+	psock_set_prog(&psock->progs.skb_verdict, NULL);
+
 	if (!psock->saved_data_ready)
 		return;
 
diff --git a/net/core/sock.c b/net/core/sock.c
index 8f2b2f2c0e7b..41e91d0f7061 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2124,8 +2124,10 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 	newsk->sk_prot_creator = prot;
 
 	/* SANITY */
-	if (likely(newsk->sk_net_refcnt))
+	if (likely(newsk->sk_net_refcnt)) {
 		get_net(sock_net(newsk));
+		sock_inuse_add(sock_net(newsk), 1);
+	}
 	sk_node_init(&newsk->sk_node);
 	sock_lock_init(newsk);
 	bh_lock_sock(newsk);
@@ -2197,8 +2199,6 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 	newsk->sk_err_soft = 0;
 	newsk->sk_priority = 0;
 	newsk->sk_incoming_cpu = raw_smp_processor_id();
-	if (likely(newsk->sk_net_refcnt))
-		sock_inuse_add(sock_net(newsk), 1);
 
 	/* Before updating sk_refcnt, we must commit prior changes to memory
 	 * (Documentation/RCU/rculist_nulls.rst for details)
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index f39ef79ced67..4ca4b11f4e5f 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -167,8 +167,11 @@ static void sock_map_del_link(struct sock *sk,
 		write_lock_bh(&sk->sk_callback_lock);
 		if (strp_stop)
 			sk_psock_stop_strp(sk, psock);
-		else
+		if (verdict_stop)
 			sk_psock_stop_verdict(sk, psock);
+
+		if (psock->psock_update_sk_prot)
+			psock->psock_update_sk_prot(sk, psock, false);
 		write_unlock_bh(&sk->sk_callback_lock);
 	}
 }
@@ -282,6 +285,12 @@ static int sock_map_link(struct bpf_map *map, struct sock *sk)
 
 	if (msg_parser)
 		psock_set_prog(&psock->progs.msg_parser, msg_parser);
+	if (stream_parser)
+		psock_set_prog(&psock->progs.stream_parser, stream_parser);
+	if (stream_verdict)
+		psock_set_prog(&psock->progs.stream_verdict, stream_verdict);
+	if (skb_verdict)
+		psock_set_prog(&psock->progs.skb_verdict, skb_verdict);
 
 	ret = sock_map_init_proto(sk, psock);
 	if (ret < 0)
@@ -292,14 +301,10 @@ static int sock_map_link(struct bpf_map *map, struct sock *sk)
 		ret = sk_psock_init_strp(sk, psock);
 		if (ret)
 			goto out_unlock_drop;
-		psock_set_prog(&psock->progs.stream_verdict, stream_verdict);
-		psock_set_prog(&psock->progs.stream_parser, stream_parser);
 		sk_psock_start_strp(sk, psock);
 	} else if (!stream_parser && stream_verdict && !psock->saved_data_ready) {
-		psock_set_prog(&psock->progs.stream_verdict, stream_verdict);
 		sk_psock_start_verdict(sk,psock);
 	} else if (!stream_verdict && skb_verdict && !psock->saved_data_ready) {
-		psock_set_prog(&psock->progs.skb_verdict, skb_verdict);
 		sk_psock_start_verdict(sk, psock);
 	}
 	write_unlock_bh(&sk->sk_callback_lock);
diff --git a/net/dsa/tag_ocelot.c b/net/dsa/tag_ocelot.c
index de1c849a0a70..4ed74d509d6a 100644
--- a/net/dsa/tag_ocelot.c
+++ b/net/dsa/tag_ocelot.c
@@ -47,9 +47,13 @@ static void ocelot_xmit_common(struct sk_buff *skb, struct net_device *netdev,
 	void *injection;
 	__be32 *prefix;
 	u32 rew_op = 0;
+	u64 qos_class;
 
 	ocelot_xmit_get_vlan_info(skb, dp, &vlan_tci, &tag_type);
 
+	qos_class = netdev_get_num_tc(netdev) ?
+		    netdev_get_prio_tc_map(netdev, skb->priority) : skb->priority;
+
 	injection = skb_push(skb, OCELOT_TAG_LEN);
 	prefix = skb_push(skb, OCELOT_SHORT_PREFIX_LEN);
 
@@ -57,7 +61,7 @@ static void ocelot_xmit_common(struct sk_buff *skb, struct net_device *netdev,
 	memset(injection, 0, OCELOT_TAG_LEN);
 	ocelot_ifh_set_bypass(injection, 1);
 	ocelot_ifh_set_src(injection, ds->num_ports);
-	ocelot_ifh_set_qos_class(injection, skb->priority);
+	ocelot_ifh_set_qos_class(injection, qos_class);
 	ocelot_ifh_set_vlan_tci(injection, vlan_tci);
 	ocelot_ifh_set_tag_type(injection, tag_type);
 
diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index 65e9bc1058b5..20bcf86970ff 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -1719,7 +1719,7 @@ static noinline_for_stack int ethtool_set_coalesce(struct net_device *dev,
 	struct ethtool_coalesce coalesce;
 	int ret;
 
-	if (!dev->ethtool_ops->set_coalesce && !dev->ethtool_ops->get_coalesce)
+	if (!dev->ethtool_ops->set_coalesce || !dev->ethtool_ops->get_coalesce)
 		return -EOPNOTSUPP;
 
 	ret = dev->ethtool_ops->get_coalesce(dev, &coalesce, &kernel_coalesce,
diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c
index 38b44c0291b1..96f4180aabd2 100644
--- a/net/ethtool/netlink.c
+++ b/net/ethtool/netlink.c
@@ -40,7 +40,8 @@ int ethnl_ops_begin(struct net_device *dev)
 	if (dev->dev.parent)
 		pm_runtime_get_sync(dev->dev.parent);
 
-	if (!netif_device_present(dev)) {
+	if (!netif_device_present(dev) ||
+	    dev->reg_state == NETREG_UNREGISTERING) {
 		ret = -ENODEV;
 		goto err;
 	}
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 0189e3cd4a7d..5f70ffdae1b5 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -154,7 +154,7 @@ void inet_sock_destruct(struct sock *sk)
 
 	kfree(rcu_dereference_protected(inet->inet_opt, 1));
 	dst_release(rcu_dereference_protected(sk->sk_dst_cache, 1));
-	dst_release(sk->sk_rx_dst);
+	dst_release(rcu_dereference_protected(sk->sk_rx_dst, 1));
 	sk_refcnt_debug_dec(sk);
 }
 EXPORT_SYMBOL(inet_sock_destruct);
@@ -1994,6 +1994,10 @@ static int __init inet_init(void)
 
 	ip_init();
 
+	/* Initialise per-cpu ipv4 mibs */
+	if (init_ipv4_mibs())
+		panic("%s: Cannot init ipv4 mibs\n", __func__);
+
 	/* Setup TCP slab cache for open requests. */
 	tcp_init();
 
@@ -2024,12 +2028,6 @@ static int __init inet_init(void)
 
 	if (init_inet_pernet_ops())
 		pr_crit("%s: Cannot init ipv4 inet pernet ops\n", __func__);
-	/*
-	 *	Initialise per-cpu ipv4 mibs
-	 */
-
-	if (init_ipv4_mibs())
-		pr_crit("%s: Cannot init ipv4 mibs\n", __func__);
 
 	ipv4_proc_init();
 
diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c
index 2cf02b4d77fb..4bb9401b0a3f 100644
--- a/net/ipv4/bpf_tcp_ca.c
+++ b/net/ipv4/bpf_tcp_ca.c
@@ -205,6 +205,8 @@ bpf_tcp_ca_get_func_proto(enum bpf_func_id func_id,
 		    offsetof(struct tcp_congestion_ops, release))
 			return &bpf_sk_getsockopt_proto;
 		return NULL;
+	case BPF_FUNC_ktime_get_coarse_ns:
+		return &bpf_ktime_get_coarse_ns_proto;
 	default:
 		return bpf_base_func_proto(func_id);
 	}
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index ec73a0d52d3e..323e622ff9b7 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -2591,7 +2591,7 @@ static int __devinet_sysctl_register(struct net *net, char *dev_name,
 free:
 	kfree(t);
 out:
-	return -ENOBUFS;
+	return -ENOMEM;
 }
 
 static void __devinet_sysctl_unregister(struct net *net,
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 9fe13e4f5d08..4d61ddd8a0ec 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1582,7 +1582,7 @@ static int __net_init fib_net_init(struct net *net)
 	int error;
 
 #ifdef CONFIG_IP_ROUTE_CLASSID
-	net->ipv4.fib_num_tclassid_users = 0;
+	atomic_set(&net->ipv4.fib_num_tclassid_users, 0);
 #endif
 	error = ip_fib_net_init(net);
 	if (error < 0)
diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
index ce54a30c2ef1..d279cb8ac158 100644
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -141,6 +141,7 @@ INDIRECT_CALLABLE_SCOPE int fib4_rule_action(struct fib_rule *rule,
 }
 
 INDIRECT_CALLABLE_SCOPE bool fib4_rule_suppress(struct fib_rule *rule,
+						int flags,
 						struct fib_lookup_arg *arg)
 {
 	struct fib_result *result = (struct fib_result *) arg->result;
@@ -263,7 +264,7 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
 	if (tb[FRA_FLOW]) {
 		rule4->tclassid = nla_get_u32(tb[FRA_FLOW]);
 		if (rule4->tclassid)
-			net->ipv4.fib_num_tclassid_users++;
+			atomic_inc(&net->ipv4.fib_num_tclassid_users);
 	}
 #endif
 
@@ -295,7 +296,7 @@ static int fib4_rule_delete(struct fib_rule *rule)
 
 #ifdef CONFIG_IP_ROUTE_CLASSID
 	if (((struct fib4_rule *)rule)->tclassid)
-		net->ipv4.fib_num_tclassid_users--;
+		atomic_dec(&net->ipv4.fib_num_tclassid_users);
 #endif
 	net->ipv4.fib_has_custom_rules = true;
 
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 3364cb9c67e0..92c29ab3d042 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -220,7 +220,7 @@ void fib_nh_release(struct net *net, struct fib_nh *fib_nh)
 {
 #ifdef CONFIG_IP_ROUTE_CLASSID
 	if (fib_nh->nh_tclassid)
-		net->ipv4.fib_num_tclassid_users--;
+		atomic_dec(&net->ipv4.fib_num_tclassid_users);
 #endif
 	fib_nh_common_release(&fib_nh->nh_common);
 }
@@ -632,7 +632,7 @@ int fib_nh_init(struct net *net, struct fib_nh *nh,
 #ifdef CONFIG_IP_ROUTE_CLASSID
 	nh->nh_tclassid = cfg->fc_flow;
 	if (nh->nh_tclassid)
-		net->ipv4.fib_num_tclassid_users++;
+		atomic_inc(&net->ipv4.fib_num_tclassid_users);
 #endif
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 	nh->fib_nh_weight = nh_weight;
@@ -662,6 +662,19 @@ static int fib_count_nexthops(struct rtnexthop *rtnh, int remaining,
 	return nhs;
 }
 
+static int fib_gw_from_attr(__be32 *gw, struct nlattr *nla,
+			    struct netlink_ext_ack *extack)
+{
+	if (nla_len(nla) < sizeof(*gw)) {
+		NL_SET_ERR_MSG(extack, "Invalid IPv4 address in RTA_GATEWAY");
+		return -EINVAL;
+	}
+
+	*gw = nla_get_in_addr(nla);
+
+	return 0;
+}
+
 /* only called when fib_nh is integrated into fib_info */
 static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh,
 		       int remaining, struct fib_config *cfg,
@@ -704,7 +717,11 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh,
 				return -EINVAL;
 			}
 			if (nla) {
-				fib_cfg.fc_gw4 = nla_get_in_addr(nla);
+				ret = fib_gw_from_attr(&fib_cfg.fc_gw4, nla,
+						       extack);
+				if (ret)
+					goto errout;
+
 				if (fib_cfg.fc_gw4)
 					fib_cfg.fc_gw_family = AF_INET;
 			} else if (nlav) {
@@ -714,10 +731,18 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh,
 			}
 
 			nla = nla_find(attrs, attrlen, RTA_FLOW);
-			if (nla)
+			if (nla) {
+				if (nla_len(nla) < sizeof(u32)) {
+					NL_SET_ERR_MSG(extack, "Invalid RTA_FLOW");
+					return -EINVAL;
+				}
 				fib_cfg.fc_flow = nla_get_u32(nla);
+			}
 
 			fib_cfg.fc_encap = nla_find(attrs, attrlen, RTA_ENCAP);
+			/* RTA_ENCAP_TYPE length checked in
+			 * lwtunnel_valid_encap_type_attr
+			 */
 			nla = nla_find(attrs, attrlen, RTA_ENCAP_TYPE);
 			if (nla)
 				fib_cfg.fc_encap_type = nla_get_u16(nla);
@@ -902,6 +927,7 @@ int fib_nh_match(struct net *net, struct fib_config *cfg, struct fib_info *fi,
 		attrlen = rtnh_attrlen(rtnh);
 		if (attrlen > 0) {
 			struct nlattr *nla, *nlav, *attrs = rtnh_attrs(rtnh);
+			int err;
 
 			nla = nla_find(attrs, attrlen, RTA_GATEWAY);
 			nlav = nla_find(attrs, attrlen, RTA_VIA);
@@ -912,12 +938,17 @@ int fib_nh_match(struct net *net, struct fib_config *cfg, struct fib_info *fi,
 			}
 
 			if (nla) {
+				__be32 gw;
+
+				err = fib_gw_from_attr(&gw, nla, extack);
+				if (err)
+					return err;
+
 				if (nh->fib_nh_gw_family != AF_INET ||
-				    nla_get_in_addr(nla) != nh->fib_nh_gw4)
+				    gw != nh->fib_nh_gw4)
 					return 1;
 			} else if (nlav) {
 				struct fib_config cfg2;
-				int err;
 
 				err = fib_gw_from_via(&cfg2, nlav, extack);
 				if (err)
@@ -940,8 +971,14 @@ int fib_nh_match(struct net *net, struct fib_config *cfg, struct fib_info *fi,
 
 #ifdef CONFIG_IP_ROUTE_CLASSID
 			nla = nla_find(attrs, attrlen, RTA_FLOW);
-			if (nla && nla_get_u32(nla) != nh->nh_tclassid)
-				return 1;
+			if (nla) {
+				if (nla_len(nla) < sizeof(u32)) {
+					NL_SET_ERR_MSG(extack, "Invalid RTA_FLOW");
+					return -EINVAL;
+				}
+				if (nla_get_u32(nla) != nh->nh_tclassid)
+					return 1;
+			}
 #endif
 		}
 
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index f7fea3a7c5e6..62a67fdc344c 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -721,7 +721,7 @@ static struct request_sock *inet_reqsk_clone(struct request_sock *req,
 
 	sk_node_init(&nreq_sk->sk_node);
 	nreq_sk->sk_tx_queue_mapping = req_sk->sk_tx_queue_mapping;
-#ifdef CONFIG_XPS
+#ifdef CONFIG_SOCK_RX_QUEUE_MAPPING
 	nreq_sk->sk_rx_queue_mapping = req_sk->sk_rx_queue_mapping;
 #endif
 	nreq_sk->sk_incoming_cpu = req_sk->sk_incoming_cpu;
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index c8fa6e7f7d12..581b5b2d72a5 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -261,6 +261,7 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
 	r->idiag_state = sk->sk_state;
 	r->idiag_timer = 0;
 	r->idiag_retrans = 0;
+	r->idiag_expires = 0;
 
 	if (inet_diag_msg_attrs_fill(sk, skb, r, ext,
 				     sk_user_ns(NETLINK_CB(cb->skb).sk),
@@ -314,9 +315,6 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
 		r->idiag_retrans = icsk->icsk_probes_out;
 		r->idiag_expires =
 			jiffies_delta_to_msecs(sk->sk_timer.expires - jiffies);
-	} else {
-		r->idiag_timer = 0;
-		r->idiag_expires = 0;
 	}
 
 	if ((ext & (1 << (INET_DIAG_INFO - 1))) && handler->idiag_info_size) {
diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index 9e8100728d46..5dbd4b5505eb 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -1899,15 +1899,36 @@ static void remove_nexthop(struct net *net, struct nexthop *nh,
 /* if any FIB entries reference this nexthop, any dst entries
  * need to be regenerated
  */
-static void nh_rt_cache_flush(struct net *net, struct nexthop *nh)
+static void nh_rt_cache_flush(struct net *net, struct nexthop *nh,
+			      struct nexthop *replaced_nh)
 {
 	struct fib6_info *f6i;
+	struct nh_group *nhg;
+	int i;
 
 	if (!list_empty(&nh->fi_list))
 		rt_cache_flush(net);
 
 	list_for_each_entry(f6i, &nh->f6i_list, nh_list)
 		ipv6_stub->fib6_update_sernum(net, f6i);
+
+	/* if an IPv6 group was replaced, we have to release all old
+	 * dsts to make sure all refcounts are released
+	 */
+	if (!replaced_nh->is_group)
+		return;
+
+	/* new dsts must use only the new nexthop group */
+	synchronize_net();
+
+	nhg = rtnl_dereference(replaced_nh->nh_grp);
+	for (i = 0; i < nhg->num_nh; i++) {
+		struct nh_grp_entry *nhge = &nhg->nh_entries[i];
+		struct nh_info *nhi = rtnl_dereference(nhge->nh->nh_info);
+
+		if (nhi->family == AF_INET6)
+			ipv6_stub->fib6_nh_release_dsts(&nhi->fib6_nh);
+	}
 }
 
 static int replace_nexthop_grp(struct net *net, struct nexthop *old,
@@ -2247,7 +2268,7 @@ static int replace_nexthop(struct net *net, struct nexthop *old,
 		err = replace_nexthop_single(net, old, new, extack);
 
 	if (!err) {
-		nh_rt_cache_flush(net, old);
+		nh_rt_cache_flush(net, old, new);
 
 		__remove_nexthop(net, new, NULL);
 		nexthop_put(new);
@@ -2544,11 +2565,15 @@ static int nh_create_ipv6(struct net *net,  struct nexthop *nh,
 	/* sets nh_dev if successful */
 	err = ipv6_stub->fib6_nh_init(net, fib6_nh, &fib6_cfg, GFP_KERNEL,
 				      extack);
-	if (err)
+	if (err) {
+		/* IPv6 is not enabled, don't call fib6_nh_release */
+		if (err == -EAFNOSUPPORT)
+			goto out;
 		ipv6_stub->fib6_nh_release(fib6_nh);
-	else
+	} else {
 		nh->nh_flags = fib6_nh->fib_nh_flags;
-
+	}
+out:
 	return err;
 }
 
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index b7796b4cf0a0..2bb28bfd83bf 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1758,6 +1758,9 @@ static skb_frag_t *skb_advance_to_frag(struct sk_buff *skb, u32 offset_skb,
 {
 	skb_frag_t *frag;
 
+	if (unlikely(offset_skb >= skb->len))
+		return NULL;
+
 	offset_skb -= skb_headlen(skb);
 	if ((int)offset_skb < 0 || skb_has_frag_list(skb))
 		return NULL;
@@ -3009,8 +3012,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 	icsk->icsk_ack.rcv_mss = TCP_MIN_MSS;
 	memset(&tp->rx_opt, 0, sizeof(tp->rx_opt));
 	__sk_dst_reset(sk);
-	dst_release(sk->sk_rx_dst);
-	sk->sk_rx_dst = NULL;
+	dst_release(xchg((__force struct dst_entry **)&sk->sk_rx_dst, NULL));
 	tcp_saved_syn_free(tp);
 	tp->compressed_ack = 0;
 	tp->segs_in = 0;
diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index 5e9d9c51164c..e07837e23b3f 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -330,8 +330,6 @@ static void cubictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 		return;
 
 	if (tcp_in_slow_start(tp)) {
-		if (hystart && after(ack, ca->end_seq))
-			bictcp_hystart_reset(sk);
 		acked = tcp_slow_start(tp, acked);
 		if (!acked)
 			return;
@@ -391,6 +389,9 @@ static void hystart_update(struct sock *sk, u32 delay)
 	struct bictcp *ca = inet_csk_ca(sk);
 	u32 threshold;
 
+	if (after(tp->snd_una, ca->end_seq))
+		bictcp_hystart_reset(sk);
+
 	if (hystart_detect & HYSTART_ACK_TRAIN) {
 		u32 now = bictcp_clock_us(sk);
 
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 246ab7b5e857..0ce46849ec3d 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5787,7 +5787,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb)
 	trace_tcp_probe(sk, skb);
 
 	tcp_mstamp_refresh(tp);
-	if (unlikely(!sk->sk_rx_dst))
+	if (unlikely(!rcu_access_pointer(sk->sk_rx_dst)))
 		inet_csk(sk)->icsk_af_ops->sk_rx_dst_set(sk, skb);
 	/*
 	 *	Header prediction.
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 13d868c43284..084df223b5df 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1701,7 +1701,10 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
 	struct sock *rsk;
 
 	if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */
-		struct dst_entry *dst = sk->sk_rx_dst;
+		struct dst_entry *dst;
+
+		dst = rcu_dereference_protected(sk->sk_rx_dst,
+						lockdep_sock_is_held(sk));
 
 		sock_rps_save_rxhash(sk, skb);
 		sk_mark_napi_id(sk, skb);
@@ -1709,8 +1712,8 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
 			if (sk->sk_rx_dst_ifindex != skb->skb_iif ||
 			    !INDIRECT_CALL_1(dst->ops->check, ipv4_dst_check,
 					     dst, 0)) {
+				RCU_INIT_POINTER(sk->sk_rx_dst, NULL);
 				dst_release(dst);
-				sk->sk_rx_dst = NULL;
 			}
 		}
 		tcp_rcv_established(sk, skb);
@@ -1786,7 +1789,7 @@ int tcp_v4_early_demux(struct sk_buff *skb)
 		skb->sk = sk;
 		skb->destructor = sock_edemux;
 		if (sk_fullsock(sk)) {
-			struct dst_entry *dst = READ_ONCE(sk->sk_rx_dst);
+			struct dst_entry *dst = rcu_dereference(sk->sk_rx_dst);
 
 			if (dst)
 				dst = dst_check(dst, 0);
@@ -2201,7 +2204,7 @@ void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
 	struct dst_entry *dst = skb_dst(skb);
 
 	if (dst && dst_hold_safe(dst)) {
-		sk->sk_rx_dst = dst;
+		rcu_assign_pointer(sk->sk_rx_dst, dst);
 		sk->sk_rx_dst_ifindex = skb->skb_iif;
 	}
 }
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index cf913a66df17..7c2d3ac2363a 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -829,8 +829,8 @@ int tcp_child_process(struct sock *parent, struct sock *child,
 	int ret = 0;
 	int state = child->sk_state;
 
-	/* record NAPI ID of child */
-	sk_mark_napi_id(child, skb);
+	/* record sk_napi_id and sk_rx_queue_mapping of child. */
+	sk_mark_napi_id_set(child, skb);
 
 	tcp_segs_in(tcp_sk(child), skb);
 	if (!sock_owned_by_user(child)) {
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 319dd7bbfe33..0cd6b857e7ec 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -916,7 +916,7 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4,
 			kfree_skb(skb);
 			return -EINVAL;
 		}
-		if (skb->len > cork->gso_size * UDP_MAX_SEGMENTS) {
+		if (datalen > cork->gso_size * UDP_MAX_SEGMENTS) {
 			kfree_skb(skb);
 			return -EINVAL;
 		}
@@ -1807,6 +1807,17 @@ int udp_read_sock(struct sock *sk, read_descriptor_t *desc,
 		skb = skb_recv_udp(sk, 0, 1, &err);
 		if (!skb)
 			return err;
+
+		if (udp_lib_checksum_complete(skb)) {
+			__UDP_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS,
+					IS_UDPLITE(sk));
+			__UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS,
+					IS_UDPLITE(sk));
+			atomic_inc(&sk->sk_drops);
+			kfree_skb(skb);
+			continue;
+		}
+
 		used = recv_actor(desc, skb, 0, skb->len);
 		if (used <= 0) {
 			if (!copied)
@@ -2239,7 +2250,7 @@ bool udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst)
 	struct dst_entry *old;
 
 	if (dst_hold_safe(dst)) {
-		old = xchg(&sk->sk_rx_dst, dst);
+		old = xchg((__force struct dst_entry **)&sk->sk_rx_dst, dst);
 		dst_release(old);
 		return old != dst;
 	}
@@ -2429,7 +2440,7 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 		struct dst_entry *dst = skb_dst(skb);
 		int ret;
 
-		if (unlikely(sk->sk_rx_dst != dst))
+		if (unlikely(rcu_dereference(sk->sk_rx_dst) != dst))
 			udp_sk_rx_dst_set(sk, dst);
 
 		ret = udp_unicast_rcv_skb(sk, skb, uh);
@@ -2588,7 +2599,7 @@ int udp_v4_early_demux(struct sk_buff *skb)
 
 	skb->sk = sk;
 	skb->destructor = sock_efree;
-	dst = READ_ONCE(sk->sk_rx_dst);
+	dst = rcu_dereference(sk->sk_rx_dst);
 
 	if (dst)
 		dst = dst_check(dst, 0);
@@ -3064,7 +3075,7 @@ int udp4_seq_show(struct seq_file *seq, void *v)
 {
 	seq_setwidth(seq, 127);
 	if (v == SEQ_START_TOKEN)
-		seq_puts(seq, "  sl  local_address rem_address   st tx_queue "
+		seq_puts(seq, "   sl  local_address rem_address   st tx_queue "
 			   "rx_queue tr tm->when retrnsmt   uid  timeout "
 			   "inode ref pointer drops");
 	else {
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 0c4da163535a..dab4a047590b 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -1026,6 +1026,7 @@ static const struct ipv6_stub ipv6_stub_impl = {
 	.ip6_mtu_from_fib6 = ip6_mtu_from_fib6,
 	.fib6_nh_init	   = fib6_nh_init,
 	.fib6_nh_release   = fib6_nh_release,
+	.fib6_nh_release_dsts = fib6_nh_release_dsts,
 	.fib6_update_sernum = fib6_update_sernum_stub,
 	.fib6_rt_update	   = fib6_rt_update,
 	.ip6_del_rt	   = ip6_del_rt,
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index ed2f061b8768..f0bac6f7ab6b 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -808,6 +808,12 @@ int esp6_input_done2(struct sk_buff *skb, int err)
 		struct tcphdr *th;
 
 		offset = ipv6_skip_exthdr(skb, offset, &nexthdr, &frag_off);
+
+		if (offset < 0) {
+			err = -EINVAL;
+			goto out;
+		}
+
 		uh = (void *)(skb->data + offset);
 		th = (void *)(skb->data + offset);
 		hdr_len += offset;
diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index 40f3e4f9f33a..dcedfe29d9d9 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -267,6 +267,7 @@ INDIRECT_CALLABLE_SCOPE int fib6_rule_action(struct fib_rule *rule,
 }
 
 INDIRECT_CALLABLE_SCOPE bool fib6_rule_suppress(struct fib_rule *rule,
+						int flags,
 						struct fib_lookup_arg *arg)
 {
 	struct fib6_result *res = arg->result;
@@ -294,8 +295,7 @@ INDIRECT_CALLABLE_SCOPE bool fib6_rule_suppress(struct fib_rule *rule,
 	return false;
 
 suppress_route:
-	if (!(arg->flags & FIB_LOOKUP_NOREF))
-		ip6_rt_put(rt);
+	ip6_rt_put_flags(rt, flags);
 	return true;
 }
 
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 1b9827ff8ccf..1cbd49d5788d 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -248,9 +248,9 @@ INDIRECT_CALLABLE_SCOPE struct sk_buff *ipv6_gro_receive(struct list_head *head,
 		 * memcmp() alone below is sufficient, right?
 		 */
 		 if ((first_word & htonl(0xF00FFFFF)) ||
-		    !ipv6_addr_equal(&iph->saddr, &iph2->saddr) ||
-		    !ipv6_addr_equal(&iph->daddr, &iph2->daddr) ||
-		    *(u16 *)&iph->nexthdr != *(u16 *)&iph2->nexthdr) {
+		     !ipv6_addr_equal(&iph->saddr, &iph2->saddr) ||
+		     !ipv6_addr_equal(&iph->daddr, &iph2->daddr) ||
+		     *(u16 *)&iph->nexthdr != *(u16 *)&iph2->nexthdr) {
 not_same_flow:
 			NAPI_GRO_CB(p)->same_flow = 0;
 			continue;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 2f044a49afa8..ff4e83e2a506 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -174,7 +174,7 @@ static int __ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff
 #if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM)
 	/* Policy lookup after SNAT yielded a new policy */
 	if (skb_dst(skb)->xfrm) {
-		IPCB(skb)->flags |= IPSKB_REROUTED;
+		IP6CB(skb)->flags |= IP6SKB_REROUTED;
 		return dst_output(net, sk, skb);
 	}
 #endif
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 527e9ead7449..5e9474bc54fc 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -808,6 +808,8 @@ vti6_siocdevprivate(struct net_device *dev, struct ifreq *ifr, void __user *data
 	struct net *net = dev_net(dev);
 	struct vti6_net *ip6n = net_generic(net, vti6_net_id);
 
+	memset(&p1, 0, sizeof(p1));
+
 	switch (cmd) {
 	case SIOCGETTUNNEL:
 		if (dev == ip6n->fb_tnl_dev) {
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 60f1e4f5be5a..c51d5ce3711c 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -1020,6 +1020,9 @@ static int do_rawv6_setsockopt(struct sock *sk, int level, int optname,
 	struct raw6_sock *rp = raw6_sk(sk);
 	int val;
 
+	if (optlen < sizeof(val))
+		return -EINVAL;
+
 	if (copy_from_sockptr(&val, optval, sizeof(val)))
 		return -EFAULT;
 
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 3ae25b8ffbd6..1deb6297aab6 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3680,6 +3680,25 @@ void fib6_nh_release(struct fib6_nh *fib6_nh)
 	fib_nh_common_release(&fib6_nh->nh_common);
 }
 
+void fib6_nh_release_dsts(struct fib6_nh *fib6_nh)
+{
+	int cpu;
+
+	if (!fib6_nh->rt6i_pcpu)
+		return;
+
+	for_each_possible_cpu(cpu) {
+		struct rt6_info *pcpu_rt, **ppcpu_rt;
+
+		ppcpu_rt = per_cpu_ptr(fib6_nh->rt6i_pcpu, cpu);
+		pcpu_rt = xchg(ppcpu_rt, NULL);
+		if (pcpu_rt) {
+			dst_dev_put(&pcpu_rt->dst);
+			dst_release(&pcpu_rt->dst);
+		}
+	}
+}
+
 static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
 					      gfp_t gfp_flags,
 					      struct netlink_ext_ack *extack)
@@ -5205,6 +5224,19 @@ out:
 	return should_notify;
 }
 
+static int fib6_gw_from_attr(struct in6_addr *gw, struct nlattr *nla,
+			     struct netlink_ext_ack *extack)
+{
+	if (nla_len(nla) < sizeof(*gw)) {
+		NL_SET_ERR_MSG(extack, "Invalid IPv6 address in RTA_GATEWAY");
+		return -EINVAL;
+	}
+
+	*gw = nla_get_in6_addr(nla);
+
+	return 0;
+}
+
 static int ip6_route_multipath_add(struct fib6_config *cfg,
 				   struct netlink_ext_ack *extack)
 {
@@ -5245,10 +5277,18 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
 
 			nla = nla_find(attrs, attrlen, RTA_GATEWAY);
 			if (nla) {
-				r_cfg.fc_gateway = nla_get_in6_addr(nla);
+				err = fib6_gw_from_attr(&r_cfg.fc_gateway, nla,
+							extack);
+				if (err)
+					goto cleanup;
+
 				r_cfg.fc_flags |= RTF_GATEWAY;
 			}
 			r_cfg.fc_encap = nla_find(attrs, attrlen, RTA_ENCAP);
+
+			/* RTA_ENCAP_TYPE length checked in
+			 * lwtunnel_valid_encap_type_attr
+			 */
 			nla = nla_find(attrs, attrlen, RTA_ENCAP_TYPE);
 			if (nla)
 				r_cfg.fc_encap_type = nla_get_u16(nla);
@@ -5415,7 +5455,13 @@ static int ip6_route_multipath_del(struct fib6_config *cfg,
 
 			nla = nla_find(attrs, attrlen, RTA_GATEWAY);
 			if (nla) {
-				nla_memcpy(&r_cfg.fc_gateway, nla, 16);
+				err = fib6_gw_from_attr(&r_cfg.fc_gateway, nla,
+							extack);
+				if (err) {
+					last_err = err;
+					goto next_rtnh;
+				}
+
 				r_cfg.fc_flags |= RTF_GATEWAY;
 			}
 		}
@@ -5423,6 +5469,7 @@ static int ip6_route_multipath_del(struct fib6_config *cfg,
 		if (err)
 			last_err = err;
 
+next_rtnh:
 		rtnh = rtnh_next(rtnh, &remaining);
 	}
 
diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index 3adc5d9211ad..d64855010948 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -161,6 +161,14 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto)
 		hdr->hop_limit = ip6_dst_hoplimit(skb_dst(skb));
 
 		memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
+
+		/* the control block has been erased, so we have to set the
+		 * iif once again.
+		 * We read the receiving interface index directly from the
+		 * skb->skb_iif as it is done in the IPv4 receiving path (i.e.:
+		 * ip_rcv_core(...)).
+		 */
+		IP6CB(skb)->iif = skb->skb_iif;
 	}
 
 	hdr->nexthdr = NEXTHDR_ROUTING;
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 1b57ee36d668..8a3618a30632 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1933,7 +1933,6 @@ static int __net_init sit_init_net(struct net *net)
 	return 0;
 
 err_reg_dev:
-	ipip6_dev_free(sitn->fb_tunnel_dev);
 	free_netdev(sitn->fb_tunnel_dev);
 err_alloc_dev:
 	return err;
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 551fce49841d..680e6481b967 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -107,7 +107,7 @@ static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
 	if (dst && dst_hold_safe(dst)) {
 		const struct rt6_info *rt = (const struct rt6_info *)dst;
 
-		sk->sk_rx_dst = dst;
+		rcu_assign_pointer(sk->sk_rx_dst, dst);
 		sk->sk_rx_dst_ifindex = skb->skb_iif;
 		sk->sk_rx_dst_cookie = rt6_get_cookie(rt);
 	}
@@ -1505,7 +1505,10 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
 		opt_skb = skb_clone(skb, sk_gfp_mask(sk, GFP_ATOMIC));
 
 	if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */
-		struct dst_entry *dst = sk->sk_rx_dst;
+		struct dst_entry *dst;
+
+		dst = rcu_dereference_protected(sk->sk_rx_dst,
+						lockdep_sock_is_held(sk));
 
 		sock_rps_save_rxhash(sk, skb);
 		sk_mark_napi_id(sk, skb);
@@ -1513,8 +1516,8 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
 			if (sk->sk_rx_dst_ifindex != skb->skb_iif ||
 			    INDIRECT_CALL_1(dst->ops->check, ip6_dst_check,
 					    dst, sk->sk_rx_dst_cookie) == NULL) {
+				RCU_INIT_POINTER(sk->sk_rx_dst, NULL);
 				dst_release(dst);
-				sk->sk_rx_dst = NULL;
 			}
 		}
 
@@ -1874,7 +1877,7 @@ INDIRECT_CALLABLE_SCOPE void tcp_v6_early_demux(struct sk_buff *skb)
 		skb->sk = sk;
 		skb->destructor = sock_edemux;
 		if (sk_fullsock(sk)) {
-			struct dst_entry *dst = READ_ONCE(sk->sk_rx_dst);
+			struct dst_entry *dst = rcu_dereference(sk->sk_rx_dst);
 
 			if (dst)
 				dst = dst_check(dst, sk->sk_rx_dst_cookie);
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index e43b31d25fb6..8cde9efd7919 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -956,7 +956,7 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 		struct dst_entry *dst = skb_dst(skb);
 		int ret;
 
-		if (unlikely(sk->sk_rx_dst != dst))
+		if (unlikely(rcu_dereference(sk->sk_rx_dst) != dst))
 			udp6_sk_rx_dst_set(sk, dst);
 
 		if (!uh->check && !udp_sk(sk)->no_check6_rx) {
@@ -1070,7 +1070,7 @@ INDIRECT_CALLABLE_SCOPE void udp_v6_early_demux(struct sk_buff *skb)
 
 	skb->sk = sk;
 	skb->destructor = sock_efree;
-	dst = READ_ONCE(sk->sk_rx_dst);
+	dst = rcu_dereference(sk->sk_rx_dst);
 
 	if (dst)
 		dst = dst_check(dst, sk->sk_rx_dst_cookie);
@@ -1204,7 +1204,7 @@ static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6,
 			kfree_skb(skb);
 			return -EINVAL;
 		}
-		if (skb->len > cork->gso_size * UDP_MAX_SEGMENTS) {
+		if (datalen > cork->gso_size * UDP_MAX_SEGMENTS) {
 			kfree_skb(skb);
 			return -EINVAL;
 		}
diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c
index 470ff0ce3dc7..7d2925bb966e 100644
--- a/net/mac80211/agg-rx.c
+++ b/net/mac80211/agg-rx.c
@@ -9,7 +9,7 @@
  * Copyright 2007, Michael Wu <flamingice@sourmilk.net>
  * Copyright 2007-2010, Intel Corporation
  * Copyright(c) 2015-2017 Intel Deutschland GmbH
- * Copyright (C) 2018-2020 Intel Corporation
+ * Copyright (C) 2018-2021 Intel Corporation
  */
 
 /**
@@ -191,7 +191,8 @@ static void ieee80211_add_addbaext(struct ieee80211_sub_if_data *sdata,
 	sband = ieee80211_get_sband(sdata);
 	if (!sband)
 		return;
-	he_cap = ieee80211_get_he_iftype_cap(sband, sdata->vif.type);
+	he_cap = ieee80211_get_he_iftype_cap(sband,
+					     ieee80211_vif_type_p2p(&sdata->vif));
 	if (!he_cap)
 		return;
 
diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c
index 430a58587538..74a878f213d3 100644
--- a/net/mac80211/agg-tx.c
+++ b/net/mac80211/agg-tx.c
@@ -9,7 +9,7 @@
  * Copyright 2007, Michael Wu <flamingice@sourmilk.net>
  * Copyright 2007-2010, Intel Corporation
  * Copyright(c) 2015-2017 Intel Deutschland GmbH
- * Copyright (C) 2018 - 2020 Intel Corporation
+ * Copyright (C) 2018 - 2021 Intel Corporation
  */
 
 #include <linux/ieee80211.h>
@@ -106,7 +106,7 @@ static void ieee80211_send_addba_request(struct ieee80211_sub_if_data *sdata,
 	mgmt->u.action.u.addba_req.start_seq_num =
 					cpu_to_le16(start_seq_num << 4);
 
-	ieee80211_tx_skb(sdata, skb);
+	ieee80211_tx_skb_tid(sdata, skb, tid);
 }
 
 void ieee80211_send_bar(struct ieee80211_vif *vif, u8 *ra, u16 tid, u16 ssn)
@@ -213,6 +213,8 @@ ieee80211_agg_start_txq(struct sta_info *sta, int tid, bool enable)
 	struct ieee80211_txq *txq = sta->sta.txq[tid];
 	struct txq_info *txqi;
 
+	lockdep_assert_held(&sta->ampdu_mlme.mtx);
+
 	if (!txq)
 		return;
 
@@ -290,7 +292,6 @@ static void ieee80211_remove_tid_tx(struct sta_info *sta, int tid)
 	ieee80211_assign_tid_tx(sta, tid, NULL);
 
 	ieee80211_agg_splice_finish(sta->sdata, tid);
-	ieee80211_agg_start_txq(sta, tid, false);
 
 	kfree_rcu(tid_tx, rcu_head);
 }
@@ -480,8 +481,7 @@ static void ieee80211_send_addba_with_timeout(struct sta_info *sta,
 
 	/* send AddBA request */
 	ieee80211_send_addba_request(sdata, sta->sta.addr, tid,
-				     tid_tx->dialog_token,
-				     sta->tid_seq[tid] >> 4,
+				     tid_tx->dialog_token, tid_tx->ssn,
 				     buf_size, tid_tx->timeout);
 
 	WARN_ON(test_and_set_bit(HT_AGG_STATE_SENT_ADDBA, &tid_tx->state));
@@ -523,6 +523,7 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid)
 
 	params.ssn = sta->tid_seq[tid] >> 4;
 	ret = drv_ampdu_action(local, sdata, &params);
+	tid_tx->ssn = params.ssn;
 	if (ret == IEEE80211_AMPDU_TX_START_DELAY_ADDBA) {
 		return;
 	} else if (ret == IEEE80211_AMPDU_TX_START_IMMEDIATE) {
@@ -889,6 +890,7 @@ void ieee80211_stop_tx_ba_cb(struct sta_info *sta, int tid,
 {
 	struct ieee80211_sub_if_data *sdata = sta->sdata;
 	bool send_delba = false;
+	bool start_txq = false;
 
 	ht_dbg(sdata, "Stopping Tx BA session for %pM tid %d\n",
 	       sta->sta.addr, tid);
@@ -906,10 +908,14 @@ void ieee80211_stop_tx_ba_cb(struct sta_info *sta, int tid,
 		send_delba = true;
 
 	ieee80211_remove_tid_tx(sta, tid);
+	start_txq = true;
 
  unlock_sta:
 	spin_unlock_bh(&sta->lock);
 
+	if (start_txq)
+		ieee80211_agg_start_txq(sta, tid, false);
+
 	if (send_delba)
 		ieee80211_send_delba(sdata, sta->sta.addr, tid,
 			WLAN_BACK_INITIATOR, WLAN_REASON_QSTA_NOT_USE);
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index e2b791c37591..2d0dd69f9753 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -80,7 +80,8 @@ static int ieee80211_set_mon_options(struct ieee80211_sub_if_data *sdata,
 	}
 
 	/* also validate MU-MIMO change */
-	monitor_sdata = rtnl_dereference(local->monitor_sdata);
+	monitor_sdata = wiphy_dereference(local->hw.wiphy,
+					  local->monitor_sdata);
 
 	if (!monitor_sdata &&
 	    (params->vht_mumimo_groups || params->vht_mumimo_follow_addr))
@@ -840,7 +841,8 @@ static int ieee80211_set_monitor_channel(struct wiphy *wiphy,
 
 	mutex_lock(&local->mtx);
 	if (local->use_chanctx) {
-		sdata = rtnl_dereference(local->monitor_sdata);
+		sdata = wiphy_dereference(local->hw.wiphy,
+					  local->monitor_sdata);
 		if (sdata) {
 			ieee80211_vif_release_channel(sdata);
 			ret = ieee80211_vif_use_channel(sdata, chandef,
@@ -1262,7 +1264,10 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev,
 	return 0;
 
 error:
+	mutex_lock(&local->mtx);
 	ieee80211_vif_release_channel(sdata);
+	mutex_unlock(&local->mtx);
+
 	return err;
 }
 
@@ -2707,7 +2712,8 @@ static int ieee80211_set_tx_power(struct wiphy *wiphy,
 		sdata = IEEE80211_WDEV_TO_SUB_IF(wdev);
 
 		if (sdata->vif.type == NL80211_IFTYPE_MONITOR) {
-			sdata = rtnl_dereference(local->monitor_sdata);
+			sdata = wiphy_dereference(local->hw.wiphy,
+						  local->monitor_sdata);
 			if (!sdata)
 				return -EOPNOTSUPP;
 		}
@@ -2767,7 +2773,8 @@ static int ieee80211_set_tx_power(struct wiphy *wiphy,
 	mutex_unlock(&local->iflist_mtx);
 
 	if (has_monitor) {
-		sdata = rtnl_dereference(local->monitor_sdata);
+		sdata = wiphy_dereference(local->hw.wiphy,
+					  local->monitor_sdata);
 		if (sdata) {
 			sdata->user_power_level = local->user_power_level;
 			if (txp_type != sdata->vif.bss_conf.txpower_type)
diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h
index cd3731cbf6c6..c336267f4599 100644
--- a/net/mac80211/driver-ops.h
+++ b/net/mac80211/driver-ops.h
@@ -1219,8 +1219,11 @@ static inline void drv_wake_tx_queue(struct ieee80211_local *local,
 {
 	struct ieee80211_sub_if_data *sdata = vif_to_sdata(txq->txq.vif);
 
-	if (local->in_reconfig)
+	/* In reconfig don't transmit now, but mark for waking later */
+	if (local->in_reconfig) {
+		set_bit(IEEE80211_TXQ_STOP_NETIF_TX, &txq->flags);
 		return;
+	}
 
 	if (!check_sdata_in_driver(sdata))
 		return;
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 9a2145c8192b..20aa5cc31f77 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -588,7 +588,7 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_do
 	 */
 	if (local->suspended) {
 		WARN_ON(local->wowlan);
-		WARN_ON(rtnl_dereference(local->monitor_sdata));
+		WARN_ON(rcu_access_pointer(local->monitor_sdata));
 		return;
 	}
 
@@ -961,6 +961,7 @@ int ieee80211_add_virtual_monitor(struct ieee80211_local *local)
 		return 0;
 
 	ASSERT_RTNL();
+	lockdep_assert_wiphy(local->hw.wiphy);
 
 	if (local->monitor_sdata)
 		return 0;
@@ -1028,6 +1029,7 @@ void ieee80211_del_virtual_monitor(struct ieee80211_local *local)
 		return;
 
 	ASSERT_RTNL();
+	lockdep_assert_wiphy(local->hw.wiphy);
 
 	mutex_lock(&local->iflist_mtx);
 
diff --git a/net/mac80211/led.h b/net/mac80211/led.h
index fb3aaa3c5606..b71a1428d883 100644
--- a/net/mac80211/led.h
+++ b/net/mac80211/led.h
@@ -72,19 +72,19 @@ static inline void ieee80211_mod_tpt_led_trig(struct ieee80211_local *local,
 #endif
 
 static inline void
-ieee80211_tpt_led_trig_tx(struct ieee80211_local *local, __le16 fc, int bytes)
+ieee80211_tpt_led_trig_tx(struct ieee80211_local *local, int bytes)
 {
 #ifdef CONFIG_MAC80211_LEDS
-	if (ieee80211_is_data(fc) && atomic_read(&local->tpt_led_active))
+	if (atomic_read(&local->tpt_led_active))
 		local->tpt_led_trigger->tx_bytes += bytes;
 #endif
 }
 
 static inline void
-ieee80211_tpt_led_trig_rx(struct ieee80211_local *local, __le16 fc, int bytes)
+ieee80211_tpt_led_trig_rx(struct ieee80211_local *local, int bytes)
 {
 #ifdef CONFIG_MAC80211_LEDS
-	if (ieee80211_is_data(fc) && atomic_read(&local->tpt_led_active))
+	if (atomic_read(&local->tpt_led_active))
 		local->tpt_led_trigger->rx_bytes += bytes;
 #endif
 }
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 54ab0e1ef6ca..37f7d975f3da 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -2452,11 +2452,18 @@ static void ieee80211_sta_tx_wmm_ac_notify(struct ieee80211_sub_if_data *sdata,
 					   u16 tx_time)
 {
 	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
-	u16 tid = ieee80211_get_tid(hdr);
-	int ac = ieee80211_ac_from_tid(tid);
-	struct ieee80211_sta_tx_tspec *tx_tspec = &ifmgd->tx_tspec[ac];
+	u16 tid;
+	int ac;
+	struct ieee80211_sta_tx_tspec *tx_tspec;
 	unsigned long now = jiffies;
 
+	if (!ieee80211_is_data_qos(hdr->frame_control))
+		return;
+
+	tid = ieee80211_get_tid(hdr);
+	ac = ieee80211_ac_from_tid(tid);
+	tx_tspec = &ifmgd->tx_tspec[ac];
+
 	if (likely(!tx_tspec->admitted_time))
 		return;
 
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index fc5c608d02e2..0544563ede52 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -364,7 +364,7 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local,
 	 * the compiler to think we have walked past the end of the
 	 * struct member.
 	 */
-	pos = (void *)&rthdr->it_optional[it_present - rthdr->it_optional];
+	pos = (void *)&rthdr->it_optional[it_present + 1 - rthdr->it_optional];
 
 	/* the order of the following fields is important */
 
@@ -1952,7 +1952,8 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx)
 		int keyid = rx->sta->ptk_idx;
 		sta_ptk = rcu_dereference(rx->sta->ptk[keyid]);
 
-		if (ieee80211_has_protected(fc)) {
+		if (ieee80211_has_protected(fc) &&
+		    !(status->flag & RX_FLAG_IV_STRIPPED)) {
 			cs = rx->sta->cipher_scheme;
 			keyid = ieee80211_get_keyid(rx->skb, cs);
 
@@ -2943,6 +2944,7 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx)
 	if (!fwd_skb)
 		goto out;
 
+	fwd_skb->dev = sdata->dev;
 	fwd_hdr =  (struct ieee80211_hdr *) fwd_skb->data;
 	fwd_hdr->frame_control &= ~cpu_to_le16(IEEE80211_FCTL_RETRY);
 	info = IEEE80211_SKB_CB(fwd_skb);
@@ -4863,6 +4865,7 @@ void ieee80211_rx_list(struct ieee80211_hw *hw, struct ieee80211_sta *pubsta,
 	struct ieee80211_rate *rate = NULL;
 	struct ieee80211_supported_band *sband;
 	struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb);
+	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
 
 	WARN_ON_ONCE(softirq_count() == 0);
 
@@ -4959,9 +4962,9 @@ void ieee80211_rx_list(struct ieee80211_hw *hw, struct ieee80211_sta *pubsta,
 	if (!(status->flag & RX_FLAG_8023))
 		skb = ieee80211_rx_monitor(local, skb, rate);
 	if (skb) {
-		ieee80211_tpt_led_trig_rx(local,
-					  ((struct ieee80211_hdr *)skb->data)->frame_control,
-					  skb->len);
+		if ((status->flag & RX_FLAG_8023) ||
+			ieee80211_is_data_present(hdr->frame_control))
+			ieee80211_tpt_led_trig_rx(local, skb->len);
 
 		if (status->flag & RX_FLAG_8023)
 			__ieee80211_rx_handle_8023(hw, pubsta, skb, list);
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index 51b49f0d3ad4..537535a88990 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -644,13 +644,13 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU)
 	/* check if STA exists already */
 	if (sta_info_get_bss(sdata, sta->sta.addr)) {
 		err = -EEXIST;
-		goto out_err;
+		goto out_cleanup;
 	}
 
 	sinfo = kzalloc(sizeof(struct station_info), GFP_KERNEL);
 	if (!sinfo) {
 		err = -ENOMEM;
-		goto out_err;
+		goto out_cleanup;
 	}
 
 	local->num_sta++;
@@ -667,6 +667,15 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU)
 
 	list_add_tail_rcu(&sta->list, &local->sta_list);
 
+	/* update channel context before notifying the driver about state
+	 * change, this enables driver using the updated channel context right away.
+	 */
+	if (sta->sta_state >= IEEE80211_STA_ASSOC) {
+		ieee80211_recalc_min_chandef(sta->sdata);
+		if (!sta->sta.support_p2p_ps)
+			ieee80211_recalc_p2p_go_ps_allowed(sta->sdata);
+	}
+
 	/* notify driver */
 	err = sta_info_insert_drv_state(local, sdata, sta);
 	if (err)
@@ -674,12 +683,6 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU)
 
 	set_sta_flag(sta, WLAN_STA_INSERTED);
 
-	if (sta->sta_state >= IEEE80211_STA_ASSOC) {
-		ieee80211_recalc_min_chandef(sta->sdata);
-		if (!sta->sta.support_p2p_ps)
-			ieee80211_recalc_p2p_go_ps_allowed(sta->sdata);
-	}
-
 	/* accept BA sessions now */
 	clear_sta_flag(sta, WLAN_STA_BLOCK_BA);
 
@@ -706,8 +709,8 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU)
  out_drop_sta:
 	local->num_sta--;
 	synchronize_net();
+ out_cleanup:
 	cleanup_single_sta(sta);
- out_err:
 	mutex_unlock(&local->sta_mtx);
 	kfree(sinfo);
 	rcu_read_lock();
diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h
index ba2796782008..379fd367197f 100644
--- a/net/mac80211/sta_info.h
+++ b/net/mac80211/sta_info.h
@@ -176,6 +176,7 @@ struct sta_info;
  * @failed_bar_ssn: ssn of the last failed BAR tx attempt
  * @bar_pending: BAR needs to be re-sent
  * @amsdu: support A-MSDU withing A-MDPU
+ * @ssn: starting sequence number of the session
  *
  * This structure's lifetime is managed by RCU, assignments to
  * the array holding it must hold the aggregation mutex.
@@ -199,6 +200,7 @@ struct tid_ampdu_tx {
 	u8 stop_initiator;
 	bool tx_stop;
 	u16 buf_size;
+	u16 ssn;
 
 	u16 failed_bar_ssn;
 	bool bar_pending;
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index a756a197c770..86a54df3aabd 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -1721,21 +1721,19 @@ static bool ieee80211_tx_frags(struct ieee80211_local *local,
  * Returns false if the frame couldn't be transmitted but was queued instead.
  */
 static bool __ieee80211_tx(struct ieee80211_local *local,
-			   struct sk_buff_head *skbs, int led_len,
-			   struct sta_info *sta, bool txpending)
+			   struct sk_buff_head *skbs, struct sta_info *sta,
+			   bool txpending)
 {
 	struct ieee80211_tx_info *info;
 	struct ieee80211_sub_if_data *sdata;
 	struct ieee80211_vif *vif;
 	struct sk_buff *skb;
 	bool result;
-	__le16 fc;
 
 	if (WARN_ON(skb_queue_empty(skbs)))
 		return true;
 
 	skb = skb_peek(skbs);
-	fc = ((struct ieee80211_hdr *)skb->data)->frame_control;
 	info = IEEE80211_SKB_CB(skb);
 	sdata = vif_to_sdata(info->control.vif);
 	if (sta && !sta->uploaded)
@@ -1769,8 +1767,6 @@ static bool __ieee80211_tx(struct ieee80211_local *local,
 
 	result = ieee80211_tx_frags(local, vif, sta, skbs, txpending);
 
-	ieee80211_tpt_led_trig_tx(local, fc, led_len);
-
 	WARN_ON_ONCE(!skb_queue_empty(skbs));
 
 	return result;
@@ -1826,15 +1822,15 @@ static int invoke_tx_handlers_late(struct ieee80211_tx_data *tx)
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx->skb);
 	ieee80211_tx_result res = TX_CONTINUE;
 
+	if (!ieee80211_hw_check(&tx->local->hw, HAS_RATE_CONTROL))
+		CALL_TXH(ieee80211_tx_h_rate_ctrl);
+
 	if (unlikely(info->flags & IEEE80211_TX_INTFL_RETRANSMISSION)) {
 		__skb_queue_tail(&tx->skbs, tx->skb);
 		tx->skb = NULL;
 		goto txh_done;
 	}
 
-	if (!ieee80211_hw_check(&tx->local->hw, HAS_RATE_CONTROL))
-		CALL_TXH(ieee80211_tx_h_rate_ctrl);
-
 	CALL_TXH(ieee80211_tx_h_michael_mic_add);
 	CALL_TXH(ieee80211_tx_h_sequence);
 	CALL_TXH(ieee80211_tx_h_fragment);
@@ -1920,7 +1916,6 @@ static bool ieee80211_tx(struct ieee80211_sub_if_data *sdata,
 	ieee80211_tx_result res_prepare;
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
 	bool result = true;
-	int led_len;
 
 	if (unlikely(skb->len < 10)) {
 		dev_kfree_skb(skb);
@@ -1928,7 +1923,6 @@ static bool ieee80211_tx(struct ieee80211_sub_if_data *sdata,
 	}
 
 	/* initialises tx */
-	led_len = skb->len;
 	res_prepare = ieee80211_tx_prepare(sdata, &tx, sta, skb);
 
 	if (unlikely(res_prepare == TX_DROP)) {
@@ -1951,8 +1945,7 @@ static bool ieee80211_tx(struct ieee80211_sub_if_data *sdata,
 		return true;
 
 	if (!invoke_tx_handlers_late(&tx))
-		result = __ieee80211_tx(local, &tx.skbs, led_len,
-					tx.sta, txpending);
+		result = __ieee80211_tx(local, &tx.skbs, tx.sta, txpending);
 
 	return result;
 }
@@ -4175,6 +4168,7 @@ void __ieee80211_subif_start_xmit(struct sk_buff *skb,
 	struct ieee80211_local *local = sdata->local;
 	struct sta_info *sta;
 	struct sk_buff *next;
+	int len = skb->len;
 
 	if (unlikely(skb->len < ETH_HLEN)) {
 		kfree_skb(skb);
@@ -4197,11 +4191,11 @@ void __ieee80211_subif_start_xmit(struct sk_buff *skb,
 
 	ieee80211_aggr_check(sdata, sta, skb);
 
+	sk_pacing_shift_update(skb->sk, sdata->local->hw.tx_sk_pacing_shift);
+
 	if (sta) {
 		struct ieee80211_fast_tx *fast_tx;
 
-		sk_pacing_shift_update(skb->sk, sdata->local->hw.tx_sk_pacing_shift);
-
 		fast_tx = rcu_dereference(sta->fast_tx);
 
 		if (fast_tx &&
@@ -4221,10 +4215,8 @@ void __ieee80211_subif_start_xmit(struct sk_buff *skb,
 		}
 	} else {
 		/* we cannot process non-linear frames on this path */
-		if (skb_linearize(skb)) {
-			kfree_skb(skb);
-			goto out;
-		}
+		if (skb_linearize(skb))
+			goto out_free;
 
 		/* the frame could be fragmented, software-encrypted, and other
 		 * things so we cannot really handle checksum offload with it -
@@ -4258,7 +4250,10 @@ void __ieee80211_subif_start_xmit(struct sk_buff *skb,
 	goto out;
  out_free:
 	kfree_skb(skb);
+	len = 0;
  out:
+	if (len)
+		ieee80211_tpt_led_trig_tx(local, len);
 	rcu_read_unlock();
 }
 
@@ -4396,8 +4391,7 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb,
 }
 
 static bool ieee80211_tx_8023(struct ieee80211_sub_if_data *sdata,
-			      struct sk_buff *skb, int led_len,
-			      struct sta_info *sta,
+			      struct sk_buff *skb, struct sta_info *sta,
 			      bool txpending)
 {
 	struct ieee80211_local *local = sdata->local;
@@ -4410,6 +4404,8 @@ static bool ieee80211_tx_8023(struct ieee80211_sub_if_data *sdata,
 	if (sta)
 		sk_pacing_shift_update(skb->sk, local->hw.tx_sk_pacing_shift);
 
+	ieee80211_tpt_led_trig_tx(local, skb->len);
+
 	if (ieee80211_queue_skb(local, sdata, sta, skb))
 		return true;
 
@@ -4498,7 +4494,7 @@ static void ieee80211_8023_xmit(struct ieee80211_sub_if_data *sdata,
 	if (key)
 		info->control.hw_key = &key->conf;
 
-	ieee80211_tx_8023(sdata, skb, skb->len, sta, false);
+	ieee80211_tx_8023(sdata, skb, sta, false);
 
 	return;
 
@@ -4637,7 +4633,7 @@ static bool ieee80211_tx_pending_skb(struct ieee80211_local *local,
 		if (IS_ERR(sta) || (sta && !sta->uploaded))
 			sta = NULL;
 
-		result = ieee80211_tx_8023(sdata, skb, skb->len, sta, true);
+		result = ieee80211_tx_8023(sdata, skb, sta, true);
 	} else {
 		struct sk_buff_head skbs;
 
@@ -4647,7 +4643,7 @@ static bool ieee80211_tx_pending_skb(struct ieee80211_local *local,
 		hdr = (struct ieee80211_hdr *)skb->data;
 		sta = sta_info_get(sdata, hdr->addr1);
 
-		result = __ieee80211_tx(local, &skbs, skb->len, sta, true);
+		result = __ieee80211_tx(local, &skbs, sta, true);
 	}
 
 	return result;
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 39fa2a50385d..0e4e1956bcea 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -796,7 +796,7 @@ static void __iterate_interfaces(struct ieee80211_local *local,
 
 	sdata = rcu_dereference_check(local->monitor_sdata,
 				      lockdep_is_held(&local->iflist_mtx) ||
-				      lockdep_rtnl_is_held());
+				      lockdep_is_held(&local->hw.wiphy->mtx));
 	if (sdata &&
 	    (iter_flags & IEEE80211_IFACE_ITER_RESUME_ALL || !active_only ||
 	     sdata->flags & IEEE80211_SDATA_IN_DRIVER))
@@ -943,7 +943,12 @@ static void ieee80211_parse_extension_element(u32 *crc,
 					      struct ieee802_11_elems *elems)
 {
 	const void *data = elem->data + 1;
-	u8 len = elem->datalen - 1;
+	u8 len;
+
+	if (!elem->datalen)
+		return;
+
+	len = elem->datalen - 1;
 
 	switch (elem->data[0]) {
 	case WLAN_EID_EXT_HE_MU_EDCA:
@@ -2063,7 +2068,7 @@ struct sk_buff *ieee80211_build_probe_req(struct ieee80211_sub_if_data *sdata,
 		chandef.chan = chan;
 
 	skb = ieee80211_probereq_get(&local->hw, src, ssid, ssid_len,
-				     100 + ie_len);
+				     local->scan_ies_len + ie_len);
 	if (!skb)
 		return NULL;
 
@@ -2381,7 +2386,7 @@ int ieee80211_reconfig(struct ieee80211_local *local)
 				   IEEE80211_TPT_LEDTRIG_FL_RADIO, 0);
 
 	/* add interfaces */
-	sdata = rtnl_dereference(local->monitor_sdata);
+	sdata = wiphy_dereference(local->hw.wiphy, local->monitor_sdata);
 	if (sdata) {
 		/* in HW restart it exists already */
 		WARN_ON(local->resuming);
@@ -2426,7 +2431,8 @@ int ieee80211_reconfig(struct ieee80211_local *local)
 				WARN_ON(drv_add_chanctx(local, ctx));
 		mutex_unlock(&local->chanctx_mtx);
 
-		sdata = rtnl_dereference(local->monitor_sdata);
+		sdata = wiphy_dereference(local->hw.wiphy,
+					  local->monitor_sdata);
 		if (sdata && ieee80211_sdata_running(sdata))
 			ieee80211_assign_chanctx(local, sdata);
 	}
@@ -2645,6 +2651,13 @@ int ieee80211_reconfig(struct ieee80211_local *local)
 		mutex_unlock(&local->sta_mtx);
 	}
 
+	/*
+	 * If this is for hw restart things are still running.
+	 * We may want to change that later, however.
+	 */
+	if (local->open_count && (!suspended || reconfig_due_to_wowlan))
+		drv_reconfig_complete(local, IEEE80211_RECONFIG_TYPE_RESTART);
+
 	if (local->in_reconfig) {
 		local->in_reconfig = false;
 		barrier();
@@ -2663,13 +2676,6 @@ int ieee80211_reconfig(struct ieee80211_local *local)
 					IEEE80211_QUEUE_STOP_REASON_SUSPEND,
 					false);
 
-	/*
-	 * If this is for hw restart things are still running.
-	 * We may want to change that later, however.
-	 */
-	if (local->open_count && (!suspended || reconfig_due_to_wowlan))
-		drv_reconfig_complete(local, IEEE80211_RECONFIG_TYPE_RESTART);
-
 	if (!suspended)
 		return 0;
 
diff --git a/net/mac80211/wme.c b/net/mac80211/wme.c
index 9ea6004abe1b..62c6733e0792 100644
--- a/net/mac80211/wme.c
+++ b/net/mac80211/wme.c
@@ -143,7 +143,6 @@ u16 ieee80211_select_queue_80211(struct ieee80211_sub_if_data *sdata,
 u16 __ieee80211_select_queue(struct ieee80211_sub_if_data *sdata,
 			     struct sta_info *sta, struct sk_buff *skb)
 {
-	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
 	struct mac80211_qos_map *qos_map;
 	bool qos;
 
@@ -156,7 +155,7 @@ u16 __ieee80211_select_queue(struct ieee80211_sub_if_data *sdata,
 	else
 		qos = false;
 
-	if (!qos || (info->control.flags & IEEE80211_TX_CTRL_DONT_REORDER)) {
+	if (!qos) {
 		skb->priority = 0; /* required for correct WPA/11i MIC */
 		return IEEE80211_AC_BE;
 	}
diff --git a/net/mctp/neigh.c b/net/mctp/neigh.c
index 5cc042121493..6ad3e33bd4d4 100644
--- a/net/mctp/neigh.c
+++ b/net/mctp/neigh.c
@@ -85,8 +85,8 @@ void mctp_neigh_remove_dev(struct mctp_dev *mdev)
 	mutex_unlock(&net->mctp.neigh_lock);
 }
 
-// TODO: add a "source" flag so netlink can only delete static neighbours?
-static int mctp_neigh_remove(struct mctp_dev *mdev, mctp_eid_t eid)
+static int mctp_neigh_remove(struct mctp_dev *mdev, mctp_eid_t eid,
+			     enum mctp_neigh_source source)
 {
 	struct net *net = dev_net(mdev->dev);
 	struct mctp_neigh *neigh, *tmp;
@@ -94,7 +94,8 @@ static int mctp_neigh_remove(struct mctp_dev *mdev, mctp_eid_t eid)
 
 	mutex_lock(&net->mctp.neigh_lock);
 	list_for_each_entry_safe(neigh, tmp, &net->mctp.neighbours, list) {
-		if (neigh->dev == mdev && neigh->eid == eid) {
+		if (neigh->dev == mdev && neigh->eid == eid &&
+		    neigh->source == source) {
 			list_del_rcu(&neigh->list);
 			/* TODO: immediate RTM_DELNEIGH */
 			call_rcu(&neigh->rcu, __mctp_neigh_free);
@@ -202,7 +203,7 @@ static int mctp_rtm_delneigh(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (!mdev)
 		return -ENODEV;
 
-	return mctp_neigh_remove(mdev, eid);
+	return mctp_neigh_remove(mdev, eid, MCTP_NEIGH_STATIC);
 }
 
 static int mctp_fill_neigh(struct sk_buff *skb, u32 portid, u32 seq, int event,
diff --git a/net/mctp/route.c b/net/mctp/route.c
index 46c44823edb7..cdf09c2a7007 100644
--- a/net/mctp/route.c
+++ b/net/mctp/route.c
@@ -952,7 +952,7 @@ static int mctp_route_add(struct mctp_dev *mdev, mctp_eid_t daddr_start,
 }
 
 static int mctp_route_remove(struct mctp_dev *mdev, mctp_eid_t daddr_start,
-			     unsigned int daddr_extent)
+			     unsigned int daddr_extent, unsigned char type)
 {
 	struct net *net = dev_net(mdev->dev);
 	struct mctp_route *rt, *tmp;
@@ -969,7 +969,8 @@ static int mctp_route_remove(struct mctp_dev *mdev, mctp_eid_t daddr_start,
 
 	list_for_each_entry_safe(rt, tmp, &net->mctp.routes, list) {
 		if (rt->dev == mdev &&
-		    rt->min == daddr_start && rt->max == daddr_end) {
+		    rt->min == daddr_start && rt->max == daddr_end &&
+		    rt->type == type) {
 			list_del_rcu(&rt->list);
 			/* TODO: immediate RTM_DELROUTE */
 			mctp_route_release(rt);
@@ -987,7 +988,7 @@ int mctp_route_add_local(struct mctp_dev *mdev, mctp_eid_t addr)
 
 int mctp_route_remove_local(struct mctp_dev *mdev, mctp_eid_t addr)
 {
-	return mctp_route_remove(mdev, addr, 0);
+	return mctp_route_remove(mdev, addr, 0, RTN_LOCAL);
 }
 
 /* removes all entries for a given device */
@@ -1195,7 +1196,7 @@ static int mctp_delroute(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (rtm->rtm_type != RTN_UNICAST)
 		return -EINVAL;
 
-	rc = mctp_route_remove(mdev, daddr_start, rtm->rtm_dst_len);
+	rc = mctp_route_remove(mdev, daddr_start, rtm->rtm_dst_len, RTN_UNICAST);
 	return rc;
 }
 
diff --git a/net/mctp/test/utils.c b/net/mctp/test/utils.c
index cc6b8803aa9d..7b7918702592 100644
--- a/net/mctp/test/utils.c
+++ b/net/mctp/test/utils.c
@@ -12,7 +12,7 @@
 static netdev_tx_t mctp_test_dev_tx(struct sk_buff *skb,
 				    struct net_device *ndev)
 {
-	kfree(skb);
+	kfree_skb(skb);
 	return NETDEV_TX_OK;
 }
 
diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index ffeb2df8be7a..0c7bde1c14a6 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -409,7 +409,7 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev,
 		goto err;
 
 	/* Find the output device */
-	out_dev = rcu_dereference(nh->nh_dev);
+	out_dev = nh->nh_dev;
 	if (!mpls_output_possible(out_dev))
 		goto tx_err;
 
@@ -698,7 +698,7 @@ static int mpls_nh_assign_dev(struct net *net, struct mpls_route *rt,
 	    (dev->addr_len != nh->nh_via_alen))
 		goto errout;
 
-	RCU_INIT_POINTER(nh->nh_dev, dev);
+	nh->nh_dev = dev;
 
 	if (!(dev->flags & IFF_UP)) {
 		nh->nh_flags |= RTNH_F_DEAD;
@@ -1491,26 +1491,53 @@ static void mpls_dev_destroy_rcu(struct rcu_head *head)
 	kfree(mdev);
 }
 
-static void mpls_ifdown(struct net_device *dev, int event)
+static int mpls_ifdown(struct net_device *dev, int event)
 {
 	struct mpls_route __rcu **platform_label;
 	struct net *net = dev_net(dev);
-	u8 alive, deleted;
 	unsigned index;
 
 	platform_label = rtnl_dereference(net->mpls.platform_label);
 	for (index = 0; index < net->mpls.platform_labels; index++) {
 		struct mpls_route *rt = rtnl_dereference(platform_label[index]);
+		bool nh_del = false;
+		u8 alive = 0;
 
 		if (!rt)
 			continue;
 
-		alive = 0;
-		deleted = 0;
+		if (event == NETDEV_UNREGISTER) {
+			u8 deleted = 0;
+
+			for_nexthops(rt) {
+				if (!nh->nh_dev || nh->nh_dev == dev)
+					deleted++;
+				if (nh->nh_dev == dev)
+					nh_del = true;
+			} endfor_nexthops(rt);
+
+			/* if there are no more nexthops, delete the route */
+			if (deleted == rt->rt_nhn) {
+				mpls_route_update(net, index, NULL, NULL);
+				continue;
+			}
+
+			if (nh_del) {
+				size_t size = sizeof(*rt) + rt->rt_nhn *
+					rt->rt_nh_size;
+				struct mpls_route *orig = rt;
+
+				rt = kmalloc(size, GFP_KERNEL);
+				if (!rt)
+					return -ENOMEM;
+				memcpy(rt, orig, size);
+			}
+		}
+
 		change_nexthops(rt) {
 			unsigned int nh_flags = nh->nh_flags;
 
-			if (rtnl_dereference(nh->nh_dev) != dev)
+			if (nh->nh_dev != dev)
 				goto next;
 
 			switch (event) {
@@ -1523,23 +1550,22 @@ static void mpls_ifdown(struct net_device *dev, int event)
 				break;
 			}
 			if (event == NETDEV_UNREGISTER)
-				RCU_INIT_POINTER(nh->nh_dev, NULL);
+				nh->nh_dev = NULL;
 
 			if (nh->nh_flags != nh_flags)
 				WRITE_ONCE(nh->nh_flags, nh_flags);
 next:
 			if (!(nh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN)))
 				alive++;
-			if (!rtnl_dereference(nh->nh_dev))
-				deleted++;
 		} endfor_nexthops(rt);
 
 		WRITE_ONCE(rt->rt_nhn_alive, alive);
 
-		/* if there are no more nexthops, delete the route */
-		if (event == NETDEV_UNREGISTER && deleted == rt->rt_nhn)
-			mpls_route_update(net, index, NULL, NULL);
+		if (nh_del)
+			mpls_route_update(net, index, rt, NULL);
 	}
+
+	return 0;
 }
 
 static void mpls_ifup(struct net_device *dev, unsigned int flags)
@@ -1559,14 +1585,12 @@ static void mpls_ifup(struct net_device *dev, unsigned int flags)
 		alive = 0;
 		change_nexthops(rt) {
 			unsigned int nh_flags = nh->nh_flags;
-			struct net_device *nh_dev =
-				rtnl_dereference(nh->nh_dev);
 
 			if (!(nh_flags & flags)) {
 				alive++;
 				continue;
 			}
-			if (nh_dev != dev)
+			if (nh->nh_dev != dev)
 				continue;
 			alive++;
 			nh_flags &= ~flags;
@@ -1597,8 +1621,12 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event,
 		return NOTIFY_OK;
 
 	switch (event) {
+		int err;
+
 	case NETDEV_DOWN:
-		mpls_ifdown(dev, event);
+		err = mpls_ifdown(dev, event);
+		if (err)
+			return notifier_from_errno(err);
 		break;
 	case NETDEV_UP:
 		flags = dev_get_flags(dev);
@@ -1609,13 +1637,18 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event,
 		break;
 	case NETDEV_CHANGE:
 		flags = dev_get_flags(dev);
-		if (flags & (IFF_RUNNING | IFF_LOWER_UP))
+		if (flags & (IFF_RUNNING | IFF_LOWER_UP)) {
 			mpls_ifup(dev, RTNH_F_DEAD | RTNH_F_LINKDOWN);
-		else
-			mpls_ifdown(dev, event);
+		} else {
+			err = mpls_ifdown(dev, event);
+			if (err)
+				return notifier_from_errno(err);
+		}
 		break;
 	case NETDEV_UNREGISTER:
-		mpls_ifdown(dev, event);
+		err = mpls_ifdown(dev, event);
+		if (err)
+			return notifier_from_errno(err);
 		mdev = mpls_dev_get(dev);
 		if (mdev) {
 			mpls_dev_sysctl_unregister(dev, mdev);
@@ -1626,8 +1659,6 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event,
 	case NETDEV_CHANGENAME:
 		mdev = mpls_dev_get(dev);
 		if (mdev) {
-			int err;
-
 			mpls_dev_sysctl_unregister(dev, mdev);
 			err = mpls_dev_sysctl_register(dev, mdev);
 			if (err)
@@ -1994,7 +2025,7 @@ static int mpls_dump_route(struct sk_buff *skb, u32 portid, u32 seq, int event,
 		    nla_put_via(skb, nh->nh_via_table, mpls_nh_via(rt, nh),
 				nh->nh_via_alen))
 			goto nla_put_failure;
-		dev = rtnl_dereference(nh->nh_dev);
+		dev = nh->nh_dev;
 		if (dev && nla_put_u32(skb, RTA_OIF, dev->ifindex))
 			goto nla_put_failure;
 		if (nh->nh_flags & RTNH_F_LINKDOWN)
@@ -2012,7 +2043,7 @@ static int mpls_dump_route(struct sk_buff *skb, u32 portid, u32 seq, int event,
 			goto nla_put_failure;
 
 		for_nexthops(rt) {
-			dev = rtnl_dereference(nh->nh_dev);
+			dev = nh->nh_dev;
 			if (!dev)
 				continue;
 
@@ -2123,18 +2154,14 @@ static int mpls_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh,
 static bool mpls_rt_uses_dev(struct mpls_route *rt,
 			     const struct net_device *dev)
 {
-	struct net_device *nh_dev;
-
 	if (rt->rt_nhn == 1) {
 		struct mpls_nh *nh = rt->rt_nh;
 
-		nh_dev = rtnl_dereference(nh->nh_dev);
-		if (dev == nh_dev)
+		if (nh->nh_dev == dev)
 			return true;
 	} else {
 		for_nexthops(rt) {
-			nh_dev = rtnl_dereference(nh->nh_dev);
-			if (nh_dev == dev)
+			if (nh->nh_dev == dev)
 				return true;
 		} endfor_nexthops(rt);
 	}
@@ -2222,7 +2249,7 @@ static inline size_t lfib_nlmsg_size(struct mpls_route *rt)
 		size_t nhsize = 0;
 
 		for_nexthops(rt) {
-			if (!rtnl_dereference(nh->nh_dev))
+			if (!nh->nh_dev)
 				continue;
 			nhsize += nla_total_size(sizeof(struct rtnexthop));
 			/* RTA_VIA */
@@ -2468,7 +2495,7 @@ static int mpls_getroute(struct sk_buff *in_skb, struct nlmsghdr *in_nlh,
 	    nla_put_via(skb, nh->nh_via_table, mpls_nh_via(rt, nh),
 			nh->nh_via_alen))
 		goto nla_put_failure;
-	dev = rtnl_dereference(nh->nh_dev);
+	dev = nh->nh_dev;
 	if (dev && nla_put_u32(skb, RTA_OIF, dev->ifindex))
 		goto nla_put_failure;
 
@@ -2507,7 +2534,7 @@ static int resize_platform_label_table(struct net *net, size_t limit)
 		rt0 = mpls_rt_alloc(1, lo->addr_len, 0);
 		if (IS_ERR(rt0))
 			goto nort0;
-		RCU_INIT_POINTER(rt0->rt_nh->nh_dev, lo);
+		rt0->rt_nh->nh_dev = lo;
 		rt0->rt_protocol = RTPROT_KERNEL;
 		rt0->rt_payload_type = MPT_IPV4;
 		rt0->rt_ttl_propagate = MPLS_TTL_PROP_DEFAULT;
@@ -2521,7 +2548,7 @@ static int resize_platform_label_table(struct net *net, size_t limit)
 		rt2 = mpls_rt_alloc(1, lo->addr_len, 0);
 		if (IS_ERR(rt2))
 			goto nort2;
-		RCU_INIT_POINTER(rt2->rt_nh->nh_dev, lo);
+		rt2->rt_nh->nh_dev = lo;
 		rt2->rt_protocol = RTPROT_KERNEL;
 		rt2->rt_payload_type = MPT_IPV6;
 		rt2->rt_ttl_propagate = MPLS_TTL_PROP_DEFAULT;
diff --git a/net/mpls/internal.h b/net/mpls/internal.h
index 838cdfc10e47..893df00b77b6 100644
--- a/net/mpls/internal.h
+++ b/net/mpls/internal.h
@@ -87,7 +87,7 @@ enum mpls_payload_type {
 };
 
 struct mpls_nh { /* next hop label forwarding entry */
-	struct net_device __rcu *nh_dev;
+	struct net_device	*nh_dev;
 
 	/* nh_flags is accessed under RCU in the packet path; it is
 	 * modified handling netdev events with rtnl lock held
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index 7c3420afb1a0..fe98e4f475ba 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -422,28 +422,6 @@ bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb,
 	return false;
 }
 
-/* MP_JOIN client subflow must wait for 4th ack before sending any data:
- * TCP can't schedule delack timer before the subflow is fully established.
- * MPTCP uses the delack timer to do 3rd ack retransmissions
- */
-static void schedule_3rdack_retransmission(struct sock *sk)
-{
-	struct inet_connection_sock *icsk = inet_csk(sk);
-	struct tcp_sock *tp = tcp_sk(sk);
-	unsigned long timeout;
-
-	/* reschedule with a timeout above RTT, as we must look only for drop */
-	if (tp->srtt_us)
-		timeout = tp->srtt_us << 1;
-	else
-		timeout = TCP_TIMEOUT_INIT;
-
-	WARN_ON_ONCE(icsk->icsk_ack.pending & ICSK_ACK_TIMER);
-	icsk->icsk_ack.pending |= ICSK_ACK_SCHED | ICSK_ACK_TIMER;
-	icsk->icsk_ack.timeout = timeout;
-	sk_reset_timer(sk, &icsk->icsk_delack_timer, timeout);
-}
-
 static void clear_3rdack_retransmission(struct sock *sk)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
@@ -526,7 +504,15 @@ static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb,
 		*size = TCPOLEN_MPTCP_MPJ_ACK;
 		pr_debug("subflow=%p", subflow);
 
-		schedule_3rdack_retransmission(sk);
+		/* we can use the full delegate action helper only from BH context
+		 * If we are in process context - sk is flushing the backlog at
+		 * socket lock release time - just set the appropriate flag, will
+		 * be handled by the release callback
+		 */
+		if (sock_owned_by_user(sk))
+			set_bit(MPTCP_DELEGATE_ACK, &subflow->delegated_status);
+		else
+			mptcp_subflow_delegate(subflow, MPTCP_DELEGATE_ACK);
 		return true;
 	}
 	return false;
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 7b96be1e9f14..f523051f5aef 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -700,6 +700,9 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk,
 
 	msk_owned_by_me(msk);
 
+	if (sk->sk_state == TCP_LISTEN)
+		return;
+
 	if (!rm_list->nr)
 		return;
 
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index b7e32e316738..54613f5b7521 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1524,7 +1524,7 @@ void __mptcp_push_pending(struct sock *sk, unsigned int flags)
 			int ret = 0;
 
 			prev_ssk = ssk;
-			mptcp_flush_join_list(msk);
+			__mptcp_flush_join_list(msk);
 			ssk = mptcp_subflow_get_send(msk);
 
 			/* First check. If the ssk has changed since
@@ -1596,7 +1596,8 @@ static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk)
 			if (!xmit_ssk)
 				goto out;
 			if (xmit_ssk != ssk) {
-				mptcp_subflow_delegate(mptcp_subflow_ctx(xmit_ssk));
+				mptcp_subflow_delegate(mptcp_subflow_ctx(xmit_ssk),
+						       MPTCP_DELEGATE_SEND);
 				goto out;
 			}
 
@@ -2878,7 +2879,7 @@ static struct sock *mptcp_accept(struct sock *sk, int flags, int *err,
 		 */
 		if (WARN_ON_ONCE(!new_mptcp_sock)) {
 			tcp_sk(newsk)->is_mptcp = 0;
-			return newsk;
+			goto out;
 		}
 
 		/* acquire the 2nd reference for the owning socket */
@@ -2890,6 +2891,8 @@ static struct sock *mptcp_accept(struct sock *sk, int flags, int *err,
 				MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK);
 	}
 
+out:
+	newsk->sk_kern_sock = kern;
 	return newsk;
 }
 
@@ -2943,7 +2946,7 @@ void __mptcp_check_push(struct sock *sk, struct sock *ssk)
 		if (xmit_ssk == ssk)
 			__mptcp_subflow_push_pending(sk, ssk);
 		else if (xmit_ssk)
-			mptcp_subflow_delegate(mptcp_subflow_ctx(xmit_ssk));
+			mptcp_subflow_delegate(mptcp_subflow_ctx(xmit_ssk), MPTCP_DELEGATE_SEND);
 	} else {
 		set_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->flags);
 	}
@@ -2993,18 +2996,50 @@ static void mptcp_release_cb(struct sock *sk)
 	__mptcp_update_rmem(sk);
 }
 
+/* MP_JOIN client subflow must wait for 4th ack before sending any data:
+ * TCP can't schedule delack timer before the subflow is fully established.
+ * MPTCP uses the delack timer to do 3rd ack retransmissions
+ */
+static void schedule_3rdack_retransmission(struct sock *ssk)
+{
+	struct inet_connection_sock *icsk = inet_csk(ssk);
+	struct tcp_sock *tp = tcp_sk(ssk);
+	unsigned long timeout;
+
+	if (mptcp_subflow_ctx(ssk)->fully_established)
+		return;
+
+	/* reschedule with a timeout above RTT, as we must look only for drop */
+	if (tp->srtt_us)
+		timeout = usecs_to_jiffies(tp->srtt_us >> (3 - 1));
+	else
+		timeout = TCP_TIMEOUT_INIT;
+	timeout += jiffies;
+
+	WARN_ON_ONCE(icsk->icsk_ack.pending & ICSK_ACK_TIMER);
+	icsk->icsk_ack.pending |= ICSK_ACK_SCHED | ICSK_ACK_TIMER;
+	icsk->icsk_ack.timeout = timeout;
+	sk_reset_timer(ssk, &icsk->icsk_delack_timer, timeout);
+}
+
 void mptcp_subflow_process_delegated(struct sock *ssk)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
 	struct sock *sk = subflow->conn;
 
-	mptcp_data_lock(sk);
-	if (!sock_owned_by_user(sk))
-		__mptcp_subflow_push_pending(sk, ssk);
-	else
-		set_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->flags);
-	mptcp_data_unlock(sk);
-	mptcp_subflow_delegated_done(subflow);
+	if (test_bit(MPTCP_DELEGATE_SEND, &subflow->delegated_status)) {
+		mptcp_data_lock(sk);
+		if (!sock_owned_by_user(sk))
+			__mptcp_subflow_push_pending(sk, ssk);
+		else
+			set_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->flags);
+		mptcp_data_unlock(sk);
+		mptcp_subflow_delegated_done(subflow, MPTCP_DELEGATE_SEND);
+	}
+	if (test_bit(MPTCP_DELEGATE_ACK, &subflow->delegated_status)) {
+		schedule_3rdack_retransmission(ssk);
+		mptcp_subflow_delegated_done(subflow, MPTCP_DELEGATE_ACK);
+	}
 }
 
 static int mptcp_hash(struct sock *sk)
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 67a61ac48b20..d87cc040352e 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -387,6 +387,7 @@ struct mptcp_delegated_action {
 DECLARE_PER_CPU(struct mptcp_delegated_action, mptcp_delegated_actions);
 
 #define MPTCP_DELEGATE_SEND		0
+#define MPTCP_DELEGATE_ACK		1
 
 /* MPTCP subflow context */
 struct mptcp_subflow_context {
@@ -492,23 +493,23 @@ static inline void mptcp_add_pending_subflow(struct mptcp_sock *msk,
 
 void mptcp_subflow_process_delegated(struct sock *ssk);
 
-static inline void mptcp_subflow_delegate(struct mptcp_subflow_context *subflow)
+static inline void mptcp_subflow_delegate(struct mptcp_subflow_context *subflow, int action)
 {
 	struct mptcp_delegated_action *delegated;
 	bool schedule;
 
+	/* the caller held the subflow bh socket lock */
+	lockdep_assert_in_softirq();
+
 	/* The implied barrier pairs with mptcp_subflow_delegated_done(), and
 	 * ensures the below list check sees list updates done prior to status
 	 * bit changes
 	 */
-	if (!test_and_set_bit(MPTCP_DELEGATE_SEND, &subflow->delegated_status)) {
+	if (!test_and_set_bit(action, &subflow->delegated_status)) {
 		/* still on delegated list from previous scheduling */
 		if (!list_empty(&subflow->delegated_node))
 			return;
 
-		/* the caller held the subflow bh socket lock */
-		lockdep_assert_in_softirq();
-
 		delegated = this_cpu_ptr(&mptcp_delegated_actions);
 		schedule = list_empty(&delegated->head);
 		list_add_tail(&subflow->delegated_node, &delegated->head);
@@ -533,16 +534,16 @@ mptcp_subflow_delegated_next(struct mptcp_delegated_action *delegated)
 
 static inline bool mptcp_subflow_has_delegated_action(const struct mptcp_subflow_context *subflow)
 {
-	return test_bit(MPTCP_DELEGATE_SEND, &subflow->delegated_status);
+	return !!READ_ONCE(subflow->delegated_status);
 }
 
-static inline void mptcp_subflow_delegated_done(struct mptcp_subflow_context *subflow)
+static inline void mptcp_subflow_delegated_done(struct mptcp_subflow_context *subflow, int action)
 {
 	/* pairs with mptcp_subflow_delegate, ensures delegate_node is updated before
 	 * touching the status bit
 	 */
 	smp_wmb();
-	clear_bit(MPTCP_DELEGATE_SEND, &subflow->delegated_status);
+	clear_bit(action, &subflow->delegated_status);
 }
 
 int mptcp_is_enabled(const struct net *net);
diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c
index 0f1e661c2032..f8efd478ac97 100644
--- a/net/mptcp/sockopt.c
+++ b/net/mptcp/sockopt.c
@@ -525,7 +525,6 @@ static bool mptcp_supported_sockopt(int level, int optname)
 		case TCP_NODELAY:
 		case TCP_THIN_LINEAR_TIMEOUTS:
 		case TCP_CONGESTION:
-		case TCP_ULP:
 		case TCP_CORK:
 		case TCP_KEEPIDLE:
 		case TCP_KEEPINTVL:
diff --git a/net/ncsi/ncsi-cmd.c b/net/ncsi/ncsi-cmd.c
index ba9ae482141b..dda8b76b7798 100644
--- a/net/ncsi/ncsi-cmd.c
+++ b/net/ncsi/ncsi-cmd.c
@@ -18,6 +18,8 @@
 #include "internal.h"
 #include "ncsi-pkt.h"
 
+static const int padding_bytes = 26;
+
 u32 ncsi_calculate_checksum(unsigned char *data, int len)
 {
 	u32 checksum = 0;
@@ -213,12 +215,17 @@ static int ncsi_cmd_handler_oem(struct sk_buff *skb,
 {
 	struct ncsi_cmd_oem_pkt *cmd;
 	unsigned int len;
+	int payload;
+	/* NC-SI spec DSP_0222_1.2.0, section 8.2.2.2
+	 * requires payload to be padded with 0 to
+	 * 32-bit boundary before the checksum field.
+	 * Ensure the padding bytes are accounted for in
+	 * skb allocation
+	 */
 
+	payload = ALIGN(nca->payload, 4);
 	len = sizeof(struct ncsi_cmd_pkt_hdr) + 4;
-	if (nca->payload < 26)
-		len += 26;
-	else
-		len += nca->payload;
+	len += max(payload, padding_bytes);
 
 	cmd = skb_put_zero(skb, len);
 	memcpy(&cmd->mfr_id, nca->data, nca->payload);
@@ -272,6 +279,7 @@ static struct ncsi_request *ncsi_alloc_command(struct ncsi_cmd_arg *nca)
 	struct net_device *dev = nd->dev;
 	int hlen = LL_RESERVED_SPACE(dev);
 	int tlen = dev->needed_tailroom;
+	int payload;
 	int len = hlen + tlen;
 	struct sk_buff *skb;
 	struct ncsi_request *nr;
@@ -281,14 +289,14 @@ static struct ncsi_request *ncsi_alloc_command(struct ncsi_cmd_arg *nca)
 		return NULL;
 
 	/* NCSI command packet has 16-bytes header, payload, 4 bytes checksum.
+	 * Payload needs padding so that the checksum field following payload is
+	 * aligned to 32-bit boundary.
 	 * The packet needs padding if its payload is less than 26 bytes to
 	 * meet 64 bytes minimal ethernet frame length.
 	 */
 	len += sizeof(struct ncsi_cmd_pkt_hdr) + 4;
-	if (nca->payload < 26)
-		len += 26;
-	else
-		len += nca->payload;
+	payload = ALIGN(nca->payload, 4);
+	len += max(payload, padding_bytes);
 
 	/* Allocate skb */
 	skb = alloc_skb(len, GFP_ATOMIC);
diff --git a/net/ncsi/ncsi-netlink.c b/net/ncsi/ncsi-netlink.c
index bb5f1650f11c..c189b4c8a182 100644
--- a/net/ncsi/ncsi-netlink.c
+++ b/net/ncsi/ncsi-netlink.c
@@ -112,7 +112,11 @@ static int ncsi_write_package_info(struct sk_buff *skb,
 		pnest = nla_nest_start_noflag(skb, NCSI_PKG_ATTR);
 		if (!pnest)
 			return -ENOMEM;
-		nla_put_u32(skb, NCSI_PKG_ATTR_ID, np->id);
+		rc = nla_put_u32(skb, NCSI_PKG_ATTR_ID, np->id);
+		if (rc) {
+			nla_nest_cancel(skb, pnest);
+			return rc;
+		}
 		if ((0x1 << np->id) == ndp->package_whitelist)
 			nla_put_flag(skb, NCSI_PKG_ATTR_FORCED);
 		cnest = nla_nest_start_noflag(skb, NCSI_PKG_ATTR_CHANNEL_LIST);
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index e93c937a8bf0..51ad557a525b 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1919,7 +1919,6 @@ ip_vs_in_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state
 	struct ip_vs_proto_data *pd;
 	struct ip_vs_conn *cp;
 	int ret, pkts;
-	int conn_reuse_mode;
 	struct sock *sk;
 	int af = state->pf;
 
@@ -1997,15 +1996,16 @@ ip_vs_in_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state
 	cp = INDIRECT_CALL_1(pp->conn_in_get, ip_vs_conn_in_get_proto,
 			     ipvs, af, skb, &iph);
 
-	conn_reuse_mode = sysctl_conn_reuse_mode(ipvs);
-	if (conn_reuse_mode && !iph.fragoffs && is_new_conn(skb, &iph) && cp) {
+	if (!iph.fragoffs && is_new_conn(skb, &iph) && cp) {
+		int conn_reuse_mode = sysctl_conn_reuse_mode(ipvs);
 		bool old_ct = false, resched = false;
 
 		if (unlikely(sysctl_expire_nodest_conn(ipvs)) && cp->dest &&
 		    unlikely(!atomic_read(&cp->dest->weight))) {
 			resched = true;
 			old_ct = ip_vs_conn_uses_old_conntrack(cp, skb);
-		} else if (is_new_conn_expected(cp, conn_reuse_mode)) {
+		} else if (conn_reuse_mode &&
+			   is_new_conn_expected(cp, conn_reuse_mode)) {
 			old_ct = ip_vs_conn_uses_old_conntrack(cp, skb);
 			if (!atomic_read(&cp->n_control)) {
 				resched = true;
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 770a63103c7a..4712a90a1820 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -684,7 +684,7 @@ bool nf_ct_delete(struct nf_conn *ct, u32 portid, int report)
 
 	tstamp = nf_conn_tstamp_find(ct);
 	if (tstamp) {
-		s32 timeout = ct->timeout - nfct_time_stamp;
+		s32 timeout = READ_ONCE(ct->timeout) - nfct_time_stamp;
 
 		tstamp->stop = ktime_get_real_ns();
 		if (timeout < 0)
@@ -1036,7 +1036,7 @@ static int nf_ct_resolve_clash_harder(struct sk_buff *skb, u32 repl_idx)
 	}
 
 	/* We want the clashing entry to go away real soon: 1 second timeout. */
-	loser_ct->timeout = nfct_time_stamp + HZ;
+	WRITE_ONCE(loser_ct->timeout, nfct_time_stamp + HZ);
 
 	/* IPS_NAT_CLASH removes the entry automatically on the first
 	 * reply.  Also prevents UDP tracker from moving the entry to
@@ -1560,7 +1560,7 @@ __nf_conntrack_alloc(struct net *net,
 	/* save hash for reusing when confirming */
 	*(unsigned long *)(&ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev) = hash;
 	ct->status = 0;
-	ct->timeout = 0;
+	WRITE_ONCE(ct->timeout, 0);
 	write_pnet(&ct->ct_net, net);
 	memset(&ct->__nfct_init_offset, 0,
 	       offsetof(struct nf_conn, proto) -
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index f1e5443fe7c7..ec4164c32d27 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -1011,11 +1011,9 @@ ctnetlink_alloc_filter(const struct nlattr * const cda[], u8 family)
 						   CTA_TUPLE_REPLY,
 						   filter->family,
 						   &filter->zone,
-						   filter->orig_flags);
-		if (err < 0) {
-			err = -EINVAL;
+						   filter->reply_flags);
+		if (err < 0)
 			goto err_filter;
-		}
 	}
 
 	return filter;
@@ -1197,8 +1195,6 @@ restart:
 		}
 		hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[cb->args[0]],
 					   hnnode) {
-			if (NF_CT_DIRECTION(h) != IP_CT_DIR_ORIGINAL)
-				continue;
 			ct = nf_ct_tuplehash_to_ctrack(h);
 			if (nf_ct_is_expired(ct)) {
 				if (i < ARRAY_SIZE(nf_ct_evict) &&
@@ -1210,6 +1206,9 @@ restart:
 			if (!net_eq(net, nf_ct_net(ct)))
 				continue;
 
+			if (NF_CT_DIRECTION(h) != IP_CT_DIR_ORIGINAL)
+				continue;
+
 			if (cb->args[1]) {
 				if (ct != last)
 					continue;
@@ -2000,7 +1999,7 @@ static int ctnetlink_change_timeout(struct nf_conn *ct,
 
 	if (timeout > INT_MAX)
 		timeout = INT_MAX;
-	ct->timeout = nfct_time_stamp + (u32)timeout;
+	WRITE_ONCE(ct->timeout, nfct_time_stamp + (u32)timeout);
 
 	if (test_bit(IPS_DYING_BIT, &ct->status))
 		return -ETIME;
diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c
index 87a7388b6c89..ed37bb9b4e58 100644
--- a/net/netfilter/nf_flow_table_core.c
+++ b/net/netfilter/nf_flow_table_core.c
@@ -201,8 +201,8 @@ static void flow_offload_fixup_ct_timeout(struct nf_conn *ct)
 	if (timeout < 0)
 		timeout = 0;
 
-	if (nf_flow_timeout_delta(ct->timeout) > (__s32)timeout)
-		ct->timeout = nfct_time_stamp + timeout;
+	if (nf_flow_timeout_delta(READ_ONCE(ct->timeout)) > (__s32)timeout)
+		WRITE_ONCE(ct->timeout, nfct_time_stamp + timeout);
 }
 
 static void flow_offload_fixup_ct_state(struct nf_conn *ct)
diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c
index d6bf1b2cd541..b561e0a44a45 100644
--- a/net/netfilter/nf_flow_table_offload.c
+++ b/net/netfilter/nf_flow_table_offload.c
@@ -65,11 +65,11 @@ static void nf_flow_rule_lwt_match(struct nf_flow_match *match,
 		       sizeof(struct in6_addr));
 		if (memcmp(&key->enc_ipv6.src, &in6addr_any,
 			   sizeof(struct in6_addr)))
-			memset(&key->enc_ipv6.src, 0xff,
+			memset(&mask->enc_ipv6.src, 0xff,
 			       sizeof(struct in6_addr));
 		if (memcmp(&key->enc_ipv6.dst, &in6addr_any,
 			   sizeof(struct in6_addr)))
-			memset(&key->enc_ipv6.dst, 0xff,
+			memset(&mask->enc_ipv6.dst, 0xff,
 			       sizeof(struct in6_addr));
 		enc_keys |= BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS);
 		key->enc_control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index c0851fec11d4..c20772822637 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -4481,9 +4481,9 @@ struct nft_set_elem_catchall {
 static void nft_set_catchall_destroy(const struct nft_ctx *ctx,
 				     struct nft_set *set)
 {
-	struct nft_set_elem_catchall *catchall;
+	struct nft_set_elem_catchall *next, *catchall;
 
-	list_for_each_entry_rcu(catchall, &set->catchall_list, list) {
+	list_for_each_entry_safe(catchall, next, &set->catchall_list, list) {
 		list_del_rcu(&catchall->list);
 		nft_set_elem_destroy(set, catchall->elem, true);
 		kfree_rcu(catchall);
diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index 691ef4cffdd9..7f83f9697fc1 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -556,7 +556,8 @@ __build_packet_message(struct nfnl_log_net *log,
 		goto nla_put_failure;
 
 	if (indev && skb->dev &&
-	    skb->mac_header != skb->network_header) {
+	    skb_mac_header_was_set(skb) &&
+	    skb_mac_header_len(skb) != 0) {
 		struct nfulnl_msg_packet_hw phw;
 		int len;
 
diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index 4acc4b8e9fe5..f0b9e21a2452 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -387,7 +387,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue,
 	struct net_device *indev;
 	struct net_device *outdev;
 	struct nf_conn *ct = NULL;
-	enum ip_conntrack_info ctinfo;
+	enum ip_conntrack_info ctinfo = 0;
 	struct nfnl_ct_hook *nfnl_ct;
 	bool csum_verify;
 	char *secdata = NULL;
@@ -560,7 +560,8 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue,
 		goto nla_put_failure;
 
 	if (indev && entskb->dev &&
-	    skb_mac_header_was_set(entskb)) {
+	    skb_mac_header_was_set(entskb) &&
+	    skb_mac_header_len(entskb) != 0) {
 		struct nfqnl_msg_packet_hw phw;
 		int len;
 
diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c
index af4ee874a067..dbe1f2e7dd9e 100644
--- a/net/netfilter/nft_exthdr.c
+++ b/net/netfilter/nft_exthdr.c
@@ -236,7 +236,7 @@ static void nft_exthdr_tcp_set_eval(const struct nft_expr *expr,
 
 	tcph = nft_tcp_header_pointer(pkt, sizeof(buff), buff, &tcphdr_len);
 	if (!tcph)
-		return;
+		goto err;
 
 	opt = (u8 *)tcph;
 	for (i = sizeof(*tcph); i < tcphdr_len - 1; i += optl) {
@@ -251,16 +251,16 @@ static void nft_exthdr_tcp_set_eval(const struct nft_expr *expr,
 			continue;
 
 		if (i + optl > tcphdr_len || priv->len + priv->offset > optl)
-			return;
+			goto err;
 
 		if (skb_ensure_writable(pkt->skb,
 					nft_thoff(pkt) + i + priv->len))
-			return;
+			goto err;
 
 		tcph = nft_tcp_header_pointer(pkt, sizeof(buff), buff,
 					      &tcphdr_len);
 		if (!tcph)
-			return;
+			goto err;
 
 		offset = i + priv->offset;
 
@@ -303,6 +303,9 @@ static void nft_exthdr_tcp_set_eval(const struct nft_expr *expr,
 
 		return;
 	}
+	return;
+err:
+	regs->verdict.code = NFT_BREAK;
 }
 
 static void nft_exthdr_sctp_eval(const struct nft_expr *expr,
diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c
index cbfe4e4a4ad7..bd689938a2e0 100644
--- a/net/netfilter/nft_payload.c
+++ b/net/netfilter/nft_payload.c
@@ -22,7 +22,6 @@
 #include <linux/icmpv6.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
-#include <linux/ip.h>
 #include <net/sctp/checksum.h>
 
 static bool nft_payload_rebuild_vlan_hdr(const struct sk_buff *skb, int mac_off,
diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c
index e517663e0cd1..6f4116e72958 100644
--- a/net/netfilter/nft_set_pipapo_avx2.c
+++ b/net/netfilter/nft_set_pipapo_avx2.c
@@ -886,7 +886,7 @@ static int nft_pipapo_avx2_lookup_8b_6(unsigned long *map, unsigned long *fill,
 			NFT_PIPAPO_AVX2_BUCKET_LOAD8(4,  lt, 4, pkt[4], bsize);
 
 			NFT_PIPAPO_AVX2_AND(5, 0, 1);
-			NFT_PIPAPO_AVX2_BUCKET_LOAD8(6,  lt, 6, pkt[5], bsize);
+			NFT_PIPAPO_AVX2_BUCKET_LOAD8(6,  lt, 5, pkt[5], bsize);
 			NFT_PIPAPO_AVX2_AND(7, 2, 3);
 
 			/* Stall */
diff --git a/net/netfilter/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c
index 2f7cf5ecebf4..0f8bb0bf558f 100644
--- a/net/netfilter/xt_IDLETIMER.c
+++ b/net/netfilter/xt_IDLETIMER.c
@@ -85,9 +85,9 @@ static ssize_t idletimer_tg_show(struct device *dev,
 	mutex_unlock(&list_mutex);
 
 	if (time_after(expires, jiffies) || ktimespec.tv_sec > 0)
-		return snprintf(buf, PAGE_SIZE, "%ld\n", time_diff);
+		return sysfs_emit(buf, "%ld\n", time_diff);
 
-	return snprintf(buf, PAGE_SIZE, "0\n");
+	return sysfs_emit(buf, "0\n");
 }
 
 static void idletimer_tg_work(struct work_struct *work)
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 4c575324a985..9eba2e648385 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1852,6 +1852,11 @@ static int netlink_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 	if (msg->msg_flags & MSG_OOB)
 		return -EOPNOTSUPP;
 
+	if (len == 0) {
+		pr_warn_once("Zero length message leads to an empty skb\n");
+		return -ENODATA;
+	}
+
 	err = scm_send(sock, msg, &scm, true);
 	if (err < 0)
 		return err;
diff --git a/net/nfc/core.c b/net/nfc/core.c
index 3c645c1d99c9..dc7a2404efdf 100644
--- a/net/nfc/core.c
+++ b/net/nfc/core.c
@@ -94,13 +94,13 @@ int nfc_dev_up(struct nfc_dev *dev)
 
 	device_lock(&dev->dev);
 
-	if (dev->rfkill && rfkill_blocked(dev->rfkill)) {
-		rc = -ERFKILL;
+	if (!device_is_registered(&dev->dev)) {
+		rc = -ENODEV;
 		goto error;
 	}
 
-	if (!device_is_registered(&dev->dev)) {
-		rc = -ENODEV;
+	if (dev->rfkill && rfkill_blocked(dev->rfkill)) {
+		rc = -ERFKILL;
 		goto error;
 	}
 
@@ -1125,11 +1125,7 @@ int nfc_register_device(struct nfc_dev *dev)
 	if (rc)
 		pr_err("Could not register llcp device\n");
 
-	rc = nfc_genl_device_added(dev);
-	if (rc)
-		pr_debug("The userspace won't be notified that the device %s was added\n",
-			 dev_name(&dev->dev));
-
+	device_lock(&dev->dev);
 	dev->rfkill = rfkill_alloc(dev_name(&dev->dev), &dev->dev,
 				   RFKILL_TYPE_NFC, &nfc_rfkill_ops, dev);
 	if (dev->rfkill) {
@@ -1138,6 +1134,12 @@ int nfc_register_device(struct nfc_dev *dev)
 			dev->rfkill = NULL;
 		}
 	}
+	device_unlock(&dev->dev);
+
+	rc = nfc_genl_device_added(dev);
+	if (rc)
+		pr_debug("The userspace won't be notified that the device %s was added\n",
+			 dev_name(&dev->dev));
 
 	return 0;
 }
@@ -1154,10 +1156,17 @@ void nfc_unregister_device(struct nfc_dev *dev)
 
 	pr_debug("dev_name=%s\n", dev_name(&dev->dev));
 
+	rc = nfc_genl_device_removed(dev);
+	if (rc)
+		pr_debug("The userspace won't be notified that the device %s "
+			 "was removed\n", dev_name(&dev->dev));
+
+	device_lock(&dev->dev);
 	if (dev->rfkill) {
 		rfkill_unregister(dev->rfkill);
 		rfkill_destroy(dev->rfkill);
 	}
+	device_unlock(&dev->dev);
 
 	if (dev->ops->check_presence) {
 		device_lock(&dev->dev);
@@ -1167,11 +1176,6 @@ void nfc_unregister_device(struct nfc_dev *dev)
 		cancel_work_sync(&dev->check_pres_work);
 	}
 
-	rc = nfc_genl_device_removed(dev);
-	if (rc)
-		pr_debug("The userspace won't be notified that the device %s "
-			 "was removed\n", dev_name(&dev->dev));
-
 	nfc_llcp_unregister_device(dev);
 
 	mutex_lock(&nfc_devlist_mutex);
diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c
index 6fd873aa86be..d2537383a3e8 100644
--- a/net/nfc/nci/core.c
+++ b/net/nfc/nci/core.c
@@ -144,12 +144,15 @@ inline int nci_request(struct nci_dev *ndev,
 {
 	int rc;
 
-	if (!test_bit(NCI_UP, &ndev->flags))
-		return -ENETDOWN;
-
 	/* Serialize all requests */
 	mutex_lock(&ndev->req_lock);
-	rc = __nci_request(ndev, req, opt, timeout);
+	/* check the state after obtaing the lock against any races
+	 * from nci_close_device when the device gets removed.
+	 */
+	if (test_bit(NCI_UP, &ndev->flags))
+		rc = __nci_request(ndev, req, opt, timeout);
+	else
+		rc = -ENETDOWN;
 	mutex_unlock(&ndev->req_lock);
 
 	return rc;
@@ -473,6 +476,11 @@ static int nci_open_device(struct nci_dev *ndev)
 
 	mutex_lock(&ndev->req_lock);
 
+	if (test_bit(NCI_UNREG, &ndev->flags)) {
+		rc = -ENODEV;
+		goto done;
+	}
+
 	if (test_bit(NCI_UP, &ndev->flags)) {
 		rc = -EALREADY;
 		goto done;
@@ -545,6 +553,10 @@ done:
 static int nci_close_device(struct nci_dev *ndev)
 {
 	nci_req_cancel(ndev, ENODEV);
+
+	/* This mutex needs to be held as a barrier for
+	 * caller nci_unregister_device
+	 */
 	mutex_lock(&ndev->req_lock);
 
 	if (!test_and_clear_bit(NCI_UP, &ndev->flags)) {
@@ -582,8 +594,8 @@ static int nci_close_device(struct nci_dev *ndev)
 
 	del_timer_sync(&ndev->cmd_timer);
 
-	/* Clear flags */
-	ndev->flags = 0;
+	/* Clear flags except NCI_UNREG */
+	ndev->flags &= BIT(NCI_UNREG);
 
 	mutex_unlock(&ndev->req_lock);
 
@@ -1266,6 +1278,12 @@ void nci_unregister_device(struct nci_dev *ndev)
 {
 	struct nci_conn_info *conn_info, *n;
 
+	/* This set_bit is not protected with specialized barrier,
+	 * However, it is fine because the mutex_lock(&ndev->req_lock);
+	 * in nci_close_device() will help to emit one.
+	 */
+	set_bit(NCI_UNREG, &ndev->flags);
+
 	nci_close_device(ndev);
 
 	destroy_workqueue(ndev->cmd_wq);
diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c
index 334f63c9529e..f184b0db79d4 100644
--- a/net/nfc/netlink.c
+++ b/net/nfc/netlink.c
@@ -636,8 +636,10 @@ static int nfc_genl_dump_devices_done(struct netlink_callback *cb)
 {
 	struct class_dev_iter *iter = (struct class_dev_iter *) cb->args[0];
 
-	nfc_device_iter_exit(iter);
-	kfree(iter);
+	if (iter) {
+		nfc_device_iter_exit(iter);
+		kfree(iter);
+	}
 
 	return 0;
 }
@@ -1392,8 +1394,10 @@ static int nfc_genl_dump_ses_done(struct netlink_callback *cb)
 {
 	struct class_dev_iter *iter = (struct class_dev_iter *) cb->args[0];
 
-	nfc_device_iter_exit(iter);
-	kfree(iter);
+	if (iter) {
+		nfc_device_iter_exit(iter);
+		kfree(iter);
+	}
 
 	return 0;
 }
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index 9713035b89e3..6d262d9aa10e 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -34,6 +34,7 @@
 #include <net/mpls.h>
 #include <net/ndisc.h>
 #include <net/nsh.h>
+#include <net/netfilter/nf_conntrack_zones.h>
 
 #include "conntrack.h"
 #include "datapath.h"
@@ -860,6 +861,7 @@ int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info,
 #endif
 	bool post_ct = false;
 	int res, err;
+	u16 zone = 0;
 
 	/* Extract metadata from packet. */
 	if (tun_info) {
@@ -898,6 +900,7 @@ int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info,
 		key->recirc_id = tc_ext ? tc_ext->chain : 0;
 		OVS_CB(skb)->mru = tc_ext ? tc_ext->mru : 0;
 		post_ct = tc_ext ? tc_ext->post_ct : false;
+		zone = post_ct ? tc_ext->zone : 0;
 	} else {
 		key->recirc_id = 0;
 	}
@@ -906,8 +909,11 @@ int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info,
 #endif
 
 	err = key_extract(skb, key);
-	if (!err)
+	if (!err) {
 		ovs_ct_fill_key(skb, key, post_ct);   /* Must be after key_extract(). */
+		if (post_ct && !skb_get_nfct(skb))
+			key->ct_zone = zone;
+	}
 	return err;
 }
 
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 46943a18a10d..76c2dca7f0a5 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -4492,9 +4492,10 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 	}
 
 out_free_pg_vec:
-	bitmap_free(rx_owner_map);
-	if (pg_vec)
+	if (pg_vec) {
+		bitmap_free(rx_owner_map);
 		free_pg_vec(pg_vec, order, req->tp_block_nr);
+	}
 out:
 	return err;
 }
diff --git a/net/phonet/pep.c b/net/phonet/pep.c
index a1525916885a..65d463ad8770 100644
--- a/net/phonet/pep.c
+++ b/net/phonet/pep.c
@@ -868,6 +868,7 @@ static struct sock *pep_sock_accept(struct sock *sk, int flags, int *errp,
 
 	err = pep_accept_conn(newsk, skb);
 	if (err) {
+		__sock_put(sk);
 		sock_put(newsk);
 		newsk = NULL;
 		goto drop;
@@ -946,6 +947,8 @@ static int pep_ioctl(struct sock *sk, int cmd, unsigned long arg)
 			ret =  -EBUSY;
 		else if (sk->sk_state == TCP_ESTABLISHED)
 			ret = -EISCONN;
+		else if (!pn->pn_sk.sobject)
+			ret = -EADDRNOTAVAIL;
 		else
 			ret = pep_sock_enable(sk, NULL, 0);
 		release_sock(sk);
diff --git a/net/rds/connection.c b/net/rds/connection.c
index a3bc4b54d491..b4cc699c5fad 100644
--- a/net/rds/connection.c
+++ b/net/rds/connection.c
@@ -253,6 +253,7 @@ static struct rds_connection *__rds_conn_create(struct net *net,
 				 * should end up here, but if it
 				 * does, reset/destroy the connection.
 				 */
+				kfree(conn->c_path);
 				kmem_cache_free(rds_conn_slab, conn);
 				conn = ERR_PTR(-EOPNOTSUPP);
 				goto out;
diff --git a/net/rds/tcp.c b/net/rds/tcp.c
index abf19c0e3ba0..5327d130c4b5 100644
--- a/net/rds/tcp.c
+++ b/net/rds/tcp.c
@@ -500,7 +500,7 @@ void rds_tcp_tune(struct socket *sock)
 		sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
 	}
 	if (rtn->rcvbuf_size > 0) {
-		sk->sk_sndbuf = rtn->rcvbuf_size;
+		sk->sk_rcvbuf = rtn->rcvbuf_size;
 		sk->sk_userlocks |= SOCK_RCVBUF_LOCK;
 	}
 	release_sock(sk);
diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c
index dbea0bfee48e..8120138dac01 100644
--- a/net/rxrpc/conn_client.c
+++ b/net/rxrpc/conn_client.c
@@ -135,16 +135,20 @@ struct rxrpc_bundle *rxrpc_get_bundle(struct rxrpc_bundle *bundle)
 	return bundle;
 }
 
+static void rxrpc_free_bundle(struct rxrpc_bundle *bundle)
+{
+	rxrpc_put_peer(bundle->params.peer);
+	kfree(bundle);
+}
+
 void rxrpc_put_bundle(struct rxrpc_bundle *bundle)
 {
 	unsigned int d = bundle->debug_id;
 	unsigned int u = atomic_dec_return(&bundle->usage);
 
 	_debug("PUT B=%x %u", d, u);
-	if (u == 0) {
-		rxrpc_put_peer(bundle->params.peer);
-		kfree(bundle);
-	}
+	if (u == 0)
+		rxrpc_free_bundle(bundle);
 }
 
 /*
@@ -328,7 +332,7 @@ static struct rxrpc_bundle *rxrpc_look_up_bundle(struct rxrpc_conn_parameters *c
 	return candidate;
 
 found_bundle_free:
-	kfree(candidate);
+	rxrpc_free_bundle(candidate);
 found_bundle:
 	rxrpc_get_bundle(bundle);
 	spin_unlock(&local->client_bundles_lock);
diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c
index 68396d052052..0298fe2ad6d3 100644
--- a/net/rxrpc/peer_object.c
+++ b/net/rxrpc/peer_object.c
@@ -299,6 +299,12 @@ static struct rxrpc_peer *rxrpc_create_peer(struct rxrpc_sock *rx,
 	return peer;
 }
 
+static void rxrpc_free_peer(struct rxrpc_peer *peer)
+{
+	rxrpc_put_local(peer->local);
+	kfree_rcu(peer, rcu);
+}
+
 /*
  * Set up a new incoming peer.  There shouldn't be any other matching peers
  * since we've already done a search in the list from the non-reentrant context
@@ -365,7 +371,7 @@ struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_sock *rx,
 		spin_unlock_bh(&rxnet->peer_hash_lock);
 
 		if (peer)
-			kfree(candidate);
+			rxrpc_free_peer(candidate);
 		else
 			peer = candidate;
 	}
@@ -420,8 +426,7 @@ static void __rxrpc_put_peer(struct rxrpc_peer *peer)
 	list_del_init(&peer->keepalive_link);
 	spin_unlock_bh(&rxnet->peer_hash_lock);
 
-	rxrpc_put_local(peer->local);
-	kfree_rcu(peer, rcu);
+	rxrpc_free_peer(peer);
 }
 
 /*
@@ -457,8 +462,7 @@ void rxrpc_put_peer_locked(struct rxrpc_peer *peer)
 	if (n == 0) {
 		hash_del_rcu(&peer->hash_link);
 		list_del_init(&peer->keepalive_link);
-		rxrpc_put_local(peer->local);
-		kfree_rcu(peer, rcu);
+		rxrpc_free_peer(peer);
 	}
 }
 
diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index 90866ae45573..ab3591408419 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -690,10 +690,10 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb,
 				   u8 family, u16 zone, bool *defrag)
 {
 	enum ip_conntrack_info ctinfo;
-	struct qdisc_skb_cb cb;
 	struct nf_conn *ct;
 	int err = 0;
 	bool frag;
+	u16 mru;
 
 	/* Previously seen (loopback)? Ignore. */
 	ct = nf_ct_get(skb, &ctinfo);
@@ -708,7 +708,7 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb,
 		return err;
 
 	skb_get(skb);
-	cb = *qdisc_skb_cb(skb);
+	mru = tc_skb_cb(skb)->mru;
 
 	if (family == NFPROTO_IPV4) {
 		enum ip_defrag_users user = IP_DEFRAG_CONNTRACK_IN + zone;
@@ -722,7 +722,7 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb,
 
 		if (!err) {
 			*defrag = true;
-			cb.mru = IPCB(skb)->frag_max_size;
+			mru = IPCB(skb)->frag_max_size;
 		}
 	} else { /* NFPROTO_IPV6 */
 #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
@@ -735,7 +735,7 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb,
 
 		if (!err) {
 			*defrag = true;
-			cb.mru = IP6CB(skb)->frag_max_size;
+			mru = IP6CB(skb)->frag_max_size;
 		}
 #else
 		err = -EOPNOTSUPP;
@@ -744,7 +744,7 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb,
 	}
 
 	if (err != -EINPROGRESS)
-		*qdisc_skb_cb(skb) = cb;
+		tc_skb_cb(skb)->mru = mru;
 	skb_clear_hash(skb);
 	skb->ignore_df = 1;
 	return err;
@@ -963,7 +963,7 @@ static int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a,
 	tcf_action_update_bstats(&c->common, skb);
 
 	if (clear) {
-		qdisc_skb_cb(skb)->post_ct = false;
+		tc_skb_cb(skb)->post_ct = false;
 		ct = nf_ct_get(skb, &ctinfo);
 		if (ct) {
 			nf_conntrack_put(&ct->ct_general);
@@ -1048,7 +1048,8 @@ do_nat:
 out_push:
 	skb_push_rcsum(skb, nh_ofs);
 
-	qdisc_skb_cb(skb)->post_ct = true;
+	tc_skb_cb(skb)->post_ct = true;
+	tc_skb_cb(skb)->zone = p->zone;
 out_clear:
 	if (defrag)
 		qdisc_skb_cb(skb)->pkt_len = skb->len;
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index d64b0eeccbe4..efc963ab995a 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -19,6 +19,7 @@
 #include <linux/if_arp.h>
 #include <net/net_namespace.h>
 #include <net/netlink.h>
+#include <net/dst.h>
 #include <net/pkt_sched.h>
 #include <net/pkt_cls.h>
 #include <linux/tc_act/tc_mirred.h>
@@ -228,6 +229,7 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a,
 	bool want_ingress;
 	bool is_redirect;
 	bool expects_nh;
+	bool at_ingress;
 	int m_eaction;
 	int mac_len;
 	bool at_nh;
@@ -263,7 +265,8 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a,
 	 * ingress - that covers the TC S/W datapath.
 	 */
 	is_redirect = tcf_mirred_is_act_redirect(m_eaction);
-	use_reinsert = skb_at_tc_ingress(skb) && is_redirect &&
+	at_ingress = skb_at_tc_ingress(skb);
+	use_reinsert = at_ingress && is_redirect &&
 		       tcf_mirred_can_reinsert(retval);
 	if (!use_reinsert) {
 		skb2 = skb_clone(skb, GFP_ATOMIC);
@@ -271,10 +274,12 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a,
 			goto out;
 	}
 
+	want_ingress = tcf_mirred_act_wants_ingress(m_eaction);
+
 	/* All mirred/redirected skbs should clear previous ct info */
 	nf_reset_ct(skb2);
-
-	want_ingress = tcf_mirred_act_wants_ingress(m_eaction);
+	if (want_ingress && !at_ingress) /* drop dst for egress -> ingress */
+		skb_dst_drop(skb2);
 
 	expects_nh = want_ingress || !m_mac_header_xmit;
 	at_nh = skb->data == skb_network_header(skb);
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 2ef8f5a6205a..35c74bdde848 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1617,12 +1617,15 @@ int tcf_classify(struct sk_buff *skb,
 
 	/* If we missed on some chain */
 	if (ret == TC_ACT_UNSPEC && last_executed_chain) {
+		struct tc_skb_cb *cb = tc_skb_cb(skb);
+
 		ext = tc_skb_ext_alloc(skb);
 		if (WARN_ON_ONCE(!ext))
 			return TC_ACT_SHOT;
 		ext->chain = last_executed_chain;
-		ext->mru = qdisc_skb_cb(skb)->mru;
-		ext->post_ct = qdisc_skb_cb(skb)->post_ct;
+		ext->mru = cb->mru;
+		ext->post_ct = cb->post_ct;
+		ext->zone = cb->zone;
 	}
 
 	return ret;
@@ -3687,6 +3690,7 @@ int tc_setup_flow_action(struct flow_action *flow_action,
 				entry->mpls_mangle.ttl = tcf_mpls_ttl(act);
 				break;
 			default:
+				err = -EOPNOTSUPP;
 				goto err_out_locked;
 			}
 		} else if (is_tcf_skbedit_ptype(act)) {
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index aab13ba11767..ef54ed395874 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -19,6 +19,7 @@
 
 #include <net/sch_generic.h>
 #include <net/pkt_cls.h>
+#include <net/pkt_sched.h>
 #include <net/ip.h>
 #include <net/flow_dissector.h>
 #include <net/geneve.h>
@@ -309,7 +310,8 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 		       struct tcf_result *res)
 {
 	struct cls_fl_head *head = rcu_dereference_bh(tp->root);
-	bool post_ct = qdisc_skb_cb(skb)->post_ct;
+	bool post_ct = tc_skb_cb(skb)->post_ct;
+	u16 zone = tc_skb_cb(skb)->zone;
 	struct fl_flow_key skb_key;
 	struct fl_flow_mask *mask;
 	struct cls_fl_filter *f;
@@ -327,7 +329,7 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 		skb_flow_dissect_ct(skb, &mask->dissector, &skb_key,
 				    fl_ct_info_to_flower_map,
 				    ARRAY_SIZE(fl_ct_info_to_flower_map),
-				    post_ct);
+				    post_ct, zone);
 		skb_flow_dissect_hash(skb, &mask->dissector, &skb_key);
 		skb_flow_dissect(skb, &mask->dissector, &skb_key,
 				 FLOW_DISSECTOR_F_STOP_BEFORE_ENCAP);
diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
index 3c2300d14468..857aaebd49f4 100644
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -2736,7 +2736,7 @@ static int cake_init(struct Qdisc *sch, struct nlattr *opt,
 	q->tins = kvcalloc(CAKE_MAX_TINS, sizeof(struct cake_tin_data),
 			   GFP_KERNEL);
 	if (!q->tins)
-		goto nomem;
+		return -ENOMEM;
 
 	for (i = 0; i < CAKE_MAX_TINS; i++) {
 		struct cake_tin_data *b = q->tins + i;
@@ -2766,10 +2766,6 @@ static int cake_init(struct Qdisc *sch, struct nlattr *opt,
 	q->min_netlen = ~0;
 	q->min_adjlen = ~0;
 	return 0;
-
-nomem:
-	cake_destroy(sch);
-	return -ENOMEM;
 }
 
 static int cake_dump(struct Qdisc *sch, struct sk_buff *skb)
diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c
index 0eae9ff5edf6..d73393493553 100644
--- a/net/sched/sch_ets.c
+++ b/net/sched/sch_ets.c
@@ -665,12 +665,14 @@ static int ets_qdisc_change(struct Qdisc *sch, struct nlattr *opt,
 			q->classes[i].deficit = quanta[i];
 		}
 	}
+	for (i = q->nbands; i < oldbands; i++) {
+		if (i >= q->nstrict && q->classes[i].qdisc->q.qlen)
+			list_del(&q->classes[i].alist);
+		qdisc_tree_flush_backlog(q->classes[i].qdisc);
+	}
 	q->nstrict = nstrict;
 	memcpy(q->prio2band, priomap, sizeof(priomap));
 
-	for (i = q->nbands; i < oldbands; i++)
-		qdisc_tree_flush_backlog(q->classes[i].qdisc);
-
 	for (i = 0; i < q->nbands; i++)
 		q->classes[i].quantum = quanta[i];
 
diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c
index 830f3559f727..d6aba6edd16e 100644
--- a/net/sched/sch_fq_pie.c
+++ b/net/sched/sch_fq_pie.c
@@ -531,6 +531,7 @@ static void fq_pie_destroy(struct Qdisc *sch)
 	struct fq_pie_sched_data *q = qdisc_priv(sch);
 
 	tcf_block_put(q->block);
+	q->p_params.tupdate = 0;
 	del_timer_sync(&q->adapt_timer);
 	kvfree(q->flows);
 }
diff --git a/net/sched/sch_frag.c b/net/sched/sch_frag.c
index 8c06381391d6..5ded4c8672a6 100644
--- a/net/sched/sch_frag.c
+++ b/net/sched/sch_frag.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
 #include <net/netlink.h>
 #include <net/sch_generic.h>
+#include <net/pkt_sched.h>
 #include <net/dst.h>
 #include <net/ip.h>
 #include <net/ip6_fib.h>
@@ -137,7 +138,7 @@ err:
 
 int sch_frag_xmit_hook(struct sk_buff *skb, int (*xmit)(struct sk_buff *skb))
 {
-	u16 mru = qdisc_skb_cb(skb)->mru;
+	u16 mru = tc_skb_cb(skb)->mru;
 	int err;
 
 	if (mru && skb->len > mru + skb->dev->hard_header_len)
diff --git a/net/sctp/diag.c b/net/sctp/diag.c
index 760b367644c1..034e2c74497d 100644
--- a/net/sctp/diag.c
+++ b/net/sctp/diag.c
@@ -245,54 +245,49 @@ static size_t inet_assoc_attr_size(struct sctp_association *asoc)
 		+ 64;
 }
 
-static int sctp_tsp_dump_one(struct sctp_transport *tsp, void *p)
+static int sctp_sock_dump_one(struct sctp_endpoint *ep, struct sctp_transport *tsp, void *p)
 {
 	struct sctp_association *assoc = tsp->asoc;
-	struct sock *sk = tsp->asoc->base.sk;
 	struct sctp_comm_param *commp = p;
-	struct sk_buff *in_skb = commp->skb;
+	struct sock *sk = ep->base.sk;
 	const struct inet_diag_req_v2 *req = commp->r;
-	const struct nlmsghdr *nlh = commp->nlh;
-	struct net *net = sock_net(in_skb->sk);
+	struct sk_buff *skb = commp->skb;
 	struct sk_buff *rep;
 	int err;
 
 	err = sock_diag_check_cookie(sk, req->id.idiag_cookie);
 	if (err)
-		goto out;
+		return err;
 
-	err = -ENOMEM;
 	rep = nlmsg_new(inet_assoc_attr_size(assoc), GFP_KERNEL);
 	if (!rep)
-		goto out;
+		return -ENOMEM;
 
 	lock_sock(sk);
-	if (sk != assoc->base.sk) {
-		release_sock(sk);
-		sk = assoc->base.sk;
-		lock_sock(sk);
+	if (ep != assoc->ep) {
+		err = -EAGAIN;
+		goto out;
 	}
-	err = inet_sctp_diag_fill(sk, assoc, rep, req,
-				  sk_user_ns(NETLINK_CB(in_skb).sk),
-				  NETLINK_CB(in_skb).portid,
-				  nlh->nlmsg_seq, 0, nlh,
-				  commp->net_admin);
-	release_sock(sk);
+
+	err = inet_sctp_diag_fill(sk, assoc, rep, req, sk_user_ns(NETLINK_CB(skb).sk),
+				  NETLINK_CB(skb).portid, commp->nlh->nlmsg_seq, 0,
+				  commp->nlh, commp->net_admin);
 	if (err < 0) {
 		WARN_ON(err == -EMSGSIZE);
-		kfree_skb(rep);
 		goto out;
 	}
+	release_sock(sk);
 
-	err = nlmsg_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid);
+	return nlmsg_unicast(sock_net(skb->sk)->diag_nlsk, rep, NETLINK_CB(skb).portid);
 
 out:
+	release_sock(sk);
+	kfree_skb(rep);
 	return err;
 }
 
-static int sctp_sock_dump(struct sctp_transport *tsp, void *p)
+static int sctp_sock_dump(struct sctp_endpoint *ep, struct sctp_transport *tsp, void *p)
 {
-	struct sctp_endpoint *ep = tsp->asoc->ep;
 	struct sctp_comm_param *commp = p;
 	struct sock *sk = ep->base.sk;
 	struct sk_buff *skb = commp->skb;
@@ -302,6 +297,8 @@ static int sctp_sock_dump(struct sctp_transport *tsp, void *p)
 	int err = 0;
 
 	lock_sock(sk);
+	if (ep != tsp->asoc->ep)
+		goto release;
 	list_for_each_entry(assoc, &ep->asocs, asocs) {
 		if (cb->args[4] < cb->args[1])
 			goto next;
@@ -344,9 +341,8 @@ release:
 	return err;
 }
 
-static int sctp_sock_filter(struct sctp_transport *tsp, void *p)
+static int sctp_sock_filter(struct sctp_endpoint *ep, struct sctp_transport *tsp, void *p)
 {
-	struct sctp_endpoint *ep = tsp->asoc->ep;
 	struct sctp_comm_param *commp = p;
 	struct sock *sk = ep->base.sk;
 	const struct inet_diag_req_v2 *r = commp->r;
@@ -429,15 +425,15 @@ static void sctp_diag_get_info(struct sock *sk, struct inet_diag_msg *r,
 static int sctp_diag_dump_one(struct netlink_callback *cb,
 			      const struct inet_diag_req_v2 *req)
 {
-	struct sk_buff *in_skb = cb->skb;
-	struct net *net = sock_net(in_skb->sk);
+	struct sk_buff *skb = cb->skb;
+	struct net *net = sock_net(skb->sk);
 	const struct nlmsghdr *nlh = cb->nlh;
 	union sctp_addr laddr, paddr;
 	struct sctp_comm_param commp = {
-		.skb = in_skb,
+		.skb = skb,
 		.r = req,
 		.nlh = nlh,
-		.net_admin = netlink_net_capable(in_skb, CAP_NET_ADMIN),
+		.net_admin = netlink_net_capable(skb, CAP_NET_ADMIN),
 	};
 
 	if (req->sdiag_family == AF_INET) {
@@ -460,7 +456,7 @@ static int sctp_diag_dump_one(struct netlink_callback *cb,
 		paddr.v6.sin6_family = AF_INET6;
 	}
 
-	return sctp_transport_lookup_process(sctp_tsp_dump_one,
+	return sctp_transport_lookup_process(sctp_sock_dump_one,
 					     net, &laddr, &paddr, &commp);
 }
 
@@ -505,8 +501,8 @@ skip:
 	if (!(idiag_states & ~(TCPF_LISTEN | TCPF_CLOSE)))
 		goto done;
 
-	sctp_for_each_transport(sctp_sock_filter, sctp_sock_dump,
-				net, &pos, &commp);
+	sctp_transport_traverse_process(sctp_sock_filter, sctp_sock_dump,
+					net, &pos, &commp);
 	cb->args[2] = pos;
 
 done:
diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c
index 48c9c2c7602f..efffde7f2328 100644
--- a/net/sctp/endpointola.c
+++ b/net/sctp/endpointola.c
@@ -184,6 +184,18 @@ void sctp_endpoint_free(struct sctp_endpoint *ep)
 }
 
 /* Final destructor for endpoint.  */
+static void sctp_endpoint_destroy_rcu(struct rcu_head *head)
+{
+	struct sctp_endpoint *ep = container_of(head, struct sctp_endpoint, rcu);
+	struct sock *sk = ep->base.sk;
+
+	sctp_sk(sk)->ep = NULL;
+	sock_put(sk);
+
+	kfree(ep);
+	SCTP_DBG_OBJCNT_DEC(ep);
+}
+
 static void sctp_endpoint_destroy(struct sctp_endpoint *ep)
 {
 	struct sock *sk;
@@ -213,18 +225,13 @@ static void sctp_endpoint_destroy(struct sctp_endpoint *ep)
 	if (sctp_sk(sk)->bind_hash)
 		sctp_put_port(sk);
 
-	sctp_sk(sk)->ep = NULL;
-	/* Give up our hold on the sock */
-	sock_put(sk);
-
-	kfree(ep);
-	SCTP_DBG_OBJCNT_DEC(ep);
+	call_rcu(&ep->rcu, sctp_endpoint_destroy_rcu);
 }
 
 /* Hold a reference to an endpoint. */
-void sctp_endpoint_hold(struct sctp_endpoint *ep)
+int sctp_endpoint_hold(struct sctp_endpoint *ep)
 {
-	refcount_inc(&ep->base.refcnt);
+	return refcount_inc_not_zero(&ep->base.refcnt);
 }
 
 /* Release a reference to an endpoint and clean up if there are
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index 39ba82ee87ce..354c1c4de19b 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -946,7 +946,7 @@ enum sctp_disposition sctp_sf_do_5_1E_ca(struct net *net,
 	sctp_add_cmd_sf(commands, SCTP_CMD_INIT_COUNTER_RESET, SCTP_NULL());
 
 	/* Set peer label for connection. */
-	security_sctp_assoc_established((struct sctp_association *)asoc, chunk->skb);
+	security_inet_conn_established(ep->base.sk, chunk->skb);
 
 	/* RFC 2960 5.1 Normal Establishment of an Association
 	 *
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 33391254fa82..da08671a3f80 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -5317,32 +5317,41 @@ int sctp_for_each_endpoint(int (*cb)(struct sctp_endpoint *, void *),
 }
 EXPORT_SYMBOL_GPL(sctp_for_each_endpoint);
 
-int sctp_transport_lookup_process(int (*cb)(struct sctp_transport *, void *),
-				  struct net *net,
+int sctp_transport_lookup_process(sctp_callback_t cb, struct net *net,
 				  const union sctp_addr *laddr,
 				  const union sctp_addr *paddr, void *p)
 {
 	struct sctp_transport *transport;
-	int err;
+	struct sctp_endpoint *ep;
+	int err = -ENOENT;
 
 	rcu_read_lock();
 	transport = sctp_addrs_lookup_transport(net, laddr, paddr);
+	if (!transport) {
+		rcu_read_unlock();
+		return err;
+	}
+	ep = transport->asoc->ep;
+	if (!sctp_endpoint_hold(ep)) { /* asoc can be peeled off */
+		sctp_transport_put(transport);
+		rcu_read_unlock();
+		return err;
+	}
 	rcu_read_unlock();
-	if (!transport)
-		return -ENOENT;
 
-	err = cb(transport, p);
+	err = cb(ep, transport, p);
+	sctp_endpoint_put(ep);
 	sctp_transport_put(transport);
-
 	return err;
 }
 EXPORT_SYMBOL_GPL(sctp_transport_lookup_process);
 
-int sctp_for_each_transport(int (*cb)(struct sctp_transport *, void *),
-			    int (*cb_done)(struct sctp_transport *, void *),
-			    struct net *net, int *pos, void *p) {
+int sctp_transport_traverse_process(sctp_callback_t cb, sctp_callback_t cb_done,
+				    struct net *net, int *pos, void *p)
+{
 	struct rhashtable_iter hti;
 	struct sctp_transport *tsp;
+	struct sctp_endpoint *ep;
 	int ret;
 
 again:
@@ -5351,26 +5360,32 @@ again:
 
 	tsp = sctp_transport_get_idx(net, &hti, *pos + 1);
 	for (; !IS_ERR_OR_NULL(tsp); tsp = sctp_transport_get_next(net, &hti)) {
-		ret = cb(tsp, p);
-		if (ret)
-			break;
+		ep = tsp->asoc->ep;
+		if (sctp_endpoint_hold(ep)) { /* asoc can be peeled off */
+			ret = cb(ep, tsp, p);
+			if (ret)
+				break;
+			sctp_endpoint_put(ep);
+		}
 		(*pos)++;
 		sctp_transport_put(tsp);
 	}
 	sctp_transport_walk_stop(&hti);
 
 	if (ret) {
-		if (cb_done && !cb_done(tsp, p)) {
+		if (cb_done && !cb_done(ep, tsp, p)) {
 			(*pos)++;
+			sctp_endpoint_put(ep);
 			sctp_transport_put(tsp);
 			goto again;
 		}
+		sctp_endpoint_put(ep);
 		sctp_transport_put(tsp);
 	}
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(sctp_for_each_transport);
+EXPORT_SYMBOL_GPL(sctp_transport_traverse_process);
 
 /* 7.2.1 Association Status (SCTP_STATUS)
 
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 59284da9116d..1c9289f56dc4 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -194,7 +194,9 @@ static int smc_release(struct socket *sock)
 	/* cleanup for a dangling non-blocking connect */
 	if (smc->connect_nonblock && sk->sk_state == SMC_INIT)
 		tcp_abort(smc->clcsock->sk, ECONNABORTED);
-	flush_work(&smc->connect_work);
+
+	if (cancel_work_sync(&smc->connect_work))
+		sock_put(&smc->sk); /* sock_hold in smc_connect for passive closing */
 
 	if (sk->sk_state == SMC_LISTEN)
 		/* smc_close_non_accepted() is called and acquires
@@ -566,6 +568,10 @@ static void smc_stat_fallback(struct smc_sock *smc)
 
 static void smc_switch_to_fallback(struct smc_sock *smc, int reason_code)
 {
+	wait_queue_head_t *smc_wait = sk_sleep(&smc->sk);
+	wait_queue_head_t *clc_wait = sk_sleep(smc->clcsock->sk);
+	unsigned long flags;
+
 	smc->use_fallback = true;
 	smc->fallback_rsn = reason_code;
 	smc_stat_fallback(smc);
@@ -575,6 +581,16 @@ static void smc_switch_to_fallback(struct smc_sock *smc, int reason_code)
 		smc->clcsock->file->private_data = smc->clcsock;
 		smc->clcsock->wq.fasync_list =
 			smc->sk.sk_socket->wq.fasync_list;
+
+		/* There may be some entries remaining in
+		 * smc socket->wq, which should be removed
+		 * to clcsocket->wq during the fallback.
+		 */
+		spin_lock_irqsave(&smc_wait->lock, flags);
+		spin_lock_nested(&clc_wait->lock, SINGLE_DEPTH_NESTING);
+		list_splice_init(&smc_wait->head, &clc_wait->head);
+		spin_unlock(&clc_wait->lock);
+		spin_unlock_irqrestore(&smc_wait->lock, flags);
 	}
 }
 
@@ -2120,8 +2136,10 @@ static int smc_listen(struct socket *sock, int backlog)
 	smc->clcsock->sk->sk_user_data =
 		(void *)((uintptr_t)smc | SK_USER_DATA_NOCOPY);
 	rc = kernel_listen(smc->clcsock, backlog);
-	if (rc)
+	if (rc) {
+		smc->clcsock->sk->sk_data_ready = smc->clcsk_data_ready;
 		goto out;
+	}
 	sk->sk_max_ack_backlog = backlog;
 	sk->sk_ack_backlog = 0;
 	sk->sk_state = SMC_LISTEN;
@@ -2354,8 +2372,10 @@ static __poll_t smc_poll(struct file *file, struct socket *sock,
 static int smc_shutdown(struct socket *sock, int how)
 {
 	struct sock *sk = sock->sk;
+	bool do_shutdown = true;
 	struct smc_sock *smc;
 	int rc = -EINVAL;
+	int old_state;
 	int rc1 = 0;
 
 	smc = smc_sk(sk);
@@ -2382,7 +2402,11 @@ static int smc_shutdown(struct socket *sock, int how)
 	}
 	switch (how) {
 	case SHUT_RDWR:		/* shutdown in both directions */
+		old_state = sk->sk_state;
 		rc = smc_close_active(smc);
+		if (old_state == SMC_ACTIVE &&
+		    sk->sk_state == SMC_PEERCLOSEWAIT1)
+			do_shutdown = false;
 		break;
 	case SHUT_WR:
 		rc = smc_close_shutdown_write(smc);
@@ -2392,7 +2416,7 @@ static int smc_shutdown(struct socket *sock, int how)
 		/* nothing more to do because peer is not involved */
 		break;
 	}
-	if (smc->clcsock)
+	if (do_shutdown && smc->clcsock)
 		rc1 = kernel_sock_shutdown(smc->clcsock, how);
 	/* map sock_shutdown_cmd constants to sk_shutdown value range */
 	sk->sk_shutdown |= how + 1;
diff --git a/net/smc/smc.h b/net/smc/smc.h
index f4286ca1f228..1a4fc1c6c4ab 100644
--- a/net/smc/smc.h
+++ b/net/smc/smc.h
@@ -180,6 +180,11 @@ struct smc_connection {
 	u16			tx_cdc_seq;	/* sequence # for CDC send */
 	u16			tx_cdc_seq_fin;	/* sequence # - tx completed */
 	spinlock_t		send_lock;	/* protect wr_sends */
+	atomic_t		cdc_pend_tx_wr; /* number of pending tx CDC wqe
+						 * - inc when post wqe,
+						 * - dec on polled tx cqe
+						 */
+	wait_queue_head_t	cdc_pend_tx_wq; /* wakeup on no cdc_pend_tx_wr*/
 	struct delayed_work	tx_work;	/* retry of smc_cdc_msg_send */
 	u32			tx_off;		/* base offset in peer rmb */
 
diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c
index 99acd337ba90..84c8a4374fdd 100644
--- a/net/smc/smc_cdc.c
+++ b/net/smc/smc_cdc.c
@@ -31,10 +31,6 @@ static void smc_cdc_tx_handler(struct smc_wr_tx_pend_priv *pnd_snd,
 	struct smc_sock *smc;
 	int diff;
 
-	if (!conn)
-		/* already dismissed */
-		return;
-
 	smc = container_of(conn, struct smc_sock, conn);
 	bh_lock_sock(&smc->sk);
 	if (!wc_status) {
@@ -51,6 +47,12 @@ static void smc_cdc_tx_handler(struct smc_wr_tx_pend_priv *pnd_snd,
 			      conn);
 		conn->tx_cdc_seq_fin = cdcpend->ctrl_seq;
 	}
+
+	if (atomic_dec_and_test(&conn->cdc_pend_tx_wr) &&
+	    unlikely(wq_has_sleeper(&conn->cdc_pend_tx_wq)))
+		wake_up(&conn->cdc_pend_tx_wq);
+	WARN_ON(atomic_read(&conn->cdc_pend_tx_wr) < 0);
+
 	smc_tx_sndbuf_nonfull(smc);
 	bh_unlock_sock(&smc->sk);
 }
@@ -107,6 +109,10 @@ int smc_cdc_msg_send(struct smc_connection *conn,
 	conn->tx_cdc_seq++;
 	conn->local_tx_ctrl.seqno = conn->tx_cdc_seq;
 	smc_host_msg_to_cdc((struct smc_cdc_msg *)wr_buf, conn, &cfed);
+
+	atomic_inc(&conn->cdc_pend_tx_wr);
+	smp_mb__after_atomic(); /* Make sure cdc_pend_tx_wr added before post */
+
 	rc = smc_wr_tx_send(link, (struct smc_wr_tx_pend_priv *)pend);
 	if (!rc) {
 		smc_curs_copy(&conn->rx_curs_confirmed, &cfed, conn);
@@ -114,6 +120,7 @@ int smc_cdc_msg_send(struct smc_connection *conn,
 	} else {
 		conn->tx_cdc_seq--;
 		conn->local_tx_ctrl.seqno = conn->tx_cdc_seq;
+		atomic_dec(&conn->cdc_pend_tx_wr);
 	}
 
 	return rc;
@@ -136,7 +143,18 @@ int smcr_cdc_msg_send_validation(struct smc_connection *conn,
 	peer->token = htonl(local->token);
 	peer->prod_flags.failover_validation = 1;
 
+	/* We need to set pend->conn here to make sure smc_cdc_tx_handler()
+	 * can handle properly
+	 */
+	smc_cdc_add_pending_send(conn, pend);
+
+	atomic_inc(&conn->cdc_pend_tx_wr);
+	smp_mb__after_atomic(); /* Make sure cdc_pend_tx_wr added before post */
+
 	rc = smc_wr_tx_send(link, (struct smc_wr_tx_pend_priv *)pend);
+	if (unlikely(rc))
+		atomic_dec(&conn->cdc_pend_tx_wr);
+
 	return rc;
 }
 
@@ -193,31 +211,9 @@ int smc_cdc_get_slot_and_msg_send(struct smc_connection *conn)
 	return rc;
 }
 
-static bool smc_cdc_tx_filter(struct smc_wr_tx_pend_priv *tx_pend,
-			      unsigned long data)
+void smc_cdc_wait_pend_tx_wr(struct smc_connection *conn)
 {
-	struct smc_connection *conn = (struct smc_connection *)data;
-	struct smc_cdc_tx_pend *cdc_pend =
-		(struct smc_cdc_tx_pend *)tx_pend;
-
-	return cdc_pend->conn == conn;
-}
-
-static void smc_cdc_tx_dismisser(struct smc_wr_tx_pend_priv *tx_pend)
-{
-	struct smc_cdc_tx_pend *cdc_pend =
-		(struct smc_cdc_tx_pend *)tx_pend;
-
-	cdc_pend->conn = NULL;
-}
-
-void smc_cdc_tx_dismiss_slots(struct smc_connection *conn)
-{
-	struct smc_link *link = conn->lnk;
-
-	smc_wr_tx_dismiss_slots(link, SMC_CDC_MSG_TYPE,
-				smc_cdc_tx_filter, smc_cdc_tx_dismisser,
-				(unsigned long)conn);
+	wait_event(conn->cdc_pend_tx_wq, !atomic_read(&conn->cdc_pend_tx_wr));
 }
 
 /* Send a SMC-D CDC header.
diff --git a/net/smc/smc_cdc.h b/net/smc/smc_cdc.h
index 0a0a89abd38b..696cc11f2303 100644
--- a/net/smc/smc_cdc.h
+++ b/net/smc/smc_cdc.h
@@ -291,7 +291,7 @@ int smc_cdc_get_free_slot(struct smc_connection *conn,
 			  struct smc_wr_buf **wr_buf,
 			  struct smc_rdma_wr **wr_rdma_buf,
 			  struct smc_cdc_tx_pend **pend);
-void smc_cdc_tx_dismiss_slots(struct smc_connection *conn);
+void smc_cdc_wait_pend_tx_wr(struct smc_connection *conn);
 int smc_cdc_msg_send(struct smc_connection *conn, struct smc_wr_buf *wr_buf,
 		     struct smc_cdc_tx_pend *pend);
 int smc_cdc_get_slot_and_msg_send(struct smc_connection *conn);
diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c
index 0f9ffba07d26..292e4d904ab6 100644
--- a/net/smc/smc_close.c
+++ b/net/smc/smc_close.c
@@ -195,6 +195,7 @@ int smc_close_active(struct smc_sock *smc)
 	int old_state;
 	long timeout;
 	int rc = 0;
+	int rc1 = 0;
 
 	timeout = current->flags & PF_EXITING ?
 		  0 : sock_flag(sk, SOCK_LINGER) ?
@@ -228,6 +229,15 @@ again:
 			/* send close request */
 			rc = smc_close_final(conn);
 			sk->sk_state = SMC_PEERCLOSEWAIT1;
+
+			/* actively shutdown clcsock before peer close it,
+			 * prevent peer from entering TIME_WAIT state.
+			 */
+			if (smc->clcsock && smc->clcsock->sk) {
+				rc1 = kernel_sock_shutdown(smc->clcsock,
+							   SHUT_RDWR);
+				rc = rc ? rc : rc1;
+			}
 		} else {
 			/* peer event has changed the state */
 			goto again;
@@ -354,9 +364,9 @@ static void smc_close_passive_work(struct work_struct *work)
 	if (rxflags->peer_conn_abort) {
 		/* peer has not received all data */
 		smc_close_passive_abort_received(smc);
-		release_sock(&smc->sk);
+		release_sock(sk);
 		cancel_delayed_work_sync(&conn->tx_work);
-		lock_sock(&smc->sk);
+		lock_sock(sk);
 		goto wakeup;
 	}
 
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 49b8ba3bb683..a6849362f4dd 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -625,18 +625,17 @@ int smcd_nl_get_lgr(struct sk_buff *skb, struct netlink_callback *cb)
 void smc_lgr_cleanup_early(struct smc_connection *conn)
 {
 	struct smc_link_group *lgr = conn->lgr;
-	struct list_head *lgr_list;
 	spinlock_t *lgr_lock;
 
 	if (!lgr)
 		return;
 
 	smc_conn_free(conn);
-	lgr_list = smc_lgr_list_head(lgr, &lgr_lock);
+	smc_lgr_list_head(lgr, &lgr_lock);
 	spin_lock_bh(lgr_lock);
 	/* do not use this link group for new connections */
-	if (!list_empty(lgr_list))
-		list_del_init(lgr_list);
+	if (!list_empty(&lgr->list))
+		list_del_init(&lgr->list);
 	spin_unlock_bh(lgr_lock);
 	__smc_lgr_terminate(lgr, true);
 }
@@ -648,7 +647,7 @@ static void smcr_lgr_link_deactivate_all(struct smc_link_group *lgr)
 	for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) {
 		struct smc_link *lnk = &lgr->lnk[i];
 
-		if (smc_link_usable(lnk))
+		if (smc_link_sendable(lnk))
 			lnk->state = SMC_LNK_INACTIVE;
 	}
 	wake_up_all(&lgr->llc_msg_waiter);
@@ -708,13 +707,14 @@ static u8 smcr_next_link_id(struct smc_link_group *lgr)
 	int i;
 
 	while (1) {
+again:
 		link_id = ++lgr->next_link_id;
 		if (!link_id)	/* skip zero as link_id */
 			link_id = ++lgr->next_link_id;
 		for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) {
 			if (smc_link_usable(&lgr->lnk[i]) &&
 			    lgr->lnk[i].link_id == link_id)
-				continue;
+				goto again;
 		}
 		break;
 	}
@@ -1127,7 +1127,7 @@ void smc_conn_free(struct smc_connection *conn)
 			smc_ism_unset_conn(conn);
 		tasklet_kill(&conn->rx_tsklet);
 	} else {
-		smc_cdc_tx_dismiss_slots(conn);
+		smc_cdc_wait_pend_tx_wr(conn);
 		if (current_work() != &conn->abort_work)
 			cancel_work_sync(&conn->abort_work);
 	}
@@ -1204,7 +1204,7 @@ void smcr_link_clear(struct smc_link *lnk, bool log)
 	smc_llc_link_clear(lnk, log);
 	smcr_buf_unmap_lgr(lnk);
 	smcr_rtoken_clear_link(lnk);
-	smc_ib_modify_qp_reset(lnk);
+	smc_ib_modify_qp_error(lnk);
 	smc_wr_free_link(lnk);
 	smc_ib_destroy_queue_pair(lnk);
 	smc_ib_dealloc_protection_domain(lnk);
@@ -1336,7 +1336,7 @@ static void smc_conn_kill(struct smc_connection *conn, bool soft)
 		else
 			tasklet_unlock_wait(&conn->rx_tsklet);
 	} else {
-		smc_cdc_tx_dismiss_slots(conn);
+		smc_cdc_wait_pend_tx_wr(conn);
 	}
 	smc_lgr_unregister_conn(conn);
 	smc_close_active_abort(smc);
@@ -1459,11 +1459,16 @@ void smc_smcd_terminate_all(struct smcd_dev *smcd)
 /* Called when an SMCR device is removed or the smc module is unloaded.
  * If smcibdev is given, all SMCR link groups using this device are terminated.
  * If smcibdev is NULL, all SMCR link groups are terminated.
+ *
+ * We must wait here for QPs been destroyed before we destroy the CQs,
+ * or we won't received any CQEs and cdc_pend_tx_wr cannot reach 0 thus
+ * smc_sock cannot be released.
  */
 void smc_smcr_terminate_all(struct smc_ib_device *smcibdev)
 {
 	struct smc_link_group *lgr, *lg;
 	LIST_HEAD(lgr_free_list);
+	LIST_HEAD(lgr_linkdown_list);
 	int i;
 
 	spin_lock_bh(&smc_lgr_list.lock);
@@ -1475,7 +1480,7 @@ void smc_smcr_terminate_all(struct smc_ib_device *smcibdev)
 		list_for_each_entry_safe(lgr, lg, &smc_lgr_list.list, list) {
 			for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) {
 				if (lgr->lnk[i].smcibdev == smcibdev)
-					smcr_link_down_cond_sched(&lgr->lnk[i]);
+					list_move_tail(&lgr->list, &lgr_linkdown_list);
 			}
 		}
 	}
@@ -1487,6 +1492,16 @@ void smc_smcr_terminate_all(struct smc_ib_device *smcibdev)
 		__smc_lgr_terminate(lgr, false);
 	}
 
+	list_for_each_entry_safe(lgr, lg, &lgr_linkdown_list, list) {
+		for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) {
+			if (lgr->lnk[i].smcibdev == smcibdev) {
+				mutex_lock(&lgr->llc_conf_mutex);
+				smcr_link_down_cond(&lgr->lnk[i]);
+				mutex_unlock(&lgr->llc_conf_mutex);
+			}
+		}
+	}
+
 	if (smcibdev) {
 		if (atomic_read(&smcibdev->lnk_cnt))
 			wait_event(smcibdev->lnks_deleted,
@@ -1586,7 +1601,6 @@ static void smcr_link_down(struct smc_link *lnk)
 	if (!lgr || lnk->state == SMC_LNK_UNUSED || list_empty(&lgr->list))
 		return;
 
-	smc_ib_modify_qp_reset(lnk);
 	to_lnk = smc_switch_conns(lgr, lnk, true);
 	if (!to_lnk) { /* no backup link available */
 		smcr_link_clear(lnk, true);
@@ -1671,14 +1685,26 @@ static void smc_link_down_work(struct work_struct *work)
 	mutex_unlock(&lgr->llc_conf_mutex);
 }
 
-/* Determine vlan of internal TCP socket.
- * @vlan_id: address to store the determined vlan id into
- */
+static int smc_vlan_by_tcpsk_walk(struct net_device *lower_dev,
+				  struct netdev_nested_priv *priv)
+{
+	unsigned short *vlan_id = (unsigned short *)priv->data;
+
+	if (is_vlan_dev(lower_dev)) {
+		*vlan_id = vlan_dev_vlan_id(lower_dev);
+		return 1;
+	}
+
+	return 0;
+}
+
+/* Determine vlan of internal TCP socket. */
 int smc_vlan_by_tcpsk(struct socket *clcsock, struct smc_init_info *ini)
 {
 	struct dst_entry *dst = sk_dst_get(clcsock->sk);
+	struct netdev_nested_priv priv;
 	struct net_device *ndev;
-	int i, nest_lvl, rc = 0;
+	int rc = 0;
 
 	ini->vlan_id = 0;
 	if (!dst) {
@@ -1696,20 +1722,9 @@ int smc_vlan_by_tcpsk(struct socket *clcsock, struct smc_init_info *ini)
 		goto out_rel;
 	}
 
+	priv.data = (void *)&ini->vlan_id;
 	rtnl_lock();
-	nest_lvl = ndev->lower_level;
-	for (i = 0; i < nest_lvl; i++) {
-		struct list_head *lower = &ndev->adj_list.lower;
-
-		if (list_empty(lower))
-			break;
-		lower = lower->next;
-		ndev = (struct net_device *)netdev_lower_get_next(ndev, &lower);
-		if (is_vlan_dev(ndev)) {
-			ini->vlan_id = vlan_dev_vlan_id(ndev);
-			break;
-		}
-	}
+	netdev_walk_all_lower_dev(ndev, smc_vlan_by_tcpsk_walk, &priv);
 	rtnl_unlock();
 
 out_rel:
@@ -1823,6 +1838,7 @@ create:
 	conn->local_tx_ctrl.common.type = SMC_CDC_MSG_TYPE;
 	conn->local_tx_ctrl.len = SMC_WR_TX_SIZE;
 	conn->urg_state = SMC_URG_READ;
+	init_waitqueue_head(&conn->cdc_pend_tx_wq);
 	INIT_WORK(&smc->conn.abort_work, smc_conn_abort_work);
 	if (ini->is_smcd) {
 		conn->rx_off = sizeof(struct smcd_cdc_msg);
diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h
index 59cef3b830d8..d63b08274197 100644
--- a/net/smc/smc_core.h
+++ b/net/smc/smc_core.h
@@ -415,6 +415,12 @@ static inline bool smc_link_usable(struct smc_link *lnk)
 	return true;
 }
 
+static inline bool smc_link_sendable(struct smc_link *lnk)
+{
+	return smc_link_usable(lnk) &&
+		lnk->qp_attr.cur_qp_state == IB_QPS_RTS;
+}
+
 static inline bool smc_link_active(struct smc_link *lnk)
 {
 	return lnk->state == SMC_LNK_ACTIVE;
diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c
index d93055ec17ae..fe5d5399c4e8 100644
--- a/net/smc/smc_ib.c
+++ b/net/smc/smc_ib.c
@@ -109,12 +109,12 @@ int smc_ib_modify_qp_rts(struct smc_link *lnk)
 			    IB_QP_MAX_QP_RD_ATOMIC);
 }
 
-int smc_ib_modify_qp_reset(struct smc_link *lnk)
+int smc_ib_modify_qp_error(struct smc_link *lnk)
 {
 	struct ib_qp_attr qp_attr;
 
 	memset(&qp_attr, 0, sizeof(qp_attr));
-	qp_attr.qp_state = IB_QPS_RESET;
+	qp_attr.qp_state = IB_QPS_ERR;
 	return ib_modify_qp(lnk->roce_qp, &qp_attr, IB_QP_STATE);
 }
 
diff --git a/net/smc/smc_ib.h b/net/smc/smc_ib.h
index 07585937370e..bfa1c6bf6313 100644
--- a/net/smc/smc_ib.h
+++ b/net/smc/smc_ib.h
@@ -90,6 +90,7 @@ int smc_ib_create_queue_pair(struct smc_link *lnk);
 int smc_ib_ready_link(struct smc_link *lnk);
 int smc_ib_modify_qp_rts(struct smc_link *lnk);
 int smc_ib_modify_qp_reset(struct smc_link *lnk);
+int smc_ib_modify_qp_error(struct smc_link *lnk);
 long smc_ib_setup_per_ibdev(struct smc_ib_device *smcibdev);
 int smc_ib_get_memory_region(struct ib_pd *pd, int access_flags,
 			     struct smc_buf_desc *buf_slot, u8 link_idx);
diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c
index b102680296b8..3e9fd8a3124c 100644
--- a/net/smc/smc_llc.c
+++ b/net/smc/smc_llc.c
@@ -1630,7 +1630,7 @@ void smc_llc_send_link_delete_all(struct smc_link_group *lgr, bool ord, u32 rsn)
 	delllc.reason = htonl(rsn);
 
 	for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) {
-		if (!smc_link_usable(&lgr->lnk[i]))
+		if (!smc_link_sendable(&lgr->lnk[i]))
 			continue;
 		if (!smc_llc_send_message_wait(&lgr->lnk[i], &delllc))
 			break;
diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c
index 600ab5889227..c6cfdea8b71b 100644
--- a/net/smc/smc_wr.c
+++ b/net/smc/smc_wr.c
@@ -62,13 +62,9 @@ static inline bool smc_wr_is_tx_pend(struct smc_link *link)
 }
 
 /* wait till all pending tx work requests on the given link are completed */
-int smc_wr_tx_wait_no_pending_sends(struct smc_link *link)
+void smc_wr_tx_wait_no_pending_sends(struct smc_link *link)
 {
-	if (wait_event_timeout(link->wr_tx_wait, !smc_wr_is_tx_pend(link),
-			       SMC_WR_TX_WAIT_PENDING_TIME))
-		return 0;
-	else /* timeout */
-		return -EPIPE;
+	wait_event(link->wr_tx_wait, !smc_wr_is_tx_pend(link));
 }
 
 static inline int smc_wr_tx_find_pending_index(struct smc_link *link, u64 wr_id)
@@ -87,7 +83,6 @@ static inline void smc_wr_tx_process_cqe(struct ib_wc *wc)
 	struct smc_wr_tx_pend pnd_snd;
 	struct smc_link *link;
 	u32 pnd_snd_idx;
-	int i;
 
 	link = wc->qp->qp_context;
 
@@ -128,14 +123,6 @@ static inline void smc_wr_tx_process_cqe(struct ib_wc *wc)
 	}
 
 	if (wc->status) {
-		for_each_set_bit(i, link->wr_tx_mask, link->wr_tx_cnt) {
-			/* clear full struct smc_wr_tx_pend including .priv */
-			memset(&link->wr_tx_pends[i], 0,
-			       sizeof(link->wr_tx_pends[i]));
-			memset(&link->wr_tx_bufs[i], 0,
-			       sizeof(link->wr_tx_bufs[i]));
-			clear_bit(i, link->wr_tx_mask);
-		}
 		if (link->lgr->smc_version == SMC_V2) {
 			memset(link->wr_tx_v2_pend, 0,
 			       sizeof(*link->wr_tx_v2_pend));
@@ -188,7 +175,7 @@ void smc_wr_tx_cq_handler(struct ib_cq *ib_cq, void *cq_context)
 static inline int smc_wr_tx_get_free_slot_index(struct smc_link *link, u32 *idx)
 {
 	*idx = link->wr_tx_cnt;
-	if (!smc_link_usable(link))
+	if (!smc_link_sendable(link))
 		return -ENOLINK;
 	for_each_clear_bit(*idx, link->wr_tx_mask, link->wr_tx_cnt) {
 		if (!test_and_set_bit(*idx, link->wr_tx_mask))
@@ -231,7 +218,7 @@ int smc_wr_tx_get_free_slot(struct smc_link *link,
 	} else {
 		rc = wait_event_interruptible_timeout(
 			link->wr_tx_wait,
-			!smc_link_usable(link) ||
+			!smc_link_sendable(link) ||
 			lgr->terminating ||
 			(smc_wr_tx_get_free_slot_index(link, &idx) != -EBUSY),
 			SMC_WR_TX_WAIT_FREE_SLOT_TIME);
@@ -358,18 +345,20 @@ int smc_wr_tx_send_wait(struct smc_link *link, struct smc_wr_tx_pend_priv *priv,
 			unsigned long timeout)
 {
 	struct smc_wr_tx_pend *pend;
+	u32 pnd_idx;
 	int rc;
 
 	pend = container_of(priv, struct smc_wr_tx_pend, priv);
 	pend->compl_requested = 1;
-	init_completion(&link->wr_tx_compl[pend->idx]);
+	pnd_idx = pend->idx;
+	init_completion(&link->wr_tx_compl[pnd_idx]);
 
 	rc = smc_wr_tx_send(link, priv);
 	if (rc)
 		return rc;
 	/* wait for completion by smc_wr_tx_process_cqe() */
 	rc = wait_for_completion_interruptible_timeout(
-					&link->wr_tx_compl[pend->idx], timeout);
+					&link->wr_tx_compl[pnd_idx], timeout);
 	if (rc <= 0)
 		rc = -ENODATA;
 	if (rc > 0)
@@ -419,25 +408,6 @@ int smc_wr_reg_send(struct smc_link *link, struct ib_mr *mr)
 	return rc;
 }
 
-void smc_wr_tx_dismiss_slots(struct smc_link *link, u8 wr_tx_hdr_type,
-			     smc_wr_tx_filter filter,
-			     smc_wr_tx_dismisser dismisser,
-			     unsigned long data)
-{
-	struct smc_wr_tx_pend_priv *tx_pend;
-	struct smc_wr_rx_hdr *wr_tx;
-	int i;
-
-	for_each_set_bit(i, link->wr_tx_mask, link->wr_tx_cnt) {
-		wr_tx = (struct smc_wr_rx_hdr *)&link->wr_tx_bufs[i];
-		if (wr_tx->type != wr_tx_hdr_type)
-			continue;
-		tx_pend = &link->wr_tx_pends[i].priv;
-		if (filter(tx_pend, data))
-			dismisser(tx_pend);
-	}
-}
-
 /****************************** receive queue ********************************/
 
 int smc_wr_rx_register_handler(struct smc_wr_rx_handler *handler)
@@ -673,10 +643,7 @@ void smc_wr_free_link(struct smc_link *lnk)
 	smc_wr_wakeup_reg_wait(lnk);
 	smc_wr_wakeup_tx_wait(lnk);
 
-	if (smc_wr_tx_wait_no_pending_sends(lnk))
-		memset(lnk->wr_tx_mask, 0,
-		       BITS_TO_LONGS(SMC_WR_BUF_CNT) *
-						sizeof(*lnk->wr_tx_mask));
+	smc_wr_tx_wait_no_pending_sends(lnk);
 	wait_event(lnk->wr_reg_wait, (!atomic_read(&lnk->wr_reg_refcnt)));
 	wait_event(lnk->wr_tx_wait, (!atomic_read(&lnk->wr_tx_refcnt)));
 
diff --git a/net/smc/smc_wr.h b/net/smc/smc_wr.h
index f353311e6f84..47512ccce5ef 100644
--- a/net/smc/smc_wr.h
+++ b/net/smc/smc_wr.h
@@ -22,7 +22,6 @@
 #define SMC_WR_BUF_CNT 16	/* # of ctrl buffers per link */
 
 #define SMC_WR_TX_WAIT_FREE_SLOT_TIME	(10 * HZ)
-#define SMC_WR_TX_WAIT_PENDING_TIME	(5 * HZ)
 
 #define SMC_WR_TX_SIZE 44 /* actual size of wr_send data (<=SMC_WR_BUF_SIZE) */
 
@@ -62,7 +61,7 @@ static inline void smc_wr_tx_set_wr_id(atomic_long_t *wr_tx_id, long val)
 
 static inline bool smc_wr_tx_link_hold(struct smc_link *link)
 {
-	if (!smc_link_usable(link))
+	if (!smc_link_sendable(link))
 		return false;
 	atomic_inc(&link->wr_tx_refcnt);
 	return true;
@@ -130,7 +129,7 @@ void smc_wr_tx_dismiss_slots(struct smc_link *lnk, u8 wr_rx_hdr_type,
 			     smc_wr_tx_filter filter,
 			     smc_wr_tx_dismisser dismisser,
 			     unsigned long data);
-int smc_wr_tx_wait_no_pending_sends(struct smc_link *link);
+void smc_wr_tx_wait_no_pending_sends(struct smc_link *link);
 
 int smc_wr_rx_register_handler(struct smc_wr_rx_handler *handler);
 int smc_wr_rx_post_init(struct smc_link *link);
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index ae48c9c84ee1..d8ee06a9650a 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -1720,15 +1720,15 @@ static void xs_local_set_port(struct rpc_xprt *xprt, unsigned short port)
 }
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
-static struct lock_class_key xs_key[2];
-static struct lock_class_key xs_slock_key[2];
+static struct lock_class_key xs_key[3];
+static struct lock_class_key xs_slock_key[3];
 
 static inline void xs_reclassify_socketu(struct socket *sock)
 {
 	struct sock *sk = sock->sk;
 
 	sock_lock_init_class_and_name(sk, "slock-AF_LOCAL-RPC",
-		&xs_slock_key[1], "sk_lock-AF_LOCAL-RPC", &xs_key[1]);
+		&xs_slock_key[0], "sk_lock-AF_LOCAL-RPC", &xs_key[0]);
 }
 
 static inline void xs_reclassify_socket4(struct socket *sock)
@@ -1736,7 +1736,7 @@ static inline void xs_reclassify_socket4(struct socket *sock)
 	struct sock *sk = sock->sk;
 
 	sock_lock_init_class_and_name(sk, "slock-AF_INET-RPC",
-		&xs_slock_key[0], "sk_lock-AF_INET-RPC", &xs_key[0]);
+		&xs_slock_key[1], "sk_lock-AF_INET-RPC", &xs_key[1]);
 }
 
 static inline void xs_reclassify_socket6(struct socket *sock)
@@ -1744,7 +1744,7 @@ static inline void xs_reclassify_socket6(struct socket *sock)
 	struct sock *sk = sock->sk;
 
 	sock_lock_init_class_and_name(sk, "slock-AF_INET6-RPC",
-		&xs_slock_key[1], "sk_lock-AF_INET6-RPC", &xs_key[1]);
+		&xs_slock_key[2], "sk_lock-AF_INET6-RPC", &xs_key[2]);
 }
 
 static inline void xs_reclassify_socket(int family, struct socket *sock)
diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c
index dc60c32bb70d..d293614d5fc6 100644
--- a/net/tipc/crypto.c
+++ b/net/tipc/crypto.c
@@ -597,6 +597,10 @@ static int tipc_aead_init(struct tipc_aead **aead, struct tipc_aead_key *ukey,
 	tmp->cloned = NULL;
 	tmp->authsize = TIPC_AES_GCM_TAG_SIZE;
 	tmp->key = kmemdup(ukey, tipc_aead_key_size(ukey), GFP_KERNEL);
+	if (!tmp->key) {
+		tipc_aead_free(&tmp->rcu);
+		return -ENOMEM;
+	}
 	memcpy(&tmp->salt, ukey->key + keylen, TIPC_AES_GCM_SALT_SIZE);
 	atomic_set(&tmp->users, 0);
 	atomic64_set(&tmp->seqno, 0);
diff --git a/net/tipc/link.c b/net/tipc/link.c
index 1b7a487c8841..09ae8448f394 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -1298,8 +1298,11 @@ static bool tipc_data_input(struct tipc_link *l, struct sk_buff *skb,
 		return false;
 #ifdef CONFIG_TIPC_CRYPTO
 	case MSG_CRYPTO:
-		tipc_crypto_msg_rcv(l->net, skb);
-		return true;
+		if (TIPC_SKB_CB(skb)->decrypted) {
+			tipc_crypto_msg_rcv(l->net, skb);
+			return true;
+		}
+		fallthrough;
 #endif
 	default:
 		pr_warn("Dropping received illegal msg type\n");
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index ad570c2450be..3e63c83e641c 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -1461,6 +1461,8 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen)
 		msg_set_syn(hdr, 1);
 	}
 
+	memset(&skaddr, 0, sizeof(skaddr));
+
 	/* Determine destination */
 	if (atype == TIPC_SERVICE_RANGE) {
 		return tipc_sendmcast(sock, ua, m, dlen, timeout);
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index acfba9f1ba72..6bc2879ba637 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -61,7 +61,7 @@ static DEFINE_MUTEX(tcpv6_prot_mutex);
 static const struct proto *saved_tcpv4_prot;
 static DEFINE_MUTEX(tcpv4_prot_mutex);
 static struct proto tls_prots[TLS_NUM_PROTS][TLS_NUM_CONFIG][TLS_NUM_CONFIG];
-static struct proto_ops tls_sw_proto_ops;
+static struct proto_ops tls_proto_ops[TLS_NUM_PROTS][TLS_NUM_CONFIG][TLS_NUM_CONFIG];
 static void build_protos(struct proto prot[TLS_NUM_CONFIG][TLS_NUM_CONFIG],
 			 const struct proto *base);
 
@@ -71,6 +71,8 @@ void update_sk_prot(struct sock *sk, struct tls_context *ctx)
 
 	WRITE_ONCE(sk->sk_prot,
 		   &tls_prots[ip_ver][ctx->tx_conf][ctx->rx_conf]);
+	WRITE_ONCE(sk->sk_socket->ops,
+		   &tls_proto_ops[ip_ver][ctx->tx_conf][ctx->rx_conf]);
 }
 
 int wait_on_pending_writer(struct sock *sk, long *timeo)
@@ -669,8 +671,6 @@ static int do_tls_setsockopt_conf(struct sock *sk, sockptr_t optval,
 	if (tx) {
 		ctx->sk_write_space = sk->sk_write_space;
 		sk->sk_write_space = tls_write_space;
-	} else {
-		sk->sk_socket->ops = &tls_sw_proto_ops;
 	}
 	goto out;
 
@@ -728,6 +728,39 @@ struct tls_context *tls_ctx_create(struct sock *sk)
 	return ctx;
 }
 
+static void build_proto_ops(struct proto_ops ops[TLS_NUM_CONFIG][TLS_NUM_CONFIG],
+			    const struct proto_ops *base)
+{
+	ops[TLS_BASE][TLS_BASE] = *base;
+
+	ops[TLS_SW  ][TLS_BASE] = ops[TLS_BASE][TLS_BASE];
+	ops[TLS_SW  ][TLS_BASE].sendpage_locked	= tls_sw_sendpage_locked;
+
+	ops[TLS_BASE][TLS_SW  ] = ops[TLS_BASE][TLS_BASE];
+	ops[TLS_BASE][TLS_SW  ].splice_read	= tls_sw_splice_read;
+
+	ops[TLS_SW  ][TLS_SW  ] = ops[TLS_SW  ][TLS_BASE];
+	ops[TLS_SW  ][TLS_SW  ].splice_read	= tls_sw_splice_read;
+
+#ifdef CONFIG_TLS_DEVICE
+	ops[TLS_HW  ][TLS_BASE] = ops[TLS_BASE][TLS_BASE];
+	ops[TLS_HW  ][TLS_BASE].sendpage_locked	= NULL;
+
+	ops[TLS_HW  ][TLS_SW  ] = ops[TLS_BASE][TLS_SW  ];
+	ops[TLS_HW  ][TLS_SW  ].sendpage_locked	= NULL;
+
+	ops[TLS_BASE][TLS_HW  ] = ops[TLS_BASE][TLS_SW  ];
+
+	ops[TLS_SW  ][TLS_HW  ] = ops[TLS_SW  ][TLS_SW  ];
+
+	ops[TLS_HW  ][TLS_HW  ] = ops[TLS_HW  ][TLS_SW  ];
+	ops[TLS_HW  ][TLS_HW  ].sendpage_locked	= NULL;
+#endif
+#ifdef CONFIG_TLS_TOE
+	ops[TLS_HW_RECORD][TLS_HW_RECORD] = *base;
+#endif
+}
+
 static void tls_build_proto(struct sock *sk)
 {
 	int ip_ver = sk->sk_family == AF_INET6 ? TLSV6 : TLSV4;
@@ -739,6 +772,8 @@ static void tls_build_proto(struct sock *sk)
 		mutex_lock(&tcpv6_prot_mutex);
 		if (likely(prot != saved_tcpv6_prot)) {
 			build_protos(tls_prots[TLSV6], prot);
+			build_proto_ops(tls_proto_ops[TLSV6],
+					sk->sk_socket->ops);
 			smp_store_release(&saved_tcpv6_prot, prot);
 		}
 		mutex_unlock(&tcpv6_prot_mutex);
@@ -749,6 +784,8 @@ static void tls_build_proto(struct sock *sk)
 		mutex_lock(&tcpv4_prot_mutex);
 		if (likely(prot != saved_tcpv4_prot)) {
 			build_protos(tls_prots[TLSV4], prot);
+			build_proto_ops(tls_proto_ops[TLSV4],
+					sk->sk_socket->ops);
 			smp_store_release(&saved_tcpv4_prot, prot);
 		}
 		mutex_unlock(&tcpv4_prot_mutex);
@@ -959,10 +996,6 @@ static int __init tls_register(void)
 	if (err)
 		return err;
 
-	tls_sw_proto_ops = inet_stream_ops;
-	tls_sw_proto_ops.splice_read = tls_sw_splice_read;
-	tls_sw_proto_ops.sendpage_locked   = tls_sw_sendpage_locked;
-
 	tls_device_init();
 	tcp_register_ulp(&tcp_tls_ulp_ops);
 
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index d81564078557..dfe623a4e72f 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -521,7 +521,7 @@ static int tls_do_encryption(struct sock *sk,
 	memcpy(&rec->iv_data[iv_offset], tls_ctx->tx.iv,
 	       prot->iv_size + prot->salt_size);
 
-	xor_iv_with_seq(prot, rec->iv_data, tls_ctx->tx.rec_seq);
+	xor_iv_with_seq(prot, rec->iv_data + iv_offset, tls_ctx->tx.rec_seq);
 
 	sge->offset += prot->prepend_size;
 	sge->length -= prot->prepend_size;
@@ -1499,7 +1499,7 @@ static int decrypt_internal(struct sock *sk, struct sk_buff *skb,
 	else
 		memcpy(iv + iv_offset, tls_ctx->rx.iv, prot->salt_size);
 
-	xor_iv_with_seq(prot, iv, tls_ctx->rx.rec_seq);
+	xor_iv_with_seq(prot, iv + iv_offset, tls_ctx->rx.rec_seq);
 
 	/* Prepare AAD */
 	tls_make_aad(aad, rxm->full_len - prot->overhead_size +
@@ -2005,6 +2005,7 @@ ssize_t tls_sw_splice_read(struct socket *sock,  loff_t *ppos,
 	struct sock *sk = sock->sk;
 	struct sk_buff *skb;
 	ssize_t copied = 0;
+	bool from_queue;
 	int err = 0;
 	long timeo;
 	int chunk;
@@ -2014,25 +2015,28 @@ ssize_t tls_sw_splice_read(struct socket *sock,  loff_t *ppos,
 
 	timeo = sock_rcvtimeo(sk, flags & SPLICE_F_NONBLOCK);
 
-	skb = tls_wait_data(sk, NULL, flags & SPLICE_F_NONBLOCK, timeo, &err);
-	if (!skb)
-		goto splice_read_end;
-
-	if (!ctx->decrypted) {
-		err = decrypt_skb_update(sk, skb, NULL, &chunk, &zc, false);
-
-		/* splice does not support reading control messages */
-		if (ctx->control != TLS_RECORD_TYPE_DATA) {
-			err = -EINVAL;
+	from_queue = !skb_queue_empty(&ctx->rx_list);
+	if (from_queue) {
+		skb = __skb_dequeue(&ctx->rx_list);
+	} else {
+		skb = tls_wait_data(sk, NULL, flags & SPLICE_F_NONBLOCK, timeo,
+				    &err);
+		if (!skb)
 			goto splice_read_end;
-		}
 
+		err = decrypt_skb_update(sk, skb, NULL, &chunk, &zc, false);
 		if (err < 0) {
 			tls_err_abort(sk, -EBADMSG);
 			goto splice_read_end;
 		}
-		ctx->decrypted = 1;
 	}
+
+	/* splice does not support reading control messages */
+	if (ctx->control != TLS_RECORD_TYPE_DATA) {
+		err = -EINVAL;
+		goto splice_read_end;
+	}
+
 	rxm = strp_msg(skb);
 
 	chunk = min_t(unsigned int, rxm->full_len, len);
@@ -2040,7 +2044,17 @@ ssize_t tls_sw_splice_read(struct socket *sock,  loff_t *ppos,
 	if (copied < 0)
 		goto splice_read_end;
 
-	tls_sw_advance_skb(sk, skb, copied);
+	if (!from_queue) {
+		ctx->recv_pkt = NULL;
+		__strp_unpause(&ctx->strp);
+	}
+	if (chunk < rxm->full_len) {
+		__skb_queue_head(&ctx->rx_list, skb);
+		rxm->offset += len;
+		rxm->full_len -= len;
+	} else {
+		consume_skb(skb);
+	}
 
 splice_read_end:
 	release_sock(sk);
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 78e08e82c08c..b0bfc78e421c 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2882,9 +2882,6 @@ static int unix_shutdown(struct socket *sock, int mode)
 
 	unix_state_lock(sk);
 	sk->sk_shutdown |= mode;
-	if ((sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) &&
-	    mode == SHUTDOWN_MASK)
-		sk->sk_state = TCP_CLOSE;
 	other = unix_peer(sk);
 	if (other)
 		sock_hold(other);
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index 59ee1be5a6dd..ec2c2afbf0d0 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -1299,7 +1299,8 @@ void virtio_transport_recv_pkt(struct virtio_transport *t,
 	space_available = virtio_transport_space_update(sk, pkt);
 
 	/* Update CID in case it has changed after a transport reset event */
-	vsk->local_addr.svm_cid = dst.svm_cid;
+	if (vsk->local_addr.svm_cid != VMADDR_CID_ANY)
+		vsk->local_addr.svm_cid = dst.svm_cid;
 
 	if (space_available)
 		sk->sk_write_space(sk);
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 81232b73df8f..a27b3b5fa210 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -936,33 +936,37 @@ nl80211_packet_pattern_policy[MAX_NL80211_PKTPAT + 1] = {
 	[NL80211_PKTPAT_OFFSET] = { .type = NLA_U32 },
 };
 
-int nl80211_prepare_wdev_dump(struct netlink_callback *cb,
-			      struct cfg80211_registered_device **rdev,
-			      struct wireless_dev **wdev)
+static int nl80211_prepare_wdev_dump(struct netlink_callback *cb,
+				     struct cfg80211_registered_device **rdev,
+				     struct wireless_dev **wdev,
+				     struct nlattr **attrbuf)
 {
 	int err;
 
 	if (!cb->args[0]) {
-		struct nlattr **attrbuf;
+		struct nlattr **attrbuf_free = NULL;
 
-		attrbuf = kcalloc(NUM_NL80211_ATTR, sizeof(*attrbuf),
-				  GFP_KERNEL);
-		if (!attrbuf)
-			return -ENOMEM;
+		if (!attrbuf) {
+			attrbuf = kcalloc(NUM_NL80211_ATTR, sizeof(*attrbuf),
+					  GFP_KERNEL);
+			if (!attrbuf)
+				return -ENOMEM;
+			attrbuf_free = attrbuf;
+		}
 
 		err = nlmsg_parse_deprecated(cb->nlh,
 					     GENL_HDRLEN + nl80211_fam.hdrsize,
 					     attrbuf, nl80211_fam.maxattr,
 					     nl80211_policy, NULL);
 		if (err) {
-			kfree(attrbuf);
+			kfree(attrbuf_free);
 			return err;
 		}
 
 		rtnl_lock();
 		*wdev = __cfg80211_wdev_from_attrs(NULL, sock_net(cb->skb->sk),
 						   attrbuf);
-		kfree(attrbuf);
+		kfree(attrbuf_free);
 		if (IS_ERR(*wdev)) {
 			rtnl_unlock();
 			return PTR_ERR(*wdev);
@@ -6197,7 +6201,7 @@ static int nl80211_dump_station(struct sk_buff *skb,
 	int sta_idx = cb->args[2];
 	int err;
 
-	err = nl80211_prepare_wdev_dump(cb, &rdev, &wdev);
+	err = nl80211_prepare_wdev_dump(cb, &rdev, &wdev, NULL);
 	if (err)
 		return err;
 	/* nl80211_prepare_wdev_dump acquired it in the successful case */
@@ -7092,7 +7096,7 @@ static int nl80211_dump_mpath(struct sk_buff *skb,
 	int path_idx = cb->args[2];
 	int err;
 
-	err = nl80211_prepare_wdev_dump(cb, &rdev, &wdev);
+	err = nl80211_prepare_wdev_dump(cb, &rdev, &wdev, NULL);
 	if (err)
 		return err;
 	/* nl80211_prepare_wdev_dump acquired it in the successful case */
@@ -7292,7 +7296,7 @@ static int nl80211_dump_mpp(struct sk_buff *skb,
 	int path_idx = cb->args[2];
 	int err;
 
-	err = nl80211_prepare_wdev_dump(cb, &rdev, &wdev);
+	err = nl80211_prepare_wdev_dump(cb, &rdev, &wdev, NULL);
 	if (err)
 		return err;
 	/* nl80211_prepare_wdev_dump acquired it in the successful case */
@@ -9718,7 +9722,7 @@ static int nl80211_dump_scan(struct sk_buff *skb, struct netlink_callback *cb)
 	int start = cb->args[2], idx = 0;
 	int err;
 
-	err = nl80211_prepare_wdev_dump(cb, &rdev, &wdev);
+	err = nl80211_prepare_wdev_dump(cb, &rdev, &wdev, NULL);
 	if (err)
 		return err;
 	/* nl80211_prepare_wdev_dump acquired it in the successful case */
@@ -9851,7 +9855,7 @@ static int nl80211_dump_survey(struct sk_buff *skb, struct netlink_callback *cb)
 	if (!attrbuf)
 		return -ENOMEM;
 
-	res = nl80211_prepare_wdev_dump(cb, &rdev, &wdev);
+	res = nl80211_prepare_wdev_dump(cb, &rdev, &wdev, attrbuf);
 	if (res) {
 		kfree(attrbuf);
 		return res;
diff --git a/net/wireless/nl80211.h b/net/wireless/nl80211.h
index a3f387770f1b..d642e3be4ee7 100644
--- a/net/wireless/nl80211.h
+++ b/net/wireless/nl80211.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Portions of this file
- * Copyright (C) 2018, 2020 Intel Corporation
+ * Copyright (C) 2018, 2020-2021 Intel Corporation
  */
 #ifndef __NET_WIRELESS_NL80211_H
 #define __NET_WIRELESS_NL80211_H
@@ -22,10 +22,6 @@ static inline u64 wdev_id(struct wireless_dev *wdev)
 	       ((u64)wiphy_to_rdev(wdev->wiphy)->wiphy_idx << 32);
 }
 
-int nl80211_prepare_wdev_dump(struct netlink_callback *cb,
-			      struct cfg80211_registered_device **rdev,
-			      struct wireless_dev **wdev);
-
 int nl80211_parse_chandef(struct cfg80211_registered_device *rdev,
 			  struct genl_info *info,
 			  struct cfg80211_chan_def *chandef);
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index df87c7f3a049..f8f01a3e020b 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -133,6 +133,7 @@ static u32 reg_is_indoor_portid;
 
 static void restore_regulatory_settings(bool reset_user, bool cached);
 static void print_regdomain(const struct ieee80211_regdomain *rd);
+static void reg_process_hint(struct regulatory_request *reg_request);
 
 static const struct ieee80211_regdomain *get_cfg80211_regdom(void)
 {
@@ -1098,6 +1099,8 @@ int reg_reload_regdb(void)
 	const struct firmware *fw;
 	void *db;
 	int err;
+	const struct ieee80211_regdomain *current_regdomain;
+	struct regulatory_request *request;
 
 	err = request_firmware(&fw, "regulatory.db", &reg_pdev->dev);
 	if (err)
@@ -1118,8 +1121,26 @@ int reg_reload_regdb(void)
 	if (!IS_ERR_OR_NULL(regdb))
 		kfree(regdb);
 	regdb = db;
-	rtnl_unlock();
 
+	/* reset regulatory domain */
+	current_regdomain = get_cfg80211_regdom();
+
+	request = kzalloc(sizeof(*request), GFP_KERNEL);
+	if (!request) {
+		err = -ENOMEM;
+		goto out_unlock;
+	}
+
+	request->wiphy_idx = WIPHY_IDX_INVALID;
+	request->alpha2[0] = current_regdomain->alpha2[0];
+	request->alpha2[1] = current_regdomain->alpha2[1];
+	request->initiator = NL80211_REGDOM_SET_BY_CORE;
+	request->user_reg_hint_type = NL80211_USER_REG_HINT_USER;
+
+	reg_process_hint(request);
+
+out_unlock:
+	rtnl_unlock();
  out:
 	release_firmware(fw);
 	return err;
@@ -2338,6 +2359,7 @@ static bool reg_wdev_chan_valid(struct wiphy *wiphy, struct wireless_dev *wdev)
 	struct cfg80211_chan_def chandef = {};
 	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	enum nl80211_iftype iftype;
+	bool ret;
 
 	wdev_lock(wdev);
 	iftype = wdev->iftype;
@@ -2387,7 +2409,11 @@ static bool reg_wdev_chan_valid(struct wiphy *wiphy, struct wireless_dev *wdev)
 	case NL80211_IFTYPE_AP:
 	case NL80211_IFTYPE_P2P_GO:
 	case NL80211_IFTYPE_ADHOC:
-		return cfg80211_reg_can_beacon_relax(wiphy, &chandef, iftype);
+		wiphy_lock(wiphy);
+		ret = cfg80211_reg_can_beacon_relax(wiphy, &chandef, iftype);
+		wiphy_unlock(wiphy);
+
+		return ret;
 	case NL80211_IFTYPE_STATION:
 	case NL80211_IFTYPE_P2P_CLIENT:
 		return cfg80211_chandef_usable(wiphy, &chandef,
diff --git a/net/wireless/util.c b/net/wireless/util.c
index 5ff1f8726faf..41ea65deb6e1 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -1046,6 +1046,7 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev,
 
 		switch (otype) {
 		case NL80211_IFTYPE_AP:
+		case NL80211_IFTYPE_P2P_GO:
 			cfg80211_stop_ap(rdev, dev, true);
 			break;
 		case NL80211_IFTYPE_ADHOC:
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index 90c4e1e819d3..fd39bb660ebc 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -83,6 +83,7 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs,
 		xskb = &pool->heads[i];
 		xskb->pool = pool;
 		xskb->xdp.frame_sz = umem->chunk_size - umem->headroom;
+		INIT_LIST_HEAD(&xskb->free_list_node);
 		if (pool->unaligned)
 			pool->free_heads[i] = xskb;
 		else
@@ -500,7 +501,7 @@ struct xdp_buff *xp_alloc(struct xsk_buff_pool *pool)
 		pool->free_list_cnt--;
 		xskb = list_first_entry(&pool->free_list, struct xdp_buff_xsk,
 					free_list_node);
-		list_del(&xskb->free_list_node);
+		list_del_init(&xskb->free_list_node);
 	}
 
 	xskb->xdp.data = xskb->xdp.data_hard_start + XDP_PACKET_HEADROOM;
@@ -568,7 +569,7 @@ static u32 xp_alloc_reused(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u3
 	i = nb_entries;
 	while (i--) {
 		xskb = list_first_entry(&pool->free_list, struct xdp_buff_xsk, free_list_node);
-		list_del(&xskb->free_list_node);
+		list_del_init(&xskb->free_list_node);
 
 		*xdp = &xskb->xdp;
 		xdp++;
@@ -615,6 +616,9 @@ EXPORT_SYMBOL(xp_can_alloc);
 
 void xp_free(struct xdp_buff_xsk *xskb)
 {
+	if (!list_empty(&xskb->free_list_node))
+		return;
+
 	xskb->pool->free_list_cnt++;
 	list_add(&xskb->free_list_node, &xskb->pool->free_list);
 }
diff --git a/samples/Kconfig b/samples/Kconfig
index bec3528aa2de..43d2e9aa557f 100644
--- a/samples/Kconfig
+++ b/samples/Kconfig
@@ -31,6 +31,15 @@ config SAMPLE_FTRACE_DIRECT
 	  This builds an ftrace direct function example
 	  that hooks to wake_up_process and prints the parameters.
 
+config SAMPLE_FTRACE_DIRECT_MULTI
+	tristate "Build register_ftrace_direct_multi() example"
+	depends on DYNAMIC_FTRACE_WITH_DIRECT_CALLS && m
+	depends on HAVE_SAMPLE_FTRACE_DIRECT_MULTI
+	help
+	  This builds an ftrace direct function example
+	  that hooks to wake_up_process and schedule, and prints
+	  the function addresses.
+
 config SAMPLE_TRACE_ARRAY
         tristate "Build sample module for kernel access to Ftrace instancess"
 	depends on EVENT_TRACING && m
@@ -237,5 +246,5 @@ endif # SAMPLES
 config HAVE_SAMPLE_FTRACE_DIRECT
 	bool
 
-config HAVE_SAMPLE_FTRACE_MULTI_DIRECT
+config HAVE_SAMPLE_FTRACE_DIRECT_MULTI
 	bool
diff --git a/samples/Makefile b/samples/Makefile
index b7b98307c2b4..4bcd6b93bffa 100644
--- a/samples/Makefile
+++ b/samples/Makefile
@@ -22,7 +22,7 @@ subdir-$(CONFIG_SAMPLE_TIMER)		+= timers
 obj-$(CONFIG_SAMPLE_TRACE_EVENTS)	+= trace_events/
 obj-$(CONFIG_SAMPLE_TRACE_PRINTK)	+= trace_printk/
 obj-$(CONFIG_SAMPLE_FTRACE_DIRECT)	+= ftrace/
-obj-$(CONFIG_SAMPLE_FTRACE_MULTI_DIRECT) += ftrace/
+obj-$(CONFIG_SAMPLE_FTRACE_DIRECT_MULTI) += ftrace/
 obj-$(CONFIG_SAMPLE_TRACE_ARRAY)	+= ftrace/
 subdir-$(CONFIG_SAMPLE_UHID)		+= uhid
 obj-$(CONFIG_VIDEO_PCI_SKELETON)	+= v4l/
diff --git a/samples/bpf/hbm_kern.h b/samples/bpf/hbm_kern.h
index 722b3fadb467..1752a46a2b05 100644
--- a/samples/bpf/hbm_kern.h
+++ b/samples/bpf/hbm_kern.h
@@ -9,8 +9,6 @@
  * Include file for sample Host Bandwidth Manager (HBM) BPF programs
  */
 #define KBUILD_MODNAME "foo"
-#include <stddef.h>
-#include <stdbool.h>
 #include <uapi/linux/bpf.h>
 #include <uapi/linux/if_ether.h>
 #include <uapi/linux/if_packet.h>
diff --git a/samples/bpf/xdp_redirect_cpu_user.c b/samples/bpf/xdp_redirect_cpu_user.c
index d84e6949007c..a81704d3317b 100644
--- a/samples/bpf/xdp_redirect_cpu_user.c
+++ b/samples/bpf/xdp_redirect_cpu_user.c
@@ -309,7 +309,6 @@ int main(int argc, char **argv)
 	const char *mprog_filename = NULL, *mprog_name = NULL;
 	struct xdp_redirect_cpu *skel;
 	struct bpf_map_info info = {};
-	char ifname_buf[IF_NAMESIZE];
 	struct bpf_cpumap_val value;
 	__u32 infosz = sizeof(info);
 	int ret = EXIT_FAIL_OPTION;
@@ -390,10 +389,10 @@ int main(int argc, char **argv)
 		case 'd':
 			if (strlen(optarg) >= IF_NAMESIZE) {
 				fprintf(stderr, "-d/--dev name too long\n");
+				usage(argv, long_options, __doc__, mask, true, skel->obj);
 				goto end_cpu;
 			}
-			safe_strncpy(ifname_buf, optarg, strlen(ifname_buf));
-			ifindex = if_nametoindex(ifname_buf);
+			ifindex = if_nametoindex(optarg);
 			if (!ifindex)
 				ifindex = strtoul(optarg, NULL, 0);
 			if (!ifindex) {
diff --git a/samples/bpf/xdp_sample_user.c b/samples/bpf/xdp_sample_user.c
index b32d82178199..8740838e7767 100644
--- a/samples/bpf/xdp_sample_user.c
+++ b/samples/bpf/xdp_sample_user.c
@@ -120,7 +120,10 @@ struct sample_output {
 		__u64 xmit;
 	} totals;
 	struct {
-		__u64 pps;
+		union {
+			__u64 pps;
+			__u64 num;
+		};
 		__u64 drop;
 		__u64 err;
 	} rx_cnt;
@@ -1322,7 +1325,7 @@ int sample_install_xdp(struct bpf_program *xdp_prog, int ifindex, bool generic,
 
 static void sample_summary_print(void)
 {
-	double period = sample_out.rx_cnt.pps;
+	double num = sample_out.rx_cnt.num;
 
 	if (sample_out.totals.rx) {
 		double pkts = sample_out.totals.rx;
@@ -1330,7 +1333,7 @@ static void sample_summary_print(void)
 		print_always("  Packets received    : %'-10llu\n",
 			     sample_out.totals.rx);
 		print_always("  Average packets/s   : %'-10.0f\n",
-			     sample_round(pkts / period));
+			     sample_round(pkts / num));
 	}
 	if (sample_out.totals.redir) {
 		double pkts = sample_out.totals.redir;
@@ -1338,7 +1341,7 @@ static void sample_summary_print(void)
 		print_always("  Packets redirected  : %'-10llu\n",
 			     sample_out.totals.redir);
 		print_always("  Average redir/s     : %'-10.0f\n",
-			     sample_round(pkts / period));
+			     sample_round(pkts / num));
 	}
 	if (sample_out.totals.drop)
 		print_always("  Rx dropped          : %'-10llu\n",
@@ -1355,7 +1358,7 @@ static void sample_summary_print(void)
 		print_always("  Packets transmitted : %'-10llu\n",
 			     sample_out.totals.xmit);
 		print_always("  Average transmit/s  : %'-10.0f\n",
-			     sample_round(pkts / period));
+			     sample_round(pkts / num));
 	}
 }
 
@@ -1422,7 +1425,7 @@ static int sample_stats_collect(struct stats_record *rec)
 	return 0;
 }
 
-static void sample_summary_update(struct sample_output *out, int interval)
+static void sample_summary_update(struct sample_output *out)
 {
 	sample_out.totals.rx += out->totals.rx;
 	sample_out.totals.redir += out->totals.redir;
@@ -1430,12 +1433,11 @@ static void sample_summary_update(struct sample_output *out, int interval)
 	sample_out.totals.drop_xmit += out->totals.drop_xmit;
 	sample_out.totals.err += out->totals.err;
 	sample_out.totals.xmit += out->totals.xmit;
-	sample_out.rx_cnt.pps += interval;
+	sample_out.rx_cnt.num++;
 }
 
 static void sample_stats_print(int mask, struct stats_record *cur,
-			       struct stats_record *prev, char *prog_name,
-			       int interval)
+			       struct stats_record *prev, char *prog_name)
 {
 	struct sample_output out = {};
 
@@ -1452,7 +1454,7 @@ static void sample_stats_print(int mask, struct stats_record *cur,
 	else if (mask & SAMPLE_DEVMAP_XMIT_CNT_MULTI)
 		stats_get_devmap_xmit_multi(cur, prev, 0, &out,
 					    mask & SAMPLE_DEVMAP_XMIT_CNT);
-	sample_summary_update(&out, interval);
+	sample_summary_update(&out);
 
 	stats_print(prog_name, mask, cur, prev, &out);
 }
@@ -1495,7 +1497,7 @@ static void swap(struct stats_record **a, struct stats_record **b)
 }
 
 static int sample_timer_cb(int timerfd, struct stats_record **rec,
-			   struct stats_record **prev, int interval)
+			   struct stats_record **prev)
 {
 	char line[64] = "Summary";
 	int ret;
@@ -1524,7 +1526,7 @@ static int sample_timer_cb(int timerfd, struct stats_record **rec,
 		snprintf(line, sizeof(line), "%s->%s", f ?: "?", t ?: "?");
 	}
 
-	sample_stats_print(sample_mask, *rec, *prev, line, interval);
+	sample_stats_print(sample_mask, *rec, *prev, line);
 	return 0;
 }
 
@@ -1579,7 +1581,7 @@ int sample_run(int interval, void (*post_cb)(void *), void *ctx)
 		if (pfd[0].revents & POLLIN)
 			ret = sample_signal_cb();
 		else if (pfd[1].revents & POLLIN)
-			ret = sample_timer_cb(timerfd, &rec, &prev, interval);
+			ret = sample_timer_cb(timerfd, &rec, &prev);
 
 		if (ret)
 			break;
diff --git a/samples/ftrace/Makefile b/samples/ftrace/Makefile
index e8a3f8520a44..faf8cdb79c5f 100644
--- a/samples/ftrace/Makefile
+++ b/samples/ftrace/Makefile
@@ -3,7 +3,8 @@
 obj-$(CONFIG_SAMPLE_FTRACE_DIRECT) += ftrace-direct.o
 obj-$(CONFIG_SAMPLE_FTRACE_DIRECT) += ftrace-direct-too.o
 obj-$(CONFIG_SAMPLE_FTRACE_DIRECT) += ftrace-direct-modify.o
-obj-$(CONFIG_SAMPLE_FTRACE_MULTI_DIRECT) += ftrace-direct-multi.o
+obj-$(CONFIG_SAMPLE_FTRACE_DIRECT_MULTI) += ftrace-direct-multi.o
+obj-$(CONFIG_SAMPLE_FTRACE_DIRECT_MULTI) += ftrace-direct-multi-modify.o
 
 CFLAGS_sample-trace-array.o := -I$(src)
 obj-$(CONFIG_SAMPLE_TRACE_ARRAY) += sample-trace-array.o
diff --git a/samples/ftrace/ftrace-direct-multi-modify.c b/samples/ftrace/ftrace-direct-multi-modify.c
new file mode 100644
index 000000000000..91bc42a7adb9
--- /dev/null
+++ b/samples/ftrace/ftrace-direct-multi-modify.c
@@ -0,0 +1,152 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/module.h>
+#include <linux/kthread.h>
+#include <linux/ftrace.h>
+#include <asm/asm-offsets.h>
+
+void my_direct_func1(unsigned long ip)
+{
+	trace_printk("my direct func1 ip %lx\n", ip);
+}
+
+void my_direct_func2(unsigned long ip)
+{
+	trace_printk("my direct func2 ip %lx\n", ip);
+}
+
+extern void my_tramp1(void *);
+extern void my_tramp2(void *);
+
+#ifdef CONFIG_X86_64
+
+asm (
+"	.pushsection    .text, \"ax\", @progbits\n"
+"	.type		my_tramp1, @function\n"
+"	.globl		my_tramp1\n"
+"   my_tramp1:"
+"	pushq %rbp\n"
+"	movq %rsp, %rbp\n"
+"	pushq %rdi\n"
+"	movq 8(%rbp), %rdi\n"
+"	call my_direct_func1\n"
+"	popq %rdi\n"
+"	leave\n"
+"	ret\n"
+"	.size		my_tramp1, .-my_tramp1\n"
+"	.type		my_tramp2, @function\n"
+"\n"
+"	.globl		my_tramp2\n"
+"   my_tramp2:"
+"	pushq %rbp\n"
+"	movq %rsp, %rbp\n"
+"	pushq %rdi\n"
+"	movq 8(%rbp), %rdi\n"
+"	call my_direct_func2\n"
+"	popq %rdi\n"
+"	leave\n"
+"	ret\n"
+"	.size		my_tramp2, .-my_tramp2\n"
+"	.popsection\n"
+);
+
+#endif /* CONFIG_X86_64 */
+
+#ifdef CONFIG_S390
+
+asm (
+"       .pushsection    .text, \"ax\", @progbits\n"
+"       .type           my_tramp1, @function\n"
+"       .globl          my_tramp1\n"
+"   my_tramp1:"
+"       lgr             %r1,%r15\n"
+"       stmg            %r0,%r5,"__stringify(__SF_GPRS)"(%r15)\n"
+"       stg             %r14,"__stringify(__SF_GPRS+8*8)"(%r15)\n"
+"       aghi            %r15,"__stringify(-STACK_FRAME_OVERHEAD)"\n"
+"       stg             %r1,"__stringify(__SF_BACKCHAIN)"(%r15)\n"
+"       lgr             %r2,%r0\n"
+"       brasl           %r14,my_direct_func1\n"
+"       aghi            %r15,"__stringify(STACK_FRAME_OVERHEAD)"\n"
+"       lmg             %r0,%r5,"__stringify(__SF_GPRS)"(%r15)\n"
+"       lg              %r14,"__stringify(__SF_GPRS+8*8)"(%r15)\n"
+"       lgr             %r1,%r0\n"
+"       br              %r1\n"
+"       .size           my_tramp1, .-my_tramp1\n"
+"\n"
+"       .type           my_tramp2, @function\n"
+"       .globl          my_tramp2\n"
+"   my_tramp2:"
+"       lgr             %r1,%r15\n"
+"       stmg            %r0,%r5,"__stringify(__SF_GPRS)"(%r15)\n"
+"       stg             %r14,"__stringify(__SF_GPRS+8*8)"(%r15)\n"
+"       aghi            %r15,"__stringify(-STACK_FRAME_OVERHEAD)"\n"
+"       stg             %r1,"__stringify(__SF_BACKCHAIN)"(%r15)\n"
+"       lgr             %r2,%r0\n"
+"       brasl           %r14,my_direct_func2\n"
+"       aghi            %r15,"__stringify(STACK_FRAME_OVERHEAD)"\n"
+"       lmg             %r0,%r5,"__stringify(__SF_GPRS)"(%r15)\n"
+"       lg              %r14,"__stringify(__SF_GPRS+8*8)"(%r15)\n"
+"       lgr             %r1,%r0\n"
+"       br              %r1\n"
+"       .size           my_tramp2, .-my_tramp2\n"
+"       .popsection\n"
+);
+
+#endif /* CONFIG_S390 */
+
+static unsigned long my_tramp = (unsigned long)my_tramp1;
+static unsigned long tramps[2] = {
+	(unsigned long)my_tramp1,
+	(unsigned long)my_tramp2,
+};
+
+static struct ftrace_ops direct;
+
+static int simple_thread(void *arg)
+{
+	static int t;
+	int ret = 0;
+
+	while (!kthread_should_stop()) {
+		set_current_state(TASK_INTERRUPTIBLE);
+		schedule_timeout(2 * HZ);
+
+		if (ret)
+			continue;
+		t ^= 1;
+		ret = modify_ftrace_direct_multi(&direct, tramps[t]);
+		if (!ret)
+			my_tramp = tramps[t];
+		WARN_ON_ONCE(ret);
+	}
+
+	return 0;
+}
+
+static struct task_struct *simple_tsk;
+
+static int __init ftrace_direct_multi_init(void)
+{
+	int ret;
+
+	ftrace_set_filter_ip(&direct, (unsigned long) wake_up_process, 0, 0);
+	ftrace_set_filter_ip(&direct, (unsigned long) schedule, 0, 0);
+
+	ret = register_ftrace_direct_multi(&direct, my_tramp);
+
+	if (!ret)
+		simple_tsk = kthread_run(simple_thread, NULL, "event-sample-fn");
+	return ret;
+}
+
+static void __exit ftrace_direct_multi_exit(void)
+{
+	kthread_stop(simple_tsk);
+	unregister_ftrace_direct_multi(&direct, my_tramp);
+}
+
+module_init(ftrace_direct_multi_init);
+module_exit(ftrace_direct_multi_exit);
+
+MODULE_AUTHOR("Jiri Olsa");
+MODULE_DESCRIPTION("Example use case of using modify_ftrace_direct_multi()");
+MODULE_LICENSE("GPL");
diff --git a/samples/ftrace/ftrace-direct-multi.c b/samples/ftrace/ftrace-direct-multi.c
index b6d7806b400e..2fafc9afcbf0 100644
--- a/samples/ftrace/ftrace-direct-multi.c
+++ b/samples/ftrace/ftrace-direct-multi.c
@@ -4,6 +4,7 @@
 #include <linux/mm.h> /* for handle_mm_fault() */
 #include <linux/ftrace.h>
 #include <linux/sched/stat.h>
+#include <asm/asm-offsets.h>
 
 extern void my_direct_func(unsigned long ip);
 
@@ -14,6 +15,8 @@ void my_direct_func(unsigned long ip)
 
 extern void my_tramp(void *);
 
+#ifdef CONFIG_X86_64
+
 asm (
 "	.pushsection    .text, \"ax\", @progbits\n"
 "	.type		my_tramp, @function\n"
@@ -31,6 +34,33 @@ asm (
 "	.popsection\n"
 );
 
+#endif /* CONFIG_X86_64 */
+
+#ifdef CONFIG_S390
+
+asm (
+"	.pushsection	.text, \"ax\", @progbits\n"
+"	.type		my_tramp, @function\n"
+"	.globl		my_tramp\n"
+"   my_tramp:"
+"	lgr		%r1,%r15\n"
+"	stmg		%r0,%r5,"__stringify(__SF_GPRS)"(%r15)\n"
+"	stg		%r14,"__stringify(__SF_GPRS+8*8)"(%r15)\n"
+"	aghi		%r15,"__stringify(-STACK_FRAME_OVERHEAD)"\n"
+"	stg		%r1,"__stringify(__SF_BACKCHAIN)"(%r15)\n"
+"	lgr		%r2,%r0\n"
+"	brasl		%r14,my_direct_func\n"
+"	aghi		%r15,"__stringify(STACK_FRAME_OVERHEAD)"\n"
+"	lmg		%r0,%r5,"__stringify(__SF_GPRS)"(%r15)\n"
+"	lg		%r14,"__stringify(__SF_GPRS+8*8)"(%r15)\n"
+"	lgr		%r1,%r0\n"
+"	br		%r1\n"
+"	.size		my_tramp, .-my_tramp\n"
+"	.popsection\n"
+);
+
+#endif /* CONFIG_S390 */
+
 static struct ftrace_ops direct;
 
 static int __init ftrace_direct_multi_init(void)
diff --git a/scripts/coccinelle/misc/do_div.cocci b/scripts/coccinelle/misc/do_div.cocci
new file mode 100644
index 000000000000..79db083c5208
--- /dev/null
+++ b/scripts/coccinelle/misc/do_div.cocci
@@ -0,0 +1,155 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/// do_div() does a 64-by-32 division.
+/// When the divisor is long, unsigned long, u64, or s64,
+/// do_div() truncates it to 32 bits, this means it can test
+/// non-zero and be truncated to 0 for division on 64bit platforms.
+///
+//# This makes an effort to find those inappropriate do_div() calls.
+//
+// Confidence: Moderate
+// Copyright: (C) 2020 Wen Yang, Alibaba.
+// Comments:
+// Options: --no-includes --include-headers
+
+virtual context
+virtual org
+virtual report
+
+@initialize:python@
+@@
+
+def get_digit_type_and_value(str):
+    is_digit = False
+    value = 0
+
+    try:
+        if (str.isdigit()):
+           is_digit = True
+           value =  int(str, 0)
+        elif (str.upper().endswith('ULL')):
+           is_digit = True
+           value = int(str[:-3], 0)
+        elif (str.upper().endswith('LL')):
+           is_digit = True
+           value = int(str[:-2], 0)
+        elif (str.upper().endswith('UL')):
+           is_digit = True
+           value = int(str[:-2], 0)
+        elif (str.upper().endswith('L')):
+           is_digit = True
+           value = int(str[:-1], 0)
+        elif (str.upper().endswith('U')):
+           is_digit = True
+           value = int(str[:-1], 0)
+    except Exception as e:
+          print('Error:',e)
+          is_digit = False
+          value = 0
+    finally:
+        return is_digit, value
+
+def filter_out_safe_constants(str):
+    is_digit, value = get_digit_type_and_value(str)
+    if (is_digit):
+        if (value >= 0x100000000):
+            return True
+        else:
+            return False
+    else:
+        return True
+
+def construct_warnings(suggested_fun):
+    msg="WARNING: do_div() does a 64-by-32 division, please consider using %s instead."
+    return  msg % suggested_fun
+
+@depends on context@
+expression f;
+long l: script:python() { filter_out_safe_constants(l) };
+unsigned long ul : script:python() { filter_out_safe_constants(ul) };
+u64 ul64 : script:python() { filter_out_safe_constants(ul64) };
+s64 sl64 : script:python() { filter_out_safe_constants(sl64) };
+
+@@
+(
+* do_div(f, l);
+|
+* do_div(f, ul);
+|
+* do_div(f, ul64);
+|
+* do_div(f, sl64);
+)
+
+@r depends on (org || report)@
+expression f;
+position p;
+long l: script:python() { filter_out_safe_constants(l) };
+unsigned long ul : script:python() { filter_out_safe_constants(ul) };
+u64 ul64 : script:python() { filter_out_safe_constants(ul64) };
+s64 sl64 : script:python() { filter_out_safe_constants(sl64) };
+@@
+(
+do_div@p(f, l);
+|
+do_div@p(f, ul);
+|
+do_div@p(f, ul64);
+|
+do_div@p(f, sl64);
+)
+
+@script:python depends on org@
+p << r.p;
+ul << r.ul;
+@@
+
+coccilib.org.print_todo(p[0], construct_warnings("div64_ul"))
+
+@script:python depends on org@
+p << r.p;
+l << r.l;
+@@
+
+coccilib.org.print_todo(p[0], construct_warnings("div64_long"))
+
+@script:python depends on org@
+p << r.p;
+ul64 << r.ul64;
+@@
+
+coccilib.org.print_todo(p[0], construct_warnings("div64_u64"))
+
+@script:python depends on org@
+p << r.p;
+sl64 << r.sl64;
+@@
+
+coccilib.org.print_todo(p[0], construct_warnings("div64_s64"))
+
+@script:python depends on report@
+p << r.p;
+ul << r.ul;
+@@
+
+coccilib.report.print_report(p[0], construct_warnings("div64_ul"))
+
+@script:python depends on report@
+p << r.p;
+l << r.l;
+@@
+
+coccilib.report.print_report(p[0], construct_warnings("div64_long"))
+
+@script:python depends on report@
+p << r.p;
+sl64 << r.sl64;
+@@
+
+coccilib.report.print_report(p[0], construct_warnings("div64_s64"))
+
+@script:python depends on report@
+p << r.p;
+ul64 << r.ul64;
+@@
+
+coccilib.report.print_report(p[0], construct_warnings("div64_u64"))
diff --git a/scripts/mod/devicetable-offsets.c b/scripts/mod/devicetable-offsets.c
index cc3625617a0e..c0d3bcb99138 100644
--- a/scripts/mod/devicetable-offsets.c
+++ b/scripts/mod/devicetable-offsets.c
@@ -259,5 +259,8 @@ int main(void)
 	DEVID_FIELD(dfl_device_id, type);
 	DEVID_FIELD(dfl_device_id, feature_id);
 
+	DEVID(ishtp_device_id);
+	DEVID_FIELD(ishtp_device_id, guid);
+
 	return 0;
 }
diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c
index 49aba862073e..5258247d78ac 100644
--- a/scripts/mod/file2alias.c
+++ b/scripts/mod/file2alias.c
@@ -115,6 +115,17 @@ static inline void add_uuid(char *str, uuid_le uuid)
 		uuid.b[12], uuid.b[13], uuid.b[14], uuid.b[15]);
 }
 
+static inline void add_guid(char *str, guid_t guid)
+{
+	int len = strlen(str);
+
+	sprintf(str + len, "%02X%02X%02X%02X-%02X%02X-%02X%02X-%02X%02X-%02X%02X%02X%02X%02X%02X",
+		guid.b[3], guid.b[2], guid.b[1], guid.b[0],
+		guid.b[5], guid.b[4], guid.b[7], guid.b[6],
+		guid.b[8], guid.b[9], guid.b[10], guid.b[11],
+		guid.b[12], guid.b[13], guid.b[14], guid.b[15]);
+}
+
 /**
  * Check that sizeof(device_id type) are consistent with size of section
  * in .o file. If in-consistent then userspace and kernel does not agree
@@ -1380,6 +1391,18 @@ static int do_mhi_entry(const char *filename, void *symval, char *alias)
 	return 1;
 }
 
+/* Looks like: ishtp:{guid} */
+static int do_ishtp_entry(const char *filename, void *symval, char *alias)
+{
+	DEF_FIELD(symval, ishtp_device_id, guid);
+
+	strcpy(alias, ISHTP_MODULE_PREFIX "{");
+	add_guid(alias, guid);
+	strcat(alias, "}");
+
+	return 1;
+}
+
 static int do_auxiliary_entry(const char *filename, void *symval, char *alias)
 {
 	DEF_FIELD_ADDR(symval, auxiliary_device_id, name);
@@ -1499,6 +1522,7 @@ static const struct devtable devtable[] = {
 	{"auxiliary", SIZE_auxiliary_device_id, do_auxiliary_entry},
 	{"ssam", SIZE_ssam_device_id, do_ssam_entry},
 	{"dfl", SIZE_dfl_device_id, do_dfl_entry},
+	{"ishtp", SIZE_ishtp_device_id, do_ishtp_entry},
 };
 
 /* Create MODULE_ALIAS() statements.
diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl
index 7d631aaa0ae1..3ccb2c70add4 100755
--- a/scripts/recordmcount.pl
+++ b/scripts/recordmcount.pl
@@ -219,7 +219,7 @@ if ($arch eq "x86_64") {
 
 } elsif ($arch eq "s390" && $bits == 64) {
     if ($cc =~ /-DCC_USING_HOTPATCH/) {
-	$mcount_regex = "^\\s*([0-9a-fA-F]+):\\s*c0 04 00 00 00 00\\s*brcl\\s*0,[0-9a-f]+ <([^\+]*)>\$";
+	$mcount_regex = "^\\s*([0-9a-fA-F]+):\\s*c0 04 00 00 00 00\\s*(brcl\\s*0,|jgnop\\s*)[0-9a-f]+ <([^\+]*)>\$";
 	$mcount_adjust = 0;
     }
     $alignment = 8;
diff --git a/scripts/remove-stale-files b/scripts/remove-stale-files
index c3eb81c3f7de..0114c41e6938 100755
--- a/scripts/remove-stale-files
+++ b/scripts/remove-stale-files
@@ -28,4 +28,9 @@ if [ -n "${building_out_of_srctree}" ]; then
 	do
 		rm -f arch/arm/boot/compressed/${f}
 	done
+
+	for f in uart-ath79.c ashldi3.c bswapdi.c bswapsi.c
+	do
+		rm -f arch/mips/boot/compressed/${f}
+	done
 fi
diff --git a/security/security.c b/security/security.c
index 779a9edea0a0..c88167a414b4 100644
--- a/security/security.c
+++ b/security/security.c
@@ -2388,13 +2388,6 @@ void security_sctp_sk_clone(struct sctp_association *asoc, struct sock *sk,
 }
 EXPORT_SYMBOL(security_sctp_sk_clone);
 
-void security_sctp_assoc_established(struct sctp_association *asoc,
-				     struct sk_buff *skb)
-{
-	call_void_hook(sctp_assoc_established, asoc, skb);
-}
-EXPORT_SYMBOL(security_sctp_assoc_established);
-
 #endif	/* CONFIG_SECURITY_NETWORK */
 
 #ifdef CONFIG_SECURITY_INFINIBAND
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 5e5215fe2e83..dde4ecc0cd18 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -611,10 +611,11 @@ static int bad_option(struct superblock_security_struct *sbsec, char flag,
 	return 0;
 }
 
-static int parse_sid(struct super_block *sb, const char *s, u32 *sid)
+static int parse_sid(struct super_block *sb, const char *s, u32 *sid,
+		     gfp_t gfp)
 {
 	int rc = security_context_str_to_sid(&selinux_state, s,
-					     sid, GFP_KERNEL);
+					     sid, gfp);
 	if (rc)
 		pr_warn("SELinux: security_context_str_to_sid"
 		       "(%s) failed for (dev %s, type %s) errno=%d\n",
@@ -685,7 +686,8 @@ static int selinux_set_mnt_opts(struct super_block *sb,
 	 */
 	if (opts) {
 		if (opts->fscontext) {
-			rc = parse_sid(sb, opts->fscontext, &fscontext_sid);
+			rc = parse_sid(sb, opts->fscontext, &fscontext_sid,
+					GFP_KERNEL);
 			if (rc)
 				goto out;
 			if (bad_option(sbsec, FSCONTEXT_MNT, sbsec->sid,
@@ -694,7 +696,8 @@ static int selinux_set_mnt_opts(struct super_block *sb,
 			sbsec->flags |= FSCONTEXT_MNT;
 		}
 		if (opts->context) {
-			rc = parse_sid(sb, opts->context, &context_sid);
+			rc = parse_sid(sb, opts->context, &context_sid,
+					GFP_KERNEL);
 			if (rc)
 				goto out;
 			if (bad_option(sbsec, CONTEXT_MNT, sbsec->mntpoint_sid,
@@ -703,7 +706,8 @@ static int selinux_set_mnt_opts(struct super_block *sb,
 			sbsec->flags |= CONTEXT_MNT;
 		}
 		if (opts->rootcontext) {
-			rc = parse_sid(sb, opts->rootcontext, &rootcontext_sid);
+			rc = parse_sid(sb, opts->rootcontext, &rootcontext_sid,
+					GFP_KERNEL);
 			if (rc)
 				goto out;
 			if (bad_option(sbsec, ROOTCONTEXT_MNT, root_isec->sid,
@@ -712,7 +716,8 @@ static int selinux_set_mnt_opts(struct super_block *sb,
 			sbsec->flags |= ROOTCONTEXT_MNT;
 		}
 		if (opts->defcontext) {
-			rc = parse_sid(sb, opts->defcontext, &defcontext_sid);
+			rc = parse_sid(sb, opts->defcontext, &defcontext_sid,
+					GFP_KERNEL);
 			if (rc)
 				goto out;
 			if (bad_option(sbsec, DEFCONTEXT_MNT, sbsec->def_sid,
@@ -2702,14 +2707,14 @@ static int selinux_sb_mnt_opts_compat(struct super_block *sb, void *mnt_opts)
 		return (sbsec->flags & SE_MNTMASK) ? 1 : 0;
 
 	if (opts->fscontext) {
-		rc = parse_sid(sb, opts->fscontext, &sid);
+		rc = parse_sid(sb, opts->fscontext, &sid, GFP_NOWAIT);
 		if (rc)
 			return 1;
 		if (bad_option(sbsec, FSCONTEXT_MNT, sbsec->sid, sid))
 			return 1;
 	}
 	if (opts->context) {
-		rc = parse_sid(sb, opts->context, &sid);
+		rc = parse_sid(sb, opts->context, &sid, GFP_NOWAIT);
 		if (rc)
 			return 1;
 		if (bad_option(sbsec, CONTEXT_MNT, sbsec->mntpoint_sid, sid))
@@ -2719,14 +2724,14 @@ static int selinux_sb_mnt_opts_compat(struct super_block *sb, void *mnt_opts)
 		struct inode_security_struct *root_isec;
 
 		root_isec = backing_inode_security(sb->s_root);
-		rc = parse_sid(sb, opts->rootcontext, &sid);
+		rc = parse_sid(sb, opts->rootcontext, &sid, GFP_NOWAIT);
 		if (rc)
 			return 1;
 		if (bad_option(sbsec, ROOTCONTEXT_MNT, root_isec->sid, sid))
 			return 1;
 	}
 	if (opts->defcontext) {
-		rc = parse_sid(sb, opts->defcontext, &sid);
+		rc = parse_sid(sb, opts->defcontext, &sid, GFP_NOWAIT);
 		if (rc)
 			return 1;
 		if (bad_option(sbsec, DEFCONTEXT_MNT, sbsec->def_sid, sid))
@@ -2749,14 +2754,14 @@ static int selinux_sb_remount(struct super_block *sb, void *mnt_opts)
 		return 0;
 
 	if (opts->fscontext) {
-		rc = parse_sid(sb, opts->fscontext, &sid);
+		rc = parse_sid(sb, opts->fscontext, &sid, GFP_KERNEL);
 		if (rc)
 			return rc;
 		if (bad_option(sbsec, FSCONTEXT_MNT, sbsec->sid, sid))
 			goto out_bad_option;
 	}
 	if (opts->context) {
-		rc = parse_sid(sb, opts->context, &sid);
+		rc = parse_sid(sb, opts->context, &sid, GFP_KERNEL);
 		if (rc)
 			return rc;
 		if (bad_option(sbsec, CONTEXT_MNT, sbsec->mntpoint_sid, sid))
@@ -2765,14 +2770,14 @@ static int selinux_sb_remount(struct super_block *sb, void *mnt_opts)
 	if (opts->rootcontext) {
 		struct inode_security_struct *root_isec;
 		root_isec = backing_inode_security(sb->s_root);
-		rc = parse_sid(sb, opts->rootcontext, &sid);
+		rc = parse_sid(sb, opts->rootcontext, &sid, GFP_KERNEL);
 		if (rc)
 			return rc;
 		if (bad_option(sbsec, ROOTCONTEXT_MNT, root_isec->sid, sid))
 			goto out_bad_option;
 	}
 	if (opts->defcontext) {
-		rc = parse_sid(sb, opts->defcontext, &sid);
+		rc = parse_sid(sb, opts->defcontext, &sid, GFP_KERNEL);
 		if (rc)
 			return rc;
 		if (bad_option(sbsec, DEFCONTEXT_MNT, sbsec->def_sid, sid))
@@ -5502,8 +5507,7 @@ static void selinux_sctp_sk_clone(struct sctp_association *asoc, struct sock *sk
 	if (!selinux_policycap_extsockclass())
 		return selinux_sk_clone_security(sk, newsk);
 
-	if (asoc->secid != SECSID_WILD)
-		newsksec->sid = asoc->secid;
+	newsksec->sid = asoc->secid;
 	newsksec->peer_sid = asoc->peer_secid;
 	newsksec->sclass = sksec->sclass;
 	selinux_netlbl_sctp_sk_clone(sk, newsk);
@@ -5559,16 +5563,6 @@ static void selinux_inet_conn_established(struct sock *sk, struct sk_buff *skb)
 	selinux_skb_peerlbl_sid(skb, family, &sksec->peer_sid);
 }
 
-static void selinux_sctp_assoc_established(struct sctp_association *asoc,
-					   struct sk_buff *skb)
-{
-	struct sk_security_struct *sksec = asoc->base.sk->sk_security;
-
-	selinux_inet_conn_established(asoc->base.sk, skb);
-	asoc->peer_secid = sksec->peer_sid;
-	asoc->secid = SECSID_WILD;
-}
-
 static int selinux_secmark_relabel_packet(u32 sid)
 {
 	const struct task_security_struct *__tsec;
@@ -5791,7 +5785,7 @@ static unsigned int selinux_ip_postroute_compat(struct sk_buff *skb,
 	struct sk_security_struct *sksec;
 	struct common_audit_data ad;
 	struct lsm_network_audit net = {0,};
-	u8 proto;
+	u8 proto = 0;
 
 	sk = skb_to_full_sk(skb);
 	if (sk == NULL)
@@ -7239,7 +7233,6 @@ static struct security_hook_list selinux_hooks[] __lsm_ro_after_init = {
 	LSM_HOOK_INIT(sctp_assoc_request, selinux_sctp_assoc_request),
 	LSM_HOOK_INIT(sctp_sk_clone, selinux_sctp_sk_clone),
 	LSM_HOOK_INIT(sctp_bind_connect, selinux_sctp_bind_connect),
-	LSM_HOOK_INIT(sctp_assoc_established, selinux_sctp_assoc_established),
 	LSM_HOOK_INIT(inet_conn_request, selinux_inet_conn_request),
 	LSM_HOOK_INIT(inet_csk_clone, selinux_inet_csk_clone),
 	LSM_HOOK_INIT(inet_conn_established, selinux_inet_conn_established),
diff --git a/security/selinux/ss/hashtab.c b/security/selinux/ss/hashtab.c
index 727c3b484bd3..0ae4e4e57a40 100644
--- a/security/selinux/ss/hashtab.c
+++ b/security/selinux/ss/hashtab.c
@@ -31,13 +31,20 @@ static u32 hashtab_compute_size(u32 nel)
 
 int hashtab_init(struct hashtab *h, u32 nel_hint)
 {
-	h->size = hashtab_compute_size(nel_hint);
+	u32 size = hashtab_compute_size(nel_hint);
+
+	/* should already be zeroed, but better be safe */
 	h->nel = 0;
-	if (!h->size)
-		return 0;
+	h->size = 0;
+	h->htable = NULL;
 
-	h->htable = kcalloc(h->size, sizeof(*h->htable), GFP_KERNEL);
-	return h->htable ? 0 : -ENOMEM;
+	if (size) {
+		h->htable = kcalloc(size, sizeof(*h->htable), GFP_KERNEL);
+		if (!h->htable)
+			return -ENOMEM;
+		h->size = size;
+	}
+	return 0;
 }
 
 int __hashtab_insert(struct hashtab *h, struct hashtab_node **dst,
diff --git a/security/tomoyo/util.c b/security/tomoyo/util.c
index 1da2e3722b12..6799b1122c9d 100644
--- a/security/tomoyo/util.c
+++ b/security/tomoyo/util.c
@@ -1051,10 +1051,11 @@ bool tomoyo_domain_quota_is_ok(struct tomoyo_request_info *r)
 		return false;
 	if (!domain)
 		return true;
+	if (READ_ONCE(domain->flags[TOMOYO_DIF_QUOTA_WARNED]))
+		return false;
 	list_for_each_entry_rcu(ptr, &domain->acl_info_list, list,
 				srcu_read_lock_held(&tomoyo_ss)) {
 		u16 perm;
-		u8 i;
 
 		if (ptr->is_deleted)
 			continue;
@@ -1065,23 +1066,23 @@ bool tomoyo_domain_quota_is_ok(struct tomoyo_request_info *r)
 		 */
 		switch (ptr->type) {
 		case TOMOYO_TYPE_PATH_ACL:
-			data_race(perm = container_of(ptr, struct tomoyo_path_acl, head)->perm);
+			perm = data_race(container_of(ptr, struct tomoyo_path_acl, head)->perm);
 			break;
 		case TOMOYO_TYPE_PATH2_ACL:
-			data_race(perm = container_of(ptr, struct tomoyo_path2_acl, head)->perm);
+			perm = data_race(container_of(ptr, struct tomoyo_path2_acl, head)->perm);
 			break;
 		case TOMOYO_TYPE_PATH_NUMBER_ACL:
-			data_race(perm = container_of(ptr, struct tomoyo_path_number_acl, head)
+			perm = data_race(container_of(ptr, struct tomoyo_path_number_acl, head)
 				  ->perm);
 			break;
 		case TOMOYO_TYPE_MKDEV_ACL:
-			data_race(perm = container_of(ptr, struct tomoyo_mkdev_acl, head)->perm);
+			perm = data_race(container_of(ptr, struct tomoyo_mkdev_acl, head)->perm);
 			break;
 		case TOMOYO_TYPE_INET_ACL:
-			data_race(perm = container_of(ptr, struct tomoyo_inet_acl, head)->perm);
+			perm = data_race(container_of(ptr, struct tomoyo_inet_acl, head)->perm);
 			break;
 		case TOMOYO_TYPE_UNIX_ACL:
-			data_race(perm = container_of(ptr, struct tomoyo_unix_acl, head)->perm);
+			perm = data_race(container_of(ptr, struct tomoyo_unix_acl, head)->perm);
 			break;
 		case TOMOYO_TYPE_MANUAL_TASK_ACL:
 			perm = 0;
@@ -1089,21 +1090,17 @@ bool tomoyo_domain_quota_is_ok(struct tomoyo_request_info *r)
 		default:
 			perm = 1;
 		}
-		for (i = 0; i < 16; i++)
-			if (perm & (1 << i))
-				count++;
+		count += hweight16(perm);
 	}
 	if (count < tomoyo_profile(domain->ns, domain->profile)->
 	    pref[TOMOYO_PREF_MAX_LEARNING_ENTRY])
 		return true;
-	if (!domain->flags[TOMOYO_DIF_QUOTA_WARNED]) {
-		domain->flags[TOMOYO_DIF_QUOTA_WARNED] = true;
-		/* r->granted = false; */
-		tomoyo_write_log(r, "%s", tomoyo_dif[TOMOYO_DIF_QUOTA_WARNED]);
+	WRITE_ONCE(domain->flags[TOMOYO_DIF_QUOTA_WARNED], true);
+	/* r->granted = false; */
+	tomoyo_write_log(r, "%s", tomoyo_dif[TOMOYO_DIF_QUOTA_WARNED]);
 #ifndef CONFIG_SECURITY_TOMOYO_INSECURE_BUILTIN_SETTING
-		pr_warn("WARNING: Domain '%s' has too many ACLs to hold. Stopped learning mode.\n",
-			domain->domainname->name);
+	pr_warn("WARNING: Domain '%s' has too many ACLs to hold. Stopped learning mode.\n",
+		domain->domainname->name);
 #endif
-	}
 	return false;
 }
diff --git a/sound/core/control_compat.c b/sound/core/control_compat.c
index 470dabc60aa0..edff063e088d 100644
--- a/sound/core/control_compat.c
+++ b/sound/core/control_compat.c
@@ -264,6 +264,7 @@ static int copy_ctl_value_to_user(void __user *userdata,
 				  struct snd_ctl_elem_value *data,
 				  int type, int count)
 {
+	struct snd_ctl_elem_value32 __user *data32 = userdata;
 	int i, size;
 
 	if (type == SNDRV_CTL_ELEM_TYPE_BOOLEAN ||
@@ -280,6 +281,8 @@ static int copy_ctl_value_to_user(void __user *userdata,
 		if (copy_to_user(valuep, data->value.bytes.data, size))
 			return -EFAULT;
 	}
+	if (copy_to_user(&data32->id, &data->id, sizeof(data32->id)))
+		return -EFAULT;
 	return 0;
 }
 
diff --git a/sound/core/jack.c b/sound/core/jack.c
index 32350c6aba84..537df1e98f8a 100644
--- a/sound/core/jack.c
+++ b/sound/core/jack.c
@@ -509,6 +509,10 @@ int snd_jack_new(struct snd_card *card, const char *id, int type,
 		return -ENOMEM;
 
 	jack->id = kstrdup(id, GFP_KERNEL);
+	if (jack->id == NULL) {
+		kfree(jack);
+		return -ENOMEM;
+	}
 
 	/* don't creat input device for phantom jack */
 	if (!phantom_jack) {
diff --git a/sound/core/oss/pcm_oss.c b/sound/core/oss/pcm_oss.c
index 82a818734a5f..20a0a4771b9a 100644
--- a/sound/core/oss/pcm_oss.c
+++ b/sound/core/oss/pcm_oss.c
@@ -147,7 +147,7 @@ snd_pcm_hw_param_value_min(const struct snd_pcm_hw_params *params,
  *
  * Return the maximum value for field PAR.
  */
-static unsigned int
+static int
 snd_pcm_hw_param_value_max(const struct snd_pcm_hw_params *params,
 			   snd_pcm_hw_param_t var, int *dir)
 {
@@ -682,18 +682,24 @@ static int snd_pcm_oss_period_size(struct snd_pcm_substream *substream,
 				   struct snd_pcm_hw_params *oss_params,
 				   struct snd_pcm_hw_params *slave_params)
 {
-	size_t s;
-	size_t oss_buffer_size, oss_period_size, oss_periods;
-	size_t min_period_size, max_period_size;
+	ssize_t s;
+	ssize_t oss_buffer_size;
+	ssize_t oss_period_size, oss_periods;
+	ssize_t min_period_size, max_period_size;
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	size_t oss_frame_size;
 
 	oss_frame_size = snd_pcm_format_physical_width(params_format(oss_params)) *
 			 params_channels(oss_params) / 8;
 
+	oss_buffer_size = snd_pcm_hw_param_value_max(slave_params,
+						     SNDRV_PCM_HW_PARAM_BUFFER_SIZE,
+						     NULL);
+	if (oss_buffer_size <= 0)
+		return -EINVAL;
 	oss_buffer_size = snd_pcm_plug_client_size(substream,
-						   snd_pcm_hw_param_value_max(slave_params, SNDRV_PCM_HW_PARAM_BUFFER_SIZE, NULL)) * oss_frame_size;
-	if (!oss_buffer_size)
+						   oss_buffer_size * oss_frame_size);
+	if (oss_buffer_size <= 0)
 		return -EINVAL;
 	oss_buffer_size = rounddown_pow_of_two(oss_buffer_size);
 	if (atomic_read(&substream->mmap_count)) {
@@ -730,7 +736,7 @@ static int snd_pcm_oss_period_size(struct snd_pcm_substream *substream,
 
 	min_period_size = snd_pcm_plug_client_size(substream,
 						   snd_pcm_hw_param_value_min(slave_params, SNDRV_PCM_HW_PARAM_PERIOD_SIZE, NULL));
-	if (min_period_size) {
+	if (min_period_size > 0) {
 		min_period_size *= oss_frame_size;
 		min_period_size = roundup_pow_of_two(min_period_size);
 		if (oss_period_size < min_period_size)
@@ -739,7 +745,7 @@ static int snd_pcm_oss_period_size(struct snd_pcm_substream *substream,
 
 	max_period_size = snd_pcm_plug_client_size(substream,
 						   snd_pcm_hw_param_value_max(slave_params, SNDRV_PCM_HW_PARAM_PERIOD_SIZE, NULL));
-	if (max_period_size) {
+	if (max_period_size > 0) {
 		max_period_size *= oss_frame_size;
 		max_period_size = rounddown_pow_of_two(max_period_size);
 		if (oss_period_size > max_period_size)
@@ -752,7 +758,7 @@ static int snd_pcm_oss_period_size(struct snd_pcm_substream *substream,
 		oss_periods = substream->oss.setup.periods;
 
 	s = snd_pcm_hw_param_value_max(slave_params, SNDRV_PCM_HW_PARAM_PERIODS, NULL);
-	if (runtime->oss.maxfrags && s > runtime->oss.maxfrags)
+	if (s > 0 && runtime->oss.maxfrags && s > runtime->oss.maxfrags)
 		s = runtime->oss.maxfrags;
 	if (oss_periods > s)
 		oss_periods = s;
@@ -878,8 +884,15 @@ static int snd_pcm_oss_change_params_locked(struct snd_pcm_substream *substream)
 		err = -EINVAL;
 		goto failure;
 	}
-	choose_rate(substream, sparams, runtime->oss.rate);
-	snd_pcm_hw_param_near(substream, sparams, SNDRV_PCM_HW_PARAM_CHANNELS, runtime->oss.channels, NULL);
+
+	err = choose_rate(substream, sparams, runtime->oss.rate);
+	if (err < 0)
+		goto failure;
+	err = snd_pcm_hw_param_near(substream, sparams,
+				    SNDRV_PCM_HW_PARAM_CHANNELS,
+				    runtime->oss.channels, NULL);
+	if (err < 0)
+		goto failure;
 
 	format = snd_pcm_oss_format_from(runtime->oss.format);
 
@@ -1956,7 +1969,7 @@ static int snd_pcm_oss_set_fragment1(struct snd_pcm_substream *substream, unsign
 	if (runtime->oss.subdivision || runtime->oss.fragshift)
 		return -EINVAL;
 	fragshift = val & 0xffff;
-	if (fragshift >= 31)
+	if (fragshift >= 25) /* should be large enough */
 		return -EINVAL;
 	runtime->oss.fragshift = fragshift;
 	runtime->oss.maxfrags = (val >> 16) & 0xffff;
diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c
index 6f30231bdb88..befa9809ff00 100644
--- a/sound/core/rawmidi.c
+++ b/sound/core/rawmidi.c
@@ -447,6 +447,7 @@ static int snd_rawmidi_open(struct inode *inode, struct file *file)
 		err = -ENOMEM;
 		goto __error;
 	}
+	rawmidi_file->user_pversion = 0;
 	init_waitqueue_entry(&wait, current);
 	add_wait_queue(&rmidi->open_wait, &wait);
 	while (1) {
diff --git a/sound/drivers/opl3/opl3_midi.c b/sound/drivers/opl3/opl3_midi.c
index e1b69c65c3c8..e2b7be67f0e3 100644
--- a/sound/drivers/opl3/opl3_midi.c
+++ b/sound/drivers/opl3/opl3_midi.c
@@ -397,7 +397,7 @@ void snd_opl3_note_on(void *p, int note, int vel, struct snd_midi_channel *chan)
 	}
 	if (instr_4op) {
 		vp2 = &opl3->voices[voice + 3];
-		if (vp->state > 0) {
+		if (vp2->state > 0) {
 			opl3_reg = reg_side | (OPL3_REG_KEYON_BLOCK +
 					       voice_offset + 3);
 			reg_val = vp->keyon_reg & ~OPL3_KEYON_BIT;
diff --git a/sound/hda/intel-dsp-config.c b/sound/hda/intel-dsp-config.c
index b9ac9e9e45a4..4208fa8a4db5 100644
--- a/sound/hda/intel-dsp-config.c
+++ b/sound/hda/intel-dsp-config.c
@@ -252,6 +252,11 @@ static const struct config_entry config_table[] = {
 		.flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE,
 		.device = 0x02c8,
 	},
+	{
+		.flags = FLAG_SOF,
+		.device = 0x02c8,
+		.codec_hid = "ESSX8336",
+	},
 /* Cometlake-H */
 	{
 		.flags = FLAG_SOF,
@@ -276,6 +281,11 @@ static const struct config_entry config_table[] = {
 		.flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE,
 		.device = 0x06c8,
 	},
+		{
+		.flags = FLAG_SOF,
+		.device = 0x06c8,
+		.codec_hid = "ESSX8336",
+	},
 #endif
 
 /* Icelake */
@@ -299,6 +309,15 @@ static const struct config_entry config_table[] = {
 	},
 #endif
 
+/* JasperLake */
+#if IS_ENABLED(CONFIG_SND_SOC_SOF_JASPERLAKE)
+	{
+		.flags = FLAG_SOF,
+		.device = 0x4dc8,
+		.codec_hid = "ESSX8336",
+	},
+#endif
+
 /* Tigerlake */
 #if IS_ENABLED(CONFIG_SND_SOC_SOF_TIGERLAKE)
 	{
diff --git a/sound/hda/intel-sdw-acpi.c b/sound/hda/intel-sdw-acpi.c
index c0123bc31c0d..b7758dbe2371 100644
--- a/sound/hda/intel-sdw-acpi.c
+++ b/sound/hda/intel-sdw-acpi.c
@@ -132,8 +132,6 @@ static acpi_status sdw_intel_acpi_cb(acpi_handle handle, u32 level,
 		return AE_NOT_FOUND;
 	}
 
-	info->handle = handle;
-
 	/*
 	 * On some Intel platforms, multiple children of the HDAS
 	 * device can be found, but only one of them is the SoundWire
@@ -144,6 +142,9 @@ static acpi_status sdw_intel_acpi_cb(acpi_handle handle, u32 level,
 	if (FIELD_GET(GENMASK(31, 28), adr) != SDW_LINK_TYPE)
 		return AE_OK; /* keep going */
 
+	/* found the correct SoundWire controller */
+	info->handle = handle;
+
 	/* device found, stop namespace walk */
 	return AE_CTRL_TERMINATE;
 }
@@ -164,8 +165,14 @@ int sdw_intel_acpi_scan(acpi_handle *parent_handle,
 	acpi_status status;
 
 	info->handle = NULL;
+	/*
+	 * In the HDAS ACPI scope, 'SNDW' may be either the child of
+	 * 'HDAS' or the grandchild of 'HDAS'. So let's go through
+	 * the ACPI from 'HDAS' at max depth of 2 to find the 'SNDW'
+	 * device.
+	 */
 	status = acpi_walk_namespace(ACPI_TYPE_DEVICE,
-				     parent_handle, 1,
+				     parent_handle, 2,
 				     sdw_intel_acpi_cb,
 				     NULL, info, NULL);
 	if (ACPI_FAILURE(status) || info->handle == NULL)
diff --git a/sound/pci/cmipci.c b/sound/pci/cmipci.c
index ea20236f35db..9a678b5cf285 100644
--- a/sound/pci/cmipci.c
+++ b/sound/pci/cmipci.c
@@ -3218,7 +3218,6 @@ static int snd_cmipci_probe(struct pci_dev *pci,
 {
 	static int dev;
 	struct snd_card *card;
-	struct cmipci *cm;
 	int err;
 
 	if (dev >= SNDRV_CARDS)
@@ -3229,10 +3228,9 @@ static int snd_cmipci_probe(struct pci_dev *pci,
 	}
 
 	err = snd_devm_card_new(&pci->dev, index[dev], id[dev], THIS_MODULE,
-				sizeof(*cm), &card);
+				sizeof(struct cmipci), &card);
 	if (err < 0)
 		return err;
-	cm = card->private_data;
 	
 	switch (pci->device) {
 	case PCI_DEVICE_ID_CMEDIA_CM8738:
diff --git a/sound/pci/ctxfi/ctamixer.c b/sound/pci/ctxfi/ctamixer.c
index da6e6350ceaf..d074727c3e21 100644
--- a/sound/pci/ctxfi/ctamixer.c
+++ b/sound/pci/ctxfi/ctamixer.c
@@ -23,16 +23,15 @@
 
 #define BLANK_SLOT		4094
 
-static int amixer_master(struct rsc *rsc)
+static void amixer_master(struct rsc *rsc)
 {
 	rsc->conj = 0;
-	return rsc->idx = container_of(rsc, struct amixer, rsc)->idx[0];
+	rsc->idx = container_of(rsc, struct amixer, rsc)->idx[0];
 }
 
-static int amixer_next_conj(struct rsc *rsc)
+static void amixer_next_conj(struct rsc *rsc)
 {
 	rsc->conj++;
-	return container_of(rsc, struct amixer, rsc)->idx[rsc->conj];
 }
 
 static int amixer_index(const struct rsc *rsc)
@@ -331,16 +330,15 @@ int amixer_mgr_destroy(struct amixer_mgr *amixer_mgr)
 
 /* SUM resource management */
 
-static int sum_master(struct rsc *rsc)
+static void sum_master(struct rsc *rsc)
 {
 	rsc->conj = 0;
-	return rsc->idx = container_of(rsc, struct sum, rsc)->idx[0];
+	rsc->idx = container_of(rsc, struct sum, rsc)->idx[0];
 }
 
-static int sum_next_conj(struct rsc *rsc)
+static void sum_next_conj(struct rsc *rsc)
 {
 	rsc->conj++;
-	return container_of(rsc, struct sum, rsc)->idx[rsc->conj];
 }
 
 static int sum_index(const struct rsc *rsc)
diff --git a/sound/pci/ctxfi/ctdaio.c b/sound/pci/ctxfi/ctdaio.c
index f589da045342..7fc720046ce2 100644
--- a/sound/pci/ctxfi/ctdaio.c
+++ b/sound/pci/ctxfi/ctdaio.c
@@ -51,12 +51,12 @@ static const struct daio_rsc_idx idx_20k2[NUM_DAIOTYP] = {
 	[SPDIFIO] = {.left = 0x05, .right = 0x85},
 };
 
-static int daio_master(struct rsc *rsc)
+static void daio_master(struct rsc *rsc)
 {
 	/* Actually, this is not the resource index of DAIO.
 	 * For DAO, it is the input mapper index. And, for DAI,
 	 * it is the output time-slot index. */
-	return rsc->conj = rsc->idx;
+	rsc->conj = rsc->idx;
 }
 
 static int daio_index(const struct rsc *rsc)
@@ -64,19 +64,19 @@ static int daio_index(const struct rsc *rsc)
 	return rsc->conj;
 }
 
-static int daio_out_next_conj(struct rsc *rsc)
+static void daio_out_next_conj(struct rsc *rsc)
 {
-	return rsc->conj += 2;
+	rsc->conj += 2;
 }
 
-static int daio_in_next_conj_20k1(struct rsc *rsc)
+static void daio_in_next_conj_20k1(struct rsc *rsc)
 {
-	return rsc->conj += 0x200;
+	rsc->conj += 0x200;
 }
 
-static int daio_in_next_conj_20k2(struct rsc *rsc)
+static void daio_in_next_conj_20k2(struct rsc *rsc)
 {
-	return rsc->conj += 0x100;
+	rsc->conj += 0x100;
 }
 
 static const struct rsc_ops daio_out_rsc_ops = {
diff --git a/sound/pci/ctxfi/ctresource.c b/sound/pci/ctxfi/ctresource.c
index 81ad26934518..be1d3e61309c 100644
--- a/sound/pci/ctxfi/ctresource.c
+++ b/sound/pci/ctxfi/ctresource.c
@@ -109,18 +109,17 @@ static int audio_ring_slot(const struct rsc *rsc)
     return (rsc->conj << 4) + offset_in_audio_slot_block[rsc->type];
 }
 
-static int rsc_next_conj(struct rsc *rsc)
+static void rsc_next_conj(struct rsc *rsc)
 {
 	unsigned int i;
 	for (i = 0; (i < 8) && (!(rsc->msr & (0x1 << i))); )
 		i++;
 	rsc->conj += (AUDIO_SLOT_BLOCK_NUM >> i);
-	return rsc->conj;
 }
 
-static int rsc_master(struct rsc *rsc)
+static void rsc_master(struct rsc *rsc)
 {
-	return rsc->conj = rsc->idx;
+	rsc->conj = rsc->idx;
 }
 
 static const struct rsc_ops rsc_generic_ops = {
diff --git a/sound/pci/ctxfi/ctresource.h b/sound/pci/ctxfi/ctresource.h
index fdbfd808816d..58553bda44f4 100644
--- a/sound/pci/ctxfi/ctresource.h
+++ b/sound/pci/ctxfi/ctresource.h
@@ -39,8 +39,8 @@ struct rsc {
 };
 
 struct rsc_ops {
-	int (*master)(struct rsc *rsc);	/* Move to master resource */
-	int (*next_conj)(struct rsc *rsc); /* Move to next conjugate resource */
+	void (*master)(struct rsc *rsc); /* Move to master resource */
+	void (*next_conj)(struct rsc *rsc); /* Move to next conjugate resource */
 	int (*index)(const struct rsc *rsc); /* Return the index of resource */
 	/* Return the output slot number */
 	int (*output_slot)(const struct rsc *rsc);
diff --git a/sound/pci/ctxfi/ctsrc.c b/sound/pci/ctxfi/ctsrc.c
index bd4697b44233..4a94b4708a77 100644
--- a/sound/pci/ctxfi/ctsrc.c
+++ b/sound/pci/ctxfi/ctsrc.c
@@ -590,16 +590,15 @@ int src_mgr_destroy(struct src_mgr *src_mgr)
 
 /* SRCIMP resource manager operations */
 
-static int srcimp_master(struct rsc *rsc)
+static void srcimp_master(struct rsc *rsc)
 {
 	rsc->conj = 0;
-	return rsc->idx = container_of(rsc, struct srcimp, rsc)->idx[0];
+	rsc->idx = container_of(rsc, struct srcimp, rsc)->idx[0];
 }
 
-static int srcimp_next_conj(struct rsc *rsc)
+static void srcimp_next_conj(struct rsc *rsc)
 {
 	rsc->conj++;
-	return container_of(rsc, struct srcimp, rsc)->idx[rsc->conj];
 }
 
 static int srcimp_index(const struct rsc *rsc)
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index fe51163f2d82..1b46b599a5cf 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -335,7 +335,10 @@ enum {
 					((pci)->device == 0x0c0c) || \
 					((pci)->device == 0x0d0c) || \
 					((pci)->device == 0x160c) || \
-					((pci)->device == 0x490d))
+					((pci)->device == 0x490d) || \
+					((pci)->device == 0x4f90) || \
+					((pci)->device == 0x4f91) || \
+					((pci)->device == 0x4f92))
 
 #define IS_BXT(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x5a98)
 
@@ -2473,6 +2476,13 @@ static const struct pci_device_id azx_ids[] = {
 	/* DG1 */
 	{ PCI_DEVICE(0x8086, 0x490d),
 	  .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE},
+	/* DG2 */
+	{ PCI_DEVICE(0x8086, 0x4f90),
+	  .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE},
+	{ PCI_DEVICE(0x8086, 0x4f91),
+	  .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE},
+	{ PCI_DEVICE(0x8086, 0x4f92),
+	  .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE},
 	/* Alderlake-S */
 	{ PCI_DEVICE(0x8086, 0x7ad0),
 	  .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE},
diff --git a/sound/pci/hda/hda_local.h b/sound/pci/hda/hda_local.h
index ea8ab8b43337..d22c96eb2f8f 100644
--- a/sound/pci/hda/hda_local.h
+++ b/sound/pci/hda/hda_local.h
@@ -438,6 +438,15 @@ int snd_hda_codec_set_pin_target(struct hda_codec *codec, hda_nid_t nid,
 #define for_each_hda_codec_node(nid, codec) \
 	for ((nid) = (codec)->core.start_nid; (nid) < (codec)->core.end_nid; (nid)++)
 
+/* Set the codec power_state flag to indicate to allow unsol event handling;
+ * see hda_codec_unsol_event() in hda_bind.c.  Calling this might confuse the
+ * state tracking, so use with care.
+ */
+static inline void snd_hda_codec_allow_unsol_events(struct hda_codec *codec)
+{
+	codec->core.dev.power.power_state = PMSG_ON;
+}
+
 /*
  * get widget capabilities
  */
diff --git a/sound/pci/hda/patch_cs8409.c b/sound/pci/hda/patch_cs8409.c
index 31ff11ab868e..039b9f2f8e94 100644
--- a/sound/pci/hda/patch_cs8409.c
+++ b/sound/pci/hda/patch_cs8409.c
@@ -750,6 +750,11 @@ static void cs42l42_resume(struct sub_codec *cs42l42)
 	if (cs42l42->full_scale_vol)
 		cs8409_i2c_write(cs42l42, 0x2001, 0x01);
 
+	/* we have to explicitly allow unsol event handling even during the
+	 * resume phase so that the jack event is processed properly
+	 */
+	snd_hda_codec_allow_unsol_events(cs42l42->codec);
+
 	cs42l42_enable_jack_detect(cs42l42);
 }
 
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index 65d2c5539919..ffcde7409d2a 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -2947,7 +2947,8 @@ static int parse_intel_hdmi(struct hda_codec *codec)
 
 /* Intel Haswell and onwards; audio component with eld notifier */
 static int intel_hsw_common_init(struct hda_codec *codec, hda_nid_t vendor_nid,
-				 const int *port_map, int port_num, int dev_num)
+				 const int *port_map, int port_num, int dev_num,
+				 bool send_silent_stream)
 {
 	struct hdmi_spec *spec;
 	int err;
@@ -2980,7 +2981,7 @@ static int intel_hsw_common_init(struct hda_codec *codec, hda_nid_t vendor_nid,
 	 * Enable silent stream feature, if it is enabled via
 	 * module param or Kconfig option
 	 */
-	if (enable_silent_stream)
+	if (send_silent_stream)
 		spec->send_silent_stream = true;
 
 	return parse_intel_hdmi(codec);
@@ -2988,12 +2989,18 @@ static int intel_hsw_common_init(struct hda_codec *codec, hda_nid_t vendor_nid,
 
 static int patch_i915_hsw_hdmi(struct hda_codec *codec)
 {
-	return intel_hsw_common_init(codec, 0x08, NULL, 0, 3);
+	return intel_hsw_common_init(codec, 0x08, NULL, 0, 3,
+				     enable_silent_stream);
 }
 
 static int patch_i915_glk_hdmi(struct hda_codec *codec)
 {
-	return intel_hsw_common_init(codec, 0x0b, NULL, 0, 3);
+	/*
+	 * Silent stream calls audio component .get_power() from
+	 * .pin_eld_notify(). On GLK this will deadlock in i915 due
+	 * to the audio vs. CDCLK workaround.
+	 */
+	return intel_hsw_common_init(codec, 0x0b, NULL, 0, 3, false);
 }
 
 static int patch_i915_icl_hdmi(struct hda_codec *codec)
@@ -3004,7 +3011,8 @@ static int patch_i915_icl_hdmi(struct hda_codec *codec)
 	 */
 	static const int map[] = {0x0, 0x4, 0x6, 0x8, 0xa, 0xb};
 
-	return intel_hsw_common_init(codec, 0x02, map, ARRAY_SIZE(map), 3);
+	return intel_hsw_common_init(codec, 0x02, map, ARRAY_SIZE(map), 3,
+				     enable_silent_stream);
 }
 
 static int patch_i915_tgl_hdmi(struct hda_codec *codec)
@@ -3016,7 +3024,8 @@ static int patch_i915_tgl_hdmi(struct hda_codec *codec)
 	static const int map[] = {0x4, 0x6, 0x8, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf};
 	int ret;
 
-	ret = intel_hsw_common_init(codec, 0x02, map, ARRAY_SIZE(map), 4);
+	ret = intel_hsw_common_init(codec, 0x02, map, ARRAY_SIZE(map), 4,
+				    enable_silent_stream);
 	if (!ret) {
 		struct hdmi_spec *spec = codec->spec;
 
@@ -4380,10 +4389,11 @@ HDA_CODEC_ENTRY(0x8086280f, "Icelake HDMI",	patch_i915_icl_hdmi),
 HDA_CODEC_ENTRY(0x80862812, "Tigerlake HDMI",	patch_i915_tgl_hdmi),
 HDA_CODEC_ENTRY(0x80862814, "DG1 HDMI",	patch_i915_tgl_hdmi),
 HDA_CODEC_ENTRY(0x80862815, "Alderlake HDMI",	patch_i915_tgl_hdmi),
-HDA_CODEC_ENTRY(0x8086281c, "Alderlake-P HDMI", patch_i915_tgl_hdmi),
 HDA_CODEC_ENTRY(0x80862816, "Rocketlake HDMI",	patch_i915_tgl_hdmi),
+HDA_CODEC_ENTRY(0x80862819, "DG2 HDMI",	patch_i915_tgl_hdmi),
 HDA_CODEC_ENTRY(0x8086281a, "Jasperlake HDMI",	patch_i915_icl_hdmi),
 HDA_CODEC_ENTRY(0x8086281b, "Elkhartlake HDMI",	patch_i915_icl_hdmi),
+HDA_CODEC_ENTRY(0x8086281c, "Alderlake-P HDMI", patch_i915_tgl_hdmi),
 HDA_CODEC_ENTRY(0x80862880, "CedarTrail HDMI",	patch_generic_hdmi),
 HDA_CODEC_ENTRY(0x80862882, "Valleyview2 HDMI",	patch_i915_byt_hdmi),
 HDA_CODEC_ENTRY(0x80862883, "Braswell HDMI",	patch_i915_byt_hdmi),
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 2f1727faec69..28255e752c4a 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -6503,22 +6503,64 @@ static void alc287_fixup_legion_15imhg05_speakers(struct hda_codec *codec,
 /* for alc285_fixup_ideapad_s740_coef() */
 #include "ideapad_s740_helper.c"
 
-static void alc256_fixup_tongfang_reset_persistent_settings(struct hda_codec *codec,
-							    const struct hda_fixup *fix,
-							    int action)
+static const struct coef_fw alc256_fixup_set_coef_defaults_coefs[] = {
+	WRITE_COEF(0x10, 0x0020), WRITE_COEF(0x24, 0x0000),
+	WRITE_COEF(0x26, 0x0000), WRITE_COEF(0x29, 0x3000),
+	WRITE_COEF(0x37, 0xfe05), WRITE_COEF(0x45, 0x5089),
+	{}
+};
+
+static void alc256_fixup_set_coef_defaults(struct hda_codec *codec,
+					   const struct hda_fixup *fix,
+					   int action)
 {
 	/*
-	* A certain other OS sets these coeffs to different values. On at least one TongFang
-	* barebone these settings might survive even a cold reboot. So to restore a clean slate the
-	* values are explicitly reset to default here. Without this, the external microphone is
-	* always in a plugged-in state, while the internal microphone is always in an unplugged
-	* state, breaking the ability to use the internal microphone.
-	*/
-	alc_write_coef_idx(codec, 0x24, 0x0000);
-	alc_write_coef_idx(codec, 0x26, 0x0000);
-	alc_write_coef_idx(codec, 0x29, 0x3000);
-	alc_write_coef_idx(codec, 0x37, 0xfe05);
-	alc_write_coef_idx(codec, 0x45, 0x5089);
+	 * A certain other OS sets these coeffs to different values. On at least
+	 * one TongFang barebone these settings might survive even a cold
+	 * reboot. So to restore a clean slate the values are explicitly reset
+	 * to default here. Without this, the external microphone is always in a
+	 * plugged-in state, while the internal microphone is always in an
+	 * unplugged state, breaking the ability to use the internal microphone.
+	 */
+	alc_process_coef_fw(codec, alc256_fixup_set_coef_defaults_coefs);
+}
+
+static const struct coef_fw alc233_fixup_no_audio_jack_coefs[] = {
+	WRITE_COEF(0x1a, 0x9003), WRITE_COEF(0x1b, 0x0e2b), WRITE_COEF(0x37, 0xfe06),
+	WRITE_COEF(0x38, 0x4981), WRITE_COEF(0x45, 0xd489), WRITE_COEF(0x46, 0x0074),
+	WRITE_COEF(0x49, 0x0149),
+	{}
+};
+
+static void alc233_fixup_no_audio_jack(struct hda_codec *codec,
+				       const struct hda_fixup *fix,
+				       int action)
+{
+	/*
+	 * The audio jack input and output is not detected on the ASRock NUC Box
+	 * 1100 series when cold booting without this fix. Warm rebooting from a
+	 * certain other OS makes the audio functional, as COEF settings are
+	 * preserved in this case. This fix sets these altered COEF values as
+	 * the default.
+	 */
+	alc_process_coef_fw(codec, alc233_fixup_no_audio_jack_coefs);
+}
+
+static void alc256_fixup_mic_no_presence_and_resume(struct hda_codec *codec,
+						    const struct hda_fixup *fix,
+						    int action)
+{
+	/*
+	 * The Clevo NJ51CU comes either with the ALC293 or the ALC256 codec,
+	 * but uses the 0x8686 subproduct id in both cases. The ALC256 codec
+	 * needs an additional quirk for sound working after suspend and resume.
+	 */
+	if (codec->core.vendor_id == 0x10ec0256) {
+		alc_update_coef_idx(codec, 0x10, 1<<9, 0);
+		snd_hda_codec_set_pincfg(codec, 0x19, 0x04a11120);
+	} else {
+		snd_hda_codec_set_pincfg(codec, 0x1a, 0x04a1113c);
+	}
 }
 
 enum {
@@ -6738,8 +6780,10 @@ enum {
 	ALC287_FIXUP_LEGION_15IMHG05_AUTOMUTE,
 	ALC287_FIXUP_YOGA7_14ITL_SPEAKERS,
 	ALC287_FIXUP_13S_GEN2_SPEAKERS,
-	ALC256_FIXUP_TONGFANG_RESET_PERSISTENT_SETTINGS,
+	ALC256_FIXUP_SET_COEF_DEFAULTS,
 	ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE,
+	ALC233_FIXUP_NO_AUDIO_JACK,
+	ALC256_FIXUP_MIC_NO_PRESENCE_AND_RESUME,
 };
 
 static const struct hda_fixup alc269_fixups[] = {
@@ -8443,9 +8487,9 @@ static const struct hda_fixup alc269_fixups[] = {
 		.chained = true,
 		.chain_id = ALC269_FIXUP_HEADSET_MODE,
 	},
-	[ALC256_FIXUP_TONGFANG_RESET_PERSISTENT_SETTINGS] = {
+	[ALC256_FIXUP_SET_COEF_DEFAULTS] = {
 		.type = HDA_FIXUP_FUNC,
-		.v.func = alc256_fixup_tongfang_reset_persistent_settings,
+		.v.func = alc256_fixup_set_coef_defaults,
 	},
 	[ALC245_FIXUP_HP_GPIO_LED] = {
 		.type = HDA_FIXUP_FUNC,
@@ -8460,6 +8504,16 @@ static const struct hda_fixup alc269_fixups[] = {
 		.chained = true,
 		.chain_id = ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC,
 	},
+	[ALC233_FIXUP_NO_AUDIO_JACK] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc233_fixup_no_audio_jack,
+	},
+	[ALC256_FIXUP_MIC_NO_PRESENCE_AND_RESUME] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc256_fixup_mic_no_presence_and_resume,
+		.chained = true,
+		.chain_id = ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC
+	},
 };
 
 static const struct snd_pci_quirk alc269_fixup_tbl[] = {
@@ -8630,6 +8684,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x84da, "HP OMEN dc0019-ur", ALC295_FIXUP_HP_OMEN),
 	SND_PCI_QUIRK(0x103c, 0x84e7, "HP Pavilion 15", ALC269_FIXUP_HP_MUTE_LED_MIC3),
 	SND_PCI_QUIRK(0x103c, 0x8519, "HP Spectre x360 15-df0xxx", ALC285_FIXUP_HP_SPECTRE_X360),
+	SND_PCI_QUIRK(0x103c, 0x860f, "HP ZBook 15 G6", ALC285_FIXUP_HP_GPIO_AMP_INIT),
 	SND_PCI_QUIRK(0x103c, 0x861f, "HP Elite Dragonfly G1", ALC285_FIXUP_HP_GPIO_AMP_INIT),
 	SND_PCI_QUIRK(0x103c, 0x869d, "HP", ALC236_FIXUP_HP_MUTE_LED),
 	SND_PCI_QUIRK(0x103c, 0x86c7, "HP Envy AiO 32", ALC274_FIXUP_HP_ENVY_GPIO),
@@ -8639,6 +8694,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x8728, "HP EliteBook 840 G7", ALC285_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8729, "HP", ALC285_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8730, "HP ProBook 445 G7", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
+	SND_PCI_QUIRK(0x103c, 0x8735, "HP ProBook 435 G7", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
 	SND_PCI_QUIRK(0x103c, 0x8736, "HP", ALC285_FIXUP_HP_GPIO_AMP_INIT),
 	SND_PCI_QUIRK(0x103c, 0x8760, "HP", ALC285_FIXUP_HP_MUTE_LED),
 	SND_PCI_QUIRK(0x103c, 0x877a, "HP", ALC285_FIXUP_HP_MUTE_LED),
@@ -8674,6 +8730,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x8896, "HP EliteBook 855 G8 Notebook PC", ALC285_FIXUP_HP_MUTE_LED),
 	SND_PCI_QUIRK(0x103c, 0x8898, "HP EliteBook 845 G8 Notebook PC", ALC285_FIXUP_HP_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x103c, 0x88d0, "HP Pavilion 15-eh1xxx (mainboard 88D0)", ALC287_FIXUP_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x89ca, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
 	SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC),
 	SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300),
 	SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
@@ -8798,7 +8855,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1558, 0x8562, "Clevo NH[57][0-9]RZ[Q]", ALC269_FIXUP_DMIC),
 	SND_PCI_QUIRK(0x1558, 0x8668, "Clevo NP50B[BE]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1558, 0x8680, "Clevo NJ50LU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
-	SND_PCI_QUIRK(0x1558, 0x8686, "Clevo NH50[CZ]U", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x1558, 0x8686, "Clevo NH50[CZ]U", ALC256_FIXUP_MIC_NO_PRESENCE_AND_RESUME),
 	SND_PCI_QUIRK(0x1558, 0x8a20, "Clevo NH55DCQ-Y", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1558, 0x8a51, "Clevo NH70RCQ-Y", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1558, 0x8d50, "Clevo NH55RCQ-M", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
@@ -8894,6 +8951,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x17aa, 0x511e, "Thinkpad", ALC298_FIXUP_TPT470_DOCK),
 	SND_PCI_QUIRK(0x17aa, 0x511f, "Thinkpad", ALC298_FIXUP_TPT470_DOCK),
 	SND_PCI_QUIRK(0x17aa, 0x9e54, "LENOVO NB", ALC269_FIXUP_LENOVO_EAPD),
+	SND_PCI_QUIRK(0x1849, 0x1233, "ASRock NUC Box 1100", ALC233_FIXUP_NO_AUDIO_JACK),
 	SND_PCI_QUIRK(0x19e5, 0x3204, "Huawei MACH-WX9", ALC256_FIXUP_HUAWEI_MACH_WX9_PINS),
 	SND_PCI_QUIRK(0x1b35, 0x1235, "CZC B20", ALC269_FIXUP_CZC_B20),
 	SND_PCI_QUIRK(0x1b35, 0x1236, "CZC TMI", ALC269_FIXUP_CZC_TMI),
@@ -8901,7 +8959,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1b7d, 0xa831, "Ordissimo EVE2 ", ALC269VB_FIXUP_ORDISSIMO_EVE2), /* Also known as Malata PC-B1303 */
 	SND_PCI_QUIRK(0x1c06, 0x2013, "Lemote A1802", ALC269_FIXUP_LEMOTE_A1802),
 	SND_PCI_QUIRK(0x1c06, 0x2015, "Lemote A190X", ALC269_FIXUP_LEMOTE_A190X),
-	SND_PCI_QUIRK(0x1d05, 0x1132, "TongFang PHxTxX1", ALC256_FIXUP_TONGFANG_RESET_PERSISTENT_SETTINGS),
+	SND_PCI_QUIRK(0x1d05, 0x1132, "TongFang PHxTxX1", ALC256_FIXUP_SET_COEF_DEFAULTS),
 	SND_PCI_QUIRK(0x1d72, 0x1602, "RedmiBook", ALC255_FIXUP_XIAOMI_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1d72, 0x1701, "XiaomiNotebook Pro", ALC298_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1d72, 0x1901, "RedmiBook 14", ALC256_FIXUP_ASUS_HEADSET_MIC),
@@ -9091,6 +9149,7 @@ static const struct hda_model_fixup alc269_fixup_models[] = {
 	{.id = ALC287_FIXUP_IDEAPAD_BASS_SPK_AMP, .name = "alc287-ideapad-bass-spk-amp"},
 	{.id = ALC623_FIXUP_LENOVO_THINKSTATION_P340, .name = "alc623-lenovo-thinkstation-p340"},
 	{.id = ALC255_FIXUP_ACER_HEADPHONE_AND_MIC, .name = "alc255-acer-headphone-and-mic"},
+	{.id = ALC285_FIXUP_HP_GPIO_AMP_INIT, .name = "alc285-hp-amp-init"},
 	{}
 };
 #define ALC225_STANDARD_PINS \
@@ -10203,6 +10262,27 @@ static void alc671_fixup_hp_headset_mic2(struct hda_codec *codec,
 	}
 }
 
+static void alc897_hp_automute_hook(struct hda_codec *codec,
+					 struct hda_jack_callback *jack)
+{
+	struct alc_spec *spec = codec->spec;
+	int vref;
+
+	snd_hda_gen_hp_automute(codec, jack);
+	vref = spec->gen.hp_jack_present ? (PIN_HP | AC_PINCTL_VREF_100) : PIN_HP;
+	snd_hda_codec_write(codec, 0x1b, 0, AC_VERB_SET_PIN_WIDGET_CONTROL,
+			    vref);
+}
+
+static void alc897_fixup_lenovo_headset_mic(struct hda_codec *codec,
+				     const struct hda_fixup *fix, int action)
+{
+	struct alc_spec *spec = codec->spec;
+	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
+		spec->gen.hp_automute_hook = alc897_hp_automute_hook;
+	}
+}
+
 static const struct coef_fw alc668_coefs[] = {
 	WRITE_COEF(0x01, 0xbebe), WRITE_COEF(0x02, 0xaaaa), WRITE_COEF(0x03,    0x0),
 	WRITE_COEF(0x04, 0x0180), WRITE_COEF(0x06,    0x0), WRITE_COEF(0x07, 0x0f80),
@@ -10283,6 +10363,8 @@ enum {
 	ALC668_FIXUP_ASUS_NO_HEADSET_MIC,
 	ALC668_FIXUP_HEADSET_MIC,
 	ALC668_FIXUP_MIC_DET_COEF,
+	ALC897_FIXUP_LENOVO_HEADSET_MIC,
+	ALC897_FIXUP_HEADSET_MIC_PIN,
 };
 
 static const struct hda_fixup alc662_fixups[] = {
@@ -10689,6 +10771,19 @@ static const struct hda_fixup alc662_fixups[] = {
 			{}
 		},
 	},
+	[ALC897_FIXUP_LENOVO_HEADSET_MIC] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc897_fixup_lenovo_headset_mic,
+	},
+	[ALC897_FIXUP_HEADSET_MIC_PIN] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x1a, 0x03a11050 },
+			{ }
+		},
+		.chained = true,
+		.chain_id = ALC897_FIXUP_LENOVO_HEADSET_MIC
+	},
 };
 
 static const struct snd_pci_quirk alc662_fixup_tbl[] = {
@@ -10733,6 +10828,10 @@ static const struct snd_pci_quirk alc662_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x144d, 0xc051, "Samsung R720", ALC662_FIXUP_IDEAPAD),
 	SND_PCI_QUIRK(0x14cd, 0x5003, "USI", ALC662_FIXUP_USI_HEADSET_MODE),
 	SND_PCI_QUIRK(0x17aa, 0x1036, "Lenovo P520", ALC662_FIXUP_LENOVO_MULTI_CODECS),
+	SND_PCI_QUIRK(0x17aa, 0x32ca, "Lenovo ThinkCentre M80", ALC897_FIXUP_HEADSET_MIC_PIN),
+	SND_PCI_QUIRK(0x17aa, 0x32cb, "Lenovo ThinkCentre M70", ALC897_FIXUP_HEADSET_MIC_PIN),
+	SND_PCI_QUIRK(0x17aa, 0x32cf, "Lenovo ThinkCentre M950", ALC897_FIXUP_HEADSET_MIC_PIN),
+	SND_PCI_QUIRK(0x17aa, 0x32f7, "Lenovo ThinkCentre M90", ALC897_FIXUP_HEADSET_MIC_PIN),
 	SND_PCI_QUIRK(0x17aa, 0x38af, "Lenovo Ideapad Y550P", ALC662_FIXUP_IDEAPAD),
 	SND_PCI_QUIRK(0x17aa, 0x3a0d, "Lenovo Ideapad Y550", ALC662_FIXUP_IDEAPAD),
 	SND_PCI_QUIRK(0x1849, 0x5892, "ASRock B150M", ALC892_FIXUP_ASROCK_MOBO),
diff --git a/sound/soc/amd/yc/pci-acp6x.c b/sound/soc/amd/yc/pci-acp6x.c
index 957eeb6fb8e3..7e9a9a9d8ddd 100644
--- a/sound/soc/amd/yc/pci-acp6x.c
+++ b/sound/soc/amd/yc/pci-acp6x.c
@@ -146,10 +146,11 @@ static int snd_acp6x_probe(struct pci_dev *pci,
 {
 	struct acp6x_dev_data *adata;
 	struct platform_device_info pdevinfo[ACP6x_DEVS];
-	int ret, index;
+	int index = 0;
 	int val = 0x00;
 	u32 addr;
 	unsigned int irqflags;
+	int ret;
 
 	irqflags = IRQF_SHARED;
 	/* Yellow Carp device check */
diff --git a/sound/soc/codecs/cs35l41-spi.c b/sound/soc/codecs/cs35l41-spi.c
index 90a921f726c3..3fa99741779a 100644
--- a/sound/soc/codecs/cs35l41-spi.c
+++ b/sound/soc/codecs/cs35l41-spi.c
@@ -42,34 +42,6 @@ static const struct spi_device_id cs35l41_id_spi[] = {
 
 MODULE_DEVICE_TABLE(spi, cs35l41_id_spi);
 
-static void cs35l41_spi_otp_setup(struct cs35l41_private *cs35l41,
-				  bool is_pre_setup, unsigned int *freq)
-{
-	struct spi_device *spi;
-	u32 orig_spi_freq;
-
-	spi = to_spi_device(cs35l41->dev);
-
-	if (!spi) {
-		dev_err(cs35l41->dev, "%s: No SPI device\n", __func__);
-		return;
-	}
-
-	if (is_pre_setup) {
-		orig_spi_freq = spi->max_speed_hz;
-		if (orig_spi_freq > CS35L41_SPI_MAX_FREQ_OTP) {
-			spi->max_speed_hz = CS35L41_SPI_MAX_FREQ_OTP;
-			spi_setup(spi);
-		}
-		*freq = orig_spi_freq;
-	} else {
-		if (spi->max_speed_hz != *freq) {
-			spi->max_speed_hz = *freq;
-			spi_setup(spi);
-		}
-	}
-}
-
 static int cs35l41_spi_probe(struct spi_device *spi)
 {
 	const struct regmap_config *regmap_config = &cs35l41_regmap_spi;
@@ -81,6 +53,9 @@ static int cs35l41_spi_probe(struct spi_device *spi)
 	if (!cs35l41)
 		return -ENOMEM;
 
+	spi->max_speed_hz = CS35L41_SPI_MAX_FREQ;
+	spi_setup(spi);
+
 	spi_set_drvdata(spi, cs35l41);
 	cs35l41->regmap = devm_regmap_init_spi(spi, regmap_config);
 	if (IS_ERR(cs35l41->regmap)) {
@@ -91,7 +66,6 @@ static int cs35l41_spi_probe(struct spi_device *spi)
 
 	cs35l41->dev = &spi->dev;
 	cs35l41->irq = spi->irq;
-	cs35l41->otp_setup = cs35l41_spi_otp_setup;
 
 	return cs35l41_probe(cs35l41, pdata);
 }
diff --git a/sound/soc/codecs/cs35l41.c b/sound/soc/codecs/cs35l41.c
index 94ed21d7676f..9c4d481f7614 100644
--- a/sound/soc/codecs/cs35l41.c
+++ b/sound/soc/codecs/cs35l41.c
@@ -302,7 +302,6 @@ static int cs35l41_otp_unpack(void *data)
 	const struct cs35l41_otp_packed_element_t *otp_map;
 	struct cs35l41_private *cs35l41 = data;
 	int bit_offset, word_offset, ret, i;
-	unsigned int orig_spi_freq;
 	unsigned int bit_sum = 8;
 	u32 otp_val, otp_id_reg;
 	u32 *otp_mem;
@@ -326,9 +325,6 @@ static int cs35l41_otp_unpack(void *data)
 		goto err_otp_unpack;
 	}
 
-	if (cs35l41->otp_setup)
-		cs35l41->otp_setup(cs35l41, true, &orig_spi_freq);
-
 	ret = regmap_bulk_read(cs35l41->regmap, CS35L41_OTP_MEM0, otp_mem,
 			       CS35L41_OTP_SIZE_WORDS);
 	if (ret < 0) {
@@ -336,9 +332,6 @@ static int cs35l41_otp_unpack(void *data)
 		goto err_otp_unpack;
 	}
 
-	if (cs35l41->otp_setup)
-		cs35l41->otp_setup(cs35l41, false, &orig_spi_freq);
-
 	otp_map = otp_map_match->map;
 
 	bit_offset = otp_map_match->bit_offset;
@@ -612,6 +605,12 @@ static const struct snd_soc_dapm_widget cs35l41_dapm_widgets[] = {
 	SND_SOC_DAPM_AIF_OUT("ASPTX3", NULL, 0, CS35L41_SP_ENABLES, 2, 0),
 	SND_SOC_DAPM_AIF_OUT("ASPTX4", NULL, 0, CS35L41_SP_ENABLES, 3, 0),
 
+	SND_SOC_DAPM_SIGGEN("VSENSE"),
+	SND_SOC_DAPM_SIGGEN("ISENSE"),
+	SND_SOC_DAPM_SIGGEN("VP"),
+	SND_SOC_DAPM_SIGGEN("VBST"),
+	SND_SOC_DAPM_SIGGEN("TEMP"),
+
 	SND_SOC_DAPM_ADC("VMON ADC", NULL, CS35L41_PWR_CTRL2, 12, 0),
 	SND_SOC_DAPM_ADC("IMON ADC", NULL, CS35L41_PWR_CTRL2, 13, 0),
 	SND_SOC_DAPM_ADC("VPMON ADC", NULL, CS35L41_PWR_CTRL2, 8, 0),
@@ -623,12 +622,6 @@ static const struct snd_soc_dapm_widget cs35l41_dapm_widgets[] = {
 			       cs35l41_main_amp_event,
 			       SND_SOC_DAPM_POST_PMD |	SND_SOC_DAPM_POST_PMU),
 
-	SND_SOC_DAPM_INPUT("VP"),
-	SND_SOC_DAPM_INPUT("VBST"),
-	SND_SOC_DAPM_INPUT("ISENSE"),
-	SND_SOC_DAPM_INPUT("VSENSE"),
-	SND_SOC_DAPM_INPUT("TEMP"),
-
 	SND_SOC_DAPM_MUX("ASP TX1 Source", SND_SOC_NOPM, 0, 0, &asp_tx1_mux),
 	SND_SOC_DAPM_MUX("ASP TX2 Source", SND_SOC_NOPM, 0, 0, &asp_tx2_mux),
 	SND_SOC_DAPM_MUX("ASP TX3 Source", SND_SOC_NOPM, 0, 0, &asp_tx3_mux),
@@ -674,8 +667,8 @@ static const struct snd_soc_dapm_route cs35l41_audio_map[] = {
 	{"VMON ADC", NULL, "VSENSE"},
 	{"IMON ADC", NULL, "ISENSE"},
 	{"VPMON ADC", NULL, "VP"},
-	{"TEMPMON ADC", NULL, "TEMP"},
 	{"VBSTMON ADC", NULL, "VBST"},
+	{"TEMPMON ADC", NULL, "TEMP"},
 
 	{"ASPRX1", NULL, "AMP Playback"},
 	{"ASPRX2", NULL, "AMP Playback"},
diff --git a/sound/soc/codecs/cs35l41.h b/sound/soc/codecs/cs35l41.h
index 6cffe8a55beb..48485b08a6f1 100644
--- a/sound/soc/codecs/cs35l41.h
+++ b/sound/soc/codecs/cs35l41.h
@@ -726,7 +726,7 @@
 #define CS35L41_FS2_WINDOW_MASK		0x00FFF800
 #define CS35L41_FS2_WINDOW_SHIFT	12
 
-#define CS35L41_SPI_MAX_FREQ_OTP	4000000
+#define CS35L41_SPI_MAX_FREQ		4000000
 
 #define CS35L41_RX_FORMATS (SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S24_LE)
 #define CS35L41_TX_FORMATS (SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S24_LE)
@@ -764,8 +764,6 @@ struct cs35l41_private {
 	int irq;
 	/* GPIO for /RST */
 	struct gpio_desc *reset_gpio;
-	void (*otp_setup)(struct cs35l41_private *cs35l41, bool is_pre_setup,
-			  unsigned int *freq);
 };
 
 int cs35l41_probe(struct cs35l41_private *cs35l41,
diff --git a/sound/soc/codecs/lpass-rx-macro.c b/sound/soc/codecs/lpass-rx-macro.c
index 2bed5cf229be..aec5127260fd 100644
--- a/sound/soc/codecs/lpass-rx-macro.c
+++ b/sound/soc/codecs/lpass-rx-macro.c
@@ -2188,7 +2188,7 @@ static int rx_macro_config_classh(struct snd_soc_component *component,
 		snd_soc_component_update_bits(component,
 				CDC_RX_CLSH_DECAY_CTRL,
 				CDC_RX_CLSH_DECAY_RATE_MASK, 0x0);
-		snd_soc_component_update_bits(component,
+		snd_soc_component_write_field(component,
 				CDC_RX_RX1_RX_PATH_CFG0,
 				CDC_RX_RXn_CLSH_EN_MASK, 0x1);
 		break;
diff --git a/sound/soc/codecs/rk817_codec.c b/sound/soc/codecs/rk817_codec.c
index 943d7d933e81..03f24edfe4f6 100644
--- a/sound/soc/codecs/rk817_codec.c
+++ b/sound/soc/codecs/rk817_codec.c
@@ -539,3 +539,4 @@ module_platform_driver(rk817_codec_driver);
 MODULE_DESCRIPTION("ASoC RK817 codec driver");
 MODULE_AUTHOR("binyuan <kevan.lan@rock-chips.com>");
 MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform:rk817-codec");
diff --git a/sound/soc/codecs/rt1011.c b/sound/soc/codecs/rt1011.c
index 297af7ff824c..b62301a6281f 100644
--- a/sound/soc/codecs/rt1011.c
+++ b/sound/soc/codecs/rt1011.c
@@ -1311,13 +1311,54 @@ static int rt1011_r0_load_info(struct snd_kcontrol *kcontrol,
 	.put = rt1011_r0_load_mode_put \
 }
 
-static const char * const rt1011_i2s_ref_texts[] = {
-	"Left Channel", "Right Channel"
+static const char * const rt1011_i2s_ref[] = {
+	"None", "Left Channel", "Right Channel"
 };
 
-static SOC_ENUM_SINGLE_DECL(rt1011_i2s_ref_enum,
-			    RT1011_TDM1_SET_1, 7,
-			    rt1011_i2s_ref_texts);
+static SOC_ENUM_SINGLE_DECL(rt1011_i2s_ref_enum, 0, 0,
+	rt1011_i2s_ref);
+
+static int rt1011_i2s_ref_put(struct snd_kcontrol *kcontrol,
+		struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *component =
+		snd_soc_kcontrol_component(kcontrol);
+	struct rt1011_priv *rt1011 =
+		snd_soc_component_get_drvdata(component);
+
+	rt1011->i2s_ref = ucontrol->value.enumerated.item[0];
+	switch (rt1011->i2s_ref) {
+	case RT1011_I2S_REF_LEFT_CH:
+		regmap_write(rt1011->regmap, RT1011_TDM_TOTAL_SET, 0x0240);
+		regmap_write(rt1011->regmap, RT1011_TDM1_SET_2, 0x8);
+		regmap_write(rt1011->regmap, RT1011_TDM1_SET_1, 0x1022);
+		regmap_write(rt1011->regmap, RT1011_ADCDAT_OUT_SOURCE, 0x4);
+		break;
+	case RT1011_I2S_REF_RIGHT_CH:
+		regmap_write(rt1011->regmap, RT1011_TDM_TOTAL_SET, 0x0240);
+		regmap_write(rt1011->regmap, RT1011_TDM1_SET_2, 0x8);
+		regmap_write(rt1011->regmap, RT1011_TDM1_SET_1, 0x10a2);
+		regmap_write(rt1011->regmap, RT1011_ADCDAT_OUT_SOURCE, 0x4);
+		break;
+	default:
+		dev_info(component->dev, "I2S Reference: Do nothing\n");
+	}
+
+	return 0;
+}
+
+static int rt1011_i2s_ref_get(struct snd_kcontrol *kcontrol,
+		struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *component =
+		snd_soc_kcontrol_component(kcontrol);
+	struct rt1011_priv *rt1011 =
+		snd_soc_component_get_drvdata(component);
+
+	ucontrol->value.enumerated.item[0] = rt1011->i2s_ref;
+
+	return 0;
+}
 
 static const struct snd_kcontrol_new rt1011_snd_controls[] = {
 	/* I2S Data In Selection */
@@ -1358,7 +1399,8 @@ static const struct snd_kcontrol_new rt1011_snd_controls[] = {
 	SOC_SINGLE("R0 Temperature", RT1011_STP_INITIAL_RESISTANCE_TEMP,
 		2, 255, 0),
 	/* I2S Reference */
-	SOC_ENUM("I2S Reference", rt1011_i2s_ref_enum),
+	SOC_ENUM_EXT("I2S Reference", rt1011_i2s_ref_enum,
+		rt1011_i2s_ref_get, rt1011_i2s_ref_put),
 };
 
 static int rt1011_is_sys_clk_from_pll(struct snd_soc_dapm_widget *source,
@@ -2017,6 +2059,7 @@ static int rt1011_probe(struct snd_soc_component *component)
 
 	schedule_work(&rt1011->cali_work);
 
+	rt1011->i2s_ref = 0;
 	rt1011->bq_drc_params = devm_kcalloc(component->dev,
 		RT1011_ADVMODE_NUM, sizeof(struct rt1011_bq_drc_params *),
 		GFP_KERNEL);
diff --git a/sound/soc/codecs/rt1011.h b/sound/soc/codecs/rt1011.h
index 68fadc15fa8c..4d6e7492d99c 100644
--- a/sound/soc/codecs/rt1011.h
+++ b/sound/soc/codecs/rt1011.h
@@ -654,6 +654,12 @@ enum {
 	RT1011_AIFS
 };
 
+enum {
+	RT1011_I2S_REF_NONE,
+	RT1011_I2S_REF_LEFT_CH,
+	RT1011_I2S_REF_RIGHT_CH,
+};
+
 /* BiQual & DRC related settings */
 #define RT1011_BQ_DRC_NUM 128
 struct rt1011_bq_drc_params {
@@ -692,6 +698,7 @@ struct rt1011_priv {
 	unsigned int r0_reg, cali_done;
 	unsigned int r0_calib, temperature_calib;
 	int recv_spk_mode;
+	int i2s_ref;
 };
 
 #endif		/* end of _RT1011_H_ */
diff --git a/sound/soc/codecs/rt5682-i2c.c b/sound/soc/codecs/rt5682-i2c.c
index 983347b65127..20e0f90ea498 100644
--- a/sound/soc/codecs/rt5682-i2c.c
+++ b/sound/soc/codecs/rt5682-i2c.c
@@ -198,6 +198,7 @@ static int rt5682_i2c_probe(struct i2c_client *i2c,
 	}
 
 	mutex_init(&rt5682->calibrate_mutex);
+	mutex_init(&rt5682->jdet_mutex);
 	rt5682_calibrate(rt5682);
 
 	rt5682_apply_patch_list(rt5682, &i2c->dev);
diff --git a/sound/soc/codecs/rt5682.c b/sound/soc/codecs/rt5682.c
index 78b4cb5fb6c8..b34a8542077d 100644
--- a/sound/soc/codecs/rt5682.c
+++ b/sound/soc/codecs/rt5682.c
@@ -48,6 +48,8 @@ static const struct reg_sequence patch_list[] = {
 	{RT5682_SAR_IL_CMD_6, 0x0110},
 	{RT5682_CHARGE_PUMP_1, 0x0210},
 	{RT5682_HP_LOGIC_CTRL_2, 0x0007},
+	{RT5682_SAR_IL_CMD_2, 0xac00},
+	{RT5682_CBJ_CTRL_7, 0x0104},
 };
 
 void rt5682_apply_patch_list(struct rt5682_priv *rt5682, struct device *dev)
@@ -927,6 +929,8 @@ int rt5682_headset_detect(struct snd_soc_component *component, int jack_insert)
 	unsigned int val, count;
 
 	if (jack_insert) {
+		snd_soc_dapm_mutex_lock(dapm);
+
 		snd_soc_component_update_bits(component, RT5682_PWR_ANLG_1,
 			RT5682_PWR_VREF2 | RT5682_PWR_MB,
 			RT5682_PWR_VREF2 | RT5682_PWR_MB);
@@ -940,6 +944,10 @@ int rt5682_headset_detect(struct snd_soc_component *component, int jack_insert)
 		snd_soc_component_update_bits(component,
 			RT5682_HP_CHARGE_PUMP_1,
 			RT5682_OSW_L_MASK | RT5682_OSW_R_MASK, 0);
+		rt5682_enable_push_button_irq(component, false);
+		snd_soc_component_update_bits(component, RT5682_CBJ_CTRL_1,
+			RT5682_TRIG_JD_MASK, RT5682_TRIG_JD_LOW);
+		usleep_range(55000, 60000);
 		snd_soc_component_update_bits(component, RT5682_CBJ_CTRL_1,
 			RT5682_TRIG_JD_MASK, RT5682_TRIG_JD_HIGH);
 
@@ -973,6 +981,8 @@ int rt5682_headset_detect(struct snd_soc_component *component, int jack_insert)
 		snd_soc_component_update_bits(component, RT5682_MICBIAS_2,
 			RT5682_PWR_CLK25M_MASK | RT5682_PWR_CLK1M_MASK,
 			RT5682_PWR_CLK25M_PU | RT5682_PWR_CLK1M_PU);
+
+		snd_soc_dapm_mutex_unlock(dapm);
 	} else {
 		rt5682_enable_push_button_irq(component, false);
 		snd_soc_component_update_bits(component, RT5682_CBJ_CTRL_1,
@@ -1092,6 +1102,7 @@ void rt5682_jack_detect_handler(struct work_struct *work)
 	while (!rt5682->component->card->instantiated)
 		usleep_range(10000, 15000);
 
+	mutex_lock(&rt5682->jdet_mutex);
 	mutex_lock(&rt5682->calibrate_mutex);
 
 	val = snd_soc_component_read(rt5682->component, RT5682_AJD1_CTRL)
@@ -1165,6 +1176,7 @@ void rt5682_jack_detect_handler(struct work_struct *work)
 	}
 
 	mutex_unlock(&rt5682->calibrate_mutex);
+	mutex_unlock(&rt5682->jdet_mutex);
 }
 EXPORT_SYMBOL_GPL(rt5682_jack_detect_handler);
 
@@ -1514,6 +1526,7 @@ static int rt5682_hp_event(struct snd_soc_dapm_widget *w,
 {
 	struct snd_soc_component *component =
 		snd_soc_dapm_to_component(w->dapm);
+	struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component);
 
 	switch (event) {
 	case SND_SOC_DAPM_PRE_PMU:
@@ -1525,12 +1538,17 @@ static int rt5682_hp_event(struct snd_soc_dapm_widget *w,
 			RT5682_DEPOP_1, 0x60, 0x60);
 		snd_soc_component_update_bits(component,
 			RT5682_DAC_ADC_DIG_VOL1, 0x00c0, 0x0080);
+
+		mutex_lock(&rt5682->jdet_mutex);
+
 		snd_soc_component_update_bits(component, RT5682_HP_CTRL_2,
 			RT5682_HP_C2_DAC_L_EN | RT5682_HP_C2_DAC_R_EN,
 			RT5682_HP_C2_DAC_L_EN | RT5682_HP_C2_DAC_R_EN);
 		usleep_range(5000, 10000);
 		snd_soc_component_update_bits(component, RT5682_CHARGE_PUMP_1,
 			RT5682_CP_SW_SIZE_MASK, RT5682_CP_SW_SIZE_L);
+
+		mutex_unlock(&rt5682->jdet_mutex);
 		break;
 
 	case SND_SOC_DAPM_POST_PMD:
@@ -2844,6 +2862,8 @@ int rt5682_register_dai_clks(struct rt5682_priv *rt5682)
 
 	for (i = 0; i < RT5682_DAI_NUM_CLKS; ++i) {
 		struct clk_init_data init = { };
+		struct clk_parent_data parent_data;
+		const struct clk_hw *parent;
 
 		dai_clk_hw = &rt5682->dai_clks_hw[i];
 
@@ -2851,17 +2871,17 @@ int rt5682_register_dai_clks(struct rt5682_priv *rt5682)
 		case RT5682_DAI_WCLK_IDX:
 			/* Make MCLK the parent of WCLK */
 			if (rt5682->mclk) {
-				init.parent_data = &(struct clk_parent_data){
+				parent_data = (struct clk_parent_data){
 					.fw_name = "mclk",
 				};
+				init.parent_data = &parent_data;
 				init.num_parents = 1;
 			}
 			break;
 		case RT5682_DAI_BCLK_IDX:
 			/* Make WCLK the parent of BCLK */
-			init.parent_hws = &(const struct clk_hw *){
-				&rt5682->dai_clks_hw[RT5682_DAI_WCLK_IDX]
-			};
+			parent = &rt5682->dai_clks_hw[RT5682_DAI_WCLK_IDX];
+			init.parent_hws = &parent;
 			init.num_parents = 1;
 			break;
 		default:
@@ -2942,10 +2962,7 @@ static int rt5682_suspend(struct snd_soc_component *component)
 
 	cancel_delayed_work_sync(&rt5682->jack_detect_work);
 	cancel_delayed_work_sync(&rt5682->jd_check_work);
-	if (rt5682->hs_jack && rt5682->jack_type == SND_JACK_HEADSET) {
-		snd_soc_component_update_bits(component, RT5682_CBJ_CTRL_1,
-			RT5682_MB1_PATH_MASK | RT5682_MB2_PATH_MASK,
-			RT5682_CTRL_MB1_REG | RT5682_CTRL_MB2_REG);
+	if (rt5682->hs_jack && (rt5682->jack_type & SND_JACK_HEADSET) == SND_JACK_HEADSET) {
 		val = snd_soc_component_read(component,
 				RT5682_CBJ_CTRL_2) & RT5682_JACK_TYPE_MASK;
 
@@ -2967,10 +2984,17 @@ static int rt5682_suspend(struct snd_soc_component *component)
 		/* enter SAR ADC power saving mode */
 		snd_soc_component_update_bits(component, RT5682_SAR_IL_CMD_1,
 			RT5682_SAR_BUTT_DET_MASK | RT5682_SAR_BUTDET_MODE_MASK |
-			RT5682_SAR_BUTDET_RST_MASK | RT5682_SAR_SEL_MB1_MB2_MASK, 0);
+			RT5682_SAR_SEL_MB1_MB2_MASK, 0);
+		usleep_range(5000, 6000);
+		snd_soc_component_update_bits(component, RT5682_CBJ_CTRL_1,
+			RT5682_MB1_PATH_MASK | RT5682_MB2_PATH_MASK,
+			RT5682_CTRL_MB1_REG | RT5682_CTRL_MB2_REG);
+		usleep_range(10000, 12000);
 		snd_soc_component_update_bits(component, RT5682_SAR_IL_CMD_1,
-			RT5682_SAR_BUTT_DET_MASK | RT5682_SAR_BUTDET_MODE_MASK | RT5682_SAR_BUTDET_RST_MASK,
-			RT5682_SAR_BUTT_DET_EN | RT5682_SAR_BUTDET_POW_SAV | RT5682_SAR_BUTDET_RST_NORMAL);
+			RT5682_SAR_BUTT_DET_MASK | RT5682_SAR_BUTDET_MODE_MASK,
+			RT5682_SAR_BUTT_DET_EN | RT5682_SAR_BUTDET_POW_SAV);
+		snd_soc_component_update_bits(component, RT5682_HP_CHARGE_PUMP_1,
+			RT5682_OSW_L_MASK | RT5682_OSW_R_MASK, 0);
 	}
 
 	regcache_cache_only(rt5682->regmap, true);
@@ -2988,10 +3012,11 @@ static int rt5682_resume(struct snd_soc_component *component)
 	regcache_cache_only(rt5682->regmap, false);
 	regcache_sync(rt5682->regmap);
 
-	if (rt5682->hs_jack && rt5682->jack_type == SND_JACK_HEADSET) {
+	if (rt5682->hs_jack && (rt5682->jack_type & SND_JACK_HEADSET) == SND_JACK_HEADSET) {
 		snd_soc_component_update_bits(component, RT5682_SAR_IL_CMD_1,
 			RT5682_SAR_BUTDET_MODE_MASK | RT5682_SAR_SEL_MB1_MB2_MASK,
 			RT5682_SAR_BUTDET_POW_NORM | RT5682_SAR_SEL_MB1_MB2_AUTO);
+		usleep_range(5000, 6000);
 		snd_soc_component_update_bits(component, RT5682_CBJ_CTRL_1,
 			RT5682_MB1_PATH_MASK | RT5682_MB2_PATH_MASK,
 			RT5682_CTRL_MB1_FSM | RT5682_CTRL_MB2_FSM);
@@ -2999,8 +3024,9 @@ static int rt5682_resume(struct snd_soc_component *component)
 			RT5682_PWR_CBJ, RT5682_PWR_CBJ);
 	}
 
+	rt5682->jack_type = 0;
 	mod_delayed_work(system_power_efficient_wq,
-		&rt5682->jack_detect_work, msecs_to_jiffies(250));
+		&rt5682->jack_detect_work, msecs_to_jiffies(0));
 
 	return 0;
 }
diff --git a/sound/soc/codecs/rt5682.h b/sound/soc/codecs/rt5682.h
index d93829c35585..c917c76200ea 100644
--- a/sound/soc/codecs/rt5682.h
+++ b/sound/soc/codecs/rt5682.h
@@ -1463,6 +1463,7 @@ struct rt5682_priv {
 
 	int jack_type;
 	int irq_work_delay_time;
+	struct mutex jdet_mutex;
 };
 
 extern const char *rt5682_supply_names[RT5682_NUM_SUPPLIES];
diff --git a/sound/soc/codecs/rt5682s.c b/sound/soc/codecs/rt5682s.c
index 470957fcad6b..d49a4f68566d 100644
--- a/sound/soc/codecs/rt5682s.c
+++ b/sound/soc/codecs/rt5682s.c
@@ -2693,6 +2693,8 @@ static int rt5682s_register_dai_clks(struct snd_soc_component *component)
 
 	for (i = 0; i < RT5682S_DAI_NUM_CLKS; ++i) {
 		struct clk_init_data init = { };
+		struct clk_parent_data parent_data;
+		const struct clk_hw *parent;
 
 		dai_clk_hw = &rt5682s->dai_clks_hw[i];
 
@@ -2700,17 +2702,17 @@ static int rt5682s_register_dai_clks(struct snd_soc_component *component)
 		case RT5682S_DAI_WCLK_IDX:
 			/* Make MCLK the parent of WCLK */
 			if (rt5682s->mclk) {
-				init.parent_data = &(struct clk_parent_data){
+				parent_data = (struct clk_parent_data){
 					.fw_name = "mclk",
 				};
+				init.parent_data = &parent_data;
 				init.num_parents = 1;
 			}
 			break;
 		case RT5682S_DAI_BCLK_IDX:
 			/* Make WCLK the parent of BCLK */
-			init.parent_hws = &(const struct clk_hw *){
-				&rt5682s->dai_clks_hw[RT5682S_DAI_WCLK_IDX]
-			};
+			parent = &rt5682s->dai_clks_hw[RT5682S_DAI_WCLK_IDX];
+			init.parent_hws = &parent;
 			init.num_parents = 1;
 			break;
 		default:
diff --git a/sound/soc/codecs/rt9120.c b/sound/soc/codecs/rt9120.c
index f9574980a407..7aa1772a915f 100644
--- a/sound/soc/codecs/rt9120.c
+++ b/sound/soc/codecs/rt9120.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 
 #include <linux/bits.h>
+#include <linux/bitfield.h>
 #include <linux/delay.h>
 #include <linux/gpio/consumer.h>
 #include <linux/i2c.h>
@@ -23,9 +24,11 @@
 #define RT9120_REG_ERRRPT	0x10
 #define RT9120_REG_MSVOL	0x20
 #define RT9120_REG_SWRESET	0x40
+#define RT9120_REG_INTERCFG	0x63
 #define RT9120_REG_INTERNAL0	0x65
 #define RT9120_REG_INTERNAL1	0x69
 #define RT9120_REG_UVPOPT	0x6C
+#define RT9120_REG_DIGCFG	0xF8
 
 #define RT9120_VID_MASK		GENMASK(15, 8)
 #define RT9120_SWRST_MASK	BIT(7)
@@ -46,8 +49,10 @@
 #define RT9120_CFG_WORDLEN_24	24
 #define RT9120_CFG_WORDLEN_32	32
 #define RT9120_DVDD_UVSEL_MASK	GENMASK(5, 4)
+#define RT9120_AUTOSYNC_MASK	BIT(6)
 
-#define RT9120_VENDOR_ID	0x4200
+#define RT9120_VENDOR_ID	0x42
+#define RT9120S_VENDOR_ID	0x43
 #define RT9120_RESET_WAITMS	20
 #define RT9120_CHIPON_WAITMS	20
 #define RT9120_AMPON_WAITMS	50
@@ -61,9 +66,16 @@
 				 SNDRV_PCM_FMTBIT_S24_LE |\
 				 SNDRV_PCM_FMTBIT_S32_LE)
 
+enum {
+	CHIP_IDX_RT9120 = 0,
+	CHIP_IDX_RT9120S,
+	CHIP_IDX_MAX
+};
+
 struct rt9120_data {
 	struct device *dev;
 	struct regmap *regmap;
+	int chip_idx;
 };
 
 /* 11bit [min,max,step] = [-103.9375dB, 24dB, 0.0625dB] */
@@ -149,8 +161,12 @@ static int rt9120_codec_probe(struct snd_soc_component *comp)
 	snd_soc_component_init_regmap(comp, data->regmap);
 
 	/* Internal setting */
-	snd_soc_component_write(comp, RT9120_REG_INTERNAL1, 0x03);
-	snd_soc_component_write(comp, RT9120_REG_INTERNAL0, 0x69);
+	if (data->chip_idx == CHIP_IDX_RT9120S) {
+		snd_soc_component_write(comp, RT9120_REG_INTERCFG, 0xde);
+		snd_soc_component_write(comp, RT9120_REG_INTERNAL0, 0x66);
+	} else
+		snd_soc_component_write(comp, RT9120_REG_INTERNAL0, 0x04);
+
 	return 0;
 }
 
@@ -201,8 +217,8 @@ static int rt9120_hw_params(struct snd_pcm_substream *substream,
 			    struct snd_soc_dai *dai)
 {
 	struct snd_soc_component *comp = dai->component;
-	unsigned int param_width, param_slot_width;
-	int width;
+	unsigned int param_width, param_slot_width, auto_sync;
+	int width, fs;
 
 	switch (width = params_width(param)) {
 	case 16:
@@ -240,6 +256,16 @@ static int rt9120_hw_params(struct snd_pcm_substream *substream,
 
 	snd_soc_component_update_bits(comp, RT9120_REG_I2SWL,
 				      RT9120_AUDWL_MASK, param_slot_width);
+
+	fs = width * params_channels(param);
+	/* If fs is divided by 48, disable auto sync */
+	if (fs % 48 == 0)
+		auto_sync = 0;
+	else
+		auto_sync = RT9120_AUTOSYNC_MASK;
+
+	snd_soc_component_update_bits(comp, RT9120_REG_DIGCFG,
+				      RT9120_AUTOSYNC_MASK, auto_sync);
 	return 0;
 }
 
@@ -279,9 +305,11 @@ static const struct regmap_range rt9120_rd_yes_ranges[] = {
 	regmap_reg_range(0x20, 0x27),
 	regmap_reg_range(0x30, 0x38),
 	regmap_reg_range(0x3A, 0x40),
+	regmap_reg_range(0x63, 0x63),
 	regmap_reg_range(0x65, 0x65),
 	regmap_reg_range(0x69, 0x69),
-	regmap_reg_range(0x6C, 0x6C)
+	regmap_reg_range(0x6C, 0x6C),
+	regmap_reg_range(0xF8, 0xF8)
 };
 
 static const struct regmap_access_table rt9120_rd_table = {
@@ -297,9 +325,11 @@ static const struct regmap_range rt9120_wr_yes_ranges[] = {
 	regmap_reg_range(0x30, 0x38),
 	regmap_reg_range(0x3A, 0x3D),
 	regmap_reg_range(0x40, 0x40),
+	regmap_reg_range(0x63, 0x63),
 	regmap_reg_range(0x65, 0x65),
 	regmap_reg_range(0x69, 0x69),
-	regmap_reg_range(0x6C, 0x6C)
+	regmap_reg_range(0x6C, 0x6C),
+	regmap_reg_range(0xF8, 0xF8)
 };
 
 static const struct regmap_access_table rt9120_wr_table = {
@@ -370,7 +400,7 @@ static int rt9120_reg_write(void *context, unsigned int reg, unsigned int val)
 static const struct regmap_config rt9120_regmap_config = {
 	.reg_bits = 8,
 	.val_bits = 32,
-	.max_register = RT9120_REG_UVPOPT,
+	.max_register = RT9120_REG_DIGCFG,
 
 	.reg_read = rt9120_reg_read,
 	.reg_write = rt9120_reg_write,
@@ -388,8 +418,16 @@ static int rt9120_check_vendor_info(struct rt9120_data *data)
 	if (ret)
 		return ret;
 
-	if ((devid & RT9120_VID_MASK) != RT9120_VENDOR_ID) {
-		dev_err(data->dev, "DEVID not correct [0x%04x]\n", devid);
+	devid = FIELD_GET(RT9120_VID_MASK, devid);
+	switch (devid) {
+	case RT9120_VENDOR_ID:
+		data->chip_idx = CHIP_IDX_RT9120;
+		break;
+	case RT9120S_VENDOR_ID:
+		data->chip_idx = CHIP_IDX_RT9120S;
+		break;
+	default:
+		dev_err(data->dev, "DEVID not correct [0x%0x]\n", devid);
 		return -ENODEV;
 	}
 
diff --git a/sound/soc/codecs/tas2770.c b/sound/soc/codecs/tas2770.c
index 172e79cbe0da..6549e7fef3e3 100644
--- a/sound/soc/codecs/tas2770.c
+++ b/sound/soc/codecs/tas2770.c
@@ -291,11 +291,11 @@ static int tas2770_set_samplerate(struct tas2770_priv *tas2770, int samplerate)
 		ramp_rate_val = TAS2770_TDM_CFG_REG0_SMP_44_1KHZ |
 				TAS2770_TDM_CFG_REG0_31_88_2_96KHZ;
 		break;
-	case 19200:
+	case 192000:
 		ramp_rate_val = TAS2770_TDM_CFG_REG0_SMP_48KHZ |
 				TAS2770_TDM_CFG_REG0_31_176_4_192KHZ;
 		break;
-	case 17640:
+	case 176400:
 		ramp_rate_val = TAS2770_TDM_CFG_REG0_SMP_44_1KHZ |
 				TAS2770_TDM_CFG_REG0_31_176_4_192KHZ;
 		break;
diff --git a/sound/soc/codecs/wcd934x.c b/sound/soc/codecs/wcd934x.c
index c496b359f2f4..e63c6b723d76 100644
--- a/sound/soc/codecs/wcd934x.c
+++ b/sound/soc/codecs/wcd934x.c
@@ -1896,9 +1896,8 @@ static int wcd934x_hw_params(struct snd_pcm_substream *substream,
 	}
 
 	wcd->dai[dai->id].sconfig.rate = params_rate(params);
-	wcd934x_slim_set_hw_params(wcd, &wcd->dai[dai->id], substream->stream);
 
-	return 0;
+	return wcd934x_slim_set_hw_params(wcd, &wcd->dai[dai->id], substream->stream);
 }
 
 static int wcd934x_hw_free(struct snd_pcm_substream *substream,
@@ -3257,6 +3256,9 @@ static int wcd934x_compander_set(struct snd_kcontrol *kc,
 	int value = ucontrol->value.integer.value[0];
 	int sel;
 
+	if (wcd->comp_enabled[comp] == value)
+		return 0;
+
 	wcd->comp_enabled[comp] = value;
 	sel = value ? WCD934X_HPH_GAIN_SRC_SEL_COMPANDER :
 		WCD934X_HPH_GAIN_SRC_SEL_REGISTER;
@@ -3280,10 +3282,10 @@ static int wcd934x_compander_set(struct snd_kcontrol *kc,
 	case COMPANDER_8:
 		break;
 	default:
-		break;
+		return 0;
 	}
 
-	return 0;
+	return 1;
 }
 
 static int wcd934x_rx_hph_mode_get(struct snd_kcontrol *kc,
@@ -3327,6 +3329,31 @@ static int slim_rx_mux_get(struct snd_kcontrol *kc,
 	return 0;
 }
 
+static int slim_rx_mux_to_dai_id(int mux)
+{
+	int aif_id;
+
+	switch (mux) {
+	case 1:
+		aif_id = AIF1_PB;
+		break;
+	case 2:
+		aif_id = AIF2_PB;
+		break;
+	case 3:
+		aif_id = AIF3_PB;
+		break;
+	case 4:
+		aif_id = AIF4_PB;
+		break;
+	default:
+		aif_id = -1;
+		break;
+	}
+
+	return aif_id;
+}
+
 static int slim_rx_mux_put(struct snd_kcontrol *kc,
 			   struct snd_ctl_elem_value *ucontrol)
 {
@@ -3334,43 +3361,59 @@ static int slim_rx_mux_put(struct snd_kcontrol *kc,
 	struct wcd934x_codec *wcd = dev_get_drvdata(w->dapm->dev);
 	struct soc_enum *e = (struct soc_enum *)kc->private_value;
 	struct snd_soc_dapm_update *update = NULL;
+	struct wcd934x_slim_ch *ch, *c;
 	u32 port_id = w->shift;
+	bool found = false;
+	int mux_idx;
+	int prev_mux_idx = wcd->rx_port_value[port_id];
+	int aif_id;
 
-	if (wcd->rx_port_value[port_id] == ucontrol->value.enumerated.item[0])
-		return 0;
+	mux_idx = ucontrol->value.enumerated.item[0];
 
-	wcd->rx_port_value[port_id] = ucontrol->value.enumerated.item[0];
+	if (mux_idx == prev_mux_idx)
+		return 0;
 
-	switch (wcd->rx_port_value[port_id]) {
+	switch(mux_idx) {
 	case 0:
-		list_del_init(&wcd->rx_chs[port_id].list);
-		break;
-	case 1:
-		list_add_tail(&wcd->rx_chs[port_id].list,
-			      &wcd->dai[AIF1_PB].slim_ch_list);
-		break;
-	case 2:
-		list_add_tail(&wcd->rx_chs[port_id].list,
-			      &wcd->dai[AIF2_PB].slim_ch_list);
-		break;
-	case 3:
-		list_add_tail(&wcd->rx_chs[port_id].list,
-			      &wcd->dai[AIF3_PB].slim_ch_list);
+		aif_id = slim_rx_mux_to_dai_id(prev_mux_idx);
+		if (aif_id < 0)
+			return 0;
+
+		list_for_each_entry_safe(ch, c, &wcd->dai[aif_id].slim_ch_list, list) {
+			if (ch->port == port_id + WCD934X_RX_START) {
+				found = true;
+				list_del_init(&ch->list);
+				break;
+			}
+		}
+		if (!found)
+			return 0;
+
 		break;
-	case 4:
-		list_add_tail(&wcd->rx_chs[port_id].list,
-			      &wcd->dai[AIF4_PB].slim_ch_list);
+	case 1 ... 4:
+		aif_id = slim_rx_mux_to_dai_id(mux_idx);
+		if (aif_id < 0)
+			return 0;
+
+		if (list_empty(&wcd->rx_chs[port_id].list)) {
+			list_add_tail(&wcd->rx_chs[port_id].list,
+				      &wcd->dai[aif_id].slim_ch_list);
+		} else {
+			dev_err(wcd->dev ,"SLIM_RX%d PORT is busy\n", port_id);
+			return 0;
+		}
 		break;
+
 	default:
-		dev_err(wcd->dev, "Unknown AIF %d\n",
-			wcd->rx_port_value[port_id]);
+		dev_err(wcd->dev, "Unknown AIF %d\n", mux_idx);
 		goto err;
 	}
 
+	wcd->rx_port_value[port_id] = mux_idx;
 	snd_soc_dapm_mux_update_power(w->dapm, kc, wcd->rx_port_value[port_id],
 				      e, update);
 
-	return 0;
+	return 1;
 err:
 	return -EINVAL;
 }
@@ -3816,6 +3859,7 @@ static int slim_tx_mixer_put(struct snd_kcontrol *kc,
 	struct soc_mixer_control *mixer =
 			(struct soc_mixer_control *)kc->private_value;
 	int enable = ucontrol->value.integer.value[0];
+	struct wcd934x_slim_ch *ch, *c;
 	int dai_id = widget->shift;
 	int port_id = mixer->shift;
 
@@ -3823,17 +3867,32 @@ static int slim_tx_mixer_put(struct snd_kcontrol *kc,
 	if (enable == wcd->tx_port_value[port_id])
 		return 0;
 
-	wcd->tx_port_value[port_id] = enable;
-
-	if (enable)
-		list_add_tail(&wcd->tx_chs[port_id].list,
-			      &wcd->dai[dai_id].slim_ch_list);
-	else
-		list_del_init(&wcd->tx_chs[port_id].list);
+	if (enable) {
+		if (list_empty(&wcd->tx_chs[port_id].list)) {
+			list_add_tail(&wcd->tx_chs[port_id].list,
+				      &wcd->dai[dai_id].slim_ch_list);
+		} else {
+			dev_err(wcd->dev ,"SLIM_TX%d PORT is busy\n", port_id);
+			return 0;
+		}
+	 } else {
+		bool found = false;
+
+		list_for_each_entry_safe(ch, c, &wcd->dai[dai_id].slim_ch_list, list) {
+			if (ch->port == port_id) {
+				found = true;
+				list_del_init(&wcd->tx_chs[port_id].list);
+				break;
+			}
+		}
+		if (!found)
+			return 0;
+	 }
 
+	wcd->tx_port_value[port_id] = enable;
 	snd_soc_dapm_mixer_update_power(widget->dapm, kc, enable, update);
 
-	return 0;
+	return 1;
 }
 
 static const struct snd_kcontrol_new aif1_slim_cap_mixer[] = {
diff --git a/sound/soc/codecs/wcd938x.c b/sound/soc/codecs/wcd938x.c
index 52de7d14b139..67151c7770c6 100644
--- a/sound/soc/codecs/wcd938x.c
+++ b/sound/soc/codecs/wcd938x.c
@@ -1174,6 +1174,9 @@ static bool wcd938x_readonly_register(struct device *dev, unsigned int reg)
 	case WCD938X_DIGITAL_INTR_STATUS_0:
 	case WCD938X_DIGITAL_INTR_STATUS_1:
 	case WCD938X_DIGITAL_INTR_STATUS_2:
+	case WCD938X_DIGITAL_INTR_CLEAR_0:
+	case WCD938X_DIGITAL_INTR_CLEAR_1:
+	case WCD938X_DIGITAL_INTR_CLEAR_2:
 	case WCD938X_DIGITAL_SWR_HM_TEST_0:
 	case WCD938X_DIGITAL_SWR_HM_TEST_1:
 	case WCD938X_DIGITAL_EFUSE_T_DATA_0:
diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c
index d4f0d72cbcc8..6cb01a8e08fb 100644
--- a/sound/soc/codecs/wm_adsp.c
+++ b/sound/soc/codecs/wm_adsp.c
@@ -617,8 +617,9 @@ static int wm_adsp_control_add(struct cs_dsp_coeff_ctl *cs_ctl)
 	switch (cs_dsp->fw_ver) {
 	case 0:
 	case 1:
-		snprintf(name, SNDRV_CTL_ELEM_ID_NAME_MAXLEN, "%s %s %x",
-			 cs_dsp->name, region_name, cs_ctl->alg_region.alg);
+		ret = scnprintf(name, SNDRV_CTL_ELEM_ID_NAME_MAXLEN,
+				"%s %s %x", cs_dsp->name, region_name,
+				cs_ctl->alg_region.alg);
 		break;
 	case 2:
 		ret = scnprintf(name, SNDRV_CTL_ELEM_ID_NAME_MAXLEN,
diff --git a/sound/soc/codecs/wsa881x.c b/sound/soc/codecs/wsa881x.c
index 2da4a5fa7a18..564b78f3cdd0 100644
--- a/sound/soc/codecs/wsa881x.c
+++ b/sound/soc/codecs/wsa881x.c
@@ -772,7 +772,8 @@ static int wsa881x_put_pa_gain(struct snd_kcontrol *kc,
 
 		usleep_range(1000, 1010);
 	}
-	return 0;
+
+	return 1;
 }
 
 static int wsa881x_get_port(struct snd_kcontrol *kcontrol,
@@ -816,15 +817,22 @@ static int wsa881x_set_port(struct snd_kcontrol *kcontrol,
 		(struct soc_mixer_control *)kcontrol->private_value;
 	int portidx = mixer->reg;
 
-	if (ucontrol->value.integer.value[0])
+	if (ucontrol->value.integer.value[0]) {
+		if (data->port_enable[portidx])
+			return 0;
+
 		data->port_enable[portidx] = true;
-	else
+	} else {
+		if (!data->port_enable[portidx])
+			return 0;
+
 		data->port_enable[portidx] = false;
+	}
 
 	if (portidx == WSA881X_PORT_BOOST) /* Boost Switch */
 		wsa881x_boost_ctrl(comp, data->port_enable[portidx]);
 
-	return 0;
+	return 1;
 }
 
 static const char * const smart_boost_lvl_text[] = {
diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c
index f10496206cee..77219c3f8766 100644
--- a/sound/soc/intel/boards/sof_sdw.c
+++ b/sound/soc/intel/boards/sof_sdw.c
@@ -248,6 +248,75 @@ static const struct dmi_system_id sof_sdw_quirk_table[] = {
 					SOF_BT_OFFLOAD_SSP(2) |
 					SOF_SSP_BT_OFFLOAD_PRESENT),
 	},
+	{
+		.callback = sof_sdw_quirk_cb,
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_SKU, "0AF3"),
+		},
+		/* No Jack */
+		.driver_data = (void *)(SOF_SDW_TGL_HDMI |
+					SOF_SDW_FOUR_SPK),
+	},
+	{
+		.callback = sof_sdw_quirk_cb,
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_SKU, "0B00")
+		},
+		.driver_data = (void *)(SOF_SDW_TGL_HDMI |
+					RT711_JD2 |
+					SOF_SDW_FOUR_SPK),
+	},
+	{
+		.callback = sof_sdw_quirk_cb,
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_SKU, "0B01")
+		},
+		.driver_data = (void *)(SOF_SDW_TGL_HDMI |
+					RT711_JD2 |
+					SOF_SDW_FOUR_SPK),
+	},
+	{
+		.callback = sof_sdw_quirk_cb,
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_SKU, "0B11")
+		},
+		.driver_data = (void *)(SOF_SDW_TGL_HDMI |
+					RT711_JD2 |
+					SOF_SDW_FOUR_SPK),
+	},
+	{
+		.callback = sof_sdw_quirk_cb,
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_SKU, "0B12")
+		},
+		.driver_data = (void *)(SOF_SDW_TGL_HDMI |
+					RT711_JD2 |
+					SOF_SDW_FOUR_SPK),
+	},
+	{
+		.callback = sof_sdw_quirk_cb,
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_SKU, "0B13"),
+		},
+		/* No Jack */
+		.driver_data = (void *)SOF_SDW_TGL_HDMI,
+	},
+	{
+		.callback = sof_sdw_quirk_cb,
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_SKU, "0B29"),
+		},
+		.driver_data = (void *)(SOF_SDW_TGL_HDMI |
+					RT711_JD2 |
+					SOF_SDW_FOUR_SPK),
+	},
 	{}
 };
 
diff --git a/sound/soc/intel/common/soc-acpi-intel-adl-match.c b/sound/soc/intel/common/soc-acpi-intel-adl-match.c
index 06f503452aa5..b61a778a9d26 100644
--- a/sound/soc/intel/common/soc-acpi-intel-adl-match.c
+++ b/sound/soc/intel/common/soc-acpi-intel-adl-match.c
@@ -74,6 +74,15 @@ static const struct snd_soc_acpi_adr_device rt711_sdca_0_adr[] = {
 	}
 };
 
+static const struct snd_soc_acpi_adr_device rt711_sdca_2_adr[] = {
+	{
+		.adr = 0x000230025D071101ull,
+		.num_endpoints = 1,
+		.endpoints = &single_endpoint,
+		.name_prefix = "rt711"
+	}
+};
+
 static const struct snd_soc_acpi_adr_device rt1316_1_group1_adr[] = {
 	{
 		.adr = 0x000131025D131601ull, /* unique ID is set for some reason */
@@ -101,6 +110,24 @@ static const struct snd_soc_acpi_adr_device rt1316_3_group1_adr[] = {
 	}
 };
 
+static const struct snd_soc_acpi_adr_device rt1316_0_group2_adr[] = {
+	{
+		.adr = 0x000031025D131601ull,
+		.num_endpoints = 1,
+		.endpoints = &spk_l_endpoint,
+		.name_prefix = "rt1316-1"
+	}
+};
+
+static const struct snd_soc_acpi_adr_device rt1316_1_group2_adr[] = {
+	{
+		.adr = 0x000130025D131601ull,
+		.num_endpoints = 1,
+		.endpoints = &spk_r_endpoint,
+		.name_prefix = "rt1316-2"
+	}
+};
+
 static const struct snd_soc_acpi_adr_device rt1316_2_single_adr[] = {
 	{
 		.adr = 0x000230025D131601ull,
@@ -209,6 +236,63 @@ static const struct snd_soc_acpi_link_adr adl_sdca_3_in_1[] = {
 	{}
 };
 
+static const struct snd_soc_acpi_link_adr adl_sdw_rt711_link2_rt1316_link01_rt714_link3[] = {
+	{
+		.mask = BIT(2),
+		.num_adr = ARRAY_SIZE(rt711_sdca_2_adr),
+		.adr_d = rt711_sdca_2_adr,
+	},
+	{
+		.mask = BIT(0),
+		.num_adr = ARRAY_SIZE(rt1316_0_group2_adr),
+		.adr_d = rt1316_0_group2_adr,
+	},
+	{
+		.mask = BIT(1),
+		.num_adr = ARRAY_SIZE(rt1316_1_group2_adr),
+		.adr_d = rt1316_1_group2_adr,
+	},
+	{
+		.mask = BIT(3),
+		.num_adr = ARRAY_SIZE(rt714_3_adr),
+		.adr_d = rt714_3_adr,
+	},
+	{}
+};
+
+static const struct snd_soc_acpi_link_adr adl_sdw_rt1316_link12_rt714_link0[] = {
+	{
+		.mask = BIT(1),
+		.num_adr = ARRAY_SIZE(rt1316_1_group1_adr),
+		.adr_d = rt1316_1_group1_adr,
+	},
+	{
+		.mask = BIT(2),
+		.num_adr = ARRAY_SIZE(rt1316_2_group1_adr),
+		.adr_d = rt1316_2_group1_adr,
+	},
+	{
+		.mask = BIT(0),
+		.num_adr = ARRAY_SIZE(rt714_0_adr),
+		.adr_d = rt714_0_adr,
+	},
+	{}
+};
+
+static const struct snd_soc_acpi_link_adr adl_sdw_rt1316_link2_rt714_link3[] = {
+	{
+		.mask = BIT(2),
+		.num_adr = ARRAY_SIZE(rt1316_2_single_adr),
+		.adr_d = rt1316_2_single_adr,
+	},
+	{
+		.mask = BIT(3),
+		.num_adr = ARRAY_SIZE(rt714_3_adr),
+		.adr_d = rt714_3_adr,
+	},
+	{}
+};
+
 static const struct snd_soc_acpi_link_adr adl_sdw_rt1316_link2_rt714_link0[] = {
 	{
 		.mask = BIT(2),
@@ -340,6 +424,27 @@ struct snd_soc_acpi_mach snd_soc_acpi_intel_adl_sdw_machines[] = {
 		.sof_tplg_filename = "sof-adl-rt711-l0-rt1316-l13-rt714-l2.tplg",
 	},
 	{
+		.link_mask = 0xF, /* 4 active links required */
+		.links = adl_sdw_rt711_link2_rt1316_link01_rt714_link3,
+		.drv_name = "sof_sdw",
+		.sof_fw_filename = "sof-adl.ri",
+		.sof_tplg_filename = "sof-adl-rt711-l2-rt1316-l01-rt714-l3.tplg",
+	},
+	{
+		.link_mask = 0xC, /* rt1316 on link2 & rt714 on link3 */
+		.links = adl_sdw_rt1316_link2_rt714_link3,
+		.drv_name = "sof_sdw",
+		.sof_fw_filename = "sof-adl.ri",
+		.sof_tplg_filename = "sof-adl-rt1316-l2-mono-rt714-l3.tplg",
+	},
+	{
+		.link_mask = 0x7, /* rt714 on link0 & two rt1316s on link1 and link2 */
+		.links = adl_sdw_rt1316_link12_rt714_link0,
+		.drv_name = "sof_sdw",
+		.sof_fw_filename = "sof-adl.ri",
+		.sof_tplg_filename = "sof-adl-rt1316-l12-rt714-l0.tplg",
+	},
+	{
 		.link_mask = 0x5, /* 2 active links required */
 		.links = adl_sdw_rt1316_link2_rt714_link0,
 		.drv_name = "sof_sdw",
diff --git a/sound/soc/intel/common/soc-acpi-intel-cml-match.c b/sound/soc/intel/common/soc-acpi-intel-cml-match.c
index b4eb0c97edf1..4eebc79d4b48 100644
--- a/sound/soc/intel/common/soc-acpi-intel-cml-match.c
+++ b/sound/soc/intel/common/soc-acpi-intel-cml-match.c
@@ -81,6 +81,12 @@ struct snd_soc_acpi_mach snd_soc_acpi_intel_cml_machines[] = {
 		.sof_fw_filename = "sof-cml.ri",
 		.sof_tplg_filename = "sof-cml-da7219-max98390.tplg",
 	},
+	{
+		.id = "ESSX8336",
+		.drv_name = "sof-essx8336",
+		.sof_fw_filename = "sof-cml.ri",
+		.sof_tplg_filename = "sof-cml-es8336.tplg",
+	},
 	{},
 };
 EXPORT_SYMBOL_GPL(snd_soc_acpi_intel_cml_machines);
diff --git a/sound/soc/mediatek/mt8173/mt8173-afe-pcm.c b/sound/soc/mediatek/mt8173/mt8173-afe-pcm.c
index 6350390414d4..31494930433f 100644
--- a/sound/soc/mediatek/mt8173/mt8173-afe-pcm.c
+++ b/sound/soc/mediatek/mt8173/mt8173-afe-pcm.c
@@ -1054,6 +1054,7 @@ static int mt8173_afe_pcm_dev_probe(struct platform_device *pdev)
 	int irq_id;
 	struct mtk_base_afe *afe;
 	struct mt8173_afe_private *afe_priv;
+	struct snd_soc_component *comp_pcm, *comp_hdmi;
 
 	ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(33));
 	if (ret)
@@ -1142,23 +1143,55 @@ static int mt8173_afe_pcm_dev_probe(struct platform_device *pdev)
 	if (ret)
 		goto err_pm_disable;
 
-	ret = devm_snd_soc_register_component(&pdev->dev,
-					 &mt8173_afe_pcm_dai_component,
-					 mt8173_afe_pcm_dais,
-					 ARRAY_SIZE(mt8173_afe_pcm_dais));
+	comp_pcm = devm_kzalloc(&pdev->dev, sizeof(*comp_pcm), GFP_KERNEL);
+	if (!comp_pcm) {
+		ret = -ENOMEM;
+		goto err_pm_disable;
+	}
+
+	ret = snd_soc_component_initialize(comp_pcm,
+					   &mt8173_afe_pcm_dai_component,
+					   &pdev->dev);
 	if (ret)
 		goto err_pm_disable;
 
-	ret = devm_snd_soc_register_component(&pdev->dev,
-					 &mt8173_afe_hdmi_dai_component,
-					 mt8173_afe_hdmi_dais,
-					 ARRAY_SIZE(mt8173_afe_hdmi_dais));
+#ifdef CONFIG_DEBUG_FS
+	comp_pcm->debugfs_prefix = "pcm";
+#endif
+
+	ret = snd_soc_add_component(comp_pcm,
+				    mt8173_afe_pcm_dais,
+				    ARRAY_SIZE(mt8173_afe_pcm_dais));
+	if (ret)
+		goto err_pm_disable;
+
+	comp_hdmi = devm_kzalloc(&pdev->dev, sizeof(*comp_hdmi), GFP_KERNEL);
+	if (!comp_hdmi) {
+		ret = -ENOMEM;
+		goto err_pm_disable;
+	}
+
+	ret = snd_soc_component_initialize(comp_hdmi,
+					   &mt8173_afe_hdmi_dai_component,
+					   &pdev->dev);
 	if (ret)
 		goto err_pm_disable;
 
+#ifdef CONFIG_DEBUG_FS
+	comp_hdmi->debugfs_prefix = "hdmi";
+#endif
+
+	ret = snd_soc_add_component(comp_hdmi,
+				    mt8173_afe_hdmi_dais,
+				    ARRAY_SIZE(mt8173_afe_hdmi_dais));
+	if (ret)
+		goto err_cleanup_components;
+
 	dev_info(&pdev->dev, "MT8173 AFE driver initialized.\n");
 	return 0;
 
+err_cleanup_components:
+	snd_soc_unregister_component(&pdev->dev);
 err_pm_disable:
 	pm_runtime_disable(&pdev->dev);
 	return ret;
@@ -1166,6 +1199,8 @@ err_pm_disable:
 
 static int mt8173_afe_pcm_dev_remove(struct platform_device *pdev)
 {
+	snd_soc_unregister_component(&pdev->dev);
+
 	pm_runtime_disable(&pdev->dev);
 	if (!pm_runtime_status_suspended(&pdev->dev))
 		mt8173_afe_runtime_suspend(&pdev->dev);
diff --git a/sound/soc/mediatek/mt8173/mt8173-rt5650.c b/sound/soc/mediatek/mt8173/mt8173-rt5650.c
index c28ebf891cb0..2cbf679f5c74 100644
--- a/sound/soc/mediatek/mt8173/mt8173-rt5650.c
+++ b/sound/soc/mediatek/mt8173/mt8173-rt5650.c
@@ -30,15 +30,15 @@ static struct mt8173_rt5650_platform_data mt8173_rt5650_priv = {
 };
 
 static const struct snd_soc_dapm_widget mt8173_rt5650_widgets[] = {
-	SND_SOC_DAPM_SPK("Speaker", NULL),
+	SND_SOC_DAPM_SPK("Ext Spk", NULL),
 	SND_SOC_DAPM_MIC("Int Mic", NULL),
 	SND_SOC_DAPM_HP("Headphone", NULL),
 	SND_SOC_DAPM_MIC("Headset Mic", NULL),
 };
 
 static const struct snd_soc_dapm_route mt8173_rt5650_routes[] = {
-	{"Speaker", NULL, "SPOL"},
-	{"Speaker", NULL, "SPOR"},
+	{"Ext Spk", NULL, "SPOL"},
+	{"Ext Spk", NULL, "SPOR"},
 	{"DMIC L1", NULL, "Int Mic"},
 	{"DMIC R1", NULL, "Int Mic"},
 	{"Headphone", NULL, "HPOL"},
@@ -48,7 +48,7 @@ static const struct snd_soc_dapm_route mt8173_rt5650_routes[] = {
 };
 
 static const struct snd_kcontrol_new mt8173_rt5650_controls[] = {
-	SOC_DAPM_PIN_SWITCH("Speaker"),
+	SOC_DAPM_PIN_SWITCH("Ext Spk"),
 	SOC_DAPM_PIN_SWITCH("Int Mic"),
 	SOC_DAPM_PIN_SWITCH("Headphone"),
 	SOC_DAPM_PIN_SWITCH("Headset Mic"),
diff --git a/sound/soc/meson/aiu-encoder-i2s.c b/sound/soc/meson/aiu-encoder-i2s.c
index 932224552146..67729de41a73 100644
--- a/sound/soc/meson/aiu-encoder-i2s.c
+++ b/sound/soc/meson/aiu-encoder-i2s.c
@@ -18,7 +18,6 @@
 #define AIU_RST_SOFT_I2S_FAST		BIT(0)
 
 #define AIU_I2S_DAC_CFG_MSB_FIRST	BIT(2)
-#define AIU_I2S_MISC_HOLD_EN		BIT(2)
 #define AIU_CLK_CTRL_I2S_DIV_EN		BIT(0)
 #define AIU_CLK_CTRL_I2S_DIV		GENMASK(3, 2)
 #define AIU_CLK_CTRL_AOCLK_INVERT	BIT(6)
@@ -36,37 +35,6 @@ static void aiu_encoder_i2s_divider_enable(struct snd_soc_component *component,
 				      enable ? AIU_CLK_CTRL_I2S_DIV_EN : 0);
 }
 
-static void aiu_encoder_i2s_hold(struct snd_soc_component *component,
-				 bool enable)
-{
-	snd_soc_component_update_bits(component, AIU_I2S_MISC,
-				      AIU_I2S_MISC_HOLD_EN,
-				      enable ? AIU_I2S_MISC_HOLD_EN : 0);
-}
-
-static int aiu_encoder_i2s_trigger(struct snd_pcm_substream *substream, int cmd,
-				   struct snd_soc_dai *dai)
-{
-	struct snd_soc_component *component = dai->component;
-
-	switch (cmd) {
-	case SNDRV_PCM_TRIGGER_START:
-	case SNDRV_PCM_TRIGGER_RESUME:
-	case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
-		aiu_encoder_i2s_hold(component, false);
-		return 0;
-
-	case SNDRV_PCM_TRIGGER_STOP:
-	case SNDRV_PCM_TRIGGER_SUSPEND:
-	case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
-		aiu_encoder_i2s_hold(component, true);
-		return 0;
-
-	default:
-		return -EINVAL;
-	}
-}
-
 static int aiu_encoder_i2s_setup_desc(struct snd_soc_component *component,
 				      struct snd_pcm_hw_params *params)
 {
@@ -353,7 +321,6 @@ static void aiu_encoder_i2s_shutdown(struct snd_pcm_substream *substream,
 }
 
 const struct snd_soc_dai_ops aiu_encoder_i2s_dai_ops = {
-	.trigger	= aiu_encoder_i2s_trigger,
 	.hw_params	= aiu_encoder_i2s_hw_params,
 	.hw_free	= aiu_encoder_i2s_hw_free,
 	.set_fmt	= aiu_encoder_i2s_set_fmt,
diff --git a/sound/soc/meson/aiu-fifo-i2s.c b/sound/soc/meson/aiu-fifo-i2s.c
index 2388a2d0b3a6..57e6e7160d2f 100644
--- a/sound/soc/meson/aiu-fifo-i2s.c
+++ b/sound/soc/meson/aiu-fifo-i2s.c
@@ -20,6 +20,8 @@
 #define AIU_MEM_I2S_CONTROL_MODE_16BIT	BIT(6)
 #define AIU_MEM_I2S_BUF_CNTL_INIT	BIT(0)
 #define AIU_RST_SOFT_I2S_FAST		BIT(0)
+#define AIU_I2S_MISC_HOLD_EN		BIT(2)
+#define AIU_I2S_MISC_FORCE_LEFT_RIGHT	BIT(4)
 
 #define AIU_FIFO_I2S_BLOCK		256
 
@@ -90,6 +92,10 @@ static int aiu_fifo_i2s_hw_params(struct snd_pcm_substream *substream,
 	unsigned int val;
 	int ret;
 
+	snd_soc_component_update_bits(component, AIU_I2S_MISC,
+				      AIU_I2S_MISC_HOLD_EN,
+				      AIU_I2S_MISC_HOLD_EN);
+
 	ret = aiu_fifo_hw_params(substream, params, dai);
 	if (ret)
 		return ret;
@@ -117,6 +123,19 @@ static int aiu_fifo_i2s_hw_params(struct snd_pcm_substream *substream,
 	snd_soc_component_update_bits(component, AIU_MEM_I2S_MASKS,
 				      AIU_MEM_I2S_MASKS_IRQ_BLOCK, val);
 
+	/*
+	 * Most (all?) supported SoCs have this bit set by default. The vendor
+	 * driver however sets it manually (depending on the version either
+	 * while un-setting AIU_I2S_MISC_HOLD_EN or right before that). Follow
+	 * the same approach for consistency with the vendor driver.
+	 */
+	snd_soc_component_update_bits(component, AIU_I2S_MISC,
+				      AIU_I2S_MISC_FORCE_LEFT_RIGHT,
+				      AIU_I2S_MISC_FORCE_LEFT_RIGHT);
+
+	snd_soc_component_update_bits(component, AIU_I2S_MISC,
+				      AIU_I2S_MISC_HOLD_EN, 0);
+
 	return 0;
 }
 
diff --git a/sound/soc/meson/aiu-fifo.c b/sound/soc/meson/aiu-fifo.c
index 4ad23267cace..d67ff4cdabd5 100644
--- a/sound/soc/meson/aiu-fifo.c
+++ b/sound/soc/meson/aiu-fifo.c
@@ -5,6 +5,7 @@
 
 #include <linux/bitfield.h>
 #include <linux/clk.h>
+#include <linux/dma-mapping.h>
 #include <sound/pcm_params.h>
 #include <sound/soc.h>
 #include <sound/soc-dai.h>
@@ -179,6 +180,11 @@ int aiu_fifo_pcm_new(struct snd_soc_pcm_runtime *rtd,
 	struct snd_card *card = rtd->card->snd_card;
 	struct aiu_fifo *fifo = dai->playback_dma_data;
 	size_t size = fifo->pcm->buffer_bytes_max;
+	int ret;
+
+	ret = dma_coerce_mask_and_coherent(card->dev, DMA_BIT_MASK(32));
+	if (ret)
+		return ret;
 
 	snd_pcm_set_managed_buffer_all(rtd->pcm, SNDRV_DMA_TYPE_DEV,
 				       card->dev, size, size);
diff --git a/sound/soc/qcom/qdsp6/audioreach.h b/sound/soc/qcom/qdsp6/audioreach.h
index 4f693a2660b5..3ee8bfcd0121 100644
--- a/sound/soc/qcom/qdsp6/audioreach.h
+++ b/sound/soc/qcom/qdsp6/audioreach.h
@@ -550,6 +550,10 @@ struct audio_hw_clk_cfg {
 	uint32_t clock_root;
 } __packed;
 
+struct audio_hw_clk_rel_cfg {
+	uint32_t clock_id;
+} __packed;
+
 #define PARAM_ID_HW_EP_POWER_MODE_CFG	0x8001176
 #define AR_HW_EP_POWER_MODE_0	0 /* default */
 #define AR_HW_EP_POWER_MODE_1	1 /* XO Shutdown allowed */
diff --git a/sound/soc/qcom/qdsp6/q6adm.c b/sound/soc/qcom/qdsp6/q6adm.c
index 3d831b635524..72c5719f1d25 100644
--- a/sound/soc/qcom/qdsp6/q6adm.c
+++ b/sound/soc/qcom/qdsp6/q6adm.c
@@ -390,7 +390,7 @@ struct q6copp *q6adm_open(struct device *dev, int port_id, int path, int rate,
 	int ret = 0;
 
 	if (port_id < 0) {
-		dev_err(dev, "Invalid port_id 0x%x\n", port_id);
+		dev_err(dev, "Invalid port_id %d\n", port_id);
 		return ERR_PTR(-EINVAL);
 	}
 
@@ -508,7 +508,7 @@ int q6adm_matrix_map(struct device *dev, int path,
 		int port_idx = payload_map.port_id[i];
 
 		if (port_idx < 0) {
-			dev_err(dev, "Invalid port_id 0x%x\n",
+			dev_err(dev, "Invalid port_id %d\n",
 				payload_map.port_id[i]);
 			kfree(pkt);
 			return -EINVAL;
diff --git a/sound/soc/qcom/qdsp6/q6asm-dai.c b/sound/soc/qcom/qdsp6/q6asm-dai.c
index 46f365528d50..b74b67720ef4 100644
--- a/sound/soc/qcom/qdsp6/q6asm-dai.c
+++ b/sound/soc/qcom/qdsp6/q6asm-dai.c
@@ -269,9 +269,7 @@ static int q6asm_dai_prepare(struct snd_soc_component *component,
 
 	if (ret < 0) {
 		dev_err(dev, "%s: q6asm_open_write failed\n", __func__);
-		q6asm_audio_client_free(prtd->audio_client);
-		prtd->audio_client = NULL;
-		return -ENOMEM;
+		goto open_err;
 	}
 
 	prtd->session_id = q6asm_get_session_id(prtd->audio_client);
@@ -279,7 +277,7 @@ static int q6asm_dai_prepare(struct snd_soc_component *component,
 			      prtd->session_id, substream->stream);
 	if (ret) {
 		dev_err(dev, "%s: stream reg failed ret:%d\n", __func__, ret);
-		return ret;
+		goto routing_err;
 	}
 
 	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
@@ -301,10 +299,19 @@ static int q6asm_dai_prepare(struct snd_soc_component *component,
 	}
 	if (ret < 0)
 		dev_info(dev, "%s: CMD Format block failed\n", __func__);
+	else
+		prtd->state = Q6ASM_STREAM_RUNNING;
 
-	prtd->state = Q6ASM_STREAM_RUNNING;
+	return ret;
 
-	return 0;
+routing_err:
+	q6asm_cmd(prtd->audio_client, prtd->stream_id,  CMD_CLOSE);
+open_err:
+	q6asm_unmap_memory_regions(substream->stream, prtd->audio_client);
+	q6asm_audio_client_free(prtd->audio_client);
+	prtd->audio_client = NULL;
+
+	return ret;
 }
 
 static int q6asm_dai_trigger(struct snd_soc_component *component,
diff --git a/sound/soc/qcom/qdsp6/q6prm.c b/sound/soc/qcom/qdsp6/q6prm.c
index 82c40f2d4e1d..cda33ded29be 100644
--- a/sound/soc/qcom/qdsp6/q6prm.c
+++ b/sound/soc/qcom/qdsp6/q6prm.c
@@ -42,6 +42,12 @@ struct prm_cmd_request_rsc {
 	struct audio_hw_clk_cfg clock_id;
 } __packed;
 
+struct prm_cmd_release_rsc {
+	struct apm_module_param_data param_data;
+	uint32_t num_clk_id;
+	struct audio_hw_clk_rel_cfg clock_id;
+} __packed;
+
 static int q6prm_send_cmd_sync(struct q6prm *prm, struct gpr_pkt *pkt, uint32_t rsp_opcode)
 {
 	return audioreach_send_cmd_sync(prm->dev, prm->gdev, &prm->result, &prm->lock,
@@ -102,8 +108,8 @@ int q6prm_unvote_lpass_core_hw(struct device *dev, uint32_t hw_block_id, uint32_
 }
 EXPORT_SYMBOL_GPL(q6prm_unvote_lpass_core_hw);
 
-int q6prm_set_lpass_clock(struct device *dev, int clk_id, int clk_attr, int clk_root,
-			  unsigned int freq)
+static int q6prm_request_lpass_clock(struct device *dev, int clk_id, int clk_attr, int clk_root,
+				     unsigned int freq)
 {
 	struct q6prm *prm = dev_get_drvdata(dev->parent);
 	struct apm_module_param_data *param_data;
@@ -138,6 +144,49 @@ int q6prm_set_lpass_clock(struct device *dev, int clk_id, int clk_attr, int clk_
 
 	return rc;
 }
+
+static int q6prm_release_lpass_clock(struct device *dev, int clk_id, int clk_attr, int clk_root,
+			  unsigned int freq)
+{
+	struct q6prm *prm = dev_get_drvdata(dev->parent);
+	struct apm_module_param_data *param_data;
+	struct prm_cmd_release_rsc *rel;
+	gpr_device_t *gdev = prm->gdev;
+	struct gpr_pkt *pkt;
+	int rc;
+
+	pkt = audioreach_alloc_cmd_pkt(sizeof(*rel), PRM_CMD_RELEASE_HW_RSC, 0, gdev->svc.id,
+				       GPR_PRM_MODULE_IID);
+	if (IS_ERR(pkt))
+		return PTR_ERR(pkt);
+
+	rel = (void *)pkt + GPR_HDR_SIZE + APM_CMD_HDR_SIZE;
+
+	param_data = &rel->param_data;
+
+	param_data->module_instance_id = GPR_PRM_MODULE_IID;
+	param_data->error_code = 0;
+	param_data->param_id = PARAM_ID_RSC_AUDIO_HW_CLK;
+	param_data->param_size = sizeof(*rel) - APM_MODULE_PARAM_DATA_SIZE;
+
+	rel->num_clk_id = 1;
+	rel->clock_id.clock_id = clk_id;
+
+	rc = q6prm_send_cmd_sync(prm, pkt, PRM_CMD_RSP_RELEASE_HW_RSC);
+
+	kfree(pkt);
+
+	return rc;
+}
+
+int q6prm_set_lpass_clock(struct device *dev, int clk_id, int clk_attr, int clk_root,
+			  unsigned int freq)
+{
+	if (freq)
+		return q6prm_request_lpass_clock(dev, clk_id, clk_attr, clk_attr, freq);
+
+	return q6prm_release_lpass_clock(dev, clk_id, clk_attr, clk_attr, freq);
+}
 EXPORT_SYMBOL_GPL(q6prm_set_lpass_clock);
 
 static int prm_callback(struct gpr_resp_pkt *data, void *priv, int op)
diff --git a/sound/soc/qcom/qdsp6/q6routing.c b/sound/soc/qcom/qdsp6/q6routing.c
index 3390ebef9549..928fd23e2c27 100644
--- a/sound/soc/qcom/qdsp6/q6routing.c
+++ b/sound/soc/qcom/qdsp6/q6routing.c
@@ -372,6 +372,12 @@ int q6routing_stream_open(int fedai_id, int perf_mode,
 	}
 
 	session = &routing_data->sessions[stream_id - 1];
+	if (session->port_id < 0) {
+		dev_err(routing_data->dev, "Routing not setup for MultiMedia%d Session\n",
+			session->fedai_id);
+		return -EINVAL;
+	}
+
 	pdata = &routing_data->port_data[session->port_id];
 
 	mutex_lock(&routing_data->lock);
@@ -492,9 +498,15 @@ static int msm_routing_put_audio_mixer(struct snd_kcontrol *kcontrol,
 	struct session_data *session = &data->sessions[session_id];
 
 	if (ucontrol->value.integer.value[0]) {
+		if (session->port_id == be_id)
+			return 0;
+
 		session->port_id = be_id;
 		snd_soc_dapm_mixer_update_power(dapm, kcontrol, 1, update);
 	} else {
+		if (session->port_id == -1 || session->port_id != be_id)
+			return 0;
+
 		session->port_id = -1;
 		snd_soc_dapm_mixer_update_power(dapm, kcontrol, 0, update);
 	}
diff --git a/sound/soc/rockchip/rockchip_i2s_tdm.c b/sound/soc/rockchip/rockchip_i2s_tdm.c
index 17b9b287853a..5f9cb5c4c7f0 100644
--- a/sound/soc/rockchip/rockchip_i2s_tdm.c
+++ b/sound/soc/rockchip/rockchip_i2s_tdm.c
@@ -95,6 +95,7 @@ struct rk_i2s_tdm_dev {
 	spinlock_t lock; /* xfer lock */
 	bool has_playback;
 	bool has_capture;
+	struct snd_soc_dai_driver *dai;
 };
 
 static int to_ch_num(unsigned int val)
@@ -1310,19 +1311,14 @@ static const struct of_device_id rockchip_i2s_tdm_match[] = {
 	{},
 };
 
-static struct snd_soc_dai_driver i2s_tdm_dai = {
+static const struct snd_soc_dai_driver i2s_tdm_dai = {
 	.probe = rockchip_i2s_tdm_dai_probe,
-	.playback = {
-		.stream_name  = "Playback",
-	},
-	.capture = {
-		.stream_name  = "Capture",
-	},
 	.ops = &rockchip_i2s_tdm_dai_ops,
 };
 
-static void rockchip_i2s_tdm_init_dai(struct rk_i2s_tdm_dev *i2s_tdm)
+static int rockchip_i2s_tdm_init_dai(struct rk_i2s_tdm_dev *i2s_tdm)
 {
+	struct snd_soc_dai_driver *dai;
 	struct property *dma_names;
 	const char *dma_name;
 	u64 formats = (SNDRV_PCM_FMTBIT_S8 | SNDRV_PCM_FMTBIT_S16_LE |
@@ -1337,19 +1333,33 @@ static void rockchip_i2s_tdm_init_dai(struct rk_i2s_tdm_dev *i2s_tdm)
 			i2s_tdm->has_capture = true;
 	}
 
+	dai = devm_kmemdup(i2s_tdm->dev, &i2s_tdm_dai,
+			   sizeof(*dai), GFP_KERNEL);
+	if (!dai)
+		return -ENOMEM;
+
 	if (i2s_tdm->has_playback) {
-		i2s_tdm_dai.playback.channels_min = 2;
-		i2s_tdm_dai.playback.channels_max = 8;
-		i2s_tdm_dai.playback.rates = SNDRV_PCM_RATE_8000_192000;
-		i2s_tdm_dai.playback.formats = formats;
+		dai->playback.stream_name  = "Playback";
+		dai->playback.channels_min = 2;
+		dai->playback.channels_max = 8;
+		dai->playback.rates = SNDRV_PCM_RATE_8000_192000;
+		dai->playback.formats = formats;
 	}
 
 	if (i2s_tdm->has_capture) {
-		i2s_tdm_dai.capture.channels_min = 2;
-		i2s_tdm_dai.capture.channels_max = 8;
-		i2s_tdm_dai.capture.rates = SNDRV_PCM_RATE_8000_192000;
-		i2s_tdm_dai.capture.formats = formats;
+		dai->capture.stream_name  = "Capture";
+		dai->capture.channels_min = 2;
+		dai->capture.channels_max = 8;
+		dai->capture.rates = SNDRV_PCM_RATE_8000_192000;
+		dai->capture.formats = formats;
 	}
+
+	if (i2s_tdm->clk_trcm != TRCM_TXRX)
+		dai->symmetric_rate = 1;
+
+	i2s_tdm->dai = dai;
+
+	return 0;
 }
 
 static int rockchip_i2s_tdm_path_check(struct rk_i2s_tdm_dev *i2s_tdm,
@@ -1541,8 +1551,6 @@ static int rockchip_i2s_tdm_probe(struct platform_device *pdev)
 	spin_lock_init(&i2s_tdm->lock);
 	i2s_tdm->soc_data = (struct rk_i2s_soc_data *)of_id->data;
 
-	rockchip_i2s_tdm_init_dai(i2s_tdm);
-
 	i2s_tdm->frame_width = 64;
 
 	i2s_tdm->clk_trcm = TRCM_TXRX;
@@ -1555,8 +1563,10 @@ static int rockchip_i2s_tdm_probe(struct platform_device *pdev)
 		}
 		i2s_tdm->clk_trcm = TRCM_RX;
 	}
-	if (i2s_tdm->clk_trcm != TRCM_TXRX)
-		i2s_tdm_dai.symmetric_rate = 1;
+
+	ret = rockchip_i2s_tdm_init_dai(i2s_tdm);
+	if (ret)
+		return ret;
 
 	i2s_tdm->grf = syscon_regmap_lookup_by_phandle(node, "rockchip,grf");
 	if (IS_ERR(i2s_tdm->grf))
@@ -1678,7 +1688,7 @@ static int rockchip_i2s_tdm_probe(struct platform_device *pdev)
 
 	ret = devm_snd_soc_register_component(&pdev->dev,
 					      &rockchip_i2s_tdm_component,
-					      &i2s_tdm_dai, 1);
+					      i2s_tdm->dai, 1);
 
 	if (ret) {
 		dev_err(&pdev->dev, "Could not register DAI\n");
diff --git a/sound/soc/sh/rcar/dma.c b/sound/soc/sh/rcar/dma.c
index 16c6e0265749..03e0d4eca781 100644
--- a/sound/soc/sh/rcar/dma.c
+++ b/sound/soc/sh/rcar/dma.c
@@ -102,7 +102,7 @@ static int rsnd_dmaen_stop(struct rsnd_mod *mod,
 	struct rsnd_dmaen *dmaen = rsnd_dma_to_dmaen(dma);
 
 	if (dmaen->chan)
-		dmaengine_terminate_sync(dmaen->chan);
+		dmaengine_terminate_async(dmaen->chan);
 
 	return 0;
 }
diff --git a/sound/soc/soc-acpi.c b/sound/soc/soc-acpi.c
index 2ae99b49d3f5..cbd7ea48837b 100644
--- a/sound/soc/soc-acpi.c
+++ b/sound/soc/soc-acpi.c
@@ -20,8 +20,10 @@ static bool snd_soc_acpi_id_present(struct snd_soc_acpi_mach *machine)
 
 	if (comp_ids) {
 		for (i = 0; i < comp_ids->num_codecs; i++) {
-			if (acpi_dev_present(comp_ids->codecs[i], NULL, -1))
+			if (acpi_dev_present(comp_ids->codecs[i], NULL, -1)) {
+				strscpy(machine->id, comp_ids->codecs[i], ACPI_ID_LEN);
 				return true;
+			}
 		}
 	}
 
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index 2892b0aba151..b06c5682445c 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -2559,8 +2559,13 @@ static struct snd_soc_dapm_widget *dapm_find_widget(
 	return NULL;
 }
 
-static int snd_soc_dapm_set_pin(struct snd_soc_dapm_context *dapm,
-				const char *pin, int status)
+/*
+ * set the DAPM pin status:
+ * returns 1 when the value has been updated, 0 when unchanged, or a negative
+ * error code; called from kcontrol put callback
+ */
+static int __snd_soc_dapm_set_pin(struct snd_soc_dapm_context *dapm,
+				  const char *pin, int status)
 {
 	struct snd_soc_dapm_widget *w = dapm_find_widget(dapm, pin, true);
 	int ret = 0;
@@ -2586,6 +2591,18 @@ static int snd_soc_dapm_set_pin(struct snd_soc_dapm_context *dapm,
 	return ret;
 }
 
+/*
+ * similar as __snd_soc_dapm_set_pin(), but returns 0 when successful;
+ * called from several API functions below
+ */
+static int snd_soc_dapm_set_pin(struct snd_soc_dapm_context *dapm,
+				const char *pin, int status)
+{
+	int ret = __snd_soc_dapm_set_pin(dapm, pin, status);
+
+	return ret < 0 ? ret : 0;
+}
+
 /**
  * snd_soc_dapm_sync_unlocked - scan and power dapm paths
  * @dapm: DAPM context
@@ -3589,10 +3606,10 @@ int snd_soc_dapm_put_pin_switch(struct snd_kcontrol *kcontrol,
 	const char *pin = (const char *)kcontrol->private_value;
 	int ret;
 
-	if (ucontrol->value.integer.value[0])
-		ret = snd_soc_dapm_enable_pin(&card->dapm, pin);
-	else
-		ret = snd_soc_dapm_disable_pin(&card->dapm, pin);
+	mutex_lock_nested(&card->dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME);
+	ret = __snd_soc_dapm_set_pin(&card->dapm, pin,
+				     !!ucontrol->value.integer.value[0]);
+	mutex_unlock(&card->dapm_mutex);
 
 	snd_soc_dapm_sync(&card->dapm);
 	return ret;
diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c
index 557e22c5254c..f5b9e66ac3b8 100644
--- a/sound/soc/soc-topology.c
+++ b/sound/soc/soc-topology.c
@@ -2700,6 +2700,7 @@ EXPORT_SYMBOL_GPL(snd_soc_tplg_component_load);
 /* remove dynamic controls from the component driver */
 int snd_soc_tplg_component_remove(struct snd_soc_component *comp)
 {
+	struct snd_card *card = comp->card->snd_card;
 	struct snd_soc_dobj *dobj, *next_dobj;
 	int pass = SOC_TPLG_PASS_END;
 
@@ -2707,6 +2708,7 @@ int snd_soc_tplg_component_remove(struct snd_soc_component *comp)
 	while (pass >= SOC_TPLG_PASS_START) {
 
 		/* remove mixer controls */
+		down_write(&card->controls_rwsem);
 		list_for_each_entry_safe(dobj, next_dobj, &comp->dobj_list,
 			list) {
 
@@ -2745,6 +2747,7 @@ int snd_soc_tplg_component_remove(struct snd_soc_component *comp)
 				break;
 			}
 		}
+		up_write(&card->controls_rwsem);
 		pass--;
 	}
 
diff --git a/sound/soc/sof/Kconfig b/sound/soc/sof/Kconfig
index 6bb4db87af03..041c54639c4d 100644
--- a/sound/soc/sof/Kconfig
+++ b/sound/soc/sof/Kconfig
@@ -47,7 +47,7 @@ config SND_SOC_SOF_OF
 	  Say Y if you need this option. If unsure select "N".
 
 config SND_SOC_SOF_COMPRESS
-	tristate
+	bool
 	select SND_SOC_COMPRESS
 
 config SND_SOC_SOF_DEBUG_PROBES
diff --git a/sound/soc/sof/control.c b/sound/soc/sof/control.c
index 58bb89af4de1..bb1dfe4f6d40 100644
--- a/sound/soc/sof/control.c
+++ b/sound/soc/sof/control.c
@@ -69,7 +69,7 @@ static void snd_sof_refresh_control(struct snd_sof_control *scontrol)
 {
 	struct sof_ipc_ctrl_data *cdata = scontrol->control_data;
 	struct snd_soc_component *scomp = scontrol->scomp;
-	enum sof_ipc_ctrl_type ctrl_type;
+	u32 ipc_cmd;
 	int ret;
 
 	if (!scontrol->comp_data_dirty)
@@ -79,9 +79,9 @@ static void snd_sof_refresh_control(struct snd_sof_control *scontrol)
 		return;
 
 	if (scontrol->cmd == SOF_CTRL_CMD_BINARY)
-		ctrl_type = SOF_IPC_COMP_GET_DATA;
+		ipc_cmd = SOF_IPC_COMP_GET_DATA;
 	else
-		ctrl_type = SOF_IPC_COMP_GET_VALUE;
+		ipc_cmd = SOF_IPC_COMP_GET_VALUE;
 
 	/* set the ABI header values */
 	cdata->data->magic = SOF_ABI_MAGIC;
@@ -89,7 +89,7 @@ static void snd_sof_refresh_control(struct snd_sof_control *scontrol)
 
 	/* refresh the component data from DSP */
 	scontrol->comp_data_dirty = false;
-	ret = snd_sof_ipc_set_get_comp_data(scontrol, ctrl_type,
+	ret = snd_sof_ipc_set_get_comp_data(scontrol, ipc_cmd,
 					    SOF_CTRL_TYPE_VALUE_CHAN_GET,
 					    scontrol->cmd, false);
 	if (ret < 0) {
diff --git a/sound/soc/sof/intel/hda-bus.c b/sound/soc/sof/intel/hda-bus.c
index 30025d3c16b6..0862ff8b6627 100644
--- a/sound/soc/sof/intel/hda-bus.c
+++ b/sound/soc/sof/intel/hda-bus.c
@@ -10,6 +10,8 @@
 #include <linux/io.h>
 #include <sound/hdaudio.h>
 #include <sound/hda_i915.h>
+#include <sound/hda_codec.h>
+#include <sound/hda_register.h>
 #include "../sof-priv.h"
 #include "hda.h"
 
@@ -21,6 +23,18 @@
 #endif
 
 #if IS_ENABLED(CONFIG_SND_SOC_SOF_HDA)
+static void update_codec_wake_enable(struct hdac_bus *bus, unsigned int addr, bool link_power)
+{
+	unsigned int mask = snd_hdac_chip_readw(bus, WAKEEN);
+
+	if (link_power)
+		mask &= ~BIT(addr);
+	else
+		mask |= BIT(addr);
+
+	snd_hdac_chip_updatew(bus, WAKEEN, STATESTS_INT_MASK, mask);
+}
+
 static void sof_hda_bus_link_power(struct hdac_device *codec, bool enable)
 {
 	struct hdac_bus *bus = codec->bus;
@@ -41,6 +55,9 @@ static void sof_hda_bus_link_power(struct hdac_device *codec, bool enable)
 	 */
 	if (codec->addr == HDA_IDISP_ADDR && !enable)
 		snd_hdac_display_power(bus, HDA_CODEC_IDX_CONTROLLER, false);
+
+	/* WAKEEN needs to be set for disabled links */
+	update_codec_wake_enable(bus, codec->addr, enable);
 }
 
 static const struct hdac_bus_ops bus_core_ops = {
diff --git a/sound/soc/sof/intel/hda-codec.c b/sound/soc/sof/intel/hda-codec.c
index 6744318de612..13cd96e6724a 100644
--- a/sound/soc/sof/intel/hda-codec.c
+++ b/sound/soc/sof/intel/hda-codec.c
@@ -22,6 +22,7 @@
 
 #if IS_ENABLED(CONFIG_SND_SOC_SOF_HDA_AUDIO_CODEC)
 #define IDISP_VID_INTEL	0x80860000
+#define CODEC_PROBE_RETRIES 3
 
 /* load the legacy HDA codec driver */
 static int request_codec_module(struct hda_codec *codec)
@@ -121,12 +122,15 @@ static int hda_codec_probe(struct snd_sof_dev *sdev, int address,
 	u32 hda_cmd = (address << 28) | (AC_NODE_ROOT << 20) |
 		(AC_VERB_PARAMETERS << 8) | AC_PAR_VENDOR_ID;
 	u32 resp = -1;
-	int ret;
+	int ret, retry = 0;
+
+	do {
+		mutex_lock(&hbus->core.cmd_mutex);
+		snd_hdac_bus_send_cmd(&hbus->core, hda_cmd);
+		snd_hdac_bus_get_response(&hbus->core, address, &resp);
+		mutex_unlock(&hbus->core.cmd_mutex);
+	} while (resp == -1 && retry++ < CODEC_PROBE_RETRIES);
 
-	mutex_lock(&hbus->core.cmd_mutex);
-	snd_hdac_bus_send_cmd(&hbus->core, hda_cmd);
-	snd_hdac_bus_get_response(&hbus->core, address, &resp);
-	mutex_unlock(&hbus->core.cmd_mutex);
 	if (resp == -1)
 		return -EIO;
 	dev_dbg(sdev->dev, "HDA codec #%d probed OK: response: %x\n",
diff --git a/sound/soc/sof/intel/hda-dsp.c b/sound/soc/sof/intel/hda-dsp.c
index 058baca2cd0e..287dc0eb6686 100644
--- a/sound/soc/sof/intel/hda-dsp.c
+++ b/sound/soc/sof/intel/hda-dsp.c
@@ -622,8 +622,7 @@ static int hda_suspend(struct snd_sof_dev *sdev, bool runtime_suspend)
 	hda_dsp_ipc_int_disable(sdev);
 
 #if IS_ENABLED(CONFIG_SND_SOC_SOF_HDA)
-	if (runtime_suspend)
-		hda_codec_jack_wake_enable(sdev, true);
+	hda_codec_jack_wake_enable(sdev, runtime_suspend);
 
 	/* power down all hda link */
 	snd_hdac_ext_bus_link_power_down_all(bus);
diff --git a/sound/soc/sof/intel/hda.c b/sound/soc/sof/intel/hda.c
index 883d78dd01b5..2c0d4d06ab36 100644
--- a/sound/soc/sof/intel/hda.c
+++ b/sound/soc/sof/intel/hda.c
@@ -58,6 +58,13 @@ int hda_ctrl_dai_widget_setup(struct snd_soc_dapm_widget *w)
 		return -EINVAL;
 	}
 
+	/* DAI already configured, reset it before reconfiguring it */
+	if (sof_dai->configured) {
+		ret = hda_ctrl_dai_widget_free(w);
+		if (ret < 0)
+			return ret;
+	}
+
 	config = &sof_dai->dai_config[sof_dai->current_config];
 
 	/*
@@ -810,6 +817,20 @@ skip_soundwire:
 	return 0;
 }
 
+static void hda_check_for_state_change(struct snd_sof_dev *sdev)
+{
+#if IS_ENABLED(CONFIG_SND_SOC_SOF_HDA)
+	struct hdac_bus *bus = sof_to_bus(sdev);
+	unsigned int codec_mask;
+
+	codec_mask = snd_hdac_chip_readw(bus, STATESTS);
+	if (codec_mask) {
+		hda_codec_jack_check(sdev);
+		snd_hdac_chip_writew(bus, STATESTS, codec_mask);
+	}
+#endif
+}
+
 static irqreturn_t hda_dsp_interrupt_handler(int irq, void *context)
 {
 	struct snd_sof_dev *sdev = context;
@@ -851,6 +872,8 @@ static irqreturn_t hda_dsp_interrupt_thread(int irq, void *context)
 	if (hda_sdw_check_wakeen_irq(sdev))
 		hda_sdw_process_wakeen(sdev);
 
+	hda_check_for_state_change(sdev);
+
 	/* enable GIE interrupt */
 	snd_sof_dsp_update_bits(sdev, HDA_DSP_HDA_BAR,
 				SOF_HDA_INTCTL,
diff --git a/sound/soc/sof/intel/pci-tgl.c b/sound/soc/sof/intel/pci-tgl.c
index f2ea34df9741..fd46210f1730 100644
--- a/sound/soc/sof/intel/pci-tgl.c
+++ b/sound/soc/sof/intel/pci-tgl.c
@@ -112,8 +112,12 @@ static const struct pci_device_id sof_pci_ids[] = {
 		.driver_data = (unsigned long)&adls_desc},
 	{ PCI_DEVICE(0x8086, 0x51c8), /* ADL-P */
 		.driver_data = (unsigned long)&adl_desc},
+	{ PCI_DEVICE(0x8086, 0x51cd), /* ADL-P */
+		.driver_data = (unsigned long)&adl_desc},
 	{ PCI_DEVICE(0x8086, 0x51cc), /* ADL-M */
 		.driver_data = (unsigned long)&adl_desc},
+	{ PCI_DEVICE(0x8086, 0x54c8), /* ADL-N */
+		.driver_data = (unsigned long)&adl_desc},
 	{ 0, }
 };
 MODULE_DEVICE_TABLE(pci, sof_pci_ids);
diff --git a/sound/soc/stm/stm32_i2s.c b/sound/soc/stm/stm32_i2s.c
index 6254bacad6eb..717f45a83445 100644
--- a/sound/soc/stm/stm32_i2s.c
+++ b/sound/soc/stm/stm32_i2s.c
@@ -700,7 +700,7 @@ static int stm32_i2s_configure_clock(struct snd_soc_dai *cpu_dai,
 		if (ret < 0)
 			return ret;
 
-		nb_bits = frame_len * ((cgfr & I2S_CGFR_CHLEN) + 1);
+		nb_bits = frame_len * (FIELD_GET(I2S_CGFR_CHLEN, cgfr) + 1);
 		ret = stm32_i2s_calc_clk_div(i2s, i2s_clock_rate,
 					     (nb_bits * rate));
 		if (ret)
diff --git a/sound/soc/tegra/tegra186_dspk.c b/sound/soc/tegra/tegra186_dspk.c
index 8ee9a77bd83d..a74c980ee775 100644
--- a/sound/soc/tegra/tegra186_dspk.c
+++ b/sound/soc/tegra/tegra186_dspk.c
@@ -26,51 +26,162 @@ static const struct reg_default tegra186_dspk_reg_defaults[] = {
 	{ TEGRA186_DSPK_CODEC_CTRL,  0x03000000 },
 };
 
-static int tegra186_dspk_get_control(struct snd_kcontrol *kcontrol,
+static int tegra186_dspk_get_fifo_th(struct snd_kcontrol *kcontrol,
 				     struct snd_ctl_elem_value *ucontrol)
 {
 	struct snd_soc_component *codec = snd_soc_kcontrol_component(kcontrol);
 	struct tegra186_dspk *dspk = snd_soc_component_get_drvdata(codec);
 
-	if (strstr(kcontrol->id.name, "FIFO Threshold"))
-		ucontrol->value.integer.value[0] = dspk->rx_fifo_th;
-	else if (strstr(kcontrol->id.name, "OSR Value"))
-		ucontrol->value.integer.value[0] = dspk->osr_val;
-	else if (strstr(kcontrol->id.name, "LR Polarity Select"))
-		ucontrol->value.integer.value[0] = dspk->lrsel;
-	else if (strstr(kcontrol->id.name, "Channel Select"))
-		ucontrol->value.integer.value[0] = dspk->ch_sel;
-	else if (strstr(kcontrol->id.name, "Mono To Stereo"))
-		ucontrol->value.integer.value[0] = dspk->mono_to_stereo;
-	else if (strstr(kcontrol->id.name, "Stereo To Mono"))
-		ucontrol->value.integer.value[0] = dspk->stereo_to_mono;
+	ucontrol->value.integer.value[0] = dspk->rx_fifo_th;
 
 	return 0;
 }
 
-static int tegra186_dspk_put_control(struct snd_kcontrol *kcontrol,
+static int tegra186_dspk_put_fifo_th(struct snd_kcontrol *kcontrol,
 				     struct snd_ctl_elem_value *ucontrol)
 {
 	struct snd_soc_component *codec = snd_soc_kcontrol_component(kcontrol);
 	struct tegra186_dspk *dspk = snd_soc_component_get_drvdata(codec);
-	int val = ucontrol->value.integer.value[0];
-
-	if (strstr(kcontrol->id.name, "FIFO Threshold"))
-		dspk->rx_fifo_th = val;
-	else if (strstr(kcontrol->id.name, "OSR Value"))
-		dspk->osr_val = val;
-	else if (strstr(kcontrol->id.name, "LR Polarity Select"))
-		dspk->lrsel = val;
-	else if (strstr(kcontrol->id.name, "Channel Select"))
-		dspk->ch_sel = val;
-	else if (strstr(kcontrol->id.name, "Mono To Stereo"))
-		dspk->mono_to_stereo = val;
-	else if (strstr(kcontrol->id.name, "Stereo To Mono"))
-		dspk->stereo_to_mono = val;
+	int value = ucontrol->value.integer.value[0];
+
+	if (value == dspk->rx_fifo_th)
+		return 0;
+
+	dspk->rx_fifo_th = value;
+
+	return 1;
+}
+
+static int tegra186_dspk_get_osr_val(struct snd_kcontrol *kcontrol,
+				     struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *codec = snd_soc_kcontrol_component(kcontrol);
+	struct tegra186_dspk *dspk = snd_soc_component_get_drvdata(codec);
+
+	ucontrol->value.enumerated.item[0] = dspk->osr_val;
 
 	return 0;
 }
 
+static int tegra186_dspk_put_osr_val(struct snd_kcontrol *kcontrol,
+				     struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *codec = snd_soc_kcontrol_component(kcontrol);
+	struct tegra186_dspk *dspk = snd_soc_component_get_drvdata(codec);
+	unsigned int value = ucontrol->value.enumerated.item[0];
+
+	if (value == dspk->osr_val)
+		return 0;
+
+	dspk->osr_val = value;
+
+	return 1;
+}
+
+static int tegra186_dspk_get_pol_sel(struct snd_kcontrol *kcontrol,
+				     struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *codec = snd_soc_kcontrol_component(kcontrol);
+	struct tegra186_dspk *dspk = snd_soc_component_get_drvdata(codec);
+
+	ucontrol->value.enumerated.item[0] = dspk->lrsel;
+
+	return 0;
+}
+
+static int tegra186_dspk_put_pol_sel(struct snd_kcontrol *kcontrol,
+				     struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *codec = snd_soc_kcontrol_component(kcontrol);
+	struct tegra186_dspk *dspk = snd_soc_component_get_drvdata(codec);
+	unsigned int value = ucontrol->value.enumerated.item[0];
+
+	if (value == dspk->lrsel)
+		return 0;
+
+	dspk->lrsel = value;
+
+	return 1;
+}
+
+static int tegra186_dspk_get_ch_sel(struct snd_kcontrol *kcontrol,
+				    struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *codec = snd_soc_kcontrol_component(kcontrol);
+	struct tegra186_dspk *dspk = snd_soc_component_get_drvdata(codec);
+
+	ucontrol->value.enumerated.item[0] = dspk->ch_sel;
+
+	return 0;
+}
+
+static int tegra186_dspk_put_ch_sel(struct snd_kcontrol *kcontrol,
+				    struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *codec = snd_soc_kcontrol_component(kcontrol);
+	struct tegra186_dspk *dspk = snd_soc_component_get_drvdata(codec);
+	unsigned int value = ucontrol->value.enumerated.item[0];
+
+	if (value == dspk->ch_sel)
+		return 0;
+
+	dspk->ch_sel = value;
+
+	return 1;
+}
+
+static int tegra186_dspk_get_mono_to_stereo(struct snd_kcontrol *kcontrol,
+					    struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *codec = snd_soc_kcontrol_component(kcontrol);
+	struct tegra186_dspk *dspk = snd_soc_component_get_drvdata(codec);
+
+	ucontrol->value.enumerated.item[0] = dspk->mono_to_stereo;
+
+	return 0;
+}
+
+static int tegra186_dspk_put_mono_to_stereo(struct snd_kcontrol *kcontrol,
+					    struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *codec = snd_soc_kcontrol_component(kcontrol);
+	struct tegra186_dspk *dspk = snd_soc_component_get_drvdata(codec);
+	unsigned int value = ucontrol->value.enumerated.item[0];
+
+	if (value == dspk->mono_to_stereo)
+		return 0;
+
+	dspk->mono_to_stereo = value;
+
+	return 1;
+}
+
+static int tegra186_dspk_get_stereo_to_mono(struct snd_kcontrol *kcontrol,
+					    struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *codec = snd_soc_kcontrol_component(kcontrol);
+	struct tegra186_dspk *dspk = snd_soc_component_get_drvdata(codec);
+
+	ucontrol->value.enumerated.item[0] = dspk->stereo_to_mono;
+
+	return 0;
+}
+
+static int tegra186_dspk_put_stereo_to_mono(struct snd_kcontrol *kcontrol,
+					    struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *codec = snd_soc_kcontrol_component(kcontrol);
+	struct tegra186_dspk *dspk = snd_soc_component_get_drvdata(codec);
+	unsigned int value = ucontrol->value.enumerated.item[0];
+
+	if (value == dspk->stereo_to_mono)
+		return 0;
+
+	dspk->stereo_to_mono = value;
+
+	return 1;
+}
+
 static int __maybe_unused tegra186_dspk_runtime_suspend(struct device *dev)
 {
 	struct tegra186_dspk *dspk = dev_get_drvdata(dev);
@@ -279,17 +390,19 @@ static const struct soc_enum tegra186_dspk_lrsel_enum =
 static const struct snd_kcontrol_new tegrat186_dspk_controls[] = {
 	SOC_SINGLE_EXT("FIFO Threshold", SND_SOC_NOPM, 0,
 		       TEGRA186_DSPK_RX_FIFO_DEPTH - 1, 0,
-		       tegra186_dspk_get_control, tegra186_dspk_put_control),
+		       tegra186_dspk_get_fifo_th, tegra186_dspk_put_fifo_th),
 	SOC_ENUM_EXT("OSR Value", tegra186_dspk_osr_enum,
-		     tegra186_dspk_get_control, tegra186_dspk_put_control),
+		     tegra186_dspk_get_osr_val, tegra186_dspk_put_osr_val),
 	SOC_ENUM_EXT("LR Polarity Select", tegra186_dspk_lrsel_enum,
-		     tegra186_dspk_get_control, tegra186_dspk_put_control),
+		     tegra186_dspk_get_pol_sel, tegra186_dspk_put_pol_sel),
 	SOC_ENUM_EXT("Channel Select", tegra186_dspk_ch_sel_enum,
-		     tegra186_dspk_get_control, tegra186_dspk_put_control),
+		     tegra186_dspk_get_ch_sel, tegra186_dspk_put_ch_sel),
 	SOC_ENUM_EXT("Mono To Stereo", tegra186_dspk_mono_conv_enum,
-		     tegra186_dspk_get_control, tegra186_dspk_put_control),
+		     tegra186_dspk_get_mono_to_stereo,
+		     tegra186_dspk_put_mono_to_stereo),
 	SOC_ENUM_EXT("Stereo To Mono", tegra186_dspk_stereo_conv_enum,
-		     tegra186_dspk_get_control, tegra186_dspk_put_control),
+		     tegra186_dspk_get_stereo_to_mono,
+		     tegra186_dspk_put_stereo_to_mono),
 };
 
 static const struct snd_soc_component_driver tegra186_dspk_cmpnt = {
diff --git a/sound/soc/tegra/tegra210_admaif.c b/sound/soc/tegra/tegra210_admaif.c
index bcccdf3ddc52..1a2e868a6220 100644
--- a/sound/soc/tegra/tegra210_admaif.c
+++ b/sound/soc/tegra/tegra210_admaif.c
@@ -424,46 +424,122 @@ static const struct snd_soc_dai_ops tegra_admaif_dai_ops = {
 	.trigger	= tegra_admaif_trigger,
 };
 
-static int tegra_admaif_get_control(struct snd_kcontrol *kcontrol,
-				    struct snd_ctl_elem_value *ucontrol)
+static int tegra210_admaif_pget_mono_to_stereo(struct snd_kcontrol *kcontrol,
+	struct snd_ctl_elem_value *ucontrol)
 {
 	struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol);
+	struct tegra_admaif *admaif = snd_soc_component_get_drvdata(cmpnt);
+	struct soc_enum *ec = (struct soc_enum *)kcontrol->private_value;
+
+	ucontrol->value.enumerated.item[0] =
+		admaif->mono_to_stereo[ADMAIF_TX_PATH][ec->reg];
+
+	return 0;
+}
+
+static int tegra210_admaif_pput_mono_to_stereo(struct snd_kcontrol *kcontrol,
+	struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol);
+	struct tegra_admaif *admaif = snd_soc_component_get_drvdata(cmpnt);
+	struct soc_enum *ec = (struct soc_enum *)kcontrol->private_value;
+	unsigned int value = ucontrol->value.enumerated.item[0];
+
+	if (value == admaif->mono_to_stereo[ADMAIF_TX_PATH][ec->reg])
+		return 0;
+
+	admaif->mono_to_stereo[ADMAIF_TX_PATH][ec->reg] = value;
+
+	return 1;
+}
+
+static int tegra210_admaif_cget_mono_to_stereo(struct snd_kcontrol *kcontrol,
+	struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol);
+	struct tegra_admaif *admaif = snd_soc_component_get_drvdata(cmpnt);
+	struct soc_enum *ec = (struct soc_enum *)kcontrol->private_value;
+
+	ucontrol->value.enumerated.item[0] =
+		admaif->mono_to_stereo[ADMAIF_RX_PATH][ec->reg];
+
+	return 0;
+}
+
+static int tegra210_admaif_cput_mono_to_stereo(struct snd_kcontrol *kcontrol,
+	struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol);
+	struct tegra_admaif *admaif = snd_soc_component_get_drvdata(cmpnt);
 	struct soc_enum *ec = (struct soc_enum *)kcontrol->private_value;
+	unsigned int value = ucontrol->value.enumerated.item[0];
+
+	if (value == admaif->mono_to_stereo[ADMAIF_RX_PATH][ec->reg])
+		return 0;
+
+	admaif->mono_to_stereo[ADMAIF_RX_PATH][ec->reg] = value;
+
+	return 1;
+}
+
+static int tegra210_admaif_pget_stereo_to_mono(struct snd_kcontrol *kcontrol,
+	struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol);
 	struct tegra_admaif *admaif = snd_soc_component_get_drvdata(cmpnt);
-	long *uctl_val = &ucontrol->value.integer.value[0];
+	struct soc_enum *ec = (struct soc_enum *)kcontrol->private_value;
 
-	if (strstr(kcontrol->id.name, "Playback Mono To Stereo"))
-		*uctl_val = admaif->mono_to_stereo[ADMAIF_TX_PATH][ec->reg];
-	else if (strstr(kcontrol->id.name, "Capture Mono To Stereo"))
-		*uctl_val = admaif->mono_to_stereo[ADMAIF_RX_PATH][ec->reg];
-	else if (strstr(kcontrol->id.name, "Playback Stereo To Mono"))
-		*uctl_val = admaif->stereo_to_mono[ADMAIF_TX_PATH][ec->reg];
-	else if (strstr(kcontrol->id.name, "Capture Stereo To Mono"))
-		*uctl_val = admaif->stereo_to_mono[ADMAIF_RX_PATH][ec->reg];
+	ucontrol->value.enumerated.item[0] =
+		admaif->stereo_to_mono[ADMAIF_TX_PATH][ec->reg];
 
 	return 0;
 }
 
-static int tegra_admaif_put_control(struct snd_kcontrol *kcontrol,
-				    struct snd_ctl_elem_value *ucontrol)
+static int tegra210_admaif_pput_stereo_to_mono(struct snd_kcontrol *kcontrol,
+	struct snd_ctl_elem_value *ucontrol)
 {
 	struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol);
+	struct tegra_admaif *admaif = snd_soc_component_get_drvdata(cmpnt);
 	struct soc_enum *ec = (struct soc_enum *)kcontrol->private_value;
+	unsigned int value = ucontrol->value.enumerated.item[0];
+
+	if (value == admaif->stereo_to_mono[ADMAIF_TX_PATH][ec->reg])
+		return 0;
+
+	admaif->stereo_to_mono[ADMAIF_TX_PATH][ec->reg] = value;
+
+	return 1;
+}
+
+static int tegra210_admaif_cget_stereo_to_mono(struct snd_kcontrol *kcontrol,
+	struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol);
 	struct tegra_admaif *admaif = snd_soc_component_get_drvdata(cmpnt);
-	int value = ucontrol->value.integer.value[0];
+	struct soc_enum *ec = (struct soc_enum *)kcontrol->private_value;
 
-	if (strstr(kcontrol->id.name, "Playback Mono To Stereo"))
-		admaif->mono_to_stereo[ADMAIF_TX_PATH][ec->reg] = value;
-	else if (strstr(kcontrol->id.name, "Capture Mono To Stereo"))
-		admaif->mono_to_stereo[ADMAIF_RX_PATH][ec->reg] = value;
-	else if (strstr(kcontrol->id.name, "Playback Stereo To Mono"))
-		admaif->stereo_to_mono[ADMAIF_TX_PATH][ec->reg] = value;
-	else if (strstr(kcontrol->id.name, "Capture Stereo To Mono"))
-		admaif->stereo_to_mono[ADMAIF_RX_PATH][ec->reg] = value;
+	ucontrol->value.enumerated.item[0] =
+		admaif->stereo_to_mono[ADMAIF_RX_PATH][ec->reg];
 
 	return 0;
 }
 
+static int tegra210_admaif_cput_stereo_to_mono(struct snd_kcontrol *kcontrol,
+	struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol);
+	struct tegra_admaif *admaif = snd_soc_component_get_drvdata(cmpnt);
+	struct soc_enum *ec = (struct soc_enum *)kcontrol->private_value;
+	unsigned int value = ucontrol->value.enumerated.item[0];
+
+	if (value == admaif->stereo_to_mono[ADMAIF_RX_PATH][ec->reg])
+		return 0;
+
+	admaif->stereo_to_mono[ADMAIF_RX_PATH][ec->reg] = value;
+
+	return 1;
+}
+
 static int tegra_admaif_dai_probe(struct snd_soc_dai *dai)
 {
 	struct tegra_admaif *admaif = snd_soc_dai_get_drvdata(dai);
@@ -559,17 +635,21 @@ static const char * const tegra_admaif_mono_conv_text[] = {
 }
 
 #define TEGRA_ADMAIF_CIF_CTRL(reg)					       \
-	NV_SOC_ENUM_EXT("ADMAIF" #reg " Playback Mono To Stereo", reg - 1,\
-			tegra_admaif_get_control, tegra_admaif_put_control,    \
+	NV_SOC_ENUM_EXT("ADMAIF" #reg " Playback Mono To Stereo", reg - 1,     \
+			tegra210_admaif_pget_mono_to_stereo,		       \
+			tegra210_admaif_pput_mono_to_stereo,		       \
 			tegra_admaif_mono_conv_text),			       \
-	NV_SOC_ENUM_EXT("ADMAIF" #reg " Playback Stereo To Mono", reg - 1,\
-			tegra_admaif_get_control, tegra_admaif_put_control,    \
+	NV_SOC_ENUM_EXT("ADMAIF" #reg " Playback Stereo To Mono", reg - 1,     \
+			tegra210_admaif_pget_stereo_to_mono,		       \
+			tegra210_admaif_pput_stereo_to_mono,		       \
 			tegra_admaif_stereo_conv_text),			       \
-	NV_SOC_ENUM_EXT("ADMAIF" #reg " Capture Mono To Stereo", reg - 1, \
-			tegra_admaif_get_control, tegra_admaif_put_control,    \
+	NV_SOC_ENUM_EXT("ADMAIF" #reg " Capture Mono To Stereo", reg - 1,      \
+			tegra210_admaif_cget_mono_to_stereo,		       \
+			tegra210_admaif_cput_mono_to_stereo,		       \
 			tegra_admaif_mono_conv_text),			       \
-	NV_SOC_ENUM_EXT("ADMAIF" #reg " Capture Stereo To Mono", reg - 1, \
-			tegra_admaif_get_control, tegra_admaif_put_control,    \
+	NV_SOC_ENUM_EXT("ADMAIF" #reg " Capture Stereo To Mono", reg - 1,      \
+			tegra210_admaif_cget_stereo_to_mono,		       \
+			tegra210_admaif_cput_stereo_to_mono,		       \
 			tegra_admaif_stereo_conv_text)
 
 static struct snd_kcontrol_new tegra210_admaif_controls[] = {
diff --git a/sound/soc/tegra/tegra210_adx.c b/sound/soc/tegra/tegra210_adx.c
index d7c7849c2f92..3785cade2d9a 100644
--- a/sound/soc/tegra/tegra210_adx.c
+++ b/sound/soc/tegra/tegra210_adx.c
@@ -193,6 +193,9 @@ static int tegra210_adx_put_byte_map(struct snd_kcontrol *kcontrol,
 	struct soc_mixer_control *mc =
 		(struct soc_mixer_control *)kcontrol->private_value;;
 
+	if (value == bytes_map[mc->reg])
+		return 0;
+
 	if (value >= 0 && value <= 255) {
 		/* update byte map and enable slot */
 		bytes_map[mc->reg] = value;
@@ -511,8 +514,8 @@ static int tegra210_adx_platform_remove(struct platform_device *pdev)
 static const struct dev_pm_ops tegra210_adx_pm_ops = {
 	SET_RUNTIME_PM_OPS(tegra210_adx_runtime_suspend,
 			   tegra210_adx_runtime_resume, NULL)
-	SET_LATE_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
-				     pm_runtime_force_resume)
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
 };
 
 static struct platform_driver tegra210_adx_driver = {
diff --git a/sound/soc/tegra/tegra210_ahub.c b/sound/soc/tegra/tegra210_ahub.c
index a1989eae2b52..388b815443c7 100644
--- a/sound/soc/tegra/tegra210_ahub.c
+++ b/sound/soc/tegra/tegra210_ahub.c
@@ -62,6 +62,7 @@ static int tegra_ahub_put_value_enum(struct snd_kcontrol *kctl,
 	unsigned int *item = uctl->value.enumerated.item;
 	unsigned int value = e->values[item[0]];
 	unsigned int i, bit_pos, reg_idx = 0, reg_val = 0;
+	int change = 0;
 
 	if (item[0] >= e->items)
 		return -EINVAL;
@@ -86,12 +87,14 @@ static int tegra_ahub_put_value_enum(struct snd_kcontrol *kctl,
 
 		/* Update widget power if state has changed */
 		if (snd_soc_component_test_bits(cmpnt, update[i].reg,
-						update[i].mask, update[i].val))
-			snd_soc_dapm_mux_update_power(dapm, kctl, item[0], e,
-						      &update[i]);
+						update[i].mask,
+						update[i].val))
+			change |= snd_soc_dapm_mux_update_power(dapm, kctl,
+								item[0], e,
+								&update[i]);
 	}
 
-	return 0;
+	return change;
 }
 
 static struct snd_soc_dai_driver tegra210_ahub_dais[] = {
diff --git a/sound/soc/tegra/tegra210_amx.c b/sound/soc/tegra/tegra210_amx.c
index af9bddfc3120..d064cc67fea6 100644
--- a/sound/soc/tegra/tegra210_amx.c
+++ b/sound/soc/tegra/tegra210_amx.c
@@ -222,6 +222,9 @@ static int tegra210_amx_put_byte_map(struct snd_kcontrol *kcontrol,
 	int reg = mc->reg;
 	int value = ucontrol->value.integer.value[0];
 
+	if (value == bytes_map[reg])
+		return 0;
+
 	if (value >= 0 && value <= 255) {
 		/* Update byte map and enable slot */
 		bytes_map[reg] = value;
@@ -580,8 +583,8 @@ static int tegra210_amx_platform_remove(struct platform_device *pdev)
 static const struct dev_pm_ops tegra210_amx_pm_ops = {
 	SET_RUNTIME_PM_OPS(tegra210_amx_runtime_suspend,
 			   tegra210_amx_runtime_resume, NULL)
-	SET_LATE_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
-				     pm_runtime_force_resume)
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
 };
 
 static struct platform_driver tegra210_amx_driver = {
diff --git a/sound/soc/tegra/tegra210_dmic.c b/sound/soc/tegra/tegra210_dmic.c
index b096478cd2ef..db95794530f4 100644
--- a/sound/soc/tegra/tegra210_dmic.c
+++ b/sound/soc/tegra/tegra210_dmic.c
@@ -156,51 +156,162 @@ static int tegra210_dmic_hw_params(struct snd_pcm_substream *substream,
 	return 0;
 }
 
-static int tegra210_dmic_get_control(struct snd_kcontrol *kcontrol,
+static int tegra210_dmic_get_boost_gain(struct snd_kcontrol *kcontrol,
+					struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *comp = snd_soc_kcontrol_component(kcontrol);
+	struct tegra210_dmic *dmic = snd_soc_component_get_drvdata(comp);
+
+	ucontrol->value.integer.value[0] = dmic->boost_gain;
+
+	return 0;
+}
+
+static int tegra210_dmic_put_boost_gain(struct snd_kcontrol *kcontrol,
+					struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *comp = snd_soc_kcontrol_component(kcontrol);
+	struct tegra210_dmic *dmic = snd_soc_component_get_drvdata(comp);
+	int value = ucontrol->value.integer.value[0];
+
+	if (value == dmic->boost_gain)
+		return 0;
+
+	dmic->boost_gain = value;
+
+	return 1;
+}
+
+static int tegra210_dmic_get_ch_select(struct snd_kcontrol *kcontrol,
+				       struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *comp = snd_soc_kcontrol_component(kcontrol);
+	struct tegra210_dmic *dmic = snd_soc_component_get_drvdata(comp);
+
+	ucontrol->value.enumerated.item[0] = dmic->ch_select;
+
+	return 0;
+}
+
+static int tegra210_dmic_put_ch_select(struct snd_kcontrol *kcontrol,
+				       struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *comp = snd_soc_kcontrol_component(kcontrol);
+	struct tegra210_dmic *dmic = snd_soc_component_get_drvdata(comp);
+	unsigned int value = ucontrol->value.enumerated.item[0];
+
+	if (value == dmic->ch_select)
+		return 0;
+
+	dmic->ch_select = value;
+
+	return 1;
+}
+
+static int tegra210_dmic_get_mono_to_stereo(struct snd_kcontrol *kcontrol,
+					    struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *comp = snd_soc_kcontrol_component(kcontrol);
+	struct tegra210_dmic *dmic = snd_soc_component_get_drvdata(comp);
+
+	ucontrol->value.enumerated.item[0] = dmic->mono_to_stereo;
+
+	return 0;
+}
+
+static int tegra210_dmic_put_mono_to_stereo(struct snd_kcontrol *kcontrol,
+					    struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *comp = snd_soc_kcontrol_component(kcontrol);
+	struct tegra210_dmic *dmic = snd_soc_component_get_drvdata(comp);
+	unsigned int value = ucontrol->value.enumerated.item[0];
+
+	if (value == dmic->mono_to_stereo)
+		return 0;
+
+	dmic->mono_to_stereo = value;
+
+	return 1;
+}
+
+static int tegra210_dmic_get_stereo_to_mono(struct snd_kcontrol *kcontrol,
+					    struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *comp = snd_soc_kcontrol_component(kcontrol);
+	struct tegra210_dmic *dmic = snd_soc_component_get_drvdata(comp);
+
+	ucontrol->value.enumerated.item[0] = dmic->stereo_to_mono;
+
+	return 0;
+}
+
+static int tegra210_dmic_put_stereo_to_mono(struct snd_kcontrol *kcontrol,
+					    struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *comp = snd_soc_kcontrol_component(kcontrol);
+	struct tegra210_dmic *dmic = snd_soc_component_get_drvdata(comp);
+	unsigned int value = ucontrol->value.enumerated.item[0];
+
+	if (value == dmic->stereo_to_mono)
+		return 0;
+
+	dmic->stereo_to_mono = value;
+
+	return 1;
+}
+
+static int tegra210_dmic_get_osr_val(struct snd_kcontrol *kcontrol,
 				     struct snd_ctl_elem_value *ucontrol)
 {
 	struct snd_soc_component *comp = snd_soc_kcontrol_component(kcontrol);
 	struct tegra210_dmic *dmic = snd_soc_component_get_drvdata(comp);
 
-	if (strstr(kcontrol->id.name, "Boost Gain Volume"))
-		ucontrol->value.integer.value[0] = dmic->boost_gain;
-	else if (strstr(kcontrol->id.name, "Channel Select"))
-		ucontrol->value.integer.value[0] = dmic->ch_select;
-	else if (strstr(kcontrol->id.name, "Mono To Stereo"))
-		ucontrol->value.integer.value[0] = dmic->mono_to_stereo;
-	else if (strstr(kcontrol->id.name, "Stereo To Mono"))
-		ucontrol->value.integer.value[0] = dmic->stereo_to_mono;
-	else if (strstr(kcontrol->id.name, "OSR Value"))
-		ucontrol->value.integer.value[0] = dmic->osr_val;
-	else if (strstr(kcontrol->id.name, "LR Polarity Select"))
-		ucontrol->value.integer.value[0] = dmic->lrsel;
+	ucontrol->value.enumerated.item[0] = dmic->osr_val;
 
 	return 0;
 }
 
-static int tegra210_dmic_put_control(struct snd_kcontrol *kcontrol,
+static int tegra210_dmic_put_osr_val(struct snd_kcontrol *kcontrol,
 				     struct snd_ctl_elem_value *ucontrol)
 {
 	struct snd_soc_component *comp = snd_soc_kcontrol_component(kcontrol);
 	struct tegra210_dmic *dmic = snd_soc_component_get_drvdata(comp);
-	int value = ucontrol->value.integer.value[0];
+	unsigned int value = ucontrol->value.enumerated.item[0];
 
-	if (strstr(kcontrol->id.name, "Boost Gain Volume"))
-		dmic->boost_gain = value;
-	else if (strstr(kcontrol->id.name, "Channel Select"))
-		dmic->ch_select = ucontrol->value.integer.value[0];
-	else if (strstr(kcontrol->id.name, "Mono To Stereo"))
-		dmic->mono_to_stereo = value;
-	else if (strstr(kcontrol->id.name, "Stereo To Mono"))
-		dmic->stereo_to_mono = value;
-	else if (strstr(kcontrol->id.name, "OSR Value"))
-		dmic->osr_val = value;
-	else if (strstr(kcontrol->id.name, "LR Polarity Select"))
-		dmic->lrsel = value;
+	if (value == dmic->osr_val)
+		return 0;
+
+	dmic->osr_val = value;
+
+	return 1;
+}
+
+static int tegra210_dmic_get_pol_sel(struct snd_kcontrol *kcontrol,
+				     struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *comp = snd_soc_kcontrol_component(kcontrol);
+	struct tegra210_dmic *dmic = snd_soc_component_get_drvdata(comp);
+
+	ucontrol->value.enumerated.item[0] = dmic->lrsel;
 
 	return 0;
 }
 
+static int tegra210_dmic_put_pol_sel(struct snd_kcontrol *kcontrol,
+				     struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *comp = snd_soc_kcontrol_component(kcontrol);
+	struct tegra210_dmic *dmic = snd_soc_component_get_drvdata(comp);
+	unsigned int value = ucontrol->value.enumerated.item[0];
+
+	if (value == dmic->lrsel)
+		return 0;
+
+	dmic->lrsel = value;
+
+	return 1;
+}
+
 static const struct snd_soc_dai_ops tegra210_dmic_dai_ops = {
 	.hw_params	= tegra210_dmic_hw_params,
 };
@@ -287,19 +398,22 @@ static const struct soc_enum tegra210_dmic_lrsel_enum =
 
 static const struct snd_kcontrol_new tegra210_dmic_controls[] = {
 	SOC_SINGLE_EXT("Boost Gain Volume", 0, 0, MAX_BOOST_GAIN, 0,
-		       tegra210_dmic_get_control, tegra210_dmic_put_control),
+		       tegra210_dmic_get_boost_gain,
+		       tegra210_dmic_put_boost_gain),
 	SOC_ENUM_EXT("Channel Select", tegra210_dmic_ch_enum,
-		     tegra210_dmic_get_control, tegra210_dmic_put_control),
+		     tegra210_dmic_get_ch_select, tegra210_dmic_put_ch_select),
 	SOC_ENUM_EXT("Mono To Stereo",
-		     tegra210_dmic_mono_conv_enum, tegra210_dmic_get_control,
-		     tegra210_dmic_put_control),
+		     tegra210_dmic_mono_conv_enum,
+		     tegra210_dmic_get_mono_to_stereo,
+		     tegra210_dmic_put_mono_to_stereo),
 	SOC_ENUM_EXT("Stereo To Mono",
-		     tegra210_dmic_stereo_conv_enum, tegra210_dmic_get_control,
-		     tegra210_dmic_put_control),
+		     tegra210_dmic_stereo_conv_enum,
+		     tegra210_dmic_get_stereo_to_mono,
+		     tegra210_dmic_put_stereo_to_mono),
 	SOC_ENUM_EXT("OSR Value", tegra210_dmic_osr_enum,
-		     tegra210_dmic_get_control, tegra210_dmic_put_control),
+		     tegra210_dmic_get_osr_val, tegra210_dmic_put_osr_val),
 	SOC_ENUM_EXT("LR Polarity Select", tegra210_dmic_lrsel_enum,
-		     tegra210_dmic_get_control, tegra210_dmic_put_control),
+		     tegra210_dmic_get_pol_sel, tegra210_dmic_put_pol_sel),
 };
 
 static const struct snd_soc_component_driver tegra210_dmic_compnt = {
diff --git a/sound/soc/tegra/tegra210_i2s.c b/sound/soc/tegra/tegra210_i2s.c
index 45f31ccb49d8..9552bbb939dd 100644
--- a/sound/soc/tegra/tegra210_i2s.c
+++ b/sound/soc/tegra/tegra210_i2s.c
@@ -302,85 +302,235 @@ static int tegra210_i2s_set_tdm_slot(struct snd_soc_dai *dai,
 	return 0;
 }
 
-static int tegra210_i2s_set_dai_bclk_ratio(struct snd_soc_dai *dai,
-					   unsigned int ratio)
+static int tegra210_i2s_get_loopback(struct snd_kcontrol *kcontrol,
+				     struct snd_ctl_elem_value *ucontrol)
 {
-	struct tegra210_i2s *i2s = snd_soc_dai_get_drvdata(dai);
+	struct snd_soc_component *compnt = snd_soc_kcontrol_component(kcontrol);
+	struct tegra210_i2s *i2s = snd_soc_component_get_drvdata(compnt);
 
-	i2s->bclk_ratio = ratio;
+	ucontrol->value.integer.value[0] = i2s->loopback;
 
 	return 0;
 }
 
-static int tegra210_i2s_get_control(struct snd_kcontrol *kcontrol,
-				    struct snd_ctl_elem_value *ucontrol)
+static int tegra210_i2s_put_loopback(struct snd_kcontrol *kcontrol,
+				     struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *compnt = snd_soc_kcontrol_component(kcontrol);
+	struct tegra210_i2s *i2s = snd_soc_component_get_drvdata(compnt);
+	int value = ucontrol->value.integer.value[0];
+
+	if (value == i2s->loopback)
+		return 0;
+
+	i2s->loopback = value;
+
+	regmap_update_bits(i2s->regmap, TEGRA210_I2S_CTRL, I2S_CTRL_LPBK_MASK,
+			   i2s->loopback << I2S_CTRL_LPBK_SHIFT);
+
+	return 1;
+}
+
+static int tegra210_i2s_get_fsync_width(struct snd_kcontrol *kcontrol,
+					struct snd_ctl_elem_value *ucontrol)
 {
 	struct snd_soc_component *compnt = snd_soc_kcontrol_component(kcontrol);
 	struct tegra210_i2s *i2s = snd_soc_component_get_drvdata(compnt);
-	long *uctl_val = &ucontrol->value.integer.value[0];
-
-	if (strstr(kcontrol->id.name, "Loopback"))
-		*uctl_val = i2s->loopback;
-	else if (strstr(kcontrol->id.name, "FSYNC Width"))
-		*uctl_val = i2s->fsync_width;
-	else if (strstr(kcontrol->id.name, "Capture Stereo To Mono"))
-		*uctl_val = i2s->stereo_to_mono[I2S_TX_PATH];
-	else if (strstr(kcontrol->id.name, "Capture Mono To Stereo"))
-		*uctl_val = i2s->mono_to_stereo[I2S_TX_PATH];
-	else if (strstr(kcontrol->id.name, "Playback Stereo To Mono"))
-		*uctl_val = i2s->stereo_to_mono[I2S_RX_PATH];
-	else if (strstr(kcontrol->id.name, "Playback Mono To Stereo"))
-		*uctl_val = i2s->mono_to_stereo[I2S_RX_PATH];
-	else if (strstr(kcontrol->id.name, "Playback FIFO Threshold"))
-		*uctl_val = i2s->rx_fifo_th;
-	else if (strstr(kcontrol->id.name, "BCLK Ratio"))
-		*uctl_val = i2s->bclk_ratio;
+
+	ucontrol->value.integer.value[0] = i2s->fsync_width;
 
 	return 0;
 }
 
-static int tegra210_i2s_put_control(struct snd_kcontrol *kcontrol,
-				    struct snd_ctl_elem_value *ucontrol)
+static int tegra210_i2s_put_fsync_width(struct snd_kcontrol *kcontrol,
+					struct snd_ctl_elem_value *ucontrol)
 {
 	struct snd_soc_component *compnt = snd_soc_kcontrol_component(kcontrol);
 	struct tegra210_i2s *i2s = snd_soc_component_get_drvdata(compnt);
 	int value = ucontrol->value.integer.value[0];
 
-	if (strstr(kcontrol->id.name, "Loopback")) {
-		i2s->loopback = value;
+	if (value == i2s->fsync_width)
+		return 0;
 
-		regmap_update_bits(i2s->regmap, TEGRA210_I2S_CTRL,
-				   I2S_CTRL_LPBK_MASK,
-				   i2s->loopback << I2S_CTRL_LPBK_SHIFT);
+	i2s->fsync_width = value;
 
-	} else if (strstr(kcontrol->id.name, "FSYNC Width")) {
-		/*
-		 * Frame sync width is used only for FSYNC modes and not
-		 * applicable for LRCK modes. Reset value for this field is "0",
-		 * which means the width is one bit clock wide.
-		 * The width requirement may depend on the codec and in such
-		 * cases mixer control is used to update custom values. A value
-		 * of "N" here means, width is "N + 1" bit clock wide.
-		 */
-		i2s->fsync_width = value;
-
-		regmap_update_bits(i2s->regmap, TEGRA210_I2S_CTRL,
-				   I2S_CTRL_FSYNC_WIDTH_MASK,
-				   i2s->fsync_width << I2S_FSYNC_WIDTH_SHIFT);
-
-	} else if (strstr(kcontrol->id.name, "Capture Stereo To Mono")) {
-		i2s->stereo_to_mono[I2S_TX_PATH] = value;
-	} else if (strstr(kcontrol->id.name, "Capture Mono To Stereo")) {
-		i2s->mono_to_stereo[I2S_TX_PATH] = value;
-	} else if (strstr(kcontrol->id.name, "Playback Stereo To Mono")) {
-		i2s->stereo_to_mono[I2S_RX_PATH] = value;
-	} else if (strstr(kcontrol->id.name, "Playback Mono To Stereo")) {
-		i2s->mono_to_stereo[I2S_RX_PATH] = value;
-	} else if (strstr(kcontrol->id.name, "Playback FIFO Threshold")) {
-		i2s->rx_fifo_th = value;
-	} else if (strstr(kcontrol->id.name, "BCLK Ratio")) {
-		i2s->bclk_ratio = value;
-	}
+	/*
+	 * Frame sync width is used only for FSYNC modes and not
+	 * applicable for LRCK modes. Reset value for this field is "0",
+	 * which means the width is one bit clock wide.
+	 * The width requirement may depend on the codec and in such
+	 * cases mixer control is used to update custom values. A value
+	 * of "N" here means, width is "N + 1" bit clock wide.
+	 */
+	regmap_update_bits(i2s->regmap, TEGRA210_I2S_CTRL,
+			   I2S_CTRL_FSYNC_WIDTH_MASK,
+			   i2s->fsync_width << I2S_FSYNC_WIDTH_SHIFT);
+
+	return 1;
+}
+
+static int tegra210_i2s_cget_stereo_to_mono(struct snd_kcontrol *kcontrol,
+					    struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *compnt = snd_soc_kcontrol_component(kcontrol);
+	struct tegra210_i2s *i2s = snd_soc_component_get_drvdata(compnt);
+
+	ucontrol->value.enumerated.item[0] = i2s->stereo_to_mono[I2S_TX_PATH];
+
+	return 0;
+}
+
+static int tegra210_i2s_cput_stereo_to_mono(struct snd_kcontrol *kcontrol,
+					    struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *compnt = snd_soc_kcontrol_component(kcontrol);
+	struct tegra210_i2s *i2s = snd_soc_component_get_drvdata(compnt);
+	unsigned int value = ucontrol->value.enumerated.item[0];
+
+	if (value == i2s->stereo_to_mono[I2S_TX_PATH])
+		return 0;
+
+	i2s->stereo_to_mono[I2S_TX_PATH] = value;
+
+	return 1;
+}
+
+static int tegra210_i2s_cget_mono_to_stereo(struct snd_kcontrol *kcontrol,
+					    struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *compnt = snd_soc_kcontrol_component(kcontrol);
+	struct tegra210_i2s *i2s = snd_soc_component_get_drvdata(compnt);
+
+	ucontrol->value.enumerated.item[0] = i2s->mono_to_stereo[I2S_TX_PATH];
+
+	return 0;
+}
+
+static int tegra210_i2s_cput_mono_to_stereo(struct snd_kcontrol *kcontrol,
+					    struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *compnt = snd_soc_kcontrol_component(kcontrol);
+	struct tegra210_i2s *i2s = snd_soc_component_get_drvdata(compnt);
+	unsigned int value = ucontrol->value.enumerated.item[0];
+
+	if (value == i2s->mono_to_stereo[I2S_TX_PATH])
+		return 0;
+
+	i2s->mono_to_stereo[I2S_TX_PATH] = value;
+
+	return 1;
+}
+
+static int tegra210_i2s_pget_stereo_to_mono(struct snd_kcontrol *kcontrol,
+					    struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *compnt = snd_soc_kcontrol_component(kcontrol);
+	struct tegra210_i2s *i2s = snd_soc_component_get_drvdata(compnt);
+
+	ucontrol->value.enumerated.item[0] = i2s->stereo_to_mono[I2S_RX_PATH];
+
+	return 0;
+}
+
+static int tegra210_i2s_pput_stereo_to_mono(struct snd_kcontrol *kcontrol,
+					    struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *compnt = snd_soc_kcontrol_component(kcontrol);
+	struct tegra210_i2s *i2s = snd_soc_component_get_drvdata(compnt);
+	unsigned int value = ucontrol->value.enumerated.item[0];
+
+	if (value == i2s->stereo_to_mono[I2S_RX_PATH])
+		return 0;
+
+	i2s->stereo_to_mono[I2S_RX_PATH] = value;
+
+	return 1;
+}
+
+static int tegra210_i2s_pget_mono_to_stereo(struct snd_kcontrol *kcontrol,
+					    struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *compnt = snd_soc_kcontrol_component(kcontrol);
+	struct tegra210_i2s *i2s = snd_soc_component_get_drvdata(compnt);
+
+	ucontrol->value.enumerated.item[0] = i2s->mono_to_stereo[I2S_RX_PATH];
+
+	return 0;
+}
+
+static int tegra210_i2s_pput_mono_to_stereo(struct snd_kcontrol *kcontrol,
+					    struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *compnt = snd_soc_kcontrol_component(kcontrol);
+	struct tegra210_i2s *i2s = snd_soc_component_get_drvdata(compnt);
+	unsigned int value = ucontrol->value.enumerated.item[0];
+
+	if (value == i2s->mono_to_stereo[I2S_RX_PATH])
+		return 0;
+
+	i2s->mono_to_stereo[I2S_RX_PATH] = value;
+
+	return 1;
+}
+
+static int tegra210_i2s_pget_fifo_th(struct snd_kcontrol *kcontrol,
+				     struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *compnt = snd_soc_kcontrol_component(kcontrol);
+	struct tegra210_i2s *i2s = snd_soc_component_get_drvdata(compnt);
+
+	ucontrol->value.integer.value[0] = i2s->rx_fifo_th;
+
+	return 0;
+}
+
+static int tegra210_i2s_pput_fifo_th(struct snd_kcontrol *kcontrol,
+				     struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *compnt = snd_soc_kcontrol_component(kcontrol);
+	struct tegra210_i2s *i2s = snd_soc_component_get_drvdata(compnt);
+	int value = ucontrol->value.integer.value[0];
+
+	if (value == i2s->rx_fifo_th)
+		return 0;
+
+	i2s->rx_fifo_th = value;
+
+	return 1;
+}
+
+static int tegra210_i2s_get_bclk_ratio(struct snd_kcontrol *kcontrol,
+				       struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *compnt = snd_soc_kcontrol_component(kcontrol);
+	struct tegra210_i2s *i2s = snd_soc_component_get_drvdata(compnt);
+
+	ucontrol->value.integer.value[0] = i2s->bclk_ratio;
+
+	return 0;
+}
+
+static int tegra210_i2s_put_bclk_ratio(struct snd_kcontrol *kcontrol,
+				       struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *compnt = snd_soc_kcontrol_component(kcontrol);
+	struct tegra210_i2s *i2s = snd_soc_component_get_drvdata(compnt);
+	int value = ucontrol->value.integer.value[0];
+
+	if (value == i2s->bclk_ratio)
+		return 0;
+
+	i2s->bclk_ratio = value;
+
+	return 1;
+}
+
+static int tegra210_i2s_set_dai_bclk_ratio(struct snd_soc_dai *dai,
+					   unsigned int ratio)
+{
+	struct tegra210_i2s *i2s = snd_soc_dai_get_drvdata(dai);
+
+	i2s->bclk_ratio = ratio;
 
 	return 0;
 }
@@ -598,22 +748,28 @@ static const struct soc_enum tegra210_i2s_stereo_conv_enum =
 			tegra210_i2s_stereo_conv_text);
 
 static const struct snd_kcontrol_new tegra210_i2s_controls[] = {
-	SOC_SINGLE_EXT("Loopback", 0, 0, 1, 0, tegra210_i2s_get_control,
-		       tegra210_i2s_put_control),
-	SOC_SINGLE_EXT("FSYNC Width", 0, 0, 255, 0, tegra210_i2s_get_control,
-		       tegra210_i2s_put_control),
+	SOC_SINGLE_EXT("Loopback", 0, 0, 1, 0, tegra210_i2s_get_loopback,
+		       tegra210_i2s_put_loopback),
+	SOC_SINGLE_EXT("FSYNC Width", 0, 0, 255, 0,
+		       tegra210_i2s_get_fsync_width,
+		       tegra210_i2s_put_fsync_width),
 	SOC_ENUM_EXT("Capture Stereo To Mono", tegra210_i2s_stereo_conv_enum,
-		     tegra210_i2s_get_control, tegra210_i2s_put_control),
+		     tegra210_i2s_cget_stereo_to_mono,
+		     tegra210_i2s_cput_stereo_to_mono),
 	SOC_ENUM_EXT("Capture Mono To Stereo", tegra210_i2s_mono_conv_enum,
-		     tegra210_i2s_get_control, tegra210_i2s_put_control),
+		     tegra210_i2s_cget_mono_to_stereo,
+		     tegra210_i2s_cput_mono_to_stereo),
 	SOC_ENUM_EXT("Playback Stereo To Mono", tegra210_i2s_stereo_conv_enum,
-		     tegra210_i2s_get_control, tegra210_i2s_put_control),
+		     tegra210_i2s_pget_mono_to_stereo,
+		     tegra210_i2s_pput_mono_to_stereo),
 	SOC_ENUM_EXT("Playback Mono To Stereo", tegra210_i2s_mono_conv_enum,
-		     tegra210_i2s_get_control, tegra210_i2s_put_control),
+		     tegra210_i2s_pget_stereo_to_mono,
+		     tegra210_i2s_pput_stereo_to_mono),
 	SOC_SINGLE_EXT("Playback FIFO Threshold", 0, 0, I2S_RX_FIFO_DEPTH - 1,
-		       0, tegra210_i2s_get_control, tegra210_i2s_put_control),
-	SOC_SINGLE_EXT("BCLK Ratio", 0, 0, INT_MAX, 0, tegra210_i2s_get_control,
-		       tegra210_i2s_put_control),
+		       0, tegra210_i2s_pget_fifo_th, tegra210_i2s_pput_fifo_th),
+	SOC_SINGLE_EXT("BCLK Ratio", 0, 0, INT_MAX, 0,
+		       tegra210_i2s_get_bclk_ratio,
+		       tegra210_i2s_put_bclk_ratio),
 };
 
 static const struct snd_soc_dapm_widget tegra210_i2s_widgets[] = {
diff --git a/sound/soc/tegra/tegra210_mixer.c b/sound/soc/tegra/tegra210_mixer.c
index 55e61776c565..16e679a95658 100644
--- a/sound/soc/tegra/tegra210_mixer.c
+++ b/sound/soc/tegra/tegra210_mixer.c
@@ -192,24 +192,24 @@ static int tegra210_mixer_get_gain(struct snd_kcontrol *kcontrol,
 	return 0;
 }
 
-static int tegra210_mixer_put_gain(struct snd_kcontrol *kcontrol,
-				   struct snd_ctl_elem_value *ucontrol)
+static int tegra210_mixer_apply_gain(struct snd_kcontrol *kcontrol,
+				     struct snd_ctl_elem_value *ucontrol,
+				     bool instant_gain)
 {
 	struct soc_mixer_control *mc =
 		(struct soc_mixer_control *)kcontrol->private_value;
 	struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol);
 	struct tegra210_mixer *mixer = snd_soc_component_get_drvdata(cmpnt);
 	unsigned int reg = mc->reg, id;
-	bool instant_gain = false;
 	int err;
 
-	if (strstr(kcontrol->id.name, "Instant Gain Volume"))
-		instant_gain = true;
-
 	/* Save gain value for specific MIXER input */
 	id = (reg - TEGRA210_MIXER_GAIN_CFG_RAM_ADDR_0) /
 	     TEGRA210_MIXER_GAIN_CFG_RAM_ADDR_STRIDE;
 
+	if (mixer->gain_value[id] == ucontrol->value.integer.value[0])
+		return 0;
+
 	mixer->gain_value[id] = ucontrol->value.integer.value[0];
 
 	err = tegra210_mixer_configure_gain(cmpnt, id, instant_gain);
@@ -221,6 +221,18 @@ static int tegra210_mixer_put_gain(struct snd_kcontrol *kcontrol,
 	return 1;
 }
 
+static int tegra210_mixer_put_gain(struct snd_kcontrol *kcontrol,
+				   struct snd_ctl_elem_value *ucontrol)
+{
+	return tegra210_mixer_apply_gain(kcontrol, ucontrol, false);
+}
+
+static int tegra210_mixer_put_instant_gain(struct snd_kcontrol *kcontrol,
+					   struct snd_ctl_elem_value *ucontrol)
+{
+	return tegra210_mixer_apply_gain(kcontrol, ucontrol, true);
+}
+
 static int tegra210_mixer_set_audio_cif(struct tegra210_mixer *mixer,
 					struct snd_pcm_hw_params *params,
 					unsigned int reg,
@@ -388,7 +400,7 @@ ADDER_CTRL_DECL(adder5, TEGRA210_MIXER_TX5_ADDER_CONFIG);
 	SOC_SINGLE_EXT("RX" #id " Instant Gain Volume",		\
 		       MIXER_GAIN_CFG_RAM_ADDR((id) - 1), 0,	\
 		       0x20000, 0, tegra210_mixer_get_gain,	\
-		       tegra210_mixer_put_gain),
+		       tegra210_mixer_put_instant_gain),
 
 /* Volume controls for all MIXER inputs */
 static const struct snd_kcontrol_new tegra210_mixer_gain_ctls[] = {
@@ -654,8 +666,8 @@ static int tegra210_mixer_platform_remove(struct platform_device *pdev)
 static const struct dev_pm_ops tegra210_mixer_pm_ops = {
 	SET_RUNTIME_PM_OPS(tegra210_mixer_runtime_suspend,
 			   tegra210_mixer_runtime_resume, NULL)
-	SET_LATE_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
-				     pm_runtime_force_resume)
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
 };
 
 static struct platform_driver tegra210_mixer_driver = {
diff --git a/sound/soc/tegra/tegra210_mvc.c b/sound/soc/tegra/tegra210_mvc.c
index 7b9c7006e419..acf59328dcb6 100644
--- a/sound/soc/tegra/tegra210_mvc.c
+++ b/sound/soc/tegra/tegra210_mvc.c
@@ -136,7 +136,7 @@ static int tegra210_mvc_put_mute(struct snd_kcontrol *kcontrol,
 	struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol);
 	struct tegra210_mvc *mvc = snd_soc_component_get_drvdata(cmpnt);
 	unsigned int value;
-	u8 mute_mask;
+	u8 new_mask, old_mask;
 	int err;
 
 	pm_runtime_get_sync(cmpnt->dev);
@@ -148,15 +148,23 @@ static int tegra210_mvc_put_mute(struct snd_kcontrol *kcontrol,
 	if (err < 0)
 		goto end;
 
-	mute_mask = ucontrol->value.integer.value[0];
+	regmap_read(mvc->regmap, TEGRA210_MVC_CTRL, &value);
+
+	old_mask = (value >> TEGRA210_MVC_MUTE_SHIFT) & TEGRA210_MUTE_MASK_EN;
+	new_mask = ucontrol->value.integer.value[0];
+
+	if (new_mask == old_mask) {
+		err = 0;
+		goto end;
+	}
 
 	err = regmap_update_bits(mvc->regmap, mc->reg,
 				 TEGRA210_MVC_MUTE_MASK,
-				 mute_mask << TEGRA210_MVC_MUTE_SHIFT);
+				 new_mask << TEGRA210_MVC_MUTE_SHIFT);
 	if (err < 0)
 		goto end;
 
-	return 1;
+	err = 1;
 
 end:
 	pm_runtime_put(cmpnt->dev);
@@ -195,7 +203,7 @@ static int tegra210_mvc_put_vol(struct snd_kcontrol *kcontrol,
 	unsigned int reg = mc->reg;
 	unsigned int value;
 	u8 chan;
-	int err;
+	int err, old_volume;
 
 	pm_runtime_get_sync(cmpnt->dev);
 
@@ -207,10 +215,16 @@ static int tegra210_mvc_put_vol(struct snd_kcontrol *kcontrol,
 		goto end;
 
 	chan = (reg - TEGRA210_MVC_TARGET_VOL) / REG_SIZE;
+	old_volume = mvc->volume[chan];
 
 	tegra210_mvc_conv_vol(mvc, chan,
 			      ucontrol->value.integer.value[0]);
 
+	if (mvc->volume[chan] == old_volume) {
+		err = 0;
+		goto end;
+	}
+
 	/* Configure init volume same as target volume */
 	regmap_write(mvc->regmap,
 		TEGRA210_MVC_REG_OFFSET(TEGRA210_MVC_INIT_VOL, chan),
@@ -222,7 +236,7 @@ static int tegra210_mvc_put_vol(struct snd_kcontrol *kcontrol,
 			   TEGRA210_MVC_VOLUME_SWITCH_MASK,
 			   TEGRA210_MVC_VOLUME_SWITCH_TRIGGER);
 
-	return 1;
+	err = 1;
 
 end:
 	pm_runtime_put(cmpnt->dev);
@@ -275,7 +289,7 @@ static int tegra210_mvc_get_curve_type(struct snd_kcontrol *kcontrol,
 	struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol);
 	struct tegra210_mvc *mvc = snd_soc_component_get_drvdata(cmpnt);
 
-	ucontrol->value.integer.value[0] = mvc->curve_type;
+	ucontrol->value.enumerated.item[0] = mvc->curve_type;
 
 	return 0;
 }
@@ -285,7 +299,7 @@ static int tegra210_mvc_put_curve_type(struct snd_kcontrol *kcontrol,
 {
 	struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol);
 	struct tegra210_mvc *mvc = snd_soc_component_get_drvdata(cmpnt);
-	int value;
+	unsigned int value;
 
 	regmap_read(mvc->regmap, TEGRA210_MVC_ENABLE, &value);
 	if (value & TEGRA210_MVC_EN) {
@@ -294,10 +308,10 @@ static int tegra210_mvc_put_curve_type(struct snd_kcontrol *kcontrol,
 		return -EINVAL;
 	}
 
-	if (mvc->curve_type == ucontrol->value.integer.value[0])
+	if (mvc->curve_type == ucontrol->value.enumerated.item[0])
 		return 0;
 
-	mvc->curve_type = ucontrol->value.integer.value[0];
+	mvc->curve_type = ucontrol->value.enumerated.item[0];
 
 	tegra210_mvc_reset_vol_settings(mvc, cmpnt->dev);
 
@@ -625,8 +639,8 @@ static int tegra210_mvc_platform_remove(struct platform_device *pdev)
 static const struct dev_pm_ops tegra210_mvc_pm_ops = {
 	SET_RUNTIME_PM_OPS(tegra210_mvc_runtime_suspend,
 			   tegra210_mvc_runtime_resume, NULL)
-	SET_LATE_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
-				     pm_runtime_force_resume)
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
 };
 
 static struct platform_driver tegra210_mvc_driver = {
diff --git a/sound/soc/tegra/tegra210_sfc.c b/sound/soc/tegra/tegra210_sfc.c
index dc477ee1b82c..368f077e7bee 100644
--- a/sound/soc/tegra/tegra210_sfc.c
+++ b/sound/soc/tegra/tegra210_sfc.c
@@ -3244,46 +3244,107 @@ static int tegra210_sfc_init(struct snd_soc_dapm_widget *w,
 	return tegra210_sfc_write_coeff_ram(cmpnt);
 }
 
-static int tegra210_sfc_get_control(struct snd_kcontrol *kcontrol,
+static int tegra210_sfc_iget_stereo_to_mono(struct snd_kcontrol *kcontrol,
 				    struct snd_ctl_elem_value *ucontrol)
 {
 	struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol);
 	struct tegra210_sfc *sfc = snd_soc_component_get_drvdata(cmpnt);
 
-	if (strstr(kcontrol->id.name, "Input Stereo To Mono"))
-		ucontrol->value.integer.value[0] =
-			sfc->stereo_to_mono[SFC_RX_PATH];
-	else if (strstr(kcontrol->id.name, "Input Mono To Stereo"))
-		ucontrol->value.integer.value[0] =
-			sfc->mono_to_stereo[SFC_RX_PATH];
-	else if (strstr(kcontrol->id.name, "Output Stereo To Mono"))
-		ucontrol->value.integer.value[0] =
-			sfc->stereo_to_mono[SFC_TX_PATH];
-	else if (strstr(kcontrol->id.name, "Output Mono To Stereo"))
-		ucontrol->value.integer.value[0] =
-			sfc->mono_to_stereo[SFC_TX_PATH];
+	ucontrol->value.enumerated.item[0] = sfc->stereo_to_mono[SFC_RX_PATH];
 
 	return 0;
 }
 
-static int tegra210_sfc_put_control(struct snd_kcontrol *kcontrol,
+static int tegra210_sfc_iput_stereo_to_mono(struct snd_kcontrol *kcontrol,
 				    struct snd_ctl_elem_value *ucontrol)
 {
 	struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol);
 	struct tegra210_sfc *sfc = snd_soc_component_get_drvdata(cmpnt);
-	int value = ucontrol->value.integer.value[0];
-
-	if (strstr(kcontrol->id.name, "Input Stereo To Mono"))
-		sfc->stereo_to_mono[SFC_RX_PATH] = value;
-	else if (strstr(kcontrol->id.name, "Input Mono To Stereo"))
-		sfc->mono_to_stereo[SFC_RX_PATH] = value;
-	else if (strstr(kcontrol->id.name, "Output Stereo To Mono"))
-		sfc->stereo_to_mono[SFC_TX_PATH] = value;
-	else if (strstr(kcontrol->id.name, "Output Mono To Stereo"))
-		sfc->mono_to_stereo[SFC_TX_PATH] = value;
-	else
+	unsigned int value = ucontrol->value.enumerated.item[0];
+
+	if (value == sfc->stereo_to_mono[SFC_RX_PATH])
+		return 0;
+
+	sfc->stereo_to_mono[SFC_RX_PATH] = value;
+
+	return 1;
+}
+
+static int tegra210_sfc_iget_mono_to_stereo(struct snd_kcontrol *kcontrol,
+				    struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol);
+	struct tegra210_sfc *sfc = snd_soc_component_get_drvdata(cmpnt);
+
+	ucontrol->value.enumerated.item[0] = sfc->mono_to_stereo[SFC_RX_PATH];
+
+	return 0;
+}
+
+static int tegra210_sfc_iput_mono_to_stereo(struct snd_kcontrol *kcontrol,
+				    struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol);
+	struct tegra210_sfc *sfc = snd_soc_component_get_drvdata(cmpnt);
+	unsigned int value = ucontrol->value.enumerated.item[0];
+
+	if (value == sfc->mono_to_stereo[SFC_RX_PATH])
 		return 0;
 
+	sfc->mono_to_stereo[SFC_RX_PATH] = value;
+
+	return 1;
+}
+
+static int tegra210_sfc_oget_stereo_to_mono(struct snd_kcontrol *kcontrol,
+				    struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol);
+	struct tegra210_sfc *sfc = snd_soc_component_get_drvdata(cmpnt);
+
+	ucontrol->value.enumerated.item[0] = sfc->stereo_to_mono[SFC_TX_PATH];
+
+	return 0;
+}
+
+static int tegra210_sfc_oput_stereo_to_mono(struct snd_kcontrol *kcontrol,
+				    struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol);
+	struct tegra210_sfc *sfc = snd_soc_component_get_drvdata(cmpnt);
+	unsigned int value = ucontrol->value.enumerated.item[0];
+
+	if (value == sfc->stereo_to_mono[SFC_TX_PATH])
+		return 0;
+
+	sfc->stereo_to_mono[SFC_TX_PATH] = value;
+
+	return 1;
+}
+
+static int tegra210_sfc_oget_mono_to_stereo(struct snd_kcontrol *kcontrol,
+				    struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol);
+	struct tegra210_sfc *sfc = snd_soc_component_get_drvdata(cmpnt);
+
+	ucontrol->value.enumerated.item[0] = sfc->mono_to_stereo[SFC_TX_PATH];
+
+	return 0;
+}
+
+static int tegra210_sfc_oput_mono_to_stereo(struct snd_kcontrol *kcontrol,
+				    struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol);
+	struct tegra210_sfc *sfc = snd_soc_component_get_drvdata(cmpnt);
+	unsigned int value = ucontrol->value.enumerated.item[0];
+
+	if (value == sfc->mono_to_stereo[SFC_TX_PATH])
+		return 0;
+
+	sfc->mono_to_stereo[SFC_TX_PATH] = value;
+
 	return 1;
 }
 
@@ -3384,13 +3445,17 @@ static const struct soc_enum tegra210_sfc_mono_conv_enum =
 
 static const struct snd_kcontrol_new tegra210_sfc_controls[] = {
 	SOC_ENUM_EXT("Input Stereo To Mono", tegra210_sfc_stereo_conv_enum,
-		tegra210_sfc_get_control, tegra210_sfc_put_control),
+		     tegra210_sfc_iget_stereo_to_mono,
+		     tegra210_sfc_iput_stereo_to_mono),
 	SOC_ENUM_EXT("Input Mono To Stereo", tegra210_sfc_mono_conv_enum,
-		tegra210_sfc_get_control, tegra210_sfc_put_control),
+		     tegra210_sfc_iget_mono_to_stereo,
+		     tegra210_sfc_iput_mono_to_stereo),
 	SOC_ENUM_EXT("Output Stereo To Mono", tegra210_sfc_stereo_conv_enum,
-		tegra210_sfc_get_control, tegra210_sfc_put_control),
+		     tegra210_sfc_oget_stereo_to_mono,
+		     tegra210_sfc_oput_stereo_to_mono),
 	SOC_ENUM_EXT("Output Mono To Stereo", tegra210_sfc_mono_conv_enum,
-		tegra210_sfc_get_control, tegra210_sfc_put_control),
+		     tegra210_sfc_oget_mono_to_stereo,
+		     tegra210_sfc_oput_mono_to_stereo),
 };
 
 static const struct snd_soc_component_driver tegra210_sfc_cmpnt = {
@@ -3529,8 +3594,8 @@ static int tegra210_sfc_platform_remove(struct platform_device *pdev)
 static const struct dev_pm_ops tegra210_sfc_pm_ops = {
 	SET_RUNTIME_PM_OPS(tegra210_sfc_runtime_suspend,
 			   tegra210_sfc_runtime_resume, NULL)
-	SET_LATE_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
-				     pm_runtime_force_resume)
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
 };
 
 static struct platform_driver tegra210_sfc_driver = {
diff --git a/sound/soc/tegra/tegra_asoc_machine.c b/sound/soc/tegra/tegra_asoc_machine.c
index b95438c3dbf7..a73404879aa1 100644
--- a/sound/soc/tegra/tegra_asoc_machine.c
+++ b/sound/soc/tegra/tegra_asoc_machine.c
@@ -116,16 +116,24 @@ static const struct snd_kcontrol_new tegra_machine_controls[] = {
 	SOC_DAPM_PIN_SWITCH("Headset Mic"),
 	SOC_DAPM_PIN_SWITCH("Internal Mic 1"),
 	SOC_DAPM_PIN_SWITCH("Internal Mic 2"),
+	SOC_DAPM_PIN_SWITCH("Headphones"),
+	SOC_DAPM_PIN_SWITCH("Mic Jack"),
 };
 
 int tegra_asoc_machine_init(struct snd_soc_pcm_runtime *rtd)
 {
 	struct snd_soc_card *card = rtd->card;
 	struct tegra_machine *machine = snd_soc_card_get_drvdata(card);
+	const char *jack_name;
 	int err;
 
 	if (machine->gpiod_hp_det && machine->asoc->add_hp_jack) {
-		err = snd_soc_card_jack_new(card, "Headphones Jack",
+		if (machine->asoc->hp_jack_name)
+			jack_name = machine->asoc->hp_jack_name;
+		else
+			jack_name = "Headphones Jack";
+
+		err = snd_soc_card_jack_new(card, jack_name,
 					    SND_JACK_HEADPHONE,
 					    &tegra_machine_hp_jack,
 					    tegra_machine_hp_jack_pins,
@@ -658,6 +666,7 @@ static struct snd_soc_card snd_soc_tegra_max98090 = {
 static const struct tegra_asoc_data tegra_max98090_data = {
 	.mclk_rate = tegra_machine_mclk_rate_12mhz,
 	.card = &snd_soc_tegra_max98090,
+	.hp_jack_name = "Headphones",
 	.add_common_dapm_widgets = true,
 	.add_common_controls = true,
 	.add_common_snd_ops = true,
diff --git a/sound/soc/tegra/tegra_asoc_machine.h b/sound/soc/tegra/tegra_asoc_machine.h
index d6a8d1320551..6f795d7dff7c 100644
--- a/sound/soc/tegra/tegra_asoc_machine.h
+++ b/sound/soc/tegra/tegra_asoc_machine.h
@@ -14,6 +14,7 @@ struct snd_soc_pcm_runtime;
 struct tegra_asoc_data {
 	unsigned int (*mclk_rate)(unsigned int srate);
 	const char *codec_dev_name;
+	const char *hp_jack_name;
 	struct snd_soc_card *card;
 	unsigned int mclk_id;
 	bool hp_jack_gpio_active_low;
diff --git a/sound/usb/mixer_quirks.c b/sound/usb/mixer_quirks.c
index d489c1de3bae..823b6b8de942 100644
--- a/sound/usb/mixer_quirks.c
+++ b/sound/usb/mixer_quirks.c
@@ -3016,11 +3016,11 @@ static const struct snd_djm_ctl snd_djm_ctls_750mk2[] = {
 
 
 static const struct snd_djm_device snd_djm_devices[] = {
-	SND_DJM_DEVICE(250mk2),
-	SND_DJM_DEVICE(750),
-	SND_DJM_DEVICE(750mk2),
-	SND_DJM_DEVICE(850),
-	SND_DJM_DEVICE(900nxs2)
+	[SND_DJM_250MK2_IDX] = SND_DJM_DEVICE(250mk2),
+	[SND_DJM_750_IDX] = SND_DJM_DEVICE(750),
+	[SND_DJM_850_IDX] = SND_DJM_DEVICE(850),
+	[SND_DJM_900NXS2_IDX] = SND_DJM_DEVICE(900nxs2),
+	[SND_DJM_750MK2_IDX] = SND_DJM_DEVICE(750mk2),
 };
 
 
diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c
index 95ec8eec1bb0..cec6e91afea2 100644
--- a/sound/usb/pcm.c
+++ b/sound/usb/pcm.c
@@ -581,6 +581,12 @@ static int snd_usb_hw_free(struct snd_pcm_substream *substream)
 	return 0;
 }
 
+/* free-wheeling mode? (e.g. dmix) */
+static int in_free_wheeling_mode(struct snd_pcm_runtime *runtime)
+{
+	return runtime->stop_threshold > runtime->buffer_size;
+}
+
 /* check whether early start is needed for playback stream */
 static int lowlatency_playback_available(struct snd_pcm_runtime *runtime,
 					 struct snd_usb_substream *subs)
@@ -592,8 +598,7 @@ static int lowlatency_playback_available(struct snd_pcm_runtime *runtime,
 	/* disabled via module option? */
 	if (!chip->lowlatency)
 		return false;
-	/* free-wheeling mode? (e.g. dmix) */
-	if (runtime->stop_threshold > runtime->buffer_size)
+	if (in_free_wheeling_mode(runtime))
 		return false;
 	/* implicit feedback mode has own operation mode */
 	if (snd_usb_endpoint_implicit_feedback_sink(subs->data_endpoint))
@@ -635,7 +640,8 @@ static int snd_usb_pcm_prepare(struct snd_pcm_substream *substream)
 	runtime->delay = 0;
 
 	subs->lowlatency_playback = lowlatency_playback_available(runtime, subs);
-	if (!subs->lowlatency_playback)
+	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK &&
+	    !subs->lowlatency_playback)
 		ret = start_endpoints(subs);
 
  unlock:
@@ -1552,6 +1558,8 @@ static int snd_usb_substream_playback_trigger(struct snd_pcm_substream *substrea
 					      subs);
 		if (subs->lowlatency_playback &&
 		    cmd == SNDRV_PCM_TRIGGER_START) {
+			if (in_free_wheeling_mode(substream->runtime))
+				subs->lowlatency_playback = false;
 			err = start_endpoints(subs);
 			if (err < 0) {
 				snd_usb_endpoint_set_callback(subs->data_endpoint,
diff --git a/sound/xen/xen_snd_front.c b/sound/xen/xen_snd_front.c
index 2cb0a19be2b8..4041748c12e5 100644
--- a/sound/xen/xen_snd_front.c
+++ b/sound/xen/xen_snd_front.c
@@ -358,6 +358,7 @@ static struct xenbus_driver xen_driver = {
 	.probe = xen_drv_probe,
 	.remove = xen_drv_remove,
 	.otherend_changed = sndback_changed,
+	.not_essential = true,
 };
 
 static int __init xen_drv_init(void)
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index d0ce5cfd3ac1..d5b5f2ab87a0 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -277,6 +277,7 @@
 #define X86_FEATURE_XSAVEC		(10*32+ 1) /* XSAVEC instruction */
 #define X86_FEATURE_XGETBV1		(10*32+ 2) /* XGETBV with ECX = 1 instruction */
 #define X86_FEATURE_XSAVES		(10*32+ 3) /* XSAVES/XRSTORS instructions */
+#define X86_FEATURE_XFD			(10*32+ 4) /* "" eXtended Feature Disabling */
 
 /*
  * Extended auxiliary flags: Linux defined - for features scattered in various
@@ -298,6 +299,7 @@
 /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
 #define X86_FEATURE_AVX_VNNI		(12*32+ 4) /* AVX VNNI instructions */
 #define X86_FEATURE_AVX512_BF16		(12*32+ 5) /* AVX512 BFLOAT16 instructions */
+#define X86_FEATURE_AMX_TILE		(18*32+24) /* AMX tile Support */
 
 /* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */
 #define X86_FEATURE_CLZERO		(13*32+ 0) /* CLZERO instruction */
diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index a7c413432b33..01e2650b9585 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -625,6 +625,8 @@
 
 #define MSR_IA32_BNDCFGS_RSVD		0x00000ffc
 
+#define MSR_IA32_XFD			0x000001c4
+#define MSR_IA32_XFD_ERR		0x000001c5
 #define MSR_IA32_XSS			0x00000da0
 
 #define MSR_IA32_APICBASE		0x0000001b
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index 2ef1f6513c68..5a776a08f78c 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -504,4 +504,8 @@ struct kvm_pmu_event_filter {
 #define KVM_PMU_EVENT_ALLOW 0
 #define KVM_PMU_EVENT_DENY 1
 
+/* for KVM_{GET,SET,HAS}_DEVICE_ATTR */
+#define KVM_VCPU_TSC_CTRL 0 /* control group for the timestamp counter (TSC) */
+#define   KVM_VCPU_TSC_OFFSET 0 /* attribute for the TSC offset */
+
 #endif /* _ASM_X86_KVM_H */
diff --git a/tools/arch/x86/include/uapi/asm/prctl.h b/tools/arch/x86/include/uapi/asm/prctl.h
index 5a6aac9fa41f..754a07856817 100644
--- a/tools/arch/x86/include/uapi/asm/prctl.h
+++ b/tools/arch/x86/include/uapi/asm/prctl.h
@@ -10,6 +10,10 @@
 #define ARCH_GET_CPUID		0x1011
 #define ARCH_SET_CPUID		0x1012
 
+#define ARCH_GET_XCOMP_SUPP	0x1021
+#define ARCH_GET_XCOMP_PERM	0x1022
+#define ARCH_REQ_XCOMP_PERM	0x1023
+
 #define ARCH_MAP_VDSO_X32	0x2001
 #define ARCH_MAP_VDSO_32	0x2002
 #define ARCH_MAP_VDSO_64	0x2003
diff --git a/tools/bpf/resolve_btfids/main.c b/tools/bpf/resolve_btfids/main.c
index a59cb0ee609c..73409e27be01 100644
--- a/tools/bpf/resolve_btfids/main.c
+++ b/tools/bpf/resolve_btfids/main.c
@@ -83,6 +83,7 @@ struct btf_id {
 		int	 cnt;
 	};
 	int		 addr_cnt;
+	bool		 is_set;
 	Elf64_Addr	 addr[ADDR_CNT];
 };
 
@@ -451,8 +452,10 @@ static int symbols_collect(struct object *obj)
 			 * in symbol's size, together with 'cnt' field hence
 			 * that - 1.
 			 */
-			if (id)
+			if (id) {
 				id->cnt = sym.st_size / sizeof(int) - 1;
+				id->is_set = true;
+			}
 		} else {
 			pr_err("FAILED unsupported prefix %s\n", prefix);
 			return -1;
@@ -568,9 +571,8 @@ static int id_patch(struct object *obj, struct btf_id *id)
 	int *ptr = data->d_buf;
 	int i;
 
-	if (!id->id) {
+	if (!id->id && !id->is_set)
 		pr_err("WARN: resolve_btfids: unresolved symbol %s\n", id->name);
-	}
 
 	for (i = 0; i < id->addr_cnt; i++) {
 		unsigned long addr = id->addr[i];
diff --git a/tools/bpf/runqslower/Makefile b/tools/bpf/runqslower/Makefile
index bbd1150578f7..8791d0e2762b 100644
--- a/tools/bpf/runqslower/Makefile
+++ b/tools/bpf/runqslower/Makefile
@@ -88,5 +88,4 @@ $(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(BPFOBJ_OU
 
 $(DEFAULT_BPFTOOL): $(BPFOBJ) | $(BPFTOOL_OUTPUT)
 	$(Q)$(MAKE) $(submake_extras) -C ../bpftool OUTPUT=$(BPFTOOL_OUTPUT)   \
-		    LIBBPF_OUTPUT=$(BPFOBJ_OUTPUT)			       \
-		    LIBBPF_DESTDIR=$(BPF_DESTDIR) CC=$(HOSTCC) LD=$(HOSTLD)
+		    CC=$(HOSTCC) LD=$(HOSTLD)
diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index 45a9a59828c3..ae61f464043a 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -48,7 +48,6 @@ FEATURE_TESTS_BASIC :=                  \
         numa_num_possible_cpus          \
         libperl                         \
         libpython                       \
-        libpython-version               \
         libslang                        \
         libslang-include-subdir         \
         libtraceevent                   \
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index 0a3244ad9673..1480910c792e 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -32,7 +32,6 @@ FILES=                                          \
          test-numa_num_possible_cpus.bin        \
          test-libperl.bin                       \
          test-libpython.bin                     \
-         test-libpython-version.bin             \
          test-libslang.bin                      \
          test-libslang-include-subdir.bin       \
          test-libtraceevent.bin                 \
@@ -227,9 +226,6 @@ $(OUTPUT)test-libperl.bin:
 $(OUTPUT)test-libpython.bin:
 	$(BUILD) $(FLAGS_PYTHON_EMBED)
 
-$(OUTPUT)test-libpython-version.bin:
-	$(BUILD)
-
 $(OUTPUT)test-libbfd.bin:
 	$(BUILD) -DPACKAGE='"perf"' -lbfd -ldl
 
diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c
index 920439527291..5ffafb967b6e 100644
--- a/tools/build/feature/test-all.c
+++ b/tools/build/feature/test-all.c
@@ -14,10 +14,6 @@
 # include "test-libpython.c"
 #undef main
 
-#define main main_test_libpython_version
-# include "test-libpython-version.c"
-#undef main
-
 #define main main_test_libperl
 # include "test-libperl.c"
 #undef main
@@ -177,7 +173,6 @@
 int main(int argc, char *argv[])
 {
 	main_test_libpython();
-	main_test_libpython_version();
 	main_test_libperl();
 	main_test_hello();
 	main_test_libelf();
@@ -200,7 +195,6 @@ int main(int argc, char *argv[])
 	main_test_timerfd();
 	main_test_stackprotector_all();
 	main_test_libdw_dwarf_unwind();
-	main_test_sync_compare_and_swap(argc, argv);
 	main_test_zlib();
 	main_test_pthread_attr_setaffinity_np();
 	main_test_pthread_barrier();
diff --git a/tools/build/feature/test-libpython-version.c b/tools/build/feature/test-libpython-version.c
deleted file mode 100644
index 47714b942d4d..000000000000
--- a/tools/build/feature/test-libpython-version.c
+++ /dev/null
@@ -1,11 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <Python.h>
-
-#if PY_VERSION_HEX >= 0x03000000
-	#error
-#endif
-
-int main(void)
-{
-	return 0;
-}
diff --git a/tools/include/linux/debug_locks.h b/tools/include/linux/debug_locks.h
deleted file mode 100644
index 72d595ce764a..000000000000
--- a/tools/include/linux/debug_locks.h
+++ /dev/null
@@ -1,14 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LIBLOCKDEP_DEBUG_LOCKS_H_
-#define _LIBLOCKDEP_DEBUG_LOCKS_H_
-
-#include <stddef.h>
-#include <linux/compiler.h>
-#include <asm/bug.h>
-
-#define DEBUG_LOCKS_WARN_ON(x) WARN_ON(x)
-
-extern bool debug_locks;
-extern bool debug_locks_silent;
-
-#endif
diff --git a/tools/include/linux/hardirq.h b/tools/include/linux/hardirq.h
deleted file mode 100644
index b25580b6a9be..000000000000
--- a/tools/include/linux/hardirq.h
+++ /dev/null
@@ -1,12 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LIBLOCKDEP_LINUX_HARDIRQ_H_
-#define _LIBLOCKDEP_LINUX_HARDIRQ_H_
-
-#define SOFTIRQ_BITS	0UL
-#define HARDIRQ_BITS	0UL
-#define SOFTIRQ_SHIFT	0UL
-#define HARDIRQ_SHIFT	0UL
-#define hardirq_count()	0UL
-#define softirq_count()	0UL
-
-#endif
diff --git a/tools/include/linux/irqflags.h b/tools/include/linux/irqflags.h
deleted file mode 100644
index 501262aee8ff..000000000000
--- a/tools/include/linux/irqflags.h
+++ /dev/null
@@ -1,39 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LIBLOCKDEP_LINUX_TRACE_IRQFLAGS_H_
-#define _LIBLOCKDEP_LINUX_TRACE_IRQFLAGS_H_
-
-# define lockdep_hardirq_context()	0
-# define lockdep_softirq_context(p)	0
-# define lockdep_hardirqs_enabled()	0
-# define lockdep_softirqs_enabled(p)	0
-# define lockdep_hardirq_enter()	do { } while (0)
-# define lockdep_hardirq_exit()		do { } while (0)
-# define lockdep_softirq_enter()	do { } while (0)
-# define lockdep_softirq_exit()		do { } while (0)
-# define INIT_TRACE_IRQFLAGS
-
-# define stop_critical_timings() do { } while (0)
-# define start_critical_timings() do { } while (0)
-
-#define raw_local_irq_disable() do { } while (0)
-#define raw_local_irq_enable() do { } while (0)
-#define raw_local_irq_save(flags) ((flags) = 0)
-#define raw_local_irq_restore(flags) ((void)(flags))
-#define raw_local_save_flags(flags) ((flags) = 0)
-#define raw_irqs_disabled_flags(flags) ((void)(flags))
-#define raw_irqs_disabled() 0
-#define raw_safe_halt()
-
-#define local_irq_enable() do { } while (0)
-#define local_irq_disable() do { } while (0)
-#define local_irq_save(flags) ((flags) = 0)
-#define local_irq_restore(flags) ((void)(flags))
-#define local_save_flags(flags)	((flags) = 0)
-#define irqs_disabled() (1)
-#define irqs_disabled_flags(flags) ((void)(flags), 0)
-#define safe_halt() do { } while (0)
-
-#define trace_lock_release(x, y)
-#define trace_lock_acquire(a, b, c, d, e, f, g)
-
-#endif
diff --git a/tools/include/linux/kernel.h b/tools/include/linux/kernel.h
index a7e54a08fb54..3e8df500cfbd 100644
--- a/tools/include/linux/kernel.h
+++ b/tools/include/linux/kernel.h
@@ -7,6 +7,7 @@
 #include <assert.h>
 #include <linux/build_bug.h>
 #include <linux/compiler.h>
+#include <linux/math.h>
 #include <endian.h>
 #include <byteswap.h>
 
@@ -14,8 +15,6 @@
 #define UINT_MAX	(~0U)
 #endif
 
-#define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d))
-
 #define PERF_ALIGN(x, a)	__PERF_ALIGN_MASK(x, (typeof(x))(a)-1)
 #define __PERF_ALIGN_MASK(x, mask)	(((x)+(mask))&~(mask))
 
@@ -52,15 +51,6 @@
 	_min1 < _min2 ? _min1 : _min2; })
 #endif
 
-#ifndef roundup
-#define roundup(x, y) (                                \
-{                                                      \
-	const typeof(y) __y = y;		       \
-	(((x) + (__y - 1)) / __y) * __y;	       \
-}                                                      \
-)
-#endif
-
 #ifndef BUG_ON
 #ifdef NDEBUG
 #define BUG_ON(cond) do { if (cond) {} } while (0)
@@ -104,16 +94,6 @@ int scnprintf_pad(char * buf, size_t size, const char * fmt, ...);
 
 #define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]) + __must_be_array(arr))
 
-/*
- * This looks more complex than it should be. But we need to
- * get the type for the ~ right in round_down (it needs to be
- * as wide as the result!), and we want to evaluate the macro
- * arguments just once each.
- */
-#define __round_mask(x, y) ((__typeof__(x))((y)-1))
-#define round_up(x, y) ((((x)-1) | __round_mask(x, y))+1)
-#define round_down(x, y) ((x) & ~__round_mask(x, y))
-
 #define current_gfp_context(k) 0
 #define synchronize_rcu()
 
diff --git a/tools/include/linux/lockdep.h b/tools/include/linux/lockdep.h
deleted file mode 100644
index e56997288f2b..000000000000
--- a/tools/include/linux/lockdep.h
+++ /dev/null
@@ -1,72 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LIBLOCKDEP_LOCKDEP_H_
-#define _LIBLOCKDEP_LOCKDEP_H_
-
-#include <sys/prctl.h>
-#include <sys/syscall.h>
-#include <string.h>
-#include <limits.h>
-#include <linux/utsname.h>
-#include <linux/compiler.h>
-#include <linux/export.h>
-#include <linux/kern_levels.h>
-#include <linux/err.h>
-#include <linux/rcu.h>
-#include <linux/list.h>
-#include <linux/hardirq.h>
-#include <unistd.h>
-
-#define MAX_LOCK_DEPTH 63UL
-
-#define asmlinkage
-#define __visible
-
-#include "../../../include/linux/lockdep.h"
-
-struct task_struct {
-	u64 curr_chain_key;
-	int lockdep_depth;
-	unsigned int lockdep_recursion;
-	struct held_lock held_locks[MAX_LOCK_DEPTH];
-	gfp_t lockdep_reclaim_gfp;
-	int pid;
-	int state;
-	char comm[17];
-};
-
-#define TASK_RUNNING 0
-
-extern struct task_struct *__curr(void);
-
-#define current (__curr())
-
-static inline int debug_locks_off(void)
-{
-	return 1;
-}
-
-#define task_pid_nr(tsk) ((tsk)->pid)
-
-#define KSYM_NAME_LEN 128
-#define printk(...) dprintf(STDOUT_FILENO, __VA_ARGS__)
-#define pr_err(format, ...) fprintf (stderr, format, ## __VA_ARGS__)
-#define pr_warn pr_err
-#define pr_cont pr_err
-
-#define list_del_rcu list_del
-
-#define atomic_t unsigned long
-#define atomic_inc(x) ((*(x))++)
-
-#define print_tainted() ""
-#define static_obj(x) 1
-
-#define debug_show_all_locks()
-extern void debug_check_no_locks_held(void);
-
-static __used bool __is_kernel_percpu_address(unsigned long addr, void *can_addr)
-{
-	return false;
-}
-
-#endif
diff --git a/tools/include/linux/math.h b/tools/include/linux/math.h
new file mode 100644
index 000000000000..4e7af99ec9eb
--- /dev/null
+++ b/tools/include/linux/math.h
@@ -0,0 +1,25 @@
+#ifndef _TOOLS_MATH_H
+#define _TOOLS_MATH_H
+
+/*
+ * This looks more complex than it should be. But we need to
+ * get the type for the ~ right in round_down (it needs to be
+ * as wide as the result!), and we want to evaluate the macro
+ * arguments just once each.
+ */
+#define __round_mask(x, y) ((__typeof__(x))((y)-1))
+#define round_up(x, y) ((((x)-1) | __round_mask(x, y))+1)
+#define round_down(x, y) ((x) & ~__round_mask(x, y))
+
+#define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d))
+
+#ifndef roundup
+#define roundup(x, y) (                                \
+{                                                      \
+	const typeof(y) __y = y;		       \
+	(((x) + (__y - 1)) / __y) * __y;	       \
+}                                                      \
+)
+#endif
+
+#endif
diff --git a/tools/include/linux/proc_fs.h b/tools/include/linux/proc_fs.h
deleted file mode 100644
index 8b3b03b64fda..000000000000
--- a/tools/include/linux/proc_fs.h
+++ /dev/null
@@ -1,4 +0,0 @@
-#ifndef _TOOLS_INCLUDE_LINUX_PROC_FS_H
-#define _TOOLS_INCLUDE_LINUX_PROC_FS_H
-
-#endif /* _TOOLS_INCLUDE_LINUX_PROC_FS_H */
diff --git a/tools/include/linux/spinlock.h b/tools/include/linux/spinlock.h
index c934572d935c..622266b197d0 100644
--- a/tools/include/linux/spinlock.h
+++ b/tools/include/linux/spinlock.h
@@ -37,6 +37,4 @@ static inline bool arch_spin_is_locked(arch_spinlock_t *mutex)
 	return true;
 }
 
-#include <linux/lockdep.h>
-
 #endif
diff --git a/tools/include/linux/stacktrace.h b/tools/include/linux/stacktrace.h
deleted file mode 100644
index ae343ac35bfa..000000000000
--- a/tools/include/linux/stacktrace.h
+++ /dev/null
@@ -1,33 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LIBLOCKDEP_LINUX_STACKTRACE_H_
-#define _LIBLOCKDEP_LINUX_STACKTRACE_H_
-
-#include <execinfo.h>
-
-struct stack_trace {
-	unsigned int nr_entries, max_entries;
-	unsigned long *entries;
-	int skip;
-};
-
-static inline void print_stack_trace(struct stack_trace *trace, int spaces)
-{
-	backtrace_symbols_fd((void **)trace->entries, trace->nr_entries, 1);
-}
-
-#define save_stack_trace(trace)	\
-	((trace)->nr_entries =	\
-		backtrace((void **)(trace)->entries, (trace)->max_entries))
-
-static inline int dump_stack(void)
-{
-	void *array[64];
-	size_t size;
-
-	size = backtrace(array, 64);
-	backtrace_symbols_fd(array, size, 1);
-
-	return 0;
-}
-
-#endif
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
index 1c5fb86d455a..4557a8b6086f 100644
--- a/tools/include/uapi/asm-generic/unistd.h
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -880,8 +880,11 @@ __SYSCALL(__NR_memfd_secret, sys_memfd_secret)
 #define __NR_process_mrelease 448
 __SYSCALL(__NR_process_mrelease, sys_process_mrelease)
 
+#define __NR_futex_waitv 449
+__SYSCALL(__NR_futex_waitv, sys_futex_waitv)
+
 #undef __NR_syscalls
-#define __NR_syscalls 449
+#define __NR_syscalls 450
 
 /*
  * 32 bit systems traditionally used different
diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
index bde5860b3686..914ebd9290e5 100644
--- a/tools/include/uapi/drm/i915_drm.h
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -1522,6 +1522,12 @@ struct drm_i915_gem_caching {
 #define I915_TILING_NONE	0
 #define I915_TILING_X		1
 #define I915_TILING_Y		2
+/*
+ * Do not add new tiling types here.  The I915_TILING_* values are for
+ * de-tiling fence registers that no longer exist on modern platforms.  Although
+ * the hardware may support new types of tiling in general (e.g., Tile4), we
+ * do not need to add them to the uapi that is specific to now-defunct ioctls.
+ */
 #define I915_TILING_LAST	I915_TILING_Y
 
 #define I915_BIT_6_SWIZZLE_NONE		0
@@ -1824,6 +1830,7 @@ struct drm_i915_gem_context_param {
  * Extensions:
  *   i915_context_engines_load_balance (I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE)
  *   i915_context_engines_bond (I915_CONTEXT_ENGINES_EXT_BOND)
+ *   i915_context_engines_parallel_submit (I915_CONTEXT_ENGINES_EXT_PARALLEL_SUBMIT)
  */
 #define I915_CONTEXT_PARAM_ENGINES	0xa
 
@@ -1846,6 +1853,55 @@ struct drm_i915_gem_context_param {
  * attempted to use it, never re-use this context param number.
  */
 #define I915_CONTEXT_PARAM_RINGSIZE	0xc
+
+/*
+ * I915_CONTEXT_PARAM_PROTECTED_CONTENT:
+ *
+ * Mark that the context makes use of protected content, which will result
+ * in the context being invalidated when the protected content session is.
+ * Given that the protected content session is killed on suspend, the device
+ * is kept awake for the lifetime of a protected context, so the user should
+ * make sure to dispose of them once done.
+ * This flag can only be set at context creation time and, when set to true,
+ * must be preceded by an explicit setting of I915_CONTEXT_PARAM_RECOVERABLE
+ * to false. This flag can't be set to true in conjunction with setting the
+ * I915_CONTEXT_PARAM_BANNABLE flag to false. Creation example:
+ *
+ * .. code-block:: C
+ *
+ *	struct drm_i915_gem_context_create_ext_setparam p_protected = {
+ *		.base = {
+ *			.name = I915_CONTEXT_CREATE_EXT_SETPARAM,
+ *		},
+ *		.param = {
+ *			.param = I915_CONTEXT_PARAM_PROTECTED_CONTENT,
+ *			.value = 1,
+ *		}
+ *	};
+ *	struct drm_i915_gem_context_create_ext_setparam p_norecover = {
+ *		.base = {
+ *			.name = I915_CONTEXT_CREATE_EXT_SETPARAM,
+ *			.next_extension = to_user_pointer(&p_protected),
+ *		},
+ *		.param = {
+ *			.param = I915_CONTEXT_PARAM_RECOVERABLE,
+ *			.value = 0,
+ *		}
+ *	};
+ *	struct drm_i915_gem_context_create_ext create = {
+ *		.flags = I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS,
+ *		.extensions = to_user_pointer(&p_norecover);
+ *	};
+ *
+ *	ctx_id = gem_context_create_ext(drm_fd, &create);
+ *
+ * In addition to the normal failure cases, setting this flag during context
+ * creation can result in the following errors:
+ *
+ * -ENODEV: feature not available
+ * -EPERM: trying to mark a recoverable or not bannable context as protected
+ */
+#define I915_CONTEXT_PARAM_PROTECTED_CONTENT    0xd
 /* Must be kept compact -- no holes and well documented */
 
 	__u64 value;
@@ -2050,6 +2106,135 @@ struct i915_context_engines_bond {
 } __attribute__((packed)) name__
 
 /**
+ * struct i915_context_engines_parallel_submit - Configure engine for
+ * parallel submission.
+ *
+ * Setup a slot in the context engine map to allow multiple BBs to be submitted
+ * in a single execbuf IOCTL. Those BBs will then be scheduled to run on the GPU
+ * in parallel. Multiple hardware contexts are created internally in the i915 to
+ * run these BBs. Once a slot is configured for N BBs only N BBs can be
+ * submitted in each execbuf IOCTL and this is implicit behavior e.g. The user
+ * doesn't tell the execbuf IOCTL there are N BBs, the execbuf IOCTL knows how
+ * many BBs there are based on the slot's configuration. The N BBs are the last
+ * N buffer objects or first N if I915_EXEC_BATCH_FIRST is set.
+ *
+ * The default placement behavior is to create implicit bonds between each
+ * context if each context maps to more than 1 physical engine (e.g. context is
+ * a virtual engine). Also we only allow contexts of same engine class and these
+ * contexts must be in logically contiguous order. Examples of the placement
+ * behavior are described below. Lastly, the default is to not allow BBs to be
+ * preempted mid-batch. Rather insert coordinated preemption points on all
+ * hardware contexts between each set of BBs. Flags could be added in the future
+ * to change both of these default behaviors.
+ *
+ * Returns -EINVAL if hardware context placement configuration is invalid or if
+ * the placement configuration isn't supported on the platform / submission
+ * interface.
+ * Returns -ENODEV if extension isn't supported on the platform / submission
+ * interface.
+ *
+ * .. code-block:: none
+ *
+ *	Examples syntax:
+ *	CS[X] = generic engine of same class, logical instance X
+ *	INVALID = I915_ENGINE_CLASS_INVALID, I915_ENGINE_CLASS_INVALID_NONE
+ *
+ *	Example 1 pseudo code:
+ *	set_engines(INVALID)
+ *	set_parallel(engine_index=0, width=2, num_siblings=1,
+ *		     engines=CS[0],CS[1])
+ *
+ *	Results in the following valid placement:
+ *	CS[0], CS[1]
+ *
+ *	Example 2 pseudo code:
+ *	set_engines(INVALID)
+ *	set_parallel(engine_index=0, width=2, num_siblings=2,
+ *		     engines=CS[0],CS[2],CS[1],CS[3])
+ *
+ *	Results in the following valid placements:
+ *	CS[0], CS[1]
+ *	CS[2], CS[3]
+ *
+ *	This can be thought of as two virtual engines, each containing two
+ *	engines thereby making a 2D array. However, there are bonds tying the
+ *	entries together and placing restrictions on how they can be scheduled.
+ *	Specifically, the scheduler can choose only vertical columns from the 2D
+ *	array. That is, CS[0] is bonded to CS[1] and CS[2] to CS[3]. So if the
+ *	scheduler wants to submit to CS[0], it must also choose CS[1] and vice
+ *	versa. Same for CS[2] requires also using CS[3].
+ *	VE[0] = CS[0], CS[2]
+ *	VE[1] = CS[1], CS[3]
+ *
+ *	Example 3 pseudo code:
+ *	set_engines(INVALID)
+ *	set_parallel(engine_index=0, width=2, num_siblings=2,
+ *		     engines=CS[0],CS[1],CS[1],CS[3])
+ *
+ *	Results in the following valid and invalid placements:
+ *	CS[0], CS[1]
+ *	CS[1], CS[3] - Not logically contiguous, return -EINVAL
+ */
+struct i915_context_engines_parallel_submit {
+	/**
+	 * @base: base user extension.
+	 */
+	struct i915_user_extension base;
+
+	/**
+	 * @engine_index: slot for parallel engine
+	 */
+	__u16 engine_index;
+
+	/**
+	 * @width: number of contexts per parallel engine or in other words the
+	 * number of batches in each submission
+	 */
+	__u16 width;
+
+	/**
+	 * @num_siblings: number of siblings per context or in other words the
+	 * number of possible placements for each submission
+	 */
+	__u16 num_siblings;
+
+	/**
+	 * @mbz16: reserved for future use; must be zero
+	 */
+	__u16 mbz16;
+
+	/**
+	 * @flags: all undefined flags must be zero, currently not defined flags
+	 */
+	__u64 flags;
+
+	/**
+	 * @mbz64: reserved for future use; must be zero
+	 */
+	__u64 mbz64[3];
+
+	/**
+	 * @engines: 2-d array of engine instances to configure parallel engine
+	 *
+	 * length = width (i) * num_siblings (j)
+	 * index = j + i * num_siblings
+	 */
+	struct i915_engine_class_instance engines[0];
+
+} __packed;
+
+#define I915_DEFINE_CONTEXT_ENGINES_PARALLEL_SUBMIT(name__, N__) struct { \
+	struct i915_user_extension base; \
+	__u16 engine_index; \
+	__u16 width; \
+	__u16 num_siblings; \
+	__u16 mbz16; \
+	__u64 flags; \
+	__u64 mbz64[3]; \
+	struct i915_engine_class_instance engines[N__]; \
+} __attribute__((packed)) name__
+
+/**
  * DOC: Context Engine Map uAPI
  *
  * Context engine map is a new way of addressing engines when submitting batch-
@@ -2108,6 +2293,7 @@ struct i915_context_param_engines {
 	__u64 extensions; /* linked chain of extension blocks, 0 terminates */
 #define I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE 0 /* see i915_context_engines_load_balance */
 #define I915_CONTEXT_ENGINES_EXT_BOND 1 /* see i915_context_engines_bond */
+#define I915_CONTEXT_ENGINES_EXT_PARALLEL_SUBMIT 2 /* see i915_context_engines_parallel_submit */
 	struct i915_engine_class_instance engines[0];
 } __attribute__((packed));
 
@@ -2726,14 +2912,20 @@ struct drm_i915_engine_info {
 
 	/** @flags: Engine flags. */
 	__u64 flags;
+#define I915_ENGINE_INFO_HAS_LOGICAL_INSTANCE		(1 << 0)
 
 	/** @capabilities: Capabilities of this engine. */
 	__u64 capabilities;
 #define I915_VIDEO_CLASS_CAPABILITY_HEVC		(1 << 0)
 #define I915_VIDEO_AND_ENHANCE_CLASS_CAPABILITY_SFC	(1 << 1)
 
+	/** @logical_instance: Logical instance of engine */
+	__u16 logical_instance;
+
 	/** @rsvd1: Reserved fields. */
-	__u64 rsvd1[4];
+	__u16 rsvd1[3];
+	/** @rsvd2: Reserved fields. */
+	__u64 rsvd2[3];
 };
 
 /**
@@ -2979,8 +3171,12 @@ struct drm_i915_gem_create_ext {
 	 *
 	 * For I915_GEM_CREATE_EXT_MEMORY_REGIONS usage see
 	 * struct drm_i915_gem_create_ext_memory_regions.
+	 *
+	 * For I915_GEM_CREATE_EXT_PROTECTED_CONTENT usage see
+	 * struct drm_i915_gem_create_ext_protected_content.
 	 */
 #define I915_GEM_CREATE_EXT_MEMORY_REGIONS 0
+#define I915_GEM_CREATE_EXT_PROTECTED_CONTENT 1
 	__u64 extensions;
 };
 
@@ -3038,6 +3234,50 @@ struct drm_i915_gem_create_ext_memory_regions {
 	__u64 regions;
 };
 
+/**
+ * struct drm_i915_gem_create_ext_protected_content - The
+ * I915_OBJECT_PARAM_PROTECTED_CONTENT extension.
+ *
+ * If this extension is provided, buffer contents are expected to be protected
+ * by PXP encryption and require decryption for scan out and processing. This
+ * is only possible on platforms that have PXP enabled, on all other scenarios
+ * using this extension will cause the ioctl to fail and return -ENODEV. The
+ * flags parameter is reserved for future expansion and must currently be set
+ * to zero.
+ *
+ * The buffer contents are considered invalid after a PXP session teardown.
+ *
+ * The encryption is guaranteed to be processed correctly only if the object
+ * is submitted with a context created using the
+ * I915_CONTEXT_PARAM_PROTECTED_CONTENT flag. This will also enable extra checks
+ * at submission time on the validity of the objects involved.
+ *
+ * Below is an example on how to create a protected object:
+ *
+ * .. code-block:: C
+ *
+ *      struct drm_i915_gem_create_ext_protected_content protected_ext = {
+ *              .base = { .name = I915_GEM_CREATE_EXT_PROTECTED_CONTENT },
+ *              .flags = 0,
+ *      };
+ *      struct drm_i915_gem_create_ext create_ext = {
+ *              .size = PAGE_SIZE,
+ *              .extensions = (uintptr_t)&protected_ext,
+ *      };
+ *
+ *      int err = ioctl(fd, DRM_IOCTL_I915_GEM_CREATE_EXT, &create_ext);
+ *      if (err) ...
+ */
+struct drm_i915_gem_create_ext_protected_content {
+	/** @base: Extension link. See struct i915_user_extension. */
+	struct i915_user_extension base;
+	/** @flags: reserved for future usage, currently MBZ */
+	__u32 flags;
+};
+
+/* ID of the protected content session managed by i915 when PXP is active */
+#define I915_PROTECTED_CONTENT_DEFAULT_SESSION 0xf
+
 #if defined(__cplusplus)
 }
 #endif
diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h
index b3610fdd1fee..eebd3894fe89 100644
--- a/tools/include/uapi/linux/if_link.h
+++ b/tools/include/uapi/linux/if_link.h
@@ -7,24 +7,23 @@
 
 /* This struct should be in sync with struct rtnl_link_stats64 */
 struct rtnl_link_stats {
-	__u32	rx_packets;		/* total packets received	*/
-	__u32	tx_packets;		/* total packets transmitted	*/
-	__u32	rx_bytes;		/* total bytes received 	*/
-	__u32	tx_bytes;		/* total bytes transmitted	*/
-	__u32	rx_errors;		/* bad packets received		*/
-	__u32	tx_errors;		/* packet transmit problems	*/
-	__u32	rx_dropped;		/* no space in linux buffers	*/
-	__u32	tx_dropped;		/* no space available in linux	*/
-	__u32	multicast;		/* multicast packets received	*/
+	__u32	rx_packets;
+	__u32	tx_packets;
+	__u32	rx_bytes;
+	__u32	tx_bytes;
+	__u32	rx_errors;
+	__u32	tx_errors;
+	__u32	rx_dropped;
+	__u32	tx_dropped;
+	__u32	multicast;
 	__u32	collisions;
-
 	/* detailed rx_errors: */
 	__u32	rx_length_errors;
-	__u32	rx_over_errors;		/* receiver ring buff overflow	*/
-	__u32	rx_crc_errors;		/* recved pkt with crc error	*/
-	__u32	rx_frame_errors;	/* recv'd frame alignment error */
-	__u32	rx_fifo_errors;		/* recv'r fifo overrun		*/
-	__u32	rx_missed_errors;	/* receiver missed packet	*/
+	__u32	rx_over_errors;
+	__u32	rx_crc_errors;
+	__u32	rx_frame_errors;
+	__u32	rx_fifo_errors;
+	__u32	rx_missed_errors;
 
 	/* detailed tx_errors */
 	__u32	tx_aborted_errors;
@@ -37,29 +36,201 @@ struct rtnl_link_stats {
 	__u32	rx_compressed;
 	__u32	tx_compressed;
 
-	__u32	rx_nohandler;		/* dropped, no handler found	*/
+	__u32	rx_nohandler;
 };
 
-/* The main device statistics structure */
+/**
+ * struct rtnl_link_stats64 - The main device statistics structure.
+ *
+ * @rx_packets: Number of good packets received by the interface.
+ *   For hardware interfaces counts all good packets received from the device
+ *   by the host, including packets which host had to drop at various stages
+ *   of processing (even in the driver).
+ *
+ * @tx_packets: Number of packets successfully transmitted.
+ *   For hardware interfaces counts packets which host was able to successfully
+ *   hand over to the device, which does not necessarily mean that packets
+ *   had been successfully transmitted out of the device, only that device
+ *   acknowledged it copied them out of host memory.
+ *
+ * @rx_bytes: Number of good received bytes, corresponding to @rx_packets.
+ *
+ *   For IEEE 802.3 devices should count the length of Ethernet Frames
+ *   excluding the FCS.
+ *
+ * @tx_bytes: Number of good transmitted bytes, corresponding to @tx_packets.
+ *
+ *   For IEEE 802.3 devices should count the length of Ethernet Frames
+ *   excluding the FCS.
+ *
+ * @rx_errors: Total number of bad packets received on this network device.
+ *   This counter must include events counted by @rx_length_errors,
+ *   @rx_crc_errors, @rx_frame_errors and other errors not otherwise
+ *   counted.
+ *
+ * @tx_errors: Total number of transmit problems.
+ *   This counter must include events counter by @tx_aborted_errors,
+ *   @tx_carrier_errors, @tx_fifo_errors, @tx_heartbeat_errors,
+ *   @tx_window_errors and other errors not otherwise counted.
+ *
+ * @rx_dropped: Number of packets received but not processed,
+ *   e.g. due to lack of resources or unsupported protocol.
+ *   For hardware interfaces this counter may include packets discarded
+ *   due to L2 address filtering but should not include packets dropped
+ *   by the device due to buffer exhaustion which are counted separately in
+ *   @rx_missed_errors (since procfs folds those two counters together).
+ *
+ * @tx_dropped: Number of packets dropped on their way to transmission,
+ *   e.g. due to lack of resources.
+ *
+ * @multicast: Multicast packets received.
+ *   For hardware interfaces this statistic is commonly calculated
+ *   at the device level (unlike @rx_packets) and therefore may include
+ *   packets which did not reach the host.
+ *
+ *   For IEEE 802.3 devices this counter may be equivalent to:
+ *
+ *    - 30.3.1.1.21 aMulticastFramesReceivedOK
+ *
+ * @collisions: Number of collisions during packet transmissions.
+ *
+ * @rx_length_errors: Number of packets dropped due to invalid length.
+ *   Part of aggregate "frame" errors in `/proc/net/dev`.
+ *
+ *   For IEEE 802.3 devices this counter should be equivalent to a sum
+ *   of the following attributes:
+ *
+ *    - 30.3.1.1.23 aInRangeLengthErrors
+ *    - 30.3.1.1.24 aOutOfRangeLengthField
+ *    - 30.3.1.1.25 aFrameTooLongErrors
+ *
+ * @rx_over_errors: Receiver FIFO overflow event counter.
+ *
+ *   Historically the count of overflow events. Such events may be
+ *   reported in the receive descriptors or via interrupts, and may
+ *   not correspond one-to-one with dropped packets.
+ *
+ *   The recommended interpretation for high speed interfaces is -
+ *   number of packets dropped because they did not fit into buffers
+ *   provided by the host, e.g. packets larger than MTU or next buffer
+ *   in the ring was not available for a scatter transfer.
+ *
+ *   Part of aggregate "frame" errors in `/proc/net/dev`.
+ *
+ *   This statistics was historically used interchangeably with
+ *   @rx_fifo_errors.
+ *
+ *   This statistic corresponds to hardware events and is not commonly used
+ *   on software devices.
+ *
+ * @rx_crc_errors: Number of packets received with a CRC error.
+ *   Part of aggregate "frame" errors in `/proc/net/dev`.
+ *
+ *   For IEEE 802.3 devices this counter must be equivalent to:
+ *
+ *    - 30.3.1.1.6 aFrameCheckSequenceErrors
+ *
+ * @rx_frame_errors: Receiver frame alignment errors.
+ *   Part of aggregate "frame" errors in `/proc/net/dev`.
+ *
+ *   For IEEE 802.3 devices this counter should be equivalent to:
+ *
+ *    - 30.3.1.1.7 aAlignmentErrors
+ *
+ * @rx_fifo_errors: Receiver FIFO error counter.
+ *
+ *   Historically the count of overflow events. Those events may be
+ *   reported in the receive descriptors or via interrupts, and may
+ *   not correspond one-to-one with dropped packets.
+ *
+ *   This statistics was used interchangeably with @rx_over_errors.
+ *   Not recommended for use in drivers for high speed interfaces.
+ *
+ *   This statistic is used on software devices, e.g. to count software
+ *   packet queue overflow (can) or sequencing errors (GRE).
+ *
+ * @rx_missed_errors: Count of packets missed by the host.
+ *   Folded into the "drop" counter in `/proc/net/dev`.
+ *
+ *   Counts number of packets dropped by the device due to lack
+ *   of buffer space. This usually indicates that the host interface
+ *   is slower than the network interface, or host is not keeping up
+ *   with the receive packet rate.
+ *
+ *   This statistic corresponds to hardware events and is not used
+ *   on software devices.
+ *
+ * @tx_aborted_errors:
+ *   Part of aggregate "carrier" errors in `/proc/net/dev`.
+ *   For IEEE 802.3 devices capable of half-duplex operation this counter
+ *   must be equivalent to:
+ *
+ *    - 30.3.1.1.11 aFramesAbortedDueToXSColls
+ *
+ *   High speed interfaces may use this counter as a general device
+ *   discard counter.
+ *
+ * @tx_carrier_errors: Number of frame transmission errors due to loss
+ *   of carrier during transmission.
+ *   Part of aggregate "carrier" errors in `/proc/net/dev`.
+ *
+ *   For IEEE 802.3 devices this counter must be equivalent to:
+ *
+ *    - 30.3.1.1.13 aCarrierSenseErrors
+ *
+ * @tx_fifo_errors: Number of frame transmission errors due to device
+ *   FIFO underrun / underflow. This condition occurs when the device
+ *   begins transmission of a frame but is unable to deliver the
+ *   entire frame to the transmitter in time for transmission.
+ *   Part of aggregate "carrier" errors in `/proc/net/dev`.
+ *
+ * @tx_heartbeat_errors: Number of Heartbeat / SQE Test errors for
+ *   old half-duplex Ethernet.
+ *   Part of aggregate "carrier" errors in `/proc/net/dev`.
+ *
+ *   For IEEE 802.3 devices possibly equivalent to:
+ *
+ *    - 30.3.2.1.4 aSQETestErrors
+ *
+ * @tx_window_errors: Number of frame transmission errors due
+ *   to late collisions (for Ethernet - after the first 64B of transmission).
+ *   Part of aggregate "carrier" errors in `/proc/net/dev`.
+ *
+ *   For IEEE 802.3 devices this counter must be equivalent to:
+ *
+ *    - 30.3.1.1.10 aLateCollisions
+ *
+ * @rx_compressed: Number of correctly received compressed packets.
+ *   This counters is only meaningful for interfaces which support
+ *   packet compression (e.g. CSLIP, PPP).
+ *
+ * @tx_compressed: Number of transmitted compressed packets.
+ *   This counters is only meaningful for interfaces which support
+ *   packet compression (e.g. CSLIP, PPP).
+ *
+ * @rx_nohandler: Number of packets received on the interface
+ *   but dropped by the networking stack because the device is
+ *   not designated to receive packets (e.g. backup link in a bond).
+ */
 struct rtnl_link_stats64 {
-	__u64	rx_packets;		/* total packets received	*/
-	__u64	tx_packets;		/* total packets transmitted	*/
-	__u64	rx_bytes;		/* total bytes received 	*/
-	__u64	tx_bytes;		/* total bytes transmitted	*/
-	__u64	rx_errors;		/* bad packets received		*/
-	__u64	tx_errors;		/* packet transmit problems	*/
-	__u64	rx_dropped;		/* no space in linux buffers	*/
-	__u64	tx_dropped;		/* no space available in linux	*/
-	__u64	multicast;		/* multicast packets received	*/
+	__u64	rx_packets;
+	__u64	tx_packets;
+	__u64	rx_bytes;
+	__u64	tx_bytes;
+	__u64	rx_errors;
+	__u64	tx_errors;
+	__u64	rx_dropped;
+	__u64	tx_dropped;
+	__u64	multicast;
 	__u64	collisions;
 
 	/* detailed rx_errors: */
 	__u64	rx_length_errors;
-	__u64	rx_over_errors;		/* receiver ring buff overflow	*/
-	__u64	rx_crc_errors;		/* recved pkt with crc error	*/
-	__u64	rx_frame_errors;	/* recv'd frame alignment error */
-	__u64	rx_fifo_errors;		/* recv'r fifo overrun		*/
-	__u64	rx_missed_errors;	/* receiver missed packet	*/
+	__u64	rx_over_errors;
+	__u64	rx_crc_errors;
+	__u64	rx_frame_errors;
+	__u64	rx_fifo_errors;
+	__u64	rx_missed_errors;
 
 	/* detailed tx_errors */
 	__u64	tx_aborted_errors;
@@ -71,8 +242,7 @@ struct rtnl_link_stats64 {
 	/* for cslip etc */
 	__u64	rx_compressed;
 	__u64	tx_compressed;
-
-	__u64	rx_nohandler;		/* dropped, no handler found	*/
+	__u64	rx_nohandler;
 };
 
 /* The struct should be in sync with struct ifmap */
@@ -170,12 +340,29 @@ enum {
 	IFLA_PROP_LIST,
 	IFLA_ALT_IFNAME, /* Alternative ifname */
 	IFLA_PERM_ADDRESS,
+	IFLA_PROTO_DOWN_REASON,
+
+	/* device (sysfs) name as parent, used instead
+	 * of IFLA_LINK where there's no parent netdev
+	 */
+	IFLA_PARENT_DEV_NAME,
+	IFLA_PARENT_DEV_BUS_NAME,
+
 	__IFLA_MAX
 };
 
 
 #define IFLA_MAX (__IFLA_MAX - 1)
 
+enum {
+	IFLA_PROTO_DOWN_REASON_UNSPEC,
+	IFLA_PROTO_DOWN_REASON_MASK,	/* u32, mask for reason bits */
+	IFLA_PROTO_DOWN_REASON_VALUE,   /* u32, reason bit value */
+
+	__IFLA_PROTO_DOWN_REASON_CNT,
+	IFLA_PROTO_DOWN_REASON_MAX = __IFLA_PROTO_DOWN_REASON_CNT - 1
+};
+
 /* backwards compatibility for userspace */
 #ifndef __KERNEL__
 #define IFLA_RTA(r)  ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct ifinfomsg))))
@@ -293,6 +480,7 @@ enum {
 	IFLA_BR_MCAST_MLD_VERSION,
 	IFLA_BR_VLAN_STATS_PER_PORT,
 	IFLA_BR_MULTI_BOOLOPT,
+	IFLA_BR_MCAST_QUERIER_STATE,
 	__IFLA_BR_MAX,
 };
 
@@ -346,6 +534,8 @@ enum {
 	IFLA_BRPORT_BACKUP_PORT,
 	IFLA_BRPORT_MRP_RING_OPEN,
 	IFLA_BRPORT_MRP_IN_OPEN,
+	IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT,
+	IFLA_BRPORT_MCAST_EHT_HOSTS_CNT,
 	__IFLA_BRPORT_MAX
 };
 #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1)
@@ -433,6 +623,7 @@ enum macvlan_macaddr_mode {
 };
 
 #define MACVLAN_FLAG_NOPROMISC	1
+#define MACVLAN_FLAG_NODST	2 /* skip dst macvlan if matching src macvlan */
 
 /* VRF section */
 enum {
@@ -597,6 +788,18 @@ enum ifla_geneve_df {
 	GENEVE_DF_MAX = __GENEVE_DF_END - 1,
 };
 
+/* Bareudp section  */
+enum {
+	IFLA_BAREUDP_UNSPEC,
+	IFLA_BAREUDP_PORT,
+	IFLA_BAREUDP_ETHERTYPE,
+	IFLA_BAREUDP_SRCPORT_MIN,
+	IFLA_BAREUDP_MULTIPROTO_MODE,
+	__IFLA_BAREUDP_MAX
+};
+
+#define IFLA_BAREUDP_MAX (__IFLA_BAREUDP_MAX - 1)
+
 /* PPP section */
 enum {
 	IFLA_PPP_UNSPEC,
@@ -899,7 +1102,14 @@ enum {
 #define IFLA_IPOIB_MAX (__IFLA_IPOIB_MAX - 1)
 
 
-/* HSR section */
+/* HSR/PRP section, both uses same interface */
+
+/* Different redundancy protocols for hsr device */
+enum {
+	HSR_PROTOCOL_HSR,
+	HSR_PROTOCOL_PRP,
+	HSR_PROTOCOL_MAX,
+};
 
 enum {
 	IFLA_HSR_UNSPEC,
@@ -909,6 +1119,9 @@ enum {
 	IFLA_HSR_SUPERVISION_ADDR,	/* Supervision frame multicast addr */
 	IFLA_HSR_SEQ_NR,
 	IFLA_HSR_VERSION,		/* HSR version */
+	IFLA_HSR_PROTOCOL,		/* Indicate different protocol than
+					 * HSR. For example PRP.
+					 */
 	__IFLA_HSR_MAX,
 };
 
@@ -1033,6 +1246,8 @@ enum {
 #define RMNET_FLAGS_INGRESS_MAP_COMMANDS          (1U << 1)
 #define RMNET_FLAGS_INGRESS_MAP_CKSUMV4           (1U << 2)
 #define RMNET_FLAGS_EGRESS_MAP_CKSUMV4            (1U << 3)
+#define RMNET_FLAGS_INGRESS_MAP_CKSUMV5           (1U << 4)
+#define RMNET_FLAGS_EGRESS_MAP_CKSUMV5            (1U << 5)
 
 enum {
 	IFLA_RMNET_UNSPEC,
@@ -1048,4 +1263,14 @@ struct ifla_rmnet_flags {
 	__u32	mask;
 };
 
+/* MCTP section */
+
+enum {
+	IFLA_MCTP_UNSPEC,
+	IFLA_MCTP_NET,
+	__IFLA_MCTP_MAX,
+};
+
+#define IFLA_MCTP_MAX (__IFLA_MCTP_MAX - 1)
+
 #endif /* _UAPI_LINUX_IF_LINK_H */
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index a067410ebea5..1daa45268de2 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -269,6 +269,7 @@ struct kvm_xen_exit {
 #define KVM_EXIT_AP_RESET_HOLD    32
 #define KVM_EXIT_X86_BUS_LOCK     33
 #define KVM_EXIT_XEN              34
+#define KVM_EXIT_RISCV_SBI        35
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
@@ -397,13 +398,23 @@ struct kvm_run {
 		 * "ndata" is correct, that new fields are enumerated in "flags",
 		 * and that each flag enumerates fields that are 64-bit aligned
 		 * and sized (so that ndata+internal.data[] is valid/accurate).
+		 *
+		 * Space beyond the defined fields may be used to store arbitrary
+		 * debug information relating to the emulation failure. It is
+		 * accounted for in "ndata" but the format is unspecified and is
+		 * not represented in "flags". Any such information is *not* ABI!
 		 */
 		struct {
 			__u32 suberror;
 			__u32 ndata;
 			__u64 flags;
-			__u8  insn_size;
-			__u8  insn_bytes[15];
+			union {
+				struct {
+					__u8  insn_size;
+					__u8  insn_bytes[15];
+				};
+			};
+			/* Arbitrary debug data may follow. */
 		} emulation_failure;
 		/* KVM_EXIT_OSI */
 		struct {
@@ -469,6 +480,13 @@ struct kvm_run {
 		} msr;
 		/* KVM_EXIT_XEN */
 		struct kvm_xen_exit xen;
+		/* KVM_EXIT_RISCV_SBI */
+		struct {
+			unsigned long extension_id;
+			unsigned long function_id;
+			unsigned long args[6];
+			unsigned long ret[2];
+		} riscv_sbi;
 		/* Fix the size of the union. */
 		char padding[256];
 	};
@@ -1112,6 +1130,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_BINARY_STATS_FD 203
 #define KVM_CAP_EXIT_ON_EMULATION_FAILURE 204
 #define KVM_CAP_ARM_MTE 205
+#define KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM 206
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1223,11 +1242,16 @@ struct kvm_irqfd {
 
 /* Do not use 1, KVM_CHECK_EXTENSION returned it before we had flags.  */
 #define KVM_CLOCK_TSC_STABLE		2
+#define KVM_CLOCK_REALTIME		(1 << 2)
+#define KVM_CLOCK_HOST_TSC		(1 << 3)
 
 struct kvm_clock_data {
 	__u64 clock;
 	__u32 flags;
-	__u32 pad[9];
+	__u32 pad0;
+	__u64 realtime;
+	__u64 host_tsc;
+	__u32 pad[4];
 };
 
 /* For KVM_CAP_SW_TLB */
diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h
index de45fcd2dcbe..bb73e9a0b24f 100644
--- a/tools/include/uapi/linux/prctl.h
+++ b/tools/include/uapi/linux/prctl.h
@@ -268,5 +268,8 @@ struct prctl_mm_map {
 # define PR_SCHED_CORE_SHARE_TO		2 /* push core_sched cookie to pid */
 # define PR_SCHED_CORE_SHARE_FROM	3 /* pull core_sched cookie to pid */
 # define PR_SCHED_CORE_MAX		4
+# define PR_SCHED_CORE_SCOPE_THREAD		0
+# define PR_SCHED_CORE_SCOPE_THREAD_GROUP	1
+# define PR_SCHED_CORE_SCOPE_PROCESS_GROUP	2
 
 #endif /* _LINUX_PRCTL_H */
diff --git a/tools/include/uapi/sound/asound.h b/tools/include/uapi/sound/asound.h
index 5859ca0a1439..5fbb79e30819 100644
--- a/tools/include/uapi/sound/asound.h
+++ b/tools/include/uapi/sound/asound.h
@@ -1002,7 +1002,7 @@ typedef int __bitwise snd_ctl_elem_iface_t;
 #define SNDRV_CTL_ELEM_ACCESS_WRITE		(1<<1)
 #define SNDRV_CTL_ELEM_ACCESS_READWRITE		(SNDRV_CTL_ELEM_ACCESS_READ|SNDRV_CTL_ELEM_ACCESS_WRITE)
 #define SNDRV_CTL_ELEM_ACCESS_VOLATILE		(1<<2)	/* control value may be changed without a notification */
-// (1 << 3) is unused.
+/* (1 << 3) is unused. */
 #define SNDRV_CTL_ELEM_ACCESS_TLV_READ		(1<<4)	/* TLV read is possible */
 #define SNDRV_CTL_ELEM_ACCESS_TLV_WRITE		(1<<5)	/* TLV write is possible */
 #define SNDRV_CTL_ELEM_ACCESS_TLV_READWRITE	(SNDRV_CTL_ELEM_ACCESS_TLV_READ|SNDRV_CTL_ELEM_ACCESS_TLV_WRITE)
diff --git a/tools/lib/bpf/bpf_gen_internal.h b/tools/lib/bpf/bpf_gen_internal.h
index d26e5472fe50..6f3df004479b 100644
--- a/tools/lib/bpf/bpf_gen_internal.h
+++ b/tools/lib/bpf/bpf_gen_internal.h
@@ -45,8 +45,8 @@ struct bpf_gen {
 	int nr_fd_array;
 };
 
-void bpf_gen__init(struct bpf_gen *gen, int log_level);
-int bpf_gen__finish(struct bpf_gen *gen);
+void bpf_gen__init(struct bpf_gen *gen, int log_level, int nr_progs, int nr_maps);
+int bpf_gen__finish(struct bpf_gen *gen, int nr_progs, int nr_maps);
 void bpf_gen__free(struct bpf_gen *gen);
 void bpf_gen__load_btf(struct bpf_gen *gen, const void *raw_data, __u32 raw_size);
 void bpf_gen__map_create(struct bpf_gen *gen, struct bpf_create_map_params *map_attr, int map_idx);
diff --git a/tools/lib/bpf/gen_loader.c b/tools/lib/bpf/gen_loader.c
index 502dea53a742..9934851ccde7 100644
--- a/tools/lib/bpf/gen_loader.c
+++ b/tools/lib/bpf/gen_loader.c
@@ -18,7 +18,7 @@
 #define MAX_USED_MAPS	64
 #define MAX_USED_PROGS	32
 #define MAX_KFUNC_DESCS 256
-#define MAX_FD_ARRAY_SZ (MAX_USED_PROGS + MAX_KFUNC_DESCS)
+#define MAX_FD_ARRAY_SZ (MAX_USED_MAPS + MAX_KFUNC_DESCS)
 
 /* The following structure describes the stack layout of the loader program.
  * In addition R6 contains the pointer to context.
@@ -33,8 +33,8 @@
  */
 struct loader_stack {
 	__u32 btf_fd;
-	__u32 prog_fd[MAX_USED_PROGS];
 	__u32 inner_map_fd;
+	__u32 prog_fd[MAX_USED_PROGS];
 };
 
 #define stack_off(field) \
@@ -42,6 +42,11 @@ struct loader_stack {
 
 #define attr_field(attr, field) (attr + offsetof(union bpf_attr, field))
 
+static int blob_fd_array_off(struct bpf_gen *gen, int index)
+{
+	return gen->fd_array + index * sizeof(int);
+}
+
 static int realloc_insn_buf(struct bpf_gen *gen, __u32 size)
 {
 	size_t off = gen->insn_cur - gen->insn_start;
@@ -102,11 +107,15 @@ static void emit2(struct bpf_gen *gen, struct bpf_insn insn1, struct bpf_insn in
 	emit(gen, insn2);
 }
 
-void bpf_gen__init(struct bpf_gen *gen, int log_level)
+static int add_data(struct bpf_gen *gen, const void *data, __u32 size);
+static void emit_sys_close_blob(struct bpf_gen *gen, int blob_off);
+
+void bpf_gen__init(struct bpf_gen *gen, int log_level, int nr_progs, int nr_maps)
 {
-	size_t stack_sz = sizeof(struct loader_stack);
+	size_t stack_sz = sizeof(struct loader_stack), nr_progs_sz;
 	int i;
 
+	gen->fd_array = add_data(gen, NULL, MAX_FD_ARRAY_SZ * sizeof(int));
 	gen->log_level = log_level;
 	/* save ctx pointer into R6 */
 	emit(gen, BPF_MOV64_REG(BPF_REG_6, BPF_REG_1));
@@ -118,19 +127,27 @@ void bpf_gen__init(struct bpf_gen *gen, int log_level)
 	emit(gen, BPF_MOV64_IMM(BPF_REG_3, 0));
 	emit(gen, BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel));
 
+	/* amount of stack actually used, only used to calculate iterations, not stack offset */
+	nr_progs_sz = offsetof(struct loader_stack, prog_fd[nr_progs]);
 	/* jump over cleanup code */
 	emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0,
-			      /* size of cleanup code below */
-			      (stack_sz / 4) * 3 + 2));
+			      /* size of cleanup code below (including map fd cleanup) */
+			      (nr_progs_sz / 4) * 3 + 2 +
+			      /* 6 insns for emit_sys_close_blob,
+			       * 6 insns for debug_regs in emit_sys_close_blob
+			       */
+			      nr_maps * (6 + (gen->log_level ? 6 : 0))));
 
 	/* remember the label where all error branches will jump to */
 	gen->cleanup_label = gen->insn_cur - gen->insn_start;
 	/* emit cleanup code: close all temp FDs */
-	for (i = 0; i < stack_sz; i += 4) {
+	for (i = 0; i < nr_progs_sz; i += 4) {
 		emit(gen, BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_10, -stack_sz + i));
 		emit(gen, BPF_JMP_IMM(BPF_JSLE, BPF_REG_1, 0, 1));
 		emit(gen, BPF_EMIT_CALL(BPF_FUNC_sys_close));
 	}
+	for (i = 0; i < nr_maps; i++)
+		emit_sys_close_blob(gen, blob_fd_array_off(gen, i));
 	/* R7 contains the error code from sys_bpf. Copy it into R0 and exit. */
 	emit(gen, BPF_MOV64_REG(BPF_REG_0, BPF_REG_7));
 	emit(gen, BPF_EXIT_INSN());
@@ -160,8 +177,6 @@ static int add_data(struct bpf_gen *gen, const void *data, __u32 size)
  */
 static int add_map_fd(struct bpf_gen *gen)
 {
-	if (!gen->fd_array)
-		gen->fd_array = add_data(gen, NULL, MAX_FD_ARRAY_SZ * sizeof(int));
 	if (gen->nr_maps == MAX_USED_MAPS) {
 		pr_warn("Total maps exceeds %d\n", MAX_USED_MAPS);
 		gen->error = -E2BIG;
@@ -174,8 +189,6 @@ static int add_kfunc_btf_fd(struct bpf_gen *gen)
 {
 	int cur;
 
-	if (!gen->fd_array)
-		gen->fd_array = add_data(gen, NULL, MAX_FD_ARRAY_SZ * sizeof(int));
 	if (gen->nr_fd_array == MAX_KFUNC_DESCS) {
 		cur = add_data(gen, NULL, sizeof(int));
 		return (cur - gen->fd_array) / sizeof(int);
@@ -183,11 +196,6 @@ static int add_kfunc_btf_fd(struct bpf_gen *gen)
 	return MAX_USED_MAPS + gen->nr_fd_array++;
 }
 
-static int blob_fd_array_off(struct bpf_gen *gen, int index)
-{
-	return gen->fd_array + index * sizeof(int);
-}
-
 static int insn_bytes_to_bpf_size(__u32 sz)
 {
 	switch (sz) {
@@ -359,10 +367,15 @@ static void emit_sys_close_blob(struct bpf_gen *gen, int blob_off)
 	__emit_sys_close(gen);
 }
 
-int bpf_gen__finish(struct bpf_gen *gen)
+int bpf_gen__finish(struct bpf_gen *gen, int nr_progs, int nr_maps)
 {
 	int i;
 
+	if (nr_progs != gen->nr_progs || nr_maps != gen->nr_maps) {
+		pr_warn("progs/maps mismatch\n");
+		gen->error = -EFAULT;
+		return gen->error;
+	}
 	emit_sys_close_stack(gen, stack_off(btf_fd));
 	for (i = 0; i < gen->nr_progs; i++)
 		move_stack2ctx(gen,
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index a1bea1953df6..7c74342bb668 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -7258,7 +7258,7 @@ int bpf_object__load_xattr(struct bpf_object_load_attr *attr)
 	}
 
 	if (obj->gen_loader)
-		bpf_gen__init(obj->gen_loader, attr->log_level);
+		bpf_gen__init(obj->gen_loader, attr->log_level, obj->nr_programs, obj->nr_maps);
 
 	err = bpf_object__probe_loading(obj);
 	err = err ? : bpf_object__load_vmlinux_btf(obj, false);
@@ -7277,7 +7277,7 @@ int bpf_object__load_xattr(struct bpf_object_load_attr *attr)
 		for (i = 0; i < obj->nr_maps; i++)
 			obj->maps[i].fd = -1;
 		if (!err)
-			err = bpf_gen__finish(obj->gen_loader);
+			err = bpf_gen__finish(obj->gen_loader, obj->nr_programs, obj->nr_maps);
 	}
 
 	/* clean up fd_array */
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index add39902166d..21735829b860 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -3310,6 +3310,9 @@ static bool ignore_unreachable_insn(struct objtool_file *file, struct instructio
 	if (!insn->func)
 		return false;
 
+	if (insn->func->static_call_tramp)
+		return true;
+
 	/*
 	 * CONFIG_UBSAN_TRAP inserts a UD2 when it sees
 	 * __builtin_unreachable().  The BUG() macro has an unreachable() after
diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c
index 81a4c543ff7e..4b384c907027 100644
--- a/tools/objtool/elf.c
+++ b/tools/objtool/elf.c
@@ -375,6 +375,7 @@ static int read_symbols(struct elf *elf)
 			return -1;
 		}
 		memset(sym, 0, sizeof(*sym));
+		INIT_LIST_HEAD(&sym->pv_target);
 		sym->alias = sym;
 
 		sym->idx = i;
diff --git a/tools/objtool/objtool.c b/tools/objtool/objtool.c
index c90c7084e45a..bdf699f6552b 100644
--- a/tools/objtool/objtool.c
+++ b/tools/objtool/objtool.c
@@ -153,6 +153,10 @@ void objtool_pv_add(struct objtool_file *f, int idx, struct symbol *func)
 	    !strcmp(func->name, "_paravirt_ident_64"))
 		return;
 
+	/* already added this function */
+	if (!list_empty(&func->pv_target))
+		return;
+
 	list_add(&func->pv_target, &f->pv_ops[idx].targets);
 	f->pv_ops[idx].clean = false;
 }
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 2d7df8703cf2..3cf7bac67239 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -469,7 +469,7 @@ This option sets the time out limit. The default value is 500 ms.
 
 --switch-events::
 Record context switch events i.e. events of type PERF_RECORD_SWITCH or
-PERF_RECORD_SWITCH_CPU_WIDE. In some cases (e.g. Intel PT or CoreSight)
+PERF_RECORD_SWITCH_CPU_WIDE. In some cases (e.g. Intel PT, CoreSight or Arm SPE)
 switch events will be enabled automatically, which can be suppressed by
 by the option --no-switch-events.
 
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 07e65a061fd3..3df74cf5651a 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -271,8 +271,6 @@ endif
 
 FEATURE_CHECK_CFLAGS-libpython := $(PYTHON_EMBED_CCOPTS)
 FEATURE_CHECK_LDFLAGS-libpython := $(PYTHON_EMBED_LDOPTS)
-FEATURE_CHECK_CFLAGS-libpython-version := $(PYTHON_EMBED_CCOPTS)
-FEATURE_CHECK_LDFLAGS-libpython-version := $(PYTHON_EMBED_LDOPTS)
 
 FEATURE_CHECK_LDFLAGS-libaio = -lrt
 
@@ -1010,6 +1008,9 @@ ifndef NO_AUXTRACE
   ifndef NO_AUXTRACE
     $(call detected,CONFIG_AUXTRACE)
     CFLAGS += -DHAVE_AUXTRACE_SUPPORT
+    ifeq ($(feature-reallocarray), 0)
+      CFLAGS += -DCOMPAT_NEED_REALLOCARRAY
+    endif
   endif
 endif
 
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 0777748b6da8..80522bcfafe0 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -516,17 +516,17 @@ kvm_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/kvm_ioctl.sh
 $(kvm_ioctl_array): $(kvm_hdr_dir)/kvm.h $(kvm_ioctl_tbl)
 	$(Q)$(SHELL) '$(kvm_ioctl_tbl)' $(kvm_hdr_dir) > $@
 
-socket_ipproto_array := $(beauty_outdir)/socket_ipproto_array.c
-socket_ipproto_tbl := $(srctree)/tools/perf/trace/beauty/socket_ipproto.sh
+socket_arrays := $(beauty_outdir)/socket.c
+socket_tbl := $(srctree)/tools/perf/trace/beauty/socket.sh
 
-$(socket_ipproto_array): $(linux_uapi_dir)/in.h $(socket_ipproto_tbl)
-	$(Q)$(SHELL) '$(socket_ipproto_tbl)' $(linux_uapi_dir) > $@
+$(socket_arrays): $(linux_uapi_dir)/in.h $(beauty_linux_dir)/socket.h $(socket_tbl)
+	$(Q)$(SHELL) '$(socket_tbl)' $(linux_uapi_dir) $(beauty_linux_dir) > $@
 
-socket_arrays := $(beauty_outdir)/socket_arrays.c
-socket_tbl := $(srctree)/tools/perf/trace/beauty/socket.sh
+sockaddr_arrays := $(beauty_outdir)/sockaddr.c
+sockaddr_tbl := $(srctree)/tools/perf/trace/beauty/sockaddr.sh
 
-$(socket_arrays): $(beauty_linux_dir)/socket.h $(socket_tbl)
-	$(Q)$(SHELL) '$(socket_tbl)' $(beauty_linux_dir) > $@
+$(sockaddr_arrays): $(beauty_linux_dir)/socket.h $(sockaddr_tbl)
+	$(Q)$(SHELL) '$(sockaddr_tbl)' $(beauty_linux_dir) > $@
 
 vhost_virtio_ioctl_array := $(beauty_ioctl_outdir)/vhost_virtio_ioctl_array.c
 vhost_virtio_hdr_dir := $(srctree)/tools/include/uapi/linux
@@ -736,8 +736,8 @@ prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h archheaders $(drm_ioc
 	$(sndrv_ctl_ioctl_array) \
 	$(kcmp_type_array) \
 	$(kvm_ioctl_array) \
-	$(socket_ipproto_array) \
 	$(socket_arrays) \
+	$(sockaddr_arrays) \
 	$(vhost_virtio_ioctl_array) \
 	$(madvise_behavior_array) \
 	$(mmap_flags_array) \
@@ -1113,8 +1113,8 @@ clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clea
 		$(OUTPUT)$(sndrv_pcm_ioctl_array) \
 		$(OUTPUT)$(kvm_ioctl_array) \
 		$(OUTPUT)$(kcmp_type_array) \
-		$(OUTPUT)$(socket_ipproto_array) \
 		$(OUTPUT)$(socket_arrays) \
+		$(OUTPUT)$(sockaddr_arrays) \
 		$(OUTPUT)$(vhost_virtio_ioctl_array) \
 		$(OUTPUT)$(perf_ioctl_array) \
 		$(OUTPUT)$(prctl_option_array) \
diff --git a/tools/perf/arch/arm/include/arch-tests.h b/tools/perf/arch/arm/include/arch-tests.h
index c62538052404..452b3d904521 100644
--- a/tools/perf/arch/arm/include/arch-tests.h
+++ b/tools/perf/arch/arm/include/arch-tests.h
@@ -2,6 +2,6 @@
 #ifndef ARCH_TESTS_H
 #define ARCH_TESTS_H
 
-extern struct test arch_tests[];
+extern struct test_suite *arch_tests[];
 
 #endif
diff --git a/tools/perf/arch/arm/tests/arch-tests.c b/tools/perf/arch/arm/tests/arch-tests.c
index 6848101a855f..69561111cc6f 100644
--- a/tools/perf/arch/arm/tests/arch-tests.c
+++ b/tools/perf/arch/arm/tests/arch-tests.c
@@ -3,18 +3,10 @@
 #include "tests/tests.h"
 #include "arch-tests.h"
 
-struct test arch_tests[] = {
+struct test_suite *arch_tests[] = {
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
-	{
-		.desc = "DWARF unwind",
-		.func = test__dwarf_unwind,
-	},
+	&suite__dwarf_unwind,
 #endif
-	{
-		.desc = "Vectors page",
-		.func = test__vectors_page,
-	},
-	{
-		.func = NULL,
-	},
+	&suite__vectors_page,
+	NULL,
 };
diff --git a/tools/perf/arch/arm/tests/vectors-page.c b/tools/perf/arch/arm/tests/vectors-page.c
index 7ffdd79971c8..55a835837466 100644
--- a/tools/perf/arch/arm/tests/vectors-page.c
+++ b/tools/perf/arch/arm/tests/vectors-page.c
@@ -9,8 +9,7 @@
 
 #define VECTORS__MAP_NAME "[vectors]"
 
-int test__vectors_page(struct test *test __maybe_unused,
-		       int subtest __maybe_unused)
+static int test__vectors_page(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 	void *start, *end;
 
@@ -22,3 +21,5 @@ int test__vectors_page(struct test *test __maybe_unused,
 
 	return TEST_OK;
 }
+
+DEFINE_SUITE("Vectors page", vectors_page);
diff --git a/tools/perf/arch/arm64/include/arch-tests.h b/tools/perf/arch/arm64/include/arch-tests.h
index c62538052404..452b3d904521 100644
--- a/tools/perf/arch/arm64/include/arch-tests.h
+++ b/tools/perf/arch/arm64/include/arch-tests.h
@@ -2,6 +2,6 @@
 #ifndef ARCH_TESTS_H
 #define ARCH_TESTS_H
 
-extern struct test arch_tests[];
+extern struct test_suite *arch_tests[];
 
 #endif
diff --git a/tools/perf/arch/arm64/tests/arch-tests.c b/tools/perf/arch/arm64/tests/arch-tests.c
index 5b1543c98022..ad16b4f8f63e 100644
--- a/tools/perf/arch/arm64/tests/arch-tests.c
+++ b/tools/perf/arch/arm64/tests/arch-tests.c
@@ -3,14 +3,9 @@
 #include "tests/tests.h"
 #include "arch-tests.h"
 
-struct test arch_tests[] = {
+struct test_suite *arch_tests[] = {
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
-	{
-		.desc = "DWARF unwind",
-		.func = test__dwarf_unwind,
-	},
+	&suite__dwarf_unwind,
 #endif
-	{
-		.func = NULL,
-	},
+	NULL,
 };
diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c
index a4420d4df503..2100d46ccf5e 100644
--- a/tools/perf/arch/arm64/util/arm-spe.c
+++ b/tools/perf/arch/arm64/util/arm-spe.c
@@ -23,6 +23,7 @@
 #include "../../../util/auxtrace.h"
 #include "../../../util/record.h"
 #include "../../../util/arm-spe.h"
+#include <tools/libc_compat.h> // reallocarray
 
 #define KiB(x) ((x) * 1024)
 #define MiB(x) ((x) * 1024 * 1024)
@@ -31,6 +32,8 @@ struct arm_spe_recording {
 	struct auxtrace_record		itr;
 	struct perf_pmu			*arm_spe_pmu;
 	struct evlist		*evlist;
+	int			wrapped_cnt;
+	bool			*wrapped;
 };
 
 static void arm_spe_set_timestamp(struct auxtrace_record *itr,
@@ -84,6 +87,55 @@ static int arm_spe_info_fill(struct auxtrace_record *itr,
 	return 0;
 }
 
+static void
+arm_spe_snapshot_resolve_auxtrace_defaults(struct record_opts *opts,
+					   bool privileged)
+{
+	/*
+	 * The default snapshot size is the auxtrace mmap size. If neither auxtrace mmap size nor
+	 * snapshot size is specified, then the default is 4MiB for privileged users, 128KiB for
+	 * unprivileged users.
+	 *
+	 * The default auxtrace mmap size is 4MiB/page_size for privileged users, 128KiB for
+	 * unprivileged users. If an unprivileged user does not specify mmap pages, the mmap pages
+	 * will be reduced from the default 512KiB/page_size to 256KiB/page_size, otherwise the
+	 * user is likely to get an error as they exceed their mlock limmit.
+	 */
+
+	/*
+	 * No size were given to '-S' or '-m,', so go with the default
+	 */
+	if (!opts->auxtrace_snapshot_size && !opts->auxtrace_mmap_pages) {
+		if (privileged) {
+			opts->auxtrace_mmap_pages = MiB(4) / page_size;
+		} else {
+			opts->auxtrace_mmap_pages = KiB(128) / page_size;
+			if (opts->mmap_pages == UINT_MAX)
+				opts->mmap_pages = KiB(256) / page_size;
+		}
+	} else if (!opts->auxtrace_mmap_pages && !privileged && opts->mmap_pages == UINT_MAX) {
+		opts->mmap_pages = KiB(256) / page_size;
+	}
+
+	/*
+	 * '-m,xyz' was specified but no snapshot size, so make the snapshot size as big as the
+	 * auxtrace mmap area.
+	 */
+	if (!opts->auxtrace_snapshot_size)
+		opts->auxtrace_snapshot_size = opts->auxtrace_mmap_pages * (size_t)page_size;
+
+	/*
+	 * '-Sxyz' was specified but no auxtrace mmap area, so make the auxtrace mmap area big
+	 * enough to fit the requested snapshot size.
+	 */
+	if (!opts->auxtrace_mmap_pages) {
+		size_t sz = opts->auxtrace_snapshot_size;
+
+		sz = round_up(sz, page_size) / page_size;
+		opts->auxtrace_mmap_pages = roundup_pow_of_two(sz);
+	}
+}
+
 static int arm_spe_recording_options(struct auxtrace_record *itr,
 				     struct evlist *evlist,
 				     struct record_opts *opts)
@@ -115,6 +167,36 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
 	if (!opts->full_auxtrace)
 		return 0;
 
+	/*
+	 * we are in snapshot mode.
+	 */
+	if (opts->auxtrace_snapshot_mode) {
+		/*
+		 * Command arguments '-Sxyz' and/or '-m,xyz' are missing, so fill those in with
+		 * default values.
+		 */
+		if (!opts->auxtrace_snapshot_size || !opts->auxtrace_mmap_pages)
+			arm_spe_snapshot_resolve_auxtrace_defaults(opts, privileged);
+
+		/*
+		 * Snapshot size can't be bigger than the auxtrace area.
+		 */
+		if (opts->auxtrace_snapshot_size > opts->auxtrace_mmap_pages * (size_t)page_size) {
+			pr_err("Snapshot size %zu must not be greater than AUX area tracing mmap size %zu\n",
+			       opts->auxtrace_snapshot_size,
+			       opts->auxtrace_mmap_pages * (size_t)page_size);
+			return -EINVAL;
+		}
+
+		/*
+		 * Something went wrong somewhere - this shouldn't happen.
+		 */
+		if (!opts->auxtrace_snapshot_size || !opts->auxtrace_mmap_pages) {
+			pr_err("Failed to calculate default snapshot size and/or AUX area tracing mmap pages\n");
+			return -EINVAL;
+		}
+	}
+
 	/* We are in full trace mode but '-m,xyz' wasn't specified */
 	if (!opts->auxtrace_mmap_pages) {
 		if (privileged) {
@@ -138,6 +220,9 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
 		}
 	}
 
+	if (opts->auxtrace_snapshot_mode)
+		pr_debug2("%sx snapshot size: %zu\n", ARM_SPE_PMU_NAME,
+			  opts->auxtrace_snapshot_size);
 
 	/*
 	 * To obtain the auxtrace buffer file descriptor, the auxtrace event
@@ -166,8 +251,199 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
 	tracking_evsel->core.attr.sample_period = 1;
 
 	/* In per-cpu case, always need the time of mmap events etc */
-	if (!perf_cpu_map__empty(cpus))
+	if (!perf_cpu_map__empty(cpus)) {
 		evsel__set_sample_bit(tracking_evsel, TIME);
+		evsel__set_sample_bit(tracking_evsel, CPU);
+
+		/* also track task context switch */
+		if (!record_opts__no_switch_events(opts))
+			tracking_evsel->core.attr.context_switch = 1;
+	}
+
+	return 0;
+}
+
+static int arm_spe_parse_snapshot_options(struct auxtrace_record *itr __maybe_unused,
+					 struct record_opts *opts,
+					 const char *str)
+{
+	unsigned long long snapshot_size = 0;
+	char *endptr;
+
+	if (str) {
+		snapshot_size = strtoull(str, &endptr, 0);
+		if (*endptr || snapshot_size > SIZE_MAX)
+			return -1;
+	}
+
+	opts->auxtrace_snapshot_mode = true;
+	opts->auxtrace_snapshot_size = snapshot_size;
+
+	return 0;
+}
+
+static int arm_spe_snapshot_start(struct auxtrace_record *itr)
+{
+	struct arm_spe_recording *ptr =
+			container_of(itr, struct arm_spe_recording, itr);
+	struct evsel *evsel;
+
+	evlist__for_each_entry(ptr->evlist, evsel) {
+		if (evsel->core.attr.type == ptr->arm_spe_pmu->type)
+			return evsel__disable(evsel);
+	}
+	return -EINVAL;
+}
+
+static int arm_spe_snapshot_finish(struct auxtrace_record *itr)
+{
+	struct arm_spe_recording *ptr =
+			container_of(itr, struct arm_spe_recording, itr);
+	struct evsel *evsel;
+
+	evlist__for_each_entry(ptr->evlist, evsel) {
+		if (evsel->core.attr.type == ptr->arm_spe_pmu->type)
+			return evsel__enable(evsel);
+	}
+	return -EINVAL;
+}
+
+static int arm_spe_alloc_wrapped_array(struct arm_spe_recording *ptr, int idx)
+{
+	bool *wrapped;
+	int cnt = ptr->wrapped_cnt, new_cnt, i;
+
+	/*
+	 * No need to allocate, so return early.
+	 */
+	if (idx < cnt)
+		return 0;
+
+	/*
+	 * Make ptr->wrapped as big as idx.
+	 */
+	new_cnt = idx + 1;
+
+	/*
+	 * Free'ed in arm_spe_recording_free().
+	 */
+	wrapped = reallocarray(ptr->wrapped, new_cnt, sizeof(bool));
+	if (!wrapped)
+		return -ENOMEM;
+
+	/*
+	 * init new allocated values.
+	 */
+	for (i = cnt; i < new_cnt; i++)
+		wrapped[i] = false;
+
+	ptr->wrapped_cnt = new_cnt;
+	ptr->wrapped = wrapped;
+
+	return 0;
+}
+
+static bool arm_spe_buffer_has_wrapped(unsigned char *buffer,
+				      size_t buffer_size, u64 head)
+{
+	u64 i, watermark;
+	u64 *buf = (u64 *)buffer;
+	size_t buf_size = buffer_size;
+
+	/*
+	 * Defensively handle the case where head might be continually increasing - if its value is
+	 * equal or greater than the size of the ring buffer, then we can safely determine it has
+	 * wrapped around. Otherwise, continue to detect if head might have wrapped.
+	 */
+	if (head >= buffer_size)
+		return true;
+
+	/*
+	 * We want to look the very last 512 byte (chosen arbitrarily) in the ring buffer.
+	 */
+	watermark = buf_size - 512;
+
+	/*
+	 * The value of head is somewhere within the size of the ring buffer. This can be that there
+	 * hasn't been enough data to fill the ring buffer yet or the trace time was so long that
+	 * head has numerically wrapped around.  To find we need to check if we have data at the
+	 * very end of the ring buffer.  We can reliably do this because mmap'ed pages are zeroed
+	 * out and there is a fresh mapping with every new session.
+	 */
+
+	/*
+	 * head is less than 512 byte from the end of the ring buffer.
+	 */
+	if (head > watermark)
+		watermark = head;
+
+	/*
+	 * Speed things up by using 64 bit transactions (see "u64 *buf" above)
+	 */
+	watermark /= sizeof(u64);
+	buf_size /= sizeof(u64);
+
+	/*
+	 * If we find trace data at the end of the ring buffer, head has been there and has
+	 * numerically wrapped around at least once.
+	 */
+	for (i = watermark; i < buf_size; i++)
+		if (buf[i])
+			return true;
+
+	return false;
+}
+
+static int arm_spe_find_snapshot(struct auxtrace_record *itr, int idx,
+				  struct auxtrace_mmap *mm, unsigned char *data,
+				  u64 *head, u64 *old)
+{
+	int err;
+	bool wrapped;
+	struct arm_spe_recording *ptr =
+			container_of(itr, struct arm_spe_recording, itr);
+
+	/*
+	 * Allocate memory to keep track of wrapping if this is the first
+	 * time we deal with this *mm.
+	 */
+	if (idx >= ptr->wrapped_cnt) {
+		err = arm_spe_alloc_wrapped_array(ptr, idx);
+		if (err)
+			return err;
+	}
+
+	/*
+	 * Check to see if *head has wrapped around.  If it hasn't only the
+	 * amount of data between *head and *old is snapshot'ed to avoid
+	 * bloating the perf.data file with zeros.  But as soon as *head has
+	 * wrapped around the entire size of the AUX ring buffer it taken.
+	 */
+	wrapped = ptr->wrapped[idx];
+	if (!wrapped && arm_spe_buffer_has_wrapped(data, mm->len, *head)) {
+		wrapped = true;
+		ptr->wrapped[idx] = true;
+	}
+
+	pr_debug3("%s: mmap index %d old head %zu new head %zu size %zu\n",
+		  __func__, idx, (size_t)*old, (size_t)*head, mm->len);
+
+	/*
+	 * No wrap has occurred, we can just use *head and *old.
+	 */
+	if (!wrapped)
+		return 0;
+
+	/*
+	 * *head has wrapped around - adjust *head and *old to pickup the
+	 * entire content of the AUX buffer.
+	 */
+	if (*head >= mm->len) {
+		*old = *head - mm->len;
+	} else {
+		*head += mm->len;
+		*old = *head - mm->len;
+	}
 
 	return 0;
 }
@@ -186,6 +462,7 @@ static void arm_spe_recording_free(struct auxtrace_record *itr)
 	struct arm_spe_recording *sper =
 			container_of(itr, struct arm_spe_recording, itr);
 
+	free(sper->wrapped);
 	free(sper);
 }
 
@@ -207,6 +484,10 @@ struct auxtrace_record *arm_spe_recording_init(int *err,
 
 	sper->arm_spe_pmu = arm_spe_pmu;
 	sper->itr.pmu = arm_spe_pmu;
+	sper->itr.snapshot_start = arm_spe_snapshot_start;
+	sper->itr.snapshot_finish = arm_spe_snapshot_finish;
+	sper->itr.find_snapshot = arm_spe_find_snapshot;
+	sper->itr.parse_snapshot_options = arm_spe_parse_snapshot_options;
 	sper->itr.recording_options = arm_spe_recording_options;
 	sper->itr.info_priv_size = arm_spe_info_priv_size;
 	sper->itr.info_fill = arm_spe_info_fill;
diff --git a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
index 1ca7bc337932..e2c481fcede6 100644
--- a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
+++ b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
@@ -363,3 +363,4 @@
 446	n64	landlock_restrict_self		sys_landlock_restrict_self
 # 447 reserved for memfd_secret
 448	n64	process_mrelease		sys_process_mrelease
+449	n64	futex_waitv			sys_futex_waitv
diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
index 7bef917cc84e..15109af9d075 100644
--- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
@@ -528,3 +528,4 @@
 446	common	landlock_restrict_self		sys_landlock_restrict_self
 # 447 reserved for memfd_secret
 448	common	process_mrelease		sys_process_mrelease
+449	common  futex_waitv                     sys_futex_waitv
diff --git a/tools/perf/arch/powerpc/include/arch-tests.h b/tools/perf/arch/powerpc/include/arch-tests.h
index c62538052404..452b3d904521 100644
--- a/tools/perf/arch/powerpc/include/arch-tests.h
+++ b/tools/perf/arch/powerpc/include/arch-tests.h
@@ -2,6 +2,6 @@
 #ifndef ARCH_TESTS_H
 #define ARCH_TESTS_H
 
-extern struct test arch_tests[];
+extern struct test_suite *arch_tests[];
 
 #endif
diff --git a/tools/perf/arch/powerpc/tests/arch-tests.c b/tools/perf/arch/powerpc/tests/arch-tests.c
index 8c3fbd4af817..eb98c57b5aeb 100644
--- a/tools/perf/arch/powerpc/tests/arch-tests.c
+++ b/tools/perf/arch/powerpc/tests/arch-tests.c
@@ -3,14 +3,10 @@
 #include "tests/tests.h"
 #include "arch-tests.h"
 
-struct test arch_tests[] = {
+
+struct test_suite *arch_tests[] = {
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
-	{
-		.desc = "Test dwarf unwind",
-		.func = test__dwarf_unwind,
-	},
+	&suite__dwarf_unwind,
 #endif
-	{
-		.func = NULL,
-	},
+	NULL,
 };
diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
index df5261e5cfe1..ed9c5c2eafad 100644
--- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
@@ -451,3 +451,4 @@
 446  common	landlock_restrict_self	sys_landlock_restrict_self	sys_landlock_restrict_self
 # 447 reserved for memfd_secret
 448  common	process_mrelease	sys_process_mrelease		sys_process_mrelease
+449  common	futex_waitv		sys_futex_waitv			sys_futex_waitv
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index 18b5500ea8bf..fe8f8dd157b4 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -370,6 +370,7 @@
 446	common	landlock_restrict_self	sys_landlock_restrict_self
 447	common	memfd_secret		sys_memfd_secret
 448	common	process_mrelease	sys_process_mrelease
+449	common	futex_waitv		sys_futex_waitv
 
 #
 # Due to a historical design error, certain syscalls are numbered differently
diff --git a/tools/perf/arch/x86/include/arch-tests.h b/tools/perf/arch/x86/include/arch-tests.h
index 9599e7a3f1af..6a1a1b3c0827 100644
--- a/tools/perf/arch/x86/include/arch-tests.h
+++ b/tools/perf/arch/x86/include/arch-tests.h
@@ -2,15 +2,15 @@
 #ifndef ARCH_TESTS_H
 #define ARCH_TESTS_H
 
-struct test;
+struct test_suite;
 
 /* Tests */
-int test__rdpmc(struct test *test, int subtest);
-int test__insn_x86(struct test *test, int subtest);
-int test__intel_pt_pkt_decoder(struct test *test, int subtest);
-int test__bp_modify(struct test *test, int subtest);
-int test__x86_sample_parsing(struct test *test, int subtest);
+int test__rdpmc(struct test_suite *test, int subtest);
+int test__insn_x86(struct test_suite *test, int subtest);
+int test__intel_pt_pkt_decoder(struct test_suite *test, int subtest);
+int test__bp_modify(struct test_suite *test, int subtest);
+int test__x86_sample_parsing(struct test_suite *test, int subtest);
 
-extern struct test arch_tests[];
+extern struct test_suite *arch_tests[];
 
 #endif
diff --git a/tools/perf/arch/x86/tests/arch-tests.c b/tools/perf/arch/x86/tests/arch-tests.c
index 71aa67367ad6..64fb73d14d2f 100644
--- a/tools/perf/arch/x86/tests/arch-tests.c
+++ b/tools/perf/arch/x86/tests/arch-tests.c
@@ -3,39 +3,28 @@
 #include "tests/tests.h"
 #include "arch-tests.h"
 
-struct test arch_tests[] = {
-	{
-		.desc = "x86 rdpmc",
-		.func = test__rdpmc,
-	},
+DEFINE_SUITE("x86 rdpmc", rdpmc);
+#ifdef HAVE_AUXTRACE_SUPPORT
+DEFINE_SUITE("x86 instruction decoder - new instructions", insn_x86);
+DEFINE_SUITE("Intel PT packet decoder", intel_pt_pkt_decoder);
+#endif
+#if defined(__x86_64__)
+DEFINE_SUITE("x86 bp modify", bp_modify);
+#endif
+DEFINE_SUITE("x86 Sample parsing", x86_sample_parsing);
+
+struct test_suite *arch_tests[] = {
+	&suite__rdpmc,
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
-	{
-		.desc = "DWARF unwind",
-		.func = test__dwarf_unwind,
-	},
+	&suite__dwarf_unwind,
 #endif
 #ifdef HAVE_AUXTRACE_SUPPORT
-	{
-		.desc = "x86 instruction decoder - new instructions",
-		.func = test__insn_x86,
-	},
-	{
-		.desc = "Intel PT packet decoder",
-		.func = test__intel_pt_pkt_decoder,
-	},
+	&suite__insn_x86,
+	&suite__intel_pt_pkt_decoder,
 #endif
 #if defined(__x86_64__)
-	{
-		.desc = "x86 bp modify",
-		.func = test__bp_modify,
-	},
+	&suite__bp_modify,
 #endif
-	{
-		.desc = "x86 Sample parsing",
-		.func = test__x86_sample_parsing,
-	},
-	{
-		.func = NULL,
-	},
-
+	&suite__x86_sample_parsing,
+	NULL,
 };
diff --git a/tools/perf/arch/x86/tests/bp-modify.c b/tools/perf/arch/x86/tests/bp-modify.c
index dffcf9b52153..0924ccd9e36d 100644
--- a/tools/perf/arch/x86/tests/bp-modify.c
+++ b/tools/perf/arch/x86/tests/bp-modify.c
@@ -204,7 +204,7 @@ out:
 	return rip == (unsigned long) bp_1 ? TEST_OK : TEST_FAIL;
 }
 
-int test__bp_modify(struct test *test __maybe_unused,
+int test__bp_modify(struct test_suite *test __maybe_unused,
 		    int subtest __maybe_unused)
 {
 	TEST_ASSERT_VAL("modify test 1 failed\n", !bp_modify1());
diff --git a/tools/perf/arch/x86/tests/insn-x86.c b/tools/perf/arch/x86/tests/insn-x86.c
index 0262b0d8ccf5..94b490c434d0 100644
--- a/tools/perf/arch/x86/tests/insn-x86.c
+++ b/tools/perf/arch/x86/tests/insn-x86.c
@@ -173,7 +173,7 @@ static int test_data_set(struct test_data *dat_set, int x86_64)
  * verbose (-v) option to see all the instructions and whether or not they
  * decoded successfully.
  */
-int test__insn_x86(struct test *test __maybe_unused, int subtest __maybe_unused)
+int test__insn_x86(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 	int ret = 0;
 
diff --git a/tools/perf/arch/x86/tests/intel-cqm.c b/tools/perf/arch/x86/tests/intel-cqm.c
index 27dd8cf9e060..cb5b2c6c3b3b 100644
--- a/tools/perf/arch/x86/tests/intel-cqm.c
+++ b/tools/perf/arch/x86/tests/intel-cqm.c
@@ -37,7 +37,7 @@ static pid_t spawn(void)
  * the last read counter value to avoid triggering a WARN_ON_ONCE() in
  * smp_call_function_many() caused by sending IPIs from NMI context.
  */
-int test__intel_cqm_count_nmi_context(struct test *test __maybe_unused, int subtest __maybe_unused)
+int test__intel_cqm_count_nmi_context(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 	struct evlist *evlist = NULL;
 	struct evsel *evsel = NULL;
diff --git a/tools/perf/arch/x86/tests/intel-pt-pkt-decoder-test.c b/tools/perf/arch/x86/tests/intel-pt-pkt-decoder-test.c
index c933e3dcd0a8..2fc882ab24c1 100644
--- a/tools/perf/arch/x86/tests/intel-pt-pkt-decoder-test.c
+++ b/tools/perf/arch/x86/tests/intel-pt-pkt-decoder-test.c
@@ -289,7 +289,7 @@ static int test_one(struct test_data *d)
  * This test feeds byte sequences to the Intel PT packet decoder and checks the
  * results. Changes to the packet context are also checked.
  */
-int test__intel_pt_pkt_decoder(struct test *test __maybe_unused, int subtest __maybe_unused)
+int test__intel_pt_pkt_decoder(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 	struct test_data *d = data;
 	int ret;
diff --git a/tools/perf/arch/x86/tests/rdpmc.c b/tools/perf/arch/x86/tests/rdpmc.c
index 1ea916656a2d..498413ad9c97 100644
--- a/tools/perf/arch/x86/tests/rdpmc.c
+++ b/tools/perf/arch/x86/tests/rdpmc.c
@@ -157,7 +157,7 @@ out_close:
 	return 0;
 }
 
-int test__rdpmc(struct test *test __maybe_unused, int subtest __maybe_unused)
+int test__rdpmc(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 	int status = 0;
 	int wret = 0;
diff --git a/tools/perf/arch/x86/tests/sample-parsing.c b/tools/perf/arch/x86/tests/sample-parsing.c
index c92db87e4479..bfbd3662b69e 100644
--- a/tools/perf/arch/x86/tests/sample-parsing.c
+++ b/tools/perf/arch/x86/tests/sample-parsing.c
@@ -115,7 +115,7 @@ out_free:
  * For now, the PERF_SAMPLE_WEIGHT_STRUCT is the only X86 specific sample type.
  * The test only checks the PERF_SAMPLE_WEIGHT_STRUCT type.
  */
-int test__x86_sample_parsing(struct test *test __maybe_unused, int subtest __maybe_unused)
+int test__x86_sample_parsing(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 	return do_test(PERF_SAMPLE_WEIGHT_STRUCT);
 }
diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c
index 5d1fe9c35807..137890f78e17 100644
--- a/tools/perf/bench/futex-lock-pi.c
+++ b/tools/perf/bench/futex-lock-pi.c
@@ -233,6 +233,7 @@ int bench_futex_lock_pi(int argc, const char **argv)
 	print_summary();
 
 	free(worker);
+	perf_cpu_map__put(cpu);
 	return ret;
 err:
 	usage_with_options(bench_futex_lock_pi_usage, options);
diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c
index 97fe31fd3a23..f7a5ffebb940 100644
--- a/tools/perf/bench/futex-requeue.c
+++ b/tools/perf/bench/futex-requeue.c
@@ -294,6 +294,7 @@ int bench_futex_requeue(int argc, const char **argv)
 	print_summary();
 
 	free(worker);
+	perf_cpu_map__put(cpu);
 	return ret;
 err:
 	usage_with_options(bench_futex_requeue_usage, options);
diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c
index e970e6b9ad53..0983f40b4b40 100644
--- a/tools/perf/bench/futex-wake-parallel.c
+++ b/tools/perf/bench/futex-wake-parallel.c
@@ -329,6 +329,7 @@ int bench_futex_wake_parallel(int argc, const char **argv)
 	print_summary();
 
 	free(blocked_worker);
+	perf_cpu_map__put(cpu);
 	return ret;
 }
 #endif /* HAVE_PTHREAD_BARRIER */
diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c
index 77f058a47790..2226a475e782 100644
--- a/tools/perf/bench/futex-wake.c
+++ b/tools/perf/bench/futex-wake.c
@@ -222,5 +222,6 @@ int bench_futex_wake(int argc, const char **argv)
 	print_summary();
 
 	free(worker);
+	perf_cpu_map__put(cpu);
 	return ret;
 }
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index bc5259db5fd9..409b721666cb 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -755,12 +755,16 @@ static int parse_vm_time_correlation(const struct option *opt, const char *str,
 	return inject->itrace_synth_opts.vm_tm_corr_args ? 0 : -ENOMEM;
 }
 
+static int output_fd(struct perf_inject *inject)
+{
+	return inject->in_place_update ? -1 : perf_data__fd(&inject->output);
+}
+
 static int __cmd_inject(struct perf_inject *inject)
 {
 	int ret = -EINVAL;
 	struct perf_session *session = inject->session;
-	struct perf_data *data_out = &inject->output;
-	int fd = inject->in_place_update ? -1 : perf_data__fd(data_out);
+	int fd = output_fd(inject);
 	u64 output_data_offset;
 
 	signal(SIGINT, sig_handler);
@@ -820,7 +824,7 @@ static int __cmd_inject(struct perf_inject *inject)
 		inject->tool.ordered_events = true;
 		inject->tool.ordering_requires_timestamps = true;
 		/* Allow space in the header for new attributes */
-		output_data_offset = 4096;
+		output_data_offset = roundup(8192 + session->header.data_offset, 4096);
 		if (inject->strip)
 			strip_init(inject);
 	}
@@ -1015,7 +1019,7 @@ int cmd_inject(int argc, const char **argv)
 	}
 
 	inject.session = __perf_session__new(&data, repipe,
-					     perf_data__fd(&inject.output),
+					     output_fd(&inject),
 					     &inject.tool);
 	if (IS_ERR(inject.session)) {
 		ret = PTR_ERR(inject.session);
@@ -1078,7 +1082,8 @@ out_delete:
 	zstd_fini(&(inject.session->zstd_data));
 	perf_session__delete(inject.session);
 out_close_output:
-	perf_data__close(&inject.output);
+	if (!inject.in_place_update)
+		perf_data__close(&inject.output);
 	free(inject.itrace_synth_opts.vm_tm_corr_args);
 	return ret;
 }
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 8167ebfe776a..8ae400429870 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -619,14 +619,17 @@ static int report__browse_hists(struct report *rep)
 	int ret;
 	struct perf_session *session = rep->session;
 	struct evlist *evlist = session->evlist;
-	const char *help = perf_tip(system_path(TIPDIR));
+	char *help = NULL, *path = NULL;
 
-	if (help == NULL) {
+	path = system_path(TIPDIR);
+	if (perf_tip(&help, path) || help == NULL) {
 		/* fallback for people who don't install perf ;-) */
-		help = perf_tip(DOCDIR);
-		if (help == NULL)
-			help = "Cannot load tips.txt file, please install perf!";
+		free(path);
+		path = system_path(DOCDIR);
+		if (perf_tip(&help, path) || help == NULL)
+			help = strdup("Cannot load tips.txt file, please install perf!");
 	}
+	free(path);
 
 	switch (use_browser) {
 	case 1:
@@ -651,7 +654,7 @@ static int report__browse_hists(struct report *rep)
 		ret = evlist__tty_browse_hists(evlist, rep, help);
 		break;
 	}
-
+	free(help);
 	return ret;
 }
 
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 624ea12ce5ca..0b52e08e558e 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -979,6 +979,8 @@ static struct syscall_fmt syscall_fmts[] = {
 	  .arg = { [2] = { .scnprintf = SCA_GETRANDOM_FLAGS, /* flags */ }, }, },
 	{ .name	    = "getrlimit",
 	  .arg = { [0] = STRARRAY(resource, rlimit_resources), }, },
+	{ .name	    = "getsockopt",
+	  .arg = { [1] = STRARRAY(level, socket_level), }, },
 	{ .name	    = "gettid",	    .errpid = true, },
 	{ .name	    = "ioctl",
 	  .arg = {
@@ -1121,6 +1123,8 @@ static struct syscall_fmt syscall_fmts[] = {
 	  .arg = { [0] = STRARRAY(which, itimers), }, },
 	{ .name	    = "setrlimit",
 	  .arg = { [0] = STRARRAY(resource, rlimit_resources), }, },
+	{ .name	    = "setsockopt",
+	  .arg = { [1] = STRARRAY(level, socket_level), }, },
 	{ .name	    = "socket",
 	  .arg = { [0] = STRARRAY(family, socket_families),
 		   [1] = { .scnprintf = SCA_SK_TYPE, /* type */ },
diff --git a/tools/perf/design.txt b/tools/perf/design.txt
index a42fab308ff6..aa8cfeabb743 100644
--- a/tools/perf/design.txt
+++ b/tools/perf/design.txt
@@ -106,6 +106,9 @@ enum perf_hw_id {
 	PERF_COUNT_HW_BRANCH_INSTRUCTIONS	= 4,
 	PERF_COUNT_HW_BRANCH_MISSES		= 5,
 	PERF_COUNT_HW_BUS_CYCLES		= 6,
+	PERF_COUNT_HW_STALLED_CYCLES_FRONTEND	= 7,
+	PERF_COUNT_HW_STALLED_CYCLES_BACKEND	= 8,
+	PERF_COUNT_HW_REF_CPU_CYCLES		= 9,
 };
 
 These are standardized types of events that work relatively uniformly
diff --git a/tools/perf/pmu-events/arch/powerpc/power10/metrics.json b/tools/perf/pmu-events/arch/powerpc/power10/metrics.json
new file mode 100644
index 000000000000..b57526fa44f2
--- /dev/null
+++ b/tools/perf/pmu-events/arch/powerpc/power10/metrics.json
@@ -0,0 +1,676 @@
+[
+    {
+        "BriefDescription": "Percentage of cycles that are run cycles",
+        "MetricExpr": "PM_RUN_CYC / PM_CYC * 100",
+        "MetricGroup": "General",
+        "MetricName": "RUN_CYCLES_RATE",
+        "ScaleUnit": "1%"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction",
+        "MetricExpr": "PM_CYC / PM_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "CYCLES_PER_INSTRUCTION"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when dispatch was stalled for any reason",
+        "MetricExpr": "PM_DISP_STALL_CYC / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "DISPATCHED_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when dispatch was stalled because there was a flush",
+        "MetricExpr": "PM_DISP_STALL_FLUSH / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "DISPATCHED_FLUSH_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when dispatch was stalled because the MMU was handling a translation miss",
+        "MetricExpr": "PM_DISP_STALL_TRANSLATION / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "DISPATCHED_TRANSLATION_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when dispatch was stalled waiting to resolve an instruction ERAT miss",
+        "MetricExpr": "PM_DISP_STALL_IERAT_ONLY_MISS / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "DISPATCHED_IERAT_ONLY_MISS_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when dispatch was stalled waiting to resolve an instruction TLB miss",
+        "MetricExpr": "PM_DISP_STALL_ITLB_MISS / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "DISPATCHED_ITLB_MISS_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when dispatch was stalled due to an icache miss",
+        "MetricExpr": "PM_DISP_STALL_IC_MISS / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "DISPATCHED_IC_MISS_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when dispatch was stalled while the instruction was fetched from the local L2",
+        "MetricExpr": "PM_DISP_STALL_IC_L2 / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "DISPATCHED_IC_L2_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when dispatch was stalled while the instruction was fetched from the local L3",
+        "MetricExpr": "PM_DISP_STALL_IC_L3 / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "DISPATCHED_IC_L3_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when dispatch was stalled while the instruction was fetched from any source beyond the local L3",
+        "MetricExpr": "PM_DISP_STALL_IC_L3MISS / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "DISPATCHED_IC_L3MISS_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when dispatch was stalled due to an icache miss after a branch mispredict",
+        "MetricExpr": "PM_DISP_STALL_BR_MPRED_ICMISS / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "DISPATCHED_BR_MPRED_ICMISS_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when dispatch was stalled while instruction was fetched from the local L2 after suffering a branch mispredict",
+        "MetricExpr": "PM_DISP_STALL_BR_MPRED_IC_L2 / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "DISPATCHED_BR_MPRED_IC_L2_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when dispatch was stalled while instruction was fetched from the local L3 after suffering a branch mispredict",
+        "MetricExpr": "PM_DISP_STALL_BR_MPRED_IC_L3 / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "DISPATCHED_BR_MPRED_IC_L3_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when dispatch was stalled while instruction was fetched from any source beyond the local L3 after suffering a branch mispredict",
+        "MetricExpr": "PM_DISP_STALL_BR_MPRED_IC_L3MISS / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "DISPATCHED_BR_MPRED_IC_L3MISS_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when dispatch was stalled due to a branch mispredict",
+        "MetricExpr": "PM_DISP_STALL_BR_MPRED / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "DISPATCHED_BR_MPRED_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when the NTC instruction was held at dispatch for any reason",
+        "MetricExpr": "PM_DISP_STALL_HELD_CYC / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "DISPATCHED_HELD_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when the NTC instruction was held at dispatch because of a synchronizing instruction that requires the ICT to be empty before dispatch",
+        "MetricExpr": "PM_DISP_STALL_HELD_SYNC_CYC / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "DISP_HELD_STALL_SYNC_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when the NTC instruction was held at dispatch while waiting on the scoreboard",
+        "MetricExpr": "PM_DISP_STALL_HELD_SCOREBOARD_CYC / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "DISP_HELD_STALL_SCOREBOARD_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when the NTC instruction was held at dispatch due to issue queue full",
+        "MetricExpr": "PM_DISP_STALL_HELD_ISSQ_FULL_CYC / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "DISP_HELD_STALL_ISSQ_FULL_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when the NTC instruction was held at dispatch because the mapper/SRB was full",
+        "MetricExpr": "PM_DISP_STALL_HELD_RENAME_CYC / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "DISPATCHED_HELD_RENAME_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when the NTC instruction was held at dispatch because the STF mapper/SRB was full",
+        "MetricExpr": "PM_DISP_STALL_HELD_STF_MAPPER_CYC / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "DISPATCHED_HELD_STF_MAPPER_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when the NTC instruction was held at dispatch because the XVFC mapper/SRB was full",
+        "MetricExpr": "PM_DISP_STALL_HELD_XVFC_MAPPER_CYC / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "DISPATCHED_HELD_XVFC_MAPPER_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when the NTC instruction was held at dispatch for any other reason",
+        "MetricExpr": "PM_DISP_STALL_HELD_OTHER_CYC / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "DISPATCHED_HELD_OTHER_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when the NTC instruction has been dispatched but not issued for any reason",
+        "MetricExpr": "PM_ISSUE_STALL / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "ISSUE_STALL_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when the NTC instruction is waiting to be finished in one of the execution units",
+        "MetricExpr": "PM_EXEC_STALL / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "EXECUTION_STALL_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction spent executing an NTC instruction that gets flushed some time after dispatch",
+        "MetricExpr": "PM_EXEC_STALL_NTC_FLUSH / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "NTC_FLUSH_STALL_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when the NTF instruction finishes at dispatch",
+        "MetricExpr": "PM_EXEC_STALL_FIN_AT_DISP / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "FIN_AT_DISP_STALL_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when the NTC instruction is executing in the branch unit",
+        "MetricExpr": "PM_EXEC_STALL_BRU / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "BRU_STALL_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when the NTC instruction is a simple fixed point instruction that is executing in the LSU",
+        "MetricExpr": "PM_EXEC_STALL_SIMPLE_FX / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "SIMPLE_FX_STALL_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when the NTC instruction is executing in the VSU",
+        "MetricExpr": "PM_EXEC_STALL_VSU / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "VSU_STALL_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when the NTC instruction is waiting to be finished in one of the execution units",
+        "MetricExpr": "PM_EXEC_STALL_TRANSLATION / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "TRANSLATION_STALL_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when the NTC instruction is a load or store that suffered a translation miss",
+        "MetricExpr": "PM_EXEC_STALL_DERAT_ONLY_MISS / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "DERAT_ONLY_MISS_STALL_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when the NTC instruction is recovering from a TLB miss",
+        "MetricExpr": "PM_EXEC_STALL_DERAT_DTLB_MISS / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "DERAT_DTLB_MISS_STALL_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when the NTC instruction is executing in the LSU",
+        "MetricExpr": "PM_EXEC_STALL_LSU / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "LSU_STALL_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when the NTC instruction is a load that is executing in the LSU",
+        "MetricExpr": "PM_EXEC_STALL_LOAD / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "LOAD_STALL_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when the NTC instruction is waiting for a load miss to resolve from either the local L2 or local L3",
+        "MetricExpr": "PM_EXEC_STALL_DMISS_L2L3 / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "DMISS_L2L3_STALL_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when the NTC instruction is waiting for a load miss to resolve from either the local L2 or local L3, with an RC dispatch conflict",
+        "MetricExpr": "PM_EXEC_STALL_DMISS_L2L3_CONFLICT / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "DMISS_L2L3_CONFLICT_STALL_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when the NTC instruction is waiting for a load miss to resolve from either the local L2 or local L3, without an RC dispatch conflict",
+        "MetricExpr": "PM_EXEC_STALL_DMISS_L2L3_NOCONFLICT / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "DMISS_L2L3_NOCONFLICT_STALL_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when the NTC instruction is waiting for a load miss to resolve from a source beyond the local L2 and local L3",
+        "MetricExpr": "PM_EXEC_STALL_DMISS_L3MISS / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "DMISS_L3MISS_STALL_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when the NTC instruction is waiting for a load miss to resolve from a neighbor chiplet's L2 or L3 in the same chip",
+        "MetricExpr": "PM_EXEC_STALL_DMISS_L21_L31 / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "DMISS_L21_L31_STALL_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when the NTC instruction is waiting for a load miss to resolve from L4, local memory or OpenCAPI chip",
+        "MetricExpr": "PM_EXEC_STALL_DMISS_LMEM / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "DMISS_LMEM_STALL_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when the NTC instruction is waiting for a load miss to resolve from a remote chip (cache, L4, memory or OpenCAPI) in the same group",
+        "MetricExpr": "PM_EXEC_STALL_DMISS_OFF_CHIP / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "DMISS_OFF_CHIP_STALL_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when the NTC instruction is waiting for a load miss to resolve from a distant chip (cache, L4, memory or OpenCAPI chip)",
+        "MetricExpr": "PM_EXEC_STALL_DMISS_OFF_NODE / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "DMISS_OFF_NODE_STALL_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when the NTC instruction is executing a TLBIEL instruction",
+        "MetricExpr": "PM_EXEC_STALL_TLBIEL / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "TLBIEL_STALL_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when the NTC instruction is finishing a load after its data has been reloaded from a data source beyond the local L1, OR when the LSU is processing an L1-hit, OR when the NTF instruction merged with another load in the LMQ",
+        "MetricExpr": "PM_EXEC_STALL_LOAD_FINISH / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "LOAD_FINISH_STALL_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when the NTC instruction is a store that is executing in the LSU",
+        "MetricExpr": "PM_EXEC_STALL_STORE / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "STORE_STALL_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when the NTC instruction is in the store unit outside of handling store misses or other special store operations",
+        "MetricExpr": "PM_EXEC_STALL_STORE_PIPE / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "STORE_PIPE_STALL_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when the NTC instruction is a store whose cache line was not resident in the L1 and had to wait for allocation of the missing line into the L1",
+        "MetricExpr": "PM_EXEC_STALL_STORE_MISS / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "STORE_MISS_STALL_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when the NTC instruction is a TLBIE instruction waiting for a response from the L2",
+        "MetricExpr": "PM_EXEC_STALL_TLBIE / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "TLBIE_STALL_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when the NTC instruction is executing a PTESYNC instruction",
+        "MetricExpr": "PM_EXEC_STALL_PTESYNC / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "PTESYNC_STALL_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when the NTC instruction cannot complete because the thread was blocked",
+        "MetricExpr": "PM_CMPL_STALL / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "COMPLETION_STALL_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when the NTC instruction cannot complete because it was interrupted by ANY exception",
+        "MetricExpr": "PM_CMPL_STALL_EXCEPTION / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "EXCEPTION_COMPLETION_STALL_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when the NTC instruction is stuck at finish waiting for the non-speculative finish of either a STCX instruction waiting for its result or a load waiting for non-critical sectors of data and ECC",
+        "MetricExpr": "PM_CMPL_STALL_MEM_ECC / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "MEM_ECC_COMPLETION_STALL_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when the NTC instruction is a STCX instruction waiting for resolution from the nest",
+        "MetricExpr": "PM_CMPL_STALL_STCX / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "STCX_COMPLETION_STALL_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when the NTC instruction is a LWSYNC instruction waiting to complete",
+        "MetricExpr": "PM_CMPL_STALL_LWSYNC / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "LWSYNC_COMPLETION_STALL_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when the NTC instruction is a HWSYNC instruction stuck at finish waiting for a response from the L2",
+        "MetricExpr": "PM_CMPL_STALL_HWSYNC / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "HWSYNC_COMPLETION_STALL_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when the NTC instruction required special handling before completion",
+        "MetricExpr": "PM_CMPL_STALL_SPECIAL / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "SPECIAL_COMPLETION_STALL_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when dispatch was stalled because fetch was being held, so there was nothing in the pipeline for this thread",
+        "MetricExpr": "PM_DISP_STALL_FETCH / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "DISPATCHED_FETCH_CPI"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when the NTC instruction was held at dispatch because of power management",
+        "MetricExpr": "PM_DISP_STALL_HELD_HALT_CYC / PM_RUN_INST_CMPL",
+        "MetricGroup": "CPI",
+        "MetricName": "DISPATCHED_HELD_HALT_CPI"
+    },
+    {
+        "BriefDescription": "Percentage of flushes per completed instruction",
+        "MetricExpr": "PM_FLUSH / PM_RUN_INST_CMPL * 100",
+        "MetricGroup": "Others",
+        "MetricName": "FLUSH_RATE",
+        "ScaleUnit": "1%"
+    },
+    {
+        "BriefDescription": "Percentage of flushes due to a branch mispredict per completed instruction",
+        "MetricExpr": "PM_FLUSH_MPRED / PM_RUN_INST_CMPL * 100",
+        "MetricGroup": "Others",
+        "MetricName": "BR_MPRED_FLUSH_RATE",
+        "ScaleUnit": "1%"
+    },
+    {
+        "BriefDescription": "Percentage of branch mispredictions per completed instruction",
+        "MetricExpr": "PM_BR_MPRED_CMPL / PM_RUN_INST_CMPL",
+        "MetricGroup": "Others",
+        "MetricName": "BRANCH_MISPREDICTION_RATE"
+    },
+    {
+        "BriefDescription": "Percentage of finished loads that missed in the L1",
+        "MetricExpr": "PM_LD_MISS_L1 / PM_LD_REF_L1 * 100",
+        "MetricGroup": "Others",
+        "MetricName": "L1_LD_MISS_RATIO",
+        "ScaleUnit": "1%"
+    },
+    {
+        "BriefDescription": "Percentage of completed instructions that were loads that missed the L1",
+        "MetricExpr": "PM_LD_MISS_L1 / PM_RUN_INST_CMPL * 100",
+        "MetricGroup": "Others",
+        "MetricName": "L1_LD_MISS_RATE",
+        "ScaleUnit": "1%"
+    },
+    {
+        "BriefDescription": "Percentage of completed instructions when the DPTEG required for the load/store instruction in execution was missing from the TLB",
+        "MetricExpr": "PM_DTLB_MISS / PM_RUN_INST_CMPL * 100",
+        "MetricGroup": "Others",
+        "MetricName": "DTLB_MISS_RATE",
+        "ScaleUnit": "1%"
+    },
+    {
+        "BriefDescription": "Average number of completed instructions dispatched per instruction completed",
+        "MetricExpr": "PM_INST_DISP / PM_RUN_INST_CMPL",
+        "MetricGroup": "General",
+        "MetricName": "DISPATCH_PER_INST_CMPL"
+    },
+    {
+        "BriefDescription": "Percentage of completed instructions that were a demand load that did not hit in the L1 or L2",
+        "MetricExpr": "PM_DATA_FROM_L2MISS / PM_RUN_INST_CMPL * 100",
+        "MetricGroup": "General",
+        "MetricName": "L2_LD_MISS_RATE",
+        "ScaleUnit": "1%"
+    },
+    {
+        "BriefDescription": "Percentage of completed instructions that were demand fetches that missed the L1 icache",
+        "MetricExpr": "PM_L1_ICACHE_MISS / PM_RUN_INST_CMPL * 100",
+        "MetricGroup": "Instruction_Misses",
+        "MetricName": "L1_INST_MISS_RATE",
+        "ScaleUnit": "1%"
+    },
+    {
+        "BriefDescription": "Percentage of completed instructions that were demand fetches that reloaded from beyond the L3 icache",
+        "MetricExpr": "PM_INST_FROM_L3MISS / PM_RUN_INST_CMPL * 100",
+        "MetricGroup": "General",
+        "MetricName": "L3_INST_MISS_RATE",
+        "ScaleUnit": "1%"
+    },
+    {
+        "BriefDescription": "Average number of completed instructions per cycle",
+        "MetricExpr": "PM_INST_CMPL / PM_CYC",
+        "MetricGroup": "General",
+        "MetricName": "IPC"
+    },
+    {
+        "BriefDescription": "Average number of cycles per completed instruction group",
+        "MetricExpr": "PM_CYC / PM_1PLUS_PPC_CMPL",
+        "MetricGroup": "General",
+        "MetricName": "CYCLES_PER_COMPLETED_INSTRUCTIONS_SET"
+    },
+    {
+        "BriefDescription": "Percentage of cycles when at least 1 instruction dispatched",
+        "MetricExpr": "PM_1PLUS_PPC_DISP / PM_RUN_CYC * 100",
+        "MetricGroup": "General",
+        "MetricName": "CYCLES_ATLEAST_ONE_INST_DISPATCHED",
+        "ScaleUnit": "1%"
+    },
+    {
+        "BriefDescription": "Average number of finished loads per completed instruction",
+        "MetricExpr": "PM_LD_REF_L1 / PM_RUN_INST_CMPL",
+        "MetricGroup": "General",
+        "MetricName": "LOADS_PER_INST"
+    },
+    {
+        "BriefDescription": "Average number of finished stores per completed instruction",
+        "MetricExpr": "PM_ST_FIN / PM_RUN_INST_CMPL",
+        "MetricGroup": "General",
+        "MetricName": "STORES_PER_INST"
+    },
+    {
+        "BriefDescription": "Percentage of demand loads that reloaded from beyond the L2 per completed instruction",
+        "MetricExpr": "PM_DATA_FROM_L2MISS / PM_RUN_INST_CMPL * 100",
+        "MetricGroup": "dL1_Reloads",
+        "MetricName": "DL1_RELOAD_FROM_L2_MISS_RATE",
+        "ScaleUnit": "1%"
+    },
+    {
+        "BriefDescription": "Percentage of demand loads that reloaded from beyond the L3 per completed instruction",
+        "MetricExpr": "PM_DATA_FROM_L3MISS / PM_RUN_INST_CMPL * 100",
+        "MetricGroup": "dL1_Reloads",
+        "MetricName": "DL1_RELOAD_FROM_L3_MISS_RATE",
+        "ScaleUnit": "1%"
+    },
+    {
+        "BriefDescription": "Percentage of DERAT misses with 4k page size per completed instruction",
+        "MetricExpr": "PM_DERAT_MISS_4K / PM_RUN_INST_CMPL * 100",
+        "MetricGroup": "Translation",
+        "MetricName": "DERAT_4K_MISS_RATE",
+        "ScaleUnit": "1%"
+    },
+    {
+        "BriefDescription": "Percentage of DERAT misses with 64k page size per completed instruction",
+        "MetricExpr": "PM_DERAT_MISS_64K / PM_RUN_INST_CMPL * 100",
+        "MetricGroup": "Translation",
+        "MetricName": "DERAT_64K_MISS_RATE",
+        "ScaleUnit": "1%"
+    },
+    {
+        "BriefDescription": "Average number of run cycles per completed instruction",
+        "MetricExpr": "PM_RUN_CYC / PM_RUN_INST_CMPL",
+        "MetricGroup": "General",
+        "MetricName": "RUN_CPI"
+    },
+    {
+        "BriefDescription": "Percentage of DERAT misses per completed instruction",
+        "MetricExpr": "PM_DERAT_MISS / PM_RUN_INST_CMPL * 100",
+        "MetricGroup": "Translation",
+        "MetricName": "DERAT_MISS_RATE",
+        "ScaleUnit": "1%"
+    },
+    {
+        "BriefDescription": "Average number of completed instructions per run cycle",
+        "MetricExpr": "PM_RUN_INST_CMPL / PM_RUN_CYC",
+        "MetricGroup": "General",
+        "MetricName": "RUN_IPC"
+    },
+    {
+        "BriefDescription": "Average number of completed instructions per instruction group",
+        "MetricExpr": "PM_RUN_INST_CMPL / PM_1PLUS_PPC_CMPL",
+        "MetricGroup": "General",
+        "MetricName": "AVERAGE_COMPLETED_INSTRUCTION_SET_SIZE"
+    },
+    {
+        "BriefDescription": "Average number of finished instructions per completed instructions",
+        "MetricExpr": "PM_INST_FIN / PM_RUN_INST_CMPL",
+        "MetricGroup": "General",
+        "MetricName": "INST_FIN_PER_CMPL"
+    },
+    {
+        "BriefDescription": "Average cycles per completed instruction when the NTF instruction is completing and the finish was overlooked",
+        "MetricExpr": "PM_EXEC_STALL_UNKNOWN / PM_RUN_INST_CMPL",
+        "MetricGroup": "General",
+        "MetricName": "EXEC_STALL_UNKOWN_CPI"
+    },
+    {
+        "BriefDescription": "Percentage of finished branches that were taken",
+        "MetricExpr": "PM_BR_TAKEN_CMPL / PM_BR_FIN * 100",
+        "MetricGroup": "General",
+        "MetricName": "TAKEN_BRANCHES",
+        "ScaleUnit": "1%"
+    },
+    {
+        "BriefDescription": "Percentage of completed instructions that were a demand load that did not hit in the L1, L2, or the L3",
+        "MetricExpr": "PM_DATA_FROM_L3MISS / PM_RUN_INST_CMPL * 100",
+        "MetricGroup": "General",
+        "MetricName": "L3_LD_MISS_RATE",
+        "ScaleUnit": "1%"
+    },
+    {
+        "BriefDescription": "Average number of finished branches per completed instruction",
+        "MetricExpr": "PM_BR_FIN / PM_RUN_INST_CMPL",
+        "MetricGroup": "General",
+        "MetricName": "BRANCHES_PER_INST"
+    },
+    {
+        "BriefDescription": "Average number of instructions finished in the LSU per completed instruction",
+        "MetricExpr": "PM_LSU_FIN / PM_RUN_INST_CMPL",
+        "MetricGroup": "General",
+        "MetricName": "LSU_PER_INST"
+    },
+    {
+        "BriefDescription": "Average number of instructions finished in the VSU per completed instruction",
+        "MetricExpr": "PM_VSU_FIN / PM_RUN_INST_CMPL",
+        "MetricGroup": "General",
+        "MetricName": "VSU_PER_INST"
+    },
+    {
+        "BriefDescription": "Average number of TLBIE instructions finished in the LSU per completed instruction",
+        "MetricExpr": "PM_TLBIE_FIN / PM_RUN_INST_CMPL",
+        "MetricGroup": "General",
+        "MetricName": "TLBIE_PER_INST"
+    },
+    {
+        "BriefDescription": "Average number of STCX instructions finshed per completed instruction",
+        "MetricExpr": "PM_STCX_FIN / PM_RUN_INST_CMPL",
+        "MetricGroup": "General",
+        "MetricName": "STXC_PER_INST"
+    },
+    {
+        "BriefDescription": "Average number of LARX instructions finshed per completed instruction",
+        "MetricExpr": "PM_LARX_FIN / PM_RUN_INST_CMPL",
+        "MetricGroup": "General",
+        "MetricName": "LARX_PER_INST"
+    },
+    {
+        "BriefDescription": "Average number of PTESYNC instructions finshed per completed instruction",
+        "MetricExpr": "PM_PTESYNC_FIN / PM_RUN_INST_CMPL",
+        "MetricGroup": "General",
+        "MetricName": "PTESYNC_PER_INST"
+    },
+    {
+        "BriefDescription": "Average number of simple fixed-point instructions finshed in the store unit per completed instruction",
+        "MetricExpr": "PM_FX_LSU_FIN / PM_RUN_INST_CMPL",
+        "MetricGroup": "General",
+        "MetricName": "FX_PER_INST"
+    },
+    {
+        "BriefDescription": "Percentage of demand load misses that reloaded the L1 cache",
+        "MetricExpr": "PM_LD_DEMAND_MISS_L1 / PM_LD_MISS_L1 * 100",
+        "MetricGroup": "General",
+        "MetricName": "DL1_MISS_RELOADS",
+        "ScaleUnit": "1%"
+    },
+    {
+        "BriefDescription": "Percentage of demand load misses that reloaded from beyond the local L2",
+        "MetricExpr": "PM_DATA_FROM_L2MISS / PM_LD_DEMAND_MISS_L1 * 100",
+        "MetricGroup": "dL1_Reloads",
+        "MetricName": "DL1_RELOAD_FROM_L2_MISS",
+        "ScaleUnit": "1%"
+    },
+    {
+        "BriefDescription": "Percentage of demand load misses that reloaded from beyond the local L3",
+        "MetricExpr": "PM_DATA_FROM_L3MISS / PM_LD_DEMAND_MISS_L1 * 100",
+        "MetricGroup": "dL1_Reloads",
+        "MetricName": "DL1_RELOAD_FROM_L3_MISS",
+        "ScaleUnit": "1%"
+    },
+    {
+        "BriefDescription": "Percentage of cycles stalled due to the NTC instruction waiting for a load miss to resolve from a source beyond the local L2 and local L3",
+        "MetricExpr": "DMISS_L3MISS_STALL_CPI / RUN_CPI * 100",
+        "MetricGroup": "General",
+        "MetricName": "DCACHE_MISS_CPI",
+        "ScaleUnit": "1%"
+    },
+    {
+        "BriefDescription": "Percentage of DERAT misses with 2M page size per completed instruction",
+        "MetricExpr": "PM_DERAT_MISS_2M / PM_RUN_INST_CMPL * 100",
+        "MetricGroup": "Translation",
+        "MetricName": "DERAT_2M_MISS_RATE",
+        "ScaleUnit": "1%"
+    },
+    {
+        "BriefDescription": "Percentage of DERAT misses with 16M page size per completed instruction",
+        "MetricExpr": "PM_DERAT_MISS_16M / PM_RUN_INST_CMPL * 100",
+        "MetricGroup": "Translation",
+        "MetricName": "DERAT_16M_MISS_RATE",
+        "ScaleUnit": "1%"
+    },
+    {
+        "BriefDescription": "DERAT miss ratio for 4K page size",
+        "MetricExpr": "PM_DERAT_MISS_4K / PM_DERAT_MISS",
+        "MetricGroup": "Translation",
+        "MetricName": "DERAT_4K_MISS_RATIO"
+    },
+    {
+        "BriefDescription": "DERAT miss ratio for 2M page size",
+        "MetricExpr": "PM_DERAT_MISS_2M / PM_DERAT_MISS",
+        "MetricGroup": "Translation",
+        "MetricName": "DERAT_2M_MISS_RATIO"
+    },
+    {
+        "BriefDescription": "DERAT miss ratio for 16M page size",
+        "MetricExpr": "PM_DERAT_MISS_16M / PM_DERAT_MISS",
+        "MetricGroup": "Translation",
+        "MetricName": "DERAT_16M_MISS_RATIO"
+    },
+    {
+        "BriefDescription": "DERAT miss ratio for 64K page size",
+        "MetricExpr": "PM_DERAT_MISS_64K / PM_DERAT_MISS",
+        "MetricGroup": "Translation",
+        "MetricName": "DERAT_64K_MISS_RATIO"
+    },
+    {
+        "BriefDescription": "Percentage of DERAT misses that resulted in TLB reloads",
+        "MetricExpr": "PM_DTLB_MISS / PM_DERAT_MISS * 100",
+        "MetricGroup": "Translation",
+        "MetricName": "DERAT_MISS_RELOAD",
+        "ScaleUnit": "1%"
+    },
+    {
+        "BriefDescription": "Percentage of icache misses that were reloaded from beyond the local L3",
+        "MetricExpr": "PM_INST_FROM_L3MISS / PM_L1_ICACHE_MISS * 100",
+        "MetricGroup": "Instruction_Misses",
+        "MetricName": "INST_FROM_L3_MISS",
+        "ScaleUnit": "1%"
+    },
+    {
+        "BriefDescription": "Percentage of icache reloads from the beyond the L3 per completed instruction",
+        "MetricExpr": "PM_INST_FROM_L3MISS / PM_RUN_INST_CMPL * 100",
+        "MetricGroup": "Instruction_Misses",
+        "MetricName": "INST_FROM_L3_MISS_RATE",
+        "ScaleUnit": "1%"
+    }
+]
diff --git a/tools/perf/tests/api-io.c b/tools/perf/tests/api-io.c
index 2ada86ad6084..e91cf2c127f1 100644
--- a/tools/perf/tests/api-io.c
+++ b/tools/perf/tests/api-io.c
@@ -289,8 +289,8 @@ static int test_get_dec(void)
 	return ret;
 }
 
-int test__api_io(struct test *test __maybe_unused,
-		int subtest __maybe_unused)
+static int test__api_io(struct test_suite *test __maybe_unused,
+			int subtest __maybe_unused)
 {
 	int ret = 0;
 
@@ -302,3 +302,5 @@ int test__api_io(struct test *test __maybe_unused,
 		ret = TEST_FAIL;
 	return ret;
 }
+
+DEFINE_SUITE("Test api io", api_io);
diff --git a/tools/perf/tests/attr.c b/tools/perf/tests/attr.c
index 9b40a25376ae..0f73e300f207 100644
--- a/tools/perf/tests/attr.c
+++ b/tools/perf/tests/attr.c
@@ -178,7 +178,7 @@ static int run_dir(const char *d, const char *perf)
 	return system(cmd) ? TEST_FAIL : TEST_OK;
 }
 
-int test__attr(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__attr(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 	struct stat st;
 	char path_perf[PATH_MAX];
@@ -207,3 +207,5 @@ int test__attr(struct test *test __maybe_unused, int subtest __maybe_unused)
 
 	return TEST_SKIP;
 }
+
+DEFINE_SUITE("Setup struct perf_event_attr", attr);
diff --git a/tools/perf/tests/backward-ring-buffer.c b/tools/perf/tests/backward-ring-buffer.c
index 7447a4478991..79a980b1e786 100644
--- a/tools/perf/tests/backward-ring-buffer.c
+++ b/tools/perf/tests/backward-ring-buffer.c
@@ -82,7 +82,7 @@ static int do_test(struct evlist *evlist, int mmap_pages,
 }
 
 
-int test__backward_ring_buffer(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__backward_ring_buffer(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 	int ret = TEST_SKIP, err, sample_count = 0, comm_count = 0;
 	char pid[16], sbuf[STRERR_BUFSIZE];
@@ -167,3 +167,5 @@ out_delete_evlist:
 	evlist__delete(evlist);
 	return ret;
 }
+
+DEFINE_SUITE("Read backward ring buffer", backward_ring_buffer);
diff --git a/tools/perf/tests/bitmap.c b/tools/perf/tests/bitmap.c
index 12b805efdca0..384856347236 100644
--- a/tools/perf/tests/bitmap.c
+++ b/tools/perf/tests/bitmap.c
@@ -40,7 +40,7 @@ static int test_bitmap(const char *str)
 	return ret;
 }
 
-int test__bitmap_print(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__bitmap_print(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 	TEST_ASSERT_VAL("failed to convert map", test_bitmap("1"));
 	TEST_ASSERT_VAL("failed to convert map", test_bitmap("1,5"));
@@ -51,3 +51,5 @@ int test__bitmap_print(struct test *test __maybe_unused, int subtest __maybe_unu
 	TEST_ASSERT_VAL("failed to convert map", test_bitmap("1-10,12-20,22-30,32-40"));
 	return 0;
 }
+
+DEFINE_SUITE("Print bitmap", bitmap_print);
diff --git a/tools/perf/tests/bp_account.c b/tools/perf/tests/bp_account.c
index 489b50604cf2..d1ebb5561e5b 100644
--- a/tools/perf/tests/bp_account.c
+++ b/tools/perf/tests/bp_account.c
@@ -19,6 +19,19 @@
 #include "../perf-sys.h"
 #include "cloexec.h"
 
+/*
+ * PowerPC and S390 do not support creation of instruction breakpoints using the
+ * perf_event interface.
+ *
+ * Just disable the test for these architectures until these issues are
+ * resolved.
+ */
+#if defined(__powerpc__) || defined(__s390x__)
+#define BP_ACCOUNT_IS_SUPPORTED 0
+#else
+#define BP_ACCOUNT_IS_SUPPORTED 1
+#endif
+
 static volatile long the_var;
 
 static noinline int test_function(void)
@@ -173,13 +186,18 @@ static int detect_share(int wp_cnt, int bp_cnt)
  *     we create another watchpoint to ensure
  *     the slot accounting is correct
  */
-int test__bp_accounting(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__bp_accounting(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 	int has_ioctl = detect_ioctl();
 	int wp_cnt = detect_cnt(false);
 	int bp_cnt = detect_cnt(true);
 	int share  = detect_share(wp_cnt, bp_cnt);
 
+	if (!BP_ACCOUNT_IS_SUPPORTED) {
+		pr_debug("Test not supported on this architecture");
+		return TEST_SKIP;
+	}
+
 	pr_debug("watchpoints count %d, breakpoints count %d, has_ioctl %d, share %d\n",
 		 wp_cnt, bp_cnt, has_ioctl, share);
 
@@ -189,18 +207,4 @@ int test__bp_accounting(struct test *test __maybe_unused, int subtest __maybe_un
 	return bp_accounting(wp_cnt, share);
 }
 
-bool test__bp_account_is_supported(void)
-{
-	/*
-	 * PowerPC and S390 do not support creation of instruction
-	 * breakpoints using the perf_event interface.
-	 *
-	 * Just disable the test for these architectures until these
-	 * issues are resolved.
-	 */
-#if defined(__powerpc__) || defined(__s390x__)
-	return false;
-#else
-	return true;
-#endif
-}
+DEFINE_SUITE("Breakpoint accounting", bp_accounting);
diff --git a/tools/perf/tests/bp_signal.c b/tools/perf/tests/bp_signal.c
index ef37353636d8..1f2908f02389 100644
--- a/tools/perf/tests/bp_signal.c
+++ b/tools/perf/tests/bp_signal.c
@@ -161,11 +161,16 @@ static long long bp_count(int fd)
 	return count;
 }
 
-int test__bp_signal(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__bp_signal(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 	struct sigaction sa;
 	long long count1, count2, count3;
 
+	if (!BP_SIGNAL_IS_SUPPORTED) {
+		pr_debug("Test not supported on this architecture");
+		return TEST_SKIP;
+	}
+
 	/* setup SIGIO signal handler */
 	memset(&sa, 0, sizeof(struct sigaction));
 	sa.sa_sigaction = (void *) sig_handler;
@@ -285,29 +290,4 @@ int test__bp_signal(struct test *test __maybe_unused, int subtest __maybe_unused
 		TEST_OK : TEST_FAIL;
 }
 
-bool test__bp_signal_is_supported(void)
-{
-	/*
-	 * PowerPC and S390 do not support creation of instruction
-	 * breakpoints using the perf_event interface.
-	 *
-	 * ARM requires explicit rounding down of the instruction
-	 * pointer in Thumb mode, and then requires the single-step
-	 * to be handled explicitly in the overflow handler to avoid
-	 * stepping into the SIGIO handler and getting stuck on the
-	 * breakpointed instruction.
-	 *
-	 * Since arm64 has the same issue with arm for the single-step
-	 * handling, this case also gets stuck on the breakpointed
-	 * instruction.
-	 *
-	 * Just disable the test for these architectures until these
-	 * issues are resolved.
-	 */
-#if defined(__powerpc__) || defined(__s390x__) || defined(__arm__) || \
-    defined(__aarch64__)
-	return false;
-#else
-	return true;
-#endif
-}
+DEFINE_SUITE("Breakpoint overflow signal handler", bp_signal);
diff --git a/tools/perf/tests/bp_signal_overflow.c b/tools/perf/tests/bp_signal_overflow.c
index eb4dbbddf4ff..4e897c2cf26b 100644
--- a/tools/perf/tests/bp_signal_overflow.c
+++ b/tools/perf/tests/bp_signal_overflow.c
@@ -59,13 +59,18 @@ static long long bp_count(int fd)
 #define EXECUTIONS 10000
 #define THRESHOLD  100
 
-int test__bp_signal_overflow(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__bp_signal_overflow(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 	struct perf_event_attr pe;
 	struct sigaction sa;
 	long long count;
 	int fd, i, fails = 0;
 
+	if (!BP_SIGNAL_IS_SUPPORTED) {
+		pr_debug("Test not supported on this architecture");
+		return TEST_SKIP;
+	}
+
 	/* setup SIGIO signal handler */
 	memset(&sa, 0, sizeof(struct sigaction));
 	sa.sa_sigaction = (void *) sig_handler;
@@ -133,3 +138,5 @@ int test__bp_signal_overflow(struct test *test __maybe_unused, int subtest __may
 
 	return fails ? TEST_FAIL : TEST_OK;
 }
+
+DEFINE_SUITE("Breakpoint overflow sampling", bp_signal_overflow);
diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c
index 2bf146e49ce8..329f77f592f4 100644
--- a/tools/perf/tests/bpf.c
+++ b/tools/perf/tests/bpf.c
@@ -62,7 +62,6 @@ static int llseek_loop(void)
 
 static struct {
 	enum test_llvm__testcase prog_id;
-	const char *desc;
 	const char *name;
 	const char *msg_compile_fail;
 	const char *msg_load_fail;
@@ -72,7 +71,6 @@ static struct {
 } bpf_testcase_table[] = {
 	{
 		.prog_id	  = LLVM_TESTCASE_BASE,
-		.desc		  = "Basic BPF filtering",
 		.name		  = "[basic_bpf_test]",
 		.msg_compile_fail = "fix 'perf test LLVM' first",
 		.msg_load_fail	  = "load bpf object failed",
@@ -81,7 +79,6 @@ static struct {
 	},
 	{
 		.prog_id	  = LLVM_TESTCASE_BASE,
-		.desc		  = "BPF pinning",
 		.name		  = "[bpf_pinning]",
 		.msg_compile_fail = "fix kbuild first",
 		.msg_load_fail	  = "check your vmlinux setting?",
@@ -92,7 +89,6 @@ static struct {
 #ifdef HAVE_BPF_PROLOGUE
 	{
 		.prog_id	  = LLVM_TESTCASE_BPF_PROLOGUE,
-		.desc		  = "BPF prologue generation",
 		.name		  = "[bpf_prologue_test]",
 		.msg_compile_fail = "fix kbuild first",
 		.msg_load_fail	  = "check your vmlinux setting?",
@@ -283,18 +279,6 @@ out:
 	return ret;
 }
 
-int test__bpf_subtest_get_nr(void)
-{
-	return (int)ARRAY_SIZE(bpf_testcase_table);
-}
-
-const char *test__bpf_subtest_get_desc(int i)
-{
-	if (i < 0 || i >= (int)ARRAY_SIZE(bpf_testcase_table))
-		return NULL;
-	return bpf_testcase_table[i].desc;
-}
-
 static int check_env(void)
 {
 	int err;
@@ -313,7 +297,7 @@ static int check_env(void)
 	}
 
 	err = bpf_load_program(BPF_PROG_TYPE_KPROBE, insns,
-			       sizeof(insns) / sizeof(insns[0]),
+			       ARRAY_SIZE(insns),
 			       license, kver_int, NULL, 0);
 	if (err < 0) {
 		pr_err("Missing basic BPF support, skip this test: %s\n",
@@ -325,7 +309,7 @@ static int check_env(void)
 	return 0;
 }
 
-int test__bpf(struct test *test __maybe_unused, int i)
+static int test__bpf(int i)
 {
 	int err;
 
@@ -343,21 +327,60 @@ int test__bpf(struct test *test __maybe_unused, int i)
 	err = __test__bpf(i);
 	return err;
 }
+#endif
 
-#else
-int test__bpf_subtest_get_nr(void)
+static int test__basic_bpf_test(struct test_suite *test __maybe_unused,
+				int subtest __maybe_unused)
 {
-	return 0;
+#ifdef HAVE_LIBBPF_SUPPORT
+	return test__bpf(0);
+#else
+	pr_debug("Skip BPF test because BPF support is not compiled\n");
+	return TEST_SKIP;
+#endif
 }
 
-const char *test__bpf_subtest_get_desc(int i __maybe_unused)
+static int test__bpf_pinning(struct test_suite *test __maybe_unused,
+			     int subtest __maybe_unused)
 {
-	return NULL;
+#ifdef HAVE_LIBBPF_SUPPORT
+	return test__bpf(1);
+#else
+	pr_debug("Skip BPF test because BPF support is not compiled\n");
+	return TEST_SKIP;
+#endif
 }
 
-int test__bpf(struct test *test __maybe_unused, int i __maybe_unused)
+static int test__bpf_prologue_test(struct test_suite *test __maybe_unused,
+				   int subtest __maybe_unused)
 {
+#if defined(HAVE_LIBBPF_SUPPORT) && defined(HAVE_BPF_PROLOGUE)
+	return test__bpf(2);
+#else
 	pr_debug("Skip BPF test because BPF support is not compiled\n");
 	return TEST_SKIP;
+#endif
 }
+
+
+static struct test_case bpf_tests[] = {
+#ifdef HAVE_LIBBPF_SUPPORT
+	TEST_CASE("Basic BPF filtering", basic_bpf_test),
+	TEST_CASE("BPF pinning", bpf_pinning),
+#ifdef HAVE_BPF_PROLOGUE
+	TEST_CASE("BPF prologue generation", bpf_prologue_test),
+#else
+	TEST_CASE_REASON("BPF prologue generation", bpf_prologue_test, "not compiled in"),
+#endif
+#else
+	TEST_CASE_REASON("Basic BPF filtering", basic_bpf_test, "not compiled in"),
+	TEST_CASE_REASON("BPF pinning", bpf_pinning, "not compiled in"),
+	TEST_CASE_REASON("BPF prologue generation", bpf_prologue_test, "not compiled in"),
 #endif
+	{ .name = NULL, }
+};
+
+struct test_suite suite__bpf = {
+	.desc = "BPF filter",
+	.test_cases = bpf_tests,
+};
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index da7dc5e45d0c..8cb5a1c3489e 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -30,350 +30,134 @@
 
 static bool dont_fork;
 
-struct test __weak arch_tests[] = {
-	{
-		.func = NULL,
-	},
+struct test_suite *__weak arch_tests[] = {
+	NULL,
 };
 
-static struct test generic_tests[] = {
-	{
-		.desc = "vmlinux symtab matches kallsyms",
-		.func = test__vmlinux_matches_kallsyms,
-	},
-	{
-		.desc = "Detect openat syscall event",
-		.func = test__openat_syscall_event,
-	},
-	{
-		.desc = "Detect openat syscall event on all cpus",
-		.func = test__openat_syscall_event_on_all_cpus,
-	},
-	{
-		.desc = "Read samples using the mmap interface",
-		.func = test__basic_mmap,
-	},
-	{
-		.desc = "Test data source output",
-		.func = test__mem,
-	},
-	{
-		.desc = "Parse event definition strings",
-		.func = test__parse_events,
-	},
-	{
-		.desc = "Simple expression parser",
-		.func = test__expr,
-	},
-	{
-		.desc = "PERF_RECORD_* events & perf_sample fields",
-		.func = test__PERF_RECORD,
-	},
-	{
-		.desc = "Parse perf pmu format",
-		.func = test__pmu,
-	},
-	{
-		.desc = "PMU events",
-		.func = test__pmu_events,
-		.subtest = {
-			.skip_if_fail	= false,
-			.get_nr		= test__pmu_events_subtest_get_nr,
-			.get_desc	= test__pmu_events_subtest_get_desc,
-			.skip_reason	= test__pmu_events_subtest_skip_reason,
-		},
-
-	},
-	{
-		.desc = "DSO data read",
-		.func = test__dso_data,
-	},
-	{
-		.desc = "DSO data cache",
-		.func = test__dso_data_cache,
-	},
-	{
-		.desc = "DSO data reopen",
-		.func = test__dso_data_reopen,
-	},
-	{
-		.desc = "Roundtrip evsel->name",
-		.func = test__perf_evsel__roundtrip_name_test,
-	},
-	{
-		.desc = "Parse sched tracepoints fields",
-		.func = test__perf_evsel__tp_sched_test,
-	},
-	{
-		.desc = "syscalls:sys_enter_openat event fields",
-		.func = test__syscall_openat_tp_fields,
-	},
-	{
-		.desc = "Setup struct perf_event_attr",
-		.func = test__attr,
-	},
-	{
-		.desc = "Match and link multiple hists",
-		.func = test__hists_link,
-	},
-	{
-		.desc = "'import perf' in python",
-		.func = test__python_use,
-	},
-	{
-		.desc = "Breakpoint overflow signal handler",
-		.func = test__bp_signal,
-		.is_supported = test__bp_signal_is_supported,
-	},
-	{
-		.desc = "Breakpoint overflow sampling",
-		.func = test__bp_signal_overflow,
-		.is_supported = test__bp_signal_is_supported,
-	},
-	{
-		.desc = "Breakpoint accounting",
-		.func = test__bp_accounting,
-		.is_supported = test__bp_account_is_supported,
-	},
-	{
-		.desc = "Watchpoint",
-		.func = test__wp,
-		.is_supported = test__wp_is_supported,
-		.subtest = {
-			.skip_if_fail	= false,
-			.get_nr		= test__wp_subtest_get_nr,
-			.get_desc	= test__wp_subtest_get_desc,
-			.skip_reason    = test__wp_subtest_skip_reason,
-		},
-	},
-	{
-		.desc = "Number of exit events of a simple workload",
-		.func = test__task_exit,
-	},
-	{
-		.desc = "Software clock events period values",
-		.func = test__sw_clock_freq,
-	},
-	{
-		.desc = "Object code reading",
-		.func = test__code_reading,
-	},
-	{
-		.desc = "Sample parsing",
-		.func = test__sample_parsing,
-	},
-	{
-		.desc = "Use a dummy software event to keep tracking",
-		.func = test__keep_tracking,
-	},
-	{
-		.desc = "Parse with no sample_id_all bit set",
-		.func = test__parse_no_sample_id_all,
-	},
-	{
-		.desc = "Filter hist entries",
-		.func = test__hists_filter,
-	},
-	{
-		.desc = "Lookup mmap thread",
-		.func = test__mmap_thread_lookup,
-	},
-	{
-		.desc = "Share thread maps",
-		.func = test__thread_maps_share,
-	},
-	{
-		.desc = "Sort output of hist entries",
-		.func = test__hists_output,
-	},
-	{
-		.desc = "Cumulate child hist entries",
-		.func = test__hists_cumulate,
-	},
-	{
-		.desc = "Track with sched_switch",
-		.func = test__switch_tracking,
-	},
-	{
-		.desc = "Filter fds with revents mask in a fdarray",
-		.func = test__fdarray__filter,
-	},
-	{
-		.desc = "Add fd to a fdarray, making it autogrow",
-		.func = test__fdarray__add,
-	},
-	{
-		.desc = "kmod_path__parse",
-		.func = test__kmod_path__parse,
-	},
-	{
-		.desc = "Thread map",
-		.func = test__thread_map,
-	},
-	{
-		.desc = "LLVM search and compile",
-		.func = test__llvm,
-		.subtest = {
-			.skip_if_fail	= true,
-			.get_nr		= test__llvm_subtest_get_nr,
-			.get_desc	= test__llvm_subtest_get_desc,
-		},
-	},
-	{
-		.desc = "Session topology",
-		.func = test__session_topology,
-	},
-	{
-		.desc = "BPF filter",
-		.func = test__bpf,
-		.subtest = {
-			.skip_if_fail	= true,
-			.get_nr		= test__bpf_subtest_get_nr,
-			.get_desc	= test__bpf_subtest_get_desc,
-		},
-	},
-	{
-		.desc = "Synthesize thread map",
-		.func = test__thread_map_synthesize,
-	},
-	{
-		.desc = "Remove thread map",
-		.func = test__thread_map_remove,
-	},
-	{
-		.desc = "Synthesize cpu map",
-		.func = test__cpu_map_synthesize,
-	},
-	{
-		.desc = "Synthesize stat config",
-		.func = test__synthesize_stat_config,
-	},
-	{
-		.desc = "Synthesize stat",
-		.func = test__synthesize_stat,
-	},
-	{
-		.desc = "Synthesize stat round",
-		.func = test__synthesize_stat_round,
-	},
-	{
-		.desc = "Synthesize attr update",
-		.func = test__event_update,
-	},
-	{
-		.desc = "Event times",
-		.func = test__event_times,
-	},
-	{
-		.desc = "Read backward ring buffer",
-		.func = test__backward_ring_buffer,
-	},
-	{
-		.desc = "Print cpu map",
-		.func = test__cpu_map_print,
-	},
-	{
-		.desc = "Merge cpu map",
-		.func = test__cpu_map_merge,
-	},
-
-	{
-		.desc = "Probe SDT events",
-		.func = test__sdt_event,
-	},
-	{
-		.desc = "is_printable_array",
-		.func = test__is_printable_array,
-	},
-	{
-		.desc = "Print bitmap",
-		.func = test__bitmap_print,
-	},
-	{
-		.desc = "perf hooks",
-		.func = test__perf_hooks,
-	},
-	{
-		.desc = "builtin clang support",
-		.func = test__clang,
-		.subtest = {
-			.skip_if_fail	= true,
-			.get_nr		= test__clang_subtest_get_nr,
-			.get_desc	= test__clang_subtest_get_desc,
-		}
-	},
-	{
-		.desc = "unit_number__scnprintf",
-		.func = test__unit_number__scnprint,
-	},
-	{
-		.desc = "mem2node",
-		.func = test__mem2node,
-	},
-	{
-		.desc = "time utils",
-		.func = test__time_utils,
-	},
-	{
-		.desc = "Test jit_write_elf",
-		.func = test__jit_write_elf,
-	},
-	{
-		.desc = "Test libpfm4 support",
-		.func = test__pfm,
-		.subtest = {
-			.skip_if_fail	= true,
-			.get_nr		= test__pfm_subtest_get_nr,
-			.get_desc	= test__pfm_subtest_get_desc,
-		}
-	},
-	{
-		.desc = "Test api io",
-		.func = test__api_io,
-	},
-	{
-		.desc = "maps__merge_in",
-		.func = test__maps__merge_in,
-	},
-	{
-		.desc = "Demangle Java",
-		.func = test__demangle_java,
-	},
-	{
-		.desc = "Demangle OCaml",
-		.func = test__demangle_ocaml,
-	},
-	{
-		.desc = "Parse and process metrics",
-		.func = test__parse_metric,
-	},
-	{
-		.desc = "PE file support",
-		.func = test__pe_file_parsing,
-	},
-	{
-		.desc = "Event expansion for cgroups",
-		.func = test__expand_cgroup_events,
-	},
-	{
-		.desc = "Convert perf time to TSC",
-		.func = test__perf_time_to_tsc,
-		.is_supported = test__tsc_is_supported,
-	},
-	{
-		.desc = "dlfilter C API",
-		.func = test__dlfilter,
-	},
-	{
-		.func = NULL,
-	},
+static struct test_suite *generic_tests[] = {
+	&suite__vmlinux_matches_kallsyms,
+	&suite__openat_syscall_event,
+	&suite__openat_syscall_event_on_all_cpus,
+	&suite__basic_mmap,
+	&suite__mem,
+	&suite__parse_events,
+	&suite__expr,
+	&suite__PERF_RECORD,
+	&suite__pmu,
+	&suite__pmu_events,
+	&suite__dso_data,
+	&suite__dso_data_cache,
+	&suite__dso_data_reopen,
+	&suite__perf_evsel__roundtrip_name_test,
+	&suite__perf_evsel__tp_sched_test,
+	&suite__syscall_openat_tp_fields,
+	&suite__attr,
+	&suite__hists_link,
+	&suite__python_use,
+	&suite__bp_signal,
+	&suite__bp_signal_overflow,
+	&suite__bp_accounting,
+	&suite__wp,
+	&suite__task_exit,
+	&suite__sw_clock_freq,
+	&suite__code_reading,
+	&suite__sample_parsing,
+	&suite__keep_tracking,
+	&suite__parse_no_sample_id_all,
+	&suite__hists_filter,
+	&suite__mmap_thread_lookup,
+	&suite__thread_maps_share,
+	&suite__hists_output,
+	&suite__hists_cumulate,
+	&suite__switch_tracking,
+	&suite__fdarray__filter,
+	&suite__fdarray__add,
+	&suite__kmod_path__parse,
+	&suite__thread_map,
+	&suite__llvm,
+	&suite__session_topology,
+	&suite__bpf,
+	&suite__thread_map_synthesize,
+	&suite__thread_map_remove,
+	&suite__cpu_map_synthesize,
+	&suite__synthesize_stat_config,
+	&suite__synthesize_stat,
+	&suite__synthesize_stat_round,
+	&suite__event_update,
+	&suite__event_times,
+	&suite__backward_ring_buffer,
+	&suite__cpu_map_print,
+	&suite__cpu_map_merge,
+	&suite__sdt_event,
+	&suite__is_printable_array,
+	&suite__bitmap_print,
+	&suite__perf_hooks,
+	&suite__clang,
+	&suite__unit_number__scnprint,
+	&suite__mem2node,
+	&suite__time_utils,
+	&suite__jit_write_elf,
+	&suite__pfm,
+	&suite__api_io,
+	&suite__maps__merge_in,
+	&suite__demangle_java,
+	&suite__demangle_ocaml,
+	&suite__parse_metric,
+	&suite__pe_file_parsing,
+	&suite__expand_cgroup_events,
+	&suite__perf_time_to_tsc,
+	&suite__dlfilter,
+	NULL,
 };
 
-static struct test *tests[] = {
+static struct test_suite **tests[] = {
 	generic_tests,
 	arch_tests,
 };
 
+static int num_subtests(const struct test_suite *t)
+{
+	int num;
+
+	if (!t->test_cases)
+		return 0;
+
+	num = 0;
+	while (t->test_cases[num].name)
+		num++;
+
+	return num;
+}
+
+static bool has_subtests(const struct test_suite *t)
+{
+	return num_subtests(t) > 1;
+}
+
+static const char *skip_reason(const struct test_suite *t, int subtest)
+{
+	if (t->test_cases && subtest >= 0)
+		return t->test_cases[subtest].skip_reason;
+
+	return NULL;
+}
+
+static const char *test_description(const struct test_suite *t, int subtest)
+{
+	if (t->test_cases && subtest >= 0)
+		return t->test_cases[subtest].desc;
+
+	return t->desc;
+}
+
+static test_fnptr test_function(const struct test_suite *t, int subtest)
+{
+	if (subtest <= 0)
+		return t->test_cases[0].run_case;
+
+	return t->test_cases[subtest].run_case;
+}
+
 static bool perf_test__matches(const char *desc, int curr, int argc, const char *argv[])
 {
 	int i;
@@ -398,7 +182,7 @@ static bool perf_test__matches(const char *desc, int curr, int argc, const char
 	return false;
 }
 
-static int run_test(struct test *test, int subtest)
+static int run_test(struct test_suite *test, int subtest)
 {
 	int status, err = -1, child = dont_fork ? 0 : fork();
 	char sbuf[STRERR_BUFSIZE];
@@ -430,7 +214,7 @@ static int run_test(struct test *test, int subtest)
 			}
 		}
 
-		err = test->func(test, subtest);
+		err = test_function(test, subtest)(test, subtest);
 		if (!dont_fork)
 			exit(err);
 	}
@@ -450,24 +234,19 @@ static int run_test(struct test *test, int subtest)
 	return err;
 }
 
-#define for_each_test(j, t)	 				\
+#define for_each_test(j, k, t)			\
 	for (j = 0; j < ARRAY_SIZE(tests); j++)	\
-		for (t = &tests[j][0]; t->func; t++)
+		for (k = 0, t = tests[j][k]; tests[j][k]; k++, t = tests[j][k])
 
-static int test_and_print(struct test *t, bool force_skip, int subtest)
+static int test_and_print(struct test_suite *t, int subtest)
 {
 	int err;
 
-	if (!force_skip) {
-		pr_debug("\n--- start ---\n");
-		err = run_test(t, subtest);
-		pr_debug("---- end ----\n");
-	} else {
-		pr_debug("\n--- force skipped ---\n");
-		err = TEST_SKIP;
-	}
+	pr_debug("\n--- start ---\n");
+	err = run_test(t, subtest);
+	pr_debug("---- end ----\n");
 
-	if (!t->subtest.get_nr)
+	if (!has_subtests(t))
 		pr_debug("%s:", t->desc);
 	else
 		pr_debug("%s subtest %d:", t->desc, subtest + 1);
@@ -477,11 +256,10 @@ static int test_and_print(struct test *t, bool force_skip, int subtest)
 		pr_info(" Ok\n");
 		break;
 	case TEST_SKIP: {
-		const char *skip_reason = NULL;
-		if (t->subtest.skip_reason)
-			skip_reason = t->subtest.skip_reason(subtest);
-		if (skip_reason)
-			color_fprintf(stderr, PERF_COLOR_YELLOW, " Skip (%s)\n", skip_reason);
+		const char *reason = skip_reason(t, subtest);
+
+		if (reason)
+			color_fprintf(stderr, PERF_COLOR_YELLOW, " Skip (%s)\n", reason);
 		else
 			color_fprintf(stderr, PERF_COLOR_YELLOW, " Skip\n");
 	}
@@ -580,7 +358,7 @@ struct shell_test {
 	const char *file;
 };
 
-static int shell_test__run(struct test *test, int subdir __maybe_unused)
+static int shell_test__run(struct test_suite *test, int subdir __maybe_unused)
 {
 	int err;
 	char script[PATH_MAX];
@@ -622,24 +400,34 @@ static int run_shell_tests(int argc, const char *argv[], int i, int width,
 	for_each_shell_test(entlist, n_dirs, st.dir, ent) {
 		int curr = i++;
 		char desc[256];
-		struct test test = {
-			.desc = shell_test__description(desc, sizeof(desc), st.dir, ent->d_name),
-			.func = shell_test__run,
+		struct test_case test_cases[] = {
+			{
+				.desc = shell_test__description(desc,
+								sizeof(desc),
+								st.dir,
+								ent->d_name),
+				.run_case = shell_test__run,
+			},
+			{ .name = NULL, }
+		};
+		struct test_suite test_suite = {
+			.desc = test_cases[0].desc,
+			.test_cases = test_cases,
 			.priv = &st,
 		};
 
-		if (!perf_test__matches(test.desc, curr, argc, argv))
+		if (!perf_test__matches(test_suite.desc, curr, argc, argv))
 			continue;
 
 		st.file = ent->d_name;
-		pr_info("%2d: %-*s:", i, width, test.desc);
+		pr_info("%2d: %-*s:", i, width, test_suite.desc);
 
 		if (intlist__find(skiplist, i)) {
 			color_fprintf(stderr, PERF_COLOR_YELLOW, " Skip (user override)\n");
 			continue;
 		}
 
-		test_and_print(&test, false, -1);
+		test_and_print(&test_suite, 0);
 	}
 
 	for (e = 0; e < n_dirs; e++)
@@ -650,33 +438,31 @@ static int run_shell_tests(int argc, const char *argv[], int i, int width,
 
 static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist)
 {
-	struct test *t;
-	unsigned int j;
+	struct test_suite *t;
+	unsigned int j, k;
 	int i = 0;
 	int width = shell_tests__max_desc_width();
 
-	for_each_test(j, t) {
-		int len = strlen(t->desc);
+	for_each_test(j, k, t) {
+		int len = strlen(test_description(t, -1));
 
 		if (width < len)
 			width = len;
 	}
 
-	for_each_test(j, t) {
-		int curr = i++, err;
+	for_each_test(j, k, t) {
+		int curr = i++;
 		int subi;
 
-		if (!perf_test__matches(t->desc, curr, argc, argv)) {
+		if (!perf_test__matches(test_description(t, -1), curr, argc, argv)) {
 			bool skip = true;
 			int subn;
 
-			if (!t->subtest.get_nr)
-				continue;
-
-			subn = t->subtest.get_nr();
+			subn = num_subtests(t);
 
 			for (subi = 0; subi < subn; subi++) {
-				if (perf_test__matches(t->subtest.get_desc(subi), curr, argc, argv))
+				if (perf_test__matches(test_description(t, subi),
+							curr, argc, argv))
 					skip = false;
 			}
 
@@ -684,22 +470,17 @@ static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist)
 				continue;
 		}
 
-		if (t->is_supported && !t->is_supported()) {
-			pr_debug("%2d: %-*s: Disabled\n", i, width, t->desc);
-			continue;
-		}
-
-		pr_info("%2d: %-*s:", i, width, t->desc);
+		pr_info("%2d: %-*s:", i, width, test_description(t, -1));
 
 		if (intlist__find(skiplist, i)) {
 			color_fprintf(stderr, PERF_COLOR_YELLOW, " Skip (user override)\n");
 			continue;
 		}
 
-		if (!t->subtest.get_nr) {
-			test_and_print(t, false, -1);
+		if (!has_subtests(t)) {
+			test_and_print(t, -1);
 		} else {
-			int subn = t->subtest.get_nr();
+			int subn = num_subtests(t);
 			/*
 			 * minus 2 to align with normal testcases.
 			 * For subtest we print additional '.x' in number.
@@ -709,7 +490,6 @@ static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist)
 			 * 35.1: Basic BPF llvm compiling test                          : Ok
 			 */
 			int subw = width > 2 ? width - 2 : width;
-			bool skip = false;
 
 			if (subn <= 0) {
 				color_fprintf(stderr, PERF_COLOR_YELLOW,
@@ -719,21 +499,20 @@ static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist)
 			pr_info("\n");
 
 			for (subi = 0; subi < subn; subi++) {
-				int len = strlen(t->subtest.get_desc(subi));
+				int len = strlen(test_description(t, subi));
 
 				if (subw < len)
 					subw = len;
 			}
 
 			for (subi = 0; subi < subn; subi++) {
-				if (!perf_test__matches(t->subtest.get_desc(subi), curr, argc, argv))
+				if (!perf_test__matches(test_description(t, subi),
+							curr, argc, argv))
 					continue;
 
 				pr_info("%2d.%1d: %-*s:", i, subi + 1, subw,
-					t->subtest.get_desc(subi));
-				err = test_and_print(t, skip, subi);
-				if (err != TEST_OK && t->subtest.skip_if_fail)
-					skip = true;
+					test_description(t, subi));
+				test_and_print(t, subi);
 			}
 		}
 	}
@@ -759,7 +538,7 @@ static int perf_test__list_shell(int argc, const char **argv, int i)
 	for_each_shell_test(entlist, n_dirs, path, ent) {
 		int curr = i++;
 		char bf[256];
-		struct test t = {
+		struct test_suite t = {
 			.desc = shell_test__description(bf, sizeof(bf), path, ent->d_name),
 		};
 
@@ -778,26 +557,25 @@ static int perf_test__list_shell(int argc, const char **argv, int i)
 
 static int perf_test__list(int argc, const char **argv)
 {
-	unsigned int j;
-	struct test *t;
+	unsigned int j, k;
+	struct test_suite *t;
 	int i = 0;
 
-	for_each_test(j, t) {
+	for_each_test(j, k, t) {
 		int curr = i++;
 
-		if (!perf_test__matches(t->desc, curr, argc, argv) ||
-		    (t->is_supported && !t->is_supported()))
+		if (!perf_test__matches(test_description(t, -1), curr, argc, argv))
 			continue;
 
-		pr_info("%2d: %s\n", i, t->desc);
+		pr_info("%2d: %s\n", i, test_description(t, -1));
 
-		if (t->subtest.get_nr) {
-			int subn = t->subtest.get_nr();
+		if (has_subtests(t)) {
+			int subn = num_subtests(t);
 			int subi;
 
 			for (subi = 0; subi < subn; subi++)
 				pr_info("%2d:%1d: %s\n", i, subi + 1,
-					t->subtest.get_desc(subi));
+					test_description(t, subi));
 		}
 	}
 
diff --git a/tools/perf/tests/clang.c b/tools/perf/tests/clang.c
index 2577d3ed1531..a7111005d5b9 100644
--- a/tools/perf/tests/clang.c
+++ b/tools/perf/tests/clang.c
@@ -3,44 +3,30 @@
 #include "c++/clang-c.h"
 #include <linux/kernel.h>
 
-static struct {
-	int (*func)(void);
-	const char *desc;
-} clang_testcase_table[] = {
-#ifdef HAVE_LIBCLANGLLVM_SUPPORT
-	{
-		.func = test__clang_to_IR,
-		.desc = "builtin clang compile C source to IR",
-	},
-	{
-		.func = test__clang_to_obj,
-		.desc = "builtin clang compile C source to ELF object",
-	},
-#endif
-};
-
-int test__clang_subtest_get_nr(void)
-{
-	return (int)ARRAY_SIZE(clang_testcase_table);
-}
-
-const char *test__clang_subtest_get_desc(int i)
-{
-	if (i < 0 || i >= (int)ARRAY_SIZE(clang_testcase_table))
-		return NULL;
-	return clang_testcase_table[i].desc;
-}
-
 #ifndef HAVE_LIBCLANGLLVM_SUPPORT
-int test__clang(struct test *test __maybe_unused, int i __maybe_unused)
+static int test__clang_to_IR(struct test_suite *test __maybe_unused,
+			     int subtest __maybe_unused)
 {
 	return TEST_SKIP;
 }
-#else
-int test__clang(struct test *test __maybe_unused, int i)
+
+static int test__clang_to_obj(struct test_suite *test __maybe_unused,
+			      int subtest __maybe_unused)
 {
-	if (i < 0 || i >= (int)ARRAY_SIZE(clang_testcase_table))
-		return TEST_FAIL;
-	return clang_testcase_table[i].func();
+	return TEST_SKIP;
 }
 #endif
+
+static struct test_case clang_tests[] = {
+	TEST_CASE_REASON("builtin clang compile C source to IR", clang_to_IR,
+			 "not compiled in"),
+	TEST_CASE_REASON("builtin clang compile C source to ELF object",
+			 clang_to_obj,
+			 "not compiled in"),
+	{ .name = NULL, }
+};
+
+struct test_suite suite__clang = {
+	.desc = "builtin clang support",
+	.test_cases = clang_tests,
+};
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index f439bd49da19..5610767b407f 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -716,7 +716,7 @@ out_err:
 	return err;
 }
 
-int test__code_reading(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__code_reading(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 	int ret;
 
@@ -743,3 +743,5 @@ int test__code_reading(struct test *test __maybe_unused, int subtest __maybe_unu
 		return -1;
 	};
 }
+
+DEFINE_SUITE("Object code reading", code_reading);
diff --git a/tools/perf/tests/cpumap.c b/tools/perf/tests/cpumap.c
index 0472b110fe65..89a155092f85 100644
--- a/tools/perf/tests/cpumap.c
+++ b/tools/perf/tests/cpumap.c
@@ -75,7 +75,7 @@ static int process_event_cpus(struct perf_tool *tool __maybe_unused,
 }
 
 
-int test__cpu_map_synthesize(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__cpu_map_synthesize(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 	struct perf_cpu_map *cpus;
 
@@ -111,7 +111,7 @@ static int cpu_map_print(const char *str)
 	return !strcmp(buf, str);
 }
 
-int test__cpu_map_print(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__cpu_map_print(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 	TEST_ASSERT_VAL("failed to convert map", cpu_map_print("1"));
 	TEST_ASSERT_VAL("failed to convert map", cpu_map_print("1,5"));
@@ -123,7 +123,7 @@ int test__cpu_map_print(struct test *test __maybe_unused, int subtest __maybe_un
 	return 0;
 }
 
-int test__cpu_map_merge(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__cpu_map_merge(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 	struct perf_cpu_map *a = perf_cpu_map__new("4,2,1");
 	struct perf_cpu_map *b = perf_cpu_map__new("4,5,7");
@@ -137,3 +137,7 @@ int test__cpu_map_merge(struct test *test __maybe_unused, int subtest __maybe_un
 	perf_cpu_map__put(c);
 	return 0;
 }
+
+DEFINE_SUITE("Synthesize cpu map", cpu_map_synthesize);
+DEFINE_SUITE("Print cpu map", cpu_map_print);
+DEFINE_SUITE("Merge cpu map", cpu_map_merge);
diff --git a/tools/perf/tests/demangle-java-test.c b/tools/perf/tests/demangle-java-test.c
index 8f3b90832fb0..44d1be303b67 100644
--- a/tools/perf/tests/demangle-java-test.c
+++ b/tools/perf/tests/demangle-java-test.c
@@ -7,7 +7,7 @@
 #include "debug.h"
 #include "demangle-java.h"
 
-int test__demangle_java(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__demangle_java(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 	int ret = TEST_OK;
 	char *buf = NULL;
@@ -40,3 +40,5 @@ int test__demangle_java(struct test *test __maybe_unused, int subtest __maybe_un
 
 	return ret;
 }
+
+DEFINE_SUITE("Demangle Java", demangle_java);
diff --git a/tools/perf/tests/demangle-ocaml-test.c b/tools/perf/tests/demangle-ocaml-test.c
index 0043be812355..90a4285e2ad5 100644
--- a/tools/perf/tests/demangle-ocaml-test.c
+++ b/tools/perf/tests/demangle-ocaml-test.c
@@ -7,7 +7,7 @@
 #include "debug.h"
 #include "demangle-ocaml.h"
 
-int test__demangle_ocaml(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__demangle_ocaml(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 	int ret = TEST_OK;
 	char *buf = NULL;
@@ -41,3 +41,5 @@ int test__demangle_ocaml(struct test *test __maybe_unused, int subtest __maybe_u
 
 	return ret;
 }
+
+DEFINE_SUITE("Demangle OCaml", demangle_ocaml);
diff --git a/tools/perf/tests/dlfilter-test.c b/tools/perf/tests/dlfilter-test.c
index bc03b5df6828..84352d55347d 100644
--- a/tools/perf/tests/dlfilter-test.c
+++ b/tools/perf/tests/dlfilter-test.c
@@ -398,7 +398,7 @@ static void test_data__free(struct test_data *td)
 	}
 }
 
-int test__dlfilter(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__dlfilter(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 	struct test_data td = {.fd = -1};
 	int pid = getpid();
@@ -414,3 +414,5 @@ int test__dlfilter(struct test *test __maybe_unused, int subtest __maybe_unused)
 	test_data__free(&td);
 	return err;
 }
+
+DEFINE_SUITE("dlfilter C API", dlfilter);
diff --git a/tools/perf/tests/dso-data.c b/tools/perf/tests/dso-data.c
index 43e1b01e5afc..3419a4ab5590 100644
--- a/tools/perf/tests/dso-data.c
+++ b/tools/perf/tests/dso-data.c
@@ -113,7 +113,7 @@ static int dso__data_fd(struct dso *dso, struct machine *machine)
 	return fd;
 }
 
-int test__dso_data(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__dso_data(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 	struct machine machine;
 	struct dso *dso;
@@ -248,7 +248,7 @@ static int set_fd_limit(int n)
 	return setrlimit(RLIMIT_NOFILE, &rlim);
 }
 
-int test__dso_data_cache(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__dso_data_cache(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 	struct machine machine;
 	long nr_end, nr = open_files_cnt();
@@ -318,7 +318,7 @@ static long new_limit(int count)
 	return ret;
 }
 
-int test__dso_data_reopen(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__dso_data_reopen(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 	struct machine machine;
 	long nr_end, nr = open_files_cnt(), lim = new_limit(3);
@@ -393,3 +393,7 @@ int test__dso_data_reopen(struct test *test __maybe_unused, int subtest __maybe_
 	TEST_ASSERT_VAL("failed leaking files", nr == nr_end);
 	return 0;
 }
+
+DEFINE_SUITE("DSO data read", dso_data);
+DEFINE_SUITE("DSO data cache", dso_data_cache);
+DEFINE_SUITE("DSO data reopen", dso_data_reopen);
diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
index c756284b3b13..2dab2d262060 100644
--- a/tools/perf/tests/dwarf-unwind.c
+++ b/tools/perf/tests/dwarf-unwind.c
@@ -195,7 +195,8 @@ NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__krava_1(struct thread *th
 	return ret;
 }
 
-int test__dwarf_unwind(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__dwarf_unwind(struct test_suite *test __maybe_unused,
+			      int subtest __maybe_unused)
 {
 	struct machine *machine;
 	struct thread *thread;
@@ -237,3 +238,5 @@ int test__dwarf_unwind(struct test *test __maybe_unused, int subtest __maybe_unu
 	machine__delete(machine);
 	return err;
 }
+
+DEFINE_SUITE("Test dwarf unwind", dwarf_unwind);
diff --git a/tools/perf/tests/event-times.c b/tools/perf/tests/event-times.c
index 04ce4401f775..7606eb3df92f 100644
--- a/tools/perf/tests/event-times.c
+++ b/tools/perf/tests/event-times.c
@@ -216,7 +216,7 @@ out_err:
  * and checks that enabled and running times
  * match.
  */
-int test__event_times(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__event_times(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 	int err, ret = 0;
 
@@ -239,3 +239,5 @@ int test__event_times(struct test *test __maybe_unused, int subtest __maybe_unus
 #undef _T
 	return ret;
 }
+
+DEFINE_SUITE("Event times", event_times);
diff --git a/tools/perf/tests/event_update.c b/tools/perf/tests/event_update.c
index 44a50527f9d9..d01532d40acb 100644
--- a/tools/perf/tests/event_update.c
+++ b/tools/perf/tests/event_update.c
@@ -83,12 +83,11 @@ static int process_event_cpus(struct perf_tool *tool __maybe_unused,
 	return 0;
 }
 
-int test__event_update(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__event_update(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 	struct evsel *evsel;
 	struct event_name tmp;
 	struct evlist *evlist = evlist__new_default();
-	char *unit = strdup("KRAVA");
 
 	TEST_ASSERT_VAL("failed to get evlist", evlist);
 
@@ -99,7 +98,8 @@ int test__event_update(struct test *test __maybe_unused, int subtest __maybe_unu
 
 	perf_evlist__id_add(&evlist->core, &evsel->core, 0, 0, 123);
 
-	evsel->unit = unit;
+	free((char *)evsel->unit);
+	evsel->unit = strdup("KRAVA");
 
 	TEST_ASSERT_VAL("failed to synthesize attr update unit",
 			!perf_event__synthesize_event_update_unit(NULL, evsel, process_event_unit));
@@ -119,7 +119,8 @@ int test__event_update(struct test *test __maybe_unused, int subtest __maybe_unu
 	TEST_ASSERT_VAL("failed to synthesize attr update cpus",
 			!perf_event__synthesize_event_update_cpus(&tmp.tool, evsel, process_event_cpus));
 
-	free(unit);
 	evlist__delete(evlist);
 	return 0;
 }
+
+DEFINE_SUITE("Synthesize attr update", event_update);
diff --git a/tools/perf/tests/evsel-roundtrip-name.c b/tools/perf/tests/evsel-roundtrip-name.c
index 4e09f0a312af..fdbf17642e45 100644
--- a/tools/perf/tests/evsel-roundtrip-name.c
+++ b/tools/perf/tests/evsel-roundtrip-name.c
@@ -99,7 +99,8 @@ out_delete_evlist:
 #define perf_evsel__name_array_test(names, distance) \
 	__perf_evsel__name_array_test(names, ARRAY_SIZE(names), distance)
 
-int test__perf_evsel__roundtrip_name_test(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__perf_evsel__roundtrip_name_test(struct test_suite *test __maybe_unused,
+						 int subtest __maybe_unused)
 {
 	int err = 0, ret = 0;
 
@@ -120,3 +121,5 @@ int test__perf_evsel__roundtrip_name_test(struct test *test __maybe_unused, int
 
 	return ret;
 }
+
+DEFINE_SUITE("Roundtrip evsel->name", perf_evsel__roundtrip_name_test);
diff --git a/tools/perf/tests/evsel-tp-sched.c b/tools/perf/tests/evsel-tp-sched.c
index f9e34bd26cf3..cf4da3d748c2 100644
--- a/tools/perf/tests/evsel-tp-sched.c
+++ b/tools/perf/tests/evsel-tp-sched.c
@@ -32,7 +32,8 @@ static int evsel__test_field(struct evsel *evsel, const char *name, int size, bo
 	return ret;
 }
 
-int test__perf_evsel__tp_sched_test(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__perf_evsel__tp_sched_test(struct test_suite *test __maybe_unused,
+					   int subtest __maybe_unused)
 {
 	struct evsel *evsel = evsel__newtp("sched", "sched_switch");
 	int ret = 0;
@@ -87,3 +88,5 @@ int test__perf_evsel__tp_sched_test(struct test *test __maybe_unused, int subtes
 	evsel__delete(evsel);
 	return ret;
 }
+
+DEFINE_SUITE("Parse sched tracepoints fields", perf_evsel__tp_sched_test);
diff --git a/tools/perf/tests/expand-cgroup.c b/tools/perf/tests/expand-cgroup.c
index 80cff8a3558c..dfefe5b60eb2 100644
--- a/tools/perf/tests/expand-cgroup.c
+++ b/tools/perf/tests/expand-cgroup.c
@@ -221,8 +221,8 @@ out:
 	return ret;
 }
 
-int test__expand_cgroup_events(struct test *test __maybe_unused,
-			       int subtest __maybe_unused)
+static int test__expand_cgroup_events(struct test_suite *test __maybe_unused,
+				      int subtest __maybe_unused)
 {
 	int ret;
 
@@ -240,3 +240,5 @@ int test__expand_cgroup_events(struct test *test __maybe_unused,
 
 	return ret;
 }
+
+DEFINE_SUITE("Event expansion for cgroups", expand_cgroup_events);
diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c
index 077783223ce0..d54c5371c6a6 100644
--- a/tools/perf/tests/expr.c
+++ b/tools/perf/tests/expr.c
@@ -62,11 +62,11 @@ static int test(struct expr_parse_ctx *ctx, const char *e, double val2)
 	return 0;
 }
 
-int test__expr(struct test *t __maybe_unused, int subtest __maybe_unused)
+static int test__expr(struct test_suite *t __maybe_unused, int subtest __maybe_unused)
 {
 	struct expr_id_data *val_ptr;
 	const char *p;
-	double val;
+	double val, num_cpus, num_cores, num_dies, num_packages;
 	int ret;
 	struct expr_parse_ctx *ctx;
 
@@ -134,6 +134,16 @@ int test__expr(struct test *t __maybe_unused, int subtest __maybe_unused)
 	TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "EVENT2,param=3@",
 						    (void **)&val_ptr));
 
+	expr__ctx_clear(ctx);
+	TEST_ASSERT_VAL("find ids",
+			expr__find_ids("dash\\-event1 - dash\\-event2",
+				       NULL, ctx) == 0);
+	TEST_ASSERT_VAL("find ids", hashmap__size(ctx->ids) == 2);
+	TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "dash-event1",
+						    (void **)&val_ptr));
+	TEST_ASSERT_VAL("find ids", hashmap__find(ctx->ids, "dash-event2",
+						    (void **)&val_ptr));
+
 	/* Only EVENT1 or EVENT2 need be measured depending on the value of smt_on. */
 	expr__ctx_clear(ctx);
 	TEST_ASSERT_VAL("find ids",
@@ -151,7 +161,33 @@ int test__expr(struct test *t __maybe_unused, int subtest __maybe_unused)
 			NULL, ctx) == 0);
 	TEST_ASSERT_VAL("find ids", hashmap__size(ctx->ids) == 0);
 
+	/* Test toplogy constants appear well ordered. */
+	expr__ctx_clear(ctx);
+	TEST_ASSERT_VAL("#num_cpus", expr__parse(&num_cpus, ctx, "#num_cpus") == 0);
+	TEST_ASSERT_VAL("#num_cores", expr__parse(&num_cores, ctx, "#num_cores") == 0);
+	TEST_ASSERT_VAL("#num_cpus >= #num_cores", num_cpus >= num_cores);
+	TEST_ASSERT_VAL("#num_dies", expr__parse(&num_dies, ctx, "#num_dies") == 0);
+	TEST_ASSERT_VAL("#num_cores >= #num_dies", num_cores >= num_dies);
+	TEST_ASSERT_VAL("#num_packages", expr__parse(&num_packages, ctx, "#num_packages") == 0);
+
+	if (num_dies) // Some platforms do not have CPU die support, for example s390
+		TEST_ASSERT_VAL("#num_dies >= #num_packages", num_dies >= num_packages);
+
+	/*
+	 * Source count returns the number of events aggregating in a leader
+	 * event including the leader. Check parsing yields an id.
+	 */
+	expr__ctx_clear(ctx);
+	TEST_ASSERT_VAL("source count",
+			expr__find_ids("source_count(EVENT1)",
+			NULL, ctx) == 0);
+	TEST_ASSERT_VAL("source count", hashmap__size(ctx->ids) == 1);
+	TEST_ASSERT_VAL("source count", hashmap__find(ctx->ids, "EVENT1",
+							(void **)&val_ptr));
+
 	expr__ctx_free(ctx);
 
 	return 0;
 }
+
+DEFINE_SUITE("Simple expression parser", expr);
diff --git a/tools/perf/tests/fdarray.c b/tools/perf/tests/fdarray.c
index d9eca8e86a6b..40983c3574b1 100644
--- a/tools/perf/tests/fdarray.c
+++ b/tools/perf/tests/fdarray.c
@@ -28,7 +28,7 @@ static int fdarray__fprintf_prefix(struct fdarray *fda, const char *prefix, FILE
 	return printed + fdarray__fprintf(fda, fp);
 }
 
-int test__fdarray__filter(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__fdarray__filter(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 	int nr_fds, err = TEST_FAIL;
 	struct fdarray *fda = fdarray__new(5, 5);
@@ -89,7 +89,7 @@ out:
 	return err;
 }
 
-int test__fdarray__add(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__fdarray__add(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 	int err = TEST_FAIL;
 	struct fdarray *fda = fdarray__new(2, 2);
@@ -158,3 +158,6 @@ out_delete:
 out:
 	return err;
 }
+
+DEFINE_SUITE("Filter fds with revents mask in a fdarray", fdarray__filter);
+DEFINE_SUITE("Add fd to a fdarray, making it autogrow", fdarray__add);
diff --git a/tools/perf/tests/genelf.c b/tools/perf/tests/genelf.c
index f797f9823e89..95f3be1b683a 100644
--- a/tools/perf/tests/genelf.c
+++ b/tools/perf/tests/genelf.c
@@ -16,8 +16,8 @@
 
 #define TEMPL "/tmp/perf-test-XXXXXX"
 
-int test__jit_write_elf(struct test *test __maybe_unused,
-			int subtest __maybe_unused)
+static int test__jit_write_elf(struct test_suite *test __maybe_unused,
+			       int subtest __maybe_unused)
 {
 #ifdef HAVE_JITDUMP
 	static unsigned char x86_code[] = {
@@ -49,3 +49,5 @@ int test__jit_write_elf(struct test *test __maybe_unused,
 	return TEST_SKIP;
 #endif
 }
+
+DEFINE_SUITE("Test jit_write_elf", jit_write_elf);
diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c
index 890cb1f5bf53..17f4fcd6bdce 100644
--- a/tools/perf/tests/hists_cumulate.c
+++ b/tools/perf/tests/hists_cumulate.c
@@ -689,7 +689,7 @@ out:
 	return err;
 }
 
-int test__hists_cumulate(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__hists_cumulate(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 	int err = TEST_FAIL;
 	struct machines machines;
@@ -736,3 +736,5 @@ out:
 
 	return err;
 }
+
+DEFINE_SUITE("Cumulate child hist entries", hists_cumulate);
diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c
index ca6120cd1d90..08cbeb9e39ae 100644
--- a/tools/perf/tests/hists_filter.c
+++ b/tools/perf/tests/hists_filter.c
@@ -101,7 +101,7 @@ out:
 	return TEST_FAIL;
 }
 
-int test__hists_filter(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__hists_filter(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 	int err = TEST_FAIL;
 	struct machines machines;
@@ -325,3 +325,5 @@ out:
 
 	return err;
 }
+
+DEFINE_SUITE("Filter hist entries", hists_filter);
diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c
index a024d3f3a412..c575e13a850d 100644
--- a/tools/perf/tests/hists_link.c
+++ b/tools/perf/tests/hists_link.c
@@ -264,7 +264,7 @@ static int validate_link(struct hists *leader, struct hists *other)
 	return __validate_link(leader, 0) || __validate_link(other, 1);
 }
 
-int test__hists_link(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__hists_link(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 	int err = -1;
 	struct hists *hists, *first_hists;
@@ -339,3 +339,5 @@ out:
 
 	return err;
 }
+
+DEFINE_SUITE("Match and link multiple hists", hists_link);
diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c
index 8973f35df604..0bde4a768c15 100644
--- a/tools/perf/tests/hists_output.c
+++ b/tools/perf/tests/hists_output.c
@@ -575,7 +575,7 @@ out:
 	return err;
 }
 
-int test__hists_output(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__hists_output(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 	int err = TEST_FAIL;
 	struct machines machines;
@@ -623,3 +623,5 @@ out:
 
 	return err;
 }
+
+DEFINE_SUITE("Sort output of hist entries", hists_output);
diff --git a/tools/perf/tests/is_printable_array.c b/tools/perf/tests/is_printable_array.c
index 9c7b3baca4fe..f72de2457ff1 100644
--- a/tools/perf/tests/is_printable_array.c
+++ b/tools/perf/tests/is_printable_array.c
@@ -5,7 +5,7 @@
 #include "debug.h"
 #include "print_binary.h"
 
-int test__is_printable_array(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__is_printable_array(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 	char buf1[] = { 'k', 'r', 4, 'v', 'a', 0 };
 	char buf2[] = { 'k', 'r', 'a', 'v', 4, 0 };
@@ -36,3 +36,5 @@ int test__is_printable_array(struct test *test __maybe_unused, int subtest __may
 
 	return TEST_OK;
 }
+
+DEFINE_SUITE("is_printable_array", is_printable_array);
diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c
index a0438b0f0805..dd2067312452 100644
--- a/tools/perf/tests/keep-tracking.c
+++ b/tools/perf/tests/keep-tracking.c
@@ -61,7 +61,7 @@ static int find_comm(struct evlist *evlist, const char *comm)
  * when an event is disabled but a dummy software event is not disabled.  If the
  * test passes %0 is returned, otherwise %-1 is returned.
  */
-int test__keep_tracking(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__keep_tracking(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 	struct record_opts opts = {
 		.mmap_pages	     = UINT_MAX,
@@ -160,3 +160,5 @@ out_err:
 
 	return err;
 }
+
+DEFINE_SUITE("Use a dummy software event to keep tracking", keep_tracking);
diff --git a/tools/perf/tests/kmod-path.c b/tools/perf/tests/kmod-path.c
index e483210b176b..dfe1bd5dabaa 100644
--- a/tools/perf/tests/kmod-path.c
+++ b/tools/perf/tests/kmod-path.c
@@ -47,7 +47,7 @@ static int test_is_kernel_module(const char *path, int cpumode, bool expect)
 #define M(path, c, e) \
 	TEST_ASSERT_VAL("failed", !test_is_kernel_module(path, c, e))
 
-int test__kmod_path__parse(struct test *t __maybe_unused, int subtest __maybe_unused)
+static int test__kmod_path__parse(struct test_suite *t __maybe_unused, int subtest __maybe_unused)
 {
 	/* path                alloc_name  kmod  comp   name   */
 	T("/xxxx/xxxx/x-x.ko", true      , true, 0    , "[x_x]");
@@ -159,3 +159,5 @@ int test__kmod_path__parse(struct test *t __maybe_unused, int subtest __maybe_un
 
 	return 0;
 }
+
+DEFINE_SUITE("kmod_path__parse", kmod_path__parse);
diff --git a/tools/perf/tests/llvm.c b/tools/perf/tests/llvm.c
index 33e43cce9064..8ac0a3a457ef 100644
--- a/tools/perf/tests/llvm.c
+++ b/tools/perf/tests/llvm.c
@@ -124,7 +124,7 @@ out:
 	return ret;
 }
 
-int test__llvm(struct test *test __maybe_unused, int subtest)
+static int test__llvm(int subtest)
 {
 	int ret;
 	void *obj_buf = NULL;
@@ -148,32 +148,72 @@ int test__llvm(struct test *test __maybe_unused, int subtest)
 
 	return ret;
 }
+#endif //HAVE_LIBBPF_SUPPORT
 
-int test__llvm_subtest_get_nr(void)
+static int test__llvm__bpf_base_prog(struct test_suite *test __maybe_unused,
+				     int subtest __maybe_unused)
 {
-	return __LLVM_TESTCASE_MAX;
+#ifdef HAVE_LIBBPF_SUPPORT
+	return test__llvm(LLVM_TESTCASE_BASE);
+#else
+	pr_debug("Skip LLVM test because BPF support is not compiled\n");
+	return TEST_SKIP;
+#endif
 }
 
-const char *test__llvm_subtest_get_desc(int subtest)
-{
-	if ((subtest < 0) || (subtest >= __LLVM_TESTCASE_MAX))
-		return NULL;
-
-	return bpf_source_table[subtest].desc;
-}
-#else //HAVE_LIBBPF_SUPPORT
-int test__llvm(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__llvm__bpf_test_kbuild_prog(struct test_suite *test __maybe_unused,
+					    int subtest __maybe_unused)
 {
+#ifdef HAVE_LIBBPF_SUPPORT
+	return test__llvm(LLVM_TESTCASE_KBUILD);
+#else
+	pr_debug("Skip LLVM test because BPF support is not compiled\n");
 	return TEST_SKIP;
+#endif
 }
 
-int test__llvm_subtest_get_nr(void)
+static int test__llvm__bpf_test_prologue_prog(struct test_suite *test __maybe_unused,
+					      int subtest __maybe_unused)
 {
-	return 0;
+#ifdef HAVE_LIBBPF_SUPPORT
+	return test__llvm(LLVM_TESTCASE_BPF_PROLOGUE);
+#else
+	pr_debug("Skip LLVM test because BPF support is not compiled\n");
+	return TEST_SKIP;
+#endif
 }
 
-const char *test__llvm_subtest_get_desc(int subtest __maybe_unused)
+static int test__llvm__bpf_test_relocation(struct test_suite *test __maybe_unused,
+					   int subtest __maybe_unused)
 {
-	return NULL;
+#ifdef HAVE_LIBBPF_SUPPORT
+	return test__llvm(LLVM_TESTCASE_BPF_RELOCATION);
+#else
+	pr_debug("Skip LLVM test because BPF support is not compiled\n");
+	return TEST_SKIP;
+#endif
 }
-#endif // HAVE_LIBBPF_SUPPORT
+
+
+static struct test_case llvm_tests[] = {
+#ifdef HAVE_LIBBPF_SUPPORT
+	TEST_CASE("Basic BPF llvm compile", llvm__bpf_base_prog),
+	TEST_CASE("kbuild searching", llvm__bpf_test_kbuild_prog),
+	TEST_CASE("Compile source for BPF prologue generation",
+		  llvm__bpf_test_prologue_prog),
+	TEST_CASE("Compile source for BPF relocation", llvm__bpf_test_relocation),
+#else
+	TEST_CASE_REASON("Basic BPF llvm compile", llvm__bpf_base_prog, "not compiled in"),
+	TEST_CASE_REASON("kbuild searching", llvm__bpf_test_kbuild_prog, "not compiled in"),
+	TEST_CASE_REASON("Compile source for BPF prologue generation",
+			llvm__bpf_test_prologue_prog, "not compiled in"),
+	TEST_CASE_REASON("Compile source for BPF relocation",
+			llvm__bpf_test_relocation, "not compiled in"),
+#endif
+	{ .name = NULL, }
+};
+
+struct test_suite suite__llvm = {
+	.desc = "LLVM search and compile",
+	.test_cases = llvm_tests,
+};
diff --git a/tools/perf/tests/maps.c b/tools/perf/tests/maps.c
index 1ac72919fa35..e308a3296cef 100644
--- a/tools/perf/tests/maps.c
+++ b/tools/perf/tests/maps.c
@@ -33,7 +33,7 @@ static int check_maps(struct map_def *merged, unsigned int size, struct maps *ma
 	return TEST_OK;
 }
 
-int test__maps__merge_in(struct test *t __maybe_unused, int subtest __maybe_unused)
+static int test__maps__merge_in(struct test_suite *t __maybe_unused, int subtest __maybe_unused)
 {
 	struct maps maps;
 	unsigned int i;
@@ -120,3 +120,5 @@ int test__maps__merge_in(struct test *t __maybe_unused, int subtest __maybe_unus
 	maps__exit(&maps);
 	return TEST_OK;
 }
+
+DEFINE_SUITE("maps__merge_in", maps__merge_in);
diff --git a/tools/perf/tests/mem.c b/tools/perf/tests/mem.c
index 673a11a6cd1b..56014ec7d49d 100644
--- a/tools/perf/tests/mem.c
+++ b/tools/perf/tests/mem.c
@@ -23,7 +23,7 @@ static int check(union perf_mem_data_src data_src,
 	return 0;
 }
 
-int test__mem(struct test *text __maybe_unused, int subtest __maybe_unused)
+static int test__mem(struct test_suite *text __maybe_unused, int subtest __maybe_unused)
 {
 	int ret = 0;
 	union perf_mem_data_src src;
@@ -56,3 +56,5 @@ int test__mem(struct test *text __maybe_unused, int subtest __maybe_unused)
 
 	return ret;
 }
+
+DEFINE_SUITE("Test data source output", mem);
diff --git a/tools/perf/tests/mem2node.c b/tools/perf/tests/mem2node.c
index e4d0d58b97f8..b17b86391383 100644
--- a/tools/perf/tests/mem2node.c
+++ b/tools/perf/tests/mem2node.c
@@ -43,7 +43,7 @@ static unsigned long *get_bitmap(const char *str, int nbits)
 	return bm && map ? bm : NULL;
 }
 
-int test__mem2node(struct test *t __maybe_unused, int subtest __maybe_unused)
+static int test__mem2node(struct test_suite *t __maybe_unused, int subtest __maybe_unused)
 {
 	struct mem2node map;
 	struct memory_node nodes[3];
@@ -77,3 +77,5 @@ int test__mem2node(struct test *t __maybe_unused, int subtest __maybe_unused)
 	mem2node__exit(&map);
 	return 0;
 }
+
+DEFINE_SUITE("mem2node", mem2node);
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index d38757db2dc2..90b2feda31ac 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -29,7 +29,7 @@
  * Then it checks if the number of syscalls reported as perf events by
  * the kernel corresponds to the number of syscalls made.
  */
-int test__basic_mmap(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__basic_mmap(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 	int err = -1;
 	union perf_event *event;
@@ -164,3 +164,5 @@ out_free_threads:
 	perf_thread_map__put(threads);
 	return err;
 }
+
+DEFINE_SUITE("Read samples using the mmap interface", basic_mmap);
diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c
index 6f2da7a72f67..a4301fc7b770 100644
--- a/tools/perf/tests/mmap-thread-lookup.c
+++ b/tools/perf/tests/mmap-thread-lookup.c
@@ -224,7 +224,7 @@ static int mmap_events(synth_cb synth)
  *
  * by using all thread objects.
  */
-int test__mmap_thread_lookup(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__mmap_thread_lookup(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 	/* perf_event__synthesize_threads synthesize */
 	TEST_ASSERT_VAL("failed with sythesizing all",
@@ -236,3 +236,5 @@ int test__mmap_thread_lookup(struct test *test __maybe_unused, int subtest __may
 
 	return 0;
 }
+
+DEFINE_SUITE("Lookup mmap thread", mmap_thread_lookup);
diff --git a/tools/perf/tests/openat-syscall-all-cpus.c b/tools/perf/tests/openat-syscall-all-cpus.c
index f7dd6c463f04..cd3dd463783f 100644
--- a/tools/perf/tests/openat-syscall-all-cpus.c
+++ b/tools/perf/tests/openat-syscall-all-cpus.c
@@ -19,7 +19,8 @@
 #include "stat.h"
 #include "util/counts.h"
 
-int test__openat_syscall_event_on_all_cpus(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__openat_syscall_event_on_all_cpus(struct test_suite *test __maybe_unused,
+						  int subtest __maybe_unused)
 {
 	int err = -1, fd, cpu;
 	struct perf_cpu_map *cpus;
@@ -127,3 +128,5 @@ out_thread_map_delete:
 	perf_thread_map__put(threads);
 	return err;
 }
+
+DEFINE_SUITE("Detect openat syscall event on all cpus", openat_syscall_event_on_all_cpus);
diff --git a/tools/perf/tests/openat-syscall-tp-fields.c b/tools/perf/tests/openat-syscall-tp-fields.c
index 5e4af2f0f14a..a7b2800652e4 100644
--- a/tools/perf/tests/openat-syscall-tp-fields.c
+++ b/tools/perf/tests/openat-syscall-tp-fields.c
@@ -22,7 +22,8 @@
 #define AT_FDCWD       -100
 #endif
 
-int test__syscall_openat_tp_fields(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__syscall_openat_tp_fields(struct test_suite *test __maybe_unused,
+					  int subtest __maybe_unused)
 {
 	struct record_opts opts = {
 		.target = {
@@ -142,3 +143,5 @@ out_delete_evlist:
 out:
 	return err;
 }
+
+DEFINE_SUITE("syscalls:sys_enter_openat event fields", syscall_openat_tp_fields);
diff --git a/tools/perf/tests/openat-syscall.c b/tools/perf/tests/openat-syscall.c
index 85a8f0fe7aea..7f4c13c4b14d 100644
--- a/tools/perf/tests/openat-syscall.c
+++ b/tools/perf/tests/openat-syscall.c
@@ -13,7 +13,8 @@
 #include "tests.h"
 #include "util/counts.h"
 
-int test__openat_syscall_event(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__openat_syscall_event(struct test_suite *test __maybe_unused,
+				      int subtest __maybe_unused)
 {
 	int err = -1, fd;
 	struct evsel *evsel;
@@ -66,3 +67,5 @@ out_thread_map_delete:
 	perf_thread_map__put(threads);
 	return err;
 }
+
+DEFINE_SUITE("Detect openat syscall event", openat_syscall_event);
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 6af94639b14a..a508f1dbcb2a 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -2276,7 +2276,7 @@ static int test_pmu_events_alias(char *event, char *alias)
 	return test_event(&e);
 }
 
-int test__parse_events(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__parse_events(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 	int ret1, ret2 = 0;
 	char *event, *alias;
@@ -2319,3 +2319,5 @@ do {							\
 
 	return ret2;
 }
+
+DEFINE_SUITE("Parse event definition strings", parse_events);
diff --git a/tools/perf/tests/parse-metric.c b/tools/perf/tests/parse-metric.c
index dfc797ecc750..07b6f4ec024f 100644
--- a/tools/perf/tests/parse-metric.c
+++ b/tools/perf/tests/parse-metric.c
@@ -109,6 +109,7 @@ static void load_runtime_stat(struct runtime_stat *st, struct evlist *evlist,
 	struct evsel *evsel;
 	u64 count;
 
+	perf_stat__reset_shadow_stats();
 	evlist__for_each_entry(evlist, evsel) {
 		count = find_value(evsel->name, vals);
 		perf_stat__update_shadow_stats(evsel, count, 0, st);
@@ -369,7 +370,7 @@ static int test_metric_group(void)
 	return 0;
 }
 
-int test__parse_metric(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__parse_metric(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 	TEST_ASSERT_VAL("IPC failed", test_ipc() == 0);
 	TEST_ASSERT_VAL("frontend failed", test_frontend() == 0);
@@ -383,3 +384,5 @@ int test__parse_metric(struct test *test __maybe_unused, int subtest __maybe_unu
 	}
 	return 0;
 }
+
+DEFINE_SUITE("Parse and process metrics", parse_metric);
diff --git a/tools/perf/tests/parse-no-sample-id-all.c b/tools/perf/tests/parse-no-sample-id-all.c
index 471273676701..d62e31595ab2 100644
--- a/tools/perf/tests/parse-no-sample-id-all.c
+++ b/tools/perf/tests/parse-no-sample-id-all.c
@@ -67,7 +67,8 @@ struct test_attr_event {
  *
  * Return: %0 on success, %-1 if the test fails.
  */
-int test__parse_no_sample_id_all(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__parse_no_sample_id_all(struct test_suite *test __maybe_unused,
+					int subtest __maybe_unused)
 {
 	int err;
 
@@ -103,3 +104,5 @@ int test__parse_no_sample_id_all(struct test *test __maybe_unused, int subtest _
 
 	return 0;
 }
+
+DEFINE_SUITE("Parse with no sample_id_all bit set", parse_no_sample_id_all);
diff --git a/tools/perf/tests/pe-file-parsing.c b/tools/perf/tests/pe-file-parsing.c
index 58b90c42eb38..c09a9fae1689 100644
--- a/tools/perf/tests/pe-file-parsing.c
+++ b/tools/perf/tests/pe-file-parsing.c
@@ -68,7 +68,7 @@ static int run_dir(const char *d)
 	return TEST_OK;
 }
 
-int test__pe_file_parsing(struct test *test __maybe_unused,
+static int test__pe_file_parsing(struct test_suite *test __maybe_unused,
 			  int subtest __maybe_unused)
 {
 	struct stat st;
@@ -89,10 +89,12 @@ int test__pe_file_parsing(struct test *test __maybe_unused,
 
 #else
 
-int test__pe_file_parsing(struct test *test __maybe_unused,
+static int test__pe_file_parsing(struct test_suite *test __maybe_unused,
 			  int subtest __maybe_unused)
 {
 	return TEST_SKIP;
 }
 
 #endif
+
+DEFINE_SUITE("PE file support", pe_file_parsing);
diff --git a/tools/perf/tests/perf-hooks.c b/tools/perf/tests/perf-hooks.c
index dd865e0bea12..78cdeb89645e 100644
--- a/tools/perf/tests/perf-hooks.c
+++ b/tools/perf/tests/perf-hooks.c
@@ -26,7 +26,7 @@ static void the_hook(void *_hook_flags)
 	raise(SIGSEGV);
 }
 
-int test__perf_hooks(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__perf_hooks(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 	int hook_flags = 0;
 
@@ -45,3 +45,5 @@ int test__perf_hooks(struct test *test __maybe_unused, int subtest __maybe_unuse
 		return TEST_FAIL;
 	return TEST_OK;
 }
+
+DEFINE_SUITE("perf hooks", perf_hooks);
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index 0df471bf1590..6354465067b8 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -41,7 +41,7 @@ realloc:
 	return cpu;
 }
 
-int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__PERF_RECORD(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 	struct record_opts opts = {
 		.target = {
@@ -332,3 +332,5 @@ out_delete_evlist:
 out:
 	return (err < 0 || errs > 0) ? -1 : 0;
 }
+
+DEFINE_SUITE("PERF_RECORD_* events & perf_sample fields", PERF_RECORD);
diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c
index 7c56bc1f4cff..d12d0ad81801 100644
--- a/tools/perf/tests/perf-time-to-tsc.c
+++ b/tools/perf/tests/perf-time-to-tsc.c
@@ -23,6 +23,16 @@
 #include "pmu.h"
 #include "pmu-hybrid.h"
 
+/*
+ * Except x86_64/i386 and Arm64, other archs don't support TSC in perf.  Just
+ * enable the test for x86_64/i386 and Arm64 archs.
+ */
+#if defined(__x86_64__) || defined(__i386__) || defined(__aarch64__)
+#define TSC_IS_SUPPORTED 1
+#else
+#define TSC_IS_SUPPORTED 0
+#endif
+
 #define CHECK__(x) {				\
 	while ((x) < 0) {			\
 		pr_debug(#x " failed!\n");	\
@@ -45,7 +55,7 @@
  * %0 is returned, otherwise %-1 is returned.  If TSC conversion is not
  * supported then then the test passes but " (not supported)" is printed.
  */
-int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 	struct record_opts opts = {
 		.mmap_pages	     = UINT_MAX,
@@ -69,6 +79,11 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe
 	u64 test_time, comm1_time = 0, comm2_time = 0;
 	struct mmap *md;
 
+	if (!TSC_IS_SUPPORTED) {
+		pr_debug("Test not supported on this architecture");
+		return TEST_SKIP;
+	}
+
 	threads = thread_map__new(-1, getpid(), UINT_MAX);
 	CHECK_NOT_NULL__(threads);
 
@@ -185,15 +200,4 @@ out_err:
 	return err;
 }
 
-bool test__tsc_is_supported(void)
-{
-	/*
-	 * Except x86_64/i386 and Arm64, other archs don't support TSC in perf.
-	 * Just enable the test for x86_64/i386 and Arm64 archs.
-	 */
-#if defined(__x86_64__) || defined(__i386__) || defined(__aarch64__)
-	return true;
-#else
-	return false;
-#endif
-}
+DEFINE_SUITE("Convert perf time to TSC", perf_time_to_tsc);
diff --git a/tools/perf/tests/pfm.c b/tools/perf/tests/pfm.c
index e8fd0da0762b..71b76deb1f92 100644
--- a/tools/perf/tests/pfm.c
+++ b/tools/perf/tests/pfm.c
@@ -12,27 +12,6 @@
 #include <linux/kernel.h>
 
 #ifdef HAVE_LIBPFM
-static int test__pfm_events(void);
-static int test__pfm_group(void);
-#endif
-
-static const struct {
-	int (*func)(void);
-	const char *desc;
-} pfm_testcase_table[] = {
-#ifdef HAVE_LIBPFM
-	{
-		.func = test__pfm_events,
-		.desc = "test of individual --pfm-events",
-	},
-	{
-		.func = test__pfm_group,
-		.desc = "test groups of --pfm-events",
-	},
-#endif
-};
-
-#ifdef HAVE_LIBPFM
 static int count_pfm_events(struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel;
@@ -44,7 +23,8 @@ static int count_pfm_events(struct perf_evlist *evlist)
 	return count;
 }
 
-static int test__pfm_events(void)
+static int test__pfm_events(struct test_suite *test __maybe_unused,
+			    int subtest __maybe_unused)
 {
 	struct evlist *evlist;
 	struct option opt;
@@ -104,7 +84,8 @@ static int test__pfm_events(void)
 	return 0;
 }
 
-static int test__pfm_group(void)
+static int test__pfm_group(struct test_suite *test __maybe_unused,
+			   int subtest __maybe_unused)
 {
 	struct evlist *evlist;
 	struct option opt;
@@ -187,27 +168,27 @@ static int test__pfm_group(void)
 	}
 	return 0;
 }
-#endif
-
-const char *test__pfm_subtest_get_desc(int i)
-{
-	if (i < 0 || i >= (int)ARRAY_SIZE(pfm_testcase_table))
-		return NULL;
-	return pfm_testcase_table[i].desc;
-}
-
-int test__pfm_subtest_get_nr(void)
+#else
+static int test__pfm_events(struct test_suite *test __maybe_unused,
+			    int subtest __maybe_unused)
 {
-	return (int)ARRAY_SIZE(pfm_testcase_table);
+	return TEST_SKIP;
 }
 
-int test__pfm(struct test *test __maybe_unused, int i __maybe_unused)
+static int test__pfm_group(struct test_suite *test __maybe_unused,
+			   int subtest __maybe_unused)
 {
-#ifdef HAVE_LIBPFM
-	if (i < 0 || i >= (int)ARRAY_SIZE(pfm_testcase_table))
-		return TEST_FAIL;
-	return pfm_testcase_table[i].func();
-#else
 	return TEST_SKIP;
-#endif
 }
+#endif
+
+static struct test_case pfm_tests[] = {
+	TEST_CASE_REASON("test of individual --pfm-events", pfm_events, "not compiled in"),
+	TEST_CASE_REASON("test groups of --pfm-events", pfm_group, "not compiled in"),
+	{ .name = NULL, }
+};
+
+struct test_suite suite__pfm = {
+	.desc = "Test libpfm4 support",
+	.test_cases = pfm_tests,
+};
diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c
index 9ae894c406d8..df1c9a3cc05b 100644
--- a/tools/perf/tests/pmu-events.c
+++ b/tools/perf/tests/pmu-events.c
@@ -418,7 +418,8 @@ static int compare_alias_to_test_event(struct perf_pmu_alias *alias,
 }
 
 /* Verify generated events from pmu-events.c are as expected */
-static int test_pmu_event_table(void)
+static int test__pmu_event_table(struct test_suite *test __maybe_unused,
+				 int subtest __maybe_unused)
 {
 	const struct pmu_event *sys_event_tables = __test_pmu_get_sys_events_table();
 	const struct pmu_events_map *map = __test_pmu_get_events_map();
@@ -705,7 +706,8 @@ static struct perf_pmu_test_pmu test_pmus[] = {
 };
 
 /* Test that aliases generated are as expected */
-static int test_aliases(void)
+static int test__aliases(struct test_suite *test __maybe_unused,
+			int subtest __maybe_unused)
 {
 	struct perf_pmu *pmu = NULL;
 	unsigned long i;
@@ -892,7 +894,8 @@ out_err:
 
 }
 
-static int test_parsing(void)
+static int test__parsing(struct test_suite *test __maybe_unused,
+			 int subtest __maybe_unused)
 {
 	const struct pmu_events_map *cpus_map = pmu_events_map__find();
 	const struct pmu_events_map *map;
@@ -1034,7 +1037,8 @@ out:
  * or all defined cpus via the 'fake_pmu'
  * in parse_events.
  */
-static int test_parsing_fake(void)
+static int test__parsing_fake(struct test_suite *test __maybe_unused,
+			      int subtest __maybe_unused)
 {
 	const struct pmu_events_map *map;
 	const struct pmu_event *pe;
@@ -1068,55 +1072,16 @@ static int test_parsing_fake(void)
 	return 0;
 }
 
-static const struct {
-	int (*func)(void);
-	const char *desc;
-} pmu_events_testcase_table[] = {
-	{
-		.func = test_pmu_event_table,
-		.desc = "PMU event table sanity",
-	},
-	{
-		.func = test_aliases,
-		.desc = "PMU event map aliases",
-	},
-	{
-		.func = test_parsing,
-		.desc = "Parsing of PMU event table metrics",
-	},
-	{
-		.func = test_parsing_fake,
-		.desc = "Parsing of PMU event table metrics with fake PMUs",
-	},
+static struct test_case pmu_events_tests[] = {
+	TEST_CASE("PMU event table sanity", pmu_event_table),
+	TEST_CASE("PMU event map aliases", aliases),
+	TEST_CASE_REASON("Parsing of PMU event table metrics", parsing,
+			 "some metrics failed"),
+	TEST_CASE("Parsing of PMU event table metrics with fake PMUs", parsing_fake),
+	{ .name = NULL, }
 };
 
-const char *test__pmu_events_subtest_get_desc(int subtest)
-{
-	if (subtest < 0 ||
-	    subtest >= (int)ARRAY_SIZE(pmu_events_testcase_table))
-		return NULL;
-	return pmu_events_testcase_table[subtest].desc;
-}
-
-const char *test__pmu_events_subtest_skip_reason(int subtest)
-{
-	if (subtest < 0 ||
-	    subtest >= (int)ARRAY_SIZE(pmu_events_testcase_table))
-		return NULL;
-	if (pmu_events_testcase_table[subtest].func != test_parsing)
-		return NULL;
-	return "some metrics failed";
-}
-
-int test__pmu_events_subtest_get_nr(void)
-{
-	return (int)ARRAY_SIZE(pmu_events_testcase_table);
-}
-
-int test__pmu_events(struct test *test __maybe_unused, int subtest)
-{
-	if (subtest < 0 ||
-	    subtest >= (int)ARRAY_SIZE(pmu_events_testcase_table))
-		return TEST_FAIL;
-	return pmu_events_testcase_table[subtest].func();
-}
+struct test_suite suite__pmu_events = {
+	.desc = "PMU events",
+	.test_cases = pmu_events_tests,
+};
diff --git a/tools/perf/tests/pmu.c b/tools/perf/tests/pmu.c
index 714e6830a758..8507bd615e97 100644
--- a/tools/perf/tests/pmu.c
+++ b/tools/perf/tests/pmu.c
@@ -137,7 +137,7 @@ static struct list_head *test_terms_list(void)
 	return &terms;
 }
 
-int test__pmu(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__pmu(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 	char *format = test_format_dir_get();
 	LIST_HEAD(formats);
@@ -177,3 +177,5 @@ int test__pmu(struct test *test __maybe_unused, int subtest __maybe_unused)
 	test_format_dir_put(format);
 	return ret;
 }
+
+DEFINE_SUITE("Parse perf pmu format", pmu);
diff --git a/tools/perf/tests/python-use.c b/tools/perf/tests/python-use.c
index 98c6d474aa6f..6b990ee38575 100644
--- a/tools/perf/tests/python-use.c
+++ b/tools/perf/tests/python-use.c
@@ -9,7 +9,7 @@
 #include "tests.h"
 #include "util/debug.h"
 
-int test__python_use(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__python_use(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 	char *cmd;
 	int ret;
@@ -23,3 +23,5 @@ int test__python_use(struct test *test __maybe_unused, int subtest __maybe_unuse
 	free(cmd);
 	return ret;
 }
+
+DEFINE_SUITE("'import perf' in python", python_use);
diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c
index c83a11514129..07f2411b0ad4 100644
--- a/tools/perf/tests/sample-parsing.c
+++ b/tools/perf/tests/sample-parsing.c
@@ -36,7 +36,7 @@
  * These are based on the input value (213) specified
  * in branch_stack variable.
  */
-#define BS_EXPECTED_BE	0xa00d000000000000
+#define BS_EXPECTED_BE	0xa000d00000000000
 #define BS_EXPECTED_LE	0xd5000000
 #define FLAG(s)	s->branch_stack->entries[i].flags
 
@@ -368,7 +368,7 @@ out_free:
  * checks sample format bits separately and together.  If the test passes %0 is
  * returned, otherwise %-1 is returned.
  */
-int test__sample_parsing(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__sample_parsing(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 	const u64 rf[] = {4, 5, 6, 7, 12, 13, 14, 15};
 	u64 sample_type;
@@ -426,3 +426,5 @@ int test__sample_parsing(struct test *test __maybe_unused, int subtest __maybe_u
 
 	return 0;
 }
+
+DEFINE_SUITE("Sample parsing", sample_parsing);
diff --git a/tools/perf/tests/sdt.c b/tools/perf/tests/sdt.c
index ed76c693f65e..919712899251 100644
--- a/tools/perf/tests/sdt.c
+++ b/tools/perf/tests/sdt.c
@@ -76,7 +76,7 @@ static int search_cached_probe(const char *target,
 	return ret;
 }
 
-int test__sdt_event(struct test *test __maybe_unused, int subtests __maybe_unused)
+static int test__sdt_event(struct test_suite *test __maybe_unused, int subtests __maybe_unused)
 {
 	int ret = TEST_FAIL;
 	char __tempdir[] = "./test-buildid-XXXXXX";
@@ -114,9 +114,11 @@ error:
 	return ret;
 }
 #else
-int test__sdt_event(struct test *test __maybe_unused, int subtests __maybe_unused)
+static int test__sdt_event(struct test_suite *test __maybe_unused, int subtests __maybe_unused)
 {
 	pr_debug("Skip SDT event test because SDT support is not compiled\n");
 	return TEST_SKIP;
 }
 #endif
+
+DEFINE_SUITE("Probe SDT events", sdt_event);
diff --git a/tools/perf/tests/shell/record+zstd_comp_decomp.sh b/tools/perf/tests/shell/record+zstd_comp_decomp.sh
index 8a168cf8bacc..49bd875d5122 100755
--- a/tools/perf/tests/shell/record+zstd_comp_decomp.sh
+++ b/tools/perf/tests/shell/record+zstd_comp_decomp.sh
@@ -12,7 +12,7 @@ skip_if_no_z_record() {
 
 collect_z_record() {
 	echo "Collecting compressed record file:"
-	[[ "$(uname -m)" != s390x ]] && gflag='-g'
+	[ "$(uname -m)" != s390x ] && gflag='-g'
 	$perf_tool record -o $trace_file $gflag -z -F 5000 -- \
 		dd count=500 if=/dev/urandom of=/dev/null
 }
diff --git a/tools/perf/tests/shell/stat_all_pmu.sh b/tools/perf/tests/shell/stat_all_pmu.sh
index 2de7fd0394fd..b30dba455f36 100755
--- a/tools/perf/tests/shell/stat_all_pmu.sh
+++ b/tools/perf/tests/shell/stat_all_pmu.sh
@@ -7,11 +7,11 @@ set -e
 for p in $(perf list --raw-dump pmu); do
   echo "Testing $p"
   result=$(perf stat -e "$p" true 2>&1)
-  if [[ ! "$result" =~ "$p" ]] && [[ ! "$result" =~ "<not supported>" ]]; then
+  if ! echo "$result" | grep -q "$p" && ! echo "$result" | grep -q "<not supported>" ; then
     # We failed to see the event and it is supported. Possibly the workload was
     # too small so retry with something longer.
     result=$(perf stat -e "$p" perf bench internals synthesize 2>&1)
-    if [[ ! "$result" =~ "$p" ]]; then
+    if ! echo "$result" | grep -q "$p" ; then
       echo "Event '$p' not printed in:"
       echo "$result"
       exit 1
diff --git a/tools/perf/tests/shell/stat_bpf_counters.sh b/tools/perf/tests/shell/stat_bpf_counters.sh
index 2aed20dc2262..13473aeba489 100755
--- a/tools/perf/tests/shell/stat_bpf_counters.sh
+++ b/tools/perf/tests/shell/stat_bpf_counters.sh
@@ -23,7 +23,7 @@ compare_number()
 
 # skip if --bpf-counters is not supported
 if ! perf stat --bpf-counters true > /dev/null 2>&1; then
-	if [ "$1" == "-v" ]; then
+	if [ "$1" = "-v" ]; then
 		echo "Skipping: --bpf-counters not supported"
 		perf --no-pager stat --bpf-counters true || true
 	fi
diff --git a/tools/perf/tests/shell/test_arm_spe.sh b/tools/perf/tests/shell/test_arm_spe.sh
new file mode 100755
index 000000000000..e59044edc406
--- /dev/null
+++ b/tools/perf/tests/shell/test_arm_spe.sh
@@ -0,0 +1,89 @@
+#!/bin/sh
+# Check Arm SPE trace data recording and synthesized samples
+
+# Uses the 'perf record' to record trace data of Arm SPE events;
+# then verify if any SPE event samples are generated by SPE with
+# 'perf script' and 'perf report' commands.
+
+# SPDX-License-Identifier: GPL-2.0
+# German Gomez <german.gomez@arm.com>, 2021
+
+skip_if_no_arm_spe_event() {
+	perf list | egrep -q 'arm_spe_[0-9]+//' && return 0
+
+	# arm_spe event doesn't exist
+	return 2
+}
+
+skip_if_no_arm_spe_event || exit 2
+
+perfdata=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
+glb_err=0
+
+cleanup_files()
+{
+	rm -f ${perfdata}
+	exit $glb_err
+}
+
+trap cleanup_files exit term int
+
+arm_spe_report() {
+	if [ $2 != 0 ]; then
+		echo "$1: FAIL"
+		glb_err=$2
+	else
+		echo "$1: PASS"
+	fi
+}
+
+perf_script_samples() {
+	echo "Looking at perf.data file for dumping samples:"
+
+	# from arm-spe.c/arm_spe_synth_events()
+	events="(ld1-miss|ld1-access|llc-miss|lld-access|tlb-miss|tlb-access|branch-miss|remote-access|memory)"
+
+	# Below is an example of the samples dumping:
+	#	dd  3048 [002]          1    l1d-access:      ffffaa64999c __GI___libc_write+0x3c (/lib/aarch64-linux-gnu/libc-2.27.so)
+	#	dd  3048 [002]          1    tlb-access:      ffffaa64999c __GI___libc_write+0x3c (/lib/aarch64-linux-gnu/libc-2.27.so)
+	#	dd  3048 [002]          1        memory:      ffffaa64999c __GI___libc_write+0x3c (/lib/aarch64-linux-gnu/libc-2.27.so)
+	perf script -F,-time -i ${perfdata} 2>&1 | \
+		egrep " +$1 +[0-9]+ .* +${events}:(.*:)? +" > /dev/null 2>&1
+}
+
+perf_report_samples() {
+	echo "Looking at perf.data file for reporting samples:"
+
+	# Below is an example of the samples reporting:
+	#   73.04%    73.04%  dd    libc-2.27.so      [.] _dl_addr
+	#    7.71%     7.71%  dd    libc-2.27.so      [.] getenv
+	#    2.59%     2.59%  dd    ld-2.27.so        [.] strcmp
+	perf report --stdio -i ${perfdata} 2>&1 | \
+		egrep " +[0-9]+\.[0-9]+% +[0-9]+\.[0-9]+% +$1 " > /dev/null 2>&1
+}
+
+arm_spe_snapshot_test() {
+	echo "Recording trace with snapshot mode $perfdata"
+	perf record -o ${perfdata} -e arm_spe// -S \
+		-- dd if=/dev/zero of=/dev/null > /dev/null 2>&1 &
+	PERFPID=$!
+
+	# Wait for perf program
+	sleep 1
+
+	# Send signal to snapshot trace data
+	kill -USR2 $PERFPID
+
+	# Stop perf program
+	kill $PERFPID
+	wait $PERFPID
+
+	perf_script_samples dd &&
+	perf_report_samples dd
+
+	err=$?
+	arm_spe_report "SPE snapshot testing" $err
+}
+
+arm_spe_snapshot_test
+exit $glb_err
diff --git a/tools/perf/tests/stat.c b/tools/perf/tests/stat.c
index c1911501c39c..2eb096b5e6da 100644
--- a/tools/perf/tests/stat.c
+++ b/tools/perf/tests/stat.c
@@ -47,7 +47,8 @@ static int process_stat_config_event(struct perf_tool *tool __maybe_unused,
 	return 0;
 }
 
-int test__synthesize_stat_config(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__synthesize_stat_config(struct test_suite *test __maybe_unused,
+					int subtest __maybe_unused)
 {
 	struct perf_stat_config stat_config = {
 		.aggr_mode	= AGGR_CORE,
@@ -77,7 +78,7 @@ static int process_stat_event(struct perf_tool *tool __maybe_unused,
 	return 0;
 }
 
-int test__synthesize_stat(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__synthesize_stat(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 	struct perf_counts_values count;
 
@@ -103,7 +104,7 @@ static int process_stat_round_event(struct perf_tool *tool __maybe_unused,
 	return 0;
 }
 
-int test__synthesize_stat_round(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__synthesize_stat_round(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 	TEST_ASSERT_VAL("failed to synthesize stat_config",
 		!perf_event__synthesize_stat_round(NULL, 0xdeadbeef, PERF_STAT_ROUND_TYPE__INTERVAL,
@@ -111,3 +112,7 @@ int test__synthesize_stat_round(struct test *test __maybe_unused, int subtest __
 
 	return 0;
 }
+
+DEFINE_SUITE("Synthesize stat config", synthesize_stat_config);
+DEFINE_SUITE("Synthesize stat", synthesize_stat);
+DEFINE_SUITE("Synthesize stat round", synthesize_stat_round);
diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
index 74988846be1d..9cd6fec375ee 100644
--- a/tools/perf/tests/sw-clock.c
+++ b/tools/perf/tests/sw-clock.c
@@ -133,7 +133,7 @@ out_delete_evlist:
 	return err;
 }
 
-int test__sw_clock_freq(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__sw_clock_freq(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 	int ret;
 
@@ -143,3 +143,5 @@ int test__sw_clock_freq(struct test *test __maybe_unused, int subtest __maybe_un
 
 	return ret;
 }
+
+DEFINE_SUITE("Software clock events period values", sw_clock_freq);
diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c
index 62c0ec21aaa8..0c0c2328bf4e 100644
--- a/tools/perf/tests/switch-tracking.c
+++ b/tools/perf/tests/switch-tracking.c
@@ -321,7 +321,7 @@ out_free_nodes:
  * evsel->core.system_wide and evsel->tracking flags (respectively) with other events
  * sometimes enabled or disabled.
  */
-int test__switch_tracking(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__switch_tracking(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 	const char *sched_switch = "sched:sched_switch";
 	struct switch_tracking switch_tracking = { .tids = NULL, };
@@ -588,3 +588,5 @@ out_err:
 	err = -1;
 	goto out;
 }
+
+DEFINE_SUITE("Track with sched_switch", switch_tracking);
diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index 4c2969db59b0..25f075fa9125 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -39,7 +39,7 @@ static void workload_exec_failed_signal(int signo __maybe_unused,
  * if the number of exit event reported by the kernel is 1 or not
  * in order to check the kernel returns correct number of event.
  */
-int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__task_exit(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 	int err = -1;
 	union perf_event *event;
@@ -151,3 +151,5 @@ out_delete_evlist:
 	evlist__delete(evlist);
 	return err;
 }
+
+DEFINE_SUITE("Number of exit events of a simple workload", task_exit);
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index fe1306f58495..8f65098110fc 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -27,112 +27,146 @@ enum {
 	TEST_SKIP = -2,
 };
 
-struct test {
+struct test_suite;
+
+typedef int (*test_fnptr)(struct test_suite *, int);
+
+struct test_case {
+	const char *name;
+	const char *desc;
+	const char *skip_reason;
+	test_fnptr run_case;
+};
+
+struct test_suite {
 	const char *desc;
-	int (*func)(struct test *test, int subtest);
-	struct {
-		bool skip_if_fail;
-		int (*get_nr)(void);
-		const char *(*get_desc)(int subtest);
-		const char *(*skip_reason)(int subtest);
-	} subtest;
-	bool (*is_supported)(void);
+	struct test_case *test_cases;
 	void *priv;
 };
 
+#define DECLARE_SUITE(name) \
+	extern struct test_suite suite__##name;
+
+#define TEST_CASE(description, _name)			\
+	{						\
+		.name = #_name,				\
+		.desc = description,			\
+		.run_case = test__##_name,		\
+	}
+
+#define TEST_CASE_REASON(description, _name, _reason)	\
+	{						\
+		.name = #_name,				\
+		.desc = description,			\
+		.run_case = test__##_name,		\
+		.skip_reason = _reason,			\
+	}
+
+#define DEFINE_SUITE(description, _name)		\
+	struct test_case tests__##_name[] = {           \
+		TEST_CASE(description, _name),		\
+		{	.name = NULL, }			\
+	};						\
+	struct test_suite suite__##_name = {		\
+		.desc = description,			\
+		.test_cases = tests__##_name,		\
+	}
+
 /* Tests */
-int test__vmlinux_matches_kallsyms(struct test *test, int subtest);
-int test__openat_syscall_event(struct test *test, int subtest);
-int test__openat_syscall_event_on_all_cpus(struct test *test, int subtest);
-int test__basic_mmap(struct test *test, int subtest);
-int test__PERF_RECORD(struct test *test, int subtest);
-int test__perf_evsel__roundtrip_name_test(struct test *test, int subtest);
-int test__perf_evsel__tp_sched_test(struct test *test, int subtest);
-int test__syscall_openat_tp_fields(struct test *test, int subtest);
-int test__pmu(struct test *test, int subtest);
-int test__pmu_events(struct test *test, int subtest);
-const char *test__pmu_events_subtest_get_desc(int subtest);
-const char *test__pmu_events_subtest_skip_reason(int subtest);
-int test__pmu_events_subtest_get_nr(void);
-int test__attr(struct test *test, int subtest);
-int test__dso_data(struct test *test, int subtest);
-int test__dso_data_cache(struct test *test, int subtest);
-int test__dso_data_reopen(struct test *test, int subtest);
-int test__parse_events(struct test *test, int subtest);
-int test__hists_link(struct test *test, int subtest);
-int test__python_use(struct test *test, int subtest);
-int test__bp_signal(struct test *test, int subtest);
-int test__bp_signal_overflow(struct test *test, int subtest);
-int test__bp_accounting(struct test *test, int subtest);
-int test__wp(struct test *test, int subtest);
-const char *test__wp_subtest_get_desc(int subtest);
-const char *test__wp_subtest_skip_reason(int subtest);
-int test__wp_subtest_get_nr(void);
-int test__task_exit(struct test *test, int subtest);
-int test__mem(struct test *test, int subtest);
-int test__sw_clock_freq(struct test *test, int subtest);
-int test__code_reading(struct test *test, int subtest);
-int test__sample_parsing(struct test *test, int subtest);
-int test__keep_tracking(struct test *test, int subtest);
-int test__parse_no_sample_id_all(struct test *test, int subtest);
-int test__dwarf_unwind(struct test *test, int subtest);
-int test__expr(struct test *test, int subtest);
-int test__hists_filter(struct test *test, int subtest);
-int test__mmap_thread_lookup(struct test *test, int subtest);
-int test__thread_maps_share(struct test *test, int subtest);
-int test__hists_output(struct test *test, int subtest);
-int test__hists_cumulate(struct test *test, int subtest);
-int test__switch_tracking(struct test *test, int subtest);
-int test__fdarray__filter(struct test *test, int subtest);
-int test__fdarray__add(struct test *test, int subtest);
-int test__kmod_path__parse(struct test *test, int subtest);
-int test__thread_map(struct test *test, int subtest);
-int test__llvm(struct test *test, int subtest);
-const char *test__llvm_subtest_get_desc(int subtest);
-int test__llvm_subtest_get_nr(void);
-int test__bpf(struct test *test, int subtest);
-const char *test__bpf_subtest_get_desc(int subtest);
-int test__bpf_subtest_get_nr(void);
-int test__session_topology(struct test *test, int subtest);
-int test__thread_map_synthesize(struct test *test, int subtest);
-int test__thread_map_remove(struct test *test, int subtest);
-int test__cpu_map_synthesize(struct test *test, int subtest);
-int test__synthesize_stat_config(struct test *test, int subtest);
-int test__synthesize_stat(struct test *test, int subtest);
-int test__synthesize_stat_round(struct test *test, int subtest);
-int test__event_update(struct test *test, int subtest);
-int test__event_times(struct test *test, int subtest);
-int test__backward_ring_buffer(struct test *test, int subtest);
-int test__cpu_map_print(struct test *test, int subtest);
-int test__cpu_map_merge(struct test *test, int subtest);
-int test__sdt_event(struct test *test, int subtest);
-int test__is_printable_array(struct test *test, int subtest);
-int test__bitmap_print(struct test *test, int subtest);
-int test__perf_hooks(struct test *test, int subtest);
-int test__clang(struct test *test, int subtest);
-const char *test__clang_subtest_get_desc(int subtest);
-int test__clang_subtest_get_nr(void);
-int test__unit_number__scnprint(struct test *test, int subtest);
-int test__mem2node(struct test *t, int subtest);
-int test__maps__merge_in(struct test *t, int subtest);
-int test__time_utils(struct test *t, int subtest);
-int test__jit_write_elf(struct test *test, int subtest);
-int test__api_io(struct test *test, int subtest);
-int test__demangle_java(struct test *test, int subtest);
-int test__demangle_ocaml(struct test *test, int subtest);
-int test__pfm(struct test *test, int subtest);
-const char *test__pfm_subtest_get_desc(int subtest);
-int test__pfm_subtest_get_nr(void);
-int test__parse_metric(struct test *test, int subtest);
-int test__pe_file_parsing(struct test *test, int subtest);
-int test__expand_cgroup_events(struct test *test, int subtest);
-int test__perf_time_to_tsc(struct test *test, int subtest);
-int test__dlfilter(struct test *test, int subtest);
-
-bool test__bp_signal_is_supported(void);
-bool test__bp_account_is_supported(void);
-bool test__wp_is_supported(void);
-bool test__tsc_is_supported(void);
+DECLARE_SUITE(vmlinux_matches_kallsyms);
+DECLARE_SUITE(openat_syscall_event);
+DECLARE_SUITE(openat_syscall_event_on_all_cpus);
+DECLARE_SUITE(basic_mmap);
+DECLARE_SUITE(PERF_RECORD);
+DECLARE_SUITE(perf_evsel__roundtrip_name_test);
+DECLARE_SUITE(perf_evsel__tp_sched_test);
+DECLARE_SUITE(syscall_openat_tp_fields);
+DECLARE_SUITE(pmu);
+DECLARE_SUITE(pmu_events);
+DECLARE_SUITE(attr);
+DECLARE_SUITE(dso_data);
+DECLARE_SUITE(dso_data_cache);
+DECLARE_SUITE(dso_data_reopen);
+DECLARE_SUITE(parse_events);
+DECLARE_SUITE(hists_link);
+DECLARE_SUITE(python_use);
+DECLARE_SUITE(bp_signal);
+DECLARE_SUITE(bp_signal_overflow);
+DECLARE_SUITE(bp_accounting);
+DECLARE_SUITE(wp);
+DECLARE_SUITE(task_exit);
+DECLARE_SUITE(mem);
+DECLARE_SUITE(sw_clock_freq);
+DECLARE_SUITE(code_reading);
+DECLARE_SUITE(sample_parsing);
+DECLARE_SUITE(keep_tracking);
+DECLARE_SUITE(parse_no_sample_id_all);
+DECLARE_SUITE(dwarf_unwind);
+DECLARE_SUITE(expr);
+DECLARE_SUITE(hists_filter);
+DECLARE_SUITE(mmap_thread_lookup);
+DECLARE_SUITE(thread_maps_share);
+DECLARE_SUITE(hists_output);
+DECLARE_SUITE(hists_cumulate);
+DECLARE_SUITE(switch_tracking);
+DECLARE_SUITE(fdarray__filter);
+DECLARE_SUITE(fdarray__add);
+DECLARE_SUITE(kmod_path__parse);
+DECLARE_SUITE(thread_map);
+DECLARE_SUITE(llvm);
+DECLARE_SUITE(bpf);
+DECLARE_SUITE(session_topology);
+DECLARE_SUITE(thread_map_synthesize);
+DECLARE_SUITE(thread_map_remove);
+DECLARE_SUITE(cpu_map_synthesize);
+DECLARE_SUITE(synthesize_stat_config);
+DECLARE_SUITE(synthesize_stat);
+DECLARE_SUITE(synthesize_stat_round);
+DECLARE_SUITE(event_update);
+DECLARE_SUITE(event_times);
+DECLARE_SUITE(backward_ring_buffer);
+DECLARE_SUITE(cpu_map_print);
+DECLARE_SUITE(cpu_map_merge);
+DECLARE_SUITE(sdt_event);
+DECLARE_SUITE(is_printable_array);
+DECLARE_SUITE(bitmap_print);
+DECLARE_SUITE(perf_hooks);
+DECLARE_SUITE(clang);
+DECLARE_SUITE(unit_number__scnprint);
+DECLARE_SUITE(mem2node);
+DECLARE_SUITE(maps__merge_in);
+DECLARE_SUITE(time_utils);
+DECLARE_SUITE(jit_write_elf);
+DECLARE_SUITE(api_io);
+DECLARE_SUITE(demangle_java);
+DECLARE_SUITE(demangle_ocaml);
+DECLARE_SUITE(pfm);
+DECLARE_SUITE(parse_metric);
+DECLARE_SUITE(pe_file_parsing);
+DECLARE_SUITE(expand_cgroup_events);
+DECLARE_SUITE(perf_time_to_tsc);
+DECLARE_SUITE(dlfilter);
+
+/*
+ * PowerPC and S390 do not support creation of instruction breakpoints using the
+ * perf_event interface.
+ *
+ * ARM requires explicit rounding down of the instruction pointer in Thumb mode,
+ * and then requires the single-step to be handled explicitly in the overflow
+ * handler to avoid stepping into the SIGIO handler and getting stuck on the
+ * breakpointed instruction.
+ *
+ * Since arm64 has the same issue with arm for the single-step handling, this
+ * case also gets stuck on the breakpointed instruction.
+ *
+ * Just disable the test for these architectures until these issues are
+ * resolved.
+ */
+#if defined(__powerpc__) || defined(__s390x__) || defined(__arm__) || defined(__aarch64__)
+#define BP_SIGNAL_IS_SUPPORTED 0
+#else
+#define BP_SIGNAL_IS_SUPPORTED 1
+#endif
 
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
 struct thread;
@@ -142,7 +176,7 @@ int test__arch_unwind_sample(struct perf_sample *sample,
 #endif
 
 #if defined(__arm__)
-int test__vectors_page(struct test *test, int subtest);
+DECLARE_SUITE(vectors_page);
 #endif
 
 #endif /* TESTS_H */
diff --git a/tools/perf/tests/thread-map.c b/tools/perf/tests/thread-map.c
index d1e208b4a571..e413c1387fcb 100644
--- a/tools/perf/tests/thread-map.c
+++ b/tools/perf/tests/thread-map.c
@@ -19,7 +19,7 @@ struct machine;
 #define NAME	(const char *) "perf"
 #define NAMEUL	(unsigned long) NAME
 
-int test__thread_map(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__thread_map(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 	struct perf_thread_map *map;
 
@@ -86,7 +86,7 @@ static int process_event(struct perf_tool *tool __maybe_unused,
 	return 0;
 }
 
-int test__thread_map_synthesize(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__thread_map_synthesize(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 	struct perf_thread_map *threads;
 
@@ -106,7 +106,7 @@ int test__thread_map_synthesize(struct test *test __maybe_unused, int subtest __
 	return 0;
 }
 
-int test__thread_map_remove(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__thread_map_remove(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 	struct perf_thread_map *threads;
 	char *str;
@@ -145,3 +145,7 @@ int test__thread_map_remove(struct test *test __maybe_unused, int subtest __mayb
 	perf_thread_map__put(threads);
 	return 0;
 }
+
+DEFINE_SUITE("Thread map", thread_map);
+DEFINE_SUITE("Synthesize thread map", thread_map_synthesize);
+DEFINE_SUITE("Remove thread map", thread_map_remove);
diff --git a/tools/perf/tests/thread-maps-share.c b/tools/perf/tests/thread-maps-share.c
index 9371484973f2..84edd82c519e 100644
--- a/tools/perf/tests/thread-maps-share.c
+++ b/tools/perf/tests/thread-maps-share.c
@@ -4,7 +4,7 @@
 #include "thread.h"
 #include "debug.h"
 
-int test__thread_maps_share(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__thread_maps_share(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 	struct machines machines;
 	struct machine *machine;
@@ -96,3 +96,5 @@ int test__thread_maps_share(struct test *test __maybe_unused, int subtest __mayb
 	machines__exit(&machines);
 	return 0;
 }
+
+DEFINE_SUITE("Share thread maps", thread_maps_share);
diff --git a/tools/perf/tests/time-utils-test.c b/tools/perf/tests/time-utils-test.c
index fe57ca3b6e54..38df10373c1e 100644
--- a/tools/perf/tests/time-utils-test.c
+++ b/tools/perf/tests/time-utils-test.c
@@ -131,7 +131,7 @@ out:
 	return pass;
 }
 
-int test__time_utils(struct test *t __maybe_unused, int subtest __maybe_unused)
+static int test__time_utils(struct test_suite *t __maybe_unused, int subtest __maybe_unused)
 {
 	bool pass = true;
 
@@ -249,3 +249,5 @@ int test__time_utils(struct test *t __maybe_unused, int subtest __maybe_unused)
 
 	return pass ? 0 : TEST_FAIL;
 }
+
+DEFINE_SUITE("time utils", time_utils);
diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c
index 4574c46260d9..869986139146 100644
--- a/tools/perf/tests/topology.c
+++ b/tools/perf/tests/topology.c
@@ -175,7 +175,7 @@ static int check_cpu_topology(char *path, struct perf_cpu_map *map)
 	return 0;
 }
 
-int test__session_topology(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__session_topology(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
 {
 	char path[PATH_MAX];
 	struct perf_cpu_map *map;
@@ -201,3 +201,5 @@ free_path:
 	unlink(path);
 	return ret;
 }
+
+DEFINE_SUITE("Session topology", session_topology);
diff --git a/tools/perf/tests/unit_number__scnprintf.c b/tools/perf/tests/unit_number__scnprintf.c
index 3721757435da..88bcada1c78f 100644
--- a/tools/perf/tests/unit_number__scnprintf.c
+++ b/tools/perf/tests/unit_number__scnprintf.c
@@ -7,7 +7,7 @@
 #include "units.h"
 #include "debug.h"
 
-int test__unit_number__scnprint(struct test *t __maybe_unused, int subtest __maybe_unused)
+static int test__unit_number__scnprint(struct test_suite *t __maybe_unused, int subtest __maybe_unused)
 {
 	struct {
 		u64		 n;
@@ -38,3 +38,5 @@ int test__unit_number__scnprint(struct test *t __maybe_unused, int subtest __may
 
 	return TEST_OK;
 }
+
+DEFINE_SUITE("unit_number__scnprintf", unit_number__scnprint);
diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c
index 4f884aabc7f4..e80df13c0420 100644
--- a/tools/perf/tests/vmlinux-kallsyms.c
+++ b/tools/perf/tests/vmlinux-kallsyms.c
@@ -111,7 +111,8 @@ static bool is_ignored_symbol(const char *name, char type)
 	return false;
 }
 
-int test__vmlinux_matches_kallsyms(struct test *test __maybe_unused, int subtest __maybe_unused)
+static int test__vmlinux_matches_kallsyms(struct test_suite *test __maybe_unused,
+					int subtest __maybe_unused)
 {
 	int err = -1;
 	struct rb_node *nd;
@@ -352,3 +353,5 @@ out:
 	machine__exit(&vmlinux);
 	return err;
 }
+
+DEFINE_SUITE("vmlinux symtab matches kallsyms", vmlinux_matches_kallsyms);
diff --git a/tools/perf/tests/wp.c b/tools/perf/tests/wp.c
index 9387fa76faa5..9d4c45184e71 100644
--- a/tools/perf/tests/wp.c
+++ b/tools/perf/tests/wp.c
@@ -21,6 +21,7 @@ do {                                            \
 volatile u64 data1;
 volatile u8 data2[3];
 
+#ifndef __s390x__
 static int wp_read(int fd, long long *count, int size)
 {
 	int ret = read(fd, count, size);
@@ -61,9 +62,14 @@ static int __event(int wp_type, void *wp_addr, unsigned long wp_len)
 
 	return fd;
 }
+#endif
 
-static int wp_ro_test(void)
+static int test__wp_ro(struct test_suite *test __maybe_unused,
+		       int subtest __maybe_unused)
 {
+#if defined(__s390x__) || defined(__x86_64__) || defined(__i386__)
+	return TEST_SKIP;
+#else
 	int fd;
 	unsigned long tmp, tmp1 = rand();
 
@@ -79,10 +85,15 @@ static int wp_ro_test(void)
 
 	close(fd);
 	return 0;
+#endif
 }
 
-static int wp_wo_test(void)
+static int test__wp_wo(struct test_suite *test __maybe_unused,
+		       int subtest __maybe_unused)
 {
+#if defined(__s390x__)
+	return TEST_SKIP;
+#else
 	int fd;
 	unsigned long tmp, tmp1 = rand();
 
@@ -98,10 +109,15 @@ static int wp_wo_test(void)
 
 	close(fd);
 	return 0;
+#endif
 }
 
-static int wp_rw_test(void)
+static int test__wp_rw(struct test_suite *test __maybe_unused,
+		       int subtest __maybe_unused)
 {
+#if defined(__s390x__)
+	return TEST_SKIP;
+#else
 	int fd;
 	unsigned long tmp, tmp1 = rand();
 
@@ -118,10 +134,15 @@ static int wp_rw_test(void)
 
 	close(fd);
 	return 0;
+#endif
 }
 
-static int wp_modify_test(void)
+static int test__wp_modify(struct test_suite *test __maybe_unused,
+			   int subtest __maybe_unused)
 {
+#if defined(__s390x__)
+	return TEST_SKIP;
+#else
 	int fd, ret;
 	unsigned long tmp = rand();
 	struct perf_event_attr new_attr;
@@ -163,93 +184,18 @@ static int wp_modify_test(void)
 
 	close(fd);
 	return 0;
-}
-
-static bool wp_ro_supported(void)
-{
-#if defined (__x86_64__) || defined (__i386__)
-	return false;
-#else
-	return true;
-#endif
-}
-
-static const char *wp_ro_skip_msg(void)
-{
-#if defined (__x86_64__) || defined (__i386__)
-	return "missing hardware support";
-#else
-	return NULL;
 #endif
 }
 
-static struct {
-	const char *desc;
-	int (*target_func)(void);
-	bool (*is_supported)(void);
-	const char *(*skip_msg)(void);
-} wp_testcase_table[] = {
-	{
-		.desc = "Read Only Watchpoint",
-		.target_func = &wp_ro_test,
-		.is_supported = &wp_ro_supported,
-		.skip_msg = &wp_ro_skip_msg,
-	},
-	{
-		.desc = "Write Only Watchpoint",
-		.target_func = &wp_wo_test,
-	},
-	{
-		.desc = "Read / Write Watchpoint",
-		.target_func = &wp_rw_test,
-	},
-	{
-		.desc = "Modify Watchpoint",
-		.target_func = &wp_modify_test,
-	},
+static struct test_case wp_tests[] = {
+	TEST_CASE_REASON("Read Only Watchpoint", wp_ro, "missing hardware support"),
+	TEST_CASE_REASON("Write Only Watchpoint", wp_wo, "missing hardware support"),
+	TEST_CASE_REASON("Read / Write Watchpoint", wp_rw, "missing hardware support"),
+	TEST_CASE_REASON("Modify Watchpoint", wp_modify, "missing hardware support"),
+	{ .name = NULL, }
 };
 
-int test__wp_subtest_get_nr(void)
-{
-	return (int)ARRAY_SIZE(wp_testcase_table);
-}
-
-const char *test__wp_subtest_get_desc(int i)
-{
-	if (i < 0 || i >= (int)ARRAY_SIZE(wp_testcase_table))
-		return NULL;
-	return wp_testcase_table[i].desc;
-}
-
-const char *test__wp_subtest_skip_reason(int i)
-{
-	if (i < 0 || i >= (int)ARRAY_SIZE(wp_testcase_table))
-		return NULL;
-	if (!wp_testcase_table[i].skip_msg)
-		return NULL;
-	return wp_testcase_table[i].skip_msg();
-}
-
-int test__wp(struct test *test __maybe_unused, int i)
-{
-	if (i < 0 || i >= (int)ARRAY_SIZE(wp_testcase_table))
-		return TEST_FAIL;
-
-	if (wp_testcase_table[i].is_supported &&
-	    !wp_testcase_table[i].is_supported())
-		return TEST_SKIP;
-
-	return !wp_testcase_table[i].target_func() ? TEST_OK : TEST_FAIL;
-}
-
-/* The s390 so far does not have support for
- * instruction breakpoint using the perf_event_open() system call.
- */
-bool test__wp_is_supported(void)
-{
-#if defined(__s390x__)
-	return false;
-#else
-	return true;
-#endif
-}
+struct test_suite suite__wp = {
+	.desc = "Watchpoint",
+	.test_cases = wp_tests,
+};
diff --git a/tools/perf/trace/beauty/beauty.h b/tools/perf/trace/beauty/beauty.h
index d6dfe68a7612..f527a46ab4e7 100644
--- a/tools/perf/trace/beauty/beauty.h
+++ b/tools/perf/trace/beauty/beauty.h
@@ -62,6 +62,8 @@ size_t pid__scnprintf_fd(struct trace *trace, pid_t pid, int fd, char *bf, size_
 
 extern struct strarray strarray__socket_families;
 
+extern struct strarray strarray__socket_level;
+
 /**
  * augmented_arg: extra payload for syscall pointer arguments
  
@@ -230,6 +232,9 @@ size_t syscall_arg__scnprintf_sockaddr(char *bf, size_t size, struct syscall_arg
 size_t syscall_arg__scnprintf_socket_protocol(char *bf, size_t size, struct syscall_arg *arg);
 #define SCA_SK_PROTO syscall_arg__scnprintf_socket_protocol
 
+size_t syscall_arg__scnprintf_socket_level(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_SK_LEVEL syscall_arg__scnprintf_socket_level
+
 size_t syscall_arg__scnprintf_statx_flags(char *bf, size_t size, struct syscall_arg *arg);
 #define SCA_STATX_FLAGS syscall_arg__scnprintf_statx_flags
 
diff --git a/tools/perf/trace/beauty/sockaddr.c b/tools/perf/trace/beauty/sockaddr.c
index cd110634ab09..2e0e867c0c1b 100644
--- a/tools/perf/trace/beauty/sockaddr.c
+++ b/tools/perf/trace/beauty/sockaddr.c
@@ -7,7 +7,7 @@
 #include <sys/un.h>
 #include <arpa/inet.h>
 
-#include "trace/beauty/generated/socket_arrays.c"
+#include "trace/beauty/generated/sockaddr.c"
 DEFINE_STRARRAY(socket_families, "PF_");
 
 static size_t af_inet__scnprintf(struct sockaddr *sa, char *bf, size_t size)
diff --git a/tools/perf/trace/beauty/sockaddr.sh b/tools/perf/trace/beauty/sockaddr.sh
new file mode 100755
index 000000000000..3820e5c82293
--- /dev/null
+++ b/tools/perf/trace/beauty/sockaddr.sh
@@ -0,0 +1,24 @@
+#!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
+
+# This one uses a copy from the kernel sources headers that is in a
+# place used just for these tools/perf/beauty/ usage, we shouldn't not
+# put it in tools/include/linux otherwise they would be used in the
+# normal compiler building process and would drag needless stuff from the
+# kernel.
+
+# When what these scripts need is already in tools/include/ then use it,
+# otherwise grab and check the copy from the kernel sources just for these
+# string table building scripts.
+
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/perf/trace/beauty/include/linux/
+
+printf "static const char *socket_families[] = {\n"
+# #define AF_LOCAL	1	/* POSIX name for AF_UNIX	*/
+regex='^#define[[:space:]]+AF_(\w+)[[:space:]]+([[:digit:]]+).*'
+
+egrep $regex ${header_dir}/socket.h | \
+	sed -r "s/$regex/\2 \1/g"	| \
+	xargs printf "\t[%s] = \"%s\",\n" | \
+	egrep -v "\"(UNIX|MAX)\""
+printf "};\n"
diff --git a/tools/perf/trace/beauty/socket.c b/tools/perf/trace/beauty/socket.c
index f23a3dda2902..b0870c7b48e5 100644
--- a/tools/perf/trace/beauty/socket.c
+++ b/tools/perf/trace/beauty/socket.c
@@ -9,9 +9,10 @@
 #include <sys/types.h>
 #include <sys/socket.h>
 
+#include "trace/beauty/generated/socket.c"
+
 static size_t socket__scnprintf_ipproto(int protocol, char *bf, size_t size, bool show_prefix)
 {
-#include "trace/beauty/generated/socket_ipproto_array.c"
 	static DEFINE_STRARRAY(socket_ipproto, "IPPROTO_");
 
 	return strarray__scnprintf(&strarray__socket_ipproto, bf, size, "%d", show_prefix, protocol);
@@ -26,3 +27,21 @@ size_t syscall_arg__scnprintf_socket_protocol(char *bf, size_t size, struct sysc
 
 	return syscall_arg__scnprintf_int(bf, size, arg);
 }
+
+static size_t socket__scnprintf_level(int level, char *bf, size_t size, bool show_prefix)
+{
+#if defined(__alpha__) || defined(__hppa__) || defined(__mips__) || defined(__sparc__)
+	const int sol_socket = 0xffff;
+#else
+	const int sol_socket = 1;
+#endif
+	if (level == sol_socket)
+		return scnprintf(bf, size, "%sSOCKET", show_prefix ? "SOL_" : "");
+
+	return strarray__scnprintf(&strarray__socket_level, bf, size, "%d", show_prefix, level);
+}
+
+size_t syscall_arg__scnprintf_socket_level(char *bf, size_t size, struct syscall_arg *arg)
+{
+	return socket__scnprintf_level(arg->val, bf, size, arg->show_string_prefix);
+}
diff --git a/tools/perf/trace/beauty/socket.sh b/tools/perf/trace/beauty/socket.sh
index 3820e5c82293..76330acb27e5 100755
--- a/tools/perf/trace/beauty/socket.sh
+++ b/tools/perf/trace/beauty/socket.sh
@@ -1,24 +1,28 @@
 #!/bin/sh
 # SPDX-License-Identifier: LGPL-2.1
 
-# This one uses a copy from the kernel sources headers that is in a
-# place used just for these tools/perf/beauty/ usage, we shouldn't not
-# put it in tools/include/linux otherwise they would be used in the
-# normal compiler building process and would drag needless stuff from the
-# kernel.
+if [ $# -gt 0 ] ; then
+	uapi_header_dir=$1
+	beauty_header_dir=$2
+else
+	uapi_header_dir=tools/include/uapi/linux/
+	beauty_header_dir=tools/perf/trace/beauty/include/linux/
+fi
 
-# When what these scripts need is already in tools/include/ then use it,
-# otherwise grab and check the copy from the kernel sources just for these
-# string table building scripts.
+printf "static const char *socket_ipproto[] = {\n"
+ipproto_regex='^[[:space:]]+IPPROTO_(\w+)[[:space:]]+=[[:space:]]+([[:digit:]]+),.*'
 
-[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/perf/trace/beauty/include/linux/
+egrep $ipproto_regex ${uapi_header_dir}/in.h | \
+	sed -r "s/$ipproto_regex/\2 \1/g"	| \
+	sort -n | xargs printf "\t[%s] = \"%s\",\n"
+printf "};\n\n"
 
-printf "static const char *socket_families[] = {\n"
-# #define AF_LOCAL	1	/* POSIX name for AF_UNIX	*/
-regex='^#define[[:space:]]+AF_(\w+)[[:space:]]+([[:digit:]]+).*'
+printf "static const char *socket_level[] = {\n"
+socket_level_regex='^#define[[:space:]]+SOL_(\w+)[[:space:]]+([[:digit:]]+)([[:space:]]+\/.*)?'
 
-egrep $regex ${header_dir}/socket.h | \
-	sed -r "s/$regex/\2 \1/g"	| \
-	xargs printf "\t[%s] = \"%s\",\n" | \
-	egrep -v "\"(UNIX|MAX)\""
-printf "};\n"
+egrep $socket_level_regex ${beauty_header_dir}/socket.h | \
+	sed -r "s/$socket_level_regex/\2 \1/g"	| \
+	sort -n | xargs printf "\t[%s] = \"%s\",\n"
+printf "};\n\n"
+
+printf 'DEFINE_STRARRAY(socket_level, "SOL_");\n'
diff --git a/tools/perf/trace/beauty/socket_ipproto.sh b/tools/perf/trace/beauty/socket_ipproto.sh
deleted file mode 100755
index de0f2f29017f..000000000000
--- a/tools/perf/trace/beauty/socket_ipproto.sh
+++ /dev/null
@@ -1,12 +0,0 @@
-#!/bin/sh
-# SPDX-License-Identifier: LGPL-2.1
-
-[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
-
-printf "static const char *socket_ipproto[] = {\n"
-regex='^[[:space:]]+IPPROTO_(\w+)[[:space:]]+=[[:space:]]+([[:digit:]]+),.*'
-
-egrep $regex ${header_dir}/in.h | \
-	sed -r "s/$regex/\2 \1/g"	| \
-	sort | xargs printf "\t[%s] = \"%s\",\n"
-printf "};\n"
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index c1f24d004852..5075ecead5f3 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -535,6 +535,18 @@ struct perf_hpp_list perf_hpp_list = {
 #undef __HPP_SORT_ACC_FN
 #undef __HPP_SORT_RAW_FN
 
+static void fmt_free(struct perf_hpp_fmt *fmt)
+{
+	/*
+	 * At this point fmt should be completely
+	 * unhooked, if not it's a bug.
+	 */
+	BUG_ON(!list_empty(&fmt->list));
+	BUG_ON(!list_empty(&fmt->sort_list));
+
+	if (fmt->free)
+		fmt->free(fmt);
+}
 
 void perf_hpp__init(void)
 {
@@ -598,9 +610,10 @@ void perf_hpp_list__prepend_sort_field(struct perf_hpp_list *list,
 	list_add(&format->sort_list, &list->sorts);
 }
 
-void perf_hpp__column_unregister(struct perf_hpp_fmt *format)
+static void perf_hpp__column_unregister(struct perf_hpp_fmt *format)
 {
 	list_del_init(&format->list);
+	fmt_free(format);
 }
 
 void perf_hpp__cancel_cumulate(void)
@@ -672,19 +685,6 @@ next:
 }
 
 
-static void fmt_free(struct perf_hpp_fmt *fmt)
-{
-	/*
-	 * At this point fmt should be completely
-	 * unhooked, if not it's a bug.
-	 */
-	BUG_ON(!list_empty(&fmt->list));
-	BUG_ON(!list_empty(&fmt->sort_list));
-
-	if (fmt->free)
-		fmt->free(fmt);
-}
-
 void perf_hpp__reset_output_field(struct perf_hpp_list *list)
 {
 	struct perf_hpp_fmt *fmt, *tmp;
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 8511af55fc3a..01900689dc00 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1255,6 +1255,17 @@ int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool r
 	return ins__scnprintf(&dl->ins, bf, size, &dl->ops, max_ins_name);
 }
 
+void annotation__init(struct annotation *notes)
+{
+	pthread_mutex_init(&notes->lock, NULL);
+}
+
+void annotation__exit(struct annotation *notes)
+{
+	annotated_source__delete(notes->src);
+	pthread_mutex_destroy(&notes->lock);
+}
+
 static void annotation_line__add(struct annotation_line *al, struct list_head *head)
 {
 	list_add_tail(&al->node, head);
@@ -3132,7 +3143,7 @@ int symbol__annotate2(struct map_symbol *ms, struct evsel *evsel,
 	notes->nr_events = nr_pcnt;
 
 	annotation__update_column_widths(notes);
-	sym->annotate2 = true;
+	sym->annotate2 = 1;
 
 	return 0;
 
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 3757416bcf46..986f2bbe4870 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -299,6 +299,9 @@ struct annotation {
 	struct annotated_source *src;
 };
 
+void annotation__init(struct annotation *notes);
+void annotation__exit(struct annotation *notes);
+
 static inline int annotation__cycles_width(struct annotation *notes)
 {
 	if (notes->have_cycles && notes->options->show_minmax_cycle)
diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c
index 32fe41835fa6..3fc528c9270c 100644
--- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c
+++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c
@@ -151,6 +151,7 @@ static int arm_spe_read_record(struct arm_spe_decoder *decoder)
 	u64 payload, ip;
 
 	memset(&decoder->record, 0x0, sizeof(decoder->record));
+	decoder->record.context_id = (u64)-1;
 
 	while (1) {
 		err = arm_spe_get_next_packet(decoder);
@@ -180,6 +181,7 @@ static int arm_spe_read_record(struct arm_spe_decoder *decoder)
 		case ARM_SPE_COUNTER:
 			break;
 		case ARM_SPE_CONTEXT:
+			decoder->record.context_id = payload;
 			break;
 		case ARM_SPE_OP_TYPE:
 			if (idx == SPE_OP_PKT_HDR_CLASS_LD_ST_ATOMIC) {
diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h
index 59bdb7309674..46a8556a9e95 100644
--- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h
+++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h
@@ -38,6 +38,7 @@ struct arm_spe_record {
 	u64 timestamp;
 	u64 virt_addr;
 	u64 phys_addr;
+	u64 context_id;
 };
 
 struct arm_spe_insn;
diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
index 58b7069c5a5f..fccac06b573a 100644
--- a/tools/perf/util/arm-spe.c
+++ b/tools/perf/util/arm-spe.c
@@ -51,6 +51,7 @@ struct arm_spe {
 	u8				timeless_decoding;
 	u8				data_queued;
 
+	u64				sample_type;
 	u8				sample_flc;
 	u8				sample_llc;
 	u8				sample_tlb;
@@ -71,6 +72,7 @@ struct arm_spe {
 	u64				kernel_start;
 
 	unsigned long			num_events;
+	u8				use_ctx_pkt_for_pid;
 };
 
 struct arm_spe_queue {
@@ -100,7 +102,7 @@ static void arm_spe_dump(struct arm_spe *spe __maybe_unused,
 	const char *color = PERF_COLOR_BLUE;
 
 	color_fprintf(stdout, color,
-		      ". ... ARM SPE data: size %zu bytes\n",
+		      ". ... ARM SPE data: size %#zx bytes\n",
 		      len);
 
 	while (len) {
@@ -226,6 +228,44 @@ static inline u8 arm_spe_cpumode(struct arm_spe *spe, u64 ip)
 		PERF_RECORD_MISC_USER;
 }
 
+static void arm_spe_set_pid_tid_cpu(struct arm_spe *spe,
+				    struct auxtrace_queue *queue)
+{
+	struct arm_spe_queue *speq = queue->priv;
+	pid_t tid;
+
+	tid = machine__get_current_tid(spe->machine, speq->cpu);
+	if (tid != -1) {
+		speq->tid = tid;
+		thread__zput(speq->thread);
+	} else
+		speq->tid = queue->tid;
+
+	if ((!speq->thread) && (speq->tid != -1)) {
+		speq->thread = machine__find_thread(spe->machine, -1,
+						    speq->tid);
+	}
+
+	if (speq->thread) {
+		speq->pid = speq->thread->pid_;
+		if (queue->cpu == -1)
+			speq->cpu = speq->thread->cpu;
+	}
+}
+
+static int arm_spe_set_tid(struct arm_spe_queue *speq, pid_t tid)
+{
+	struct arm_spe *spe = speq->spe;
+	int err = machine__set_current_tid(spe->machine, speq->cpu, -1, tid);
+
+	if (err)
+		return err;
+
+	arm_spe_set_pid_tid_cpu(spe, &spe->queues.queue_array[speq->queue_nr]);
+
+	return 0;
+}
+
 static void arm_spe_prep_sample(struct arm_spe *spe,
 				struct arm_spe_queue *speq,
 				union perf_event *event,
@@ -248,6 +288,12 @@ static void arm_spe_prep_sample(struct arm_spe *spe,
 	event->sample.header.size = sizeof(struct perf_event_header);
 }
 
+static int arm_spe__inject_event(union perf_event *event, struct perf_sample *sample, u64 type)
+{
+	event->header.size = perf_event__sample_event_size(sample, type, 0);
+	return perf_event__synthesize_sample(event, type, 0, sample);
+}
+
 static inline int
 arm_spe_deliver_synth_event(struct arm_spe *spe,
 			    struct arm_spe_queue *speq __maybe_unused,
@@ -256,6 +302,12 @@ arm_spe_deliver_synth_event(struct arm_spe *spe,
 {
 	int ret;
 
+	if (spe->synth_opts.inject) {
+		ret = arm_spe__inject_event(event, sample, spe->sample_type);
+		if (ret)
+			return ret;
+	}
+
 	ret = perf_session__deliver_synth_event(spe->session, event, sample);
 	if (ret)
 		pr_err("ARM SPE: failed to deliver event, error %d\n", ret);
@@ -460,6 +512,19 @@ static int arm_spe_run_decoder(struct arm_spe_queue *speq, u64 *timestamp)
 		 * can correlate samples between Arm SPE trace data and other
 		 * perf events with correct time ordering.
 		 */
+
+		/*
+		 * Update pid/tid info.
+		 */
+		record = &speq->decoder->record;
+		if (!spe->timeless_decoding && record->context_id != (u64)-1) {
+			ret = arm_spe_set_tid(speq, record->context_id);
+			if (ret)
+				return ret;
+
+			spe->use_ctx_pkt_for_pid = true;
+		}
+
 		ret = arm_spe_sample(speq);
 		if (ret)
 			return ret;
@@ -586,31 +651,6 @@ static bool arm_spe__is_timeless_decoding(struct arm_spe *spe)
 	return timeless_decoding;
 }
 
-static void arm_spe_set_pid_tid_cpu(struct arm_spe *spe,
-				    struct auxtrace_queue *queue)
-{
-	struct arm_spe_queue *speq = queue->priv;
-	pid_t tid;
-
-	tid = machine__get_current_tid(spe->machine, speq->cpu);
-	if (tid != -1) {
-		speq->tid = tid;
-		thread__zput(speq->thread);
-	} else
-		speq->tid = queue->tid;
-
-	if ((!speq->thread) && (speq->tid != -1)) {
-		speq->thread = machine__find_thread(spe->machine, -1,
-						    speq->tid);
-	}
-
-	if (speq->thread) {
-		speq->pid = speq->thread->pid_;
-		if (queue->cpu == -1)
-			speq->cpu = speq->thread->cpu;
-	}
-}
-
 static int arm_spe_process_queues(struct arm_spe *spe, u64 timestamp)
 {
 	unsigned int queue_nr;
@@ -641,7 +681,12 @@ static int arm_spe_process_queues(struct arm_spe *spe, u64 timestamp)
 			ts = timestamp;
 		}
 
-		arm_spe_set_pid_tid_cpu(spe, queue);
+		/*
+		 * A previous context-switch event has set pid/tid in the machine's context, so
+		 * here we need to update the pid/tid in the thread and SPE queue.
+		 */
+		if (!spe->use_ctx_pkt_for_pid)
+			arm_spe_set_pid_tid_cpu(spe, queue);
 
 		ret = arm_spe_run_decoder(speq, &ts);
 		if (ret < 0) {
@@ -681,6 +726,25 @@ static int arm_spe_process_timeless_queues(struct arm_spe *spe, pid_t tid,
 	return 0;
 }
 
+static int arm_spe_context_switch(struct arm_spe *spe, union perf_event *event,
+				  struct perf_sample *sample)
+{
+	pid_t pid, tid;
+	int cpu;
+
+	if (!(event->header.misc & PERF_RECORD_MISC_SWITCH_OUT))
+		return 0;
+
+	pid = event->context_switch.next_prev_pid;
+	tid = event->context_switch.next_prev_tid;
+	cpu = sample->cpu;
+
+	if (tid == -1)
+		pr_warning("context_switch event has no tid\n");
+
+	return machine__set_current_tid(spe->machine, cpu, pid, tid);
+}
+
 static int arm_spe_process_event(struct perf_session *session,
 				 union perf_event *event,
 				 struct perf_sample *sample,
@@ -718,6 +782,13 @@ static int arm_spe_process_event(struct perf_session *session,
 		}
 	} else if (timestamp) {
 		err = arm_spe_process_queues(spe, timestamp);
+		if (err)
+			return err;
+
+		if (!spe->use_ctx_pkt_for_pid &&
+		    (event->header.type == PERF_RECORD_SWITCH_CPU_WIDE ||
+		    event->header.type == PERF_RECORD_SWITCH))
+			err = arm_spe_context_switch(spe, event, sample);
 	}
 
 	return err;
@@ -783,7 +854,15 @@ static int arm_spe_flush(struct perf_session *session __maybe_unused,
 		return arm_spe_process_timeless_queues(spe, -1,
 				MAX_TIMESTAMP - 1);
 
-	return arm_spe_process_queues(spe, MAX_TIMESTAMP);
+	ret = arm_spe_process_queues(spe, MAX_TIMESTAMP);
+	if (ret)
+		return ret;
+
+	if (!spe->use_ctx_pkt_for_pid)
+		ui__warning("Arm SPE CONTEXT packets not found in the traces.\n"
+			    "Matching of TIDs to SPE events could be inaccurate.\n");
+
+	return 0;
 }
 
 static void arm_spe_free_queue(void *priv)
@@ -920,6 +999,8 @@ arm_spe_synth_events(struct arm_spe *spe, struct perf_session *session)
 	else
 		attr.sample_type |= PERF_SAMPLE_TIME;
 
+	spe->sample_type = attr.sample_type;
+
 	attr.exclude_user = evsel->core.attr.exclude_user;
 	attr.exclude_kernel = evsel->core.attr.exclude_kernel;
 	attr.exclude_hv = evsel->core.attr.exclude_hv;
diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c
index 4d3b4cdce176..a517eaa51eb3 100644
--- a/tools/perf/util/bpf-event.c
+++ b/tools/perf/util/bpf-event.c
@@ -33,6 +33,33 @@ struct btf * __weak btf__load_from_kernel_by_id(__u32 id)
        return err ? ERR_PTR(err) : btf;
 }
 
+struct bpf_program * __weak
+bpf_object__next_program(const struct bpf_object *obj, struct bpf_program *prev)
+{
+#pragma GCC diagnostic push
+#pragma GCC diagnostic ignored "-Wdeprecated-declarations"
+	return bpf_program__next(prev, obj);
+#pragma GCC diagnostic pop
+}
+
+struct bpf_map * __weak
+bpf_object__next_map(const struct bpf_object *obj, const struct bpf_map *prev)
+{
+#pragma GCC diagnostic push
+#pragma GCC diagnostic ignored "-Wdeprecated-declarations"
+	return bpf_map__next(prev, obj);
+#pragma GCC diagnostic pop
+}
+
+const void * __weak
+btf__raw_data(const struct btf *btf_ro, __u32 *size)
+{
+#pragma GCC diagnostic push
+#pragma GCC diagnostic ignored "-Wdeprecated-declarations"
+	return btf__get_raw_data(btf_ro, size);
+#pragma GCC diagnostic pop
+}
+
 static int snprintf_hex(char *buf, size_t size, unsigned char *data, size_t len)
 {
 	int ret = 0;
@@ -119,7 +146,11 @@ static int perf_env__fetch_btf(struct perf_env *env,
 	node->data_size = data_size;
 	memcpy(node->data, data, data_size);
 
-	perf_env__insert_btf(env, node);
+	if (!perf_env__insert_btf(env, node)) {
+		/* Insertion failed because of a duplicate. */
+		free(node);
+		return -1;
+	}
 	return 0;
 }
 
diff --git a/tools/perf/util/bpf_skel/bperf.h b/tools/perf/util/bpf_skel/bperf.h
deleted file mode 100644
index 186a5551ddb9..000000000000
--- a/tools/perf/util/bpf_skel/bperf.h
+++ /dev/null
@@ -1,14 +0,0 @@
-// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
-// Copyright (c) 2021 Facebook
-
-#ifndef __BPERF_STAT_H
-#define __BPERF_STAT_H
-
-typedef struct {
-	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
-	__uint(key_size, sizeof(__u32));
-	__uint(value_size, sizeof(struct bpf_perf_event_value));
-	__uint(max_entries, 1);
-} reading_map;
-
-#endif /* __BPERF_STAT_H */
diff --git a/tools/perf/util/bpf_skel/bperf_follower.bpf.c b/tools/perf/util/bpf_skel/bperf_follower.bpf.c
index b8fa3cb2da23..f193998530d4 100644
--- a/tools/perf/util/bpf_skel/bperf_follower.bpf.c
+++ b/tools/perf/util/bpf_skel/bperf_follower.bpf.c
@@ -1,14 +1,23 @@
 // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 // Copyright (c) 2021 Facebook
-#include <linux/bpf.h>
-#include <linux/perf_event.h>
+#include "vmlinux.h"
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
-#include "bperf.h"
 #include "bperf_u.h"
 
-reading_map diff_readings SEC(".maps");
-reading_map accum_readings SEC(".maps");
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(struct bpf_perf_event_value));
+	__uint(max_entries, 1);
+} diff_readings SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(struct bpf_perf_event_value));
+	__uint(max_entries, 1);
+} accum_readings SEC(".maps");
 
 struct {
 	__uint(type, BPF_MAP_TYPE_HASH);
diff --git a/tools/perf/util/bpf_skel/bperf_leader.bpf.c b/tools/perf/util/bpf_skel/bperf_leader.bpf.c
index 4f70d1459e86..e2a2d4cd7779 100644
--- a/tools/perf/util/bpf_skel/bperf_leader.bpf.c
+++ b/tools/perf/util/bpf_skel/bperf_leader.bpf.c
@@ -1,10 +1,8 @@
 // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 // Copyright (c) 2021 Facebook
-#include <linux/bpf.h>
-#include <linux/perf_event.h>
+#include "vmlinux.h"
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
-#include "bperf.h"
 
 struct {
 	__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
@@ -13,8 +11,19 @@ struct {
 	__uint(map_flags, BPF_F_PRESERVE_ELEMS);
 } events SEC(".maps");
 
-reading_map prev_readings SEC(".maps");
-reading_map diff_readings SEC(".maps");
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(struct bpf_perf_event_value));
+	__uint(max_entries, 1);
+} prev_readings SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(struct bpf_perf_event_value));
+	__uint(max_entries, 1);
+} diff_readings SEC(".maps");
 
 SEC("raw_tp/sched_switch")
 int BPF_PROG(on_switch)
diff --git a/tools/perf/util/bpf_skel/bpf_prog_profiler.bpf.c b/tools/perf/util/bpf_skel/bpf_prog_profiler.bpf.c
index ab12b4c4ece2..97037d3b3d9f 100644
--- a/tools/perf/util/bpf_skel/bpf_prog_profiler.bpf.c
+++ b/tools/perf/util/bpf_skel/bpf_prog_profiler.bpf.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 // Copyright (c) 2020 Facebook
-#include <linux/bpf.h>
+#include "vmlinux.h"
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 
diff --git a/tools/perf/util/c++/clang-c.h b/tools/perf/util/c++/clang-c.h
index 2df8a45bd088..d3731a876b6c 100644
--- a/tools/perf/util/c++/clang-c.h
+++ b/tools/perf/util/c++/clang-c.h
@@ -12,8 +12,9 @@ extern "C" {
 extern void perf_clang__init(void);
 extern void perf_clang__cleanup(void);
 
-extern int test__clang_to_IR(void);
-extern int test__clang_to_obj(void);
+struct test_suite;
+extern int test__clang_to_IR(struct test_suite *test, int subtest);
+extern int test__clang_to_obj(struct test_suite *test, int subtest);
 
 extern int perf_clang__compile_bpf(const char *filename,
 				   void **p_obj_buf,
@@ -26,9 +27,6 @@ extern int perf_clang__compile_bpf(const char *filename,
 static inline void perf_clang__init(void) { }
 static inline void perf_clang__cleanup(void) { }
 
-static inline int test__clang_to_IR(void) { return -1; }
-static inline int test__clang_to_obj(void) { return -1;}
-
 static inline int
 perf_clang__compile_bpf(const char *filename __maybe_unused,
 			void **p_obj_buf __maybe_unused,
diff --git a/tools/perf/util/c++/clang-test.cpp b/tools/perf/util/c++/clang-test.cpp
index 21b23605f78b..a4683ca53697 100644
--- a/tools/perf/util/c++/clang-test.cpp
+++ b/tools/perf/util/c++/clang-test.cpp
@@ -35,7 +35,8 @@ __test__clang_to_IR(void)
 }
 
 extern "C" {
-int test__clang_to_IR(void)
+int test__clang_to_IR(struct test_suite *test __maybe_unused,
+                      int subtest __maybe_unused)
 {
 	perf_clang_scope _scope;
 
@@ -48,7 +49,8 @@ int test__clang_to_IR(void)
 	return -1;
 }
 
-int test__clang_to_obj(void)
+int test__clang_to_obj(struct test_suite *test __maybe_unused,
+                       int subtest __maybe_unused)
 {
 	perf_clang_scope _scope;
 
diff --git a/tools/perf/util/cputopo.c b/tools/perf/util/cputopo.c
index ec77e2a7b3ca..51b429c86f98 100644
--- a/tools/perf/util/cputopo.c
+++ b/tools/perf/util/cputopo.c
@@ -14,14 +14,16 @@
 #include "env.h"
 #include "pmu-hybrid.h"
 
-#define CORE_SIB_FMT \
+#define PACKAGE_CPUS_FMT \
+	"%s/devices/system/cpu/cpu%d/topology/package_cpus_list"
+#define PACKAGE_CPUS_FMT_OLD \
 	"%s/devices/system/cpu/cpu%d/topology/core_siblings_list"
-#define DIE_SIB_FMT \
+#define DIE_CPUS_FMT \
 	"%s/devices/system/cpu/cpu%d/topology/die_cpus_list"
-#define THRD_SIB_FMT \
-	"%s/devices/system/cpu/cpu%d/topology/thread_siblings_list"
-#define THRD_SIB_FMT_NEW \
+#define CORE_CPUS_FMT \
 	"%s/devices/system/cpu/cpu%d/topology/core_cpus_list"
+#define CORE_CPUS_FMT_OLD \
+	"%s/devices/system/cpu/cpu%d/topology/thread_siblings_list"
 #define NODE_ONLINE_FMT \
 	"%s/devices/system/node/online"
 #define NODE_MEMINFO_FMT \
@@ -39,8 +41,12 @@ static int build_cpu_topology(struct cpu_topology *tp, int cpu)
 	u32 i = 0;
 	int ret = -1;
 
-	scnprintf(filename, MAXPATHLEN, CORE_SIB_FMT,
+	scnprintf(filename, MAXPATHLEN, PACKAGE_CPUS_FMT,
 		  sysfs__mountpoint(), cpu);
+	if (access(filename, F_OK) == -1) {
+		scnprintf(filename, MAXPATHLEN, PACKAGE_CPUS_FMT_OLD,
+			sysfs__mountpoint(), cpu);
+	}
 	fp = fopen(filename, "r");
 	if (!fp)
 		goto try_dies;
@@ -54,23 +60,23 @@ static int build_cpu_topology(struct cpu_topology *tp, int cpu)
 	if (p)
 		*p = '\0';
 
-	for (i = 0; i < tp->core_sib; i++) {
-		if (!strcmp(buf, tp->core_siblings[i]))
+	for (i = 0; i < tp->package_cpus_lists; i++) {
+		if (!strcmp(buf, tp->package_cpus_list[i]))
 			break;
 	}
-	if (i == tp->core_sib) {
-		tp->core_siblings[i] = buf;
-		tp->core_sib++;
+	if (i == tp->package_cpus_lists) {
+		tp->package_cpus_list[i] = buf;
+		tp->package_cpus_lists++;
 		buf = NULL;
 		len = 0;
 	}
 	ret = 0;
 
 try_dies:
-	if (!tp->die_siblings)
+	if (!tp->die_cpus_list)
 		goto try_threads;
 
-	scnprintf(filename, MAXPATHLEN, DIE_SIB_FMT,
+	scnprintf(filename, MAXPATHLEN, DIE_CPUS_FMT,
 		  sysfs__mountpoint(), cpu);
 	fp = fopen(filename, "r");
 	if (!fp)
@@ -85,23 +91,23 @@ try_dies:
 	if (p)
 		*p = '\0';
 
-	for (i = 0; i < tp->die_sib; i++) {
-		if (!strcmp(buf, tp->die_siblings[i]))
+	for (i = 0; i < tp->die_cpus_lists; i++) {
+		if (!strcmp(buf, tp->die_cpus_list[i]))
 			break;
 	}
-	if (i == tp->die_sib) {
-		tp->die_siblings[i] = buf;
-		tp->die_sib++;
+	if (i == tp->die_cpus_lists) {
+		tp->die_cpus_list[i] = buf;
+		tp->die_cpus_lists++;
 		buf = NULL;
 		len = 0;
 	}
 	ret = 0;
 
 try_threads:
-	scnprintf(filename, MAXPATHLEN, THRD_SIB_FMT_NEW,
+	scnprintf(filename, MAXPATHLEN, CORE_CPUS_FMT,
 		  sysfs__mountpoint(), cpu);
 	if (access(filename, F_OK) == -1) {
-		scnprintf(filename, MAXPATHLEN, THRD_SIB_FMT,
+		scnprintf(filename, MAXPATHLEN, CORE_CPUS_FMT_OLD,
 			  sysfs__mountpoint(), cpu);
 	}
 	fp = fopen(filename, "r");
@@ -115,13 +121,13 @@ try_threads:
 	if (p)
 		*p = '\0';
 
-	for (i = 0; i < tp->thread_sib; i++) {
-		if (!strcmp(buf, tp->thread_siblings[i]))
+	for (i = 0; i < tp->core_cpus_lists; i++) {
+		if (!strcmp(buf, tp->core_cpus_list[i]))
 			break;
 	}
-	if (i == tp->thread_sib) {
-		tp->thread_siblings[i] = buf;
-		tp->thread_sib++;
+	if (i == tp->core_cpus_lists) {
+		tp->core_cpus_list[i] = buf;
+		tp->core_cpus_lists++;
 		buf = NULL;
 	}
 	ret = 0;
@@ -139,16 +145,14 @@ void cpu_topology__delete(struct cpu_topology *tp)
 	if (!tp)
 		return;
 
-	for (i = 0 ; i < tp->core_sib; i++)
-		zfree(&tp->core_siblings[i]);
+	for (i = 0 ; i < tp->package_cpus_lists; i++)
+		zfree(&tp->package_cpus_list[i]);
 
-	if (tp->die_sib) {
-		for (i = 0 ; i < tp->die_sib; i++)
-			zfree(&tp->die_siblings[i]);
-	}
+	for (i = 0 ; i < tp->die_cpus_lists; i++)
+		zfree(&tp->die_cpus_list[i]);
 
-	for (i = 0 ; i < tp->thread_sib; i++)
-		zfree(&tp->thread_siblings[i]);
+	for (i = 0 ; i < tp->core_cpus_lists; i++)
+		zfree(&tp->core_cpus_list[i]);
 
 	free(tp);
 }
@@ -164,7 +168,7 @@ static bool has_die_topology(void)
 	if (strncmp(uts.machine, "x86_64", 6))
 		return false;
 
-	scnprintf(filename, MAXPATHLEN, DIE_SIB_FMT,
+	scnprintf(filename, MAXPATHLEN, DIE_CPUS_FMT,
 		  sysfs__mountpoint(), 0);
 	if (access(filename, F_OK) == -1)
 		return false;
@@ -205,13 +209,13 @@ struct cpu_topology *cpu_topology__new(void)
 
 	tp = addr;
 	addr += sizeof(*tp);
-	tp->core_siblings = addr;
+	tp->package_cpus_list = addr;
 	addr += sz;
 	if (has_die) {
-		tp->die_siblings = addr;
+		tp->die_cpus_list = addr;
 		addr += sz;
 	}
-	tp->thread_siblings = addr;
+	tp->core_cpus_list = addr;
 
 	for (i = 0; i < nr; i++) {
 		if (!cpu_map__has(map, i))
diff --git a/tools/perf/util/cputopo.h b/tools/perf/util/cputopo.h
index d9af97177068..854e18f9041e 100644
--- a/tools/perf/util/cputopo.h
+++ b/tools/perf/util/cputopo.h
@@ -5,12 +5,33 @@
 #include <linux/types.h>
 
 struct cpu_topology {
-	u32	  core_sib;
-	u32	  die_sib;
-	u32	  thread_sib;
-	char	**core_siblings;
-	char	**die_siblings;
-	char	**thread_siblings;
+	/* The number of unique package_cpus_lists below. */
+	u32	  package_cpus_lists;
+	/* The number of unique die_cpu_lists below. */
+	u32	  die_cpus_lists;
+	/* The number of unique core_cpu_lists below. */
+	u32	  core_cpus_lists;
+	/*
+	 * An array of strings where each string is unique and read from
+	 * /sys/devices/system/cpu/cpuX/topology/package_cpus_list. From the ABI
+	 * each of these is a human-readable list of CPUs sharing the same
+	 * physical_package_id. The format is like 0-3, 8-11, 14,17.
+	 */
+	const char **package_cpus_list;
+	/*
+	 * An array of string where each string is unique and from
+	 * /sys/devices/system/cpu/cpuX/topology/die_cpus_list. From the ABI
+	 * each of these is a human-readable list of CPUs within the same die.
+	 * The format is like 0-3, 8-11, 14,17.
+	 */
+	const char **die_cpus_list;
+	/*
+	 * An array of string where each string is unique and from
+	 * /sys/devices/system/cpu/cpuX/topology/core_cpus_list. From the ABI
+	 * each of these is a human-readable list of CPUs within the same
+	 * core. The format is like 0-3, 8-11, 14,17.
+	 */
+	const char **core_cpus_list;
 };
 
 struct numa_topology_node {
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index f323adb1af85..4f672f7d008c 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -537,7 +537,7 @@ static void cs_etm__dump_event(struct cs_etm_queue *etmq,
 
 	fprintf(stdout, "\n");
 	color_fprintf(stdout, color,
-		     ". ... CoreSight %s Trace data: size %zu bytes\n",
+		     ". ... CoreSight %s Trace data: size %#zx bytes\n",
 		     cs_etm_decoder__get_name(etmq->decoder), buffer->size);
 
 	do {
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index 17f1dd0680b4..b9904896eb97 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -75,12 +75,13 @@ out:
 	return node;
 }
 
-void perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node)
+bool perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node)
 {
 	struct rb_node *parent = NULL;
 	__u32 btf_id = btf_node->id;
 	struct btf_node *node;
 	struct rb_node **p;
+	bool ret = true;
 
 	down_write(&env->bpf_progs.lock);
 	p = &env->bpf_progs.btfs.rb_node;
@@ -94,6 +95,7 @@ void perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node)
 			p = &(*p)->rb_right;
 		} else {
 			pr_debug("duplicated btf %u\n", btf_id);
+			ret = false;
 			goto out;
 		}
 	}
@@ -103,6 +105,7 @@ void perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node)
 	env->bpf_progs.btfs_cnt++;
 out:
 	up_write(&env->bpf_progs.lock);
+	return ret;
 }
 
 struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id)
diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h
index 1383876f72b3..163e5ec503a2 100644
--- a/tools/perf/util/env.h
+++ b/tools/perf/util/env.h
@@ -167,7 +167,7 @@ void perf_env__insert_bpf_prog_info(struct perf_env *env,
 				    struct bpf_prog_info_node *info_node);
 struct bpf_prog_info_node *perf_env__find_bpf_prog_info(struct perf_env *env,
 							__u32 prog_id);
-void perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node);
+bool perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node);
 struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id);
 
 int perf_env__numa_node(struct perf_env *env, int cpu);
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 95ffed66369c..c59331eea1d9 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -44,13 +44,16 @@ struct perf_event_attr;
 /* perf sample has 16 bits size limit */
 #define PERF_SAMPLE_MAX_SIZE (1 << 16)
 
+/* number of register is bound by the number of bits in regs_dump::mask (64) */
+#define PERF_SAMPLE_REGS_CACHE_SIZE (8 * sizeof(u64))
+
 struct regs_dump {
 	u64 abi;
 	u64 mask;
 	u64 *regs;
 
 	/* Cached values/mask filled by first register access. */
-	u64 cache_regs[PERF_REGS_MAX];
+	u64 cache_regs[PERF_SAMPLE_REGS_CACHE_SIZE];
 	u64 cache_mask;
 };
 
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index ec967fb8d7d9..ac0127be0459 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -241,7 +241,7 @@ void evsel__init(struct evsel *evsel,
 {
 	perf_evsel__init(&evsel->core, attr, idx);
 	evsel->tracking	   = !idx;
-	evsel->unit	   = "";
+	evsel->unit	   = strdup("");
 	evsel->scale	   = 1.0;
 	evsel->max_events  = ULONG_MAX;
 	evsel->evlist	   = NULL;
@@ -276,13 +276,8 @@ struct evsel *evsel__new_idx(struct perf_event_attr *attr, int idx)
 	}
 
 	if (evsel__is_clock(evsel)) {
-		/*
-		 * The evsel->unit points to static alias->unit
-		 * so it's ok to use static string in here.
-		 */
-		static const char *unit = "msec";
-
-		evsel->unit = unit;
+		free((char *)evsel->unit);
+		evsel->unit = strdup("msec");
 		evsel->scale = 1e-6;
 	}
 
@@ -420,7 +415,11 @@ struct evsel *evsel__clone(struct evsel *orig)
 
 	evsel->max_events = orig->max_events;
 	evsel->tool_event = orig->tool_event;
-	evsel->unit = orig->unit;
+	free((char *)evsel->unit);
+	evsel->unit = strdup(orig->unit);
+	if (evsel->unit == NULL)
+		goto out_err;
+
 	evsel->scale = orig->scale;
 	evsel->snapshot = orig->snapshot;
 	evsel->per_pkg = orig->per_pkg;
@@ -1441,6 +1440,7 @@ void evsel__exit(struct evsel *evsel)
 	zfree(&evsel->group_name);
 	zfree(&evsel->name);
 	zfree(&evsel->pmu_name);
+	zfree(&evsel->unit);
 	zfree(&evsel->metric_id);
 	evsel__zero_per_pkg(evsel);
 	hashmap__free(evsel->per_pkg_mask);
@@ -3037,3 +3037,15 @@ void evsel__set_leader(struct evsel *evsel, struct evsel *leader)
 {
 	evsel->core.leader = &leader->core;
 }
+
+int evsel__source_count(const struct evsel *evsel)
+{
+	struct evsel *pos;
+	int count = 0;
+
+	evlist__for_each_entry(evsel->evlist, pos) {
+		if (pos->metric_leader == evsel)
+			count++;
+	}
+	return count;
+}
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 3ea687141afa..29d49a8c1e92 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -489,6 +489,7 @@ struct evsel *evsel__leader(struct evsel *evsel);
 bool evsel__has_leader(struct evsel *evsel, struct evsel *leader);
 bool evsel__is_leader(struct evsel *evsel);
 void evsel__set_leader(struct evsel *evsel, struct evsel *leader);
+int evsel__source_count(const struct evsel *evsel);
 
 /*
  * Macro to swap the bit-field postition and size.
diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c
index 77c6ad81a923..254601060b39 100644
--- a/tools/perf/util/expr.c
+++ b/tools/perf/util/expr.c
@@ -5,13 +5,18 @@
 #include <stdlib.h>
 #include <string.h>
 #include "metricgroup.h"
+#include "cpumap.h"
+#include "cputopo.h"
 #include "debug.h"
 #include "expr.h"
 #include "expr-bison.h"
 #include "expr-flex.h"
+#include "smt.h"
+#include <linux/err.h>
 #include <linux/kernel.h>
 #include <linux/zalloc.h>
 #include <ctype.h>
+#include <math.h>
 
 #ifdef PARSER_DEBUG
 extern int expr_debug;
@@ -19,7 +24,10 @@ extern int expr_debug;
 
 struct expr_id_data {
 	union {
-		double val;
+		struct {
+			double val;
+			int source_count;
+		} val;
 		struct {
 			double val;
 			const char *metric_name;
@@ -137,6 +145,13 @@ int expr__add_id(struct expr_parse_ctx *ctx, const char *id)
 /* Caller must make sure id is allocated */
 int expr__add_id_val(struct expr_parse_ctx *ctx, const char *id, double val)
 {
+	return expr__add_id_val_source_count(ctx, id, val, /*source_count=*/1);
+}
+
+/* Caller must make sure id is allocated */
+int expr__add_id_val_source_count(struct expr_parse_ctx *ctx, const char *id,
+				  double val, int source_count)
+{
 	struct expr_id_data *data_ptr = NULL, *old_data = NULL;
 	char *old_key = NULL;
 	int ret;
@@ -144,7 +159,8 @@ int expr__add_id_val(struct expr_parse_ctx *ctx, const char *id, double val)
 	data_ptr = malloc(sizeof(*data_ptr));
 	if (!data_ptr)
 		return -ENOMEM;
-	data_ptr->val = val;
+	data_ptr->val.val = val;
+	data_ptr->val.source_count = source_count;
 	data_ptr->kind = EXPR_ID_DATA__VALUE;
 
 	ret = hashmap__set(ctx->ids, id, data_ptr,
@@ -240,7 +256,7 @@ int expr__resolve_id(struct expr_parse_ctx *ctx, const char *id,
 
 	switch (data->kind) {
 	case EXPR_ID_DATA__VALUE:
-		pr_debug2("lookup(%s): val %f\n", id, data->val);
+		pr_debug2("lookup(%s): val %f\n", id, data->val.val);
 		break;
 	case EXPR_ID_DATA__REF:
 		pr_debug2("lookup(%s): ref metric name %s\n", id,
@@ -251,7 +267,7 @@ int expr__resolve_id(struct expr_parse_ctx *ctx, const char *id,
 			pr_debug("%s failed to count\n", id);
 			return -1;
 		}
-		pr_debug("processing metric: %s EXIT: %f\n", id, data->val);
+		pr_debug("processing metric: %s EXIT: %f\n", id, data->ref.val);
 		break;
 	case EXPR_ID_DATA__REF_VALUE:
 		pr_debug2("lookup(%s): ref val %f metric name %s\n", id,
@@ -284,6 +300,10 @@ struct expr_parse_ctx *expr__ctx_new(void)
 		return NULL;
 
 	ctx->ids = hashmap__new(key_hash, key_equal, NULL);
+	if (IS_ERR(ctx->ids)) {
+		free(ctx);
+		return NULL;
+	}
 	ctx->runtime = 0;
 
 	return ctx;
@@ -366,7 +386,47 @@ int expr__find_ids(const char *expr, const char *one,
 double expr_id_data__value(const struct expr_id_data *data)
 {
 	if (data->kind == EXPR_ID_DATA__VALUE)
-		return data->val;
+		return data->val.val;
 	assert(data->kind == EXPR_ID_DATA__REF_VALUE);
 	return data->ref.val;
 }
+
+double expr_id_data__source_count(const struct expr_id_data *data)
+{
+	assert(data->kind == EXPR_ID_DATA__VALUE);
+	return data->val.source_count;
+}
+
+double expr__get_literal(const char *literal)
+{
+	static struct cpu_topology *topology;
+
+	if (!strcmp("#smt_on", literal))
+		return smt_on() > 0 ? 1.0 : 0.0;
+
+	if (!strcmp("#num_cpus", literal))
+		return cpu__max_present_cpu();
+
+	/*
+	 * Assume that topology strings are consistent, such as CPUs "0-1"
+	 * wouldn't be listed as "0,1", and so after deduplication the number of
+	 * these strings gives an indication of the number of packages, dies,
+	 * etc.
+	 */
+	if (!topology) {
+		topology = cpu_topology__new();
+		if (!topology) {
+			pr_err("Error creating CPU topology");
+			return NAN;
+		}
+	}
+	if (!strcmp("#num_packages", literal))
+		return topology->package_cpus_lists;
+	if (!strcmp("#num_dies", literal))
+		return topology->die_cpus_lists;
+	if (!strcmp("#num_cores", literal))
+		return topology->core_cpus_lists;
+
+	pr_err("Unrecognized literal '%s'", literal);
+	return NAN;
+}
diff --git a/tools/perf/util/expr.h b/tools/perf/util/expr.h
index cf81f9166dbb..bd2116983bbb 100644
--- a/tools/perf/util/expr.h
+++ b/tools/perf/util/expr.h
@@ -40,6 +40,8 @@ void expr__ctx_free(struct expr_parse_ctx *ctx);
 void expr__del_id(struct expr_parse_ctx *ctx, const char *id);
 int expr__add_id(struct expr_parse_ctx *ctx, const char *id);
 int expr__add_id_val(struct expr_parse_ctx *ctx, const char *id, double val);
+int expr__add_id_val_source_count(struct expr_parse_ctx *ctx, const char *id,
+				double val, int source_count);
 int expr__add_ref(struct expr_parse_ctx *ctx, struct metric_ref *ref);
 int expr__get_id(struct expr_parse_ctx *ctx, const char *id,
 		 struct expr_id_data **data);
@@ -55,5 +57,7 @@ int expr__find_ids(const char *expr, const char *one,
 		   struct expr_parse_ctx *ids);
 
 double expr_id_data__value(const struct expr_id_data *data);
+double expr_id_data__source_count(const struct expr_id_data *data);
+double expr__get_literal(const char *literal);
 
 #endif
diff --git a/tools/perf/util/expr.l b/tools/perf/util/expr.l
index bd20f33418ba..0a13eb20c814 100644
--- a/tools/perf/util/expr.l
+++ b/tools/perf/util/expr.l
@@ -6,6 +6,7 @@
 #include <linux/compiler.h>
 #include "expr.h"
 #include "expr-bison.h"
+#include <math.h>
 
 char *expr_get_text(yyscan_t yyscanner);
 YYSTYPE *expr_get_lval(yyscan_t yyscanner);
@@ -77,6 +78,17 @@ static int str(yyscan_t scanner, int token, int runtime)
 	yylval->str = normalize(yylval->str, runtime);
 	return token;
 }
+
+static int literal(yyscan_t scanner)
+{
+	YYSTYPE *yylval = expr_get_lval(scanner);
+
+	yylval->num = expr__get_literal(expr_get_text(scanner));
+	if (isnan(yylval->num))
+		return EXPR_ERROR;
+
+	return LITERAL;
+}
 %}
 
 number		([0-9]+\.?[0-9]*|[0-9]*\.?[0-9]+)
@@ -85,6 +97,7 @@ sch		[-,=]
 spec		\\{sch}
 sym		[0-9a-zA-Z_\.:@?]+
 symbol		({spec}|{sym})+
+literal		#[0-9a-zA-Z_\.\-]+
 
 %%
 	struct expr_scanner_ctx *sctx = expr_get_extra(yyscanner);
@@ -94,7 +107,8 @@ max		{ return MAX; }
 min		{ return MIN; }
 if		{ return IF; }
 else		{ return ELSE; }
-#smt_on		{ return SMT_ON; }
+source_count	{ return SOURCE_COUNT; }
+{literal}	{ return literal(yyscanner); }
 {number}	{ return value(yyscanner); }
 {symbol}	{ return str(yyscanner, ID, sctx->runtime); }
 "|"		{ return '|'; }
diff --git a/tools/perf/util/expr.y b/tools/perf/util/expr.y
index f969dfa525bd..a30b825adb7b 100644
--- a/tools/perf/util/expr.y
+++ b/tools/perf/util/expr.y
@@ -3,8 +3,8 @@
 #define YYDEBUG 1
 #include <assert.h>
 #include <math.h>
+#include <stdlib.h>
 #include "util/debug.h"
-#include "smt.h"
 #define IN_EXPR_Y 1
 #include "expr.h"
 %}
@@ -37,7 +37,7 @@
 	} ids;
 }
 
-%token ID NUMBER MIN MAX IF ELSE SMT_ON D_RATIO EXPR_ERROR
+%token ID NUMBER MIN MAX IF ELSE LITERAL D_RATIO SOURCE_COUNT EXPR_ERROR
 %left MIN MAX IF
 %left '|'
 %left '^'
@@ -46,7 +46,7 @@
 %left '-' '+'
 %left '*' '/' '%'
 %left NEG NOT
-%type <num> NUMBER
+%type <num> NUMBER LITERAL
 %type <str> ID
 %destructor { free ($$); } <str>
 %type <ids> expr if_expr
@@ -83,6 +83,41 @@ static struct ids union_expr(struct ids ids1, struct ids ids2)
 	return result;
 }
 
+static struct ids handle_id(struct expr_parse_ctx *ctx, char *id,
+			    bool compute_ids, bool source_count)
+{
+	struct ids result;
+
+	if (!compute_ids) {
+		/*
+		 * Compute the event's value from ID. If the ID isn't known then
+		 * it isn't used to compute the formula so set to NAN.
+		 */
+		struct expr_id_data *data;
+
+		result.val = NAN;
+		if (expr__resolve_id(ctx, id, &data) == 0) {
+			result.val = source_count
+				? expr_id_data__source_count(data)
+				: expr_id_data__value(data);
+		}
+		result.ids = NULL;
+		free(id);
+	} else {
+		/*
+		 * Set the value to BOTTOM to show that any value is possible
+		 * when the event is computed. Create a set of just the ID.
+		 */
+		result.val = BOTTOM;
+		result.ids = ids__new();
+		if (!result.ids || ids__insert(result.ids, id)) {
+			pr_err("Error creating IDs for '%s'", id);
+			free(id);
+		}
+	}
+	return result;
+}
+
 /*
  * If we're not computing ids or $1 and $3 are constants, compute the new
  * constant value using OP. Its invariant that there are no ids.  If computing
@@ -168,32 +203,8 @@ expr: NUMBER
 	$$.val = $1;
 	$$.ids = NULL;
 }
-| ID
-{
-	if (!compute_ids) {
-		/*
-		 * Compute the event's value from ID. If the ID isn't known then
-		 * it isn't used to compute the formula so set to NAN.
-		 */
-		struct expr_id_data *data;
-
-		$$.val = NAN;
-		if (expr__resolve_id(ctx, $1, &data) == 0)
-			$$.val = expr_id_data__value(data);
-
-		$$.ids = NULL;
-		free($1);
-	} else {
-		/*
-		 * Set the value to BOTTOM to show that any value is possible
-		 * when the event is computed. Create a set of just the ID.
-		 */
-		$$.val = BOTTOM;
-		$$.ids = ids__new();
-		if (!$$.ids || ids__insert($$.ids, $1))
-			YYABORT;
-	}
-}
+| ID				{ $$ = handle_id(ctx, $1, compute_ids, /*source_count=*/false); }
+| SOURCE_COUNT '(' ID ')'	{ $$ = handle_id(ctx, $3, compute_ids, /*source_count=*/true); }
 | expr '|' expr { BINARY_LONG_OP($$, |, $1, $3); }
 | expr '&' expr { BINARY_LONG_OP($$, &, $1, $3); }
 | expr '^' expr { BINARY_LONG_OP($$, ^, $1, $3); }
@@ -280,9 +291,9 @@ expr: NUMBER
 		$$ = union_expr($3, $5);
 	}
 }
-| SMT_ON
+| LITERAL
 {
-	$$.val = smt_on() > 0 ? 1.0 : 0.0;
+	$$.val = $1;
 	$$.ids = NULL;
 }
 ;
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 56511db8fa03..e3c1a532d059 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -583,21 +583,21 @@ static int write_cpu_topology(struct feat_fd *ff,
 	if (!tp)
 		return -1;
 
-	ret = do_write(ff, &tp->core_sib, sizeof(tp->core_sib));
+	ret = do_write(ff, &tp->package_cpus_lists, sizeof(tp->package_cpus_lists));
 	if (ret < 0)
 		goto done;
 
-	for (i = 0; i < tp->core_sib; i++) {
-		ret = do_write_string(ff, tp->core_siblings[i]);
+	for (i = 0; i < tp->package_cpus_lists; i++) {
+		ret = do_write_string(ff, tp->package_cpus_list[i]);
 		if (ret < 0)
 			goto done;
 	}
-	ret = do_write(ff, &tp->thread_sib, sizeof(tp->thread_sib));
+	ret = do_write(ff, &tp->core_cpus_lists, sizeof(tp->core_cpus_lists));
 	if (ret < 0)
 		goto done;
 
-	for (i = 0; i < tp->thread_sib; i++) {
-		ret = do_write_string(ff, tp->thread_siblings[i]);
+	for (i = 0; i < tp->core_cpus_lists; i++) {
+		ret = do_write_string(ff, tp->core_cpus_list[i]);
 		if (ret < 0)
 			break;
 	}
@@ -617,15 +617,15 @@ static int write_cpu_topology(struct feat_fd *ff,
 			return ret;
 	}
 
-	if (!tp->die_sib)
+	if (!tp->die_cpus_lists)
 		goto done;
 
-	ret = do_write(ff, &tp->die_sib, sizeof(tp->die_sib));
+	ret = do_write(ff, &tp->die_cpus_lists, sizeof(tp->die_cpus_lists));
 	if (ret < 0)
 		goto done;
 
-	for (i = 0; i < tp->die_sib; i++) {
-		ret = do_write_string(ff, tp->die_siblings[i]);
+	for (i = 0; i < tp->die_cpus_lists; i++) {
+		ret = do_write_string(ff, tp->die_cpus_list[i]);
 		if (ret < 0)
 			goto done;
 	}
@@ -2321,6 +2321,7 @@ out:
 #define FEAT_PROCESS_STR_FUN(__feat, __feat_env) \
 static int process_##__feat(struct feat_fd *ff, void *data __maybe_unused) \
 {\
+	free(ff->ph->env.__feat_env);		     \
 	ff->ph->env.__feat_env = do_read_string(ff); \
 	return ff->ph->env.__feat_env ? 0 : -ENOMEM; \
 }
@@ -4124,6 +4125,7 @@ int perf_event__process_feature(struct perf_session *session,
 	struct perf_record_header_feature *fe = (struct perf_record_header_feature *)event;
 	int type = fe->header.type;
 	u64 feat = fe->feat_id;
+	int ret = 0;
 
 	if (type < 0 || type >= PERF_RECORD_HEADER_MAX) {
 		pr_warning("invalid record type %d in pipe-mode\n", type);
@@ -4141,11 +4143,13 @@ int perf_event__process_feature(struct perf_session *session,
 	ff.size = event->header.size - sizeof(*fe);
 	ff.ph = &session->header;
 
-	if (feat_ops[feat].process(&ff, NULL))
-		return -1;
+	if (feat_ops[feat].process(&ff, NULL)) {
+		ret = -1;
+		goto out;
+	}
 
 	if (!feat_ops[feat].print || !tool->show_feat_hdr)
-		return 0;
+		goto out;
 
 	if (!feat_ops[feat].full_only ||
 	    tool->show_feat_hdr >= SHOW_FEAT_HEADER_FULL_INFO) {
@@ -4154,8 +4158,9 @@ int perf_event__process_feature(struct perf_session *session,
 		fprintf(stdout, "# %s info available, use -I to display\n",
 			feat_ops[feat].name);
 	}
-
-	return 0;
+out:
+	free_event_desc(ff.events);
+	return ret;
 }
 
 size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp)
@@ -4257,9 +4262,11 @@ int perf_event__process_event_update(struct perf_tool *tool __maybe_unused,
 
 	switch (ev->type) {
 	case PERF_EVENT_UPDATE__UNIT:
+		free((char *)evsel->unit);
 		evsel->unit = strdup(ev->data);
 		break;
 	case PERF_EVENT_UPDATE__NAME:
+		free(evsel->name);
 		evsel->name = strdup(ev->data);
 		break;
 	case PERF_EVENT_UPDATE__SCALE:
@@ -4268,11 +4275,11 @@ int perf_event__process_event_update(struct perf_tool *tool __maybe_unused,
 		break;
 	case PERF_EVENT_UPDATE__CPUS:
 		ev_cpus = (struct perf_record_event_update_cpus *)ev->data;
-
 		map = cpu_map__new_data(&ev_cpus->cpus);
-		if (map)
+		if (map) {
+			perf_cpu_map__put(evsel->core.own_cpus);
 			evsel->core.own_cpus = map;
-		else
+		} else
 			pr_err("failed to get event_update cpus\n");
 	default:
 		break;
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 65fe65ba03c2..b776465e04ef 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -289,15 +289,10 @@ static long hist_time(unsigned long htime)
 	return htime;
 }
 
-static void he_stat__add_period(struct he_stat *he_stat, u64 period,
-				u64 weight, u64 ins_lat, u64 p_stage_cyc)
+static void he_stat__add_period(struct he_stat *he_stat, u64 period)
 {
-
 	he_stat->period		+= period;
-	he_stat->weight		+= weight;
 	he_stat->nr_events	+= 1;
-	he_stat->ins_lat	+= ins_lat;
-	he_stat->p_stage_cyc	+= p_stage_cyc;
 }
 
 static void he_stat__add_stat(struct he_stat *dest, struct he_stat *src)
@@ -308,9 +303,6 @@ static void he_stat__add_stat(struct he_stat *dest, struct he_stat *src)
 	dest->period_guest_sys	+= src->period_guest_sys;
 	dest->period_guest_us	+= src->period_guest_us;
 	dest->nr_events		+= src->nr_events;
-	dest->weight		+= src->weight;
-	dest->ins_lat		+= src->ins_lat;
-	dest->p_stage_cyc		+= src->p_stage_cyc;
 }
 
 static void he_stat__decay(struct he_stat *he_stat)
@@ -598,9 +590,6 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists,
 	struct hist_entry *he;
 	int64_t cmp;
 	u64 period = entry->stat.period;
-	u64 weight = entry->stat.weight;
-	u64 ins_lat = entry->stat.ins_lat;
-	u64 p_stage_cyc = entry->stat.p_stage_cyc;
 	bool leftmost = true;
 
 	p = &hists->entries_in->rb_root.rb_node;
@@ -619,11 +608,11 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists,
 
 		if (!cmp) {
 			if (sample_self) {
-				he_stat__add_period(&he->stat, period, weight, ins_lat, p_stage_cyc);
+				he_stat__add_period(&he->stat, period);
 				hist_entry__add_callchain_period(he, period);
 			}
 			if (symbol_conf.cumulate_callchain)
-				he_stat__add_period(he->stat_acc, period, weight, ins_lat, p_stage_cyc);
+				he_stat__add_period(he->stat_acc, period);
 
 			/*
 			 * This mem info was allocated from sample__resolve_mem
@@ -733,9 +722,6 @@ __hists__add_entry(struct hists *hists,
 		.stat = {
 			.nr_events = 1,
 			.period	= sample->period,
-			.weight = sample->weight,
-			.ins_lat = sample->ins_lat,
-			.p_stage_cyc = sample->p_stage_cyc,
 		},
 		.parent = sym_parent,
 		.filtered = symbol__parent_filter(sym_parent) | al->filtered,
@@ -748,6 +734,9 @@ __hists__add_entry(struct hists *hists,
 		.raw_size = sample->raw_size,
 		.ops = ops,
 		.time = hist_time(sample->time),
+		.weight = sample->weight,
+		.ins_lat = sample->ins_lat,
+		.p_stage_cyc = sample->p_stage_cyc,
 	}, *he = hists__findnew_entry(hists, &entry, al, sample_self);
 
 	if (!hists->has_callchains && he && he->callchain_size != 0)
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 5343b62476e6..621f35ae1efa 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -369,7 +369,6 @@ enum {
 };
 
 void perf_hpp__init(void);
-void perf_hpp__column_unregister(struct perf_hpp_fmt *format);
 void perf_hpp__cancel_cumulate(void);
 void perf_hpp__setup_output_field(struct perf_hpp_list *list);
 void perf_hpp__reset_output_field(struct perf_hpp_list *list);
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
index 5f83937bf8f3..0e013c2d9eb4 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -1205,61 +1205,69 @@ out_no_progress:
 
 static bool intel_pt_fup_event(struct intel_pt_decoder *decoder)
 {
+	enum intel_pt_sample_type type = decoder->state.type;
 	bool ret = false;
 
+	decoder->state.type &= ~INTEL_PT_BRANCH;
+
 	if (decoder->set_fup_tx_flags) {
 		decoder->set_fup_tx_flags = false;
 		decoder->tx_flags = decoder->fup_tx_flags;
-		decoder->state.type = INTEL_PT_TRANSACTION;
+		decoder->state.type |= INTEL_PT_TRANSACTION;
 		if (decoder->fup_tx_flags & INTEL_PT_ABORT_TX)
 			decoder->state.type |= INTEL_PT_BRANCH;
-		decoder->state.from_ip = decoder->ip;
-		decoder->state.to_ip = 0;
 		decoder->state.flags = decoder->fup_tx_flags;
-		return true;
+		ret = true;
 	}
 	if (decoder->set_fup_ptw) {
 		decoder->set_fup_ptw = false;
-		decoder->state.type = INTEL_PT_PTW;
+		decoder->state.type |= INTEL_PT_PTW;
 		decoder->state.flags |= INTEL_PT_FUP_IP;
-		decoder->state.from_ip = decoder->ip;
-		decoder->state.to_ip = 0;
 		decoder->state.ptw_payload = decoder->fup_ptw_payload;
-		return true;
+		ret = true;
 	}
 	if (decoder->set_fup_mwait) {
 		decoder->set_fup_mwait = false;
-		decoder->state.type = INTEL_PT_MWAIT_OP;
-		decoder->state.from_ip = decoder->ip;
-		decoder->state.to_ip = 0;
+		decoder->state.type |= INTEL_PT_MWAIT_OP;
 		decoder->state.mwait_payload = decoder->fup_mwait_payload;
 		ret = true;
 	}
 	if (decoder->set_fup_pwre) {
 		decoder->set_fup_pwre = false;
 		decoder->state.type |= INTEL_PT_PWR_ENTRY;
-		decoder->state.type &= ~INTEL_PT_BRANCH;
-		decoder->state.from_ip = decoder->ip;
-		decoder->state.to_ip = 0;
 		decoder->state.pwre_payload = decoder->fup_pwre_payload;
 		ret = true;
 	}
 	if (decoder->set_fup_exstop) {
 		decoder->set_fup_exstop = false;
 		decoder->state.type |= INTEL_PT_EX_STOP;
-		decoder->state.type &= ~INTEL_PT_BRANCH;
 		decoder->state.flags |= INTEL_PT_FUP_IP;
-		decoder->state.from_ip = decoder->ip;
-		decoder->state.to_ip = 0;
 		ret = true;
 	}
 	if (decoder->set_fup_bep) {
 		decoder->set_fup_bep = false;
 		decoder->state.type |= INTEL_PT_BLK_ITEMS;
-		decoder->state.type &= ~INTEL_PT_BRANCH;
+		ret = true;
+	}
+	if (decoder->overflow) {
+		decoder->overflow = false;
+		if (!ret && !decoder->pge) {
+			if (decoder->hop) {
+				decoder->state.type = 0;
+				decoder->pkt_state = INTEL_PT_STATE_RESAMPLE;
+			}
+			decoder->pge = true;
+			decoder->state.type |= INTEL_PT_BRANCH | INTEL_PT_TRACE_BEGIN;
+			decoder->state.from_ip = 0;
+			decoder->state.to_ip = decoder->ip;
+			return true;
+		}
+	}
+	if (ret) {
 		decoder->state.from_ip = decoder->ip;
 		decoder->state.to_ip = 0;
-		ret = true;
+	} else {
+		decoder->state.type = type;
 	}
 	return ret;
 }
@@ -1608,7 +1616,16 @@ static int intel_pt_overflow(struct intel_pt_decoder *decoder)
 	intel_pt_clear_tx_flags(decoder);
 	intel_pt_set_nr(decoder);
 	decoder->timestamp_insn_cnt = 0;
-	decoder->pkt_state = INTEL_PT_STATE_ERR_RESYNC;
+	decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
+	decoder->state.from_ip = decoder->ip;
+	decoder->ip = 0;
+	decoder->pge = false;
+	decoder->set_fup_tx_flags = false;
+	decoder->set_fup_ptw = false;
+	decoder->set_fup_mwait = false;
+	decoder->set_fup_pwre = false;
+	decoder->set_fup_exstop = false;
+	decoder->set_fup_bep = false;
 	decoder->overflow = true;
 	return -EOVERFLOW;
 }
@@ -2666,6 +2683,8 @@ static int intel_pt_scan_for_psb(struct intel_pt_decoder *decoder);
 /* Hop mode: Ignore TNT, do not walk code, but get ip from FUPs and TIPs */
 static int intel_pt_hop_trace(struct intel_pt_decoder *decoder, bool *no_tip, int *err)
 {
+	*err = 0;
+
 	/* Leap from PSB to PSB, getting ip from FUP within PSB+ */
 	if (decoder->leap && !decoder->in_psb && decoder->packet.type != INTEL_PT_PSB) {
 		*err = intel_pt_scan_for_psb(decoder);
@@ -2678,6 +2697,7 @@ static int intel_pt_hop_trace(struct intel_pt_decoder *decoder, bool *no_tip, in
 		return HOP_IGNORE;
 
 	case INTEL_PT_TIP_PGD:
+		decoder->pge = false;
 		if (!decoder->packet.count) {
 			intel_pt_set_nr(decoder);
 			return HOP_IGNORE;
@@ -2705,18 +2725,21 @@ static int intel_pt_hop_trace(struct intel_pt_decoder *decoder, bool *no_tip, in
 		if (!decoder->packet.count)
 			return HOP_IGNORE;
 		intel_pt_set_ip(decoder);
-		if (intel_pt_fup_event(decoder))
-			return HOP_RETURN;
-		if (!decoder->branch_enable)
+		if (decoder->set_fup_mwait || decoder->set_fup_pwre)
+			*no_tip = true;
+		if (!decoder->branch_enable || !decoder->pge)
 			*no_tip = true;
 		if (*no_tip) {
 			decoder->state.type = INTEL_PT_INSTRUCTION;
 			decoder->state.from_ip = decoder->ip;
 			decoder->state.to_ip = 0;
+			intel_pt_fup_event(decoder);
 			return HOP_RETURN;
 		}
+		intel_pt_fup_event(decoder);
+		decoder->state.type |= INTEL_PT_INSTRUCTION | INTEL_PT_BRANCH;
 		*err = intel_pt_walk_fup_tip(decoder);
-		if (!*err)
+		if (!*err && decoder->state.to_ip)
 			decoder->pkt_state = INTEL_PT_STATE_RESAMPLE;
 		return HOP_RETURN;
 
@@ -2897,7 +2920,7 @@ static bool intel_pt_psb_with_fup(struct intel_pt_decoder *decoder, int *err)
 {
 	struct intel_pt_psb_info data = { .fup = false };
 
-	if (!decoder->branch_enable || !decoder->pge)
+	if (!decoder->branch_enable)
 		return false;
 
 	intel_pt_pkt_lookahead(decoder, intel_pt_psb_lookahead_cb, &data);
@@ -2924,6 +2947,7 @@ static int intel_pt_walk_trace(struct intel_pt_decoder *decoder)
 		if (err)
 			return err;
 next:
+		err = 0;
 		if (decoder->cyc_threshold) {
 			if (decoder->sample_cyc && last_packet_type != INTEL_PT_CYC)
 				decoder->sample_cyc = false;
@@ -2962,6 +2986,7 @@ next:
 
 		case INTEL_PT_TIP_PGE: {
 			decoder->pge = true;
+			decoder->overflow = false;
 			intel_pt_mtc_cyc_cnt_pge(decoder);
 			intel_pt_set_nr(decoder);
 			if (decoder->packet.count == 0) {
@@ -2999,7 +3024,7 @@ next:
 				break;
 			}
 			intel_pt_set_last_ip(decoder);
-			if (!decoder->branch_enable) {
+			if (!decoder->branch_enable || !decoder->pge) {
 				decoder->ip = decoder->last_ip;
 				if (intel_pt_fup_event(decoder))
 					return 0;
@@ -3467,10 +3492,10 @@ static int intel_pt_sync_ip(struct intel_pt_decoder *decoder)
 	decoder->set_fup_pwre = false;
 	decoder->set_fup_exstop = false;
 	decoder->set_fup_bep = false;
+	decoder->overflow = false;
 
 	if (!decoder->branch_enable) {
 		decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
-		decoder->overflow = false;
 		decoder->state.type = 0; /* Do not have a sample */
 		return 0;
 	}
@@ -3485,7 +3510,6 @@ static int intel_pt_sync_ip(struct intel_pt_decoder *decoder)
 		decoder->pkt_state = INTEL_PT_STATE_RESAMPLE;
 	else
 		decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
-	decoder->overflow = false;
 
 	decoder->state.from_ip = 0;
 	decoder->state.to_ip = decoder->ip;
@@ -3607,7 +3631,7 @@ static int intel_pt_sync(struct intel_pt_decoder *decoder)
 	}
 
 	decoder->have_last_ip = true;
-	decoder->pkt_state = INTEL_PT_STATE_NO_IP;
+	decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
 
 	err = intel_pt_walk_psb(decoder);
 	if (err)
@@ -3704,7 +3728,8 @@ const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder)
 
 	if (err) {
 		decoder->state.err = intel_pt_ext_err(err);
-		decoder->state.from_ip = decoder->ip;
+		if (err != -EOVERFLOW)
+			decoder->state.from_ip = decoder->ip;
 		intel_pt_update_sample_time(decoder);
 		decoder->sample_tot_cyc_cnt = decoder->tot_cyc_cnt;
 		intel_pt_set_nr(decoder);
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 556a893508da..10c3187e4c5a 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -2565,6 +2565,7 @@ static int intel_pt_run_decoder(struct intel_pt_queue *ptq, u64 *timestamp)
 				ptq->sync_switch = false;
 				intel_pt_next_tid(pt, ptq);
 			}
+			ptq->timestamp = state->est_timestamp;
 			if (pt->synth_opts.errors) {
 				err = intel_ptq_synth_error(ptq, state);
 				if (err)
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 5bfb6f892489..ba74fdf74af9 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -402,8 +402,10 @@ static int add_event_tool(struct list_head *list, int *idx,
 	if (!evsel)
 		return -ENOMEM;
 	evsel->tool_event = tool_event;
-	if (tool_event == PERF_TOOL_DURATION_TIME)
-		evsel->unit = "ns";
+	if (tool_event == PERF_TOOL_DURATION_TIME) {
+		free((char *)evsel->unit);
+		evsel->unit = strdup("ns");
+	}
 	return 0;
 }
 
@@ -1630,7 +1632,8 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,
 	if (parse_state->fake_pmu)
 		return 0;
 
-	evsel->unit = info.unit;
+	free((char *)evsel->unit);
+	evsel->unit = strdup(info.unit);
 	evsel->scale = info.scale;
 	evsel->per_pkg = info.per_pkg;
 	evsel->snapshot = info.snapshot;
diff --git a/tools/perf/util/perf_regs.c b/tools/perf/util/perf_regs.c
index 5ee47ae1509c..06a7461ba864 100644
--- a/tools/perf/util/perf_regs.c
+++ b/tools/perf/util/perf_regs.c
@@ -25,6 +25,9 @@ int perf_reg_value(u64 *valp, struct regs_dump *regs, int id)
 	int i, idx = 0;
 	u64 mask = regs->mask;
 
+	if ((u64)id >= PERF_SAMPLE_REGS_CACHE_SIZE)
+		return -EINVAL;
+
 	if (regs->cache_mask & (1ULL << id))
 		goto out;
 
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 563a9ba8954f..7f782a31bda3 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -461,7 +461,7 @@ get_tracepoint_field(struct pyrf_event *pevent, PyObject *attr_name)
 		struct tep_event *tp_format;
 
 		tp_format = trace_event__tp_format_id(evsel->core.attr.config);
-		if (!tp_format)
+		if (IS_ERR_OR_NULL(tp_format))
 			return NULL;
 
 		evsel->tp_format = tp_format;
diff --git a/tools/perf/util/smt.c b/tools/perf/util/smt.c
index 20bacd5972ad..34f1b1b1176c 100644
--- a/tools/perf/util/smt.c
+++ b/tools/perf/util/smt.c
@@ -15,7 +15,7 @@ int smt_on(void)
 	if (cached)
 		return cached_result;
 
-	if (sysfs__read_int("devices/system/cpu/smt/active", &cached_result) > 0)
+	if (sysfs__read_int("devices/system/cpu/smt/active", &cached_result) >= 0)
 		goto done;
 
 	ncpu = sysconf(_SC_NPROCESSORS_CONF);
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 568a88c001c6..a111065b484e 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -1325,88 +1325,68 @@ struct sort_entry sort_mispredict = {
 	.se_width_idx	= HISTC_MISPREDICT,
 };
 
-static u64 he_weight(struct hist_entry *he)
-{
-	return he->stat.nr_events ? he->stat.weight / he->stat.nr_events : 0;
-}
-
 static int64_t
-sort__local_weight_cmp(struct hist_entry *left, struct hist_entry *right)
+sort__weight_cmp(struct hist_entry *left, struct hist_entry *right)
 {
-	return he_weight(left) - he_weight(right);
+	return left->weight - right->weight;
 }
 
 static int hist_entry__local_weight_snprintf(struct hist_entry *he, char *bf,
 				    size_t size, unsigned int width)
 {
-	return repsep_snprintf(bf, size, "%-*llu", width, he_weight(he));
+	return repsep_snprintf(bf, size, "%-*llu", width, he->weight);
 }
 
 struct sort_entry sort_local_weight = {
 	.se_header	= "Local Weight",
-	.se_cmp		= sort__local_weight_cmp,
+	.se_cmp		= sort__weight_cmp,
 	.se_snprintf	= hist_entry__local_weight_snprintf,
 	.se_width_idx	= HISTC_LOCAL_WEIGHT,
 };
 
-static int64_t
-sort__global_weight_cmp(struct hist_entry *left, struct hist_entry *right)
-{
-	return left->stat.weight - right->stat.weight;
-}
-
 static int hist_entry__global_weight_snprintf(struct hist_entry *he, char *bf,
 					      size_t size, unsigned int width)
 {
-	return repsep_snprintf(bf, size, "%-*llu", width, he->stat.weight);
+	return repsep_snprintf(bf, size, "%-*llu", width,
+			       he->weight * he->stat.nr_events);
 }
 
 struct sort_entry sort_global_weight = {
 	.se_header	= "Weight",
-	.se_cmp		= sort__global_weight_cmp,
+	.se_cmp		= sort__weight_cmp,
 	.se_snprintf	= hist_entry__global_weight_snprintf,
 	.se_width_idx	= HISTC_GLOBAL_WEIGHT,
 };
 
-static u64 he_ins_lat(struct hist_entry *he)
-{
-		return he->stat.nr_events ? he->stat.ins_lat / he->stat.nr_events : 0;
-}
-
 static int64_t
-sort__local_ins_lat_cmp(struct hist_entry *left, struct hist_entry *right)
+sort__ins_lat_cmp(struct hist_entry *left, struct hist_entry *right)
 {
-		return he_ins_lat(left) - he_ins_lat(right);
+	return left->ins_lat - right->ins_lat;
 }
 
 static int hist_entry__local_ins_lat_snprintf(struct hist_entry *he, char *bf,
 					      size_t size, unsigned int width)
 {
-		return repsep_snprintf(bf, size, "%-*u", width, he_ins_lat(he));
+	return repsep_snprintf(bf, size, "%-*u", width, he->ins_lat);
 }
 
 struct sort_entry sort_local_ins_lat = {
 	.se_header	= "Local INSTR Latency",
-	.se_cmp		= sort__local_ins_lat_cmp,
+	.se_cmp		= sort__ins_lat_cmp,
 	.se_snprintf	= hist_entry__local_ins_lat_snprintf,
 	.se_width_idx	= HISTC_LOCAL_INS_LAT,
 };
 
-static int64_t
-sort__global_ins_lat_cmp(struct hist_entry *left, struct hist_entry *right)
-{
-		return left->stat.ins_lat - right->stat.ins_lat;
-}
-
 static int hist_entry__global_ins_lat_snprintf(struct hist_entry *he, char *bf,
 					       size_t size, unsigned int width)
 {
-		return repsep_snprintf(bf, size, "%-*u", width, he->stat.ins_lat);
+	return repsep_snprintf(bf, size, "%-*u", width,
+			       he->ins_lat * he->stat.nr_events);
 }
 
 struct sort_entry sort_global_ins_lat = {
 	.se_header	= "INSTR Latency",
-	.se_cmp		= sort__global_ins_lat_cmp,
+	.se_cmp		= sort__ins_lat_cmp,
 	.se_snprintf	= hist_entry__global_ins_lat_snprintf,
 	.se_width_idx	= HISTC_GLOBAL_INS_LAT,
 };
@@ -1414,13 +1394,13 @@ struct sort_entry sort_global_ins_lat = {
 static int64_t
 sort__global_p_stage_cyc_cmp(struct hist_entry *left, struct hist_entry *right)
 {
-	return left->stat.p_stage_cyc - right->stat.p_stage_cyc;
+	return left->p_stage_cyc - right->p_stage_cyc;
 }
 
 static int hist_entry__p_stage_cyc_snprintf(struct hist_entry *he, char *bf,
 					size_t size, unsigned int width)
 {
-	return repsep_snprintf(bf, size, "%-*u", width, he->stat.p_stage_cyc);
+	return repsep_snprintf(bf, size, "%-*u", width, he->p_stage_cyc);
 }
 
 struct sort_entry sort_p_stage_cyc = {
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index b67c469aba79..7b7145501933 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -49,9 +49,6 @@ struct he_stat {
 	u64			period_us;
 	u64			period_guest_sys;
 	u64			period_guest_us;
-	u64			weight;
-	u64			ins_lat;
-	u64			p_stage_cyc;
 	u32			nr_events;
 };
 
@@ -109,6 +106,9 @@ struct hist_entry {
 	s32			socket;
 	s32			cpu;
 	u64			code_page_size;
+	u64			weight;
+	u64			ins_lat;
+	u64			p_stage_cyc;
 	u8			cpumode;
 	u8			depth;
 
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index e4fb02b05130..5c7308efa768 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -829,10 +829,12 @@ static int prepare_metric(struct evsel **metric_events,
 		struct saved_value *v;
 		struct stats *stats;
 		u64 metric_total = 0;
+		int source_count;
 
 		if (!strcmp(metric_events[i]->name, "duration_time")) {
 			stats = &walltime_nsecs_stats;
 			scale = 1e-9;
+			source_count = 1;
 		} else {
 			v = saved_value_lookup(metric_events[i], cpu, false,
 					       STAT_NONE, 0, st,
@@ -841,6 +843,7 @@ static int prepare_metric(struct evsel **metric_events,
 				break;
 			stats = &v->stats;
 			scale = 1.0;
+			source_count = evsel__source_count(metric_events[i]);
 
 			if (v->metric_other)
 				metric_total = v->metric_total;
@@ -849,7 +852,9 @@ static int prepare_metric(struct evsel **metric_events,
 		if (!n)
 			return -ENOMEM;
 
-		expr__add_id_val(pctx, n, metric_total ? : avg_stats(stats) * scale);
+		expr__add_id_val_source_count(pctx, n,
+					metric_total ? : avg_stats(stats) * scale,
+					source_count);
 	}
 
 	for (j = 0; metric_refs && metric_refs[j].metric_name; j++) {
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index aa1b7c12fd61..b2ed3140a1fa 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -274,7 +274,7 @@ struct symbol *symbol__new(u64 start, u64 len, u8 binding, u8 type, const char *
 	if (symbol_conf.priv_size) {
 		if (symbol_conf.init_annotation) {
 			struct annotation *notes = (void *)sym;
-			pthread_mutex_init(&notes->lock, NULL);
+			annotation__init(notes);
 		}
 		sym = ((void *)sym) + symbol_conf.priv_size;
 	}
@@ -294,6 +294,13 @@ struct symbol *symbol__new(u64 start, u64 len, u8 binding, u8 type, const char *
 
 void symbol__delete(struct symbol *sym)
 {
+	if (symbol_conf.priv_size) {
+		if (symbol_conf.init_annotation) {
+			struct annotation *notes = symbol__annotation(sym);
+
+			annotation__exit(notes);
+		}
+	}
 	free(((void *)sym) - symbol_conf.priv_size);
 }
 
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 166196686f2e..fbf866d82dcc 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -40,22 +40,33 @@ Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep,
 			     GElf_Shdr *shp, const char *name, size_t *idx);
 #endif
 
-/** struct symbol - symtab entry
- *
- * @ignore - resolvable but tools ignore it (e.g. idle routines)
+/**
+ * A symtab entry. When allocated this may be preceded by an annotation (see
+ * symbol__annotation), a browser_index (see symbol__browser_index) and rb_node
+ * to sort by name (see struct symbol_name_rb_node).
  */
 struct symbol {
 	struct rb_node	rb_node;
+	/** Range of symbol [start, end). */
 	u64		start;
 	u64		end;
+	/** Length of the string name. */
 	u16		namelen;
+	/** ELF symbol type as defined for st_info. E.g STT_OBJECT or STT_FUNC. */
 	u8		type:4;
+	/** ELF binding type as defined for st_info. E.g. STB_WEAK or STB_GLOBAL. */
 	u8		binding:4;
+	/** Set true for kernel symbols of idle routines. */
 	u8		idle:1;
+	/** Resolvable but tools ignore it (e.g. idle routines). */
 	u8		ignore:1;
+	/** Symbol for an inlined function. */
 	u8		inlined:1;
+	/** Has symbol__annotate2 been performed. */
+	u8		annotate2:1;
+	/** Architecture specific. Unused except on PPC where it holds st_other. */
 	u8		arch_sym;
-	bool		annotate2;
+	/** The name of length namelen associated with the symbol. */
 	char		name[];
 };
 
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 37a9492edb3e..df3c4671be72 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -379,32 +379,32 @@ fetch_kernel_version(unsigned int *puint, char *str,
 	return 0;
 }
 
-const char *perf_tip(const char *dirpath)
+int perf_tip(char **strp, const char *dirpath)
 {
 	struct strlist *tips;
 	struct str_node *node;
-	char *tip = NULL;
 	struct strlist_config conf = {
 		.dirname = dirpath,
 		.file_only = true,
 	};
+	int ret = 0;
 
+	*strp = NULL;
 	tips = strlist__new("tips.txt", &conf);
 	if (tips == NULL)
-		return errno == ENOENT ? NULL :
-			"Tip: check path of tips.txt or get more memory! ;-p";
+		return -errno;
 
 	if (strlist__nr_entries(tips) == 0)
 		goto out;
 
 	node = strlist__entry(tips, random() % strlist__nr_entries(tips));
-	if (asprintf(&tip, "Tip: %s", node->s) < 0)
-		tip = (char *)"Tip: get more memory! ;-)";
+	if (asprintf(strp, "Tip: %s", node->s) < 0)
+		ret = -ENOMEM;
 
 out:
 	strlist__delete(tips);
 
-	return tip;
+	return ret;
 }
 
 char *perf_exe(char *buf, int len)
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index ad737052e597..9f0d36ba77f2 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -39,7 +39,7 @@ int fetch_kernel_version(unsigned int *puint,
 #define KVER_FMT	"%d.%d.%d"
 #define KVER_PARAM(x)	KVER_VERSION(x), KVER_PATCHLEVEL(x), KVER_SUBLEVEL(x)
 
-const char *perf_tip(const char *dirpath);
+int perf_tip(char **strp, const char *dirpath);
 
 #ifndef HAVE_SCHED_GETCPU_SUPPORT
 int sched_getcpu(void);
diff --git a/tools/power/acpi/Makefile.config b/tools/power/acpi/Makefile.config
index 331f6d30f472..cd7106876a5f 100644
--- a/tools/power/acpi/Makefile.config
+++ b/tools/power/acpi/Makefile.config
@@ -69,6 +69,7 @@ KERNEL_INCLUDE := $(OUTPUT)include
 ACPICA_INCLUDE := $(srctree)/../../../drivers/acpi/acpica
 CFLAGS += -D_LINUX -I$(KERNEL_INCLUDE) -I$(ACPICA_INCLUDE)
 CFLAGS += $(WARNINGS)
+MKDIR = mkdir
 
 ifeq ($(strip $(V)),false)
 	QUIET=@
diff --git a/tools/power/acpi/Makefile.rules b/tools/power/acpi/Makefile.rules
index 2a6c170b57cd..1d7616f5d0ae 100644
--- a/tools/power/acpi/Makefile.rules
+++ b/tools/power/acpi/Makefile.rules
@@ -21,6 +21,7 @@ $(KERNEL_INCLUDE):
 
 $(objdir)%.o: %.c $(KERNEL_INCLUDE)
 	$(ECHO) "  CC      " $(subst $(OUTPUT),,$@)
+	$(QUIET) $(MKDIR) -p $(objdir) 2>/dev/null
 	$(QUIET) $(CC) -c $(CFLAGS) -o $@ $<
 
 all: $(OUTPUT)$(TOOL)
diff --git a/tools/testing/radix-tree/linux/lockdep.h b/tools/testing/radix-tree/linux/lockdep.h
index 565fccdfe6e9..016cff473cfc 100644
--- a/tools/testing/radix-tree/linux/lockdep.h
+++ b/tools/testing/radix-tree/linux/lockdep.h
@@ -1,5 +1,8 @@
 #ifndef _LINUX_LOCKDEP_H
 #define _LINUX_LOCKDEP_H
+
+#include <linux/spinlock.h>
+
 struct lock_class_key {
 	unsigned int a;
 };
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 54b0a41a3775..62fafbeb4672 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -187,7 +187,7 @@ DEFAULT_BPFTOOL := $(HOST_SCRATCH_DIR)/sbin/bpftool
 $(OUTPUT)/runqslower: $(BPFOBJ) | $(DEFAULT_BPFTOOL) $(RUNQSLOWER_OUTPUT)
 	$(Q)$(MAKE) $(submake_extras) -C $(TOOLSDIR)/bpf/runqslower	       \
 		    OUTPUT=$(RUNQSLOWER_OUTPUT) VMLINUX_BTF=$(VMLINUX_BTF)     \
-		    BPFTOOL_OUTPUT=$(BUILD_DIR)/bpftool/		       \
+		    BPFTOOL_OUTPUT=$(HOST_BUILD_DIR)/bpftool/		       \
 		    BPFOBJ_OUTPUT=$(BUILD_DIR)/libbpf			       \
 		    BPFOBJ=$(BPFOBJ) BPF_INCLUDE=$(INCLUDE_DIR) &&	       \
 		    cp $(RUNQSLOWER_OUTPUT)runqslower $@
diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
index 5d52ea2768df..df3b292a8ffe 100644
--- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
+++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
@@ -33,6 +33,22 @@ noinline int bpf_testmod_loop_test(int n)
 	return sum;
 }
 
+__weak noinline struct file *bpf_testmod_return_ptr(int arg)
+{
+	static struct file f = {};
+
+	switch (arg) {
+	case 1: return (void *)EINVAL;		/* user addr */
+	case 2: return (void *)0xcafe4a11;	/* user addr */
+	case 3: return (void *)-EINVAL;		/* canonical, but invalid */
+	case 4: return (void *)(1ull << 60);	/* non-canonical and invalid */
+	case 5: return (void *)~(1ull << 30);	/* trigger extable */
+	case 6: return &f;			/* valid addr */
+	case 7: return (void *)((long)&f | 1);	/* kernel tricks */
+	default: return NULL;
+	}
+}
+
 noinline ssize_t
 bpf_testmod_test_read(struct file *file, struct kobject *kobj,
 		      struct bin_attribute *bin_attr,
@@ -43,6 +59,10 @@ bpf_testmod_test_read(struct file *file, struct kobject *kobj,
 		.off = off,
 		.len = len,
 	};
+	int i = 1;
+
+	while (bpf_testmod_return_ptr(i))
+		i++;
 
 	/* This is always true. Use the check to make sure the compiler
 	 * doesn't remove bpf_testmod_loop_test.
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_skc_cls_ingress.c b/tools/testing/selftests/bpf/prog_tests/btf_skc_cls_ingress.c
index 762f6a9da8b5..664ffc0364f4 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_skc_cls_ingress.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_skc_cls_ingress.c
@@ -90,7 +90,7 @@ static void print_err_line(void)
 
 static void test_conn(void)
 {
-	int listen_fd = -1, cli_fd = -1, err;
+	int listen_fd = -1, cli_fd = -1, srv_fd = -1, err;
 	socklen_t addrlen = sizeof(srv_sa6);
 	int srv_port;
 
@@ -112,6 +112,10 @@ static void test_conn(void)
 	if (CHECK_FAIL(cli_fd == -1))
 		goto done;
 
+	srv_fd = accept(listen_fd, NULL, NULL);
+	if (CHECK_FAIL(srv_fd == -1))
+		goto done;
+
 	if (CHECK(skel->bss->listen_tp_sport != srv_port ||
 		  skel->bss->req_sk_sport != srv_port,
 		  "Unexpected sk src port",
@@ -134,11 +138,13 @@ done:
 		close(listen_fd);
 	if (cli_fd != -1)
 		close(cli_fd);
+	if (srv_fd != -1)
+		close(srv_fd);
 }
 
 static void test_syncookie(void)
 {
-	int listen_fd = -1, cli_fd = -1, err;
+	int listen_fd = -1, cli_fd = -1, srv_fd = -1, err;
 	socklen_t addrlen = sizeof(srv_sa6);
 	int srv_port;
 
@@ -161,6 +167,10 @@ static void test_syncookie(void)
 	if (CHECK_FAIL(cli_fd == -1))
 		goto done;
 
+	srv_fd = accept(listen_fd, NULL, NULL);
+	if (CHECK_FAIL(srv_fd == -1))
+		goto done;
+
 	if (CHECK(skel->bss->listen_tp_sport != srv_port,
 		  "Unexpected tp src port",
 		  "listen_tp_sport:%u expected:%u\n",
@@ -188,6 +198,8 @@ done:
 		close(listen_fd);
 	if (cli_fd != -1)
 		close(cli_fd);
+	if (srv_fd != -1)
+		close(srv_fd);
 }
 
 struct test {
diff --git a/tools/testing/selftests/bpf/prog_tests/helper_restricted.c b/tools/testing/selftests/bpf/prog_tests/helper_restricted.c
new file mode 100644
index 000000000000..e1de5f80c3b2
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/helper_restricted.c
@@ -0,0 +1,33 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+#include "test_helper_restricted.skel.h"
+
+void test_helper_restricted(void)
+{
+	int prog_i = 0, prog_cnt;
+	int duration = 0;
+
+	do {
+		struct test_helper_restricted *test;
+		int maybeOK;
+
+		test = test_helper_restricted__open();
+		if (!ASSERT_OK_PTR(test, "open"))
+			return;
+
+		prog_cnt = test->skeleton->prog_cnt;
+
+		for (int j = 0; j < prog_cnt; ++j) {
+			struct bpf_program *prog = *test->skeleton->progs[j].prog;
+
+			maybeOK = bpf_program__set_autoload(prog, prog_i == j);
+			ASSERT_OK(maybeOK, "set autoload");
+		}
+
+		maybeOK = test_helper_restricted__load(test);
+		CHECK(!maybeOK, test->skeleton->progs[prog_i].name, "helper isn't restricted");
+
+		test_helper_restricted__destroy(test);
+	} while (++prog_i < prog_cnt);
+}
diff --git a/tools/testing/selftests/bpf/progs/test_helper_restricted.c b/tools/testing/selftests/bpf/progs/test_helper_restricted.c
new file mode 100644
index 000000000000..68d64c365f90
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_helper_restricted.c
@@ -0,0 +1,123 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <time.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+struct timer {
+	struct bpf_timer t;
+};
+
+struct lock {
+	struct bpf_spin_lock l;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, struct timer);
+} timers SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, struct lock);
+} locks SEC(".maps");
+
+static int timer_cb(void *map, int *key, struct timer *timer)
+{
+	return 0;
+}
+
+static void timer_work(void)
+{
+	struct timer *timer;
+	const int key = 0;
+
+	timer  = bpf_map_lookup_elem(&timers, &key);
+	if (timer) {
+		bpf_timer_init(&timer->t, &timers, CLOCK_MONOTONIC);
+		bpf_timer_set_callback(&timer->t, timer_cb);
+		bpf_timer_start(&timer->t, 10E9, 0);
+		bpf_timer_cancel(&timer->t);
+	}
+}
+
+static void spin_lock_work(void)
+{
+	const int key = 0;
+	struct lock *lock;
+
+	lock = bpf_map_lookup_elem(&locks, &key);
+	if (lock) {
+		bpf_spin_lock(&lock->l);
+		bpf_spin_unlock(&lock->l);
+	}
+}
+
+SEC("raw_tp/sys_enter")
+int raw_tp_timer(void *ctx)
+{
+	timer_work();
+
+	return 0;
+}
+
+SEC("tp/syscalls/sys_enter_nanosleep")
+int tp_timer(void *ctx)
+{
+	timer_work();
+
+	return 0;
+}
+
+SEC("kprobe/sys_nanosleep")
+int kprobe_timer(void *ctx)
+{
+	timer_work();
+
+	return 0;
+}
+
+SEC("perf_event")
+int perf_event_timer(void *ctx)
+{
+	timer_work();
+
+	return 0;
+}
+
+SEC("raw_tp/sys_enter")
+int raw_tp_spin_lock(void *ctx)
+{
+	spin_lock_work();
+
+	return 0;
+}
+
+SEC("tp/syscalls/sys_enter_nanosleep")
+int tp_spin_lock(void *ctx)
+{
+	spin_lock_work();
+
+	return 0;
+}
+
+SEC("kprobe/sys_nanosleep")
+int kprobe_spin_lock(void *ctx)
+{
+	spin_lock_work();
+
+	return 0;
+}
+
+SEC("perf_event")
+int perf_event_spin_lock(void *ctx)
+{
+	spin_lock_work();
+
+	return 0;
+}
+
+const char LICENSE[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_module_attach.c b/tools/testing/selftests/bpf/progs/test_module_attach.c
index b36857093f71..50ce16d02da7 100644
--- a/tools/testing/selftests/bpf/progs/test_module_attach.c
+++ b/tools/testing/selftests/bpf/progs/test_module_attach.c
@@ -87,6 +87,18 @@ int BPF_PROG(handle_fexit,
 	return 0;
 }
 
+SEC("fexit/bpf_testmod_return_ptr")
+int BPF_PROG(handle_fexit_ret, int arg, struct file *ret)
+{
+	long buf = 0;
+
+	bpf_probe_read_kernel(&buf, 8, ret);
+	bpf_probe_read_kernel(&buf, 8, (char *)ret + 256);
+	*(volatile long long *)ret;
+	*(volatile int *)&ret->f_mode;
+	return 0;
+}
+
 __u32 fmod_ret_read_sz = 0;
 
 SEC("fmod_ret/bpf_testmod_test_read")
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 25afe423b3f0..d3bf83d5c6cf 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -54,7 +54,7 @@
 #define MAX_INSNS	BPF_MAXINSNS
 #define MAX_TEST_INSNS	1000000
 #define MAX_FIXUPS	8
-#define MAX_NR_MAPS	21
+#define MAX_NR_MAPS	22
 #define MAX_TEST_RUNS	8
 #define POINTER_VALUE	0xcafe4all
 #define TEST_DATA_LEN	64
@@ -92,6 +92,7 @@ struct bpf_test {
 	int fixup_map_event_output[MAX_FIXUPS];
 	int fixup_map_reuseport_array[MAX_FIXUPS];
 	int fixup_map_ringbuf[MAX_FIXUPS];
+	int fixup_map_timer[MAX_FIXUPS];
 	/* Expected verifier log output for result REJECT or VERBOSE_ACCEPT.
 	 * Can be a tab-separated sequence of expected strings. An empty string
 	 * means no log verification.
@@ -604,8 +605,15 @@ static int create_cgroup_storage(bool percpu)
  *   int cnt;
  *   struct bpf_spin_lock l;
  * };
+ * struct bpf_timer {
+ *   __u64 :64;
+ *   __u64 :64;
+ * } __attribute__((aligned(8)));
+ * struct timer {
+ *   struct bpf_timer t;
+ * };
  */
-static const char btf_str_sec[] = "\0bpf_spin_lock\0val\0cnt\0l";
+static const char btf_str_sec[] = "\0bpf_spin_lock\0val\0cnt\0l\0bpf_timer\0timer\0t";
 static __u32 btf_raw_types[] = {
 	/* int */
 	BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),  /* [1] */
@@ -616,6 +624,11 @@ static __u32 btf_raw_types[] = {
 	BTF_TYPE_ENC(15, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), 8),
 	BTF_MEMBER_ENC(19, 1, 0), /* int cnt; */
 	BTF_MEMBER_ENC(23, 2, 32),/* struct bpf_spin_lock l; */
+	/* struct bpf_timer */                          /* [4] */
+	BTF_TYPE_ENC(25, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 0), 16),
+	/* struct timer */                              /* [5] */
+	BTF_TYPE_ENC(35, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 1), 16),
+	BTF_MEMBER_ENC(41, 4, 0), /* struct bpf_timer t; */
 };
 
 static int load_btf(void)
@@ -696,6 +709,29 @@ static int create_sk_storage_map(void)
 	return fd;
 }
 
+static int create_map_timer(void)
+{
+	struct bpf_create_map_attr attr = {
+		.name = "test_map",
+		.map_type = BPF_MAP_TYPE_ARRAY,
+		.key_size = 4,
+		.value_size = 16,
+		.max_entries = 1,
+		.btf_key_type_id = 1,
+		.btf_value_type_id = 5,
+	};
+	int fd, btf_fd;
+
+	btf_fd = load_btf();
+	if (btf_fd < 0)
+		return -1;
+	attr.btf_fd = btf_fd;
+	fd = bpf_create_map_xattr(&attr);
+	if (fd < 0)
+		printf("Failed to create map with timer\n");
+	return fd;
+}
+
 static char bpf_vlog[UINT_MAX >> 8];
 
 static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type,
@@ -722,6 +758,7 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type,
 	int *fixup_map_event_output = test->fixup_map_event_output;
 	int *fixup_map_reuseport_array = test->fixup_map_reuseport_array;
 	int *fixup_map_ringbuf = test->fixup_map_ringbuf;
+	int *fixup_map_timer = test->fixup_map_timer;
 
 	if (test->fill_helper) {
 		test->fill_insns = calloc(MAX_TEST_INSNS, sizeof(struct bpf_insn));
@@ -907,6 +944,13 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type,
 			fixup_map_ringbuf++;
 		} while (*fixup_map_ringbuf);
 	}
+	if (*fixup_map_timer) {
+		map_fds[21] = create_map_timer();
+		do {
+			prog[*fixup_map_timer].imm = map_fds[21];
+			fixup_map_timer++;
+		} while (*fixup_map_timer);
+	}
 }
 
 struct libcap {
diff --git a/tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c b/tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c
index c22dc83a41fd..b39665f33524 100644
--- a/tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c
+++ b/tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c
@@ -138,6 +138,8 @@
 		BPF_EXIT_INSN(),
 	},
 	.result = ACCEPT,
+	.result_unpriv = REJECT,
+	.errstr_unpriv = "R0 leaks addr into mem",
 },
 {
 	"Dest pointer in r0 - succeed",
@@ -156,4 +158,88 @@
 		BPF_EXIT_INSN(),
 	},
 	.result = ACCEPT,
+	.result_unpriv = REJECT,
+	.errstr_unpriv = "R0 leaks addr into mem",
+},
+{
+	"Dest pointer in r0 - succeed, check 2",
+	.insns = {
+		/* r0 = &val */
+		BPF_MOV64_REG(BPF_REG_0, BPF_REG_10),
+		/* val = r0; */
+		BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8),
+		/* r5 = &val */
+		BPF_MOV64_REG(BPF_REG_5, BPF_REG_10),
+		/* r0 = atomic_cmpxchg(&val, r0, r5); */
+		BPF_ATOMIC_OP(BPF_DW, BPF_CMPXCHG, BPF_REG_10, BPF_REG_5, -8),
+		/* r1 = *r0 */
+		BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, -8),
+		/* exit(0); */
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.result_unpriv = REJECT,
+	.errstr_unpriv = "R0 leaks addr into mem",
+},
+{
+	"Dest pointer in r0 - succeed, check 3",
+	.insns = {
+		/* r0 = &val */
+		BPF_MOV64_REG(BPF_REG_0, BPF_REG_10),
+		/* val = r0; */
+		BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8),
+		/* r5 = &val */
+		BPF_MOV64_REG(BPF_REG_5, BPF_REG_10),
+		/* r0 = atomic_cmpxchg(&val, r0, r5); */
+		BPF_ATOMIC_OP(BPF_W, BPF_CMPXCHG, BPF_REG_10, BPF_REG_5, -8),
+		/* exit(0); */
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	},
+	.result = REJECT,
+	.errstr = "invalid size of register fill",
+	.errstr_unpriv = "R0 leaks addr into mem",
+},
+{
+	"Dest pointer in r0 - succeed, check 4",
+	.insns = {
+		/* r0 = &val */
+		BPF_MOV32_REG(BPF_REG_0, BPF_REG_10),
+		/* val = r0; */
+		BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -8),
+		/* r5 = &val */
+		BPF_MOV32_REG(BPF_REG_5, BPF_REG_10),
+		/* r0 = atomic_cmpxchg(&val, r0, r5); */
+		BPF_ATOMIC_OP(BPF_W, BPF_CMPXCHG, BPF_REG_10, BPF_REG_5, -8),
+		/* r1 = *r10 */
+		BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_10, -8),
+		/* exit(0); */
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.result_unpriv = REJECT,
+	.errstr_unpriv = "R10 partial copy of pointer",
+},
+{
+	"Dest pointer in r0 - succeed, check 5",
+	.insns = {
+		/* r0 = &val */
+		BPF_MOV32_REG(BPF_REG_0, BPF_REG_10),
+		/* val = r0; */
+		BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -8),
+		/* r5 = &val */
+		BPF_MOV32_REG(BPF_REG_5, BPF_REG_10),
+		/* r0 = atomic_cmpxchg(&val, r0, r5); */
+		BPF_ATOMIC_OP(BPF_W, BPF_CMPXCHG, BPF_REG_10, BPF_REG_5, -8),
+		/* r1 = *r0 */
+		BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, -8),
+		/* exit(0); */
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	},
+	.result = REJECT,
+	.errstr = "R0 invalid mem access",
+	.errstr_unpriv = "R10 partial copy of pointer",
 },
diff --git a/tools/testing/selftests/bpf/verifier/atomic_fetch.c b/tools/testing/selftests/bpf/verifier/atomic_fetch.c
index 3bc9ff7a860b..5bf03fb4fa2b 100644
--- a/tools/testing/selftests/bpf/verifier/atomic_fetch.c
+++ b/tools/testing/selftests/bpf/verifier/atomic_fetch.c
@@ -1,3 +1,97 @@
+{
+	"atomic dw/fetch and address leakage of (map ptr & -1) via stack slot",
+	.insns = {
+		BPF_LD_IMM64(BPF_REG_1, -1),
+		BPF_LD_MAP_FD(BPF_REG_8, 0),
+		BPF_LD_MAP_FD(BPF_REG_9, 0),
+		BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+		BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+		BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_9, 0),
+		BPF_ATOMIC_OP(BPF_DW, BPF_AND | BPF_FETCH, BPF_REG_2, BPF_REG_1, 0),
+		BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_2, 0),
+		BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+		BPF_MOV64_REG(BPF_REG_1, BPF_REG_8),
+		BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+		BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+		BPF_STX_MEM(BPF_DW, BPF_REG_0, BPF_REG_9, 0),
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	},
+	.fixup_map_array_48b = { 2, 4 },
+	.result = ACCEPT,
+	.result_unpriv = REJECT,
+	.errstr_unpriv = "leaking pointer from stack off -8",
+},
+{
+	"atomic dw/fetch and address leakage of (map ptr & -1) via returned value",
+	.insns = {
+		BPF_LD_IMM64(BPF_REG_1, -1),
+		BPF_LD_MAP_FD(BPF_REG_8, 0),
+		BPF_LD_MAP_FD(BPF_REG_9, 0),
+		BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+		BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+		BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_9, 0),
+		BPF_ATOMIC_OP(BPF_DW, BPF_AND | BPF_FETCH, BPF_REG_2, BPF_REG_1, 0),
+		BPF_MOV64_REG(BPF_REG_9, BPF_REG_1),
+		BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+		BPF_MOV64_REG(BPF_REG_1, BPF_REG_8),
+		BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+		BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+		BPF_STX_MEM(BPF_DW, BPF_REG_0, BPF_REG_9, 0),
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	},
+	.fixup_map_array_48b = { 2, 4 },
+	.result = ACCEPT,
+	.result_unpriv = REJECT,
+	.errstr_unpriv = "leaking pointer from stack off -8",
+},
+{
+	"atomic w/fetch and address leakage of (map ptr & -1) via stack slot",
+	.insns = {
+		BPF_LD_IMM64(BPF_REG_1, -1),
+		BPF_LD_MAP_FD(BPF_REG_8, 0),
+		BPF_LD_MAP_FD(BPF_REG_9, 0),
+		BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+		BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+		BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_9, 0),
+		BPF_ATOMIC_OP(BPF_W, BPF_AND | BPF_FETCH, BPF_REG_2, BPF_REG_1, 0),
+		BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_2, 0),
+		BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+		BPF_MOV64_REG(BPF_REG_1, BPF_REG_8),
+		BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+		BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+		BPF_STX_MEM(BPF_DW, BPF_REG_0, BPF_REG_9, 0),
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	},
+	.fixup_map_array_48b = { 2, 4 },
+	.result = REJECT,
+	.errstr = "invalid size of register fill",
+},
+{
+	"atomic w/fetch and address leakage of (map ptr & -1) via returned value",
+	.insns = {
+		BPF_LD_IMM64(BPF_REG_1, -1),
+		BPF_LD_MAP_FD(BPF_REG_8, 0),
+		BPF_LD_MAP_FD(BPF_REG_9, 0),
+		BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+		BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+		BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_9, 0),
+		BPF_ATOMIC_OP(BPF_W, BPF_AND | BPF_FETCH, BPF_REG_2, BPF_REG_1, 0),
+		BPF_MOV64_REG(BPF_REG_9, BPF_REG_1),
+		BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+		BPF_MOV64_REG(BPF_REG_1, BPF_REG_8),
+		BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+		BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+		BPF_STX_MEM(BPF_DW, BPF_REG_0, BPF_REG_9, 0),
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	},
+	.fixup_map_array_48b = { 2, 4 },
+	.result = REJECT,
+	.errstr = "invalid size of register fill",
+},
 #define __ATOMIC_FETCH_OP_TEST(src_reg, dst_reg, operand1, op, operand2, expect) \
 	{								\
 		"atomic fetch " #op ", src=" #dst_reg " dst=" #dst_reg,	\
diff --git a/tools/testing/selftests/bpf/verifier/helper_restricted.c b/tools/testing/selftests/bpf/verifier/helper_restricted.c
new file mode 100644
index 000000000000..a067b7098b97
--- /dev/null
+++ b/tools/testing/selftests/bpf/verifier/helper_restricted.c
@@ -0,0 +1,196 @@
+{
+	"bpf_ktime_get_coarse_ns is forbidden in BPF_PROG_TYPE_KPROBE",
+	.insns = {
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ktime_get_coarse_ns),
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	},
+	.errstr = "unknown func bpf_ktime_get_coarse_ns",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_KPROBE,
+},
+{
+	"bpf_ktime_get_coarse_ns is forbidden in BPF_PROG_TYPE_TRACEPOINT",
+	.insns = {
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ktime_get_coarse_ns),
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	},
+	.errstr = "unknown func bpf_ktime_get_coarse_ns",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+},
+{
+	"bpf_ktime_get_coarse_ns is forbidden in BPF_PROG_TYPE_PERF_EVENT",
+	.insns = {
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ktime_get_coarse_ns),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.errstr = "unknown func bpf_ktime_get_coarse_ns",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_PERF_EVENT,
+},
+{
+	"bpf_ktime_get_coarse_ns is forbidden in BPF_PROG_TYPE_RAW_TRACEPOINT",
+	.insns = {
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ktime_get_coarse_ns),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.errstr = "unknown func bpf_ktime_get_coarse_ns",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_RAW_TRACEPOINT,
+},
+{
+	"bpf_timer_init isn restricted in BPF_PROG_TYPE_KPROBE",
+	.insns = {
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_LD_MAP_FD(BPF_REG_2, 0),
+	BPF_MOV64_IMM(BPF_REG_3, 1),
+	BPF_EMIT_CALL(BPF_FUNC_timer_init),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_timer = { 3, 8 },
+	.errstr = "tracing progs cannot use bpf_timer yet",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_KPROBE,
+},
+{
+	"bpf_timer_init is forbidden in BPF_PROG_TYPE_PERF_EVENT",
+	.insns = {
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_LD_MAP_FD(BPF_REG_2, 0),
+	BPF_MOV64_IMM(BPF_REG_3, 1),
+	BPF_EMIT_CALL(BPF_FUNC_timer_init),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_timer = { 3, 8 },
+	.errstr = "tracing progs cannot use bpf_timer yet",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_PERF_EVENT,
+},
+{
+	"bpf_timer_init is forbidden in BPF_PROG_TYPE_TRACEPOINT",
+	.insns = {
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_LD_MAP_FD(BPF_REG_2, 0),
+	BPF_MOV64_IMM(BPF_REG_3, 1),
+	BPF_EMIT_CALL(BPF_FUNC_timer_init),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_timer = { 3, 8 },
+	.errstr = "tracing progs cannot use bpf_timer yet",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+},
+{
+	"bpf_timer_init is forbidden in BPF_PROG_TYPE_RAW_TRACEPOINT",
+	.insns = {
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_LD_MAP_FD(BPF_REG_2, 0),
+	BPF_MOV64_IMM(BPF_REG_3, 1),
+	BPF_EMIT_CALL(BPF_FUNC_timer_init),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_timer = { 3, 8 },
+	.errstr = "tracing progs cannot use bpf_timer yet",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_RAW_TRACEPOINT,
+},
+{
+	"bpf_spin_lock is forbidden in BPF_PROG_TYPE_KPROBE",
+	.insns = {
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_EMIT_CALL(BPF_FUNC_spin_lock),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_spin_lock = { 3 },
+	.errstr = "tracing progs cannot use bpf_spin_lock yet",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_KPROBE,
+},
+{
+	"bpf_spin_lock is forbidden in BPF_PROG_TYPE_TRACEPOINT",
+	.insns = {
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_EMIT_CALL(BPF_FUNC_spin_lock),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_spin_lock = { 3 },
+	.errstr = "tracing progs cannot use bpf_spin_lock yet",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+},
+{
+	"bpf_spin_lock is forbidden in BPF_PROG_TYPE_PERF_EVENT",
+	.insns = {
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_EMIT_CALL(BPF_FUNC_spin_lock),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_spin_lock = { 3 },
+	.errstr = "tracing progs cannot use bpf_spin_lock yet",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_PERF_EVENT,
+},
+{
+	"bpf_spin_lock is forbidden in BPF_PROG_TYPE_RAW_TRACEPOINT",
+	.insns = {
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_EMIT_CALL(BPF_FUNC_spin_lock),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_spin_lock = { 3 },
+	.errstr = "tracing progs cannot use bpf_spin_lock yet",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_RAW_TRACEPOINT,
+},
diff --git a/tools/testing/selftests/bpf/verifier/map_in_map.c b/tools/testing/selftests/bpf/verifier/map_in_map.c
index 2798927ee9ff..128a348b762d 100644
--- a/tools/testing/selftests/bpf/verifier/map_in_map.c
+++ b/tools/testing/selftests/bpf/verifier/map_in_map.c
@@ -19,6 +19,40 @@
 	.result = ACCEPT,
 },
 {
+	"map in map state pruning",
+	.insns = {
+	BPF_ST_MEM(0, BPF_REG_10, -4, 0),
+	BPF_MOV64_REG(BPF_REG_6, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -4),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_6),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_6),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 11),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_6),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_6),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+	BPF_EXIT_INSN(),
+	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_in_map = { 4, 14 },
+	.flags = BPF_F_TEST_STATE_FREQ,
+	.result = VERBOSE_ACCEPT,
+	.errstr = "processed 25 insns",
+	.prog_type = BPF_PROG_TYPE_XDP,
+},
+{
 	"invalid inner map pointer",
 	.insns = {
 	BPF_ST_MEM(0, BPF_REG_10, -4, 0),
diff --git a/tools/testing/selftests/bpf/verifier/search_pruning.c b/tools/testing/selftests/bpf/verifier/search_pruning.c
index 7e50cb80873a..682519769fe3 100644
--- a/tools/testing/selftests/bpf/verifier/search_pruning.c
+++ b/tools/testing/selftests/bpf/verifier/search_pruning.c
@@ -133,6 +133,77 @@
 	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 },
 {
+	"precision tracking for u32 spill/fill",
+	.insns = {
+		BPF_MOV64_REG(BPF_REG_7, BPF_REG_1),
+		BPF_EMIT_CALL(BPF_FUNC_get_prandom_u32),
+		BPF_MOV32_IMM(BPF_REG_6, 32),
+		BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+		BPF_MOV32_IMM(BPF_REG_6, 4),
+		/* Additional insns to introduce a pruning point. */
+		BPF_EMIT_CALL(BPF_FUNC_get_prandom_u32),
+		BPF_MOV64_IMM(BPF_REG_3, 0),
+		BPF_MOV64_IMM(BPF_REG_3, 0),
+		BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+		BPF_MOV64_IMM(BPF_REG_3, 0),
+		/* u32 spill/fill */
+		BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_6, -8),
+		BPF_LDX_MEM(BPF_W, BPF_REG_8, BPF_REG_10, -8),
+		/* out-of-bound map value access for r6=32 */
+		BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, 0),
+		BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+		BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -16),
+		BPF_LD_MAP_FD(BPF_REG_1, 0),
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+		BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+		BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_8),
+		BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	},
+	.fixup_map_hash_8b = { 15 },
+	.result = REJECT,
+	.errstr = "R0 min value is outside of the allowed memory range",
+	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+},
+{
+	"precision tracking for u32 spills, u64 fill",
+	.insns = {
+		BPF_EMIT_CALL(BPF_FUNC_get_prandom_u32),
+		BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+		BPF_MOV32_IMM(BPF_REG_7, 0xffffffff),
+		/* Additional insns to introduce a pruning point. */
+		BPF_MOV64_IMM(BPF_REG_3, 1),
+		BPF_MOV64_IMM(BPF_REG_3, 1),
+		BPF_MOV64_IMM(BPF_REG_3, 1),
+		BPF_MOV64_IMM(BPF_REG_3, 1),
+		BPF_EMIT_CALL(BPF_FUNC_get_prandom_u32),
+		BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+		BPF_MOV64_IMM(BPF_REG_3, 1),
+		BPF_ALU32_IMM(BPF_DIV, BPF_REG_3, 0),
+		/* u32 spills, u64 fill */
+		BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_6, -4),
+		BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_7, -8),
+		BPF_LDX_MEM(BPF_DW, BPF_REG_8, BPF_REG_10, -8),
+		/* if r8 != X goto pc+1  r8 known in fallthrough branch */
+		BPF_JMP_IMM(BPF_JNE, BPF_REG_8, 0xffffffff, 1),
+		BPF_MOV64_IMM(BPF_REG_3, 1),
+		/* if r8 == X goto pc+1  condition always true on first
+		 * traversal, so starts backtracking to mark r8 as requiring
+		 * precision. r7 marked as needing precision. r6 not marked
+		 * since it's not tracked.
+		 */
+		BPF_JMP_IMM(BPF_JEQ, BPF_REG_8, 0xffffffff, 1),
+		/* fails if r8 correctly marked unknown after fill. */
+		BPF_ALU32_IMM(BPF_DIV, BPF_REG_3, 0),
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	},
+	.result = REJECT,
+	.errstr = "div by zero",
+	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+},
+{
 	"allocated_stack",
 	.insns = {
 		BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_1),
diff --git a/tools/testing/selftests/bpf/verifier/spill_fill.c b/tools/testing/selftests/bpf/verifier/spill_fill.c
index 7ab3de108761..6c907144311f 100644
--- a/tools/testing/selftests/bpf/verifier/spill_fill.c
+++ b/tools/testing/selftests/bpf/verifier/spill_fill.c
@@ -176,6 +176,38 @@
 	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 },
 {
+	"Spill u32 const scalars.  Refill as u64.  Offset to skb->data",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+		    offsetof(struct __sk_buff, data)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+		    offsetof(struct __sk_buff, data_end)),
+	/* r6 = 0 */
+	BPF_MOV32_IMM(BPF_REG_6, 0),
+	/* r7 = 20 */
+	BPF_MOV32_IMM(BPF_REG_7, 20),
+	/* *(u32 *)(r10 -4) = r6 */
+	BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_6, -4),
+	/* *(u32 *)(r10 -8) = r7 */
+	BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_7, -8),
+	/* r4 = *(u64 *)(r10 -8) */
+	BPF_LDX_MEM(BPF_H, BPF_REG_4, BPF_REG_10, -8),
+	/* r0 = r2 */
+	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+	/* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=inv,umax=65535 */
+	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_4),
+	/* if (r0 > r3) R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=inv,umax=65535 */
+	BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1),
+	/* r0 = *(u32 *)r2 R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=inv20 */
+	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 0),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = REJECT,
+	.errstr = "invalid access to packet",
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+},
+{
 	"Spill a u32 const scalar.  Refill as u16 from fp-6.  Offset to skb->data",
 	.insns = {
 	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
diff --git a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
index 2debba4e8a3a..359f3e8f8b60 100644
--- a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
+++ b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
@@ -1078,6 +1078,29 @@
 	.errstr_unpriv = "R0 pointer -= pointer prohibited",
 },
 {
+	"map access: trying to leak tainted dst reg",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+	BPF_MOV32_IMM(BPF_REG_1, 0xFFFFFFFF),
+	BPF_MOV32_REG(BPF_REG_1, BPF_REG_1),
+	BPF_ALU64_REG(BPF_SUB, BPF_REG_2, BPF_REG_1),
+	BPF_STX_MEM(BPF_DW, BPF_REG_0, BPF_REG_2, 0),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_array_48b = { 4 },
+	.result = REJECT,
+	.errstr = "math between map_value pointer and 4294967295 is not allowed",
+},
+{
 	"32bit pkt_ptr -= scalar",
 	.insns = {
 	BPF_LDX_MEM(BPF_W, BPF_REG_8, BPF_REG_1,
diff --git a/tools/testing/selftests/bpf/verifier/xdp_direct_packet_access.c b/tools/testing/selftests/bpf/verifier/xdp_direct_packet_access.c
index bfb97383e6b5..b4ec228eb95d 100644
--- a/tools/testing/selftests/bpf/verifier/xdp_direct_packet_access.c
+++ b/tools/testing/selftests/bpf/verifier/xdp_direct_packet_access.c
@@ -35,7 +35,7 @@
 	.prog_type = BPF_PROG_TYPE_XDP,
 },
 {
-	"XDP pkt read, pkt_data' > pkt_end, good access",
+	"XDP pkt read, pkt_data' > pkt_end, corner case, good access",
 	.insns = {
 	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
 	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
@@ -88,6 +88,41 @@
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
+	"XDP pkt read, pkt_data' > pkt_end, corner case +1, good access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+		    offsetof(struct xdp_md, data_end)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9),
+	BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+	"XDP pkt read, pkt_data' > pkt_end, corner case -1, bad access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+		    offsetof(struct xdp_md, data_end)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
+	BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.errstr = "R1 offset is outside of the packet",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
 	"XDP pkt read, pkt_end > pkt_data', good access",
 	.insns = {
 	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
@@ -106,16 +141,16 @@
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
-	"XDP pkt read, pkt_end > pkt_data', bad access 1",
+	"XDP pkt read, pkt_end > pkt_data', corner case -1, bad access",
 	.insns = {
 	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
 	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
 		    offsetof(struct xdp_md, data_end)),
 	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6),
 	BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1),
 	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6),
 	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
@@ -143,6 +178,42 @@
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
+	"XDP pkt read, pkt_end > pkt_data', corner case, good access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+		    offsetof(struct xdp_md, data_end)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
+	BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1),
+	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+	"XDP pkt read, pkt_end > pkt_data', corner case +1, good access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+		    offsetof(struct xdp_md, data_end)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+	BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1),
+	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
 	"XDP pkt read, pkt_data' < pkt_end, good access",
 	.insns = {
 	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
@@ -161,16 +232,16 @@
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
-	"XDP pkt read, pkt_data' < pkt_end, bad access 1",
+	"XDP pkt read, pkt_data' < pkt_end, corner case -1, bad access",
 	.insns = {
 	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
 	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
 		    offsetof(struct xdp_md, data_end)),
 	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6),
 	BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1),
 	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6),
 	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
@@ -198,7 +269,43 @@
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
-	"XDP pkt read, pkt_end < pkt_data', good access",
+	"XDP pkt read, pkt_data' < pkt_end, corner case, good access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+		    offsetof(struct xdp_md, data_end)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
+	BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1),
+	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+	"XDP pkt read, pkt_data' < pkt_end, corner case +1, good access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+		    offsetof(struct xdp_md, data_end)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+	BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1),
+	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+	"XDP pkt read, pkt_end < pkt_data', corner case, good access",
 	.insns = {
 	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
 	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
@@ -251,6 +358,41 @@
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
+	"XDP pkt read, pkt_end < pkt_data', corner case +1, good access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+		    offsetof(struct xdp_md, data_end)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9),
+	BPF_JMP_REG(BPF_JLT, BPF_REG_3, BPF_REG_1, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+	"XDP pkt read, pkt_end < pkt_data', corner case -1, bad access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+		    offsetof(struct xdp_md, data_end)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
+	BPF_JMP_REG(BPF_JLT, BPF_REG_3, BPF_REG_1, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.errstr = "R1 offset is outside of the packet",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
 	"XDP pkt read, pkt_data' >= pkt_end, good access",
 	.insns = {
 	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
@@ -268,15 +410,15 @@
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
-	"XDP pkt read, pkt_data' >= pkt_end, bad access 1",
+	"XDP pkt read, pkt_data' >= pkt_end, corner case -1, bad access",
 	.insns = {
 	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
 	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
 		    offsetof(struct xdp_md, data_end)),
 	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6),
 	BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6),
 	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
@@ -304,7 +446,41 @@
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
-	"XDP pkt read, pkt_end >= pkt_data', good access",
+	"XDP pkt read, pkt_data' >= pkt_end, corner case, good access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+		    offsetof(struct xdp_md, data_end)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
+	BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+	"XDP pkt read, pkt_data' >= pkt_end, corner case +1, good access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+		    offsetof(struct xdp_md, data_end)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+	BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+	"XDP pkt read, pkt_end >= pkt_data', corner case, good access",
 	.insns = {
 	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
 	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
@@ -359,7 +535,44 @@
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
-	"XDP pkt read, pkt_data' <= pkt_end, good access",
+	"XDP pkt read, pkt_end >= pkt_data', corner case +1, good access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+		    offsetof(struct xdp_md, data_end)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9),
+	BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 1),
+	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+	"XDP pkt read, pkt_end >= pkt_data', corner case -1, bad access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+		    offsetof(struct xdp_md, data_end)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
+	BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 1),
+	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.errstr = "R1 offset is outside of the packet",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+	"XDP pkt read, pkt_data' <= pkt_end, corner case, good access",
 	.insns = {
 	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
 	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
@@ -414,6 +627,43 @@
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
+	"XDP pkt read, pkt_data' <= pkt_end, corner case +1, good access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+		    offsetof(struct xdp_md, data_end)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9),
+	BPF_JMP_REG(BPF_JLE, BPF_REG_1, BPF_REG_3, 1),
+	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+	"XDP pkt read, pkt_data' <= pkt_end, corner case -1, bad access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+		    offsetof(struct xdp_md, data_end)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
+	BPF_JMP_REG(BPF_JLE, BPF_REG_1, BPF_REG_3, 1),
+	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.errstr = "R1 offset is outside of the packet",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
 	"XDP pkt read, pkt_end <= pkt_data', good access",
 	.insns = {
 	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
@@ -431,15 +681,15 @@
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
-	"XDP pkt read, pkt_end <= pkt_data', bad access 1",
+	"XDP pkt read, pkt_end <= pkt_data', corner case -1, bad access",
 	.insns = {
 	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
 	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
 		    offsetof(struct xdp_md, data_end)),
 	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6),
 	BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6),
 	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
@@ -467,7 +717,41 @@
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
-	"XDP pkt read, pkt_meta' > pkt_data, good access",
+	"XDP pkt read, pkt_end <= pkt_data', corner case, good access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+		    offsetof(struct xdp_md, data_end)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
+	BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+	"XDP pkt read, pkt_end <= pkt_data', corner case +1, good access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+		    offsetof(struct xdp_md, data_end)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+	BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+	"XDP pkt read, pkt_meta' > pkt_data, corner case, good access",
 	.insns = {
 	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
 		    offsetof(struct xdp_md, data_meta)),
@@ -520,6 +804,41 @@
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
+	"XDP pkt read, pkt_meta' > pkt_data, corner case +1, good access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+		    offsetof(struct xdp_md, data_meta)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9),
+	BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+	"XDP pkt read, pkt_meta' > pkt_data, corner case -1, bad access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+		    offsetof(struct xdp_md, data_meta)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
+	BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.errstr = "R1 offset is outside of the packet",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
 	"XDP pkt read, pkt_data > pkt_meta', good access",
 	.insns = {
 	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
@@ -538,16 +857,16 @@
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
-	"XDP pkt read, pkt_data > pkt_meta', bad access 1",
+	"XDP pkt read, pkt_data > pkt_meta', corner case -1, bad access",
 	.insns = {
 	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
 		    offsetof(struct xdp_md, data_meta)),
 	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
 	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6),
 	BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1),
 	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6),
 	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
@@ -575,6 +894,42 @@
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
+	"XDP pkt read, pkt_data > pkt_meta', corner case, good access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+		    offsetof(struct xdp_md, data_meta)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
+	BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1),
+	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+	"XDP pkt read, pkt_data > pkt_meta', corner case +1, good access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+		    offsetof(struct xdp_md, data_meta)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+	BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1),
+	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
 	"XDP pkt read, pkt_meta' < pkt_data, good access",
 	.insns = {
 	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
@@ -593,16 +948,16 @@
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
-	"XDP pkt read, pkt_meta' < pkt_data, bad access 1",
+	"XDP pkt read, pkt_meta' < pkt_data, corner case -1, bad access",
 	.insns = {
 	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
 		    offsetof(struct xdp_md, data_meta)),
 	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
 	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6),
 	BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1),
 	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6),
 	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
@@ -630,7 +985,43 @@
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
-	"XDP pkt read, pkt_data < pkt_meta', good access",
+	"XDP pkt read, pkt_meta' < pkt_data, corner case, good access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+		    offsetof(struct xdp_md, data_meta)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
+	BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1),
+	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+	"XDP pkt read, pkt_meta' < pkt_data, corner case +1, good access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+		    offsetof(struct xdp_md, data_meta)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+	BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1),
+	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+	"XDP pkt read, pkt_data < pkt_meta', corner case, good access",
 	.insns = {
 	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
 		    offsetof(struct xdp_md, data_meta)),
@@ -683,6 +1074,41 @@
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
+	"XDP pkt read, pkt_data < pkt_meta', corner case +1, good access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+		    offsetof(struct xdp_md, data_meta)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9),
+	BPF_JMP_REG(BPF_JLT, BPF_REG_3, BPF_REG_1, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+	"XDP pkt read, pkt_data < pkt_meta', corner case -1, bad access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+		    offsetof(struct xdp_md, data_meta)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
+	BPF_JMP_REG(BPF_JLT, BPF_REG_3, BPF_REG_1, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.errstr = "R1 offset is outside of the packet",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
 	"XDP pkt read, pkt_meta' >= pkt_data, good access",
 	.insns = {
 	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
@@ -700,15 +1126,15 @@
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
-	"XDP pkt read, pkt_meta' >= pkt_data, bad access 1",
+	"XDP pkt read, pkt_meta' >= pkt_data, corner case -1, bad access",
 	.insns = {
 	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
 		    offsetof(struct xdp_md, data_meta)),
 	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
 	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6),
 	BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6),
 	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
@@ -736,7 +1162,41 @@
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
-	"XDP pkt read, pkt_data >= pkt_meta', good access",
+	"XDP pkt read, pkt_meta' >= pkt_data, corner case, good access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+		    offsetof(struct xdp_md, data_meta)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
+	BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+	"XDP pkt read, pkt_meta' >= pkt_data, corner case +1, good access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+		    offsetof(struct xdp_md, data_meta)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+	BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+	"XDP pkt read, pkt_data >= pkt_meta', corner case, good access",
 	.insns = {
 	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
 		    offsetof(struct xdp_md, data_meta)),
@@ -791,7 +1251,44 @@
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
-	"XDP pkt read, pkt_meta' <= pkt_data, good access",
+	"XDP pkt read, pkt_data >= pkt_meta', corner case +1, good access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+		    offsetof(struct xdp_md, data_meta)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9),
+	BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 1),
+	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+	"XDP pkt read, pkt_data >= pkt_meta', corner case -1, bad access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+		    offsetof(struct xdp_md, data_meta)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
+	BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 1),
+	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.errstr = "R1 offset is outside of the packet",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+	"XDP pkt read, pkt_meta' <= pkt_data, corner case, good access",
 	.insns = {
 	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
 		    offsetof(struct xdp_md, data_meta)),
@@ -846,6 +1343,43 @@
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
+	"XDP pkt read, pkt_meta' <= pkt_data, corner case +1, good access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+		    offsetof(struct xdp_md, data_meta)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9),
+	BPF_JMP_REG(BPF_JLE, BPF_REG_1, BPF_REG_3, 1),
+	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+	"XDP pkt read, pkt_meta' <= pkt_data, corner case -1, bad access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+		    offsetof(struct xdp_md, data_meta)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
+	BPF_JMP_REG(BPF_JLE, BPF_REG_1, BPF_REG_3, 1),
+	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.errstr = "R1 offset is outside of the packet",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
 	"XDP pkt read, pkt_data <= pkt_meta', good access",
 	.insns = {
 	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
@@ -863,15 +1397,15 @@
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
-	"XDP pkt read, pkt_data <= pkt_meta', bad access 1",
+	"XDP pkt read, pkt_data <= pkt_meta', corner case -1, bad access",
 	.insns = {
 	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
 		    offsetof(struct xdp_md, data_meta)),
 	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
 	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6),
 	BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6),
 	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
@@ -898,3 +1432,37 @@
 	.prog_type = BPF_PROG_TYPE_XDP,
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
+{
+	"XDP pkt read, pkt_data <= pkt_meta', corner case, good access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+		    offsetof(struct xdp_md, data_meta)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
+	BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+	"XDP pkt read, pkt_data <= pkt_meta', corner case +1, good access",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+		    offsetof(struct xdp_md, data_meta)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+	BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
diff --git a/arch/mips/boot/compressed/.gitignore b/tools/testing/selftests/damon/.gitignore
index d358395614c9..c6c2965a6607 100644
--- a/arch/mips/boot/compressed/.gitignore
+++ b/tools/testing/selftests/damon/.gitignore
@@ -1,3 +1,2 @@
 # SPDX-License-Identifier: GPL-2.0-only
-ashldi3.c
-bswapsi.c
+huge_count_read_write
diff --git a/tools/testing/selftests/damon/Makefile b/tools/testing/selftests/damon/Makefile
index 8a3f2cd9fec0..937d36ae9a69 100644
--- a/tools/testing/selftests/damon/Makefile
+++ b/tools/testing/selftests/damon/Makefile
@@ -1,7 +1,10 @@
 # SPDX-License-Identifier: GPL-2.0
 # Makefile for damon selftests
 
-TEST_FILES = _chk_dependency.sh
-TEST_PROGS = debugfs_attrs.sh
+TEST_GEN_FILES += huge_count_read_write
+
+TEST_FILES = _chk_dependency.sh _debugfs_common.sh
+TEST_PROGS = debugfs_attrs.sh debugfs_schemes.sh debugfs_target_ids.sh
+TEST_PROGS += debugfs_empty_targets.sh debugfs_huge_count_read_write.sh
 
 include ../lib.mk
diff --git a/tools/testing/selftests/damon/_debugfs_common.sh b/tools/testing/selftests/damon/_debugfs_common.sh
new file mode 100644
index 000000000000..48989d4813ae
--- /dev/null
+++ b/tools/testing/selftests/damon/_debugfs_common.sh
@@ -0,0 +1,52 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+test_write_result() {
+	file=$1
+	content=$2
+	orig_content=$3
+	expect_reason=$4
+	expected=$5
+
+	echo "$content" > "$file"
+	if [ $? -ne "$expected" ]
+	then
+		echo "writing $content to $file doesn't return $expected"
+		echo "expected because: $expect_reason"
+		echo "$orig_content" > "$file"
+		exit 1
+	fi
+}
+
+test_write_succ() {
+	test_write_result "$1" "$2" "$3" "$4" 0
+}
+
+test_write_fail() {
+	test_write_result "$1" "$2" "$3" "$4" 1
+}
+
+test_content() {
+	file=$1
+	orig_content=$2
+	expected=$3
+	expect_reason=$4
+
+	content=$(cat "$file")
+	if [ "$content" != "$expected" ]
+	then
+		echo "reading $file expected $expected but $content"
+		echo "expected because: $expect_reason"
+		echo "$orig_content" > "$file"
+		exit 1
+	fi
+}
+
+source ./_chk_dependency.sh
+
+damon_onoff="$DBGFS/monitor_on"
+if [ $(cat "$damon_onoff") = "on" ]
+then
+	echo "monitoring is on"
+	exit $ksft_skip
+fi
diff --git a/tools/testing/selftests/damon/debugfs_attrs.sh b/tools/testing/selftests/damon/debugfs_attrs.sh
index 196b6640bf37..902e312bca89 100644
--- a/tools/testing/selftests/damon/debugfs_attrs.sh
+++ b/tools/testing/selftests/damon/debugfs_attrs.sh
@@ -1,48 +1,7 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
-test_write_result() {
-	file=$1
-	content=$2
-	orig_content=$3
-	expect_reason=$4
-	expected=$5
-
-	echo "$content" > "$file"
-	if [ $? -ne "$expected" ]
-	then
-		echo "writing $content to $file doesn't return $expected"
-		echo "expected because: $expect_reason"
-		echo "$orig_content" > "$file"
-		exit 1
-	fi
-}
-
-test_write_succ() {
-	test_write_result "$1" "$2" "$3" "$4" 0
-}
-
-test_write_fail() {
-	test_write_result "$1" "$2" "$3" "$4" 1
-}
-
-test_content() {
-	file=$1
-	orig_content=$2
-	expected=$3
-	expect_reason=$4
-
-	content=$(cat "$file")
-	if [ "$content" != "$expected" ]
-	then
-		echo "reading $file expected $expected but $content"
-		echo "expected because: $expect_reason"
-		echo "$orig_content" > "$file"
-		exit 1
-	fi
-}
-
-source ./_chk_dependency.sh
+source _debugfs_common.sh
 
 # Test attrs file
 # ===============
@@ -56,33 +15,3 @@ test_write_fail "$file" "1 2 3 5 4" "$orig_content" \
 	"min_nr_regions > max_nr_regions"
 test_content "$file" "$orig_content" "1 2 3 4 5" "successfully written"
 echo "$orig_content" > "$file"
-
-# Test schemes file
-# =================
-
-file="$DBGFS/schemes"
-orig_content=$(cat "$file")
-
-test_write_succ "$file" "1 2 3 4 5 6 4 0 0 0 1 2 3 1 100 3 2 1" \
-	"$orig_content" "valid input"
-test_write_fail "$file" "1 2
-3 4 5 6 3 0 0 0 1 2 3 1 100 3 2 1" "$orig_content" "multi lines"
-test_write_succ "$file" "" "$orig_content" "disabling"
-echo "$orig_content" > "$file"
-
-# Test target_ids file
-# ====================
-
-file="$DBGFS/target_ids"
-orig_content=$(cat "$file")
-
-test_write_succ "$file" "1 2 3 4" "$orig_content" "valid input"
-test_write_succ "$file" "1 2 abc 4" "$orig_content" "still valid input"
-test_content "$file" "$orig_content" "1 2" "non-integer was there"
-test_write_succ "$file" "abc 2 3" "$orig_content" "the file allows wrong input"
-test_content "$file" "$orig_content" "" "wrong input written"
-test_write_succ "$file" "" "$orig_content" "empty input"
-test_content "$file" "$orig_content" "" "empty input written"
-echo "$orig_content" > "$file"
-
-echo "PASS"
diff --git a/tools/testing/selftests/damon/debugfs_empty_targets.sh b/tools/testing/selftests/damon/debugfs_empty_targets.sh
new file mode 100644
index 000000000000..87aff8083822
--- /dev/null
+++ b/tools/testing/selftests/damon/debugfs_empty_targets.sh
@@ -0,0 +1,13 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source _debugfs_common.sh
+
+# Test empty targets case
+# =======================
+
+orig_target_ids=$(cat "$DBGFS/target_ids")
+echo "" > "$DBGFS/target_ids"
+orig_monitor_on=$(cat "$DBGFS/monitor_on")
+test_write_fail "$DBGFS/monitor_on" "on" "orig_monitor_on" "empty target ids"
+echo "$orig_target_ids" > "$DBGFS/target_ids"
diff --git a/tools/testing/selftests/damon/debugfs_huge_count_read_write.sh b/tools/testing/selftests/damon/debugfs_huge_count_read_write.sh
new file mode 100644
index 000000000000..922cadac2950
--- /dev/null
+++ b/tools/testing/selftests/damon/debugfs_huge_count_read_write.sh
@@ -0,0 +1,22 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source _debugfs_common.sh
+
+# Test huge count read write
+# ==========================
+
+dmesg -C
+
+for file in "$DBGFS/"*
+do
+	./huge_count_read_write "$file"
+done
+
+if dmesg | grep -q WARNING
+then
+	dmesg
+	exit 1
+else
+	exit 0
+fi
diff --git a/tools/testing/selftests/damon/debugfs_schemes.sh b/tools/testing/selftests/damon/debugfs_schemes.sh
new file mode 100644
index 000000000000..5b39ab44731c
--- /dev/null
+++ b/tools/testing/selftests/damon/debugfs_schemes.sh
@@ -0,0 +1,19 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source _debugfs_common.sh
+
+# Test schemes file
+# =================
+
+file="$DBGFS/schemes"
+orig_content=$(cat "$file")
+
+test_write_succ "$file" "1 2 3 4 5 6 4 0 0 0 1 2 3 1 100 3 2 1" \
+	"$orig_content" "valid input"
+test_write_fail "$file" "1 2
+3 4 5 6 3 0 0 0 1 2 3 1 100 3 2 1" "$orig_content" "multi lines"
+test_write_succ "$file" "" "$orig_content" "disabling"
+test_write_fail "$file" "2 1 2 1 10 1 3 10 1 1 1 1 1 1 1 1 2 3" \
+	"$orig_content" "wrong condition ranges"
+echo "$orig_content" > "$file"
diff --git a/tools/testing/selftests/damon/debugfs_target_ids.sh b/tools/testing/selftests/damon/debugfs_target_ids.sh
new file mode 100644
index 000000000000..49aeabdb0aae
--- /dev/null
+++ b/tools/testing/selftests/damon/debugfs_target_ids.sh
@@ -0,0 +1,19 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source _debugfs_common.sh
+
+# Test target_ids file
+# ====================
+
+file="$DBGFS/target_ids"
+orig_content=$(cat "$file")
+
+test_write_succ "$file" "1 2 3 4" "$orig_content" "valid input"
+test_write_succ "$file" "1 2 abc 4" "$orig_content" "still valid input"
+test_content "$file" "$orig_content" "1 2" "non-integer was there"
+test_write_succ "$file" "abc 2 3" "$orig_content" "the file allows wrong input"
+test_content "$file" "$orig_content" "" "wrong input written"
+test_write_succ "$file" "" "$orig_content" "empty input"
+test_content "$file" "$orig_content" "" "empty input written"
+echo "$orig_content" > "$file"
diff --git a/tools/testing/selftests/damon/huge_count_read_write.c b/tools/testing/selftests/damon/huge_count_read_write.c
new file mode 100644
index 000000000000..ad7a6b4cf338
--- /dev/null
+++ b/tools/testing/selftests/damon/huge_count_read_write.c
@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Author: SeongJae Park <sj@kernel.org>
+ */
+
+#include <fcntl.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <stdio.h>
+
+void write_read_with_huge_count(char *file)
+{
+	int filedesc = open(file, O_RDWR);
+	char buf[25];
+	int ret;
+
+	printf("%s %s\n", __func__, file);
+	if (filedesc < 0) {
+		fprintf(stderr, "failed opening %s\n", file);
+		exit(1);
+	}
+
+	write(filedesc, "", 0xfffffffful);
+	perror("after write: ");
+	ret = read(filedesc, buf, 0xfffffffful);
+	perror("after read: ");
+	close(filedesc);
+}
+
+int main(int argc, char *argv[])
+{
+	if (argc != 2) {
+		fprintf(stderr, "Usage: %s <file>\n", argv[0]);
+		exit(1);
+	}
+	write_read_with_huge_count(argv[1]);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/drivers/net/mlxsw/rif_mac_profiles_occ.sh b/tools/testing/selftests/drivers/net/mlxsw/rif_mac_profiles_occ.sh
index b513f64d9092..026a126f584d 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/rif_mac_profiles_occ.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/rif_mac_profiles_occ.sh
@@ -72,6 +72,35 @@ rif_mac_profile_replacement_test()
 	ip link set $h1.10 address $h1_10_mac
 }
 
+rif_mac_profile_consolidation_test()
+{
+	local count=$1; shift
+	local h1_20_mac
+
+	RET=0
+
+	if [[ $count -eq 1 ]]; then
+		return
+	fi
+
+	h1_20_mac=$(mac_get $h1.20)
+
+	# Set the MAC of $h1.20 to that of $h1.10 and confirm that they are
+	# using the same MAC profile.
+	ip link set $h1.20 address 00:11:11:11:11:11
+	check_err $?
+
+	occ=$(devlink -j resource show $DEVLINK_DEV \
+	      | jq '.[][][] | select(.name=="rif_mac_profiles") |.["occ"]')
+
+	[[ $occ -eq $((count - 1)) ]]
+	check_err $? "MAC profile occupancy did not decrease"
+
+	log_test "RIF MAC profile consolidation"
+
+	ip link set $h1.20 address $h1_20_mac
+}
+
 rif_mac_profile_shared_replacement_test()
 {
 	local count=$1; shift
@@ -104,6 +133,7 @@ rif_mac_profile_edit_test()
 	create_max_rif_mac_profiles $count
 
 	rif_mac_profile_replacement_test
+	rif_mac_profile_consolidation_test $count
 	rif_mac_profile_shared_replacement_test $count
 }
 
diff --git a/tools/testing/selftests/gpio/Makefile b/tools/testing/selftests/gpio/Makefile
index 39f2bbe8dd3d..d7b312b44a62 100644
--- a/tools/testing/selftests/gpio/Makefile
+++ b/tools/testing/selftests/gpio/Makefile
@@ -3,5 +3,6 @@
 TEST_PROGS := gpio-mockup.sh
 TEST_FILES := gpio-mockup-sysfs.sh
 TEST_GEN_PROGS_EXTENDED := gpio-mockup-cdev
+CFLAGS += -O2 -g -Wall -I../../../../usr/include/
 
 include ../lib.mk
diff --git a/tools/testing/selftests/gpio/gpio-mockup-cdev.c b/tools/testing/selftests/gpio/gpio-mockup-cdev.c
index e83eac71621a..d1640f44f8ac 100644
--- a/tools/testing/selftests/gpio/gpio-mockup-cdev.c
+++ b/tools/testing/selftests/gpio/gpio-mockup-cdev.c
@@ -117,7 +117,7 @@ int main(int argc, char *argv[])
 {
 	char *chip;
 	int opt, ret, cfd, lfd;
-	unsigned int offset, val, abiv;
+	unsigned int offset, val = 0, abiv;
 	uint32_t flags_v1;
 	uint64_t flags_v2;
 
diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index d4a830139683..3cb5ac5da087 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -23,16 +23,19 @@
 /x86_64/platform_info_test
 /x86_64/set_boot_cpu_id
 /x86_64/set_sregs_test
+/x86_64/sev_migrate_tests
 /x86_64/smm_test
 /x86_64/state_test
 /x86_64/svm_vmcall_test
 /x86_64/svm_int_ctl_test
 /x86_64/sync_regs_test
 /x86_64/tsc_msrs_test
+/x86_64/userspace_io_test
 /x86_64/userspace_msr_exit_test
 /x86_64/vmx_apic_access_test
 /x86_64/vmx_close_while_nested_test
 /x86_64/vmx_dirty_log_test
+/x86_64/vmx_invalid_nested_guest_state
 /x86_64/vmx_preemption_timer_test
 /x86_64/vmx_set_nested_state_test
 /x86_64/vmx_tsc_adjust_test
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index c23e89dea0b6..17342b575e85 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -59,10 +59,12 @@ TEST_GEN_PROGS_x86_64 += x86_64/vmx_preemption_timer_test
 TEST_GEN_PROGS_x86_64 += x86_64/svm_vmcall_test
 TEST_GEN_PROGS_x86_64 += x86_64/svm_int_ctl_test
 TEST_GEN_PROGS_x86_64 += x86_64/sync_regs_test
+TEST_GEN_PROGS_x86_64 += x86_64/userspace_io_test
 TEST_GEN_PROGS_x86_64 += x86_64/userspace_msr_exit_test
 TEST_GEN_PROGS_x86_64 += x86_64/vmx_apic_access_test
 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_invalid_nested_guest_state
 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/vmx_nested_tsc_scaling_test
@@ -73,7 +75,8 @@ TEST_GEN_PROGS_x86_64 += x86_64/tsc_msrs_test
 TEST_GEN_PROGS_x86_64 += x86_64/vmx_pmu_msrs_test
 TEST_GEN_PROGS_x86_64 += x86_64/xen_shinfo_test
 TEST_GEN_PROGS_x86_64 += x86_64/xen_vmcall_test
-TEST_GEN_PROGS_x86_64 += access_tracking_perf_test
+TEST_GEN_PROGS_x86_64 += x86_64/vmx_pi_mmio_test
+TEST_GEN_PROGS_x86_64 += x86_64/sev_migrate_tests
 TEST_GEN_PROGS_x86_64 += demand_paging_test
 TEST_GEN_PROGS_x86_64 += dirty_log_test
 TEST_GEN_PROGS_x86_64 += dirty_log_perf_test
diff --git a/tools/testing/selftests/kvm/access_tracking_perf_test.c b/tools/testing/selftests/kvm/access_tracking_perf_test.c
index 5d95113c7b7c..d8909032317a 100644
--- a/tools/testing/selftests/kvm/access_tracking_perf_test.c
+++ b/tools/testing/selftests/kvm/access_tracking_perf_test.c
@@ -47,7 +47,7 @@
 #include "guest_modes.h"
 
 /* Global variable used to synchronize all of the vCPU threads. */
-static int iteration = -1;
+static int iteration;
 
 /* Defines what vCPU threads should do during a given iteration. */
 static enum {
@@ -215,12 +215,11 @@ static bool spin_wait_for_next_iteration(int *current_iteration)
 	return true;
 }
 
-static void *vcpu_thread_main(void *arg)
+static void vcpu_thread_main(struct perf_test_vcpu_args *vcpu_args)
 {
-	struct perf_test_vcpu_args *vcpu_args = arg;
 	struct kvm_vm *vm = perf_test_args.vm;
 	int vcpu_id = vcpu_args->vcpu_id;
-	int current_iteration = -1;
+	int current_iteration = 0;
 
 	while (spin_wait_for_next_iteration(&current_iteration)) {
 		switch (READ_ONCE(iteration_work)) {
@@ -235,8 +234,6 @@ static void *vcpu_thread_main(void *arg)
 
 		vcpu_last_completed_iteration[vcpu_id] = current_iteration;
 	}
-
-	return NULL;
 }
 
 static void spin_wait_for_vcpu(int vcpu_id, int target_iteration)
@@ -277,8 +274,7 @@ static void run_iteration(struct kvm_vm *vm, int vcpus, const char *description)
 static void access_memory(struct kvm_vm *vm, int vcpus, enum access_type access,
 			  const char *description)
 {
-	perf_test_args.wr_fract = (access == ACCESS_READ) ? INT_MAX : 1;
-	sync_global_to_guest(vm, perf_test_args);
+	perf_test_set_wr_fract(vm, (access == ACCESS_READ) ? INT_MAX : 1);
 	iteration_work = ITERATION_ACCESS_MEMORY;
 	run_iteration(vm, vcpus, description);
 }
@@ -296,48 +292,16 @@ static void mark_memory_idle(struct kvm_vm *vm, int vcpus)
 	run_iteration(vm, vcpus, "Mark memory idle");
 }
 
-static pthread_t *create_vcpu_threads(int vcpus)
-{
-	pthread_t *vcpu_threads;
-	int i;
-
-	vcpu_threads = malloc(vcpus * sizeof(vcpu_threads[0]));
-	TEST_ASSERT(vcpu_threads, "Failed to allocate vcpu_threads.");
-
-	for (i = 0; i < vcpus; i++) {
-		vcpu_last_completed_iteration[i] = iteration;
-		pthread_create(&vcpu_threads[i], NULL, vcpu_thread_main,
-			       &perf_test_args.vcpu_args[i]);
-	}
-
-	return vcpu_threads;
-}
-
-static void terminate_vcpu_threads(pthread_t *vcpu_threads, int vcpus)
-{
-	int i;
-
-	/* Set done to signal the vCPU threads to exit */
-	done = true;
-
-	for (i = 0; i < vcpus; i++)
-		pthread_join(vcpu_threads[i], NULL);
-}
-
 static void run_test(enum vm_guest_mode mode, void *arg)
 {
 	struct test_params *params = arg;
 	struct kvm_vm *vm;
-	pthread_t *vcpu_threads;
 	int vcpus = params->vcpus;
 
 	vm = perf_test_create_vm(mode, vcpus, params->vcpu_memory_bytes, 1,
-				 params->backing_src);
+				 params->backing_src, !overlap_memory_access);
 
-	perf_test_setup_vcpus(vm, vcpus, params->vcpu_memory_bytes,
-			      !overlap_memory_access);
-
-	vcpu_threads = create_vcpu_threads(vcpus);
+	perf_test_start_vcpu_threads(vcpus, vcpu_thread_main);
 
 	pr_info("\n");
 	access_memory(vm, vcpus, ACCESS_WRITE, "Populating memory");
@@ -352,8 +316,10 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	mark_memory_idle(vm, vcpus);
 	access_memory(vm, vcpus, ACCESS_READ, "Reading from idle memory");
 
-	terminate_vcpu_threads(vcpu_threads, vcpus);
-	free(vcpu_threads);
+	/* Set done to signal the vCPU threads to exit */
+	done = true;
+
+	perf_test_join_vcpu_threads(vcpus);
 	perf_test_destroy_vm(vm);
 }
 
diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c
index 1510b21e6306..6a719d065599 100644
--- a/tools/testing/selftests/kvm/demand_paging_test.c
+++ b/tools/testing/selftests/kvm/demand_paging_test.c
@@ -42,10 +42,9 @@ static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE;
 static size_t demand_paging_size;
 static char *guest_data_prototype;
 
-static void *vcpu_worker(void *data)
+static void vcpu_worker(struct perf_test_vcpu_args *vcpu_args)
 {
 	int ret;
-	struct perf_test_vcpu_args *vcpu_args = (struct perf_test_vcpu_args *)data;
 	int vcpu_id = vcpu_args->vcpu_id;
 	struct kvm_vm *vm = perf_test_args.vm;
 	struct kvm_run *run;
@@ -68,8 +67,6 @@ static void *vcpu_worker(void *data)
 	ts_diff = timespec_elapsed(start);
 	PER_VCPU_DEBUG("vCPU %d execution time: %ld.%.9lds\n", vcpu_id,
 		       ts_diff.tv_sec, ts_diff.tv_nsec);
-
-	return NULL;
 }
 
 static int handle_uffd_page_request(int uffd_mode, int uffd, uint64_t addr)
@@ -282,7 +279,6 @@ struct test_params {
 static void run_test(enum vm_guest_mode mode, void *arg)
 {
 	struct test_params *p = arg;
-	pthread_t *vcpu_threads;
 	pthread_t *uffd_handler_threads = NULL;
 	struct uffd_handler_args *uffd_args = NULL;
 	struct timespec start;
@@ -293,9 +289,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	int r;
 
 	vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size, 1,
-				 p->src_type);
-
-	perf_test_args.wr_fract = 1;
+				 p->src_type, p->partition_vcpu_memory_access);
 
 	demand_paging_size = get_backing_src_pagesz(p->src_type);
 
@@ -304,12 +298,6 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 		    "Failed to allocate buffer for guest data pattern");
 	memset(guest_data_prototype, 0xAB, demand_paging_size);
 
-	vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads));
-	TEST_ASSERT(vcpu_threads, "Memory allocation failed");
-
-	perf_test_setup_vcpus(vm, nr_vcpus, guest_percpu_mem_size,
-			      p->partition_vcpu_memory_access);
-
 	if (p->uffd_mode) {
 		uffd_handler_threads =
 			malloc(nr_vcpus * sizeof(*uffd_handler_threads));
@@ -322,26 +310,15 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 		TEST_ASSERT(pipefds, "Unable to allocate memory for pipefd");
 
 		for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
-			vm_paddr_t vcpu_gpa;
+			struct perf_test_vcpu_args *vcpu_args;
 			void *vcpu_hva;
 			void *vcpu_alias;
-			uint64_t vcpu_mem_size;
-
 
-			if (p->partition_vcpu_memory_access) {
-				vcpu_gpa = guest_test_phys_mem +
-					   (vcpu_id * guest_percpu_mem_size);
-				vcpu_mem_size = guest_percpu_mem_size;
-			} else {
-				vcpu_gpa = guest_test_phys_mem;
-				vcpu_mem_size = guest_percpu_mem_size * nr_vcpus;
-			}
-			PER_VCPU_DEBUG("Added VCPU %d with test mem gpa [%lx, %lx)\n",
-				       vcpu_id, vcpu_gpa, vcpu_gpa + vcpu_mem_size);
+			vcpu_args = &perf_test_args.vcpu_args[vcpu_id];
 
 			/* Cache the host addresses of the region */
-			vcpu_hva = addr_gpa2hva(vm, vcpu_gpa);
-			vcpu_alias = addr_gpa2alias(vm, vcpu_gpa);
+			vcpu_hva = addr_gpa2hva(vm, vcpu_args->gpa);
+			vcpu_alias = addr_gpa2alias(vm, vcpu_args->gpa);
 
 			/*
 			 * Set up user fault fd to handle demand paging
@@ -355,32 +332,18 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 					    pipefds[vcpu_id * 2], p->uffd_mode,
 					    p->uffd_delay, &uffd_args[vcpu_id],
 					    vcpu_hva, vcpu_alias,
-					    vcpu_mem_size);
+					    vcpu_args->pages * perf_test_args.guest_page_size);
 		}
 	}
 
-	/* Export the shared variables to the guest */
-	sync_global_to_guest(vm, perf_test_args);
-
 	pr_info("Finished creating vCPUs and starting uffd threads\n");
 
 	clock_gettime(CLOCK_MONOTONIC, &start);
-
-	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
-		pthread_create(&vcpu_threads[vcpu_id], NULL, vcpu_worker,
-			       &perf_test_args.vcpu_args[vcpu_id]);
-	}
-
+	perf_test_start_vcpu_threads(nr_vcpus, vcpu_worker);
 	pr_info("Started all vCPUs\n");
 
-	/* Wait for the vcpu threads to quit */
-	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
-		pthread_join(vcpu_threads[vcpu_id], NULL);
-		PER_VCPU_DEBUG("Joined thread for vCPU %d\n", vcpu_id);
-	}
-
+	perf_test_join_vcpu_threads(nr_vcpus);
 	ts_diff = timespec_elapsed(start);
-
 	pr_info("All vCPU threads joined\n");
 
 	if (p->uffd_mode) {
@@ -404,7 +367,6 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	perf_test_destroy_vm(vm);
 
 	free(guest_data_prototype);
-	free(vcpu_threads);
 	if (p->uffd_mode) {
 		free(uffd_handler_threads);
 		free(uffd_args);
diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c
index 7ffab5bd5ce5..1954b964d1cf 100644
--- a/tools/testing/selftests/kvm/dirty_log_perf_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c
@@ -31,7 +31,7 @@ static bool host_quit;
 static int iteration;
 static int vcpu_last_completed_iteration[KVM_MAX_VCPUS];
 
-static void *vcpu_worker(void *data)
+static void vcpu_worker(struct perf_test_vcpu_args *vcpu_args)
 {
 	int ret;
 	struct kvm_vm *vm = perf_test_args.vm;
@@ -41,7 +41,6 @@ static void *vcpu_worker(void *data)
 	struct timespec ts_diff;
 	struct timespec total = (struct timespec){0};
 	struct timespec avg;
-	struct perf_test_vcpu_args *vcpu_args = (struct perf_test_vcpu_args *)data;
 	int vcpu_id = vcpu_args->vcpu_id;
 
 	run = vcpu_state(vm, vcpu_id);
@@ -83,8 +82,6 @@ static void *vcpu_worker(void *data)
 	pr_debug("\nvCPU %d dirtied 0x%lx pages over %d iterations in %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n",
 		vcpu_id, pages_count, vcpu_last_completed_iteration[vcpu_id],
 		total.tv_sec, total.tv_nsec, avg.tv_sec, avg.tv_nsec);
-
-	return NULL;
 }
 
 struct test_params {
@@ -170,7 +167,6 @@ static void free_bitmaps(unsigned long *bitmaps[], int slots)
 static void run_test(enum vm_guest_mode mode, void *arg)
 {
 	struct test_params *p = arg;
-	pthread_t *vcpu_threads;
 	struct kvm_vm *vm;
 	unsigned long **bitmaps;
 	uint64_t guest_num_pages;
@@ -186,9 +182,10 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	struct timespec clear_dirty_log_total = (struct timespec){0};
 
 	vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size,
-				 p->slots, p->backing_src);
+				 p->slots, p->backing_src,
+				 p->partition_vcpu_memory_access);
 
-	perf_test_args.wr_fract = p->wr_fract;
+	perf_test_set_wr_fract(vm, p->wr_fract);
 
 	guest_num_pages = (nr_vcpus * guest_percpu_mem_size) >> vm_get_page_shift(vm);
 	guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages);
@@ -203,25 +200,15 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 		vm_enable_cap(vm, &cap);
 	}
 
-	vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads));
-	TEST_ASSERT(vcpu_threads, "Memory allocation failed");
-
-	perf_test_setup_vcpus(vm, nr_vcpus, guest_percpu_mem_size,
-			      p->partition_vcpu_memory_access);
-
-	sync_global_to_guest(vm, perf_test_args);
-
 	/* Start the iterations */
 	iteration = 0;
 	host_quit = false;
 
 	clock_gettime(CLOCK_MONOTONIC, &start);
-	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
+	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++)
 		vcpu_last_completed_iteration[vcpu_id] = -1;
 
-		pthread_create(&vcpu_threads[vcpu_id], NULL, vcpu_worker,
-			       &perf_test_args.vcpu_args[vcpu_id]);
-	}
+	perf_test_start_vcpu_threads(nr_vcpus, vcpu_worker);
 
 	/* Allow the vCPUs to populate memory */
 	pr_debug("Starting iteration %d - Populating\n", iteration);
@@ -290,8 +277,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 
 	/* Tell the vcpu thread to quit */
 	host_quit = true;
-	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++)
-		pthread_join(vcpu_threads[vcpu_id], NULL);
+	perf_test_join_vcpu_threads(nr_vcpus);
 
 	avg = timespec_div(get_dirty_log_total, p->iterations);
 	pr_info("Get dirty log over %lu iterations took %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n",
@@ -306,7 +292,6 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	}
 
 	free_bitmaps(bitmaps, p->slots);
-	free(vcpu_threads);
 	perf_test_destroy_vm(vm);
 }
 
diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c
index 792c60e1b17d..3fcd89e195c7 100644
--- a/tools/testing/selftests/kvm/dirty_log_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_test.c
@@ -115,7 +115,7 @@ static void guest_code(void)
 			addr = guest_test_virt_mem;
 			addr += (READ_ONCE(random_array[i]) % guest_num_pages)
 				* guest_page_size;
-			addr &= ~(host_page_size - 1);
+			addr = align_down(addr, host_page_size);
 			*(uint64_t *)addr = READ_ONCE(iteration);
 		}
 
@@ -737,14 +737,14 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	if (!p->phys_offset) {
 		guest_test_phys_mem = (vm_get_max_gfn(vm) -
 				       guest_num_pages) * guest_page_size;
-		guest_test_phys_mem &= ~(host_page_size - 1);
+		guest_test_phys_mem = align_down(guest_test_phys_mem, host_page_size);
 	} else {
 		guest_test_phys_mem = p->phys_offset;
 	}
 
 #ifdef __s390x__
 	/* Align to 1M (segment size) */
-	guest_test_phys_mem &= ~((1 << 20) - 1);
+	guest_test_phys_mem = align_down(guest_test_phys_mem, 1 << 20);
 #endif
 
 	pr_info("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem);
diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index f6b3794f306b..2d62edc49d67 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -82,6 +82,7 @@ struct vm_guest_mode_params {
 };
 extern const struct vm_guest_mode_params vm_guest_mode_params[];
 
+int open_path_or_exit(const char *path, int flags);
 int open_kvm_dev_path_or_exit(void);
 int kvm_check_cap(long cap);
 int vm_enable_cap(struct kvm_vm *vm, struct kvm_enable_cap *cap);
@@ -320,6 +321,7 @@ bool vm_is_unrestricted_guest(struct kvm_vm *vm);
 
 unsigned int vm_get_page_size(struct kvm_vm *vm);
 unsigned int vm_get_page_shift(struct kvm_vm *vm);
+unsigned long vm_compute_max_gfn(struct kvm_vm *vm);
 uint64_t vm_get_max_gfn(struct kvm_vm *vm);
 int vm_get_fd(struct kvm_vm *vm);
 
diff --git a/tools/testing/selftests/kvm/include/perf_test_util.h b/tools/testing/selftests/kvm/include/perf_test_util.h
index df9f1a3a3ffb..a86f953d8d36 100644
--- a/tools/testing/selftests/kvm/include/perf_test_util.h
+++ b/tools/testing/selftests/kvm/include/perf_test_util.h
@@ -8,6 +8,8 @@
 #ifndef SELFTEST_KVM_PERF_TEST_UTIL_H
 #define SELFTEST_KVM_PERF_TEST_UTIL_H
 
+#include <pthread.h>
+
 #include "kvm_util.h"
 
 /* Default guest test virtual memory offset */
@@ -18,6 +20,7 @@
 #define PERF_TEST_MEM_SLOT_INDEX	1
 
 struct perf_test_vcpu_args {
+	uint64_t gpa;
 	uint64_t gva;
 	uint64_t pages;
 
@@ -27,7 +30,7 @@ struct perf_test_vcpu_args {
 
 struct perf_test_args {
 	struct kvm_vm *vm;
-	uint64_t host_page_size;
+	uint64_t gpa;
 	uint64_t guest_page_size;
 	int wr_fract;
 
@@ -36,19 +39,15 @@ struct perf_test_args {
 
 extern struct perf_test_args perf_test_args;
 
-/*
- * Guest physical memory offset of the testing memory slot.
- * This will be set to the topmost valid physical address minus
- * the test memory size.
- */
-extern uint64_t guest_test_phys_mem;
-
 struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 				   uint64_t vcpu_memory_bytes, int slots,
-				   enum vm_mem_backing_src_type backing_src);
+				   enum vm_mem_backing_src_type backing_src,
+				   bool partition_vcpu_memory_access);
 void perf_test_destroy_vm(struct kvm_vm *vm);
-void perf_test_setup_vcpus(struct kvm_vm *vm, int vcpus,
-			   uint64_t vcpu_memory_bytes,
-			   bool partition_vcpu_memory_access);
+
+void perf_test_set_wr_fract(struct kvm_vm *vm, int wr_fract);
+
+void perf_test_start_vcpu_threads(int vcpus, void (*vcpu_fn)(struct perf_test_vcpu_args *));
+void perf_test_join_vcpu_threads(int vcpus);
 
 #endif /* SELFTEST_KVM_PERF_TEST_UTIL_H */
diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h
index f8fddc84c0d3..99e0dcdc923f 100644
--- a/tools/testing/selftests/kvm/include/test_util.h
+++ b/tools/testing/selftests/kvm/include/test_util.h
@@ -104,6 +104,7 @@ size_t get_trans_hugepagesz(void);
 size_t get_def_hugetlb_pagesz(void);
 const struct vm_mem_backing_src_alias *vm_mem_backing_src_alias(uint32_t i);
 size_t get_backing_src_pagesz(uint32_t i);
+bool is_backing_src_hugetlb(uint32_t i);
 void backing_src_help(const char *flag);
 enum vm_mem_backing_src_type parse_backing_src_type(const char *type_name);
 long get_run_delay(void);
@@ -117,4 +118,29 @@ static inline bool backing_src_is_shared(enum vm_mem_backing_src_type t)
 	return vm_mem_backing_src_alias(t)->flag & MAP_SHARED;
 }
 
+/* Aligns x up to the next multiple of size. Size must be a power of 2. */
+static inline uint64_t align_up(uint64_t x, uint64_t size)
+{
+	uint64_t mask = size - 1;
+
+	TEST_ASSERT(size != 0 && !(size & (size - 1)),
+		    "size not a power of 2: %lu", size);
+	return ((x + mask) & ~mask);
+}
+
+static inline uint64_t align_down(uint64_t x, uint64_t size)
+{
+	uint64_t x_aligned_up = align_up(x, size);
+
+	if (x == x_aligned_up)
+		return x;
+	else
+		return x_aligned_up - size;
+}
+
+static inline void *align_ptr_up(void *x, size_t size)
+{
+	return (void *)align_up((unsigned long)x, size);
+}
+
 #endif /* SELFTEST_KVM_TEST_UTIL_H */
diff --git a/tools/testing/selftests/kvm/include/x86_64/svm_util.h b/tools/testing/selftests/kvm/include/x86_64/svm_util.h
index b7531c83b8ae..587fbe408b99 100644
--- a/tools/testing/selftests/kvm/include/x86_64/svm_util.h
+++ b/tools/testing/selftests/kvm/include/x86_64/svm_util.h
@@ -46,4 +46,6 @@ static inline bool cpu_has_svm(void)
 	return ecx & CPUID_SVM;
 }
 
+int open_sev_dev_path_or_exit(void);
+
 #endif /* SELFTEST_KVM_SVM_UTILS_H */
diff --git a/tools/testing/selftests/kvm/kvm_create_max_vcpus.c b/tools/testing/selftests/kvm/kvm_create_max_vcpus.c
index f968dfd4ee88..aed9dc3ca1e9 100644
--- a/tools/testing/selftests/kvm/kvm_create_max_vcpus.c
+++ b/tools/testing/selftests/kvm/kvm_create_max_vcpus.c
@@ -12,6 +12,7 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
+#include <sys/resource.h>
 
 #include "test_util.h"
 
@@ -40,11 +41,40 @@ int main(int argc, char *argv[])
 {
 	int kvm_max_vcpu_id = kvm_check_cap(KVM_CAP_MAX_VCPU_ID);
 	int kvm_max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS);
+	/*
+	 * Number of file descriptors reqired, KVM_CAP_MAX_VCPUS for vCPU fds +
+	 * an arbitrary number for everything else.
+	 */
+	int nr_fds_wanted = kvm_max_vcpus + 100;
+	struct rlimit rl;
 
 	pr_info("KVM_CAP_MAX_VCPU_ID: %d\n", kvm_max_vcpu_id);
 	pr_info("KVM_CAP_MAX_VCPUS: %d\n", kvm_max_vcpus);
 
 	/*
+	 * Check that we're allowed to open nr_fds_wanted file descriptors and
+	 * try raising the limits if needed.
+	 */
+	TEST_ASSERT(!getrlimit(RLIMIT_NOFILE, &rl), "getrlimit() failed!");
+
+	if (rl.rlim_cur < nr_fds_wanted) {
+		rl.rlim_cur = nr_fds_wanted;
+		if (rl.rlim_max < nr_fds_wanted) {
+			int old_rlim_max = rl.rlim_max;
+			rl.rlim_max = nr_fds_wanted;
+
+			int r = setrlimit(RLIMIT_NOFILE, &rl);
+			if (r < 0) {
+				printf("RLIMIT_NOFILE hard limit is too low (%d, wanted %d)\n",
+				       old_rlim_max, nr_fds_wanted);
+				exit(KSFT_SKIP);
+			}
+		} else {
+			TEST_ASSERT(!setrlimit(RLIMIT_NOFILE, &rl), "setrlimit() failed!");
+		}
+	}
+
+	/*
 	 * Upstream KVM prior to 4.8 does not support KVM_CAP_MAX_VCPU_ID.
 	 * Userspace is supposed to use KVM_CAP_MAX_VCPUS as the maximum ID
 	 * in this case.
diff --git a/tools/testing/selftests/kvm/kvm_page_table_test.c b/tools/testing/selftests/kvm/kvm_page_table_test.c
index 36407cb0ec85..ba1fdc3dcf4a 100644
--- a/tools/testing/selftests/kvm/kvm_page_table_test.c
+++ b/tools/testing/selftests/kvm/kvm_page_table_test.c
@@ -280,7 +280,7 @@ static struct kvm_vm *pre_init_before_test(enum vm_guest_mode mode, void *arg)
 #ifdef __s390x__
 	alignment = max(0x100000, alignment);
 #endif
-	guest_test_phys_mem &= ~(alignment - 1);
+	guest_test_phys_mem = align_down(guest_test_phys_mem, alignment);
 
 	/* Set up the shared data structure test_args */
 	test_args.vm = vm;
diff --git a/tools/testing/selftests/kvm/lib/elf.c b/tools/testing/selftests/kvm/lib/elf.c
index eac44f5d0db0..13e8e3dcf984 100644
--- a/tools/testing/selftests/kvm/lib/elf.c
+++ b/tools/testing/selftests/kvm/lib/elf.c
@@ -157,8 +157,7 @@ void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename)
 			"memsize of 0,\n"
 			"  phdr index: %u p_memsz: 0x%" PRIx64,
 			n1, (uint64_t) phdr.p_memsz);
-		vm_vaddr_t seg_vstart = phdr.p_vaddr;
-		seg_vstart &= ~(vm_vaddr_t)(vm->page_size - 1);
+		vm_vaddr_t seg_vstart = align_down(phdr.p_vaddr, vm->page_size);
 		vm_vaddr_t seg_vend = phdr.p_vaddr + phdr.p_memsz - 1;
 		seg_vend |= vm->page_size - 1;
 		size_t seg_size = seg_vend - seg_vstart + 1;
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 041004c0fda7..53d2b5d04b82 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -22,13 +22,17 @@
 
 static int vcpu_mmap_sz(void);
 
-/* Aligns x up to the next multiple of size. Size must be a power of 2. */
-static void *align(void *x, size_t size)
+int open_path_or_exit(const char *path, int flags)
 {
-	size_t mask = size - 1;
-	TEST_ASSERT(size != 0 && !(size & (size - 1)),
-		    "size not a power of 2: %lu", size);
-	return (void *) (((size_t) x + mask) & ~mask);
+	int fd;
+
+	fd = open(path, flags);
+	if (fd < 0) {
+		print_skip("%s not available (errno: %d)", path, errno);
+		exit(KSFT_SKIP);
+	}
+
+	return fd;
 }
 
 /*
@@ -42,16 +46,7 @@ static void *align(void *x, size_t size)
  */
 static int _open_kvm_dev_path_or_exit(int flags)
 {
-	int fd;
-
-	fd = open(KVM_DEV_PATH, flags);
-	if (fd < 0) {
-		print_skip("%s not available, is KVM loaded? (errno: %d)",
-			   KVM_DEV_PATH, errno);
-		exit(KSFT_SKIP);
-	}
-
-	return fd;
+	return open_path_or_exit(KVM_DEV_PATH, flags);
 }
 
 int open_kvm_dev_path_or_exit(void)
@@ -187,15 +182,15 @@ const char *vm_guest_mode_string(uint32_t i)
 }
 
 const struct vm_guest_mode_params vm_guest_mode_params[] = {
-	{ 52, 48,  0x1000, 12 },
-	{ 52, 48, 0x10000, 16 },
-	{ 48, 48,  0x1000, 12 },
-	{ 48, 48, 0x10000, 16 },
-	{ 40, 48,  0x1000, 12 },
-	{ 40, 48, 0x10000, 16 },
-	{  0,  0,  0x1000, 12 },
-	{ 47, 64,  0x1000, 12 },
-	{ 44, 64,  0x1000, 12 },
+	[VM_MODE_P52V48_4K]	= { 52, 48,  0x1000, 12 },
+	[VM_MODE_P52V48_64K]	= { 52, 48, 0x10000, 16 },
+	[VM_MODE_P48V48_4K]	= { 48, 48,  0x1000, 12 },
+	[VM_MODE_P48V48_64K]	= { 48, 48, 0x10000, 16 },
+	[VM_MODE_P40V48_4K]	= { 40, 48,  0x1000, 12 },
+	[VM_MODE_P40V48_64K]	= { 40, 48, 0x10000, 16 },
+	[VM_MODE_PXXV48_4K]	= {  0,  0,  0x1000, 12 },
+	[VM_MODE_P47V64_4K]	= { 47, 64,  0x1000, 12 },
+	[VM_MODE_P44V64_4K]	= { 44, 64,  0x1000, 12 },
 };
 _Static_assert(sizeof(vm_guest_mode_params)/sizeof(struct vm_guest_mode_params) == NUM_VM_MODES,
 	       "Missing new mode params?");
@@ -307,7 +302,7 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
 		(1ULL << (vm->va_bits - 1)) >> vm->page_shift);
 
 	/* Limit physical addresses to PA-bits. */
-	vm->max_gfn = ((1ULL << vm->pa_bits) >> vm->page_shift) - 1;
+	vm->max_gfn = vm_compute_max_gfn(vm);
 
 	/* Allocate and setup memory for guest. */
 	vm->vpages_mapped = sparsebit_alloc();
@@ -875,9 +870,17 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 	alignment = 1;
 #endif
 
+	/*
+	 * When using THP mmap is not guaranteed to returned a hugepage aligned
+	 * address so we have to pad the mmap. Padding is not needed for HugeTLB
+	 * because mmap will always return an address aligned to the HugeTLB
+	 * page size.
+	 */
 	if (src_type == VM_MEM_SRC_ANONYMOUS_THP)
 		alignment = max(backing_src_pagesz, alignment);
 
+	ASSERT_EQ(guest_paddr, align_up(guest_paddr, backing_src_pagesz));
+
 	/* Add enough memory to align up if necessary */
 	if (alignment > 1)
 		region->mmap_size += alignment;
@@ -910,8 +913,13 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 		    "test_malloc failed, mmap_start: %p errno: %i",
 		    region->mmap_start, errno);
 
+	TEST_ASSERT(!is_backing_src_hugetlb(src_type) ||
+		    region->mmap_start == align_ptr_up(region->mmap_start, backing_src_pagesz),
+		    "mmap_start %p is not aligned to HugeTLB page size 0x%lx",
+		    region->mmap_start, backing_src_pagesz);
+
 	/* Align host address */
-	region->host_mem = align(region->mmap_start, alignment);
+	region->host_mem = align_ptr_up(region->mmap_start, alignment);
 
 	/* As needed perform madvise */
 	if ((src_type == VM_MEM_SRC_ANONYMOUS ||
@@ -954,7 +962,7 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 			    "mmap of alias failed, errno: %i", errno);
 
 		/* Align host alias address */
-		region->host_alias = align(region->mmap_alias, alignment);
+		region->host_alias = align_ptr_up(region->mmap_alias, alignment);
 	}
 }
 
@@ -2320,6 +2328,11 @@ unsigned int vm_get_page_shift(struct kvm_vm *vm)
 	return vm->page_shift;
 }
 
+unsigned long __attribute__((weak)) vm_compute_max_gfn(struct kvm_vm *vm)
+{
+	return ((1ULL << vm->pa_bits) >> vm->page_shift) - 1;
+}
+
 uint64_t vm_get_max_gfn(struct kvm_vm *vm)
 {
 	return vm->max_gfn;
diff --git a/tools/testing/selftests/kvm/lib/perf_test_util.c b/tools/testing/selftests/kvm/lib/perf_test_util.c
index 0ef80dbdc116..722df3a28791 100644
--- a/tools/testing/selftests/kvm/lib/perf_test_util.c
+++ b/tools/testing/selftests/kvm/lib/perf_test_util.c
@@ -10,21 +10,40 @@
 
 struct perf_test_args perf_test_args;
 
-uint64_t guest_test_phys_mem;
-
 /*
  * Guest virtual memory offset of the testing memory slot.
  * Must not conflict with identity mapped test code.
  */
 static uint64_t guest_test_virt_mem = DEFAULT_GUEST_TEST_MEM;
 
+struct vcpu_thread {
+	/* The id of the vCPU. */
+	int vcpu_id;
+
+	/* The pthread backing the vCPU. */
+	pthread_t thread;
+
+	/* Set to true once the vCPU thread is up and running. */
+	bool running;
+};
+
+/* The vCPU threads involved in this test. */
+static struct vcpu_thread vcpu_threads[KVM_MAX_VCPUS];
+
+/* The function run by each vCPU thread, as provided by the test. */
+static void (*vcpu_thread_fn)(struct perf_test_vcpu_args *);
+
+/* Set to true once all vCPU threads are up and running. */
+static bool all_vcpu_threads_running;
+
 /*
  * Continuously write to the first 8 bytes of each page in the
  * specified region.
  */
 static void guest_code(uint32_t vcpu_id)
 {
-	struct perf_test_vcpu_args *vcpu_args = &perf_test_args.vcpu_args[vcpu_id];
+	struct perf_test_args *pta = &perf_test_args;
+	struct perf_test_vcpu_args *vcpu_args = &pta->vcpu_args[vcpu_id];
 	uint64_t gva;
 	uint64_t pages;
 	int i;
@@ -37,9 +56,9 @@ static void guest_code(uint32_t vcpu_id)
 
 	while (true) {
 		for (i = 0; i < pages; i++) {
-			uint64_t addr = gva + (i * perf_test_args.guest_page_size);
+			uint64_t addr = gva + (i * pta->guest_page_size);
 
-			if (i % perf_test_args.wr_fract == 0)
+			if (i % pta->wr_fract == 0)
 				*(uint64_t *)addr = 0x0123456789ABCDEF;
 			else
 				READ_ONCE(*(uint64_t *)addr);
@@ -49,35 +68,81 @@ static void guest_code(uint32_t vcpu_id)
 	}
 }
 
+void perf_test_setup_vcpus(struct kvm_vm *vm, int vcpus,
+			   uint64_t vcpu_memory_bytes,
+			   bool partition_vcpu_memory_access)
+{
+	struct perf_test_args *pta = &perf_test_args;
+	struct perf_test_vcpu_args *vcpu_args;
+	int vcpu_id;
+
+	for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
+		vcpu_args = &pta->vcpu_args[vcpu_id];
+
+		vcpu_args->vcpu_id = vcpu_id;
+		if (partition_vcpu_memory_access) {
+			vcpu_args->gva = guest_test_virt_mem +
+					 (vcpu_id * vcpu_memory_bytes);
+			vcpu_args->pages = vcpu_memory_bytes /
+					   pta->guest_page_size;
+			vcpu_args->gpa = pta->gpa + (vcpu_id * vcpu_memory_bytes);
+		} else {
+			vcpu_args->gva = guest_test_virt_mem;
+			vcpu_args->pages = (vcpus * vcpu_memory_bytes) /
+					   pta->guest_page_size;
+			vcpu_args->gpa = pta->gpa;
+		}
+
+		vcpu_args_set(vm, vcpu_id, 1, vcpu_id);
+
+		pr_debug("Added VCPU %d with test mem gpa [%lx, %lx)\n",
+			 vcpu_id, vcpu_args->gpa, vcpu_args->gpa +
+			 (vcpu_args->pages * pta->guest_page_size));
+	}
+}
+
 struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 				   uint64_t vcpu_memory_bytes, int slots,
-				   enum vm_mem_backing_src_type backing_src)
+				   enum vm_mem_backing_src_type backing_src,
+				   bool partition_vcpu_memory_access)
 {
+	struct perf_test_args *pta = &perf_test_args;
 	struct kvm_vm *vm;
 	uint64_t guest_num_pages;
+	uint64_t backing_src_pagesz = get_backing_src_pagesz(backing_src);
 	int i;
 
 	pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode));
 
-	perf_test_args.host_page_size = getpagesize();
-	perf_test_args.guest_page_size = vm_guest_mode_params[mode].page_size;
+	/* By default vCPUs will write to memory. */
+	pta->wr_fract = 1;
+
+	/*
+	 * Snapshot the non-huge page size.  This is used by the guest code to
+	 * access/dirty pages at the logging granularity.
+	 */
+	pta->guest_page_size = vm_guest_mode_params[mode].page_size;
 
 	guest_num_pages = vm_adjust_num_guest_pages(mode,
-				(vcpus * vcpu_memory_bytes) / perf_test_args.guest_page_size);
+				(vcpus * vcpu_memory_bytes) / pta->guest_page_size);
 
-	TEST_ASSERT(vcpu_memory_bytes % perf_test_args.host_page_size == 0,
+	TEST_ASSERT(vcpu_memory_bytes % getpagesize() == 0,
 		    "Guest memory size is not host page size aligned.");
-	TEST_ASSERT(vcpu_memory_bytes % perf_test_args.guest_page_size == 0,
+	TEST_ASSERT(vcpu_memory_bytes % pta->guest_page_size == 0,
 		    "Guest memory size is not guest page size aligned.");
 	TEST_ASSERT(guest_num_pages % slots == 0,
 		    "Guest memory cannot be evenly divided into %d slots.",
 		    slots);
 
+	/*
+	 * Pass guest_num_pages to populate the page tables for test memory.
+	 * The memory is also added to memslot 0, but that's a benign side
+	 * effect as KVM allows aliasing HVAs in meslots.
+	 */
 	vm = vm_create_with_vcpus(mode, vcpus, DEFAULT_GUEST_PHY_PAGES,
-				  (vcpus * vcpu_memory_bytes) / perf_test_args.guest_page_size,
-				  0, guest_code, NULL);
+				  guest_num_pages, 0, guest_code, NULL);
 
-	perf_test_args.vm = vm;
+	pta->vm = vm;
 
 	/*
 	 * If there should be more memory in the guest test region than there
@@ -90,20 +155,18 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 		    guest_num_pages, vm_get_max_gfn(vm), vcpus,
 		    vcpu_memory_bytes);
 
-	guest_test_phys_mem = (vm_get_max_gfn(vm) - guest_num_pages) *
-			      perf_test_args.guest_page_size;
-	guest_test_phys_mem &= ~(perf_test_args.host_page_size - 1);
+	pta->gpa = (vm_get_max_gfn(vm) - guest_num_pages) * pta->guest_page_size;
+	pta->gpa = align_down(pta->gpa, backing_src_pagesz);
 #ifdef __s390x__
 	/* Align to 1M (segment size) */
-	guest_test_phys_mem &= ~((1 << 20) - 1);
+	pta->gpa = align_down(pta->gpa, 1 << 20);
 #endif
-	pr_info("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem);
+	pr_info("guest physical test memory offset: 0x%lx\n", pta->gpa);
 
 	/* Add extra memory slots for testing */
 	for (i = 0; i < slots; i++) {
 		uint64_t region_pages = guest_num_pages / slots;
-		vm_paddr_t region_start = guest_test_phys_mem +
-			region_pages * perf_test_args.guest_page_size * i;
+		vm_paddr_t region_start = pta->gpa + region_pages * pta->guest_page_size * i;
 
 		vm_userspace_mem_region_add(vm, backing_src, region_start,
 					    PERF_TEST_MEM_SLOT_INDEX + i,
@@ -111,10 +174,15 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 	}
 
 	/* Do mapping for the demand paging memory slot */
-	virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, guest_num_pages);
+	virt_map(vm, guest_test_virt_mem, pta->gpa, guest_num_pages);
+
+	perf_test_setup_vcpus(vm, vcpus, vcpu_memory_bytes, partition_vcpu_memory_access);
 
 	ucall_init(vm, NULL);
 
+	/* Export the shared variables to the guest. */
+	sync_global_to_guest(vm, perf_test_args);
+
 	return vm;
 }
 
@@ -124,36 +192,60 @@ void perf_test_destroy_vm(struct kvm_vm *vm)
 	kvm_vm_free(vm);
 }
 
-void perf_test_setup_vcpus(struct kvm_vm *vm, int vcpus,
-			   uint64_t vcpu_memory_bytes,
-			   bool partition_vcpu_memory_access)
+void perf_test_set_wr_fract(struct kvm_vm *vm, int wr_fract)
+{
+	perf_test_args.wr_fract = wr_fract;
+	sync_global_to_guest(vm, perf_test_args);
+}
+
+static void *vcpu_thread_main(void *data)
+{
+	struct vcpu_thread *vcpu = data;
+
+	WRITE_ONCE(vcpu->running, true);
+
+	/*
+	 * Wait for all vCPU threads to be up and running before calling the test-
+	 * provided vCPU thread function. This prevents thread creation (which
+	 * requires taking the mmap_sem in write mode) from interfering with the
+	 * guest faulting in its memory.
+	 */
+	while (!READ_ONCE(all_vcpu_threads_running))
+		;
+
+	vcpu_thread_fn(&perf_test_args.vcpu_args[vcpu->vcpu_id]);
+
+	return NULL;
+}
+
+void perf_test_start_vcpu_threads(int vcpus, void (*vcpu_fn)(struct perf_test_vcpu_args *))
 {
-	vm_paddr_t vcpu_gpa;
-	struct perf_test_vcpu_args *vcpu_args;
 	int vcpu_id;
 
+	vcpu_thread_fn = vcpu_fn;
+	WRITE_ONCE(all_vcpu_threads_running, false);
+
 	for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
-		vcpu_args = &perf_test_args.vcpu_args[vcpu_id];
+		struct vcpu_thread *vcpu = &vcpu_threads[vcpu_id];
 
-		vcpu_args->vcpu_id = vcpu_id;
-		if (partition_vcpu_memory_access) {
-			vcpu_args->gva = guest_test_virt_mem +
-					 (vcpu_id * vcpu_memory_bytes);
-			vcpu_args->pages = vcpu_memory_bytes /
-					   perf_test_args.guest_page_size;
-			vcpu_gpa = guest_test_phys_mem +
-				   (vcpu_id * vcpu_memory_bytes);
-		} else {
-			vcpu_args->gva = guest_test_virt_mem;
-			vcpu_args->pages = (vcpus * vcpu_memory_bytes) /
-					   perf_test_args.guest_page_size;
-			vcpu_gpa = guest_test_phys_mem;
-		}
+		vcpu->vcpu_id = vcpu_id;
+		WRITE_ONCE(vcpu->running, false);
 
-		vcpu_args_set(vm, vcpu_id, 1, vcpu_id);
+		pthread_create(&vcpu->thread, NULL, vcpu_thread_main, vcpu);
+	}
 
-		pr_debug("Added VCPU %d with test mem gpa [%lx, %lx)\n",
-			 vcpu_id, vcpu_gpa, vcpu_gpa +
-			 (vcpu_args->pages * perf_test_args.guest_page_size));
+	for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
+		while (!READ_ONCE(vcpu_threads[vcpu_id].running))
+			;
 	}
+
+	WRITE_ONCE(all_vcpu_threads_running, true);
+}
+
+void perf_test_join_vcpu_threads(int vcpus)
+{
+	int vcpu_id;
+
+	for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++)
+		pthread_join(vcpu_threads[vcpu_id].thread, NULL);
 }
diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c
index b72429108993..6d23878bbfe1 100644
--- a/tools/testing/selftests/kvm/lib/test_util.c
+++ b/tools/testing/selftests/kvm/lib/test_util.c
@@ -283,6 +283,11 @@ size_t get_backing_src_pagesz(uint32_t i)
 	}
 }
 
+bool is_backing_src_hugetlb(uint32_t i)
+{
+	return !!(vm_mem_backing_src_alias(i)->flag & MAP_HUGETLB);
+}
+
 static void print_available_backing_src_types(const char *prefix)
 {
 	int i;
diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
index 82c39db91369..eef7b34756d5 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -1431,3 +1431,71 @@ struct kvm_cpuid2 *vcpu_get_supported_hv_cpuid(struct kvm_vm *vm, uint32_t vcpui
 
 	return cpuid;
 }
+
+#define X86EMUL_CPUID_VENDOR_AuthenticAMD_ebx 0x68747541
+#define X86EMUL_CPUID_VENDOR_AuthenticAMD_ecx 0x444d4163
+#define X86EMUL_CPUID_VENDOR_AuthenticAMD_edx 0x69746e65
+
+static inline unsigned x86_family(unsigned int eax)
+{
+        unsigned int x86;
+
+        x86 = (eax >> 8) & 0xf;
+
+        if (x86 == 0xf)
+                x86 += (eax >> 20) & 0xff;
+
+        return x86;
+}
+
+unsigned long vm_compute_max_gfn(struct kvm_vm *vm)
+{
+	const unsigned long num_ht_pages = 12 << (30 - vm->page_shift); /* 12 GiB */
+	unsigned long ht_gfn, max_gfn, max_pfn;
+	uint32_t eax, ebx, ecx, edx, max_ext_leaf;
+
+	max_gfn = (1ULL << (vm->pa_bits - vm->page_shift)) - 1;
+
+	/* Avoid reserved HyperTransport region on AMD processors.  */
+	eax = ecx = 0;
+	cpuid(&eax, &ebx, &ecx, &edx);
+	if (ebx != X86EMUL_CPUID_VENDOR_AuthenticAMD_ebx ||
+	    ecx != X86EMUL_CPUID_VENDOR_AuthenticAMD_ecx ||
+	    edx != X86EMUL_CPUID_VENDOR_AuthenticAMD_edx)
+		return max_gfn;
+
+	/* On parts with <40 physical address bits, the area is fully hidden */
+	if (vm->pa_bits < 40)
+		return max_gfn;
+
+	/* Before family 17h, the HyperTransport area is just below 1T.  */
+	ht_gfn = (1 << 28) - num_ht_pages;
+	eax = 1;
+	cpuid(&eax, &ebx, &ecx, &edx);
+	if (x86_family(eax) < 0x17)
+		goto done;
+
+	/*
+	 * Otherwise it's at the top of the physical address space, possibly
+	 * reduced due to SME by bits 11:6 of CPUID[0x8000001f].EBX.  Use
+	 * the old conservative value if MAXPHYADDR is not enumerated.
+	 */
+	eax = 0x80000000;
+	cpuid(&eax, &ebx, &ecx, &edx);
+	max_ext_leaf = eax;
+	if (max_ext_leaf < 0x80000008)
+		goto done;
+
+	eax = 0x80000008;
+	cpuid(&eax, &ebx, &ecx, &edx);
+	max_pfn = (1ULL << ((eax & 0xff) - vm->page_shift)) - 1;
+	if (max_ext_leaf >= 0x8000001f) {
+		eax = 0x8000001f;
+		cpuid(&eax, &ebx, &ecx, &edx);
+		max_pfn >>= (ebx >> 6) & 0x3f;
+	}
+
+	ht_gfn = max_pfn - num_ht_pages;
+done:
+	return min(max_gfn, ht_gfn - 1);
+}
diff --git a/tools/testing/selftests/kvm/lib/x86_64/svm.c b/tools/testing/selftests/kvm/lib/x86_64/svm.c
index 161eba7cd128..0ebc03ce079c 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/svm.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/svm.c
@@ -13,6 +13,8 @@
 #include "processor.h"
 #include "svm_util.h"
 
+#define SEV_DEV_PATH "/dev/sev"
+
 struct gpr64_regs guest_regs;
 u64 rflags;
 
@@ -172,3 +174,14 @@ void nested_svm_check_supported(void)
 		exit(KSFT_SKIP);
 	}
 }
+
+/*
+ * Open SEV_DEV_PATH if available, otherwise exit the entire program.
+ *
+ * Return:
+ *   The opened file descriptor of /dev/sev.
+ */
+int open_sev_dev_path_or_exit(void)
+{
+	return open_path_or_exit(SEV_DEV_PATH, 0);
+}
diff --git a/tools/testing/selftests/kvm/memslot_modification_stress_test.c b/tools/testing/selftests/kvm/memslot_modification_stress_test.c
index 4cfcafea9f5a..1410d0a9141a 100644
--- a/tools/testing/selftests/kvm/memslot_modification_stress_test.c
+++ b/tools/testing/selftests/kvm/memslot_modification_stress_test.c
@@ -36,11 +36,9 @@ static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE;
 
 static bool run_vcpus = true;
 
-static void *vcpu_worker(void *data)
+static void vcpu_worker(struct perf_test_vcpu_args *vcpu_args)
 {
 	int ret;
-	struct perf_test_vcpu_args *vcpu_args =
-		(struct perf_test_vcpu_args *)data;
 	int vcpu_id = vcpu_args->vcpu_id;
 	struct kvm_vm *vm = perf_test_args.vm;
 	struct kvm_run *run;
@@ -59,8 +57,6 @@ static void *vcpu_worker(void *data)
 			    "Invalid guest sync status: exit_reason=%s\n",
 			    exit_reason_str(run->exit_reason));
 	}
-
-	return NULL;
 }
 
 struct memslot_antagonist_args {
@@ -80,7 +76,7 @@ static void add_remove_memslot(struct kvm_vm *vm, useconds_t delay,
 	 * Add the dummy memslot just below the perf_test_util memslot, which is
 	 * at the top of the guest physical address space.
 	 */
-	gpa = guest_test_phys_mem - pages * vm_get_page_size(vm);
+	gpa = perf_test_args.gpa - pages * vm_get_page_size(vm);
 
 	for (i = 0; i < nr_modifications; i++) {
 		usleep(delay);
@@ -100,29 +96,15 @@ struct test_params {
 static void run_test(enum vm_guest_mode mode, void *arg)
 {
 	struct test_params *p = arg;
-	pthread_t *vcpu_threads;
 	struct kvm_vm *vm;
-	int vcpu_id;
 
 	vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size, 1,
-				 VM_MEM_SRC_ANONYMOUS);
-
-	perf_test_args.wr_fract = 1;
-
-	vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads));
-	TEST_ASSERT(vcpu_threads, "Memory allocation failed");
-
-	perf_test_setup_vcpus(vm, nr_vcpus, guest_percpu_mem_size,
-			      p->partition_vcpu_memory_access);
-
-	/* Export the shared variables to the guest */
-	sync_global_to_guest(vm, perf_test_args);
+				 VM_MEM_SRC_ANONYMOUS,
+				 p->partition_vcpu_memory_access);
 
 	pr_info("Finished creating vCPUs\n");
 
-	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++)
-		pthread_create(&vcpu_threads[vcpu_id], NULL, vcpu_worker,
-			       &perf_test_args.vcpu_args[vcpu_id]);
+	perf_test_start_vcpu_threads(nr_vcpus, vcpu_worker);
 
 	pr_info("Started all vCPUs\n");
 
@@ -131,16 +113,10 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 
 	run_vcpus = false;
 
-	/* Wait for the vcpu threads to quit */
-	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++)
-		pthread_join(vcpu_threads[vcpu_id], NULL);
-
+	perf_test_join_vcpu_threads(nr_vcpus);
 	pr_info("All vCPU threads joined\n");
 
-	ucall_uninit(vm);
-	kvm_vm_free(vm);
-
-	free(vcpu_threads);
+	perf_test_destroy_vm(vm);
 }
 
 static void help(char *name)
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_features.c b/tools/testing/selftests/kvm/x86_64/hyperv_features.c
index 91d88aaa9899..672915ce73d8 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_features.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_features.c
@@ -165,10 +165,10 @@ static void hv_set_cpuid(struct kvm_vm *vm, struct kvm_cpuid2 *cpuid,
 	vcpu_set_cpuid(vm, VCPU_ID, cpuid);
 }
 
-static void guest_test_msrs_access(struct kvm_vm *vm, struct msr_data *msr,
-				   struct kvm_cpuid2 *best)
+static void guest_test_msrs_access(void)
 {
 	struct kvm_run *run;
+	struct kvm_vm *vm;
 	struct ucall uc;
 	int stage = 0, r;
 	struct kvm_cpuid_entry2 feat = {
@@ -180,11 +180,34 @@ static void guest_test_msrs_access(struct kvm_vm *vm, struct msr_data *msr,
 	struct kvm_cpuid_entry2 dbg = {
 		.function = HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES
 	};
-	struct kvm_enable_cap cap = {0};
-
-	run = vcpu_state(vm, VCPU_ID);
+	struct kvm_cpuid2 *best;
+	vm_vaddr_t msr_gva;
+	struct kvm_enable_cap cap = {
+		.cap = KVM_CAP_HYPERV_ENFORCE_CPUID,
+		.args = {1}
+	};
+	struct msr_data *msr;
 
 	while (true) {
+		vm = vm_create_default(VCPU_ID, 0, guest_msr);
+
+		msr_gva = vm_vaddr_alloc_page(vm);
+		memset(addr_gva2hva(vm, msr_gva), 0x0, getpagesize());
+		msr = addr_gva2hva(vm, msr_gva);
+
+		vcpu_args_set(vm, VCPU_ID, 1, msr_gva);
+		vcpu_enable_cap(vm, VCPU_ID, &cap);
+
+		vcpu_set_hv_cpuid(vm, VCPU_ID);
+
+		best = kvm_get_supported_hv_cpuid();
+
+		vm_init_descriptor_tables(vm);
+		vcpu_init_descriptor_tables(vm, VCPU_ID);
+		vm_install_exception_handler(vm, GP_VECTOR, guest_gp_handler);
+
+		run = vcpu_state(vm, VCPU_ID);
+
 		switch (stage) {
 		case 0:
 			/*
@@ -315,6 +338,7 @@ static void guest_test_msrs_access(struct kvm_vm *vm, struct msr_data *msr,
 			 * capability enabled and guest visible CPUID bit unset.
 			 */
 			cap.cap = KVM_CAP_HYPERV_SYNIC2;
+			cap.args[0] = 0;
 			vcpu_enable_cap(vm, VCPU_ID, &cap);
 			break;
 		case 22:
@@ -461,9 +485,9 @@ static void guest_test_msrs_access(struct kvm_vm *vm, struct msr_data *msr,
 
 		switch (get_ucall(vm, VCPU_ID, &uc)) {
 		case UCALL_SYNC:
-			TEST_ASSERT(uc.args[1] == stage,
-				    "Unexpected stage: %ld (%d expected)\n",
-				    uc.args[1], stage);
+			TEST_ASSERT(uc.args[1] == 0,
+				    "Unexpected stage: %ld (0 expected)\n",
+				    uc.args[1]);
 			break;
 		case UCALL_ABORT:
 			TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0],
@@ -474,13 +498,14 @@ static void guest_test_msrs_access(struct kvm_vm *vm, struct msr_data *msr,
 		}
 
 		stage++;
+		kvm_vm_free(vm);
 	}
 }
 
-static void guest_test_hcalls_access(struct kvm_vm *vm, struct hcall_data *hcall,
-				     void *input, void *output, struct kvm_cpuid2 *best)
+static void guest_test_hcalls_access(void)
 {
 	struct kvm_run *run;
+	struct kvm_vm *vm;
 	struct ucall uc;
 	int stage = 0, r;
 	struct kvm_cpuid_entry2 feat = {
@@ -493,10 +518,38 @@ static void guest_test_hcalls_access(struct kvm_vm *vm, struct hcall_data *hcall
 	struct kvm_cpuid_entry2 dbg = {
 		.function = HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES
 	};
-
-	run = vcpu_state(vm, VCPU_ID);
+	struct kvm_enable_cap cap = {
+		.cap = KVM_CAP_HYPERV_ENFORCE_CPUID,
+		.args = {1}
+	};
+	vm_vaddr_t hcall_page, hcall_params;
+	struct hcall_data *hcall;
+	struct kvm_cpuid2 *best;
 
 	while (true) {
+		vm = vm_create_default(VCPU_ID, 0, guest_hcall);
+
+		vm_init_descriptor_tables(vm);
+		vcpu_init_descriptor_tables(vm, VCPU_ID);
+		vm_install_exception_handler(vm, UD_VECTOR, guest_ud_handler);
+
+		/* Hypercall input/output */
+		hcall_page = vm_vaddr_alloc_pages(vm, 2);
+		hcall = addr_gva2hva(vm, hcall_page);
+		memset(addr_gva2hva(vm, hcall_page), 0x0, 2 * getpagesize());
+
+		hcall_params = vm_vaddr_alloc_page(vm);
+		memset(addr_gva2hva(vm, hcall_params), 0x0, getpagesize());
+
+		vcpu_args_set(vm, VCPU_ID, 2, addr_gva2gpa(vm, hcall_page), hcall_params);
+		vcpu_enable_cap(vm, VCPU_ID, &cap);
+
+		vcpu_set_hv_cpuid(vm, VCPU_ID);
+
+		best = kvm_get_supported_hv_cpuid();
+
+		run = vcpu_state(vm, VCPU_ID);
+
 		switch (stage) {
 		case 0:
 			hcall->control = 0xdeadbeef;
@@ -606,9 +659,9 @@ static void guest_test_hcalls_access(struct kvm_vm *vm, struct hcall_data *hcall
 
 		switch (get_ucall(vm, VCPU_ID, &uc)) {
 		case UCALL_SYNC:
-			TEST_ASSERT(uc.args[1] == stage,
-				    "Unexpected stage: %ld (%d expected)\n",
-				    uc.args[1], stage);
+			TEST_ASSERT(uc.args[1] == 0,
+				    "Unexpected stage: %ld (0 expected)\n",
+				    uc.args[1]);
 			break;
 		case UCALL_ABORT:
 			TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0],
@@ -619,66 +672,15 @@ static void guest_test_hcalls_access(struct kvm_vm *vm, struct hcall_data *hcall
 		}
 
 		stage++;
+		kvm_vm_free(vm);
 	}
 }
 
 int main(void)
 {
-	struct kvm_cpuid2 *best;
-	struct kvm_vm *vm;
-	vm_vaddr_t msr_gva, hcall_page, hcall_params;
-	struct kvm_enable_cap cap = {
-		.cap = KVM_CAP_HYPERV_ENFORCE_CPUID,
-		.args = {1}
-	};
-
-	/* Test MSRs */
-	vm = vm_create_default(VCPU_ID, 0, guest_msr);
-
-	msr_gva = vm_vaddr_alloc_page(vm);
-	memset(addr_gva2hva(vm, msr_gva), 0x0, getpagesize());
-	vcpu_args_set(vm, VCPU_ID, 1, msr_gva);
-	vcpu_enable_cap(vm, VCPU_ID, &cap);
-
-	vcpu_set_hv_cpuid(vm, VCPU_ID);
-
-	best = kvm_get_supported_hv_cpuid();
-
-	vm_init_descriptor_tables(vm);
-	vcpu_init_descriptor_tables(vm, VCPU_ID);
-	vm_install_exception_handler(vm, GP_VECTOR, guest_gp_handler);
-
 	pr_info("Testing access to Hyper-V specific MSRs\n");
-	guest_test_msrs_access(vm, addr_gva2hva(vm, msr_gva),
-			       best);
-	kvm_vm_free(vm);
-
-	/* Test hypercalls */
-	vm = vm_create_default(VCPU_ID, 0, guest_hcall);
-
-	vm_init_descriptor_tables(vm);
-	vcpu_init_descriptor_tables(vm, VCPU_ID);
-	vm_install_exception_handler(vm, UD_VECTOR, guest_ud_handler);
-
-	/* Hypercall input/output */
-	hcall_page = vm_vaddr_alloc_pages(vm, 2);
-	memset(addr_gva2hva(vm, hcall_page), 0x0, 2 * getpagesize());
-
-	hcall_params = vm_vaddr_alloc_page(vm);
-	memset(addr_gva2hva(vm, hcall_params), 0x0, getpagesize());
-
-	vcpu_args_set(vm, VCPU_ID, 2, addr_gva2gpa(vm, hcall_page), hcall_params);
-	vcpu_enable_cap(vm, VCPU_ID, &cap);
-
-	vcpu_set_hv_cpuid(vm, VCPU_ID);
-
-	best = kvm_get_supported_hv_cpuid();
+	guest_test_msrs_access();
 
 	pr_info("Testing access to Hyper-V hypercalls\n");
-	guest_test_hcalls_access(vm, addr_gva2hva(vm, hcall_params),
-				 addr_gva2hva(vm, hcall_page),
-				 addr_gva2hva(vm, hcall_page) + getpagesize(),
-				 best);
-
-	kvm_vm_free(vm);
+	guest_test_hcalls_access();
 }
diff --git a/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c b/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c
new file mode 100644
index 000000000000..29b18d565cf4
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c
@@ -0,0 +1,348 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/kvm.h>
+#include <linux/psp-sev.h>
+#include <stdio.h>
+#include <sys/ioctl.h>
+#include <stdlib.h>
+#include <errno.h>
+#include <pthread.h>
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+#include "svm_util.h"
+#include "kselftest.h"
+#include "../lib/kvm_util_internal.h"
+
+#define SEV_POLICY_ES 0b100
+
+#define NR_MIGRATE_TEST_VCPUS 4
+#define NR_MIGRATE_TEST_VMS 3
+#define NR_LOCK_TESTING_THREADS 3
+#define NR_LOCK_TESTING_ITERATIONS 10000
+
+static void sev_ioctl(int vm_fd, int cmd_id, void *data)
+{
+	struct kvm_sev_cmd cmd = {
+		.id = cmd_id,
+		.data = (uint64_t)data,
+		.sev_fd = open_sev_dev_path_or_exit(),
+	};
+	int ret;
+
+	ret = ioctl(vm_fd, KVM_MEMORY_ENCRYPT_OP, &cmd);
+	TEST_ASSERT((ret == 0 || cmd.error == SEV_RET_SUCCESS),
+		    "%d failed: return code: %d, errno: %d, fw error: %d",
+		    cmd_id, ret, errno, cmd.error);
+}
+
+static struct kvm_vm *sev_vm_create(bool es)
+{
+	struct kvm_vm *vm;
+	struct kvm_sev_launch_start start = { 0 };
+	int i;
+
+	vm = vm_create(VM_MODE_DEFAULT, 0, O_RDWR);
+	sev_ioctl(vm->fd, es ? KVM_SEV_ES_INIT : KVM_SEV_INIT, NULL);
+	for (i = 0; i < NR_MIGRATE_TEST_VCPUS; ++i)
+		vm_vcpu_add(vm, i);
+	if (es)
+		start.policy |= SEV_POLICY_ES;
+	sev_ioctl(vm->fd, KVM_SEV_LAUNCH_START, &start);
+	if (es)
+		sev_ioctl(vm->fd, KVM_SEV_LAUNCH_UPDATE_VMSA, NULL);
+	return vm;
+}
+
+static struct kvm_vm *aux_vm_create(bool with_vcpus)
+{
+	struct kvm_vm *vm;
+	int i;
+
+	vm = vm_create(VM_MODE_DEFAULT, 0, O_RDWR);
+	if (!with_vcpus)
+		return vm;
+
+	for (i = 0; i < NR_MIGRATE_TEST_VCPUS; ++i)
+		vm_vcpu_add(vm, i);
+
+	return vm;
+}
+
+static int __sev_migrate_from(int dst_fd, int src_fd)
+{
+	struct kvm_enable_cap cap = {
+		.cap = KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM,
+		.args = { src_fd }
+	};
+
+	return ioctl(dst_fd, KVM_ENABLE_CAP, &cap);
+}
+
+
+static void sev_migrate_from(int dst_fd, int src_fd)
+{
+	int ret;
+
+	ret = __sev_migrate_from(dst_fd, src_fd);
+	TEST_ASSERT(!ret, "Migration failed, ret: %d, errno: %d\n", ret, errno);
+}
+
+static void test_sev_migrate_from(bool es)
+{
+	struct kvm_vm *src_vm;
+	struct kvm_vm *dst_vms[NR_MIGRATE_TEST_VMS];
+	int i, ret;
+
+	src_vm = sev_vm_create(es);
+	for (i = 0; i < NR_MIGRATE_TEST_VMS; ++i)
+		dst_vms[i] = aux_vm_create(true);
+
+	/* Initial migration from the src to the first dst. */
+	sev_migrate_from(dst_vms[0]->fd, src_vm->fd);
+
+	for (i = 1; i < NR_MIGRATE_TEST_VMS; i++)
+		sev_migrate_from(dst_vms[i]->fd, dst_vms[i - 1]->fd);
+
+	/* Migrate the guest back to the original VM. */
+	ret = __sev_migrate_from(src_vm->fd, dst_vms[NR_MIGRATE_TEST_VMS - 1]->fd);
+	TEST_ASSERT(ret == -1 && errno == EIO,
+		    "VM that was migrated from should be dead. ret %d, errno: %d\n", ret,
+		    errno);
+
+	kvm_vm_free(src_vm);
+	for (i = 0; i < NR_MIGRATE_TEST_VMS; ++i)
+		kvm_vm_free(dst_vms[i]);
+}
+
+struct locking_thread_input {
+	struct kvm_vm *vm;
+	int source_fds[NR_LOCK_TESTING_THREADS];
+};
+
+static void *locking_test_thread(void *arg)
+{
+	int i, j;
+	struct locking_thread_input *input = (struct locking_thread_input *)arg;
+
+	for (i = 0; i < NR_LOCK_TESTING_ITERATIONS; ++i) {
+		j = i % NR_LOCK_TESTING_THREADS;
+		__sev_migrate_from(input->vm->fd, input->source_fds[j]);
+	}
+
+	return NULL;
+}
+
+static void test_sev_migrate_locking(void)
+{
+	struct locking_thread_input input[NR_LOCK_TESTING_THREADS];
+	pthread_t pt[NR_LOCK_TESTING_THREADS];
+	int i;
+
+	for (i = 0; i < NR_LOCK_TESTING_THREADS; ++i) {
+		input[i].vm = sev_vm_create(/* es= */ false);
+		input[0].source_fds[i] = input[i].vm->fd;
+	}
+	for (i = 1; i < NR_LOCK_TESTING_THREADS; ++i)
+		memcpy(input[i].source_fds, input[0].source_fds,
+		       sizeof(input[i].source_fds));
+
+	for (i = 0; i < NR_LOCK_TESTING_THREADS; ++i)
+		pthread_create(&pt[i], NULL, locking_test_thread, &input[i]);
+
+	for (i = 0; i < NR_LOCK_TESTING_THREADS; ++i)
+		pthread_join(pt[i], NULL);
+	for (i = 0; i < NR_LOCK_TESTING_THREADS; ++i)
+		kvm_vm_free(input[i].vm);
+}
+
+static void test_sev_migrate_parameters(void)
+{
+	struct kvm_vm *sev_vm, *sev_es_vm, *vm_no_vcpu, *vm_no_sev,
+		*sev_es_vm_no_vmsa;
+	int ret;
+
+	sev_vm = sev_vm_create(/* es= */ false);
+	sev_es_vm = sev_vm_create(/* es= */ true);
+	vm_no_vcpu = vm_create(VM_MODE_DEFAULT, 0, O_RDWR);
+	vm_no_sev = aux_vm_create(true);
+	sev_es_vm_no_vmsa = vm_create(VM_MODE_DEFAULT, 0, O_RDWR);
+	sev_ioctl(sev_es_vm_no_vmsa->fd, KVM_SEV_ES_INIT, NULL);
+	vm_vcpu_add(sev_es_vm_no_vmsa, 1);
+
+	ret = __sev_migrate_from(sev_vm->fd, sev_es_vm->fd);
+	TEST_ASSERT(
+		ret == -1 && errno == EINVAL,
+		"Should not be able migrate to SEV enabled VM. ret: %d, errno: %d\n",
+		ret, errno);
+
+	ret = __sev_migrate_from(sev_es_vm->fd, sev_vm->fd);
+	TEST_ASSERT(
+		ret == -1 && errno == EINVAL,
+		"Should not be able migrate to SEV-ES enabled VM. ret: %d, errno: %d\n",
+		ret, errno);
+
+	ret = __sev_migrate_from(vm_no_vcpu->fd, sev_es_vm->fd);
+	TEST_ASSERT(
+		ret == -1 && errno == EINVAL,
+		"SEV-ES migrations require same number of vCPUS. ret: %d, errno: %d\n",
+		ret, errno);
+
+	ret = __sev_migrate_from(vm_no_vcpu->fd, sev_es_vm_no_vmsa->fd);
+	TEST_ASSERT(
+		ret == -1 && errno == EINVAL,
+		"SEV-ES migrations require UPDATE_VMSA. ret %d, errno: %d\n",
+		ret, errno);
+
+	ret = __sev_migrate_from(vm_no_vcpu->fd, vm_no_sev->fd);
+	TEST_ASSERT(ret == -1 && errno == EINVAL,
+		    "Migrations require SEV enabled. ret %d, errno: %d\n", ret,
+		    errno);
+
+	kvm_vm_free(sev_vm);
+	kvm_vm_free(sev_es_vm);
+	kvm_vm_free(sev_es_vm_no_vmsa);
+	kvm_vm_free(vm_no_vcpu);
+	kvm_vm_free(vm_no_sev);
+}
+
+static int __sev_mirror_create(int dst_fd, int src_fd)
+{
+	struct kvm_enable_cap cap = {
+		.cap = KVM_CAP_VM_COPY_ENC_CONTEXT_FROM,
+		.args = { src_fd }
+	};
+
+	return ioctl(dst_fd, KVM_ENABLE_CAP, &cap);
+}
+
+
+static void sev_mirror_create(int dst_fd, int src_fd)
+{
+	int ret;
+
+	ret = __sev_mirror_create(dst_fd, src_fd);
+	TEST_ASSERT(!ret, "Copying context failed, ret: %d, errno: %d\n", ret, errno);
+}
+
+static void test_sev_mirror(bool es)
+{
+	struct kvm_vm *src_vm, *dst_vm;
+	struct kvm_sev_launch_start start = {
+		.policy = es ? SEV_POLICY_ES : 0
+	};
+	int i;
+
+	src_vm = sev_vm_create(es);
+	dst_vm = aux_vm_create(false);
+
+	sev_mirror_create(dst_vm->fd, src_vm->fd);
+
+	/* Check that we can complete creation of the mirror VM.  */
+	for (i = 0; i < NR_MIGRATE_TEST_VCPUS; ++i)
+		vm_vcpu_add(dst_vm, i);
+	sev_ioctl(dst_vm->fd, KVM_SEV_LAUNCH_START, &start);
+	if (es)
+		sev_ioctl(dst_vm->fd, KVM_SEV_LAUNCH_UPDATE_VMSA, NULL);
+
+	kvm_vm_free(src_vm);
+	kvm_vm_free(dst_vm);
+}
+
+static void test_sev_mirror_parameters(void)
+{
+	struct kvm_vm *sev_vm, *sev_es_vm, *vm_no_vcpu, *vm_with_vcpu;
+	int ret;
+
+	sev_vm = sev_vm_create(/* es= */ false);
+	sev_es_vm = sev_vm_create(/* es= */ true);
+	vm_with_vcpu = aux_vm_create(true);
+	vm_no_vcpu = aux_vm_create(false);
+
+	ret = __sev_mirror_create(sev_vm->fd, sev_vm->fd);
+	TEST_ASSERT(
+		ret == -1 && errno == EINVAL,
+		"Should not be able copy context to self. ret: %d, errno: %d\n",
+		ret, errno);
+
+	ret = __sev_mirror_create(sev_vm->fd, sev_es_vm->fd);
+	TEST_ASSERT(
+		ret == -1 && errno == EINVAL,
+		"Should not be able copy context to SEV enabled VM. ret: %d, errno: %d\n",
+		ret, errno);
+
+	ret = __sev_mirror_create(sev_es_vm->fd, sev_vm->fd);
+	TEST_ASSERT(
+		ret == -1 && errno == EINVAL,
+		"Should not be able copy context to SEV-ES enabled VM. ret: %d, errno: %d\n",
+		ret, errno);
+
+	ret = __sev_mirror_create(vm_no_vcpu->fd, vm_with_vcpu->fd);
+	TEST_ASSERT(ret == -1 && errno == EINVAL,
+		    "Copy context requires SEV enabled. ret %d, errno: %d\n", ret,
+		    errno);
+
+	ret = __sev_mirror_create(vm_with_vcpu->fd, sev_vm->fd);
+	TEST_ASSERT(
+		ret == -1 && errno == EINVAL,
+		"SEV copy context requires no vCPUS on the destination. ret: %d, errno: %d\n",
+		ret, errno);
+
+	kvm_vm_free(sev_vm);
+	kvm_vm_free(sev_es_vm);
+	kvm_vm_free(vm_with_vcpu);
+	kvm_vm_free(vm_no_vcpu);
+}
+
+static void test_sev_move_copy(void)
+{
+	struct kvm_vm *dst_vm, *sev_vm, *mirror_vm, *dst_mirror_vm;
+	int ret;
+
+	sev_vm = sev_vm_create(/* es= */ false);
+	dst_vm = aux_vm_create(true);
+	mirror_vm = aux_vm_create(false);
+	dst_mirror_vm = aux_vm_create(false);
+
+	sev_mirror_create(mirror_vm->fd, sev_vm->fd);
+	ret = __sev_migrate_from(dst_vm->fd, sev_vm->fd);
+	TEST_ASSERT(ret == -1 && errno == EBUSY,
+		    "Cannot migrate VM that has mirrors. ret %d, errno: %d\n", ret,
+		    errno);
+
+	/* The mirror itself can be migrated.  */
+	sev_migrate_from(dst_mirror_vm->fd, mirror_vm->fd);
+	ret = __sev_migrate_from(dst_vm->fd, sev_vm->fd);
+	TEST_ASSERT(ret == -1 && errno == EBUSY,
+		    "Cannot migrate VM that has mirrors. ret %d, errno: %d\n", ret,
+		    errno);
+
+	/*
+	 * mirror_vm is not a mirror anymore, dst_mirror_vm is.  Thus,
+	 * the owner can be copied as soon as dst_mirror_vm is gone.
+	 */
+	kvm_vm_free(dst_mirror_vm);
+	sev_migrate_from(dst_vm->fd, sev_vm->fd);
+
+	kvm_vm_free(mirror_vm);
+	kvm_vm_free(dst_vm);
+	kvm_vm_free(sev_vm);
+}
+
+int main(int argc, char *argv[])
+{
+	if (kvm_check_cap(KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM)) {
+		test_sev_migrate_from(/* es= */ false);
+		test_sev_migrate_from(/* es= */ true);
+		test_sev_migrate_locking();
+		test_sev_migrate_parameters();
+		if (kvm_check_cap(KVM_CAP_VM_COPY_ENC_CONTEXT_FROM))
+			test_sev_move_copy();
+	}
+	if (kvm_check_cap(KVM_CAP_VM_COPY_ENC_CONTEXT_FROM)) {
+		test_sev_mirror(/* es= */ false);
+		test_sev_mirror(/* es= */ true);
+		test_sev_mirror_parameters();
+	}
+	return 0;
+}
diff --git a/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c b/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c
index df04f56ce859..30a81038df46 100644
--- a/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c
+++ b/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c
@@ -75,7 +75,7 @@ static void l1_guest_code(struct svm_test_data *svm)
 	vmcb->control.int_ctl &= ~V_INTR_MASKING_MASK;
 
 	/* No intercepts for real and virtual interrupts */
-	vmcb->control.intercept &= ~(1ULL << INTERCEPT_INTR | INTERCEPT_VINTR);
+	vmcb->control.intercept &= ~(BIT(INTERCEPT_INTR) | BIT(INTERCEPT_VINTR));
 
 	/* Make a virtual interrupt VINTR_IRQ_NUMBER pending */
 	vmcb->control.int_ctl |= V_IRQ_MASK | (0x1 << V_INTR_PRIO_SHIFT);
diff --git a/tools/testing/selftests/kvm/x86_64/userspace_io_test.c b/tools/testing/selftests/kvm/x86_64/userspace_io_test.c
new file mode 100644
index 000000000000..e4bef2e05686
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/userspace_io_test.c
@@ -0,0 +1,114 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+
+#include "test_util.h"
+
+#include "kvm_util.h"
+#include "processor.h"
+
+#define VCPU_ID			1
+
+static void guest_ins_port80(uint8_t *buffer, unsigned int count)
+{
+	unsigned long end;
+
+	if (count == 2)
+		end = (unsigned long)buffer + 1;
+	else
+		end = (unsigned long)buffer + 8192;
+
+	asm volatile("cld; rep; insb" : "+D"(buffer), "+c"(count) : "d"(0x80) : "memory");
+	GUEST_ASSERT_1(count == 0, count);
+	GUEST_ASSERT_2((unsigned long)buffer == end, buffer, end);
+}
+
+static void guest_code(void)
+{
+	uint8_t buffer[8192];
+	int i;
+
+	/*
+	 * Special case tests.  main() will adjust RCX 2 => 1 and 3 => 8192 to
+	 * test that KVM doesn't explode when userspace modifies the "count" on
+	 * a userspace I/O exit.  KVM isn't required to play nice with the I/O
+	 * itself as KVM doesn't support manipulating the count, it just needs
+	 * to not explode or overflow a buffer.
+	 */
+	guest_ins_port80(buffer, 2);
+	guest_ins_port80(buffer, 3);
+
+	/* Verify KVM fills the buffer correctly when not stuffing RCX. */
+	memset(buffer, 0, sizeof(buffer));
+	guest_ins_port80(buffer, 8192);
+	for (i = 0; i < 8192; i++)
+		GUEST_ASSERT_2(buffer[i] == 0xaa, i, buffer[i]);
+
+	GUEST_DONE();
+}
+
+int main(int argc, char *argv[])
+{
+	struct kvm_regs regs;
+	struct kvm_run *run;
+	struct kvm_vm *vm;
+	struct ucall uc;
+	int rc;
+
+	/* Tell stdout not to buffer its content */
+	setbuf(stdout, NULL);
+
+	/* Create VM */
+	vm = vm_create_default(VCPU_ID, 0, guest_code);
+	run = vcpu_state(vm, VCPU_ID);
+
+	memset(&regs, 0, sizeof(regs));
+
+	while (1) {
+		rc = _vcpu_run(vm, VCPU_ID);
+
+		TEST_ASSERT(rc == 0, "vcpu_run failed: %d\n", rc);
+		TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+			    "Unexpected exit reason: %u (%s),\n",
+			    run->exit_reason,
+			    exit_reason_str(run->exit_reason));
+
+		if (get_ucall(vm, VCPU_ID, &uc))
+			break;
+
+		TEST_ASSERT(run->io.port == 0x80,
+			    "Expected I/O at port 0x80, got port 0x%x\n", run->io.port);
+
+		/*
+		 * Modify the rep string count in RCX: 2 => 1 and 3 => 8192.
+		 * Note, this abuses KVM's batching of rep string I/O to avoid
+		 * getting stuck in an infinite loop.  That behavior isn't in
+		 * scope from a testing perspective as it's not ABI in any way,
+		 * i.e. it really is abusing internal KVM knowledge.
+		 */
+		vcpu_regs_get(vm, VCPU_ID, &regs);
+		if (regs.rcx == 2)
+			regs.rcx = 1;
+		if (regs.rcx == 3)
+			regs.rcx = 8192;
+		memset((void *)run + run->io.data_offset, 0xaa, 4096);
+		vcpu_regs_set(vm, VCPU_ID, &regs);
+	}
+
+	switch (uc.cmd) {
+	case UCALL_DONE:
+		break;
+	case UCALL_ABORT:
+		TEST_FAIL("%s at %s:%ld : argN+1 = 0x%lx, argN+2 = 0x%lx",
+			  (const char *)uc.args[0], __FILE__, uc.args[1],
+			  uc.args[2], uc.args[3]);
+	default:
+		TEST_FAIL("Unknown ucall %lu", uc.cmd);
+	}
+
+	kvm_vm_free(vm);
+	return 0;
+}
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_invalid_nested_guest_state.c b/tools/testing/selftests/kvm/x86_64/vmx_invalid_nested_guest_state.c
new file mode 100644
index 000000000000..489fbed4ca6f
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/vmx_invalid_nested_guest_state.c
@@ -0,0 +1,105 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+#include "vmx.h"
+
+#include <string.h>
+#include <sys/ioctl.h>
+
+#include "kselftest.h"
+
+#define VCPU_ID	0
+#define ARBITRARY_IO_PORT 0x2000
+
+static struct kvm_vm *vm;
+
+static void l2_guest_code(void)
+{
+	/*
+	 * Generate an exit to L0 userspace, i.e. main(), via I/O to an
+	 * arbitrary port.
+	 */
+	asm volatile("inb %%dx, %%al"
+		     : : [port] "d" (ARBITRARY_IO_PORT) : "rax");
+}
+
+static void l1_guest_code(struct vmx_pages *vmx_pages)
+{
+#define L2_GUEST_STACK_SIZE 64
+	unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+
+	GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages));
+	GUEST_ASSERT(load_vmcs(vmx_pages));
+
+	/* Prepare the VMCS for L2 execution. */
+	prepare_vmcs(vmx_pages, l2_guest_code,
+		     &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+
+	/*
+	 * L2 must be run without unrestricted guest, verify that the selftests
+	 * library hasn't enabled it.  Because KVM selftests jump directly to
+	 * 64-bit mode, unrestricted guest support isn't required.
+	 */
+	GUEST_ASSERT(!(vmreadz(CPU_BASED_VM_EXEC_CONTROL) & CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) ||
+		     !(vmreadz(SECONDARY_VM_EXEC_CONTROL) & SECONDARY_EXEC_UNRESTRICTED_GUEST));
+
+	GUEST_ASSERT(!vmlaunch());
+
+	/* L2 should triple fault after main() stuffs invalid guest state. */
+	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_TRIPLE_FAULT);
+	GUEST_DONE();
+}
+
+int main(int argc, char *argv[])
+{
+	vm_vaddr_t vmx_pages_gva;
+	struct kvm_sregs sregs;
+	struct kvm_run *run;
+	struct ucall uc;
+
+	nested_vmx_check_supported();
+
+	vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code);
+
+	/* Allocate VMX pages and shared descriptors (vmx_pages). */
+	vcpu_alloc_vmx(vm, &vmx_pages_gva);
+	vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva);
+
+	vcpu_run(vm, VCPU_ID);
+
+	run = vcpu_state(vm, VCPU_ID);
+
+	/*
+	 * The first exit to L0 userspace should be an I/O access from L2.
+	 * Running L1 should launch L2 without triggering an exit to userspace.
+	 */
+	TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+		    "Expected KVM_EXIT_IO, got: %u (%s)\n",
+		    run->exit_reason, exit_reason_str(run->exit_reason));
+
+	TEST_ASSERT(run->io.port == ARBITRARY_IO_PORT,
+		    "Expected IN from port %d from L2, got port %d",
+		    ARBITRARY_IO_PORT, run->io.port);
+
+	/*
+	 * Stuff invalid guest state for L2 by making TR unusuable.  The next
+	 * KVM_RUN should induce a TRIPLE_FAULT in L2 as KVM doesn't support
+	 * emulating invalid guest state for L2.
+	 */
+	memset(&sregs, 0, sizeof(sregs));
+	vcpu_sregs_get(vm, VCPU_ID, &sregs);
+	sregs.tr.unusable = 1;
+	vcpu_sregs_set(vm, VCPU_ID, &sregs);
+
+	vcpu_run(vm, VCPU_ID);
+
+	switch (get_ucall(vm, VCPU_ID, &uc)) {
+	case UCALL_DONE:
+		break;
+	case UCALL_ABORT:
+		TEST_FAIL("%s", (const char *)uc.args[0]);
+	default:
+		TEST_FAIL("Unexpected ucall: %lu", uc.cmd);
+	}
+}
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_pmu_msrs_test.c b/tools/testing/selftests/kvm/x86_64/vmx_pmu_msrs_test.c
index 23051d84b907..2454a1f2ca0c 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_pmu_msrs_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_pmu_msrs_test.c
@@ -110,22 +110,5 @@ int main(int argc, char *argv[])
 	ret = _vcpu_set_msr(vm, 0, MSR_IA32_PERF_CAPABILITIES, PMU_CAP_LBR_FMT);
 	TEST_ASSERT(ret == 0, "Bad PERF_CAPABILITIES didn't fail.");
 
-	/* testcase 4, set capabilities when we don't have PDCM bit */
-	entry_1_0->ecx &= ~X86_FEATURE_PDCM;
-	vcpu_set_cpuid(vm, VCPU_ID, cpuid);
-	ret = _vcpu_set_msr(vm, 0, MSR_IA32_PERF_CAPABILITIES, host_cap.capabilities);
-	TEST_ASSERT(ret == 0, "Bad PERF_CAPABILITIES didn't fail.");
-
-	/* testcase 5, set capabilities when we don't have PMU version bits */
-	entry_1_0->ecx |= X86_FEATURE_PDCM;
-	eax.split.version_id = 0;
-	entry_1_0->ecx = eax.full;
-	vcpu_set_cpuid(vm, VCPU_ID, cpuid);
-	ret = _vcpu_set_msr(vm, 0, MSR_IA32_PERF_CAPABILITIES, PMU_CAP_FW_WRITES);
-	TEST_ASSERT(ret == 0, "Bad PERF_CAPABILITIES didn't fail.");
-
-	vcpu_set_msr(vm, 0, MSR_IA32_PERF_CAPABILITIES, 0);
-	ASSERT_EQ(vcpu_get_msr(vm, VCPU_ID, MSR_IA32_PERF_CAPABILITIES), 0);
-
 	kvm_vm_free(vm);
 }
diff --git a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
index eda0d2a51224..a0699f00b3d6 100644
--- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
+++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
@@ -24,8 +24,12 @@
 
 #define PVTIME_ADDR	(SHINFO_REGION_GPA + PAGE_SIZE)
 #define RUNSTATE_ADDR	(SHINFO_REGION_GPA + PAGE_SIZE + 0x20)
+#define VCPU_INFO_ADDR	(SHINFO_REGION_GPA + 0x40)
 
 #define RUNSTATE_VADDR	(SHINFO_REGION_GVA + PAGE_SIZE + 0x20)
+#define VCPU_INFO_VADDR	(SHINFO_REGION_GVA + 0x40)
+
+#define EVTCHN_VECTOR	0x10
 
 static struct kvm_vm *vm;
 
@@ -56,15 +60,44 @@ struct vcpu_runstate_info {
     uint64_t time[4];
 };
 
+struct arch_vcpu_info {
+    unsigned long cr2;
+    unsigned long pad; /* sizeof(vcpu_info_t) == 64 */
+};
+
+struct vcpu_info {
+        uint8_t evtchn_upcall_pending;
+        uint8_t evtchn_upcall_mask;
+        unsigned long evtchn_pending_sel;
+        struct arch_vcpu_info arch;
+        struct pvclock_vcpu_time_info time;
+}; /* 64 bytes (x86) */
+
 #define RUNSTATE_running  0
 #define RUNSTATE_runnable 1
 #define RUNSTATE_blocked  2
 #define RUNSTATE_offline  3
 
+static void evtchn_handler(struct ex_regs *regs)
+{
+	struct vcpu_info *vi = (void *)VCPU_INFO_VADDR;
+	vi->evtchn_upcall_pending = 0;
+
+	GUEST_SYNC(0x20);
+}
+
 static void guest_code(void)
 {
 	struct vcpu_runstate_info *rs = (void *)RUNSTATE_VADDR;
 
+	__asm__ __volatile__(
+		"sti\n"
+		"nop\n"
+	);
+
+	/* Trigger an interrupt injection */
+	GUEST_SYNC(0);
+
 	/* Test having the host set runstates manually */
 	GUEST_SYNC(RUNSTATE_runnable);
 	GUEST_ASSERT(rs->time[RUNSTATE_runnable] != 0);
@@ -153,7 +186,7 @@ int main(int argc, char *argv[])
 
 	struct kvm_xen_vcpu_attr vi = {
 		.type = KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO,
-		.u.gpa = SHINFO_REGION_GPA + 0x40,
+		.u.gpa = VCPU_INFO_ADDR,
 	};
 	vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &vi);
 
@@ -163,6 +196,16 @@ int main(int argc, char *argv[])
 	};
 	vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &pvclock);
 
+	struct kvm_xen_hvm_attr vec = {
+		.type = KVM_XEN_ATTR_TYPE_UPCALL_VECTOR,
+		.u.vector = EVTCHN_VECTOR,
+	};
+	vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &vec);
+
+	vm_init_descriptor_tables(vm);
+	vcpu_init_descriptor_tables(vm, VCPU_ID);
+	vm_install_exception_handler(vm, EVTCHN_VECTOR, evtchn_handler);
+
 	if (do_runstate_tests) {
 		struct kvm_xen_vcpu_attr st = {
 			.type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR,
@@ -171,9 +214,14 @@ int main(int argc, char *argv[])
 		vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &st);
 	}
 
+	struct vcpu_info *vinfo = addr_gpa2hva(vm, VCPU_INFO_VADDR);
+	vinfo->evtchn_upcall_pending = 0;
+
 	struct vcpu_runstate_info *rs = addr_gpa2hva(vm, RUNSTATE_ADDR);
 	rs->state = 0x5a;
 
+	bool evtchn_irq_expected = false;
+
 	for (;;) {
 		volatile struct kvm_run *run = vcpu_state(vm, VCPU_ID);
 		struct ucall uc;
@@ -193,16 +241,21 @@ int main(int argc, char *argv[])
 			struct kvm_xen_vcpu_attr rst;
 			long rundelay;
 
-			/* If no runstate support, bail out early */
-			if (!do_runstate_tests)
-				goto done;
-
-			TEST_ASSERT(rs->state_entry_time == rs->time[0] +
-				    rs->time[1] + rs->time[2] + rs->time[3],
-				    "runstate times don't add up");
+			if (do_runstate_tests)
+				TEST_ASSERT(rs->state_entry_time == rs->time[0] +
+					    rs->time[1] + rs->time[2] + rs->time[3],
+					    "runstate times don't add up");
 
 			switch (uc.args[1]) {
-			case RUNSTATE_running...RUNSTATE_offline:
+			case 0:
+				evtchn_irq_expected = true;
+				vinfo->evtchn_upcall_pending = 1;
+				break;
+
+			case RUNSTATE_runnable...RUNSTATE_offline:
+				TEST_ASSERT(!evtchn_irq_expected, "Event channel IRQ not seen");
+				if (!do_runstate_tests)
+					goto done;
 				rst.type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT;
 				rst.u.runstate.state = uc.args[1];
 				vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &rst);
@@ -236,6 +289,10 @@ int main(int argc, char *argv[])
 					sched_yield();
 				} while (get_run_delay() < rundelay);
 				break;
+			case 0x20:
+				TEST_ASSERT(evtchn_irq_expected, "Unexpected event channel IRQ");
+				evtchn_irq_expected = false;
+				break;
 			}
 			break;
 		}
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 7615f29831eb..9897fa9ab953 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -34,6 +34,7 @@ TEST_PROGS += srv6_end_dt46_l3vpn_test.sh
 TEST_PROGS += srv6_end_dt4_l3vpn_test.sh
 TEST_PROGS += srv6_end_dt6_l3vpn_test.sh
 TEST_PROGS += vrf_strict_mode_test.sh
+TEST_PROGS += arp_ndisc_evict_nocarrier.sh
 TEST_PROGS_EXTENDED := in_netns.sh setup_loopback.sh setup_veth.sh
 TEST_PROGS_EXTENDED += toeplitz_client.sh toeplitz.sh
 TEST_GEN_FILES =  socket nettest
diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh
index 3313566ce906..ad2982b72e02 100755
--- a/tools/testing/selftests/net/fcnal-test.sh
+++ b/tools/testing/selftests/net/fcnal-test.sh
@@ -455,6 +455,22 @@ cleanup()
 	ip netns del ${NSC} >/dev/null 2>&1
 }
 
+cleanup_vrf_dup()
+{
+	ip link del ${NSA_DEV2} >/dev/null 2>&1
+	ip netns pids ${NSC} | xargs kill 2>/dev/null
+	ip netns del ${NSC} >/dev/null 2>&1
+}
+
+setup_vrf_dup()
+{
+	# some VRF tests use ns-C which has the same config as
+	# ns-B but for a device NOT in the VRF
+	create_ns ${NSC} "-" "-"
+	connect_ns ${NSA} ${NSA_DEV2} ${NSA_IP}/24 ${NSA_IP6}/64 \
+		   ${NSC} ${NSC_DEV} ${NSB_IP}/24 ${NSB_IP6}/64
+}
+
 setup()
 {
 	local with_vrf=${1}
@@ -484,12 +500,6 @@ setup()
 
 		ip -netns ${NSB} ro add ${VRF_IP}/32 via ${NSA_IP} dev ${NSB_DEV}
 		ip -netns ${NSB} -6 ro add ${VRF_IP6}/128 via ${NSA_IP6} dev ${NSB_DEV}
-
-		# some VRF tests use ns-C which has the same config as
-		# ns-B but for a device NOT in the VRF
-		create_ns ${NSC} "-" "-"
-		connect_ns ${NSA} ${NSA_DEV2} ${NSA_IP}/24 ${NSA_IP6}/64 \
-			   ${NSC} ${NSC_DEV} ${NSB_IP}/24 ${NSB_IP6}/64
 	else
 		ip -netns ${NSA} ro add ${NSB_LO_IP}/32 via ${NSB_IP} dev ${NSA_DEV}
 		ip -netns ${NSA} ro add ${NSB_LO_IP6}/128 via ${NSB_IP6} dev ${NSA_DEV}
@@ -1240,7 +1250,9 @@ ipv4_tcp_vrf()
 	log_test_addr ${a} $? 1 "Global server, local connection"
 
 	# run MD5 tests
+	setup_vrf_dup
 	ipv4_tcp_md5
+	cleanup_vrf_dup
 
 	#
 	# enable VRF global server
@@ -1798,8 +1810,9 @@ ipv4_addr_bind_vrf()
 	for a in ${NSA_IP} ${VRF_IP}
 	do
 		log_start
+		show_hint "Socket not bound to VRF, but address is in VRF"
 		run_cmd nettest -s -R -P icmp -l ${a} -b
-		log_test_addr ${a} $? 0 "Raw socket bind to local address"
+		log_test_addr ${a} $? 1 "Raw socket bind to local address"
 
 		log_start
 		run_cmd nettest -s -R -P icmp -l ${a} -I ${NSA_DEV} -b
@@ -2191,7 +2204,7 @@ ipv6_ping_vrf()
 		log_start
 		show_hint "Fails since VRF device does not support linklocal or multicast"
 		run_cmd ${ping6} -c1 -w1 ${a}
-		log_test_addr ${a} $? 2 "ping out, VRF bind"
+		log_test_addr ${a} $? 1 "ping out, VRF bind"
 	done
 
 	for a in ${NSB_IP6} ${NSB_LO_IP6} ${NSB_LINKIP6}%${NSA_DEV} ${MCAST}%${NSA_DEV}
@@ -2719,7 +2732,9 @@ ipv6_tcp_vrf()
 	log_test_addr ${a} $? 1 "Global server, local connection"
 
 	# run MD5 tests
+	setup_vrf_dup
 	ipv6_tcp_md5
+	cleanup_vrf_dup
 
 	#
 	# enable VRF global server
@@ -3414,11 +3429,14 @@ ipv6_addr_bind_novrf()
 	run_cmd nettest -6 -s -l ${a} -I ${NSA_DEV} -t1 -b
 	log_test_addr ${a} $? 0 "TCP socket bind to local address after device bind"
 
+	# Sadly, the kernel allows binding a socket to a device and then
+	# binding to an address not on the device. So this test passes
+	# when it really should not
 	a=${NSA_LO_IP6}
 	log_start
-	show_hint "Should fail with 'Cannot assign requested address'"
+	show_hint "Tecnically should fail since address is not on device but kernel allows"
 	run_cmd nettest -6 -s -l ${a} -I ${NSA_DEV} -t1 -b
-	log_test_addr ${a} $? 1 "TCP socket bind to out of scope local address"
+	log_test_addr ${a} $? 0 "TCP socket bind to out of scope local address"
 }
 
 ipv6_addr_bind_vrf()
@@ -3459,10 +3477,15 @@ ipv6_addr_bind_vrf()
 	run_cmd nettest -6 -s -l ${a} -I ${NSA_DEV} -t1 -b
 	log_test_addr ${a} $? 0 "TCP socket bind to local address with device bind"
 
+	# Sadly, the kernel allows binding a socket to a device and then
+	# binding to an address not on the device. The only restriction
+	# is that the address is valid in the L3 domain. So this test
+	# passes when it really should not
 	a=${VRF_IP6}
 	log_start
+	show_hint "Tecnically should fail since address is not on device but kernel allows"
 	run_cmd nettest -6 -s -l ${a} -I ${NSA_DEV} -t1 -b
-	log_test_addr ${a} $? 1 "TCP socket bind to VRF address with device bind"
+	log_test_addr ${a} $? 0 "TCP socket bind to VRF address with device bind"
 
 	a=${NSA_LO_IP6}
 	log_start
@@ -4002,8 +4025,8 @@ EOF
 ################################################################################
 # main
 
-TESTS_IPV4="ipv4_ping ipv4_tcp ipv4_udp ipv4_addr_bind ipv4_runtime ipv4_netfilter"
-TESTS_IPV6="ipv6_ping ipv6_tcp ipv6_udp ipv6_addr_bind ipv6_runtime ipv6_netfilter"
+TESTS_IPV4="ipv4_ping ipv4_tcp ipv4_udp ipv4_bind ipv4_runtime ipv4_netfilter"
+TESTS_IPV6="ipv6_ping ipv6_tcp ipv6_udp ipv6_bind ipv6_runtime ipv6_netfilter"
 TESTS_OTHER="use_cases"
 
 PAUSE_ON_FAIL=no
@@ -4077,3 +4100,11 @@ cleanup 2>/dev/null
 
 printf "\nTests passed: %3d\n" ${nsuccess}
 printf "Tests failed: %3d\n"   ${nfail}
+
+if [ $nfail -ne 0 ]; then
+	exit 1 # KSFT_FAIL
+elif [ $nsuccess -eq 0 ]; then
+	exit $ksft_skip
+fi
+
+exit 0 # KSFT_PASS
diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh
index b5a69ad191b0..d444ee6aa3cb 100755
--- a/tools/testing/selftests/net/fib_nexthops.sh
+++ b/tools/testing/selftests/net/fib_nexthops.sh
@@ -629,6 +629,66 @@ ipv6_fcnal()
 	log_test $? 0 "Nexthops removed on admin down"
 }
 
+ipv6_grp_refs()
+{
+	if [ ! -x "$(command -v mausezahn)" ]; then
+		echo "SKIP: Could not run test; need mausezahn tool"
+		return
+	fi
+
+	run_cmd "$IP link set dev veth1 up"
+	run_cmd "$IP link add veth1.10 link veth1 up type vlan id 10"
+	run_cmd "$IP link add veth1.20 link veth1 up type vlan id 20"
+	run_cmd "$IP -6 addr add 2001:db8:91::1/64 dev veth1.10"
+	run_cmd "$IP -6 addr add 2001:db8:92::1/64 dev veth1.20"
+	run_cmd "$IP -6 neigh add 2001:db8:91::2 lladdr 00:11:22:33:44:55 dev veth1.10"
+	run_cmd "$IP -6 neigh add 2001:db8:92::2 lladdr 00:11:22:33:44:55 dev veth1.20"
+	run_cmd "$IP nexthop add id 100 via 2001:db8:91::2 dev veth1.10"
+	run_cmd "$IP nexthop add id 101 via 2001:db8:92::2 dev veth1.20"
+	run_cmd "$IP nexthop add id 102 group 100"
+	run_cmd "$IP route add 2001:db8:101::1/128 nhid 102"
+
+	# create per-cpu dsts through nh 100
+	run_cmd "ip netns exec me mausezahn -6 veth1.10 -B 2001:db8:101::1 -A 2001:db8:91::1 -c 5 -t tcp "dp=1-1023, flags=syn" >/dev/null 2>&1"
+
+	# remove nh 100 from the group to delete the route potentially leaving
+	# a stale per-cpu dst which holds a reference to the nexthop's net
+	# device and to the IPv6 route
+	run_cmd "$IP nexthop replace id 102 group 101"
+	run_cmd "$IP route del 2001:db8:101::1/128"
+
+	# add both nexthops to the group so a reference is taken on them
+	run_cmd "$IP nexthop replace id 102 group 100/101"
+
+	# if the bug described in commit "net: nexthop: release IPv6 per-cpu
+	# dsts when replacing a nexthop group" exists at this point we have
+	# an unlinked IPv6 route (but not freed due to stale dst) with a
+	# reference over the group so we delete the group which will again
+	# only unlink it due to the route reference
+	run_cmd "$IP nexthop del id 102"
+
+	# delete the nexthop with stale dst, since we have an unlinked
+	# group with a ref to it and an unlinked IPv6 route with ref to the
+	# group, the nh will only be unlinked and not freed so the stale dst
+	# remains forever and we get a net device refcount imbalance
+	run_cmd "$IP nexthop del id 100"
+
+	# if a reference was lost this command will hang because the net device
+	# cannot be removed
+	timeout -s KILL 5 ip netns exec me ip link del veth1.10 >/dev/null 2>&1
+
+	# we can't cleanup if the command is hung trying to delete the netdev
+	if [ $? -eq 137 ]; then
+		return 1
+	fi
+
+	# cleanup
+	run_cmd "$IP link del veth1.20"
+	run_cmd "$IP nexthop flush"
+
+	return 0
+}
+
 ipv6_grp_fcnal()
 {
 	local rc
@@ -734,6 +794,9 @@ ipv6_grp_fcnal()
 
 	run_cmd "$IP nexthop add id 108 group 31/24"
 	log_test $? 2 "Nexthop group can not have a blackhole and another nexthop"
+
+	ipv6_grp_refs
+	log_test $? 0 "Nexthop group replace refcounts"
 }
 
 ipv6_res_grp_fcnal()
diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh
index 5abe92d55b69..996af1ae3d3d 100755
--- a/tools/testing/selftests/net/fib_tests.sh
+++ b/tools/testing/selftests/net/fib_tests.sh
@@ -444,24 +444,63 @@ fib_rp_filter_test()
 	setup
 
 	set -e
+	ip netns add ns2
+	ip netns set ns2 auto
+
+	ip -netns ns2 link set dev lo up
+
+	$IP link add name veth1 type veth peer name veth2
+	$IP link set dev veth2 netns ns2
+	$IP address add 192.0.2.1/24 dev veth1
+	ip -netns ns2 address add 192.0.2.1/24 dev veth2
+	$IP link set dev veth1 up
+	ip -netns ns2 link set dev veth2 up
+
 	$IP link set dev lo address 52:54:00:6a:c7:5e
-	$IP link set dummy0 address 52:54:00:6a:c7:5e
-	$IP link add dummy1 type dummy
-	$IP link set dummy1 address 52:54:00:6a:c7:5e
-	$IP link set dev dummy1 up
+	$IP link set dev veth1 address 52:54:00:6a:c7:5e
+	ip -netns ns2 link set dev lo address 52:54:00:6a:c7:5e
+	ip -netns ns2 link set dev veth2 address 52:54:00:6a:c7:5e
+
+	# 1. (ns2) redirect lo's egress to veth2's egress
+	ip netns exec ns2 tc qdisc add dev lo parent root handle 1: fq_codel
+	ip netns exec ns2 tc filter add dev lo parent 1: protocol arp basic \
+		action mirred egress redirect dev veth2
+	ip netns exec ns2 tc filter add dev lo parent 1: protocol ip basic \
+		action mirred egress redirect dev veth2
+
+	# 2. (ns1) redirect veth1's ingress to lo's ingress
+	$NS_EXEC tc qdisc add dev veth1 ingress
+	$NS_EXEC tc filter add dev veth1 ingress protocol arp basic \
+		action mirred ingress redirect dev lo
+	$NS_EXEC tc filter add dev veth1 ingress protocol ip basic \
+		action mirred ingress redirect dev lo
+
+	# 3. (ns1) redirect lo's egress to veth1's egress
+	$NS_EXEC tc qdisc add dev lo parent root handle 1: fq_codel
+	$NS_EXEC tc filter add dev lo parent 1: protocol arp basic \
+		action mirred egress redirect dev veth1
+	$NS_EXEC tc filter add dev lo parent 1: protocol ip basic \
+		action mirred egress redirect dev veth1
+
+	# 4. (ns2) redirect veth2's ingress to lo's ingress
+	ip netns exec ns2 tc qdisc add dev veth2 ingress
+	ip netns exec ns2 tc filter add dev veth2 ingress protocol arp basic \
+		action mirred ingress redirect dev lo
+	ip netns exec ns2 tc filter add dev veth2 ingress protocol ip basic \
+		action mirred ingress redirect dev lo
+
 	$NS_EXEC sysctl -qw net.ipv4.conf.all.rp_filter=1
 	$NS_EXEC sysctl -qw net.ipv4.conf.all.accept_local=1
 	$NS_EXEC sysctl -qw net.ipv4.conf.all.route_localnet=1
-
-	$NS_EXEC tc qd add dev dummy1 parent root handle 1: fq_codel
-	$NS_EXEC tc filter add dev dummy1 parent 1: protocol arp basic action mirred egress redirect dev lo
-	$NS_EXEC tc filter add dev dummy1 parent 1: protocol ip basic action mirred egress redirect dev lo
+	ip netns exec ns2 sysctl -qw net.ipv4.conf.all.rp_filter=1
+	ip netns exec ns2 sysctl -qw net.ipv4.conf.all.accept_local=1
+	ip netns exec ns2 sysctl -qw net.ipv4.conf.all.route_localnet=1
 	set +e
 
-	run_cmd "ip netns exec ns1 ping -I dummy1 -w1 -c1 198.51.100.1"
+	run_cmd "ip netns exec ns2 ping -w1 -c1 192.0.2.1"
 	log_test $? 0 "rp_filter passes local packets"
 
-	run_cmd "ip netns exec ns1 ping -I dummy1 -w1 -c1 127.0.0.1"
+	run_cmd "ip netns exec ns2 ping -w1 -c1 127.0.0.1"
 	log_test $? 0 "rp_filter passes loopback packets"
 
 	cleanup
diff --git a/tools/testing/selftests/net/forwarding/config b/tools/testing/selftests/net/forwarding/config
index a4bd1b087303..697994a9278b 100644
--- a/tools/testing/selftests/net/forwarding/config
+++ b/tools/testing/selftests/net/forwarding/config
@@ -6,6 +6,7 @@ CONFIG_IPV6_MULTIPLE_TABLES=y
 CONFIG_NET_VRF=m
 CONFIG_BPF_SYSCALL=y
 CONFIG_CGROUP_BPF=y
+CONFIG_NET_ACT_CT=m
 CONFIG_NET_ACT_MIRRED=m
 CONFIG_NET_ACT_MPLS=m
 CONFIG_NET_ACT_VLAN=m
diff --git a/tools/testing/selftests/net/forwarding/forwarding.config.sample b/tools/testing/selftests/net/forwarding/forwarding.config.sample
index bf17e485684f..b0980a2efa31 100644
--- a/tools/testing/selftests/net/forwarding/forwarding.config.sample
+++ b/tools/testing/selftests/net/forwarding/forwarding.config.sample
@@ -13,6 +13,8 @@ NETIFS[p5]=veth4
 NETIFS[p6]=veth5
 NETIFS[p7]=veth6
 NETIFS[p8]=veth7
+NETIFS[p9]=veth8
+NETIFS[p10]=veth9
 
 # Port that does not have a cable connected.
 NETIF_NO_CABLE=eth8
diff --git a/tools/testing/selftests/net/forwarding/tc_actions.sh b/tools/testing/selftests/net/forwarding/tc_actions.sh
index d9eca227136b..de19eb6c38f0 100755
--- a/tools/testing/selftests/net/forwarding/tc_actions.sh
+++ b/tools/testing/selftests/net/forwarding/tc_actions.sh
@@ -3,7 +3,7 @@
 
 ALL_TESTS="gact_drop_and_ok_test mirred_egress_redirect_test \
 	mirred_egress_mirror_test matchall_mirred_egress_mirror_test \
-	gact_trap_test"
+	gact_trap_test mirred_egress_to_ingress_test"
 NUM_NETIFS=4
 source tc_common.sh
 source lib.sh
@@ -13,10 +13,12 @@ tcflags="skip_hw"
 h1_create()
 {
 	simple_if_init $h1 192.0.2.1/24
+	tc qdisc add dev $h1 clsact
 }
 
 h1_destroy()
 {
+	tc qdisc del dev $h1 clsact
 	simple_if_fini $h1 192.0.2.1/24
 }
 
@@ -153,6 +155,49 @@ gact_trap_test()
 	log_test "trap ($tcflags)"
 }
 
+mirred_egress_to_ingress_test()
+{
+	RET=0
+
+	tc filter add dev $h1 protocol ip pref 100 handle 100 egress flower \
+		ip_proto icmp src_ip 192.0.2.1 dst_ip 192.0.2.2 type 8 action \
+			ct commit nat src addr 192.0.2.2 pipe \
+			ct clear pipe \
+			ct commit nat dst addr 192.0.2.1 pipe \
+			mirred ingress redirect dev $h1
+
+	tc filter add dev $swp1 protocol ip pref 11 handle 111 ingress flower \
+		ip_proto icmp src_ip 192.0.2.1 dst_ip 192.0.2.2 type 8 action drop
+	tc filter add dev $swp1 protocol ip pref 12 handle 112 ingress flower \
+		ip_proto icmp src_ip 192.0.2.1 dst_ip 192.0.2.2 type 0 action pass
+
+	$MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
+		-t icmp "ping,id=42,seq=10" -q
+
+	tc_check_packets "dev $h1 egress" 100 1
+	check_err $? "didn't mirror first packet"
+
+	tc_check_packets "dev $swp1 ingress" 111 1
+	check_fail $? "didn't redirect first packet"
+	tc_check_packets "dev $swp1 ingress" 112 1
+	check_err $? "didn't receive reply to first packet"
+
+	ping 192.0.2.2 -I$h1 -c1 -w1 -q 1>/dev/null 2>&1
+
+	tc_check_packets "dev $h1 egress" 100 2
+	check_err $? "didn't mirror second packet"
+	tc_check_packets "dev $swp1 ingress" 111 1
+	check_fail $? "didn't redirect second packet"
+	tc_check_packets "dev $swp1 ingress" 112 2
+	check_err $? "didn't receive reply to second packet"
+
+	tc filter del dev $h1 egress protocol ip pref 100 handle 100 flower
+	tc filter del dev $swp1 ingress protocol ip pref 11 handle 111 flower
+	tc filter del dev $swp1 ingress protocol ip pref 12 handle 112 flower
+
+	log_test "mirred_egress_to_ingress ($tcflags)"
+}
+
 setup_prepare()
 {
 	h1=${NETIFS[p1]}
diff --git a/tools/testing/selftests/net/gre_gso.sh b/tools/testing/selftests/net/gre_gso.sh
index fdeb44d621eb..3224651db97b 100755
--- a/tools/testing/selftests/net/gre_gso.sh
+++ b/tools/testing/selftests/net/gre_gso.sh
@@ -118,16 +118,18 @@ gre_gst_test_checks()
 	local addr=$2
 	local proto=$3
 
-	$NS_EXEC nc $proto -kl $port >/dev/null &
+	[ "$proto" == 6 ] && addr="[$addr]"
+
+	$NS_EXEC socat - tcp${proto}-listen:$port,reuseaddr,fork >/dev/null &
 	PID=$!
 	while ! $NS_EXEC ss -ltn | grep -q $port; do ((i++)); sleep 0.01; done
 
-	cat $TMPFILE | timeout 1 nc $proto -N $addr $port
+	cat $TMPFILE | timeout 1 socat -u STDIN TCP:$addr:$port
 	log_test $? 0 "$name - copy file w/ TSO"
 
 	ethtool -K veth0 tso off
 
-	cat $TMPFILE | timeout 1 nc $proto -N $addr $port
+	cat $TMPFILE | timeout 1 socat -u STDIN TCP:$addr:$port
 	log_test $? 0 "$name - copy file w/ GSO"
 
 	ethtool -K veth0 tso on
@@ -155,8 +157,8 @@ gre6_gso_test()
 
 	sleep 2
 
-	gre_gst_test_checks GREv6/v4 172.16.2.2
-	gre_gst_test_checks GREv6/v6 2001:db8:1::2 -6
+	gre_gst_test_checks GREv6/v4 172.16.2.2 4
+	gre_gst_test_checks GREv6/v6 2001:db8:1::2 6
 
 	cleanup
 }
@@ -212,8 +214,8 @@ if [ ! -x "$(command -v ip)" ]; then
 	exit $ksft_skip
 fi
 
-if [ ! -x "$(command -v nc)" ]; then
-	echo "SKIP: Could not run test without nc tool"
+if [ ! -x "$(command -v socat)" ]; then
+	echo "SKIP: Could not run test without socat tool"
 	exit $ksft_skip
 fi
 
diff --git a/tools/testing/selftests/net/icmp_redirect.sh b/tools/testing/selftests/net/icmp_redirect.sh
index ecbf57f264ed..7b9d6e31b8e7 100755
--- a/tools/testing/selftests/net/icmp_redirect.sh
+++ b/tools/testing/selftests/net/icmp_redirect.sh
@@ -311,7 +311,7 @@ check_exception()
 		ip -netns h1 ro get ${H1_VRF_ARG} ${H2_N2_IP} | \
 		grep -E -v 'mtu|redirected' | grep -q "cache"
 	fi
-	log_test $? 0 "IPv4: ${desc}"
+	log_test $? 0 "IPv4: ${desc}" 0
 
 	# No PMTU info for test "redirect" and "mtu exception plus redirect"
 	if [ "$with_redirect" = "yes" ] && [ "$desc" != "redirect exception plus mtu" ]; then
diff --git a/tools/testing/selftests/net/mptcp/config b/tools/testing/selftests/net/mptcp/config
index 0faaccd21447..2b82628decb1 100644
--- a/tools/testing/selftests/net/mptcp/config
+++ b/tools/testing/selftests/net/mptcp/config
@@ -9,7 +9,6 @@ CONFIG_NETFILTER=y
 CONFIG_NETFILTER_ADVANCED=y
 CONFIG_NETFILTER_NETLINK=m
 CONFIG_NF_TABLES=m
-CONFIG_NFT_COUNTER=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NETFILTER_XTABLES=m
 CONFIG_NETFILTER_XT_MATCH_BPF=m
diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index e61fc4c32ba2..6e468e0f42f7 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -31,6 +31,8 @@ struct tls_crypto_info_keys {
 		struct tls12_crypto_info_chacha20_poly1305 chacha20;
 		struct tls12_crypto_info_sm4_gcm sm4gcm;
 		struct tls12_crypto_info_sm4_ccm sm4ccm;
+		struct tls12_crypto_info_aes_ccm_128 aesccm128;
+		struct tls12_crypto_info_aes_gcm_256 aesgcm256;
 	};
 	size_t len;
 };
@@ -61,6 +63,16 @@ static void tls_crypto_info_init(uint16_t tls_version, uint16_t cipher_type,
 		tls12->sm4ccm.info.version = tls_version;
 		tls12->sm4ccm.info.cipher_type = cipher_type;
 		break;
+	case TLS_CIPHER_AES_CCM_128:
+		tls12->len = sizeof(struct tls12_crypto_info_aes_ccm_128);
+		tls12->aesccm128.info.version = tls_version;
+		tls12->aesccm128.info.cipher_type = cipher_type;
+		break;
+	case TLS_CIPHER_AES_GCM_256:
+		tls12->len = sizeof(struct tls12_crypto_info_aes_gcm_256);
+		tls12->aesgcm256.info.version = tls_version;
+		tls12->aesgcm256.info.cipher_type = cipher_type;
+		break;
 	default:
 		break;
 	}
@@ -78,26 +90,21 @@ static void memrnd(void *s, size_t n)
 		*byte++ = rand();
 }
 
-FIXTURE(tls_basic)
-{
-	int fd, cfd;
-	bool notls;
-};
-
-FIXTURE_SETUP(tls_basic)
+static void ulp_sock_pair(struct __test_metadata *_metadata,
+			  int *fd, int *cfd, bool *notls)
 {
 	struct sockaddr_in addr;
 	socklen_t len;
 	int sfd, ret;
 
-	self->notls = false;
+	*notls = false;
 	len = sizeof(addr);
 
 	addr.sin_family = AF_INET;
 	addr.sin_addr.s_addr = htonl(INADDR_ANY);
 	addr.sin_port = 0;
 
-	self->fd = socket(AF_INET, SOCK_STREAM, 0);
+	*fd = socket(AF_INET, SOCK_STREAM, 0);
 	sfd = socket(AF_INET, SOCK_STREAM, 0);
 
 	ret = bind(sfd, &addr, sizeof(addr));
@@ -108,26 +115,96 @@ FIXTURE_SETUP(tls_basic)
 	ret = getsockname(sfd, &addr, &len);
 	ASSERT_EQ(ret, 0);
 
-	ret = connect(self->fd, &addr, sizeof(addr));
+	ret = connect(*fd, &addr, sizeof(addr));
 	ASSERT_EQ(ret, 0);
 
-	self->cfd = accept(sfd, &addr, &len);
-	ASSERT_GE(self->cfd, 0);
+	*cfd = accept(sfd, &addr, &len);
+	ASSERT_GE(*cfd, 0);
 
 	close(sfd);
 
-	ret = setsockopt(self->fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls"));
+	ret = setsockopt(*fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls"));
 	if (ret != 0) {
 		ASSERT_EQ(errno, ENOENT);
-		self->notls = true;
+		*notls = true;
 		printf("Failure setting TCP_ULP, testing without tls\n");
 		return;
 	}
 
-	ret = setsockopt(self->cfd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls"));
+	ret = setsockopt(*cfd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls"));
 	ASSERT_EQ(ret, 0);
 }
 
+/* Produce a basic cmsg */
+static int tls_send_cmsg(int fd, unsigned char record_type,
+			 void *data, size_t len, int flags)
+{
+	char cbuf[CMSG_SPACE(sizeof(char))];
+	int cmsg_len = sizeof(char);
+	struct cmsghdr *cmsg;
+	struct msghdr msg;
+	struct iovec vec;
+
+	vec.iov_base = data;
+	vec.iov_len = len;
+	memset(&msg, 0, sizeof(struct msghdr));
+	msg.msg_iov = &vec;
+	msg.msg_iovlen = 1;
+	msg.msg_control = cbuf;
+	msg.msg_controllen = sizeof(cbuf);
+	cmsg = CMSG_FIRSTHDR(&msg);
+	cmsg->cmsg_level = SOL_TLS;
+	/* test sending non-record types. */
+	cmsg->cmsg_type = TLS_SET_RECORD_TYPE;
+	cmsg->cmsg_len = CMSG_LEN(cmsg_len);
+	*CMSG_DATA(cmsg) = record_type;
+	msg.msg_controllen = cmsg->cmsg_len;
+
+	return sendmsg(fd, &msg, flags);
+}
+
+static int tls_recv_cmsg(struct __test_metadata *_metadata,
+			 int fd, unsigned char record_type,
+			 void *data, size_t len, int flags)
+{
+	char cbuf[CMSG_SPACE(sizeof(char))];
+	struct cmsghdr *cmsg;
+	unsigned char ctype;
+	struct msghdr msg;
+	struct iovec vec;
+	int n;
+
+	vec.iov_base = data;
+	vec.iov_len = len;
+	memset(&msg, 0, sizeof(struct msghdr));
+	msg.msg_iov = &vec;
+	msg.msg_iovlen = 1;
+	msg.msg_control = cbuf;
+	msg.msg_controllen = sizeof(cbuf);
+
+	n = recvmsg(fd, &msg, flags);
+
+	cmsg = CMSG_FIRSTHDR(&msg);
+	EXPECT_NE(cmsg, NULL);
+	EXPECT_EQ(cmsg->cmsg_level, SOL_TLS);
+	EXPECT_EQ(cmsg->cmsg_type, TLS_GET_RECORD_TYPE);
+	ctype = *((unsigned char *)CMSG_DATA(cmsg));
+	EXPECT_EQ(ctype, record_type);
+
+	return n;
+}
+
+FIXTURE(tls_basic)
+{
+	int fd, cfd;
+	bool notls;
+};
+
+FIXTURE_SETUP(tls_basic)
+{
+	ulp_sock_pair(_metadata, &self->fd, &self->cfd, &self->notls);
+}
+
 FIXTURE_TEARDOWN(tls_basic)
 {
 	close(self->fd);
@@ -196,63 +273,48 @@ FIXTURE_VARIANT_ADD(tls, 13_sm4_ccm)
 	.cipher_type = TLS_CIPHER_SM4_CCM,
 };
 
+FIXTURE_VARIANT_ADD(tls, 12_aes_ccm)
+{
+	.tls_version = TLS_1_2_VERSION,
+	.cipher_type = TLS_CIPHER_AES_CCM_128,
+};
+
+FIXTURE_VARIANT_ADD(tls, 13_aes_ccm)
+{
+	.tls_version = TLS_1_3_VERSION,
+	.cipher_type = TLS_CIPHER_AES_CCM_128,
+};
+
+FIXTURE_VARIANT_ADD(tls, 12_aes_gcm_256)
+{
+	.tls_version = TLS_1_2_VERSION,
+	.cipher_type = TLS_CIPHER_AES_GCM_256,
+};
+
+FIXTURE_VARIANT_ADD(tls, 13_aes_gcm_256)
+{
+	.tls_version = TLS_1_3_VERSION,
+	.cipher_type = TLS_CIPHER_AES_GCM_256,
+};
+
 FIXTURE_SETUP(tls)
 {
 	struct tls_crypto_info_keys tls12;
-	struct sockaddr_in addr;
-	socklen_t len;
-	int sfd, ret;
-
-	self->notls = false;
-	len = sizeof(addr);
+	int ret;
 
 	tls_crypto_info_init(variant->tls_version, variant->cipher_type,
 			     &tls12);
 
-	addr.sin_family = AF_INET;
-	addr.sin_addr.s_addr = htonl(INADDR_ANY);
-	addr.sin_port = 0;
-
-	self->fd = socket(AF_INET, SOCK_STREAM, 0);
-	sfd = socket(AF_INET, SOCK_STREAM, 0);
+	ulp_sock_pair(_metadata, &self->fd, &self->cfd, &self->notls);
 
-	ret = bind(sfd, &addr, sizeof(addr));
-	ASSERT_EQ(ret, 0);
-	ret = listen(sfd, 10);
-	ASSERT_EQ(ret, 0);
+	if (self->notls)
+		return;
 
-	ret = getsockname(sfd, &addr, &len);
+	ret = setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len);
 	ASSERT_EQ(ret, 0);
 
-	ret = connect(self->fd, &addr, sizeof(addr));
+	ret = setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12, tls12.len);
 	ASSERT_EQ(ret, 0);
-
-	ret = setsockopt(self->fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls"));
-	if (ret != 0) {
-		self->notls = true;
-		printf("Failure setting TCP_ULP, testing without tls\n");
-	}
-
-	if (!self->notls) {
-		ret = setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12,
-				 tls12.len);
-		ASSERT_EQ(ret, 0);
-	}
-
-	self->cfd = accept(sfd, &addr, &len);
-	ASSERT_GE(self->cfd, 0);
-
-	if (!self->notls) {
-		ret = setsockopt(self->cfd, IPPROTO_TCP, TCP_ULP, "tls",
-				 sizeof("tls"));
-		ASSERT_EQ(ret, 0);
-
-		ret = setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12,
-				 tls12.len);
-		ASSERT_EQ(ret, 0);
-	}
-
-	close(sfd);
 }
 
 FIXTURE_TEARDOWN(tls)
@@ -613,6 +675,95 @@ TEST_F(tls, splice_to_pipe)
 	EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0);
 }
 
+TEST_F(tls, splice_cmsg_to_pipe)
+{
+	char *test_str = "test_read";
+	char record_type = 100;
+	int send_len = 10;
+	char buf[10];
+	int p[2];
+
+	ASSERT_GE(pipe(p), 0);
+	EXPECT_EQ(tls_send_cmsg(self->fd, 100, test_str, send_len, 0), 10);
+	EXPECT_EQ(splice(self->cfd, NULL, p[1], NULL, send_len, 0), -1);
+	EXPECT_EQ(errno, EINVAL);
+	EXPECT_EQ(recv(self->cfd, buf, send_len, 0), -1);
+	EXPECT_EQ(errno, EIO);
+	EXPECT_EQ(tls_recv_cmsg(_metadata, self->cfd, record_type,
+				buf, sizeof(buf), MSG_WAITALL),
+		  send_len);
+	EXPECT_EQ(memcmp(test_str, buf, send_len), 0);
+}
+
+TEST_F(tls, splice_dec_cmsg_to_pipe)
+{
+	char *test_str = "test_read";
+	char record_type = 100;
+	int send_len = 10;
+	char buf[10];
+	int p[2];
+
+	ASSERT_GE(pipe(p), 0);
+	EXPECT_EQ(tls_send_cmsg(self->fd, 100, test_str, send_len, 0), 10);
+	EXPECT_EQ(recv(self->cfd, buf, send_len, 0), -1);
+	EXPECT_EQ(errno, EIO);
+	EXPECT_EQ(splice(self->cfd, NULL, p[1], NULL, send_len, 0), -1);
+	EXPECT_EQ(errno, EINVAL);
+	EXPECT_EQ(tls_recv_cmsg(_metadata, self->cfd, record_type,
+				buf, sizeof(buf), MSG_WAITALL),
+		  send_len);
+	EXPECT_EQ(memcmp(test_str, buf, send_len), 0);
+}
+
+TEST_F(tls, recv_and_splice)
+{
+	int send_len = TLS_PAYLOAD_MAX_LEN;
+	char mem_send[TLS_PAYLOAD_MAX_LEN];
+	char mem_recv[TLS_PAYLOAD_MAX_LEN];
+	int half = send_len / 2;
+	int p[2];
+
+	ASSERT_GE(pipe(p), 0);
+	EXPECT_EQ(send(self->fd, mem_send, send_len, 0), send_len);
+	/* Recv hald of the record, splice the other half */
+	EXPECT_EQ(recv(self->cfd, mem_recv, half, MSG_WAITALL), half);
+	EXPECT_EQ(splice(self->cfd, NULL, p[1], NULL, half, SPLICE_F_NONBLOCK),
+		  half);
+	EXPECT_EQ(read(p[0], &mem_recv[half], half), half);
+	EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0);
+}
+
+TEST_F(tls, peek_and_splice)
+{
+	int send_len = TLS_PAYLOAD_MAX_LEN;
+	char mem_send[TLS_PAYLOAD_MAX_LEN];
+	char mem_recv[TLS_PAYLOAD_MAX_LEN];
+	int chunk = TLS_PAYLOAD_MAX_LEN / 4;
+	int n, i, p[2];
+
+	memrnd(mem_send, sizeof(mem_send));
+
+	ASSERT_GE(pipe(p), 0);
+	for (i = 0; i < 4; i++)
+		EXPECT_EQ(send(self->fd, &mem_send[chunk * i], chunk, 0),
+			  chunk);
+
+	EXPECT_EQ(recv(self->cfd, mem_recv, chunk * 5 / 2,
+		       MSG_WAITALL | MSG_PEEK),
+		  chunk * 5 / 2);
+	EXPECT_EQ(memcmp(mem_send, mem_recv, chunk * 5 / 2), 0);
+
+	n = 0;
+	while (n < send_len) {
+		i = splice(self->cfd, NULL, p[1], NULL, send_len - n, 0);
+		EXPECT_GT(i, 0);
+		n += i;
+	}
+	EXPECT_EQ(n, send_len);
+	EXPECT_EQ(read(p[0], mem_recv, send_len), send_len);
+	EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0);
+}
+
 TEST_F(tls, recvmsg_single)
 {
 	char const *test_str = "test_recvmsg_single";
@@ -1193,60 +1344,30 @@ TEST_F(tls, mutliproc_sendpage_writers)
 
 TEST_F(tls, control_msg)
 {
-	if (self->notls)
-		return;
-
-	char cbuf[CMSG_SPACE(sizeof(char))];
-	char const *test_str = "test_read";
-	int cmsg_len = sizeof(char);
+	char *test_str = "test_read";
 	char record_type = 100;
-	struct cmsghdr *cmsg;
-	struct msghdr msg;
 	int send_len = 10;
-	struct iovec vec;
 	char buf[10];
 
-	vec.iov_base = (char *)test_str;
-	vec.iov_len = 10;
-	memset(&msg, 0, sizeof(struct msghdr));
-	msg.msg_iov = &vec;
-	msg.msg_iovlen = 1;
-	msg.msg_control = cbuf;
-	msg.msg_controllen = sizeof(cbuf);
-	cmsg = CMSG_FIRSTHDR(&msg);
-	cmsg->cmsg_level = SOL_TLS;
-	/* test sending non-record types. */
-	cmsg->cmsg_type = TLS_SET_RECORD_TYPE;
-	cmsg->cmsg_len = CMSG_LEN(cmsg_len);
-	*CMSG_DATA(cmsg) = record_type;
-	msg.msg_controllen = cmsg->cmsg_len;
+	if (self->notls)
+		SKIP(return, "no TLS support");
 
-	EXPECT_EQ(sendmsg(self->fd, &msg, 0), send_len);
+	EXPECT_EQ(tls_send_cmsg(self->fd, record_type, test_str, send_len, 0),
+		  send_len);
 	/* Should fail because we didn't provide a control message */
 	EXPECT_EQ(recv(self->cfd, buf, send_len, 0), -1);
 
-	vec.iov_base = buf;
-	EXPECT_EQ(recvmsg(self->cfd, &msg, MSG_WAITALL | MSG_PEEK), send_len);
-
-	cmsg = CMSG_FIRSTHDR(&msg);
-	EXPECT_NE(cmsg, NULL);
-	EXPECT_EQ(cmsg->cmsg_level, SOL_TLS);
-	EXPECT_EQ(cmsg->cmsg_type, TLS_GET_RECORD_TYPE);
-	record_type = *((unsigned char *)CMSG_DATA(cmsg));
-	EXPECT_EQ(record_type, 100);
+	EXPECT_EQ(tls_recv_cmsg(_metadata, self->cfd, record_type,
+				buf, sizeof(buf), MSG_WAITALL | MSG_PEEK),
+		  send_len);
 	EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
 
 	/* Recv the message again without MSG_PEEK */
-	record_type = 0;
 	memset(buf, 0, sizeof(buf));
 
-	EXPECT_EQ(recvmsg(self->cfd, &msg, MSG_WAITALL), send_len);
-	cmsg = CMSG_FIRSTHDR(&msg);
-	EXPECT_NE(cmsg, NULL);
-	EXPECT_EQ(cmsg->cmsg_level, SOL_TLS);
-	EXPECT_EQ(cmsg->cmsg_type, TLS_GET_RECORD_TYPE);
-	record_type = *((unsigned char *)CMSG_DATA(cmsg));
-	EXPECT_EQ(record_type, 100);
+	EXPECT_EQ(tls_recv_cmsg(_metadata, self->cfd, record_type,
+				buf, sizeof(buf), MSG_WAITALL),
+		  send_len);
 	EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
 }
 
@@ -1301,6 +1422,160 @@ TEST_F(tls, shutdown_reuse)
 	EXPECT_EQ(errno, EISCONN);
 }
 
+FIXTURE(tls_err)
+{
+	int fd, cfd;
+	int fd2, cfd2;
+	bool notls;
+};
+
+FIXTURE_VARIANT(tls_err)
+{
+	uint16_t tls_version;
+};
+
+FIXTURE_VARIANT_ADD(tls_err, 12_aes_gcm)
+{
+	.tls_version = TLS_1_2_VERSION,
+};
+
+FIXTURE_VARIANT_ADD(tls_err, 13_aes_gcm)
+{
+	.tls_version = TLS_1_3_VERSION,
+};
+
+FIXTURE_SETUP(tls_err)
+{
+	struct tls_crypto_info_keys tls12;
+	int ret;
+
+	tls_crypto_info_init(variant->tls_version, TLS_CIPHER_AES_GCM_128,
+			     &tls12);
+
+	ulp_sock_pair(_metadata, &self->fd, &self->cfd, &self->notls);
+	ulp_sock_pair(_metadata, &self->fd2, &self->cfd2, &self->notls);
+	if (self->notls)
+		return;
+
+	ret = setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len);
+	ASSERT_EQ(ret, 0);
+
+	ret = setsockopt(self->cfd2, SOL_TLS, TLS_RX, &tls12, tls12.len);
+	ASSERT_EQ(ret, 0);
+}
+
+FIXTURE_TEARDOWN(tls_err)
+{
+	close(self->fd);
+	close(self->cfd);
+	close(self->fd2);
+	close(self->cfd2);
+}
+
+TEST_F(tls_err, bad_rec)
+{
+	char buf[64];
+
+	if (self->notls)
+		SKIP(return, "no TLS support");
+
+	memset(buf, 0x55, sizeof(buf));
+	EXPECT_EQ(send(self->fd2, buf, sizeof(buf), 0), sizeof(buf));
+	EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), -1);
+	EXPECT_EQ(errno, EMSGSIZE);
+	EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), MSG_DONTWAIT), -1);
+	EXPECT_EQ(errno, EAGAIN);
+}
+
+TEST_F(tls_err, bad_auth)
+{
+	char buf[128];
+	int n;
+
+	if (self->notls)
+		SKIP(return, "no TLS support");
+
+	memrnd(buf, sizeof(buf) / 2);
+	EXPECT_EQ(send(self->fd, buf, sizeof(buf) / 2, 0), sizeof(buf) / 2);
+	n = recv(self->cfd, buf, sizeof(buf), 0);
+	EXPECT_GT(n, sizeof(buf) / 2);
+
+	buf[n - 1]++;
+
+	EXPECT_EQ(send(self->fd2, buf, n, 0), n);
+	EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), -1);
+	EXPECT_EQ(errno, EBADMSG);
+	EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), -1);
+	EXPECT_EQ(errno, EBADMSG);
+}
+
+TEST_F(tls_err, bad_in_large_read)
+{
+	char txt[3][64];
+	char cip[3][128];
+	char buf[3 * 128];
+	int i, n;
+
+	if (self->notls)
+		SKIP(return, "no TLS support");
+
+	/* Put 3 records in the sockets */
+	for (i = 0; i < 3; i++) {
+		memrnd(txt[i], sizeof(txt[i]));
+		EXPECT_EQ(send(self->fd, txt[i], sizeof(txt[i]), 0),
+			  sizeof(txt[i]));
+		n = recv(self->cfd, cip[i], sizeof(cip[i]), 0);
+		EXPECT_GT(n, sizeof(txt[i]));
+		/* Break the third message */
+		if (i == 2)
+			cip[2][n - 1]++;
+		EXPECT_EQ(send(self->fd2, cip[i], n, 0), n);
+	}
+
+	/* We should be able to receive the first two messages */
+	EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), sizeof(txt[0]) * 2);
+	EXPECT_EQ(memcmp(buf, txt[0], sizeof(txt[0])), 0);
+	EXPECT_EQ(memcmp(buf + sizeof(txt[0]), txt[1], sizeof(txt[1])), 0);
+	/* Third mesasge is bad */
+	EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), -1);
+	EXPECT_EQ(errno, EBADMSG);
+	EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), -1);
+	EXPECT_EQ(errno, EBADMSG);
+}
+
+TEST_F(tls_err, bad_cmsg)
+{
+	char *test_str = "test_read";
+	int send_len = 10;
+	char cip[128];
+	char buf[128];
+	char txt[64];
+	int n;
+
+	if (self->notls)
+		SKIP(return, "no TLS support");
+
+	/* Queue up one data record */
+	memrnd(txt, sizeof(txt));
+	EXPECT_EQ(send(self->fd, txt, sizeof(txt), 0), sizeof(txt));
+	n = recv(self->cfd, cip, sizeof(cip), 0);
+	EXPECT_GT(n, sizeof(txt));
+	EXPECT_EQ(send(self->fd2, cip, n, 0), n);
+
+	EXPECT_EQ(tls_send_cmsg(self->fd, 100, test_str, send_len, 0), 10);
+	n = recv(self->cfd, cip, sizeof(cip), 0);
+	cip[n - 1]++; /* Break it */
+	EXPECT_GT(n, send_len);
+	EXPECT_EQ(send(self->fd2, cip, n, 0), n);
+
+	EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), sizeof(txt));
+	EXPECT_EQ(memcmp(buf, txt, sizeof(txt)), 0);
+	EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), -1);
+	EXPECT_EQ(errno, EBADMSG);
+	EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), -1);
+	EXPECT_EQ(errno, EBADMSG);
+}
+
 TEST(non_established) {
 	struct tls12_crypto_info_aes_gcm_256 tls12;
 	struct sockaddr_in addr;
@@ -1355,64 +1630,82 @@ TEST(non_established) {
 
 TEST(keysizes) {
 	struct tls12_crypto_info_aes_gcm_256 tls12;
-	struct sockaddr_in addr;
-	int sfd, ret, fd, cfd;
-	socklen_t len;
+	int ret, fd, cfd;
 	bool notls;
 
-	notls = false;
-	len = sizeof(addr);
-
 	memset(&tls12, 0, sizeof(tls12));
 	tls12.info.version = TLS_1_2_VERSION;
 	tls12.info.cipher_type = TLS_CIPHER_AES_GCM_256;
 
-	addr.sin_family = AF_INET;
-	addr.sin_addr.s_addr = htonl(INADDR_ANY);
-	addr.sin_port = 0;
+	ulp_sock_pair(_metadata, &fd, &cfd, &notls);
 
-	fd = socket(AF_INET, SOCK_STREAM, 0);
-	sfd = socket(AF_INET, SOCK_STREAM, 0);
+	if (!notls) {
+		ret = setsockopt(fd, SOL_TLS, TLS_TX, &tls12,
+				 sizeof(tls12));
+		EXPECT_EQ(ret, 0);
+
+		ret = setsockopt(cfd, SOL_TLS, TLS_RX, &tls12,
+				 sizeof(tls12));
+		EXPECT_EQ(ret, 0);
+	}
+
+	close(fd);
+	close(cfd);
+}
+
+TEST(tls_v6ops) {
+	struct tls_crypto_info_keys tls12;
+	struct sockaddr_in6 addr, addr2;
+	int sfd, ret, fd;
+	socklen_t len, len2;
+
+	tls_crypto_info_init(TLS_1_2_VERSION, TLS_CIPHER_AES_GCM_128, &tls12);
+
+	addr.sin6_family = AF_INET6;
+	addr.sin6_addr = in6addr_any;
+	addr.sin6_port = 0;
+
+	fd = socket(AF_INET6, SOCK_STREAM, 0);
+	sfd = socket(AF_INET6, SOCK_STREAM, 0);
 
 	ret = bind(sfd, &addr, sizeof(addr));
 	ASSERT_EQ(ret, 0);
 	ret = listen(sfd, 10);
 	ASSERT_EQ(ret, 0);
 
+	len = sizeof(addr);
 	ret = getsockname(sfd, &addr, &len);
 	ASSERT_EQ(ret, 0);
 
 	ret = connect(fd, &addr, sizeof(addr));
 	ASSERT_EQ(ret, 0);
 
+	len = sizeof(addr);
+	ret = getsockname(fd, &addr, &len);
+	ASSERT_EQ(ret, 0);
+
 	ret = setsockopt(fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls"));
-	if (ret != 0) {
-		notls = true;
-		printf("Failure setting TCP_ULP, testing without tls\n");
+	if (ret) {
+		ASSERT_EQ(errno, ENOENT);
+		SKIP(return, "no TLS support");
 	}
+	ASSERT_EQ(ret, 0);
 
-	if (!notls) {
-		ret = setsockopt(fd, SOL_TLS, TLS_TX, &tls12,
-				 sizeof(tls12));
-		EXPECT_EQ(ret, 0);
-	}
+	ret = setsockopt(fd, SOL_TLS, TLS_TX, &tls12, tls12.len);
+	ASSERT_EQ(ret, 0);
 
-	cfd = accept(sfd, &addr, &len);
-	ASSERT_GE(cfd, 0);
+	ret = setsockopt(fd, SOL_TLS, TLS_RX, &tls12, tls12.len);
+	ASSERT_EQ(ret, 0);
 
-	if (!notls) {
-		ret = setsockopt(cfd, IPPROTO_TCP, TCP_ULP, "tls",
-				 sizeof("tls"));
-		EXPECT_EQ(ret, 0);
+	len2 = sizeof(addr2);
+	ret = getsockname(fd, &addr2, &len2);
+	ASSERT_EQ(ret, 0);
 
-		ret = setsockopt(cfd, SOL_TLS, TLS_RX, &tls12,
-				 sizeof(tls12));
-		EXPECT_EQ(ret, 0);
-	}
+	EXPECT_EQ(len2, len);
+	EXPECT_EQ(memcmp(&addr, &addr2, len), 0);
 
-	close(sfd);
 	close(fd);
-	close(cfd);
+	close(sfd);
 }
 
 TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/net/toeplitz.c b/tools/testing/selftests/net/toeplitz.c
index 710ac956bdb3..c5489341cfb8 100644
--- a/tools/testing/selftests/net/toeplitz.c
+++ b/tools/testing/selftests/net/toeplitz.c
@@ -498,7 +498,7 @@ static void parse_opts(int argc, char **argv)
 	bool have_toeplitz = false;
 	int index, c;
 
-	while ((c = getopt_long(argc, argv, "46C:d:i:k:r:stT:u:v", long_options, &index)) != -1) {
+	while ((c = getopt_long(argc, argv, "46C:d:i:k:r:stT:uv", long_options, &index)) != -1) {
 		switch (c) {
 		case '4':
 			cfg_family = AF_INET;
diff --git a/tools/testing/selftests/net/udpgro_fwd.sh b/tools/testing/selftests/net/udpgro_fwd.sh
index 7f26591f236b..6f05e06f6761 100755
--- a/tools/testing/selftests/net/udpgro_fwd.sh
+++ b/tools/testing/selftests/net/udpgro_fwd.sh
@@ -132,7 +132,7 @@ run_test() {
 	local rcv=`ip netns exec $NS_DST $ipt"-save" -c | grep 'dport 8000' | \
 							  sed -e 's/\[//' -e 's/:.*//'`
 	if [ $rcv != $pkts ]; then
-		echo " fail - received $rvs packets, expected $pkts"
+		echo " fail - received $rcv packets, expected $pkts"
 		ret=1
 		return
 	fi
@@ -185,6 +185,7 @@ for family in 4 6; do
 	IPT=iptables
 	SUFFIX=24
 	VXDEV=vxlan
+	PING=ping
 
 	if [ $family = 6 ]; then
 		BM_NET=$BM_NET_V6
@@ -192,6 +193,8 @@ for family in 4 6; do
 		SUFFIX="64 nodad"
 		VXDEV=vxlan6
 		IPT=ip6tables
+		# Use ping6 on systems where ping doesn't handle IPv6
+		ping -w 1 -c 1 ::1 > /dev/null 2>&1 || PING="ping6"
 	fi
 
 	echo "IPv$family"
@@ -237,7 +240,7 @@ for family in 4 6; do
 
 	# load arp cache before running the test to reduce the amount of
 	# stray traffic on top of the UDP tunnel
-	ip netns exec $NS_SRC ping -q -c 1 $OL_NET$DST_NAT >/dev/null
+	ip netns exec $NS_SRC $PING -q -c 1 $OL_NET$DST_NAT >/dev/null
 	run_test "GRO fwd over UDP tunnel" $OL_NET$DST_NAT 1 1 $OL_NET$DST
 	cleanup
 
diff --git a/tools/testing/selftests/net/udpgso.c b/tools/testing/selftests/net/udpgso.c
index c66da6ffd6d8..7badaf215de2 100644
--- a/tools/testing/selftests/net/udpgso.c
+++ b/tools/testing/selftests/net/udpgso.c
@@ -156,13 +156,13 @@ struct testcase testcases_v4[] = {
 	},
 	{
 		/* send max number of min sized segments */
-		.tlen = UDP_MAX_SEGMENTS - CONST_HDRLEN_V4,
+		.tlen = UDP_MAX_SEGMENTS,
 		.gso_len = 1,
-		.r_num_mss = UDP_MAX_SEGMENTS - CONST_HDRLEN_V4,
+		.r_num_mss = UDP_MAX_SEGMENTS,
 	},
 	{
 		/* send max number + 1 of min sized segments: fail */
-		.tlen = UDP_MAX_SEGMENTS - CONST_HDRLEN_V4 + 1,
+		.tlen = UDP_MAX_SEGMENTS + 1,
 		.gso_len = 1,
 		.tfail = true,
 	},
@@ -259,13 +259,13 @@ struct testcase testcases_v6[] = {
 	},
 	{
 		/* send max number of min sized segments */
-		.tlen = UDP_MAX_SEGMENTS - CONST_HDRLEN_V6,
+		.tlen = UDP_MAX_SEGMENTS,
 		.gso_len = 1,
-		.r_num_mss = UDP_MAX_SEGMENTS - CONST_HDRLEN_V6,
+		.r_num_mss = UDP_MAX_SEGMENTS,
 	},
 	{
 		/* send max number + 1 of min sized segments: fail */
-		.tlen = UDP_MAX_SEGMENTS - CONST_HDRLEN_V6 + 1,
+		.tlen = UDP_MAX_SEGMENTS + 1,
 		.gso_len = 1,
 		.tfail = true,
 	},
diff --git a/tools/testing/selftests/net/udpgso_bench_tx.c b/tools/testing/selftests/net/udpgso_bench_tx.c
index 17512a43885e..f1fdaa270291 100644
--- a/tools/testing/selftests/net/udpgso_bench_tx.c
+++ b/tools/testing/selftests/net/udpgso_bench_tx.c
@@ -419,6 +419,7 @@ static void usage(const char *filepath)
 
 static void parse_opts(int argc, char **argv)
 {
+	const char *bind_addr = NULL;
 	int max_len, hdrlen;
 	int c;
 
@@ -446,7 +447,7 @@ static void parse_opts(int argc, char **argv)
 			cfg_cpu = strtol(optarg, NULL, 0);
 			break;
 		case 'D':
-			setup_sockaddr(cfg_family, optarg, &cfg_dst_addr);
+			bind_addr = optarg;
 			break;
 		case 'l':
 			cfg_runtime_ms = strtoul(optarg, NULL, 10) * 1000;
@@ -492,6 +493,11 @@ static void parse_opts(int argc, char **argv)
 		}
 	}
 
+	if (!bind_addr)
+		bind_addr = cfg_family == PF_INET6 ? "::" : "0.0.0.0";
+
+	setup_sockaddr(cfg_family, bind_addr, &cfg_dst_addr);
+
 	if (optind != argc)
 		usage(argv[0]);
 
diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile
index 8748199ac109..ffca314897c4 100644
--- a/tools/testing/selftests/netfilter/Makefile
+++ b/tools/testing/selftests/netfilter/Makefile
@@ -5,7 +5,8 @@ TEST_PROGS := nft_trans_stress.sh nft_fib.sh nft_nat.sh bridge_brouter.sh \
 	conntrack_icmp_related.sh nft_flowtable.sh ipvs.sh \
 	nft_concat_range.sh nft_conntrack_helper.sh \
 	nft_queue.sh nft_meta.sh nf_nat_edemux.sh \
-	ipip-conntrack-mtu.sh conntrack_tcp_unreplied.sh
+	ipip-conntrack-mtu.sh conntrack_tcp_unreplied.sh \
+	conntrack_vrf.sh
 
 LDLIBS = -lmnl
 TEST_GEN_FILES =  nf-queue
diff --git a/tools/testing/selftests/netfilter/conntrack_vrf.sh b/tools/testing/selftests/netfilter/conntrack_vrf.sh
new file mode 100755
index 000000000000..8b5ea9234588
--- /dev/null
+++ b/tools/testing/selftests/netfilter/conntrack_vrf.sh
@@ -0,0 +1,241 @@
+#!/bin/sh
+
+# This script demonstrates interaction of conntrack and vrf.
+# The vrf driver calls the netfilter hooks again, with oif/iif
+# pointing at the VRF device.
+#
+# For ingress, this means first iteration has iifname of lower/real
+# device.  In this script, thats veth0.
+# Second iteration is iifname set to vrf device, tvrf in this script.
+#
+# For egress, this is reversed: first iteration has the vrf device,
+# second iteration is done with the lower/real/veth0 device.
+#
+# test_ct_zone_in demonstrates unexpected change of nftables
+# behavior # caused by commit 09e856d54bda5f28 "vrf: Reset skb conntrack
+# connection on VRF rcv"
+#
+# It was possible to assign conntrack zone to a packet (or mark it for
+# `notracking`) in the prerouting chain before conntrack, based on real iif.
+#
+# After the change, the zone assignment is lost and the zone is assigned based
+# on the VRF master interface (in case such a rule exists).
+# assignment is lost. Instead, assignment based on the `iif` matching
+# Thus it is impossible to distinguish packets based on the original
+# interface.
+#
+# test_masquerade_vrf and test_masquerade_veth0 demonstrate the problem
+# that was supposed to be fixed by the commit mentioned above to make sure
+# that any fix to test case 1 won't break masquerade again.
+
+ksft_skip=4
+
+IP0=172.30.30.1
+IP1=172.30.30.2
+PFXL=30
+ret=0
+
+sfx=$(mktemp -u "XXXXXXXX")
+ns0="ns0-$sfx"
+ns1="ns1-$sfx"
+
+cleanup()
+{
+	ip netns pids $ns0 | xargs kill 2>/dev/null
+	ip netns pids $ns1 | xargs kill 2>/dev/null
+
+	ip netns del $ns0 $ns1
+}
+
+nft --version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not run test without nft tool"
+	exit $ksft_skip
+fi
+
+ip -Version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not run test without ip tool"
+	exit $ksft_skip
+fi
+
+ip netns add "$ns0"
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not create net namespace $ns0"
+	exit $ksft_skip
+fi
+ip netns add "$ns1"
+
+trap cleanup EXIT
+
+ip netns exec $ns0 sysctl -q -w net.ipv4.conf.default.rp_filter=0
+ip netns exec $ns0 sysctl -q -w net.ipv4.conf.all.rp_filter=0
+ip netns exec $ns0 sysctl -q -w net.ipv4.conf.all.rp_filter=0
+
+ip link add veth0 netns "$ns0" type veth peer name veth0 netns "$ns1" > /dev/null 2>&1
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not add veth device"
+	exit $ksft_skip
+fi
+
+ip -net $ns0 li add tvrf type vrf table 9876
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not add vrf device"
+	exit $ksft_skip
+fi
+
+ip -net $ns0 li set lo up
+
+ip -net $ns0 li set veth0 master tvrf
+ip -net $ns0 li set tvrf up
+ip -net $ns0 li set veth0 up
+ip -net $ns1 li set veth0 up
+
+ip -net $ns0 addr add $IP0/$PFXL dev veth0
+ip -net $ns1 addr add $IP1/$PFXL dev veth0
+
+ip netns exec $ns1 iperf3 -s > /dev/null 2>&1&
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not start iperf3"
+	exit $ksft_skip
+fi
+
+# test vrf ingress handling.
+# The incoming connection should be placed in conntrack zone 1,
+# as decided by the first iteration of the ruleset.
+test_ct_zone_in()
+{
+ip netns exec $ns0 nft -f - <<EOF
+table testct {
+	chain rawpre {
+		type filter hook prerouting priority raw;
+
+		iif { veth0, tvrf } counter meta nftrace set 1
+		iif veth0 counter ct zone set 1 counter return
+		iif tvrf counter ct zone set 2 counter return
+		ip protocol icmp counter
+		notrack counter
+	}
+
+	chain rawout {
+		type filter hook output priority raw;
+
+		oif veth0 counter ct zone set 1 counter return
+		oif tvrf counter ct zone set 2 counter return
+		notrack counter
+	}
+}
+EOF
+	ip netns exec $ns1 ping -W 1 -c 1 -I veth0 $IP0 > /dev/null
+
+	# should be in zone 1, not zone 2
+	count=$(ip netns exec $ns0 conntrack -L -s $IP1 -d $IP0 -p icmp --zone 1 2>/dev/null | wc -l)
+	if [ $count -eq 1 ]; then
+		echo "PASS: entry found in conntrack zone 1"
+	else
+		echo "FAIL: entry not found in conntrack zone 1"
+		count=$(ip netns exec $ns0 conntrack -L -s $IP1 -d $IP0 -p icmp --zone 2 2> /dev/null | wc -l)
+		if [ $count -eq 1 ]; then
+			echo "FAIL: entry found in zone 2 instead"
+		else
+			echo "FAIL: entry not in zone 1 or 2, dumping table"
+			ip netns exec $ns0 conntrack -L
+			ip netns exec $ns0 nft list ruleset
+		fi
+	fi
+}
+
+# add masq rule that gets evaluated w. outif set to vrf device.
+# This tests the first iteration of the packet through conntrack,
+# oifname is the vrf device.
+test_masquerade_vrf()
+{
+	local qdisc=$1
+
+	if [ "$qdisc" != "default" ]; then
+		tc -net $ns0 qdisc add dev tvrf root $qdisc
+	fi
+
+	ip netns exec $ns0 conntrack -F 2>/dev/null
+
+ip netns exec $ns0 nft -f - <<EOF
+flush ruleset
+table ip nat {
+	chain rawout {
+		type filter hook output priority raw;
+
+		oif tvrf ct state untracked counter
+	}
+	chain postrouting2 {
+		type filter hook postrouting priority mangle;
+
+		oif tvrf ct state untracked counter
+	}
+	chain postrouting {
+		type nat hook postrouting priority 0;
+		# NB: masquerade should always be combined with 'oif(name) bla',
+		# lack of this is intentional here, we want to exercise double-snat.
+		ip saddr 172.30.30.0/30 counter masquerade random
+	}
+}
+EOF
+	ip netns exec $ns0 ip vrf exec tvrf iperf3 -t 1 -c $IP1 >/dev/null
+	if [ $? -ne 0 ]; then
+		echo "FAIL: iperf3 connect failure with masquerade + sport rewrite on vrf device"
+		ret=1
+		return
+	fi
+
+	# must also check that nat table was evaluated on second (lower device) iteration.
+	ip netns exec $ns0 nft list table ip nat |grep -q 'counter packets 2' &&
+	ip netns exec $ns0 nft list table ip nat |grep -q 'untracked counter packets [1-9]'
+	if [ $? -eq 0 ]; then
+		echo "PASS: iperf3 connect with masquerade + sport rewrite on vrf device ($qdisc qdisc)"
+	else
+		echo "FAIL: vrf rules have unexpected counter value"
+		ret=1
+	fi
+
+	if [ "$qdisc" != "default" ]; then
+		tc -net $ns0 qdisc del dev tvrf root
+	fi
+}
+
+# add masq rule that gets evaluated w. outif set to veth device.
+# This tests the 2nd iteration of the packet through conntrack,
+# oifname is the lower device (veth0 in this case).
+test_masquerade_veth()
+{
+	ip netns exec $ns0 conntrack -F 2>/dev/null
+ip netns exec $ns0 nft -f - <<EOF
+flush ruleset
+table ip nat {
+	chain postrouting {
+		type nat hook postrouting priority 0;
+		meta oif veth0 ip saddr 172.30.30.0/30 counter masquerade random
+	}
+}
+EOF
+	ip netns exec $ns0 ip vrf exec tvrf iperf3 -t 1 -c $IP1 > /dev/null
+	if [ $? -ne 0 ]; then
+		echo "FAIL: iperf3 connect failure with masquerade + sport rewrite on veth device"
+		ret=1
+		return
+	fi
+
+	# must also check that nat table was evaluated on second (lower device) iteration.
+	ip netns exec $ns0 nft list table ip nat |grep -q 'counter packets 2'
+	if [ $? -eq 0 ]; then
+		echo "PASS: iperf3 connect with masquerade + sport rewrite on veth device"
+	else
+		echo "FAIL: vrf masq rule has unexpected counter value"
+		ret=1
+	fi
+}
+
+test_ct_zone_in
+test_masquerade_vrf "default"
+test_masquerade_vrf "pfifo"
+test_masquerade_veth
+
+exit $ret
diff --git a/tools/testing/selftests/netfilter/nft_concat_range.sh b/tools/testing/selftests/netfilter/nft_concat_range.sh
index 5a4938d6dcf2..ed61f6cab60f 100755
--- a/tools/testing/selftests/netfilter/nft_concat_range.sh
+++ b/tools/testing/selftests/netfilter/nft_concat_range.sh
@@ -23,8 +23,8 @@ TESTS="reported_issues correctness concurrency timeout"
 
 # Set types, defined by TYPE_ variables below
 TYPES="net_port port_net net6_port port_proto net6_port_mac net6_port_mac_proto
-       net_port_net net_mac net_mac_icmp net6_mac_icmp net6_port_net6_port
-       net_port_mac_proto_net"
+       net_port_net net_mac mac_net net_mac_icmp net6_mac_icmp
+       net6_port_net6_port net_port_mac_proto_net"
 
 # Reported bugs, also described by TYPE_ variables below
 BUGS="flush_remove_add"
@@ -277,6 +277,23 @@ perf_entries	1000
 perf_proto	ipv4
 "
 
+TYPE_mac_net="
+display		mac,net
+type_spec	ether_addr . ipv4_addr
+chain_spec	ether saddr . ip saddr
+dst		 
+src		mac addr4
+start		1
+count		5
+src_delta	2000
+tools		sendip nc bash
+proto		udp
+
+race_repeat	0
+
+perf_duration	0
+"
+
 TYPE_net_mac_icmp="
 display		net,mac - ICMP
 type_spec	ipv4_addr . ether_addr
@@ -984,7 +1001,8 @@ format() {
 		fi
 	done
 	for f in ${src}; do
-		__expr="${__expr} . "
+		[ "${__expr}" != "{ " ] && __expr="${__expr} . "
+
 		__start="$(eval format_"${f}" "${srcstart}")"
 		__end="$(eval format_"${f}" "${srcend}")"
 
diff --git a/tools/testing/selftests/netfilter/nft_nat.sh b/tools/testing/selftests/netfilter/nft_nat.sh
index da1c1e4b6c86..d88867d2fed7 100755
--- a/tools/testing/selftests/netfilter/nft_nat.sh
+++ b/tools/testing/selftests/netfilter/nft_nat.sh
@@ -759,19 +759,21 @@ test_port_shadow()
 	local result=""
 	local logmsg=""
 
-	echo ROUTER | ip netns exec "$ns0" nc -w 5 -u -l -p 1405 >/dev/null 2>&1 &
-	nc_r=$!
+	# make shadow entry, from client (ns2), going to (ns1), port 41404, sport 1405.
+	echo "fake-entry" | ip netns exec "$ns2" timeout 1 socat -u STDIN UDP:"$daddrc":41404,sourceport=1405
 
-	echo CLIENT | ip netns exec "$ns2" nc -w 5 -u -l -p 1405 >/dev/null 2>&1 &
-	nc_c=$!
+	echo ROUTER | ip netns exec "$ns0" timeout 5 socat -u STDIN UDP4-LISTEN:1405 &
+	sc_r=$!
 
-	# make shadow entry, from client (ns2), going to (ns1), port 41404, sport 1405.
-	echo "fake-entry" | ip netns exec "$ns2" nc -w 1 -p 1405 -u "$daddrc" 41404 > /dev/null
+	echo CLIENT | ip netns exec "$ns2" timeout 5 socat -u STDIN UDP4-LISTEN:1405,reuseport &
+	sc_c=$!
+
+	sleep 0.3
 
 	# ns1 tries to connect to ns0:1405.  With default settings this should connect
 	# to client, it matches the conntrack entry created above.
 
-	result=$(echo "" | ip netns exec "$ns1" nc -w 1 -p 41404 -u "$daddrs" 1405)
+	result=$(echo "data" | ip netns exec "$ns1" timeout 1 socat - UDP:"$daddrs":1405,sourceport=41404)
 
 	if [ "$result" = "$expect" ] ;then
 		echo "PASS: portshadow test $test: got reply from ${expect}${logmsg}"
@@ -780,7 +782,7 @@ test_port_shadow()
 		ret=1
 	fi
 
-	kill $nc_r $nc_c 2>/dev/null
+	kill $sc_r $sc_c 2>/dev/null
 
 	# flush udp entries for next test round, if any
 	ip netns exec "$ns0" conntrack -F >/dev/null 2>&1
@@ -816,11 +818,10 @@ table $family raw {
 	chain prerouting {
 		type filter hook prerouting priority -300; policy accept;
 		meta iif veth0 udp dport 1405 notrack
-		udp dport 1405 notrack
 	}
 	chain output {
 		type filter hook output priority -300; policy accept;
-		udp sport 1405 notrack
+		meta oif veth0 udp sport 1405 notrack
 	}
 }
 EOF
@@ -851,6 +852,18 @@ test_port_shadowing()
 {
 	local family="ip"
 
+	conntrack -h >/dev/null 2>&1
+	if [ $? -ne 0 ];then
+		echo "SKIP: Could not run nat port shadowing test without conntrack tool"
+		return
+	fi
+
+	socat -h > /dev/null 2>&1
+	if [ $? -ne 0 ];then
+		echo "SKIP: Could not run nat port shadowing test without socat tool"
+		return
+	fi
+
 	ip netns exec "$ns0" sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null
 	ip netns exec "$ns0" sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null
 
diff --git a/tools/testing/selftests/netfilter/nft_queue.sh b/tools/testing/selftests/netfilter/nft_queue.sh
index 3d202b90b33d..7d27f1f3bc01 100755
--- a/tools/testing/selftests/netfilter/nft_queue.sh
+++ b/tools/testing/selftests/netfilter/nft_queue.sh
@@ -16,6 +16,10 @@ timeout=4
 
 cleanup()
 {
+	ip netns pids ${ns1} | xargs kill 2>/dev/null
+	ip netns pids ${ns2} | xargs kill 2>/dev/null
+	ip netns pids ${nsrouter} | xargs kill 2>/dev/null
+
 	ip netns del ${ns1}
 	ip netns del ${ns2}
 	ip netns del ${nsrouter}
@@ -332,6 +336,55 @@ EOF
 	echo "PASS: tcp via loopback and re-queueing"
 }
 
+test_icmp_vrf() {
+	ip -net $ns1 link add tvrf type vrf table 9876
+	if [ $? -ne 0 ];then
+		echo "SKIP: Could not add vrf device"
+		return
+	fi
+
+	ip -net $ns1 li set eth0 master tvrf
+	ip -net $ns1 li set tvrf up
+
+	ip -net $ns1 route add 10.0.2.0/24 via 10.0.1.1 dev eth0 table 9876
+ip netns exec ${ns1} nft -f /dev/stdin <<EOF
+flush ruleset
+table inet filter {
+	chain output {
+		type filter hook output priority 0; policy accept;
+		meta oifname "tvrf" icmp type echo-request counter queue num 1
+		meta oifname "eth0" icmp type echo-request counter queue num 1
+	}
+	chain post {
+		type filter hook postrouting priority 0; policy accept;
+		meta oifname "tvrf" icmp type echo-request counter queue num 1
+		meta oifname "eth0" icmp type echo-request counter queue num 1
+	}
+}
+EOF
+	ip netns exec ${ns1} ./nf-queue -q 1 -t $timeout &
+	local nfqpid=$!
+
+	sleep 1
+	ip netns exec ${ns1} ip vrf exec tvrf ping -c 1 10.0.2.99 > /dev/null
+
+	for n in output post; do
+		for d in tvrf eth0; do
+			ip netns exec ${ns1} nft list chain inet filter $n | grep -q "oifname \"$d\" icmp type echo-request counter packets 1"
+			if [ $? -ne 0 ] ; then
+				echo "FAIL: chain $n: icmp packet counter mismatch for device $d" 1>&2
+				ip netns exec ${ns1} nft list ruleset
+				ret=1
+				return
+			fi
+		done
+	done
+
+	wait $nfqpid
+	[ $? -eq 0 ] && echo "PASS: icmp+nfqueue via vrf"
+	wait 2>/dev/null
+}
+
 ip netns exec ${nsrouter} sysctl net.ipv6.conf.all.forwarding=1 > /dev/null
 ip netns exec ${nsrouter} sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null
 ip netns exec ${nsrouter} sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null
@@ -372,5 +425,6 @@ test_queue 20
 test_tcp_forward
 test_tcp_localhost
 test_tcp_localhost_requeue
+test_icmp_vrf
 
 exit $ret
diff --git a/tools/testing/selftests/netfilter/nft_zones_many.sh b/tools/testing/selftests/netfilter/nft_zones_many.sh
index ac646376eb01..04633119b29a 100755
--- a/tools/testing/selftests/netfilter/nft_zones_many.sh
+++ b/tools/testing/selftests/netfilter/nft_zones_many.sh
@@ -18,11 +18,17 @@ cleanup()
 	ip netns del $ns
 }
 
-ip netns add $ns
-if [ $? -ne 0 ];then
-	echo "SKIP: Could not create net namespace $gw"
-	exit $ksft_skip
-fi
+checktool (){
+	if ! $1 > /dev/null 2>&1; then
+		echo "SKIP: Could not $2"
+		exit $ksft_skip
+	fi
+}
+
+checktool "nft --version" "run test without nft tool"
+checktool "ip -Version" "run test without ip tool"
+checktool "socat -V" "run test without socat tool"
+checktool "ip netns add $ns" "create net namespace"
 
 trap cleanup EXIT
 
@@ -71,7 +77,8 @@ EOF
 		local start=$(date +%s%3N)
 		i=$((i + 10000))
 		j=$((j + 1))
-		dd if=/dev/zero of=/dev/stdout bs=8k count=10000 2>/dev/null | ip netns exec "$ns" nc -w 1 -q 1 -u -p 12345 127.0.0.1 12345 > /dev/null
+		# nft rule in output places each packet in a different zone.
+		dd if=/dev/zero of=/dev/stdout bs=8k count=10000 2>/dev/null | ip netns exec "$ns" socat STDIN UDP:127.0.0.1:12345,sourceport=12345
 		if [ $? -ne 0 ] ;then
 			ret=1
 			break
diff --git a/tools/testing/selftests/tc-testing/config b/tools/testing/selftests/tc-testing/config
index b71828df5a6d..a3239d5e40c7 100644
--- a/tools/testing/selftests/tc-testing/config
+++ b/tools/testing/selftests/tc-testing/config
@@ -60,6 +60,8 @@ CONFIG_NET_IFE_SKBTCINDEX=m
 CONFIG_NET_SCH_FIFO=y
 CONFIG_NET_SCH_ETS=m
 CONFIG_NET_SCH_RED=m
+CONFIG_NET_SCH_FQ_PIE=m
+CONFIG_NETDEVSIM=m
 
 #
 ## Network testing
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json b/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json
index 503982b8f295..91832400ddbd 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json
@@ -68,7 +68,7 @@
         "cmdUnderTest": "$TC action add action bpf object-file $EBPFDIR/action.o section action-ok index 667",
         "expExitCode": "0",
         "verifyCmd": "$TC action get action bpf index 667",
-        "matchPattern": "action order [0-9]*: bpf action.o:\\[action-ok\\] id [0-9]* tag [0-9a-f]{16}( jited)? default-action pipe.*index 667 ref",
+        "matchPattern": "action order [0-9]*: bpf action.o:\\[action-ok\\] id [0-9].* tag [0-9a-f]{16}( jited)? default-action pipe.*index 667 ref",
         "matchCount": "1",
         "teardown": [
             "$TC action flush action bpf"
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/mq.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/mq.json
index 88a20c781e49..c6046096d9db 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/mq.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/mq.json
@@ -15,7 +15,7 @@
 	    "cmdUnderTest": "$TC qdisc add dev $ETH root handle 1: mq",
 	    "expExitCode": "0",
 	    "verifyCmd": "$TC qdisc show dev $ETH",
-	    "matchPattern": "qdisc pfifo_fast 0: parent 1:[1-4] bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1",
+	    "matchPattern": "qdisc [a-zA-Z0-9_]+ 0: parent 1:[1-4]",
 	    "matchCount": "4",
 	    "teardown": [
 		    "echo \"1\" > /sys/bus/netdevsim/del_device"
@@ -37,7 +37,7 @@
 	    "cmdUnderTest": "$TC qdisc add dev $ETH root handle 1: mq",
 	    "expExitCode": "0",
 	    "verifyCmd": "$TC qdisc show dev $ETH",
-	    "matchPattern": "qdisc pfifo_fast 0: parent 1:[1-9,a-f][0-9,a-f]{0,2} bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1",
+	    "matchPattern": "qdisc [a-zA-Z0-9_]+ 0: parent 1:[1-9,a-f][0-9,a-f]{0,2}",
 	    "matchCount": "256",
 	    "teardown": [
 		    "echo \"1\" > /sys/bus/netdevsim/del_device"
@@ -60,7 +60,7 @@
 	    "cmdUnderTest": "$TC qdisc add dev $ETH root handle 1: mq",
 	    "expExitCode": "2",
 	    "verifyCmd": "$TC qdisc show dev $ETH",
-	    "matchPattern": "qdisc pfifo_fast 0: parent 1:[1-4] bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1",
+	    "matchPattern": "qdisc [a-zA-Z0-9_]+ 0: parent 1:[1-4]",
 	    "matchCount": "4",
 	    "teardown": [
 		    "echo \"1\" > /sys/bus/netdevsim/del_device"
@@ -82,7 +82,7 @@
 	    "cmdUnderTest": "$TC qdisc del dev $ETH root handle 1: mq",
 	    "expExitCode": "2",
 	    "verifyCmd": "$TC qdisc show dev $ETH",
-	    "matchPattern": "qdisc pfifo_fast 0: parent 1:[1-4] bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1",
+	    "matchPattern": "qdisc [a-zA-Z0-9_]+ 0: parent 1:[1-4]",
 	    "matchCount": "0",
 	    "teardown": [
 		    "echo \"1\" > /sys/bus/netdevsim/del_device"
@@ -106,7 +106,7 @@
 	    "cmdUnderTest": "$TC qdisc del dev $ETH root handle 1: mq",
 	    "expExitCode": "2",
 	    "verifyCmd": "$TC qdisc show dev $ETH",
-	    "matchPattern": "qdisc pfifo_fast 0: parent 1:[1-4] bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1",
+	    "matchPattern": "qdisc [a-zA-Z0-9_]+ 0: parent 1:[1-4]",
 	    "matchCount": "0",
 	    "teardown": [
 		    "echo \"1\" > /sys/bus/netdevsim/del_device"
@@ -128,7 +128,7 @@
 	    "cmdUnderTest": "$TC qdisc add dev $ETH root handle 1: mq",
 	    "expExitCode": "2",
 	    "verifyCmd": "$TC qdisc show dev $ETH",
-	    "matchPattern": "qdisc pfifo_fast 0: parent 1:[1-4] bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1",
+	    "matchPattern": "qdisc [a-zA-Z0-9_]+ 0: parent 1:[1-4]",
 	    "matchCount": "0",
 	    "teardown": [
 		    "echo \"1\" > /sys/bus/netdevsim/del_device"
diff --git a/tools/testing/selftests/tc-testing/tdc.py b/tools/testing/selftests/tc-testing/tdc.py
index a3e43189d940..ee22e3447ec7 100755
--- a/tools/testing/selftests/tc-testing/tdc.py
+++ b/tools/testing/selftests/tc-testing/tdc.py
@@ -716,6 +716,7 @@ def set_operation_mode(pm, parser, args, remaining):
         list_test_cases(alltests)
         exit(0)
 
+    exit_code = 0 # KSFT_PASS
     if len(alltests):
         req_plugins = pm.get_required_plugins(alltests)
         try:
@@ -724,6 +725,8 @@ def set_operation_mode(pm, parser, args, remaining):
             print('The following plugins were not found:')
             print('{}'.format(pde.missing_pg))
         catresults = test_runner(pm, args, alltests)
+        if catresults.count_failures() != 0:
+            exit_code = 1 # KSFT_FAIL
         if args.format == 'none':
             print('Test results output suppression requested\n')
         else:
@@ -748,6 +751,8 @@ def set_operation_mode(pm, parser, args, remaining):
                         gid=int(os.getenv('SUDO_GID')))
     else:
         print('No tests found\n')
+        exit_code = 4 # KSFT_SKIP
+    exit(exit_code)
 
 def main():
     """
@@ -767,8 +772,5 @@ def main():
 
     set_operation_mode(pm, parser, args, remaining)
 
-    exit(0)
-
-
 if __name__ == "__main__":
     main()
diff --git a/tools/testing/selftests/tc-testing/tdc.sh b/tools/testing/selftests/tc-testing/tdc.sh
index 7fe38c76db44..afb0cd86fa3d 100755
--- a/tools/testing/selftests/tc-testing/tdc.sh
+++ b/tools/testing/selftests/tc-testing/tdc.sh
@@ -1,5 +1,6 @@
 #!/bin/sh
 # SPDX-License-Identifier: GPL-2.0
 
+modprobe netdevsim
 ./tdc.py -c actions --nobuildebpf
 ./tdc.py -c qdisc
diff --git a/tools/testing/selftests/wireguard/netns.sh b/tools/testing/selftests/wireguard/netns.sh
index ebc4ee0fe179..8a9461aa0878 100755
--- a/tools/testing/selftests/wireguard/netns.sh
+++ b/tools/testing/selftests/wireguard/netns.sh
@@ -276,7 +276,11 @@ n0 ping -W 1 -c 1 192.168.241.2
 n1 wg set wg0 peer "$pub2" endpoint 192.168.241.2:7
 ip2 link del wg0
 ip2 link del wg1
-! n0 ping -W 1 -c 10 -f 192.168.241.2 || false # Should not crash kernel
+read _ _ tx_bytes_before < <(n0 wg show wg1 transfer)
+! n0 ping -W 1 -c 10 -f 192.168.241.2 || false
+sleep 1
+read _ _ tx_bytes_after < <(n0 wg show wg1 transfer)
+(( tx_bytes_after - tx_bytes_before < 70000 ))
 
 ip0 link del wg1
 ip1 link del wg0
@@ -609,6 +613,28 @@ ip0 link set wg0 up
 kill $ncat_pid
 ip0 link del wg0
 
+# Ensure that dst_cache references don't outlive netns lifetime
+ip1 link add dev wg0 type wireguard
+ip2 link add dev wg0 type wireguard
+configure_peers
+ip1 link add veth1 type veth peer name veth2
+ip1 link set veth2 netns $netns2
+ip1 addr add fd00:aa::1/64 dev veth1
+ip2 addr add fd00:aa::2/64 dev veth2
+ip1 link set veth1 up
+ip2 link set veth2 up
+waitiface $netns1 veth1
+waitiface $netns2 veth2
+ip1 -6 route add default dev veth1 via fd00:aa::2
+ip2 -6 route add default dev veth2 via fd00:aa::1
+n1 wg set wg0 peer "$pub2" endpoint [fd00:aa::2]:2
+n2 wg set wg0 peer "$pub1" endpoint [fd00:aa::1]:1
+n1 ping6 -c 1 fd00::2
+pp ip netns delete $netns1
+pp ip netns delete $netns2
+pp ip netns add $netns1
+pp ip netns add $netns2
+
 # Ensure there aren't circular reference loops
 ip1 link add wg1 type wireguard
 ip2 link add wg2 type wireguard
@@ -627,7 +653,7 @@ while read -t 0.1 -r line 2>/dev/null || [[ $? -ne 142 ]]; do
 done < /dev/kmsg
 alldeleted=1
 for object in "${!objects[@]}"; do
-	if [[ ${objects["$object"]} != *createddestroyed ]]; then
+	if [[ ${objects["$object"]} != *createddestroyed && ${objects["$object"]} != *createdcreateddestroyeddestroyed ]]; then
 		echo "Error: $object: merely ${objects["$object"]}" >&3
 		alldeleted=0
 	fi
diff --git a/tools/testing/selftests/wireguard/qemu/debug.config b/tools/testing/selftests/wireguard/qemu/debug.config
index fe07d97df9fa..2b321b8a96cf 100644
--- a/tools/testing/selftests/wireguard/qemu/debug.config
+++ b/tools/testing/selftests/wireguard/qemu/debug.config
@@ -47,7 +47,7 @@ CONFIG_DEBUG_ATOMIC_SLEEP=y
 CONFIG_TRACE_IRQFLAGS=y
 CONFIG_DEBUG_BUGVERBOSE=y
 CONFIG_DEBUG_LIST=y
-CONFIG_DEBUG_PI_LIST=y
+CONFIG_DEBUG_PLIST=y
 CONFIG_PROVE_RCU=y
 CONFIG_SPARSE_RCU_POINTER=y
 CONFIG_RCU_CPU_STALL_TIMEOUT=21
diff --git a/tools/testing/selftests/wireguard/qemu/kernel.config b/tools/testing/selftests/wireguard/qemu/kernel.config
index 74db83a0aedd..a9b5a520a1d2 100644
--- a/tools/testing/selftests/wireguard/qemu/kernel.config
+++ b/tools/testing/selftests/wireguard/qemu/kernel.config
@@ -66,6 +66,7 @@ CONFIG_PROC_SYSCTL=y
 CONFIG_SYSFS=y
 CONFIG_TMPFS=y
 CONFIG_CONSOLE_LOGLEVEL_DEFAULT=15
+CONFIG_LOG_BUF_SHIFT=18
 CONFIG_PRINTK_TIME=y
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_LEGACY_VSYSCALL_NONE=y
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 3f6d450355f0..72c4e6b39389 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1531,11 +1531,10 @@ static struct kvm_memslots *kvm_dup_memslots(struct kvm_memslots *old,
 
 static int kvm_set_memslot(struct kvm *kvm,
 			   const struct kvm_userspace_memory_region *mem,
-			   struct kvm_memory_slot *old,
 			   struct kvm_memory_slot *new, int as_id,
 			   enum kvm_mr_change change)
 {
-	struct kvm_memory_slot *slot;
+	struct kvm_memory_slot *slot, old;
 	struct kvm_memslots *slots;
 	int r;
 
@@ -1566,7 +1565,7 @@ static int kvm_set_memslot(struct kvm *kvm,
 		 * Note, the INVALID flag needs to be in the appropriate entry
 		 * in the freshly allocated memslots, not in @old or @new.
 		 */
-		slot = id_to_memslot(slots, old->id);
+		slot = id_to_memslot(slots, new->id);
 		slot->flags |= KVM_MEMSLOT_INVALID;
 
 		/*
@@ -1597,6 +1596,26 @@ static int kvm_set_memslot(struct kvm *kvm,
 		kvm_copy_memslots(slots, __kvm_memslots(kvm, as_id));
 	}
 
+	/*
+	 * Make a full copy of the old memslot, the pointer will become stale
+	 * when the memslots are re-sorted by update_memslots(), and the old
+	 * memslot needs to be referenced after calling update_memslots(), e.g.
+	 * to free its resources and for arch specific behavior.  This needs to
+	 * happen *after* (re)acquiring slots_arch_lock.
+	 */
+	slot = id_to_memslot(slots, new->id);
+	if (slot) {
+		old = *slot;
+	} else {
+		WARN_ON_ONCE(change != KVM_MR_CREATE);
+		memset(&old, 0, sizeof(old));
+		old.id = new->id;
+		old.as_id = as_id;
+	}
+
+	/* Copy the arch-specific data, again after (re)acquiring slots_arch_lock. */
+	memcpy(&new->arch, &old.arch, sizeof(old.arch));
+
 	r = kvm_arch_prepare_memory_region(kvm, new, mem, change);
 	if (r)
 		goto out_slots;
@@ -1604,14 +1623,18 @@ static int kvm_set_memslot(struct kvm *kvm,
 	update_memslots(slots, new, change);
 	slots = install_new_memslots(kvm, as_id, slots);
 
-	kvm_arch_commit_memory_region(kvm, mem, old, new, change);
+	kvm_arch_commit_memory_region(kvm, mem, &old, new, change);
+
+	/* Free the old memslot's metadata.  Note, this is the full copy!!! */
+	if (change == KVM_MR_DELETE)
+		kvm_free_memslot(kvm, &old);
 
 	kvfree(slots);
 	return 0;
 
 out_slots:
 	if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) {
-		slot = id_to_memslot(slots, old->id);
+		slot = id_to_memslot(slots, new->id);
 		slot->flags &= ~KVM_MEMSLOT_INVALID;
 		slots = install_new_memslots(kvm, as_id, slots);
 	} else {
@@ -1626,7 +1649,6 @@ static int kvm_delete_memslot(struct kvm *kvm,
 			      struct kvm_memory_slot *old, int as_id)
 {
 	struct kvm_memory_slot new;
-	int r;
 
 	if (!old->npages)
 		return -EINVAL;
@@ -1639,12 +1661,7 @@ static int kvm_delete_memslot(struct kvm *kvm,
 	 */
 	new.as_id = as_id;
 
-	r = kvm_set_memslot(kvm, mem, old, &new, as_id, KVM_MR_DELETE);
-	if (r)
-		return r;
-
-	kvm_free_memslot(kvm, old);
-	return 0;
+	return kvm_set_memslot(kvm, mem, &new, as_id, KVM_MR_DELETE);
 }
 
 /*
@@ -1672,7 +1689,8 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	id = (u16)mem->slot;
 
 	/* General sanity checks */
-	if (mem->memory_size & (PAGE_SIZE - 1))
+	if ((mem->memory_size & (PAGE_SIZE - 1)) ||
+	    (mem->memory_size != (unsigned long)mem->memory_size))
 		return -EINVAL;
 	if (mem->guest_phys_addr & (PAGE_SIZE - 1))
 		return -EINVAL;
@@ -1718,7 +1736,6 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	if (!old.npages) {
 		change = KVM_MR_CREATE;
 		new.dirty_bitmap = NULL;
-		memset(&new.arch, 0, sizeof(new.arch));
 	} else { /* Modify an existing slot. */
 		if ((new.userspace_addr != old.userspace_addr) ||
 		    (new.npages != old.npages) ||
@@ -1732,9 +1749,8 @@ int __kvm_set_memory_region(struct kvm *kvm,
 		else /* Nothing to change. */
 			return 0;
 
-		/* Copy dirty_bitmap and arch from the current memslot. */
+		/* Copy dirty_bitmap from the current memslot. */
 		new.dirty_bitmap = old.dirty_bitmap;
-		memcpy(&new.arch, &old.arch, sizeof(new.arch));
 	}
 
 	if ((change == KVM_MR_CREATE) || (change == KVM_MR_MOVE)) {
@@ -1760,7 +1776,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 			bitmap_set(new.dirty_bitmap, 0, new.npages);
 	}
 
-	r = kvm_set_memslot(kvm, mem, &old, &new, as_id, change);
+	r = kvm_set_memslot(kvm, mem, &new, as_id, change);
 	if (r)
 		goto out_bitmap;
 
@@ -2548,72 +2564,36 @@ struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn)
 }
 EXPORT_SYMBOL_GPL(gfn_to_page);
 
-void kvm_release_pfn(kvm_pfn_t pfn, bool dirty, struct gfn_to_pfn_cache *cache)
+void kvm_release_pfn(kvm_pfn_t pfn, bool dirty)
 {
 	if (pfn == 0)
 		return;
 
-	if (cache)
-		cache->pfn = cache->gfn = 0;
-
 	if (dirty)
 		kvm_release_pfn_dirty(pfn);
 	else
 		kvm_release_pfn_clean(pfn);
 }
 
-static void kvm_cache_gfn_to_pfn(struct kvm_memory_slot *slot, gfn_t gfn,
-				 struct gfn_to_pfn_cache *cache, u64 gen)
-{
-	kvm_release_pfn(cache->pfn, cache->dirty, cache);
-
-	cache->pfn = gfn_to_pfn_memslot(slot, gfn);
-	cache->gfn = gfn;
-	cache->dirty = false;
-	cache->generation = gen;
-}
-
-static int __kvm_map_gfn(struct kvm_memslots *slots, gfn_t gfn,
-			 struct kvm_host_map *map,
-			 struct gfn_to_pfn_cache *cache,
-			 bool atomic)
+int kvm_vcpu_map(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map)
 {
 	kvm_pfn_t pfn;
 	void *hva = NULL;
 	struct page *page = KVM_UNMAPPED_PAGE;
-	struct kvm_memory_slot *slot = __gfn_to_memslot(slots, gfn);
-	u64 gen = slots->generation;
 
 	if (!map)
 		return -EINVAL;
 
-	if (cache) {
-		if (!cache->pfn || cache->gfn != gfn ||
-			cache->generation != gen) {
-			if (atomic)
-				return -EAGAIN;
-			kvm_cache_gfn_to_pfn(slot, gfn, cache, gen);
-		}
-		pfn = cache->pfn;
-	} else {
-		if (atomic)
-			return -EAGAIN;
-		pfn = gfn_to_pfn_memslot(slot, gfn);
-	}
+	pfn = gfn_to_pfn(vcpu->kvm, gfn);
 	if (is_error_noslot_pfn(pfn))
 		return -EINVAL;
 
 	if (pfn_valid(pfn)) {
 		page = pfn_to_page(pfn);
-		if (atomic)
-			hva = kmap_atomic(page);
-		else
-			hva = kmap(page);
+		hva = kmap(page);
 #ifdef CONFIG_HAS_IOMEM
-	} else if (!atomic) {
-		hva = memremap(pfn_to_hpa(pfn), PAGE_SIZE, MEMREMAP_WB);
 	} else {
-		return -EINVAL;
+		hva = memremap(pfn_to_hpa(pfn), PAGE_SIZE, MEMREMAP_WB);
 #endif
 	}
 
@@ -2627,27 +2607,9 @@ static int __kvm_map_gfn(struct kvm_memslots *slots, gfn_t gfn,
 
 	return 0;
 }
-
-int kvm_map_gfn(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map,
-		struct gfn_to_pfn_cache *cache, bool atomic)
-{
-	return __kvm_map_gfn(kvm_memslots(vcpu->kvm), gfn, map,
-			cache, atomic);
-}
-EXPORT_SYMBOL_GPL(kvm_map_gfn);
-
-int kvm_vcpu_map(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map)
-{
-	return __kvm_map_gfn(kvm_vcpu_memslots(vcpu), gfn, map,
-		NULL, false);
-}
 EXPORT_SYMBOL_GPL(kvm_vcpu_map);
 
-static void __kvm_unmap_gfn(struct kvm *kvm,
-			struct kvm_memory_slot *memslot,
-			struct kvm_host_map *map,
-			struct gfn_to_pfn_cache *cache,
-			bool dirty, bool atomic)
+void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty)
 {
 	if (!map)
 		return;
@@ -2655,45 +2617,21 @@ static void __kvm_unmap_gfn(struct kvm *kvm,
 	if (!map->hva)
 		return;
 
-	if (map->page != KVM_UNMAPPED_PAGE) {
-		if (atomic)
-			kunmap_atomic(map->hva);
-		else
-			kunmap(map->page);
-	}
+	if (map->page != KVM_UNMAPPED_PAGE)
+		kunmap(map->page);
 #ifdef CONFIG_HAS_IOMEM
-	else if (!atomic)
-		memunmap(map->hva);
 	else
-		WARN_ONCE(1, "Unexpected unmapping in atomic context");
+		memunmap(map->hva);
 #endif
 
 	if (dirty)
-		mark_page_dirty_in_slot(kvm, memslot, map->gfn);
+		kvm_vcpu_mark_page_dirty(vcpu, map->gfn);
 
-	if (cache)
-		cache->dirty |= dirty;
-	else
-		kvm_release_pfn(map->pfn, dirty, NULL);
+	kvm_release_pfn(map->pfn, dirty);
 
 	map->hva = NULL;
 	map->page = NULL;
 }
-
-int kvm_unmap_gfn(struct kvm_vcpu *vcpu, struct kvm_host_map *map, 
-		  struct gfn_to_pfn_cache *cache, bool dirty, bool atomic)
-{
-	__kvm_unmap_gfn(vcpu->kvm, gfn_to_memslot(vcpu->kvm, map->gfn), map,
-			cache, dirty, atomic);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(kvm_unmap_gfn);
-
-void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty)
-{
-	__kvm_unmap_gfn(vcpu->kvm, kvm_vcpu_gfn_to_memslot(vcpu, map->gfn),
-			map, NULL, dirty, false);
-}
 EXPORT_SYMBOL_GPL(kvm_vcpu_unmap);
 
 struct page *kvm_vcpu_gfn_to_page(struct kvm_vcpu *vcpu, gfn_t gfn)
@@ -2993,7 +2931,8 @@ int kvm_write_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 	int r;
 	gpa_t gpa = ghc->gpa + offset;
 
-	BUG_ON(len + offset > ghc->len);
+	if (WARN_ON_ONCE(len + offset > ghc->len))
+		return -EINVAL;
 
 	if (slots->generation != ghc->generation) {
 		if (__kvm_gfn_to_hva_cache_init(slots, ghc, ghc->gpa, ghc->len))
@@ -3030,7 +2969,8 @@ int kvm_read_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 	int r;
 	gpa_t gpa = ghc->gpa + offset;
 
-	BUG_ON(len + offset > ghc->len);
+	if (WARN_ON_ONCE(len + offset > ghc->len))
+		return -EINVAL;
 
 	if (slots->generation != ghc->generation) {
 		if (__kvm_gfn_to_hva_cache_init(slots, ghc, ghc->gpa, ghc->len))
@@ -3747,7 +3687,7 @@ static long kvm_vcpu_ioctl(struct file *filp,
 	struct kvm_fpu *fpu = NULL;
 	struct kvm_sregs *kvm_sregs = NULL;
 
-	if (vcpu->kvm->mm != current->mm || vcpu->kvm->vm_bugged)
+	if (vcpu->kvm->mm != current->mm || vcpu->kvm->vm_dead)
 		return -EIO;
 
 	if (unlikely(_IOC_TYPE(ioctl) != KVMIO))
@@ -3957,7 +3897,7 @@ static long kvm_vcpu_compat_ioctl(struct file *filp,
 	void __user *argp = compat_ptr(arg);
 	int r;
 
-	if (vcpu->kvm->mm != current->mm || vcpu->kvm->vm_bugged)
+	if (vcpu->kvm->mm != current->mm || vcpu->kvm->vm_dead)
 		return -EIO;
 
 	switch (ioctl) {
@@ -4023,7 +3963,7 @@ static long kvm_device_ioctl(struct file *filp, unsigned int ioctl,
 {
 	struct kvm_device *dev = filp->private_data;
 
-	if (dev->kvm->mm != current->mm || dev->kvm->vm_bugged)
+	if (dev->kvm->mm != current->mm || dev->kvm->vm_dead)
 		return -EIO;
 
 	switch (ioctl) {
@@ -4345,7 +4285,7 @@ static long kvm_vm_ioctl(struct file *filp,
 	void __user *argp = (void __user *)arg;
 	int r;
 
-	if (kvm->mm != current->mm || kvm->vm_bugged)
+	if (kvm->mm != current->mm || kvm->vm_dead)
 		return -EIO;
 	switch (ioctl) {
 	case KVM_CREATE_VCPU:
@@ -4556,7 +4496,7 @@ static long kvm_vm_compat_ioctl(struct file *filp,
 	struct kvm *kvm = filp->private_data;
 	int r;
 
-	if (kvm->mm != current->mm || kvm->vm_bugged)
+	if (kvm->mm != current->mm || kvm->vm_dead)
 		return -EIO;
 	switch (ioctl) {
 #ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT